diff options
168 files changed, 98946 insertions, 0 deletions
diff --git a/plugins/Pcre16/docs/AUTHORS b/plugins/Pcre16/docs/AUTHORS new file mode 100644 index 0000000000..5eee1af4c6 --- /dev/null +++ b/plugins/Pcre16/docs/AUTHORS @@ -0,0 +1,45 @@ +THE MAIN PCRE LIBRARY +--------------------- + +Written by: Philip Hazel +Email local part: ph10 +Email domain: cam.ac.uk + +University of Cambridge Computing Service, +Cambridge, England. + +Copyright (c) 1997-2014 University of Cambridge +All rights reserved + + +PCRE JUST-IN-TIME COMPILATION SUPPORT +------------------------------------- + +Written by: Zoltan Herczeg +Email local part: hzmester +Emain domain: freemail.hu + +Copyright(c) 2010-2014 Zoltan Herczeg +All rights reserved. + + +STACK-LESS JUST-IN-TIME COMPILER +-------------------------------- + +Written by: Zoltan Herczeg +Email local part: hzmester +Emain domain: freemail.hu + +Copyright(c) 2009-2014 Zoltan Herczeg +All rights reserved. + + +THE C++ WRAPPER LIBRARY +----------------------- + +Written by: Google Inc. + +Copyright (c) 2007-2012 Google Inc +All rights reserved + +#### diff --git a/plugins/Pcre16/docs/COPYING b/plugins/Pcre16/docs/COPYING new file mode 100644 index 0000000000..58eed01b61 --- /dev/null +++ b/plugins/Pcre16/docs/COPYING @@ -0,0 +1,5 @@ +PCRE LICENCE + +Please see the file LICENCE in the PCRE distribution for licensing details. + +End diff --git a/plugins/Pcre16/docs/ChangeLog b/plugins/Pcre16/docs/ChangeLog new file mode 100644 index 0000000000..7801ef8411 --- /dev/null +++ b/plugins/Pcre16/docs/ChangeLog @@ -0,0 +1,5477 @@ +ChangeLog for PCRE +------------------ + +Version 8.35 04-April-2014 +-------------------------- + +1. A new flag is set, when property checks are present in an XCLASS. + When this flag is not set, PCRE can perform certain optimizations + such as studying these XCLASS-es. + +2. The auto-possessification of character sets were improved: a normal + and an extended character set can be compared now. Furthermore + the JIT compiler optimizes more character set checks. + +3. Got rid of some compiler warnings for potentially uninitialized variables + that show up only when compiled with -O2. + +4. A pattern such as (?=ab\K) that uses \K in an assertion can set the start + of a match later then the end of the match. The pcretest program was not + handling the case sensibly - it was outputting from the start to the next + binary zero. It now reports this situation in a message, and outputs the + text from the end to the start. + +5. Fast forward search is improved in JIT. Instead of the first three + characters, any three characters with fixed position can be searched. + Search order: first, last, middle. + +6. Improve character range checks in JIT. Characters are read by an inprecise + function now, which returns with an unknown value if the character code is + above a certain treshold (e.g: 256). The only limitation is that the value + must be bigger than the treshold as well. This function is useful, when + the characters above the treshold are handled in the same way. + +7. The macros whose names start with RAWUCHAR are placeholders for a future + mode in which only the bottom 21 bits of 32-bit data items are used. To + make this more memorable for those maintaining the code, the names have + been changed to start with UCHAR21, and an extensive comment has been added + to their definition. + +8. Add missing (new) files sljitNativeTILEGX.c and sljitNativeTILEGX-encoder.c + to the export list in Makefile.am (they were accidentally omitted from the + 8.34 tarball). + +9. The informational output from pcretest used the phrase "starting byte set" + which is inappropriate for the 16-bit and 32-bit libraries. As the output + for "first char" and "need char" really means "non-UTF-char", I've changed + "byte" to "char", and slightly reworded the output. The documentation about + these values has also been (I hope) clarified. + +10. Another JIT related optimization: use table jumps for selecting the correct + backtracking path, when more than four alternatives are present inside a + bracket. + +11. Empty match is not possible, when the minimum length is greater than zero, + and there is no \K in the pattern. JIT should avoid empty match checks in + such cases. + +12. In a caseless character class with UCP support, when a character with more + than one alternative case was not the first character of a range, not all + the alternative cases were added to the class. For example, s and \x{17f} + are both alternative cases for S: the class [RST] was handled correctly, + but [R-T] was not. + +13. The configure.ac file always checked for pthread support when JIT was + enabled. This is not used in Windows, so I have put this test inside a + check for the presence of windows.h (which was already tested for). + +14. Improve pattern prefix search by a simplified Boyer-Moore algorithm in JIT. + The algorithm provides a way to skip certain starting offsets, and usually + faster than linear prefix searches. + +15. Change 13 for 8.20 updated RunTest to check for the 'fr' locale as well + as for 'fr_FR' and 'french'. For some reason, however, it then used the + Windows-specific input and output files, which have 'french' screwed in. + So this could never have worked. One of the problems with locales is that + they aren't always the same. I have now updated RunTest so that it checks + the output of the locale test (test 3) against three different output + files, and it allows the test to pass if any one of them matches. With luck + this should make the test pass on some versions of Solaris where it was + failing. Because of the uncertainty, the script did not used to stop if + test 3 failed; it now does. If further versions of a French locale ever + come to light, they can now easily be added. + +16. If --with-pcregrep-bufsize was given a non-integer value such as "50K", + there was a message during ./configure, but it did not stop. This now + provokes an error. The invalid example in README has been corrected. + If a value less than the minimum is given, the minimum value has always + been used, but now a warning is given. + +17. If --enable-bsr-anycrlf was set, the special 16/32-bit test failed. This + was a bug in the test system, which is now fixed. Also, the list of various + configurations that are tested for each release did not have one with both + 16/32 bits and --enable-bar-anycrlf. It now does. + +18. pcretest was missing "-C bsr" for displaying the \R default setting. + +19. Little endian PowerPC systems are supported now by the JIT compiler. + +20. The fast forward newline mechanism could enter to an infinite loop on + certain invalid UTF-8 input. Although we don't support these cases + this issue can be fixed by a performance optimization. + +21. Change 33 of 8.34 is not sufficient to ensure stack safety because it does + not take account if existing stack usage. There is now a new global + variable called pcre_stack_guard that can be set to point to an external + function to check stack availability. It is called at the start of + processing every parenthesized group. + +22. A typo in the code meant that in ungreedy mode the max/min qualifier + behaved like a min-possessive qualifier, and, for example, /a{1,3}b/U did + not match "ab". + +23. When UTF was disabled, the JIT program reported some incorrect compile + errors. These messages are silenced now. + +24. Experimental support for ARM-64 and MIPS-64 has been added to the JIT + compiler. + +25. Change all the temporary files used in RunGrepTest to be different to those + used by RunTest so that the tests can be run simultaneously, for example by + "make -j check". + + +Version 8.34 15-December-2013 +----------------------------- + +1. Add pcre[16|32]_jit_free_unused_memory to forcibly free unused JIT + executable memory. Patch inspired by Carsten Klein. + +2. ./configure --enable-coverage defined SUPPORT_GCOV in config.h, although + this macro is never tested and has no effect, because the work to support + coverage involves only compiling and linking options and special targets in + the Makefile. The comment in config.h implied that defining the macro would + enable coverage support, which is totally false. There was also support for + setting this macro in the CMake files (my fault, I just copied it from + configure). SUPPORT_GCOV has now been removed. + +3. Make a small performance improvement in strlen16() and strlen32() in + pcretest. + +4. Change 36 for 8.33 left some unreachable statements in pcre_exec.c, + detected by the Solaris compiler (gcc doesn't seem to be able to diagnose + these cases). There was also one in pcretest.c. + +5. Cleaned up a "may be uninitialized" compiler warning in pcre_exec.c. + +6. In UTF mode, the code for checking whether a group could match an empty + string (which is used for indefinitely repeated groups to allow for + breaking an infinite loop) was broken when the group contained a repeated + negated single-character class with a character that occupied more than one + data item and had a minimum repetition of zero (for example, [^\x{100}]* in + UTF-8 mode). The effect was undefined: the group might or might not be + deemed as matching an empty string, or the program might have crashed. + +7. The code for checking whether a group could match an empty string was not + recognizing that \h, \H, \v, \V, and \R must match a character. + +8. Implemented PCRE_INFO_MATCH_EMPTY, which yields 1 if the pattern can match + an empty string. If it can, pcretest shows this in its information output. + +9. Fixed two related bugs that applied to Unicode extended grapheme clusters + that were repeated with a maximizing qualifier (e.g. \X* or \X{2,5}) when + matched by pcre_exec() without using JIT: + + (a) If the rest of the pattern did not match after a maximal run of + grapheme clusters, the code for backing up to try with fewer of them + did not always back up over a full grapheme when characters that do not + have the modifier quality were involved, e.g. Hangul syllables. + + (b) If the match point in a subject started with modifier character, and + there was no match, the code could incorrectly back up beyond the match + point, and potentially beyond the first character in the subject, + leading to a segfault or an incorrect match result. + +10. A conditional group with an assertion condition could lead to PCRE + recording an incorrect first data item for a match if no other first data + item was recorded. For example, the pattern (?(?=ab)ab) recorded "a" as a + first data item, and therefore matched "ca" after "c" instead of at the + start. + +11. Change 40 for 8.33 (allowing pcregrep to find empty strings) showed up a + bug that caused the command "echo a | ./pcregrep -M '|a'" to loop. + +12. The source of pcregrep now includes z/OS-specific code so that it can be + compiled for z/OS as part of the special z/OS distribution. + +13. Added the -T and -TM options to pcretest. + +14. The code in pcre_compile.c for creating the table of named capturing groups + has been refactored. Instead of creating the table dynamically during the + actual compiling pass, the information is remembered during the pre-compile + pass (on the stack unless there are more than 20 named groups, in which + case malloc() is used) and the whole table is created before the actual + compile happens. This has simplified the code (it is now nearly 150 lines + shorter) and prepared the way for better handling of references to groups + with duplicate names. + +15. A back reference to a named subpattern when there is more than one of the + same name now checks them in the order in which they appear in the pattern. + The first one that is set is used for the reference. Previously only the + first one was inspected. This change makes PCRE more compatible with Perl. + +16. Unicode character properties were updated from Unicode 6.3.0. + +17. The compile-time code for auto-possessification has been refactored, based + on a patch by Zoltan Herczeg. It now happens after instead of during + compilation. The code is cleaner, and more cases are handled. The option + PCRE_NO_AUTO_POSSESS is added for testing purposes, and the -O and /O + options in pcretest are provided to set it. It can also be set by + (*NO_AUTO_POSSESS) at the start of a pattern. + +18. The character VT has been added to the default ("C" locale) set of + characters that match \s and are generally treated as white space, + following this same change in Perl 5.18. There is now no difference between + "Perl space" and "POSIX space". Whether VT is treated as white space in + other locales depends on the locale. + +19. The code for checking named groups as conditions, either for being set or + for being recursed, has been refactored (this is related to 14 and 15 + above). Processing unduplicated named groups should now be as fast at + numerical groups, and processing duplicated groups should be faster than + before. + +20. Two patches to the CMake build system, by Alexander Barkov: + + (1) Replace the "source" command by "." in CMakeLists.txt because + "source" is a bash-ism. + + (2) Add missing HAVE_STDINT_H and HAVE_INTTYPES_H to config-cmake.h.in; + without these the CMake build does not work on Solaris. + +21. Perl has changed its handling of \8 and \9. If there is no previously + encountered capturing group of those numbers, they are treated as the + literal characters 8 and 9 instead of a binary zero followed by the + literals. PCRE now does the same. + +22. Following Perl, added \o{} to specify codepoints in octal, making it + possible to specify values greater than 0777 and also making them + unambiguous. + +23. Perl now gives an error for missing closing braces after \x{... instead of + treating the string as literal. PCRE now does the same. + +24. RunTest used to grumble if an inappropriate test was selected explicitly, + but just skip it when running all tests. This make it awkward to run ranges + of tests when one of them was inappropriate. Now it just skips any + inappropriate tests, as it always did when running all tests. + +25. If PCRE_AUTO_CALLOUT and PCRE_UCP were set for a pattern that contained + character types such as \d or \w, too many callouts were inserted, and the + data that they returned was rubbish. + +26. In UCP mode, \s was not matching two of the characters that Perl matches, + namely NEL (U+0085) and MONGOLIAN VOWEL SEPARATOR (U+180E), though they + were matched by \h. The code has now been refactored so that the lists of + the horizontal and vertical whitespace characters used for \h and \v (which + are defined only in one place) are now also used for \s. + +27. Add JIT support for the 64 bit TileGX architecture. + Patch by Jiong Wang (Tilera Corporation). + +28. Possessive quantifiers for classes (both explicit and automatically + generated) now use special opcodes instead of wrapping in ONCE brackets. + +29. Whereas an item such as A{4}+ ignored the possessivenes of the quantifier + (because it's meaningless), this was not happening when PCRE_CASELESS was + set. Not wrong, but inefficient. + +30. Updated perltest.pl to add /u (force Unicode mode) when /W (use Unicode + properties for \w, \d, etc) is present in a test regex. Otherwise if the + test contains no characters greater than 255, Perl doesn't realise it + should be using Unicode semantics. + +31. Upgraded the handling of the POSIX classes [:graph:], [:print:], and + [:punct:] when PCRE_UCP is set so as to include the same characters as Perl + does in Unicode mode. + +32. Added the "forbid" facility to pcretest so that putting tests into the + wrong test files can sometimes be quickly detected. + +33. There is now a limit (default 250) on the depth of nesting of parentheses. + This limit is imposed to control the amount of system stack used at compile + time. It can be changed at build time by --with-parens-nest-limit=xxx or + the equivalent in CMake. + +34. Character classes such as [A-\d] or [a-[:digit:]] now cause compile-time + errors. Perl warns for these when in warning mode, but PCRE has no facility + for giving warnings. + +35. Change 34 for 8.13 allowed quantifiers on assertions, because Perl does. + However, this was not working for (?!) because it is optimized to (*FAIL), + for which PCRE does not allow quantifiers. The optimization is now disabled + when a quantifier follows (?!). I can't see any use for this, but it makes + things uniform. + +36. Perl no longer allows group names to start with digits, so I have made this + change also in PCRE. It simplifies the code a bit. + +37. In extended mode, Perl ignores spaces before a + that indicates a + possessive quantifier. PCRE allowed a space before the quantifier, but not + before the possessive +. It now does. + +38. The use of \K (reset reported match start) within a repeated possessive + group such as (a\Kb)*+ was not working. + +40. Document that the same character tables must be used at compile time and + run time, and that the facility to pass tables to pcre_exec() and + pcre_dfa_exec() is for use only with saved/restored patterns. + +41. Applied Jeff Trawick's patch CMakeLists.txt, which "provides two new + features for Builds with MSVC: + + 1. Support pcre.rc and/or pcreposix.rc (as is already done for MinGW + builds). The .rc files can be used to set FileDescription and many other + attributes. + + 2. Add an option (-DINSTALL_MSVC_PDB) to enable installation of .pdb files. + This allows higher-level build scripts which want .pdb files to avoid + hard-coding the exact files needed." + +42. Added support for [[:<:]] and [[:>:]] as used in the BSD POSIX library to + mean "start of word" and "end of word", respectively, as a transition aid. + +43. A minimizing repeat of a class containing codepoints greater than 255 in + non-UTF 16-bit or 32-bit modes caused an internal error when PCRE was + compiled to use the heap for recursion. + +44. Got rid of some compiler warnings for unused variables when UTF but not UCP + is configured. + + +Version 8.33 28-May-2013 +------------------------ + +1. Added 'U' to some constants that are compared to unsigned integers, to + avoid compiler signed/unsigned warnings. Added (int) casts to unsigned + variables that are added to signed variables, to ensure the result is + signed and can be negated. + +2. Applied patch by Daniel Richard G for quashing MSVC warnings to the + CMake config files. + +3. Revise the creation of config.h.generic so that all boolean macros are + #undefined, whereas non-boolean macros are #ifndef/#endif-ed. This makes + overriding via -D on the command line possible. + +4. Changing the definition of the variable "op" in pcre_exec.c from pcre_uchar + to unsigned int is reported to make a quite noticeable speed difference in + a specific Windows environment. Testing on Linux did also appear to show + some benefit (and it is clearly not harmful). Also fixed the definition of + Xop which should be unsigned. + +5. Related to (4), changing the definition of the intermediate variable cc + in repeated character loops from pcre_uchar to pcre_uint32 also gave speed + improvements. + +6. Fix forward search in JIT when link size is 3 or greater. Also removed some + unnecessary spaces. + +7. Adjust autogen.sh and configure.ac to lose warnings given by automake 1.12 + and later. + +8. Fix two buffer over read issues in 16 and 32 bit modes. Affects JIT only. + +9. Optimizing fast_forward_start_bits in JIT. + +10. Adding support for callouts in JIT, and fixing some issues revealed + during this work. Namely: + + (a) Unoptimized capturing brackets incorrectly reset on backtrack. + + (b) Minimum length was not checked before the matching is started. + +11. The value of capture_last that is passed to callouts was incorrect in some + cases when there was a capture on one path that was subsequently abandoned + after a backtrack. Also, the capture_last value is now reset after a + recursion, since all captures are also reset in this case. + +12. The interpreter no longer returns the "too many substrings" error in the + case when an overflowing capture is in a branch that is subsequently + abandoned after a backtrack. + +13. In the pathological case when an offset vector of size 2 is used, pcretest + now prints out the matched string after a yield of 0 or 1. + +14. Inlining subpatterns in recursions, when certain conditions are fulfilled. + Only supported by the JIT compiler at the moment. + +15. JIT compiler now supports 32 bit Macs thanks to Lawrence Velazquez. + +16. Partial matches now set offsets[2] to the "bumpalong" value, that is, the + offset of the starting point of the matching process, provided the offsets + vector is large enough. + +17. The \A escape now records a lookbehind value of 1, though its execution + does not actually inspect the previous character. This is to ensure that, + in partial multi-segment matching, at least one character from the old + segment is retained when a new segment is processed. Otherwise, if there + are no lookbehinds in the pattern, \A might match incorrectly at the start + of a new segment. + +18. Added some #ifdef __VMS code into pcretest.c to help VMS implementations. + +19. Redefined some pcre_uchar variables in pcre_exec.c as pcre_uint32; this + gives some modest performance improvement in 8-bit mode. + +20. Added the PCRE-specific property \p{Xuc} for matching characters that can + be expressed in certain programming languages using Universal Character + Names. + +21. Unicode validation has been updated in the light of Unicode Corrigendum #9, + which points out that "non characters" are not "characters that may not + appear in Unicode strings" but rather "characters that are reserved for + internal use and have only local meaning". + +22. When a pattern was compiled with automatic callouts (PCRE_AUTO_CALLOUT) and + there was a conditional group that depended on an assertion, if the + assertion was false, the callout that immediately followed the alternation + in the condition was skipped when pcre_exec() was used for matching. + +23. Allow an explicit callout to be inserted before an assertion that is the + condition for a conditional group, for compatibility with automatic + callouts, which always insert a callout at this point. + +24. In 8.31, (*COMMIT) was confined to within a recursive subpattern. Perl also + confines (*SKIP) and (*PRUNE) in the same way, and this has now been done. + +25. (*PRUNE) is now supported by the JIT compiler. + +26. Fix infinite loop when /(?<=(*SKIP)ac)a/ is matched against aa. + +27. Fix the case where there are two or more SKIPs with arguments that may be + ignored. + +28. (*SKIP) is now supported by the JIT compiler. + +29. (*THEN) is now supported by the JIT compiler. + +30. Update RunTest with additional test selector options. + +31. The way PCRE handles backtracking verbs has been changed in two ways. + + (1) Previously, in something like (*COMMIT)(*SKIP), COMMIT would override + SKIP. Now, PCRE acts on whichever backtracking verb is reached first by + backtracking. In some cases this makes it more Perl-compatible, but Perl's + rather obscure rules do not always do the same thing. + + (2) Previously, backtracking verbs were confined within assertions. This is + no longer the case for positive assertions, except for (*ACCEPT). Again, + this sometimes improves Perl compatibility, and sometimes does not. + +32. A number of tests that were in test 2 because Perl did things differently + have been moved to test 1, because either Perl or PCRE has changed, and + these tests are now compatible. + +32. Backtracking control verbs are now handled in the same way in JIT and + interpreter. + +33. An opening parenthesis in a MARK/PRUNE/SKIP/THEN name in a pattern that + contained a forward subroutine reference caused a compile error. + +34. Auto-detect and optimize limited repetitions in JIT. + +35. Implement PCRE_NEVER_UTF to lock out the use of UTF, in particular, + blocking (*UTF) etc. + +36. In the interpreter, maximizing pattern repetitions for characters and + character types now use tail recursion, which reduces stack usage. + +37. The value of the max lookbehind was not correctly preserved if a compiled + and saved regex was reloaded on a host of different endianness. + +38. Implemented (*LIMIT_MATCH) and (*LIMIT_RECURSION). As part of the extension + of the compiled pattern block, expand the flags field from 16 to 32 bits + because it was almost full. + +39. Try madvise first before posix_madvise. + +40. Change 7 for PCRE 7.9 made it impossible for pcregrep to find empty lines + with a pattern such as ^$. It has taken 4 years for anybody to notice! The + original change locked out all matches of empty strings. This has been + changed so that one match of an empty string per line is recognized. + Subsequent searches on the same line (for colouring or for --only-matching, + for example) do not recognize empty strings. + +41. Applied a user patch to fix a number of spelling mistakes in comments. + +42. Data lines longer than 65536 caused pcretest to crash. + +43. Clarified the data type for length and startoffset arguments for pcre_exec + and pcre_dfa_exec in the function-specific man pages, where they were + explicitly stated to be in bytes, never having been updated. I also added + some clarification to the pcreapi man page. + +44. A call to pcre_dfa_exec() with an output vector size less than 2 caused + a segmentation fault. + + +Version 8.32 30-November-2012 +----------------------------- + +1. Improved JIT compiler optimizations for first character search and single + character iterators. + +2. Supporting IBM XL C compilers for PPC architectures in the JIT compiler. + Patch by Daniel Richard G. + +3. Single character iterator optimizations in the JIT compiler. + +4. Improved JIT compiler optimizations for character ranges. + +5. Rename the "leave" variable names to "quit" to improve WinCE compatibility. + Reported by Giuseppe D'Angelo. + +6. The PCRE_STARTLINE bit, indicating that a match can occur only at the start + of a line, was being set incorrectly in cases where .* appeared inside + atomic brackets at the start of a pattern, or where there was a subsequent + *PRUNE or *SKIP. + +7. Improved instruction cache flush for POWER/PowerPC. + Patch by Daniel Richard G. + +8. Fixed a number of issues in pcregrep, making it more compatible with GNU + grep: + + (a) There is now no limit to the number of patterns to be matched. + + (b) An error is given if a pattern is too long. + + (c) Multiple uses of --exclude, --exclude-dir, --include, and --include-dir + are now supported. + + (d) --exclude-from and --include-from (multiple use) have been added. + + (e) Exclusions and inclusions now apply to all files and directories, not + just to those obtained from scanning a directory recursively. + + (f) Multiple uses of -f and --file-list are now supported. + + (g) In a Windows environment, the default for -d has been changed from + "read" (the GNU grep default) to "skip", because otherwise the presence + of a directory in the file list provokes an error. + + (h) The documentation has been revised and clarified in places. + +9. Improve the matching speed of capturing brackets. + +10. Changed the meaning of \X so that it now matches a Unicode extended + grapheme cluster. + +11. Patch by Daniel Richard G to the autoconf files to add a macro for sorting + out POSIX threads when JIT support is configured. + +12. Added support for PCRE_STUDY_EXTRA_NEEDED. + +13. In the POSIX wrapper regcomp() function, setting re_nsub field in the preg + structure could go wrong in environments where size_t is not the same size + as int. + +14. Applied user-supplied patch to pcrecpp.cc to allow PCRE_NO_UTF8_CHECK to be + set. + +15. The EBCDIC support had decayed; later updates to the code had included + explicit references to (e.g.) \x0a instead of CHAR_LF. There has been a + general tidy up of EBCDIC-related issues, and the documentation was also + not quite right. There is now a test that can be run on ASCII systems to + check some of the EBCDIC-related things (but is it not a full test). + +16. The new PCRE_STUDY_EXTRA_NEEDED option is now used by pcregrep, resulting + in a small tidy to the code. + +17. Fix JIT tests when UTF is disabled and both 8 and 16 bit mode are enabled. + +18. If the --only-matching (-o) option in pcregrep is specified multiple + times, each one causes appropriate output. For example, -o1 -o2 outputs the + substrings matched by the 1st and 2nd capturing parentheses. A separating + string can be specified by --om-separator (default empty). + +19. Improving the first n character searches. + +20. Turn case lists for horizontal and vertical white space into macros so that + they are defined only once. + +21. This set of changes together give more compatible Unicode case-folding + behaviour for characters that have more than one other case when UCP + support is available. + + (a) The Unicode property table now has offsets into a new table of sets of + three or more characters that are case-equivalent. The MultiStage2.py + script that generates these tables (the pcre_ucd.c file) now scans + CaseFolding.txt instead of UnicodeData.txt for character case + information. + + (b) The code for adding characters or ranges of characters to a character + class has been abstracted into a generalized function that also handles + case-independence. In UTF-mode with UCP support, this uses the new data + to handle characters with more than one other case. + + (c) A bug that is fixed as a result of (b) is that codepoints less than 256 + whose other case is greater than 256 are now correctly matched + caselessly. Previously, the high codepoint matched the low one, but not + vice versa. + + (d) The processing of \h, \H, \v, and \ in character classes now makes use + of the new class addition function, using character lists defined as + macros alongside the case definitions of 20 above. + + (e) Caseless back references now work with characters that have more than + one other case. + + (f) General caseless matching of characters with more than one other case + is supported. + +22. Unicode character properties were updated from Unicode 6.2.0 + +23. Improved CMake support under Windows. Patch by Daniel Richard G. + +24. Add support for 32-bit character strings, and UTF-32 + +25. Major JIT compiler update (code refactoring and bugfixing). + Experimental Sparc 32 support is added. + +26. Applied a modified version of Daniel Richard G's patch to create + pcre.h.generic and config.h.generic by "make" instead of in the + PrepareRelease script. + +27. Added a definition for CHAR_NULL (helpful for the z/OS port), and use it in + pcre_compile.c when checking for a zero character. + +28. Introducing a native interface for JIT. Through this interface, the compiled + machine code can be directly executed. The purpose of this interface is to + provide fast pattern matching, so several sanity checks are not performed. + However, feature tests are still performed. The new interface provides + 1.4x speedup compared to the old one. + +29. If pcre_exec() or pcre_dfa_exec() was called with a negative value for + the subject string length, the error given was PCRE_ERROR_BADOFFSET, which + was confusing. There is now a new error PCRE_ERROR_BADLENGTH for this case. + +30. In 8-bit UTF-8 mode, pcretest failed to give an error for data codepoints + greater than 0x7fffffff (which cannot be represented in UTF-8, even under + the "old" RFC 2279). Instead, it ended up passing a negative length to + pcre_exec(). + +31. Add support for GCC's visibility feature to hide internal functions. + +32. Running "pcretest -C pcre8" or "pcretest -C pcre16" gave a spurious error + "unknown -C option" after outputting 0 or 1. + +33. There is now support for generating a code coverage report for the test + suite in environments where gcc is the compiler and lcov is installed. This + is mainly for the benefit of the developers. + +34. If PCRE is built with --enable-valgrind, certain memory regions are marked + unaddressable using valgrind annotations, allowing valgrind to detect + invalid memory accesses. This is mainly for the benefit of the developers. + +25. (*UTF) can now be used to start a pattern in any of the three libraries. + +26. Give configure error if --enable-cpp but no C++ compiler found. + + +Version 8.31 06-July-2012 +------------------------- + +1. Fixing a wrong JIT test case and some compiler warnings. + +2. Removed a bashism from the RunTest script. + +3. Add a cast to pcre_exec.c to fix the warning "unary minus operator applied + to unsigned type, result still unsigned" that was given by an MS compiler + on encountering the code "-sizeof(xxx)". + +4. Partial matching support is added to the JIT compiler. + +5. Fixed several bugs concerned with partial matching of items that consist + of more than one character: + + (a) /^(..)\1/ did not partially match "aba" because checking references was + done on an "all or nothing" basis. This also applied to repeated + references. + + (b) \R did not give a hard partial match if \r was found at the end of the + subject. + + (c) \X did not give a hard partial match after matching one or more + characters at the end of the subject. + + (d) When newline was set to CRLF, a pattern such as /a$/ did not recognize + a partial match for the string "\r". + + (e) When newline was set to CRLF, the metacharacter "." did not recognize + a partial match for a CR character at the end of the subject string. + +6. If JIT is requested using /S++ or -s++ (instead of just /S+ or -s+) when + running pcretest, the text "(JIT)" added to the output whenever JIT is + actually used to run the match. + +7. Individual JIT compile options can be set in pcretest by following -s+[+] + or /S+[+] with a digit between 1 and 7. + +8. OP_NOT now supports any UTF character not just single-byte ones. + +9. (*MARK) control verb is now supported by the JIT compiler. + +10. The command "./RunTest list" lists the available tests without actually + running any of them. (Because I keep forgetting what they all are.) + +11. Add PCRE_INFO_MAXLOOKBEHIND. + +12. Applied a (slightly modified) user-supplied patch that improves performance + when the heap is used for recursion (compiled with --disable-stack-for- + recursion). Instead of malloc and free for each heap frame each time a + logical recursion happens, frames are retained on a chain and re-used where + possible. This sometimes gives as much as 30% improvement. + +13. As documented, (*COMMIT) is now confined to within a recursive subpattern + call. + +14. As documented, (*COMMIT) is now confined to within a positive assertion. + +15. It is now possible to link pcretest with libedit as an alternative to + libreadline. + +16. (*COMMIT) control verb is now supported by the JIT compiler. + +17. The Unicode data tables have been updated to Unicode 6.1.0. + +18. Added --file-list option to pcregrep. + +19. Added binary file support to pcregrep, including the -a, --binary-files, + -I, and --text options. + +20. The madvise function is renamed for posix_madvise for QNX compatibility + reasons. Fixed by Giuseppe D'Angelo. + +21. Fixed a bug for backward assertions with REVERSE 0 in the JIT compiler. + +22. Changed the option for creating symbolic links for 16-bit man pages from + -s to -sf so that re-installing does not cause issues. + +23. Support PCRE_NO_START_OPTIMIZE in JIT as (*MARK) support requires it. + +24. Fixed a very old bug in pcretest that caused errors with restarted DFA + matches in certain environments (the workspace was not being correctly + retained). Also added to pcre_dfa_exec() a simple plausibility check on + some of the workspace data at the beginning of a restart. + +25. \s*\R was auto-possessifying the \s* when it should not, whereas \S*\R + was not doing so when it should - probably a typo introduced by SVN 528 + (change 8.10/14). + +26. When PCRE_UCP was not set, \w+\x{c4} was incorrectly auto-possessifying the + \w+ when the character tables indicated that \x{c4} was a word character. + There were several related cases, all because the tests for doing a table + lookup were testing for characters less than 127 instead of 255. + +27. If a pattern contains capturing parentheses that are not used in a match, + their slots in the ovector are set to -1. For those that are higher than + any matched groups, this happens at the end of processing. In the case when + there were back references that the ovector was too small to contain + (causing temporary malloc'd memory to be used during matching), and the + highest capturing number was not used, memory off the end of the ovector + was incorrectly being set to -1. (It was using the size of the temporary + memory instead of the true size.) + +28. To catch bugs like 27 using valgrind, when pcretest is asked to specify an + ovector size, it uses memory at the end of the block that it has got. + +29. Check for an overlong MARK name and give an error at compile time. The + limit is 255 for the 8-bit library and 65535 for the 16-bit library. + +30. JIT compiler update. + +31. JIT is now supported on jailbroken iOS devices. Thanks for Ruiger + Rill for the patch. + +32. Put spaces around SLJIT_PRINT_D in the JIT compiler. Required by CXX11. + +33. Variable renamings in the PCRE-JIT compiler. No functionality change. + +34. Fixed typos in pcregrep: in two places there was SUPPORT_LIBZ2 instead of + SUPPORT_LIBBZ2. This caused a build problem when bzip2 but not gzip (zlib) + was enabled. + +35. Improve JIT code generation for greedy plus quantifier. + +36. When /((?:a?)*)*c/ or /((?>a?)*)*c/ was matched against "aac", it set group + 1 to "aa" instead of to an empty string. The bug affected repeated groups + that could potentially match an empty string. + +37. Optimizing single character iterators in JIT. + +38. Wide characters specified with \uxxxx in JavaScript mode are now subject to + the same checks as \x{...} characters in non-JavaScript mode. Specifically, + codepoints that are too big for the mode are faulted, and in a UTF mode, + disallowed codepoints are also faulted. + +39. If PCRE was compiled with UTF support, in three places in the DFA + matcher there was code that should only have been obeyed in UTF mode, but + was being obeyed unconditionally. In 8-bit mode this could cause incorrect + processing when bytes with values greater than 127 were present. In 16-bit + mode the bug would be provoked by values in the range 0xfc00 to 0xdc00. In + both cases the values are those that cannot be the first data item in a UTF + character. The three items that might have provoked this were recursions, + possessively repeated groups, and atomic groups. + +40. Ensure that libpcre is explicitly listed in the link commands for pcretest + and pcregrep, because some OS require shared objects to be explicitly + passed to ld, causing the link step to fail if they are not. + +41. There were two incorrect #ifdefs in pcre_study.c, meaning that, in 16-bit + mode, patterns that started with \h* or \R* might be incorrectly matched. + + +Version 8.30 04-February-2012 +----------------------------- + +1. Renamed "isnumber" as "is_a_number" because in some Mac environments this + name is defined in ctype.h. + +2. Fixed a bug in fixed-length calculation for lookbehinds that would show up + only in quite long subpatterns. + +3. Removed the function pcre_info(), which has been obsolete and deprecated + since it was replaced by pcre_fullinfo() in February 2000. + +4. For a non-anchored pattern, if (*SKIP) was given with a name that did not + match a (*MARK), and the match failed at the start of the subject, a + reference to memory before the start of the subject could occur. This bug + was introduced by fix 17 of release 8.21. + +5. A reference to an unset group with zero minimum repetition was giving + totally wrong answers (in non-JavaScript-compatibility mode). For example, + /(another)?(\1?)test/ matched against "hello world test". This bug was + introduced in release 8.13. + +6. Add support for 16-bit character strings (a large amount of work involving + many changes and refactorings). + +7. RunGrepTest failed on msys because \r\n was replaced by whitespace when the + command "pattern=`printf 'xxx\r\njkl'`" was run. The pattern is now taken + from a file. + +8. Ovector size of 2 is also supported by JIT based pcre_exec (the ovector size + rounding is not applied in this particular case). + +9. The invalid Unicode surrogate codepoints U+D800 to U+DFFF are now rejected + if they appear, or are escaped, in patterns. + +10. Get rid of a number of -Wunused-but-set-variable warnings. + +11. The pattern /(?=(*:x))(q|)/ matches an empty string, and returns the mark + "x". The similar pattern /(?=(*:x))((*:y)q|)/ did not return a mark at all. + Oddly, Perl behaves the same way. PCRE has been fixed so that this pattern + also returns the mark "x". This bug applied to capturing parentheses, + non-capturing parentheses, and atomic parentheses. It also applied to some + assertions. + +12. Stephen Kelly's patch to CMakeLists.txt allows it to parse the version + information out of configure.ac instead of relying on pcre.h.generic, which + is not stored in the repository. + +13. Applied Dmitry V. Levin's patch for a more portable method for linking with + -lreadline. + +14. ZH added PCRE_CONFIG_JITTARGET; added its output to pcretest -C. + +15. Applied Graycode's patch to put the top-level frame on the stack rather + than the heap when not using the stack for recursion. This gives a + performance improvement in many cases when recursion is not deep. + +16. Experimental code added to "pcretest -C" to output the stack frame size. + + +Version 8.21 12-Dec-2011 +------------------------ + +1. Updating the JIT compiler. + +2. JIT compiler now supports OP_NCREF, OP_RREF and OP_NRREF. New test cases + are added as well. + +3. Fix cache-flush issue on PowerPC (It is still an experimental JIT port). + PCRE_EXTRA_TABLES is not suported by JIT, and should be checked before + calling _pcre_jit_exec. Some extra comments are added. + +4. (*MARK) settings inside atomic groups that do not contain any capturing + parentheses, for example, (?>a(*:m)), were not being passed out. This bug + was introduced by change 18 for 8.20. + +5. Supporting of \x, \U and \u in JavaScript compatibility mode based on the + ECMA-262 standard. + +6. Lookbehinds such as (?<=a{2}b) that contained a fixed repetition were + erroneously being rejected as "not fixed length" if PCRE_CASELESS was set. + This bug was probably introduced by change 9 of 8.13. + +7. While fixing 6 above, I noticed that a number of other items were being + incorrectly rejected as "not fixed length". This arose partly because newer + opcodes had not been added to the fixed-length checking code. I have (a) + corrected the bug and added tests for these items, and (b) arranged for an + error to occur if an unknown opcode is encountered while checking for fixed + length instead of just assuming "not fixed length". The items that were + rejected were: (*ACCEPT), (*COMMIT), (*FAIL), (*MARK), (*PRUNE), (*SKIP), + (*THEN), \h, \H, \v, \V, and single character negative classes with fixed + repetitions, e.g. [^a]{3}, with and without PCRE_CASELESS. + +8. A possessively repeated conditional subpattern such as (?(?=c)c|d)++ was + being incorrectly compiled and would have given unpredicatble results. + +9. A possessively repeated subpattern with minimum repeat count greater than + one behaved incorrectly. For example, (A){2,}+ behaved as if it was + (A)(A)++ which meant that, after a subsequent mismatch, backtracking into + the first (A) could occur when it should not. + +10. Add a cast and remove a redundant test from the code. + +11. JIT should use pcre_malloc/pcre_free for allocation. + +12. Updated pcre-config so that it no longer shows -L/usr/lib, which seems + best practice nowadays, and helps with cross-compiling. (If the exec_prefix + is anything other than /usr, -L is still shown). + +13. In non-UTF-8 mode, \C is now supported in lookbehinds and DFA matching. + +14. Perl does not support \N without a following name in a [] class; PCRE now + also gives an error. + +15. If a forward reference was repeated with an upper limit of around 2000, + it caused the error "internal error: overran compiling workspace". The + maximum number of forward references (including repeats) was limited by the + internal workspace, and dependent on the LINK_SIZE. The code has been + rewritten so that the workspace expands (via pcre_malloc) if necessary, and + the default depends on LINK_SIZE. There is a new upper limit (for safety) + of around 200,000 forward references. While doing this, I also speeded up + the filling in of repeated forward references. + +16. A repeated forward reference in a pattern such as (a)(?2){2}(.) was + incorrectly expecting the subject to contain another "a" after the start. + +17. When (*SKIP:name) is activated without a corresponding (*MARK:name) earlier + in the match, the SKIP should be ignored. This was not happening; instead + the SKIP was being treated as NOMATCH. For patterns such as + /A(*MARK:A)A+(*SKIP:B)Z|AAC/ this meant that the AAC branch was never + tested. + +18. The behaviour of (*MARK), (*PRUNE), and (*THEN) has been reworked and is + now much more compatible with Perl, in particular in cases where the result + is a non-match for a non-anchored pattern. For example, if + /b(*:m)f|a(*:n)w/ is matched against "abc", the non-match returns the name + "m", where previously it did not return a name. A side effect of this + change is that for partial matches, the last encountered mark name is + returned, as for non matches. A number of tests that were previously not + Perl-compatible have been moved into the Perl-compatible test files. The + refactoring has had the pleasing side effect of removing one argument from + the match() function, thus reducing its stack requirements. + +19. If the /S+ option was used in pcretest to study a pattern using JIT, + subsequent uses of /S (without +) incorrectly behaved like /S+. + +21. Retrieve executable code size support for the JIT compiler and fixing + some warnings. + +22. A caseless match of a UTF-8 character whose other case uses fewer bytes did + not work when the shorter character appeared right at the end of the + subject string. + +23. Added some (int) casts to non-JIT modules to reduce warnings on 64-bit + systems. + +24. Added PCRE_INFO_JITSIZE to pass on the value from (21) above, and also + output it when the /M option is used in pcretest. + +25. The CheckMan script was not being included in the distribution. Also, added + an explicit "perl" to run Perl scripts from the PrepareRelease script + because this is reportedly needed in Windows. + +26. If study data was being save in a file and studying had not found a set of + "starts with" bytes for the pattern, the data written to the file (though + never used) was taken from uninitialized memory and so caused valgrind to + complain. + +27. Updated RunTest.bat as provided by Sheri Pierce. + +28. Fixed a possible uninitialized memory bug in pcre_jit_compile.c. + +29. Computation of memory usage for the table of capturing group names was + giving an unnecessarily large value. + + +Version 8.20 21-Oct-2011 +------------------------ + +1. Change 37 of 8.13 broke patterns like [:a]...[b:] because it thought it had + a POSIX class. After further experiments with Perl, which convinced me that + Perl has bugs and confusions, a closing square bracket is no longer allowed + in a POSIX name. This bug also affected patterns with classes that started + with full stops. + +2. If a pattern such as /(a)b|ac/ is matched against "ac", there is no + captured substring, but while checking the failing first alternative, + substring 1 is temporarily captured. If the output vector supplied to + pcre_exec() was not big enough for this capture, the yield of the function + was still zero ("insufficient space for captured substrings"). This cannot + be totally fixed without adding another stack variable, which seems a lot + of expense for a edge case. However, I have improved the situation in cases + such as /(a)(b)x|abc/ matched against "abc", where the return code + indicates that fewer than the maximum number of slots in the ovector have + been set. + +3. Related to (2) above: when there are more back references in a pattern than + slots in the output vector, pcre_exec() uses temporary memory during + matching, and copies in the captures as far as possible afterwards. It was + using the entire output vector, but this conflicts with the specification + that only 2/3 is used for passing back captured substrings. Now it uses + only the first 2/3, for compatibility. This is, of course, another edge + case. + +4. Zoltan Herczeg's just-in-time compiler support has been integrated into the + main code base, and can be used by building with --enable-jit. When this is + done, pcregrep automatically uses it unless --disable-pcregrep-jit or the + runtime --no-jit option is given. + +5. When the number of matches in a pcre_dfa_exec() run exactly filled the + ovector, the return from the function was zero, implying that there were + other matches that did not fit. The correct "exactly full" value is now + returned. + +6. If a subpattern that was called recursively or as a subroutine contained + (*PRUNE) or any other control that caused it to give a non-standard return, + invalid errors such as "Error -26 (nested recursion at the same subject + position)" or even infinite loops could occur. + +7. If a pattern such as /a(*SKIP)c|b(*ACCEPT)|/ was studied, it stopped + computing the minimum length on reaching *ACCEPT, and so ended up with the + wrong value of 1 rather than 0. Further investigation indicates that + computing a minimum subject length in the presence of *ACCEPT is difficult + (think back references, subroutine calls), and so I have changed the code + so that no minimum is registered for a pattern that contains *ACCEPT. + +8. If (*THEN) was present in the first (true) branch of a conditional group, + it was not handled as intended. [But see 16 below.] + +9. Replaced RunTest.bat and CMakeLists.txt with improved versions provided by + Sheri Pierce. + +10. A pathological pattern such as /(*ACCEPT)a/ was miscompiled, thinking that + the first byte in a match must be "a". + +11. Change 17 for 8.13 increased the recursion depth for patterns like + /a(?:.)*?a/ drastically. I've improved things by remembering whether a + pattern contains any instances of (*THEN). If it does not, the old + optimizations are restored. It would be nice to do this on a per-group + basis, but at the moment that is not feasible. + +12. In some environments, the output of pcretest -C is CRLF terminated. This + broke RunTest's code that checks for the link size. A single white space + character after the value is now allowed for. + +13. RunTest now checks for the "fr" locale as well as for "fr_FR" and "french". + For "fr", it uses the Windows-specific input and output files. + +14. If (*THEN) appeared in a group that was called recursively or as a + subroutine, it did not work as intended. [But see next item.] + +15. Consider the pattern /A (B(*THEN)C) | D/ where A, B, C, and D are complex + pattern fragments (but not containing any | characters). If A and B are + matched, but there is a failure in C so that it backtracks to (*THEN), PCRE + was behaving differently to Perl. PCRE backtracked into A, but Perl goes to + D. In other words, Perl considers parentheses that do not contain any | + characters to be part of a surrounding alternative, whereas PCRE was + treading (B(*THEN)C) the same as (B(*THEN)C|(*FAIL)) -- which Perl handles + differently. PCRE now behaves in the same way as Perl, except in the case + of subroutine/recursion calls such as (?1) which have in any case always + been different (but PCRE had them first :-). + +16. Related to 15 above: Perl does not treat the | in a conditional group as + creating alternatives. Such a group is treated in the same way as an + ordinary group without any | characters when processing (*THEN). PCRE has + been changed to match Perl's behaviour. + +17. If a user had set PCREGREP_COLO(U)R to something other than 1:31, the + RunGrepTest script failed. + +18. Change 22 for version 13 caused atomic groups to use more stack. This is + inevitable for groups that contain captures, but it can lead to a lot of + stack use in large patterns. The old behaviour has been restored for atomic + groups that do not contain any capturing parentheses. + +19. If the PCRE_NO_START_OPTIMIZE option was set for pcre_compile(), it did not + suppress the check for a minimum subject length at run time. (If it was + given to pcre_exec() or pcre_dfa_exec() it did work.) + +20. Fixed an ASCII-dependent infelicity in pcretest that would have made it + fail to work when decoding hex characters in data strings in EBCDIC + environments. + +21. It appears that in at least one Mac OS environment, the isxdigit() function + is implemented as a macro that evaluates to its argument more than once, + contravening the C 90 Standard (I haven't checked a later standard). There + was an instance in pcretest which caused it to go wrong when processing + \x{...} escapes in subject strings. The has been rewritten to avoid using + things like p++ in the argument of isxdigit(). + + +Version 8.13 16-Aug-2011 +------------------------ + +1. The Unicode data tables have been updated to Unicode 6.0.0. + +2. Two minor typos in pcre_internal.h have been fixed. + +3. Added #include <string.h> to pcre_scanner_unittest.cc, pcrecpp.cc, and + pcrecpp_unittest.cc. They are needed for strcmp(), memset(), and strchr() + in some environments (e.g. Solaris 10/SPARC using Sun Studio 12U2). + +4. There were a number of related bugs in the code for matching backrefences + caselessly in UTF-8 mode when codes for the characters concerned were + different numbers of bytes. For example, U+023A and U+2C65 are an upper + and lower case pair, using 2 and 3 bytes, respectively. The main bugs were: + (a) A reference to 3 copies of a 2-byte code matched only 2 of a 3-byte + code. (b) A reference to 2 copies of a 3-byte code would not match 2 of a + 2-byte code at the end of the subject (it thought there wasn't enough data + left). + +5. Comprehensive information about what went wrong is now returned by + pcre_exec() and pcre_dfa_exec() when the UTF-8 string check fails, as long + as the output vector has at least 2 elements. The offset of the start of + the failing character and a reason code are placed in the vector. + +6. When the UTF-8 string check fails for pcre_compile(), the offset that is + now returned is for the first byte of the failing character, instead of the + last byte inspected. This is an incompatible change, but I hope it is small + enough not to be a problem. It makes the returned offset consistent with + pcre_exec() and pcre_dfa_exec(). + +7. pcretest now gives a text phrase as well as the error number when + pcre_exec() or pcre_dfa_exec() fails; if the error is a UTF-8 check + failure, the offset and reason code are output. + +8. When \R was used with a maximizing quantifier it failed to skip backwards + over a \r\n pair if the subsequent match failed. Instead, it just skipped + back over a single character (\n). This seems wrong (because it treated the + two characters as a single entity when going forwards), conflicts with the + documentation that \R is equivalent to (?>\r\n|\n|...etc), and makes the + behaviour of \R* different to (\R)*, which also seems wrong. The behaviour + has been changed. + +9. Some internal refactoring has changed the processing so that the handling + of the PCRE_CASELESS and PCRE_MULTILINE options is done entirely at compile + time (the PCRE_DOTALL option was changed this way some time ago: version + 7.7 change 16). This has made it possible to abolish the OP_OPT op code, + which was always a bit of a fudge. It also means that there is one less + argument for the match() function, which reduces its stack requirements + slightly. This change also fixes an incompatibility with Perl: the pattern + (?i:([^b]))(?1) should not match "ab", but previously PCRE gave a match. + +10. More internal refactoring has drastically reduced the number of recursive + calls to match() for possessively repeated groups such as (abc)++ when + using pcre_exec(). + +11. While implementing 10, a number of bugs in the handling of groups were + discovered and fixed: + + (?<=(a)+) was not diagnosed as invalid (non-fixed-length lookbehind). + (a|)*(?1) gave a compile-time internal error. + ((a|)+)+ did not notice that the outer group could match an empty string. + (^a|^)+ was not marked as anchored. + (.*a|.*)+ was not marked as matching at start or after a newline. + +12. Yet more internal refactoring has removed another argument from the match() + function. Special calls to this function are now indicated by setting a + value in a variable in the "match data" data block. + +13. Be more explicit in pcre_study() instead of relying on "default" for + opcodes that mean there is no starting character; this means that when new + ones are added and accidentally left out of pcre_study(), testing should + pick them up. + +14. The -s option of pcretest has been documented for ages as being an old + synonym of -m (show memory usage). I have changed it to mean "force study + for every regex", that is, assume /S for every regex. This is similar to -i + and -d etc. It's slightly incompatible, but I'm hoping nobody is still + using it. It makes it easier to run collections of tests with and without + study enabled, and thereby test pcre_study() more easily. All the standard + tests are now run with and without -s (but some patterns can be marked as + "never study" - see 20 below). + +15. When (*ACCEPT) was used in a subpattern that was called recursively, the + restoration of the capturing data to the outer values was not happening + correctly. + +16. If a recursively called subpattern ended with (*ACCEPT) and matched an + empty string, and PCRE_NOTEMPTY was set, pcre_exec() thought the whole + pattern had matched an empty string, and so incorrectly returned a no + match. + +17. There was optimizing code for the last branch of non-capturing parentheses, + and also for the obeyed branch of a conditional subexpression, which used + tail recursion to cut down on stack usage. Unfortunately, now that there is + the possibility of (*THEN) occurring in these branches, tail recursion is + no longer possible because the return has to be checked for (*THEN). These + two optimizations have therefore been removed. [But see 8.20/11 above.] + +18. If a pattern containing \R was studied, it was assumed that \R always + matched two bytes, thus causing the minimum subject length to be + incorrectly computed because \R can also match just one byte. + +19. If a pattern containing (*ACCEPT) was studied, the minimum subject length + was incorrectly computed. + +20. If /S is present twice on a test pattern in pcretest input, it now + *disables* studying, thereby overriding the use of -s on the command line + (see 14 above). This is necessary for one or two tests to keep the output + identical in both cases. + +21. When (*ACCEPT) was used in an assertion that matched an empty string and + PCRE_NOTEMPTY was set, PCRE applied the non-empty test to the assertion. + +22. When an atomic group that contained a capturing parenthesis was + successfully matched, but the branch in which it appeared failed, the + capturing was not being forgotten if a higher numbered group was later + captured. For example, /(?>(a))b|(a)c/ when matching "ac" set capturing + group 1 to "a", when in fact it should be unset. This applied to multi- + branched capturing and non-capturing groups, repeated or not, and also to + positive assertions (capturing in negative assertions does not happen + in PCRE) and also to nested atomic groups. + +23. Add the ++ qualifier feature to pcretest, to show the remainder of the + subject after a captured substring, to make it easier to tell which of a + number of identical substrings has been captured. + +24. The way atomic groups are processed by pcre_exec() has been changed so that + if they are repeated, backtracking one repetition now resets captured + values correctly. For example, if ((?>(a+)b)+aabab) is matched against + "aaaabaaabaabab" the value of captured group 2 is now correctly recorded as + "aaa". Previously, it would have been "a". As part of this code + refactoring, the way recursive calls are handled has also been changed. + +25. If an assertion condition captured any substrings, they were not passed + back unless some other capturing happened later. For example, if + (?(?=(a))a) was matched against "a", no capturing was returned. + +26. When studying a pattern that contained subroutine calls or assertions, + the code for finding the minimum length of a possible match was handling + direct recursions such as (xxx(?1)|yyy) but not mutual recursions (where + group 1 called group 2 while simultaneously a separate group 2 called group + 1). A stack overflow occurred in this case. I have fixed this by limiting + the recursion depth to 10. + +27. Updated RunTest.bat in the distribution to the version supplied by Tom + Fortmann. This supports explicit test numbers on the command line, and has + argument validation and error reporting. + +28. An instance of \X with an unlimited repeat could fail if at any point the + first character it looked at was a mark character. + +29. Some minor code refactoring concerning Unicode properties and scripts + should reduce the stack requirement of match() slightly. + +30. Added the '=' option to pcretest to check the setting of unused capturing + slots at the end of the pattern, which are documented as being -1, but are + not included in the return count. + +31. If \k was not followed by a braced, angle-bracketed, or quoted name, PCRE + compiled something random. Now it gives a compile-time error (as does + Perl). + +32. A *MARK encountered during the processing of a positive assertion is now + recorded and passed back (compatible with Perl). + +33. If --only-matching or --colour was set on a pcregrep call whose pattern + had alternative anchored branches, the search for a second match in a line + was done as if at the line start. Thus, for example, /^01|^02/ incorrectly + matched the line "0102" twice. The same bug affected patterns that started + with a backwards assertion. For example /\b01|\b02/ also matched "0102" + twice. + +34. Previously, PCRE did not allow quantification of assertions. However, Perl + does, and because of capturing effects, quantifying parenthesized + assertions may at times be useful. Quantifiers are now allowed for + parenthesized assertions. + +35. A minor code tidy in pcre_compile() when checking options for \R usage. + +36. \g was being checked for fancy things in a character class, when it should + just be a literal "g". + +37. PCRE was rejecting [:a[:digit:]] whereas Perl was not. It seems that the + appearance of a nested POSIX class supersedes an apparent external class. + For example, [:a[:digit:]b:] matches "a", "b", ":", or a digit. Also, + unescaped square brackets may also appear as part of class names. For + example, [:a[:abc]b:] gives unknown class "[:abc]b:]". PCRE now behaves + more like Perl. (But see 8.20/1 above.) + +38. PCRE was giving an error for \N with a braced quantifier such as {1,} (this + was because it thought it was \N{name}, which is not supported). + +39. Add minix to OS list not supporting the -S option in pcretest. + +40. PCRE tries to detect cases of infinite recursion at compile time, but it + cannot analyze patterns in sufficient detail to catch mutual recursions + such as ((?1))((?2)). There is now a runtime test that gives an error if a + subgroup is called recursively as a subpattern for a second time at the + same position in the subject string. In previous releases this might have + been caught by the recursion limit, or it might have run out of stack. + +41. A pattern such as /(?(R)a+|(?R)b)/ is quite safe, as the recursion can + happen only once. PCRE was, however incorrectly giving a compile time error + "recursive call could loop indefinitely" because it cannot analyze the + pattern in sufficient detail. The compile time test no longer happens when + PCRE is compiling a conditional subpattern, but actual runaway loops are + now caught at runtime (see 40 above). + +42. It seems that Perl allows any characters other than a closing parenthesis + to be part of the NAME in (*MARK:NAME) and other backtracking verbs. PCRE + has been changed to be the same. + +43. Updated configure.ac to put in more quoting round AC_LANG_PROGRAM etc. so + as not to get warnings when autogen.sh is called. Also changed + AC_PROG_LIBTOOL (deprecated) to LT_INIT (the current macro). + +44. To help people who use pcregrep to scan files containing exceedingly long + lines, the following changes have been made: + + (a) The default value of the buffer size parameter has been increased from + 8K to 20K. (The actual buffer used is three times this size.) + + (b) The default can be changed by ./configure --with-pcregrep-bufsize when + PCRE is built. + + (c) A --buffer-size=n option has been added to pcregrep, to allow the size + to be set at run time. + + (d) Numerical values in pcregrep options can be followed by K or M, for + example --buffer-size=50K. + + (e) If a line being scanned overflows pcregrep's buffer, an error is now + given and the return code is set to 2. + +45. Add a pointer to the latest mark to the callout data block. + +46. The pattern /.(*F)/, when applied to "abc" with PCRE_PARTIAL_HARD, gave a + partial match of an empty string instead of no match. This was specific to + the use of ".". + +47. The pattern /f.*/8s, when applied to "for" with PCRE_PARTIAL_HARD, gave a + complete match instead of a partial match. This bug was dependent on both + the PCRE_UTF8 and PCRE_DOTALL options being set. + +48. For a pattern such as /\babc|\bdef/ pcre_study() was failing to set up the + starting byte set, because \b was not being ignored. + + +Version 8.12 15-Jan-2011 +------------------------ + +1. Fixed some typos in the markup of the man pages, and wrote a script that + checks for such things as part of the documentation building process. + +2. On a big-endian 64-bit system, pcregrep did not correctly process the + --match-limit and --recursion-limit options (added for 8.11). In + particular, this made one of the standard tests fail. (The integer value + went into the wrong half of a long int.) + +3. If the --colour option was given to pcregrep with -v (invert match), it + did strange things, either producing crazy output, or crashing. It should, + of course, ignore a request for colour when reporting lines that do not + match. + +4. Another pcregrep bug caused similar problems if --colour was specified with + -M (multiline) and the pattern match finished with a line ending. + +5. In pcregrep, when a pattern that ended with a literal newline sequence was + matched in multiline mode, the following line was shown as part of the + match. This seems wrong, so I have changed it. + +6. Another pcregrep bug in multiline mode, when --colour was specified, caused + the check for further matches in the same line (so they could be coloured) + to overrun the end of the current line. If another match was found, it was + incorrectly shown (and then shown again when found in the next line). + +7. If pcregrep was compiled under Windows, there was a reference to the + function pcregrep_exit() before it was defined. I am assuming this was + the cause of the "error C2371: 'pcregrep_exit' : redefinition;" that was + reported by a user. I've moved the definition above the reference. + + +Version 8.11 10-Dec-2010 +------------------------ + +1. (*THEN) was not working properly if there were untried alternatives prior + to it in the current branch. For example, in ((a|b)(*THEN)(*F)|c..) it + backtracked to try for "b" instead of moving to the next alternative branch + at the same level (in this case, to look for "c"). The Perl documentation + is clear that when (*THEN) is backtracked onto, it goes to the "next + alternative in the innermost enclosing group". + +2. (*COMMIT) was not overriding (*THEN), as it does in Perl. In a pattern + such as (A(*COMMIT)B(*THEN)C|D) any failure after matching A should + result in overall failure. Similarly, (*COMMIT) now overrides (*PRUNE) and + (*SKIP), (*SKIP) overrides (*PRUNE) and (*THEN), and (*PRUNE) overrides + (*THEN). + +3. If \s appeared in a character class, it removed the VT character from + the class, even if it had been included by some previous item, for example + in [\x00-\xff\s]. (This was a bug related to the fact that VT is not part + of \s, but is part of the POSIX "space" class.) + +4. A partial match never returns an empty string (because you can always + match an empty string at the end of the subject); however the checking for + an empty string was starting at the "start of match" point. This has been + changed to the "earliest inspected character" point, because the returned + data for a partial match starts at this character. This means that, for + example, /(?<=abc)def/ gives a partial match for the subject "abc" + (previously it gave "no match"). + +5. Changes have been made to the way PCRE_PARTIAL_HARD affects the matching + of $, \z, \Z, \b, and \B. If the match point is at the end of the string, + previously a full match would be given. However, setting PCRE_PARTIAL_HARD + has an implication that the given string is incomplete (because a partial + match is preferred over a full match). For this reason, these items now + give a partial match in this situation. [Aside: previously, the one case + /t\b/ matched against "cat" with PCRE_PARTIAL_HARD set did return a partial + match rather than a full match, which was wrong by the old rules, but is + now correct.] + +6. There was a bug in the handling of #-introduced comments, recognized when + PCRE_EXTENDED is set, when PCRE_NEWLINE_ANY and PCRE_UTF8 were also set. + If a UTF-8 multi-byte character included the byte 0x85 (e.g. +U0445, whose + UTF-8 encoding is 0xd1,0x85), this was misinterpreted as a newline when + scanning for the end of the comment. (*Character* 0x85 is an "any" newline, + but *byte* 0x85 is not, in UTF-8 mode). This bug was present in several + places in pcre_compile(). + +7. Related to (6) above, when pcre_compile() was skipping #-introduced + comments when looking ahead for named forward references to subpatterns, + the only newline sequence it recognized was NL. It now handles newlines + according to the set newline convention. + +8. SunOS4 doesn't have strerror() or strtoul(); pcregrep dealt with the + former, but used strtoul(), whereas pcretest avoided strtoul() but did not + cater for a lack of strerror(). These oversights have been fixed. + +9. Added --match-limit and --recursion-limit to pcregrep. + +10. Added two casts needed to build with Visual Studio when NO_RECURSE is set. + +11. When the -o option was used, pcregrep was setting a return code of 1, even + when matches were found, and --line-buffered was not being honoured. + +12. Added an optional parentheses number to the -o and --only-matching options + of pcregrep. + +13. Imitating Perl's /g action for multiple matches is tricky when the pattern + can match an empty string. The code to do it in pcretest and pcredemo + needed fixing: + + (a) When the newline convention was "crlf", pcretest got it wrong, skipping + only one byte after an empty string match just before CRLF (this case + just got forgotten; "any" and "anycrlf" were OK). + + (b) The pcretest code also had a bug, causing it to loop forever in UTF-8 + mode when an empty string match preceded an ASCII character followed by + a non-ASCII character. (The code for advancing by one character rather + than one byte was nonsense.) + + (c) The pcredemo.c sample program did not have any code at all to handle + the cases when CRLF is a valid newline sequence. + +14. Neither pcre_exec() nor pcre_dfa_exec() was checking that the value given + as a starting offset was within the subject string. There is now a new + error, PCRE_ERROR_BADOFFSET, which is returned if the starting offset is + negative or greater than the length of the string. In order to test this, + pcretest is extended to allow the setting of negative starting offsets. + +15. In both pcre_exec() and pcre_dfa_exec() the code for checking that the + starting offset points to the beginning of a UTF-8 character was + unnecessarily clumsy. I tidied it up. + +16. Added PCRE_ERROR_SHORTUTF8 to make it possible to distinguish between a + bad UTF-8 sequence and one that is incomplete when using PCRE_PARTIAL_HARD. + +17. Nobody had reported that the --include_dir option, which was added in + release 7.7 should have been called --include-dir (hyphen, not underscore) + for compatibility with GNU grep. I have changed it to --include-dir, but + left --include_dir as an undocumented synonym, and the same for + --exclude-dir, though that is not available in GNU grep, at least as of + release 2.5.4. + +18. At a user's suggestion, the macros GETCHAR and friends (which pick up UTF-8 + characters from a string of bytes) have been redefined so as not to use + loops, in order to improve performance in some environments. At the same + time, I abstracted some of the common code into auxiliary macros to save + repetition (this should not affect the compiled code). + +19. If \c was followed by a multibyte UTF-8 character, bad things happened. A + compile-time error is now given if \c is not followed by an ASCII + character, that is, a byte less than 128. (In EBCDIC mode, the code is + different, and any byte value is allowed.) + +20. Recognize (*NO_START_OPT) at the start of a pattern to set the PCRE_NO_ + START_OPTIMIZE option, which is now allowed at compile time - but just + passed through to pcre_exec() or pcre_dfa_exec(). This makes it available + to pcregrep and other applications that have no direct access to PCRE + options. The new /Y option in pcretest sets this option when calling + pcre_compile(). + +21. Change 18 of release 8.01 broke the use of named subpatterns for recursive + back references. Groups containing recursive back references were forced to + be atomic by that change, but in the case of named groups, the amount of + memory required was incorrectly computed, leading to "Failed: internal + error: code overflow". This has been fixed. + +22. Some patches to pcre_stringpiece.h, pcre_stringpiece_unittest.cc, and + pcretest.c, to avoid build problems in some Borland environments. + + +Version 8.10 25-Jun-2010 +------------------------ + +1. Added support for (*MARK:ARG) and for ARG additions to PRUNE, SKIP, and + THEN. + +2. (*ACCEPT) was not working when inside an atomic group. + +3. Inside a character class, \B is treated as a literal by default, but + faulted if PCRE_EXTRA is set. This mimics Perl's behaviour (the -w option + causes the error). The code is unchanged, but I tidied the documentation. + +4. Inside a character class, PCRE always treated \R and \X as literals, + whereas Perl faults them if its -w option is set. I have changed PCRE so + that it faults them when PCRE_EXTRA is set. + +5. Added support for \N, which always matches any character other than + newline. (It is the same as "." when PCRE_DOTALL is not set.) + +6. When compiling pcregrep with newer versions of gcc which may have + FORTIFY_SOURCE set, several warnings "ignoring return value of 'fwrite', + declared with attribute warn_unused_result" were given. Just casting the + result to (void) does not stop the warnings; a more elaborate fudge is + needed. I've used a macro to implement this. + +7. Minor change to pcretest.c to avoid a compiler warning. + +8. Added four artifical Unicode properties to help with an option to make + \s etc use properties (see next item). The new properties are: Xan + (alphanumeric), Xsp (Perl space), Xps (POSIX space), and Xwd (word). + +9. Added PCRE_UCP to make \b, \d, \s, \w, and certain POSIX character classes + use Unicode properties. (*UCP) at the start of a pattern can be used to set + this option. Modified pcretest to add /W to test this facility. Added + REG_UCP to make it available via the POSIX interface. + +10. Added --line-buffered to pcregrep. + +11. In UTF-8 mode, if a pattern that was compiled with PCRE_CASELESS was + studied, and the match started with a letter with a code point greater than + 127 whose first byte was different to the first byte of the other case of + the letter, the other case of this starting letter was not recognized + (#976). + +12. If a pattern that was studied started with a repeated Unicode property + test, for example, \p{Nd}+, there was the theoretical possibility of + setting up an incorrect bitmap of starting bytes, but fortunately it could + not have actually happened in practice until change 8 above was made (it + added property types that matched character-matching opcodes). + +13. pcre_study() now recognizes \h, \v, and \R when constructing a bit map of + possible starting bytes for non-anchored patterns. + +14. Extended the "auto-possessify" feature of pcre_compile(). It now recognizes + \R, and also a number of cases that involve Unicode properties, both + explicit and implicit when PCRE_UCP is set. + +15. If a repeated Unicode property match (e.g. \p{Lu}*) was used with non-UTF-8 + input, it could crash or give wrong results if characters with values + greater than 0xc0 were present in the subject string. (Detail: it assumed + UTF-8 input when processing these items.) + +16. Added a lot of (int) casts to avoid compiler warnings in systems where + size_t is 64-bit (#991). + +17. Added a check for running out of memory when PCRE is compiled with + --disable-stack-for-recursion (#990). + +18. If the last data line in a file for pcretest does not have a newline on + the end, a newline was missing in the output. + +19. The default pcre_chartables.c file recognizes only ASCII characters (values + less than 128) in its various bitmaps. However, there is a facility for + generating tables according to the current locale when PCRE is compiled. It + turns out that in some environments, 0x85 and 0xa0, which are Unicode space + characters, are recognized by isspace() and therefore were getting set in + these tables, and indeed these tables seem to approximate to ISO 8859. This + caused a problem in UTF-8 mode when pcre_study() was used to create a list + of bytes that can start a match. For \s, it was including 0x85 and 0xa0, + which of course cannot start UTF-8 characters. I have changed the code so + that only real ASCII characters (less than 128) and the correct starting + bytes for UTF-8 encodings are set for characters greater than 127 when in + UTF-8 mode. (When PCRE_UCP is set - see 9 above - the code is different + altogether.) + +20. Added the /T option to pcretest so as to be able to run tests with non- + standard character tables, thus making it possible to include the tests + used for 19 above in the standard set of tests. + +21. A pattern such as (?&t)(?#()(?(DEFINE)(?<t>a)) which has a forward + reference to a subpattern the other side of a comment that contains an + opening parenthesis caused either an internal compiling error, or a + reference to the wrong subpattern. + + +Version 8.02 19-Mar-2010 +------------------------ + +1. The Unicode data tables have been updated to Unicode 5.2.0. + +2. Added the option --libs-cpp to pcre-config, but only when C++ support is + configured. + +3. Updated the licensing terms in the pcregexp.pas file, as agreed with the + original author of that file, following a query about its status. + +4. On systems that do not have stdint.h (e.g. Solaris), check for and include + inttypes.h instead. This fixes a bug that was introduced by change 8.01/8. + +5. A pattern such as (?&t)*+(?(DEFINE)(?<t>.)) which has a possessive + quantifier applied to a forward-referencing subroutine call, could compile + incorrect code or give the error "internal error: previously-checked + referenced subpattern not found". + +6. Both MS Visual Studio and Symbian OS have problems with initializing + variables to point to external functions. For these systems, therefore, + pcre_malloc etc. are now initialized to local functions that call the + relevant global functions. + +7. There were two entries missing in the vectors called coptable and poptable + in pcre_dfa_exec.c. This could lead to memory accesses outsize the vectors. + I've fixed the data, and added a kludgy way of testing at compile time that + the lengths are correct (equal to the number of opcodes). + +8. Following on from 7, I added a similar kludge to check the length of the + eint vector in pcreposix.c. + +9. Error texts for pcre_compile() are held as one long string to avoid too + much relocation at load time. To find a text, the string is searched, + counting zeros. There was no check for running off the end of the string, + which could happen if a new error number was added without updating the + string. + +10. \K gave a compile-time error if it appeared in a lookbehind assersion. + +11. \K was not working if it appeared in an atomic group or in a group that + was called as a "subroutine", or in an assertion. Perl 5.11 documents that + \K is "not well defined" if used in an assertion. PCRE now accepts it if + the assertion is positive, but not if it is negative. + +12. Change 11 fortuitously reduced the size of the stack frame used in the + "match()" function of pcre_exec.c by one pointer. Forthcoming + implementation of support for (*MARK) will need an extra pointer on the + stack; I have reserved it now, so that the stack frame size does not + decrease. + +13. A pattern such as (?P<L1>(?P<L2>0)|(?P>L2)(?P>L1)) in which the only other + item in branch that calls a recursion is a subroutine call - as in the + second branch in the above example - was incorrectly given the compile- + time error "recursive call could loop indefinitely" because pcre_compile() + was not correctly checking the subroutine for matching a non-empty string. + +14. The checks for overrunning compiling workspace could trigger after an + overrun had occurred. This is a "should never occur" error, but it can be + triggered by pathological patterns such as hundreds of nested parentheses. + The checks now trigger 100 bytes before the end of the workspace. + +15. Fix typo in configure.ac: "srtoq" should be "strtoq". + + +Version 8.01 19-Jan-2010 +------------------------ + +1. If a pattern contained a conditional subpattern with only one branch (in + particular, this includes all (*DEFINE) patterns), a call to pcre_study() + computed the wrong minimum data length (which is of course zero for such + subpatterns). This could cause incorrect "no match" results. + +2. For patterns such as (?i)a(?-i)b|c where an option setting at the start of + the pattern is reset in the first branch, pcre_compile() failed with + "internal error: code overflow at offset...". This happened only when + the reset was to the original external option setting. (An optimization + abstracts leading options settings into an external setting, which was the + cause of this.) + +3. A pattern such as ^(?!a(*SKIP)b) where a negative assertion contained one + of the verbs SKIP, PRUNE, or COMMIT, did not work correctly. When the + assertion pattern did not match (meaning that the assertion was true), it + was incorrectly treated as false if the SKIP had been reached during the + matching. This also applied to assertions used as conditions. + +4. If an item that is not supported by pcre_dfa_exec() was encountered in an + assertion subpattern, including such a pattern used as a condition, + unpredictable results occurred, instead of the error return + PCRE_ERROR_DFA_UITEM. + +5. The C++ GlobalReplace function was not working like Perl for the special + situation when an empty string is matched. It now does the fancy magic + stuff that is necessary. + +6. In pcre_internal.h, obsolete includes to setjmp.h and stdarg.h have been + removed. (These were left over from very, very early versions of PCRE.) + +7. Some cosmetic changes to the code to make life easier when compiling it + as part of something else: + + (a) Change DEBUG to PCRE_DEBUG. + + (b) In pcre_compile(), rename the member of the "branch_chain" structure + called "current" as "current_branch", to prevent a collision with the + Linux macro when compiled as a kernel module. + + (c) In pcre_study(), rename the function set_bit() as set_table_bit(), to + prevent a collision with the Linux macro when compiled as a kernel + module. + +8. In pcre_compile() there are some checks for integer overflows that used to + cast potentially large values to (double). This has been changed to that + when building, a check for int64_t is made, and if it is found, it is used + instead, thus avoiding the use of floating point arithmetic. (There is no + other use of FP in PCRE.) If int64_t is not found, the fallback is to + double. + +9. Added two casts to avoid signed/unsigned warnings from VS Studio Express + 2005 (difference between two addresses compared to an unsigned value). + +10. Change the standard AC_CHECK_LIB test for libbz2 in configure.ac to a + custom one, because of the following reported problem in Windows: + + - libbz2 uses the Pascal calling convention (WINAPI) for the functions + under Win32. + - The standard autoconf AC_CHECK_LIB fails to include "bzlib.h", + therefore missing the function definition. + - The compiler thus generates a "C" signature for the test function. + - The linker fails to find the "C" function. + - PCRE fails to configure if asked to do so against libbz2. + +11. When running libtoolize from libtool-2.2.6b as part of autogen.sh, these + messages were output: + + Consider adding `AC_CONFIG_MACRO_DIR([m4])' to configure.ac and + rerunning libtoolize, to keep the correct libtool macros in-tree. + Consider adding `-I m4' to ACLOCAL_AMFLAGS in Makefile.am. + + I have done both of these things. + +12. Although pcre_dfa_exec() does not use nearly as much stack as pcre_exec() + most of the time, it *can* run out if it is given a pattern that contains a + runaway infinite recursion. I updated the discussion in the pcrestack man + page. + +13. Now that we have gone to the x.xx style of version numbers, the minor + version may start with zero. Using 08 or 09 is a bad idea because users + might check the value of PCRE_MINOR in their code, and 08 or 09 may be + interpreted as invalid octal numbers. I've updated the previous comment in + configure.ac, and also added a check that gives an error if 08 or 09 are + used. + +14. Change 8.00/11 was not quite complete: code had been accidentally omitted, + causing partial matching to fail when the end of the subject matched \W + in a UTF-8 pattern where \W was quantified with a minimum of 3. + +15. There were some discrepancies between the declarations in pcre_internal.h + of _pcre_is_newline(), _pcre_was_newline(), and _pcre_valid_utf8() and + their definitions. The declarations used "const uschar *" and the + definitions used USPTR. Even though USPTR is normally defined as "const + unsigned char *" (and uschar is typedeffed as "unsigned char"), it was + reported that: "This difference in casting confuses some C++ compilers, for + example, SunCC recognizes above declarations as different functions and + generates broken code for hbpcre." I have changed the declarations to use + USPTR. + +16. GNU libtool is named differently on some systems. The autogen.sh script now + tries several variants such as glibtoolize (MacOSX) and libtoolize1x + (FreeBSD). + +17. Applied Craig's patch that fixes an HP aCC compile error in pcre 8.00 + (strtoXX undefined when compiling pcrecpp.cc). The patch contains this + comment: "Figure out how to create a longlong from a string: strtoll and + equivalent. It's not enough to call AC_CHECK_FUNCS: hpux has a strtoll, for + instance, but it only takes 2 args instead of 3!" + +18. A subtle bug concerned with back references has been fixed by a change of + specification, with a corresponding code fix. A pattern such as + ^(xa|=?\1a)+$ which contains a back reference inside the group to which it + refers, was giving matches when it shouldn't. For example, xa=xaaa would + match that pattern. Interestingly, Perl (at least up to 5.11.3) has the + same bug. Such groups have to be quantified to be useful, or contained + inside another quantified group. (If there's no repetition, the reference + can never match.) The problem arises because, having left the group and + moved on to the rest of the pattern, a later failure that backtracks into + the group uses the captured value from the final iteration of the group + rather than the correct earlier one. I have fixed this in PCRE by forcing + any group that contains a reference to itself to be an atomic group; that + is, there cannot be any backtracking into it once it has completed. This is + similar to recursive and subroutine calls. + + +Version 8.00 19-Oct-09 +---------------------- + +1. The table for translating pcre_compile() error codes into POSIX error codes + was out-of-date, and there was no check on the pcre_compile() error code + being within the table. This could lead to an OK return being given in + error. + +2. Changed the call to open a subject file in pcregrep from fopen(pathname, + "r") to fopen(pathname, "rb"), which fixed a problem with some of the tests + in a Windows environment. + +3. The pcregrep --count option prints the count for each file even when it is + zero, as does GNU grep. However, pcregrep was also printing all files when + --files-with-matches was added. Now, when both options are given, it prints + counts only for those files that have at least one match. (GNU grep just + prints the file name in this circumstance, but including the count seems + more useful - otherwise, why use --count?) Also ensured that the + combination -clh just lists non-zero counts, with no names. + +4. The long form of the pcregrep -F option was incorrectly implemented as + --fixed_strings instead of --fixed-strings. This is an incompatible change, + but it seems right to fix it, and I didn't think it was worth preserving + the old behaviour. + +5. The command line items --regex=pattern and --regexp=pattern were not + recognized by pcregrep, which required --regex pattern or --regexp pattern + (with a space rather than an '='). The man page documented the '=' forms, + which are compatible with GNU grep; these now work. + +6. No libpcreposix.pc file was created for pkg-config; there was just + libpcre.pc and libpcrecpp.pc. The omission has been rectified. + +7. Added #ifndef SUPPORT_UCP into the pcre_ucd.c module, to reduce its size + when UCP support is not needed, by modifying the Python script that + generates it from Unicode data files. This should not matter if the module + is correctly used as a library, but I received one complaint about 50K of + unwanted data. My guess is that the person linked everything into his + program rather than using a library. Anyway, it does no harm. + +8. A pattern such as /\x{123}{2,2}+/8 was incorrectly compiled; the trigger + was a minimum greater than 1 for a wide character in a possessive + repetition. The same bug could also affect patterns like /(\x{ff}{0,2})*/8 + which had an unlimited repeat of a nested, fixed maximum repeat of a wide + character. Chaos in the form of incorrect output or a compiling loop could + result. + +9. The restrictions on what a pattern can contain when partial matching is + requested for pcre_exec() have been removed. All patterns can now be + partially matched by this function. In addition, if there are at least two + slots in the offset vector, the offset of the earliest inspected character + for the match and the offset of the end of the subject are set in them when + PCRE_ERROR_PARTIAL is returned. + +10. Partial matching has been split into two forms: PCRE_PARTIAL_SOFT, which is + synonymous with PCRE_PARTIAL, for backwards compatibility, and + PCRE_PARTIAL_HARD, which causes a partial match to supersede a full match, + and may be more useful for multi-segment matching. + +11. Partial matching with pcre_exec() is now more intuitive. A partial match + used to be given if ever the end of the subject was reached; now it is + given only if matching could not proceed because another character was + needed. This makes a difference in some odd cases such as Z(*FAIL) with the + string "Z", which now yields "no match" instead of "partial match". In the + case of pcre_dfa_exec(), "no match" is given if every matching path for the + final character ended with (*FAIL). + +12. Restarting a match using pcre_dfa_exec() after a partial match did not work + if the pattern had a "must contain" character that was already found in the + earlier partial match, unless partial matching was again requested. For + example, with the pattern /dog.(body)?/, the "must contain" character is + "g". If the first part-match was for the string "dog", restarting with + "sbody" failed. This bug has been fixed. + +13. The string returned by pcre_dfa_exec() after a partial match has been + changed so that it starts at the first inspected character rather than the + first character of the match. This makes a difference only if the pattern + starts with a lookbehind assertion or \b or \B (\K is not supported by + pcre_dfa_exec()). It's an incompatible change, but it makes the two + matching functions compatible, and I think it's the right thing to do. + +14. Added a pcredemo man page, created automatically from the pcredemo.c file, + so that the demonstration program is easily available in environments where + PCRE has not been installed from source. + +15. Arranged to add -DPCRE_STATIC to cflags in libpcre.pc, libpcreposix.cp, + libpcrecpp.pc and pcre-config when PCRE is not compiled as a shared + library. + +16. Added REG_UNGREEDY to the pcreposix interface, at the request of a user. + It maps to PCRE_UNGREEDY. It is not, of course, POSIX-compatible, but it + is not the first non-POSIX option to be added. Clearly some people find + these options useful. + +17. If a caller to the POSIX matching function regexec() passes a non-zero + value for nmatch with a NULL value for pmatch, the value of + nmatch is forced to zero. + +18. RunGrepTest did not have a test for the availability of the -u option of + the diff command, as RunTest does. It now checks in the same way as + RunTest, and also checks for the -b option. + +19. If an odd number of negated classes containing just a single character + interposed, within parentheses, between a forward reference to a named + subpattern and the definition of the subpattern, compilation crashed with + an internal error, complaining that it could not find the referenced + subpattern. An example of a crashing pattern is /(?&A)(([^m])(?<A>))/. + [The bug was that it was starting one character too far in when skipping + over the character class, thus treating the ] as data rather than + terminating the class. This meant it could skip too much.] + +20. Added PCRE_NOTEMPTY_ATSTART in order to be able to correctly implement the + /g option in pcretest when the pattern contains \K, which makes it possible + to have an empty string match not at the start, even when the pattern is + anchored. Updated pcretest and pcredemo to use this option. + +21. If the maximum number of capturing subpatterns in a recursion was greater + than the maximum at the outer level, the higher number was returned, but + with unset values at the outer level. The correct (outer level) value is + now given. + +22. If (*ACCEPT) appeared inside capturing parentheses, previous releases of + PCRE did not set those parentheses (unlike Perl). I have now found a way to + make it do so. The string so far is captured, making this feature + compatible with Perl. + +23. The tests have been re-organized, adding tests 11 and 12, to make it + possible to check the Perl 5.10 features against Perl 5.10. + +24. Perl 5.10 allows subroutine calls in lookbehinds, as long as the subroutine + pattern matches a fixed length string. PCRE did not allow this; now it + does. Neither allows recursion. + +25. I finally figured out how to implement a request to provide the minimum + length of subject string that was needed in order to match a given pattern. + (It was back references and recursion that I had previously got hung up + on.) This code has now been added to pcre_study(); it finds a lower bound + to the length of subject needed. It is not necessarily the greatest lower + bound, but using it to avoid searching strings that are too short does give + some useful speed-ups. The value is available to calling programs via + pcre_fullinfo(). + +26. While implementing 25, I discovered to my embarrassment that pcretest had + not been passing the result of pcre_study() to pcre_dfa_exec(), so the + study optimizations had never been tested with that matching function. + Oops. What is worse, even when it was passed study data, there was a bug in + pcre_dfa_exec() that meant it never actually used it. Double oops. There + were also very few tests of studied patterns with pcre_dfa_exec(). + +27. If (?| is used to create subpatterns with duplicate numbers, they are now + allowed to have the same name, even if PCRE_DUPNAMES is not set. However, + on the other side of the coin, they are no longer allowed to have different + names, because these cannot be distinguished in PCRE, and this has caused + confusion. (This is a difference from Perl.) + +28. When duplicate subpattern names are present (necessarily with different + numbers, as required by 27 above), and a test is made by name in a + conditional pattern, either for a subpattern having been matched, or for + recursion in such a pattern, all the associated numbered subpatterns are + tested, and the overall condition is true if the condition is true for any + one of them. This is the way Perl works, and is also more like the way + testing by number works. + + +Version 7.9 11-Apr-09 +--------------------- + +1. When building with support for bzlib/zlib (pcregrep) and/or readline + (pcretest), all targets were linked against these libraries. This included + libpcre, libpcreposix, and libpcrecpp, even though they do not use these + libraries. This caused unwanted dependencies to be created. This problem + has been fixed, and now only pcregrep is linked with bzlib/zlib and only + pcretest is linked with readline. + +2. The "typedef int BOOL" in pcre_internal.h that was included inside the + "#ifndef FALSE" condition by an earlier change (probably 7.8/18) has been + moved outside it again, because FALSE and TRUE are already defined in AIX, + but BOOL is not. + +3. The pcre_config() function was treating the PCRE_MATCH_LIMIT and + PCRE_MATCH_LIMIT_RECURSION values as ints, when they should be long ints. + +4. The pcregrep documentation said spaces were inserted as well as colons (or + hyphens) following file names and line numbers when outputting matching + lines. This is not true; no spaces are inserted. I have also clarified the + wording for the --colour (or --color) option. + +5. In pcregrep, when --colour was used with -o, the list of matching strings + was not coloured; this is different to GNU grep, so I have changed it to be + the same. + +6. When --colo(u)r was used in pcregrep, only the first matching substring in + each matching line was coloured. Now it goes on to look for further matches + of any of the test patterns, which is the same behaviour as GNU grep. + +7. A pattern that could match an empty string could cause pcregrep to loop; it + doesn't make sense to accept an empty string match in pcregrep, so I have + locked it out (using PCRE's PCRE_NOTEMPTY option). By experiment, this + seems to be how GNU grep behaves. [But see later change 40 for release + 8.33.] + +8. The pattern (?(?=.*b)b|^) was incorrectly compiled as "match must be at + start or after a newline", because the conditional assertion was not being + correctly handled. The rule now is that both the assertion and what follows + in the first alternative must satisfy the test. + +9. If auto-callout was enabled in a pattern with a conditional group whose + condition was an assertion, PCRE could crash during matching, both with + pcre_exec() and pcre_dfa_exec(). + +10. The PCRE_DOLLAR_ENDONLY option was not working when pcre_dfa_exec() was + used for matching. + +11. Unicode property support in character classes was not working for + characters (bytes) greater than 127 when not in UTF-8 mode. + +12. Added the -M command line option to pcretest. + +14. Added the non-standard REG_NOTEMPTY option to the POSIX interface. + +15. Added the PCRE_NO_START_OPTIMIZE match-time option. + +16. Added comments and documentation about mis-use of no_arg in the C++ + wrapper. + +17. Implemented support for UTF-8 encoding in EBCDIC environments, a patch + from Martin Jerabek that uses macro names for all relevant character and + string constants. + +18. Added to pcre_internal.h two configuration checks: (a) If both EBCDIC and + SUPPORT_UTF8 are set, give an error; (b) If SUPPORT_UCP is set without + SUPPORT_UTF8, define SUPPORT_UTF8. The "configure" script handles both of + these, but not everybody uses configure. + +19. A conditional group that had only one branch was not being correctly + recognized as an item that could match an empty string. This meant that an + enclosing group might also not be so recognized, causing infinite looping + (and probably a segfault) for patterns such as ^"((?(?=[a])[^"])|b)*"$ + with the subject "ab", where knowledge that the repeated group can match + nothing is needed in order to break the loop. + +20. If a pattern that was compiled with callouts was matched using pcre_dfa_ + exec(), but without supplying a callout function, matching went wrong. + +21. If PCRE_ERROR_MATCHLIMIT occurred during a recursion, there was a memory + leak if the size of the offset vector was greater than 30. When the vector + is smaller, the saved offsets during recursion go onto a local stack + vector, but for larger vectors malloc() is used. It was failing to free + when the recursion yielded PCRE_ERROR_MATCH_LIMIT (or any other "abnormal" + error, in fact). + +22. There was a missing #ifdef SUPPORT_UTF8 round one of the variables in the + heapframe that is used only when UTF-8 support is enabled. This caused no + problem, but was untidy. + +23. Steven Van Ingelgem's patch to CMakeLists.txt to change the name + CMAKE_BINARY_DIR to PROJECT_BINARY_DIR so that it works when PCRE is + included within another project. + +24. Steven Van Ingelgem's patches to add more options to the CMake support, + slightly modified by me: + + (a) PCRE_BUILD_TESTS can be set OFF not to build the tests, including + not building pcregrep. + + (b) PCRE_BUILD_PCREGREP can be see OFF not to build pcregrep, but only + if PCRE_BUILD_TESTS is also set OFF, because the tests use pcregrep. + +25. Forward references, both numeric and by name, in patterns that made use of + duplicate group numbers, could behave incorrectly or give incorrect errors, + because when scanning forward to find the reference group, PCRE was not + taking into account the duplicate group numbers. A pattern such as + ^X(?3)(a)(?|(b)|(q))(Y) is an example. + +26. Changed a few more instances of "const unsigned char *" to USPTR, making + the feature of a custom pointer more persuasive (as requested by a user). + +27. Wrapped the definitions of fileno and isatty for Windows, which appear in + pcretest.c, inside #ifndefs, because it seems they are sometimes already + pre-defined. + +28. Added support for (*UTF8) at the start of a pattern. + +29. Arrange for flags added by the "release type" setting in CMake to be shown + in the configuration summary. + + +Version 7.8 05-Sep-08 +--------------------- + +1. Replaced UCP searching code with optimized version as implemented for Ad + Muncher (http://www.admuncher.com/) by Peter Kankowski. This uses a two- + stage table and inline lookup instead of a function, giving speed ups of 2 + to 5 times on some simple patterns that I tested. Permission was given to + distribute the MultiStage2.py script that generates the tables (it's not in + the tarball, but is in the Subversion repository). + +2. Updated the Unicode datatables to Unicode 5.1.0. This adds yet more + scripts. + +3. Change 12 for 7.7 introduced a bug in pcre_study() when a pattern contained + a group with a zero qualifier. The result of the study could be incorrect, + or the function might crash, depending on the pattern. + +4. Caseless matching was not working for non-ASCII characters in back + references. For example, /(\x{de})\1/8i was not matching \x{de}\x{fe}. + It now works when Unicode Property Support is available. + +5. In pcretest, an escape such as \x{de} in the data was always generating + a UTF-8 string, even in non-UTF-8 mode. Now it generates a single byte in + non-UTF-8 mode. If the value is greater than 255, it gives a warning about + truncation. + +6. Minor bugfix in pcrecpp.cc (change "" == ... to NULL == ...). + +7. Added two (int) casts to pcregrep when printing the difference of two + pointers, in case they are 64-bit values. + +8. Added comments about Mac OS X stack usage to the pcrestack man page and to + test 2 if it fails. + +9. Added PCRE_CALL_CONVENTION just before the names of all exported functions, + and a #define of that name to empty if it is not externally set. This is to + allow users of MSVC to set it if necessary. + +10. The PCRE_EXP_DEFN macro which precedes exported functions was missing from + the convenience functions in the pcre_get.c source file. + +11. An option change at the start of a pattern that had top-level alternatives + could cause overwriting and/or a crash. This command provoked a crash in + some environments: + + printf "/(?i)[\xc3\xa9\xc3\xbd]|[\xc3\xa9\xc3\xbdA]/8\n" | pcretest + + This potential security problem was recorded as CVE-2008-2371. + +12. For a pattern where the match had to start at the beginning or immediately + after a newline (e.g /.*anything/ without the DOTALL flag), pcre_exec() and + pcre_dfa_exec() could read past the end of the passed subject if there was + no match. To help with detecting such bugs (e.g. with valgrind), I modified + pcretest so that it places the subject at the end of its malloc-ed buffer. + +13. The change to pcretest in 12 above threw up a couple more cases when pcre_ + exec() might read past the end of the data buffer in UTF-8 mode. + +14. A similar bug to 7.3/2 existed when the PCRE_FIRSTLINE option was set and + the data contained the byte 0x85 as part of a UTF-8 character within its + first line. This applied both to normal and DFA matching. + +15. Lazy qualifiers were not working in some cases in UTF-8 mode. For example, + /^[^d]*?$/8 failed to match "abc". + +16. Added a missing copyright notice to pcrecpp_internal.h. + +17. Make it more clear in the documentation that values returned from + pcre_exec() in ovector are byte offsets, not character counts. + +18. Tidied a few places to stop certain compilers from issuing warnings. + +19. Updated the Virtual Pascal + BCC files to compile the latest v7.7, as + supplied by Stefan Weber. I made a further small update for 7.8 because + there is a change of source arrangements: the pcre_searchfuncs.c module is + replaced by pcre_ucd.c. + + +Version 7.7 07-May-08 +--------------------- + +1. Applied Craig's patch to sort out a long long problem: "If we can't convert + a string to a long long, pretend we don't even have a long long." This is + done by checking for the strtoq, strtoll, and _strtoi64 functions. + +2. Applied Craig's patch to pcrecpp.cc to restore ABI compatibility with + pre-7.6 versions, which defined a global no_arg variable instead of putting + it in the RE class. (See also #8 below.) + +3. Remove a line of dead code, identified by coverity and reported by Nuno + Lopes. + +4. Fixed two related pcregrep bugs involving -r with --include or --exclude: + + (1) The include/exclude patterns were being applied to the whole pathnames + of files, instead of just to the final components. + + (2) If there was more than one level of directory, the subdirectories were + skipped unless they satisfied the include/exclude conditions. This is + inconsistent with GNU grep (and could even be seen as contrary to the + pcregrep specification - which I improved to make it absolutely clear). + The action now is always to scan all levels of directory, and just + apply the include/exclude patterns to regular files. + +5. Added the --include_dir and --exclude_dir patterns to pcregrep, and used + --exclude_dir in the tests to avoid scanning .svn directories. + +6. Applied Craig's patch to the QuoteMeta function so that it escapes the + NUL character as backslash + 0 rather than backslash + NUL, because PCRE + doesn't support NULs in patterns. + +7. Added some missing "const"s to declarations of static tables in + pcre_compile.c and pcre_dfa_exec.c. + +8. Applied Craig's patch to pcrecpp.cc to fix a problem in OS X that was + caused by fix #2 above. (Subsequently also a second patch to fix the + first patch. And a third patch - this was a messy problem.) + +9. Applied Craig's patch to remove the use of push_back(). + +10. Applied Alan Lehotsky's patch to add REG_STARTEND support to the POSIX + matching function regexec(). + +11. Added support for the Oniguruma syntax \g<name>, \g<n>, \g'name', \g'n', + which, however, unlike Perl's \g{...}, are subroutine calls, not back + references. PCRE supports relative numbers with this syntax (I don't think + Oniguruma does). + +12. Previously, a group with a zero repeat such as (...){0} was completely + omitted from the compiled regex. However, this means that if the group + was called as a subroutine from elsewhere in the pattern, things went wrong + (an internal error was given). Such groups are now left in the compiled + pattern, with a new opcode that causes them to be skipped at execution + time. + +13. Added the PCRE_JAVASCRIPT_COMPAT option. This makes the following changes + to the way PCRE behaves: + + (a) A lone ] character is dis-allowed (Perl treats it as data). + + (b) A back reference to an unmatched subpattern matches an empty string + (Perl fails the current match path). + + (c) A data ] in a character class must be notated as \] because if the + first data character in a class is ], it defines an empty class. (In + Perl it is not possible to have an empty class.) The empty class [] + never matches; it forces failure and is equivalent to (*FAIL) or (?!). + The negative empty class [^] matches any one character, independently + of the DOTALL setting. + +14. A pattern such as /(?2)[]a()b](abc)/ which had a forward reference to a + non-existent subpattern following a character class starting with ']' and + containing () gave an internal compiling error instead of "reference to + non-existent subpattern". Fortunately, when the pattern did exist, the + compiled code was correct. (When scanning forwards to check for the + existence of the subpattern, it was treating the data ']' as terminating + the class, so got the count wrong. When actually compiling, the reference + was subsequently set up correctly.) + +15. The "always fail" assertion (?!) is optimzed to (*FAIL) by pcre_compile; + it was being rejected as not supported by pcre_dfa_exec(), even though + other assertions are supported. I have made pcre_dfa_exec() support + (*FAIL). + +16. The implementation of 13c above involved the invention of a new opcode, + OP_ALLANY, which is like OP_ANY but doesn't check the /s flag. Since /s + cannot be changed at match time, I realized I could make a small + improvement to matching performance by compiling OP_ALLANY instead of + OP_ANY for "." when DOTALL was set, and then removing the runtime tests + on the OP_ANY path. + +17. Compiling pcretest on Windows with readline support failed without the + following two fixes: (1) Make the unistd.h include conditional on + HAVE_UNISTD_H; (2) #define isatty and fileno as _isatty and _fileno. + +18. Changed CMakeLists.txt and cmake/FindReadline.cmake to arrange for the + ncurses library to be included for pcretest when ReadLine support is + requested, but also to allow for it to be overridden. This patch came from + Daniel Bergström. + +19. There was a typo in the file ucpinternal.h where f0_rangeflag was defined + as 0x00f00000 instead of 0x00800000. Luckily, this would not have caused + any errors with the current Unicode tables. Thanks to Peter Kankowski for + spotting this. + + +Version 7.6 28-Jan-08 +--------------------- + +1. A character class containing a very large number of characters with + codepoints greater than 255 (in UTF-8 mode, of course) caused a buffer + overflow. + +2. Patch to cut out the "long long" test in pcrecpp_unittest when + HAVE_LONG_LONG is not defined. + +3. Applied Christian Ehrlicher's patch to update the CMake build files to + bring them up to date and include new features. This patch includes: + + - Fixed PH's badly added libz and libbz2 support. + - Fixed a problem with static linking. + - Added pcredemo. [But later removed - see 7 below.] + - Fixed dftables problem and added an option. + - Added a number of HAVE_XXX tests, including HAVE_WINDOWS_H and + HAVE_LONG_LONG. + - Added readline support for pcretest. + - Added an listing of the option settings after cmake has run. + +4. A user submitted a patch to Makefile that makes it easy to create + "pcre.dll" under mingw when using Configure/Make. I added stuff to + Makefile.am that cause it to include this special target, without + affecting anything else. Note that the same mingw target plus all + the other distribution libraries and programs are now supported + when configuring with CMake (see 6 below) instead of with + Configure/Make. + +5. Applied Craig's patch that moves no_arg into the RE class in the C++ code. + This is an attempt to solve the reported problem "pcrecpp::no_arg is not + exported in the Windows port". It has not yet been confirmed that the patch + solves the problem, but it does no harm. + +6. Applied Sheri's patch to CMakeLists.txt to add NON_STANDARD_LIB_PREFIX and + NON_STANDARD_LIB_SUFFIX for dll names built with mingw when configured + with CMake, and also correct the comment about stack recursion. + +7. Remove the automatic building of pcredemo from the ./configure system and + from CMakeLists.txt. The whole idea of pcredemo.c is that it is an example + of a program that users should build themselves after PCRE is installed, so + building it automatically is not really right. What is more, it gave + trouble in some build environments. + +8. Further tidies to CMakeLists.txt from Sheri and Christian. + + +Version 7.5 10-Jan-08 +--------------------- + +1. Applied a patch from Craig: "This patch makes it possible to 'ignore' + values in parens when parsing an RE using the C++ wrapper." + +2. Negative specials like \S did not work in character classes in UTF-8 mode. + Characters greater than 255 were excluded from the class instead of being + included. + +3. The same bug as (2) above applied to negated POSIX classes such as + [:^space:]. + +4. PCRECPP_STATIC was referenced in pcrecpp_internal.h, but nowhere was it + defined or documented. It seems to have been a typo for PCRE_STATIC, so + I have changed it. + +5. The construct (?&) was not diagnosed as a syntax error (it referenced the + first named subpattern) and a construct such as (?&a) would reference the + first named subpattern whose name started with "a" (in other words, the + length check was missing). Both these problems are fixed. "Subpattern name + expected" is now given for (?&) (a zero-length name), and this patch also + makes it give the same error for \k'' (previously it complained that that + was a reference to a non-existent subpattern). + +6. The erroneous patterns (?+-a) and (?-+a) give different error messages; + this is right because (?- can be followed by option settings as well as by + digits. I have, however, made the messages clearer. + +7. Patterns such as (?(1)a|b) (a pattern that contains fewer subpatterns + than the number used in the conditional) now cause a compile-time error. + This is actually not compatible with Perl, which accepts such patterns, but + treats the conditional as always being FALSE (as PCRE used to), but it + seems to me that giving a diagnostic is better. + +8. Change "alphameric" to the more common word "alphanumeric" in comments + and messages. + +9. Fix two occurrences of "backslash" in comments that should have been + "backspace". + +10. Remove two redundant lines of code that can never be obeyed (their function + was moved elsewhere). + +11. The program that makes PCRE's Unicode character property table had a bug + which caused it to generate incorrect table entries for sequences of + characters that have the same character type, but are in different scripts. + It amalgamated them into a single range, with the script of the first of + them. In other words, some characters were in the wrong script. There were + thirteen such cases, affecting characters in the following ranges: + + U+002b0 - U+002c1 + U+0060c - U+0060d + U+0061e - U+00612 + U+0064b - U+0065e + U+0074d - U+0076d + U+01800 - U+01805 + U+01d00 - U+01d77 + U+01d9b - U+01dbf + U+0200b - U+0200f + U+030fc - U+030fe + U+03260 - U+0327f + U+0fb46 - U+0fbb1 + U+10450 - U+1049d + +12. The -o option (show only the matching part of a line) for pcregrep was not + compatible with GNU grep in that, if there was more than one match in a + line, it showed only the first of them. It now behaves in the same way as + GNU grep. + +13. If the -o and -v options were combined for pcregrep, it printed a blank + line for every non-matching line. GNU grep prints nothing, and pcregrep now + does the same. The return code can be used to tell if there were any + non-matching lines. + +14. Added --file-offsets and --line-offsets to pcregrep. + +15. The pattern (?=something)(?R) was not being diagnosed as a potentially + infinitely looping recursion. The bug was that positive lookaheads were not + being skipped when checking for a possible empty match (negative lookaheads + and both kinds of lookbehind were skipped). + +16. Fixed two typos in the Windows-only code in pcregrep.c, and moved the + inclusion of <windows.h> to before rather than after the definition of + INVALID_FILE_ATTRIBUTES (patch from David Byron). + +17. Specifying a possessive quantifier with a specific limit for a Unicode + character property caused pcre_compile() to compile bad code, which led at + runtime to PCRE_ERROR_INTERNAL (-14). Examples of patterns that caused this + are: /\p{Zl}{2,3}+/8 and /\p{Cc}{2}+/8. It was the possessive "+" that + caused the error; without that there was no problem. + +18. Added --enable-pcregrep-libz and --enable-pcregrep-libbz2. + +19. Added --enable-pcretest-libreadline. + +20. In pcrecpp.cc, the variable 'count' was incremented twice in + RE::GlobalReplace(). As a result, the number of replacements returned was + double what it should be. I removed one of the increments, but Craig sent a + later patch that removed the other one (the right fix) and added unit tests + that check the return values (which was not done before). + +21. Several CMake things: + + (1) Arranged that, when cmake is used on Unix, the libraries end up with + the names libpcre and libpcreposix, not just pcre and pcreposix. + + (2) The above change means that pcretest and pcregrep are now correctly + linked with the newly-built libraries, not previously installed ones. + + (3) Added PCRE_SUPPORT_LIBREADLINE, PCRE_SUPPORT_LIBZ, PCRE_SUPPORT_LIBBZ2. + +22. In UTF-8 mode, with newline set to "any", a pattern such as .*a.*=.b.* + crashed when matching a string such as a\x{2029}b (note that \x{2029} is a + UTF-8 newline character). The key issue is that the pattern starts .*; + this means that the match must be either at the beginning, or after a + newline. The bug was in the code for advancing after a failed match and + checking that the new position followed a newline. It was not taking + account of UTF-8 characters correctly. + +23. PCRE was behaving differently from Perl in the way it recognized POSIX + character classes. PCRE was not treating the sequence [:...:] as a + character class unless the ... were all letters. Perl, however, seems to + allow any characters between [: and :], though of course it rejects as + unknown any "names" that contain non-letters, because all the known class + names consist only of letters. Thus, Perl gives an error for [[:1234:]], + for example, whereas PCRE did not - it did not recognize a POSIX character + class. This seemed a bit dangerous, so the code has been changed to be + closer to Perl. The behaviour is not identical to Perl, because PCRE will + diagnose an unknown class for, for example, [[:l\ower:]] where Perl will + treat it as [[:lower:]]. However, PCRE does now give "unknown" errors where + Perl does, and where it didn't before. + +24. Rewrite so as to remove the single use of %n from pcregrep because in some + Windows environments %n is disabled by default. + + +Version 7.4 21-Sep-07 +--------------------- + +1. Change 7.3/28 was implemented for classes by looking at the bitmap. This + means that a class such as [\s] counted as "explicit reference to CR or + LF". That isn't really right - the whole point of the change was to try to + help when there was an actual mention of one of the two characters. So now + the change happens only if \r or \n (or a literal CR or LF) character is + encountered. + +2. The 32-bit options word was also used for 6 internal flags, but the numbers + of both had grown to the point where there were only 3 bits left. + Fortunately, there was spare space in the data structure, and so I have + moved the internal flags into a new 16-bit field to free up more option + bits. + +3. The appearance of (?J) at the start of a pattern set the DUPNAMES option, + but did not set the internal JCHANGED flag - either of these is enough to + control the way the "get" function works - but the PCRE_INFO_JCHANGED + facility is supposed to tell if (?J) was ever used, so now (?J) at the + start sets both bits. + +4. Added options (at build time, compile time, exec time) to change \R from + matching any Unicode line ending sequence to just matching CR, LF, or CRLF. + +5. doc/pcresyntax.html was missing from the distribution. + +6. Put back the definition of PCRE_ERROR_NULLWSLIMIT, for backward + compatibility, even though it is no longer used. + +7. Added macro for snprintf to pcrecpp_unittest.cc and also for strtoll and + strtoull to pcrecpp.cc to select the available functions in WIN32 when the + windows.h file is present (where different names are used). [This was + reversed later after testing - see 16 below.] + +8. Changed all #include <config.h> to #include "config.h". There were also + some further <pcre.h> cases that I changed to "pcre.h". + +9. When pcregrep was used with the --colour option, it missed the line ending + sequence off the lines that it output. + +10. It was pointed out to me that arrays of string pointers cause lots of + relocations when a shared library is dynamically loaded. A technique of + using a single long string with a table of offsets can drastically reduce + these. I have refactored PCRE in four places to do this. The result is + dramatic: + + Originally: 290 + After changing UCP table: 187 + After changing error message table: 43 + After changing table of "verbs" 36 + After changing table of Posix names 22 + + Thanks to the folks working on Gregex for glib for this insight. + +11. --disable-stack-for-recursion caused compiling to fail unless -enable- + unicode-properties was also set. + +12. Updated the tests so that they work when \R is defaulted to ANYCRLF. + +13. Added checks for ANY and ANYCRLF to pcrecpp.cc where it previously + checked only for CRLF. + +14. Added casts to pcretest.c to avoid compiler warnings. + +15. Added Craig's patch to various pcrecpp modules to avoid compiler warnings. + +16. Added Craig's patch to remove the WINDOWS_H tests, that were not working, + and instead check for _strtoi64 explicitly, and avoid the use of snprintf() + entirely. This removes changes made in 7 above. + +17. The CMake files have been updated, and there is now more information about + building with CMake in the NON-UNIX-USE document. + + +Version 7.3 28-Aug-07 +--------------------- + + 1. In the rejigging of the build system that eventually resulted in 7.1, the + line "#include <pcre.h>" was included in pcre_internal.h. The use of angle + brackets there is not right, since it causes compilers to look for an + installed pcre.h, not the version that is in the source that is being + compiled (which of course may be different). I have changed it back to: + + #include "pcre.h" + + I have a vague recollection that the change was concerned with compiling in + different directories, but in the new build system, that is taken care of + by the VPATH setting the Makefile. + + 2. The pattern .*$ when run in not-DOTALL UTF-8 mode with newline=any failed + when the subject happened to end in the byte 0x85 (e.g. if the last + character was \x{1ec5}). *Character* 0x85 is one of the "any" newline + characters but of course it shouldn't be taken as a newline when it is part + of another character. The bug was that, for an unlimited repeat of . in + not-DOTALL UTF-8 mode, PCRE was advancing by bytes rather than by + characters when looking for a newline. + + 3. A small performance improvement in the DOTALL UTF-8 mode .* case. + + 4. Debugging: adjusted the names of opcodes for different kinds of parentheses + in debug output. + + 5. Arrange to use "%I64d" instead of "%lld" and "%I64u" instead of "%llu" for + long printing in the pcrecpp unittest when running under MinGW. + + 6. ESC_K was left out of the EBCDIC table. + + 7. Change 7.0/38 introduced a new limit on the number of nested non-capturing + parentheses; I made it 1000, which seemed large enough. Unfortunately, the + limit also applies to "virtual nesting" when a pattern is recursive, and in + this case 1000 isn't so big. I have been able to remove this limit at the + expense of backing off one optimization in certain circumstances. Normally, + when pcre_exec() would call its internal match() function recursively and + immediately return the result unconditionally, it uses a "tail recursion" + feature to save stack. However, when a subpattern that can match an empty + string has an unlimited repetition quantifier, it no longer makes this + optimization. That gives it a stack frame in which to save the data for + checking that an empty string has been matched. Previously this was taken + from the 1000-entry workspace that had been reserved. So now there is no + explicit limit, but more stack is used. + + 8. Applied Daniel's patches to solve problems with the import/export magic + syntax that is required for Windows, and which was going wrong for the + pcreposix and pcrecpp parts of the library. These were overlooked when this + problem was solved for the main library. + + 9. There were some crude static tests to avoid integer overflow when computing + the size of patterns that contain repeated groups with explicit upper + limits. As the maximum quantifier is 65535, the maximum group length was + set at 30,000 so that the product of these two numbers did not overflow a + 32-bit integer. However, it turns out that people want to use groups that + are longer than 30,000 bytes (though not repeat them that many times). + Change 7.0/17 (the refactoring of the way the pattern size is computed) has + made it possible to implement the integer overflow checks in a much more + dynamic way, which I have now done. The artificial limitation on group + length has been removed - we now have only the limit on the total length of + the compiled pattern, which depends on the LINK_SIZE setting. + +10. Fixed a bug in the documentation for get/copy named substring when + duplicate names are permitted. If none of the named substrings are set, the + functions return PCRE_ERROR_NOSUBSTRING (7); the doc said they returned an + empty string. + +11. Because Perl interprets \Q...\E at a high level, and ignores orphan \E + instances, patterns such as [\Q\E] or [\E] or even [^\E] cause an error, + because the ] is interpreted as the first data character and the + terminating ] is not found. PCRE has been made compatible with Perl in this + regard. Previously, it interpreted [\Q\E] as an empty class, and [\E] could + cause memory overwriting. + +10. Like Perl, PCRE automatically breaks an unlimited repeat after an empty + string has been matched (to stop an infinite loop). It was not recognizing + a conditional subpattern that could match an empty string if that + subpattern was within another subpattern. For example, it looped when + trying to match (((?(1)X|))*) but it was OK with ((?(1)X|)*) where the + condition was not nested. This bug has been fixed. + +12. A pattern like \X?\d or \P{L}?\d in non-UTF-8 mode could cause a backtrack + past the start of the subject in the presence of bytes with the top bit + set, for example "\x8aBCD". + +13. Added Perl 5.10 experimental backtracking controls (*FAIL), (*F), (*PRUNE), + (*SKIP), (*THEN), (*COMMIT), and (*ACCEPT). + +14. Optimized (?!) to (*FAIL). + +15. Updated the test for a valid UTF-8 string to conform to the later RFC 3629. + This restricts code points to be within the range 0 to 0x10FFFF, excluding + the "low surrogate" sequence 0xD800 to 0xDFFF. Previously, PCRE allowed the + full range 0 to 0x7FFFFFFF, as defined by RFC 2279. Internally, it still + does: it's just the validity check that is more restrictive. + +16. Inserted checks for integer overflows during escape sequence (backslash) + processing, and also fixed erroneous offset values for syntax errors during + backslash processing. + +17. Fixed another case of looking too far back in non-UTF-8 mode (cf 12 above) + for patterns like [\PPP\x8a]{1,}\x80 with the subject "A\x80". + +18. An unterminated class in a pattern like (?1)\c[ with a "forward reference" + caused an overrun. + +19. A pattern like (?:[\PPa*]*){8,} which had an "extended class" (one with + something other than just ASCII characters) inside a group that had an + unlimited repeat caused a loop at compile time (while checking to see + whether the group could match an empty string). + +20. Debugging a pattern containing \p or \P could cause a crash. For example, + [\P{Any}] did so. (Error in the code for printing property names.) + +21. An orphan \E inside a character class could cause a crash. + +22. A repeated capturing bracket such as (A)? could cause a wild memory + reference during compilation. + +23. There are several functions in pcre_compile() that scan along a compiled + expression for various reasons (e.g. to see if it's fixed length for look + behind). There were bugs in these functions when a repeated \p or \P was + present in the pattern. These operators have additional parameters compared + with \d, etc, and these were not being taken into account when moving along + the compiled data. Specifically: + + (a) A item such as \p{Yi}{3} in a lookbehind was not treated as fixed + length. + + (b) An item such as \pL+ within a repeated group could cause crashes or + loops. + + (c) A pattern such as \p{Yi}+(\P{Yi}+)(?1) could give an incorrect + "reference to non-existent subpattern" error. + + (d) A pattern like (\P{Yi}{2}\277)? could loop at compile time. + +24. A repeated \S or \W in UTF-8 mode could give wrong answers when multibyte + characters were involved (for example /\S{2}/8g with "A\x{a3}BC"). + +25. Using pcregrep in multiline, inverted mode (-Mv) caused it to loop. + +26. Patterns such as [\P{Yi}A] which include \p or \P and just one other + character were causing crashes (broken optimization). + +27. Patterns such as (\P{Yi}*\277)* (group with possible zero repeat containing + \p or \P) caused a compile-time loop. + +28. More problems have arisen in unanchored patterns when CRLF is a valid line + break. For example, the unstudied pattern [\r\n]A does not match the string + "\r\nA" because change 7.0/46 below moves the current point on by two + characters after failing to match at the start. However, the pattern \nA + *does* match, because it doesn't start till \n, and if [\r\n]A is studied, + the same is true. There doesn't seem any very clean way out of this, but + what I have chosen to do makes the common cases work: PCRE now takes note + of whether there can be an explicit match for \r or \n anywhere in the + pattern, and if so, 7.0/46 no longer applies. As part of this change, + there's a new PCRE_INFO_HASCRORLF option for finding out whether a compiled + pattern has explicit CR or LF references. + +29. Added (*CR) etc for changing newline setting at start of pattern. + + +Version 7.2 19-Jun-07 +--------------------- + + 1. If the fr_FR locale cannot be found for test 3, try the "french" locale, + which is apparently normally available under Windows. + + 2. Re-jig the pcregrep tests with different newline settings in an attempt + to make them independent of the local environment's newline setting. + + 3. Add code to configure.ac to remove -g from the CFLAGS default settings. + + 4. Some of the "internals" tests were previously cut out when the link size + was not 2, because the output contained actual offsets. The recent new + "Z" feature of pcretest means that these can be cut out, making the tests + usable with all link sizes. + + 5. Implemented Stan Switzer's goto replacement for longjmp() when not using + stack recursion. This gives a massive performance boost under BSD, but just + a small improvement under Linux. However, it saves one field in the frame + in all cases. + + 6. Added more features from the forthcoming Perl 5.10: + + (a) (?-n) (where n is a string of digits) is a relative subroutine or + recursion call. It refers to the nth most recently opened parentheses. + + (b) (?+n) is also a relative subroutine call; it refers to the nth next + to be opened parentheses. + + (c) Conditions that refer to capturing parentheses can be specified + relatively, for example, (?(-2)... or (?(+3)... + + (d) \K resets the start of the current match so that everything before + is not part of it. + + (e) \k{name} is synonymous with \k<name> and \k'name' (.NET compatible). + + (f) \g{name} is another synonym - part of Perl 5.10's unification of + reference syntax. + + (g) (?| introduces a group in which the numbering of parentheses in each + alternative starts with the same number. + + (h) \h, \H, \v, and \V match horizontal and vertical whitespace. + + 7. Added two new calls to pcre_fullinfo(): PCRE_INFO_OKPARTIAL and + PCRE_INFO_JCHANGED. + + 8. A pattern such as (.*(.)?)* caused pcre_exec() to fail by either not + terminating or by crashing. Diagnosed by Viktor Griph; it was in the code + for detecting groups that can match an empty string. + + 9. A pattern with a very large number of alternatives (more than several + hundred) was running out of internal workspace during the pre-compile + phase, where pcre_compile() figures out how much memory will be needed. A + bit of new cunning has reduced the workspace needed for groups with + alternatives. The 1000-alternative test pattern now uses 12 bytes of + workspace instead of running out of the 4096 that are available. + +10. Inserted some missing (unsigned int) casts to get rid of compiler warnings. + +11. Applied patch from Google to remove an optimization that didn't quite work. + The report of the bug said: + + pcrecpp::RE("a*").FullMatch("aaa") matches, while + pcrecpp::RE("a*?").FullMatch("aaa") does not, and + pcrecpp::RE("a*?\\z").FullMatch("aaa") does again. + +12. If \p or \P was used in non-UTF-8 mode on a character greater than 127 + it matched the wrong number of bytes. + + +Version 7.1 24-Apr-07 +--------------------- + + 1. Applied Bob Rossi and Daniel G's patches to convert the build system to one + that is more "standard", making use of automake and other Autotools. There + is some re-arrangement of the files and adjustment of comments consequent + on this. + + 2. Part of the patch fixed a problem with the pcregrep tests. The test of -r + for recursive directory scanning broke on some systems because the files + are not scanned in any specific order and on different systems the order + was different. A call to "sort" has been inserted into RunGrepTest for the + approprate test as a short-term fix. In the longer term there may be an + alternative. + + 3. I had an email from Eric Raymond about problems translating some of PCRE's + man pages to HTML (despite the fact that I distribute HTML pages, some + people do their own conversions for various reasons). The problems + concerned the use of low-level troff macros .br and .in. I have therefore + removed all such uses from the man pages (some were redundant, some could + be replaced by .nf/.fi pairs). The 132html script that I use to generate + HTML has been updated to handle .nf/.fi and to complain if it encounters + .br or .in. + + 4. Updated comments in configure.ac that get placed in config.h.in and also + arranged for config.h to be included in the distribution, with the name + config.h.generic, for the benefit of those who have to compile without + Autotools (compare pcre.h, which is now distributed as pcre.h.generic). + + 5. Updated the support (such as it is) for Virtual Pascal, thanks to Stefan + Weber: (1) pcre_internal.h was missing some function renames; (2) updated + makevp.bat for the current PCRE, using the additional files + makevp_c.txt, makevp_l.txt, and pcregexp.pas. + + 6. A Windows user reported a minor discrepancy with test 2, which turned out + to be caused by a trailing space on an input line that had got lost in his + copy. The trailing space was an accident, so I've just removed it. + + 7. Add -Wl,-R... flags in pcre-config.in for *BSD* systems, as I'm told + that is needed. + + 8. Mark ucp_table (in ucptable.h) and ucp_gentype (in pcre_ucp_searchfuncs.c) + as "const" (a) because they are and (b) because it helps the PHP + maintainers who have recently made a script to detect big data structures + in the php code that should be moved to the .rodata section. I remembered + to update Builducptable as well, so it won't revert if ucptable.h is ever + re-created. + + 9. Added some extra #ifdef SUPPORT_UTF8 conditionals into pcretest.c, + pcre_printint.src, pcre_compile.c, pcre_study.c, and pcre_tables.c, in + order to be able to cut out the UTF-8 tables in the latter when UTF-8 + support is not required. This saves 1.5-2K of code, which is important in + some applications. + + Later: more #ifdefs are needed in pcre_ord2utf8.c and pcre_valid_utf8.c + so as not to refer to the tables, even though these functions will never be + called when UTF-8 support is disabled. Otherwise there are problems with a + shared library. + +10. Fixed two bugs in the emulated memmove() function in pcre_internal.h: + + (a) It was defining its arguments as char * instead of void *. + + (b) It was assuming that all moves were upwards in memory; this was true + a long time ago when I wrote it, but is no longer the case. + + The emulated memove() is provided for those environments that have neither + memmove() nor bcopy(). I didn't think anyone used it these days, but that + is clearly not the case, as these two bugs were recently reported. + +11. The script PrepareRelease is now distributed: it calls 132html, CleanTxt, + and Detrail to create the HTML documentation, the .txt form of the man + pages, and it removes trailing spaces from listed files. It also creates + pcre.h.generic and config.h.generic from pcre.h and config.h. In the latter + case, it wraps all the #defines with #ifndefs. This script should be run + before "make dist". + +12. Fixed two fairly obscure bugs concerned with quantified caseless matching + with Unicode property support. + + (a) For a maximizing quantifier, if the two different cases of the + character were of different lengths in their UTF-8 codings (there are + some cases like this - I found 11), and the matching function had to + back up over a mixture of the two cases, it incorrectly assumed they + were both the same length. + + (b) When PCRE was configured to use the heap rather than the stack for + recursion during matching, it was not correctly preserving the data for + the other case of a UTF-8 character when checking ahead for a match + while processing a minimizing repeat. If the check also involved + matching a wide character, but failed, corruption could cause an + erroneous result when trying to check for a repeat of the original + character. + +13. Some tidying changes to the testing mechanism: + + (a) The RunTest script now detects the internal link size and whether there + is UTF-8 and UCP support by running ./pcretest -C instead of relying on + values substituted by "configure". (The RunGrepTest script already did + this for UTF-8.) The configure.ac script no longer substitutes the + relevant variables. + + (b) The debugging options /B and /D in pcretest show the compiled bytecode + with length and offset values. This means that the output is different + for different internal link sizes. Test 2 is skipped for link sizes + other than 2 because of this, bypassing the problem. Unfortunately, + there was also a test in test 3 (the locale tests) that used /B and + failed for link sizes other than 2. Rather than cut the whole test out, + I have added a new /Z option to pcretest that replaces the length and + offset values with spaces. This is now used to make test 3 independent + of link size. (Test 2 will be tidied up later.) + +14. If erroroffset was passed as NULL to pcre_compile, it provoked a + segmentation fault instead of returning the appropriate error message. + +15. In multiline mode when the newline sequence was set to "any", the pattern + ^$ would give a match between the \r and \n of a subject such as "A\r\nB". + This doesn't seem right; it now treats the CRLF combination as the line + ending, and so does not match in that case. It's only a pattern such as ^$ + that would hit this one: something like ^ABC$ would have failed after \r + and then tried again after \r\n. + +16. Changed the comparison command for RunGrepTest from "diff -u" to "diff -ub" + in an attempt to make files that differ only in their line terminators + compare equal. This works on Linux. + +17. Under certain error circumstances pcregrep might try to free random memory + as it exited. This is now fixed, thanks to valgrind. + +19. In pcretest, if the pattern /(?m)^$/g<any> was matched against the string + "abc\r\n\r\n", it found an unwanted second match after the second \r. This + was because its rules for how to advance for /g after matching an empty + string at the end of a line did not allow for this case. They now check for + it specially. + +20. pcretest is supposed to handle patterns and data of any length, by + extending its buffers when necessary. It was getting this wrong when the + buffer for a data line had to be extended. + +21. Added PCRE_NEWLINE_ANYCRLF which is like ANY, but matches only CR, LF, or + CRLF as a newline sequence. + +22. Code for handling Unicode properties in pcre_dfa_exec() wasn't being cut + out by #ifdef SUPPORT_UCP. This did no harm, as it could never be used, but + I have nevertheless tidied it up. + +23. Added some casts to kill warnings from HP-UX ia64 compiler. + +24. Added a man page for pcre-config. + + +Version 7.0 19-Dec-06 +--------------------- + + 1. Fixed a signed/unsigned compiler warning in pcre_compile.c, shown up by + moving to gcc 4.1.1. + + 2. The -S option for pcretest uses setrlimit(); I had omitted to #include + sys/time.h, which is documented as needed for this function. It doesn't + seem to matter on Linux, but it showed up on some releases of OS X. + + 3. It seems that there are systems where bytes whose values are greater than + 127 match isprint() in the "C" locale. The "C" locale should be the + default when a C program starts up. In most systems, only ASCII printing + characters match isprint(). This difference caused the output from pcretest + to vary, making some of the tests fail. I have changed pcretest so that: + + (a) When it is outputting text in the compiled version of a pattern, bytes + other than 32-126 are always shown as hex escapes. + + (b) When it is outputting text that is a matched part of a subject string, + it does the same, unless a different locale has been set for the match + (using the /L modifier). In this case, it uses isprint() to decide. + + 4. Fixed a major bug that caused incorrect computation of the amount of memory + required for a compiled pattern when options that changed within the + pattern affected the logic of the preliminary scan that determines the + length. The relevant options are -x, and -i in UTF-8 mode. The result was + that the computed length was too small. The symptoms of this bug were + either the PCRE error "internal error: code overflow" from pcre_compile(), + or a glibc crash with a message such as "pcretest: free(): invalid next + size (fast)". Examples of patterns that provoked this bug (shown in + pcretest format) are: + + /(?-x: )/x + /(?x)(?-x: \s*#\s*)/ + /((?i)[\x{c0}])/8 + /(?i:[\x{c0}])/8 + + HOWEVER: Change 17 below makes this fix obsolete as the memory computation + is now done differently. + + 5. Applied patches from Google to: (a) add a QuoteMeta function to the C++ + wrapper classes; (b) implement a new function in the C++ scanner that is + more efficient than the old way of doing things because it avoids levels of + recursion in the regex matching; (c) add a paragraph to the documentation + for the FullMatch() function. + + 6. The escape sequence \n was being treated as whatever was defined as + "newline". Not only was this contrary to the documentation, which states + that \n is character 10 (hex 0A), but it also went horribly wrong when + "newline" was defined as CRLF. This has been fixed. + + 7. In pcre_dfa_exec.c the value of an unsigned integer (the variable called c) + was being set to -1 for the "end of line" case (supposedly a value that no + character can have). Though this value is never used (the check for end of + line is "zero bytes in current character"), it caused compiler complaints. + I've changed it to 0xffffffff. + + 8. In pcre_version.c, the version string was being built by a sequence of + C macros that, in the event of PCRE_PRERELEASE being defined as an empty + string (as it is for production releases) called a macro with an empty + argument. The C standard says the result of this is undefined. The gcc + compiler treats it as an empty string (which was what was wanted) but it is + reported that Visual C gives an error. The source has been hacked around to + avoid this problem. + + 9. On the advice of a Windows user, included <io.h> and <fcntl.h> in Windows + builds of pcretest, and changed the call to _setmode() to use _O_BINARY + instead of 0x8000. Made all the #ifdefs test both _WIN32 and WIN32 (not all + of them did). + +10. Originally, pcretest opened its input and output without "b"; then I was + told that "b" was needed in some environments, so it was added for release + 5.0 to both the input and output. (It makes no difference on Unix-like + systems.) Later I was told that it is wrong for the input on Windows. I've + now abstracted the modes into two macros, to make it easier to fiddle with + them, and removed "b" from the input mode under Windows. + +11. Added pkgconfig support for the C++ wrapper library, libpcrecpp. + +12. Added -help and --help to pcretest as an official way of being reminded + of the options. + +13. Removed some redundant semicolons after macro calls in pcrecpparg.h.in + and pcrecpp.cc because they annoy compilers at high warning levels. + +14. A bit of tidying/refactoring in pcre_exec.c in the main bumpalong loop. + +15. Fixed an occurrence of == in configure.ac that should have been = (shell + scripts are not C programs :-) and which was not noticed because it works + on Linux. + +16. pcretest is supposed to handle any length of pattern and data line (as one + line or as a continued sequence of lines) by extending its input buffer if + necessary. This feature was broken for very long pattern lines, leading to + a string of junk being passed to pcre_compile() if the pattern was longer + than about 50K. + +17. I have done a major re-factoring of the way pcre_compile() computes the + amount of memory needed for a compiled pattern. Previously, there was code + that made a preliminary scan of the pattern in order to do this. That was + OK when PCRE was new, but as the facilities have expanded, it has become + harder and harder to keep it in step with the real compile phase, and there + have been a number of bugs (see for example, 4 above). I have now found a + cunning way of running the real compile function in a "fake" mode that + enables it to compute how much memory it would need, while actually only + ever using a few hundred bytes of working memory and without too many + tests of the mode. This should make future maintenance and development + easier. A side effect of this work is that the limit of 200 on the nesting + depth of parentheses has been removed (though this was never a serious + limitation, I suspect). However, there is a downside: pcre_compile() now + runs more slowly than before (30% or more, depending on the pattern). I + hope this isn't a big issue. There is no effect on runtime performance. + +18. Fixed a minor bug in pcretest: if a pattern line was not terminated by a + newline (only possible for the last line of a file) and it was a + pattern that set a locale (followed by /Lsomething), pcretest crashed. + +19. Added additional timing features to pcretest. (1) The -tm option now times + matching only, not compiling. (2) Both -t and -tm can be followed, as a + separate command line item, by a number that specifies the number of + repeats to use when timing. The default is 50000; this gives better + precision, but takes uncomfortably long for very large patterns. + +20. Extended pcre_study() to be more clever in cases where a branch of a + subpattern has no definite first character. For example, (a*|b*)[cd] would + previously give no result from pcre_study(). Now it recognizes that the + first character must be a, b, c, or d. + +21. There was an incorrect error "recursive call could loop indefinitely" if + a subpattern (or the entire pattern) that was being tested for matching an + empty string contained only one non-empty item after a nested subpattern. + For example, the pattern (?>\x{100}*)\d(?R) provoked this error + incorrectly, because the \d was being skipped in the check. + +22. The pcretest program now has a new pattern option /B and a command line + option -b, which is equivalent to adding /B to every pattern. This causes + it to show the compiled bytecode, without the additional information that + -d shows. The effect of -d is now the same as -b with -i (and similarly, /D + is the same as /B/I). + +23. A new optimization is now able automatically to treat some sequences such + as a*b as a*+b. More specifically, if something simple (such as a character + or a simple class like \d) has an unlimited quantifier, and is followed by + something that cannot possibly match the quantified thing, the quantifier + is automatically "possessified". + +24. A recursive reference to a subpattern whose number was greater than 39 + went wrong under certain circumstances in UTF-8 mode. This bug could also + have affected the operation of pcre_study(). + +25. Realized that a little bit of performance could be had by replacing + (c & 0xc0) == 0xc0 with c >= 0xc0 when processing UTF-8 characters. + +26. Timing data from pcretest is now shown to 4 decimal places instead of 3. + +27. Possessive quantifiers such as a++ were previously implemented by turning + them into atomic groups such as ($>a+). Now they have their own opcodes, + which improves performance. This includes the automatically created ones + from 23 above. + +28. A pattern such as (?=(\w+))\1: which simulates an atomic group using a + lookahead was broken if it was not anchored. PCRE was mistakenly expecting + the first matched character to be a colon. This applied both to named and + numbered groups. + +29. The ucpinternal.h header file was missing its idempotency #ifdef. + +30. I was sent a "project" file called libpcre.a.dev which I understand makes + building PCRE on Windows easier, so I have included it in the distribution. + +31. There is now a check in pcretest against a ridiculously large number being + returned by pcre_exec() or pcre_dfa_exec(). If this happens in a /g or /G + loop, the loop is abandoned. + +32. Forward references to subpatterns in conditions such as (?(2)...) where + subpattern 2 is defined later cause pcre_compile() to search forwards in + the pattern for the relevant set of parentheses. This search went wrong + when there were unescaped parentheses in a character class, parentheses + escaped with \Q...\E, or parentheses in a #-comment in /x mode. + +33. "Subroutine" calls and backreferences were previously restricted to + referencing subpatterns earlier in the regex. This restriction has now + been removed. + +34. Added a number of extra features that are going to be in Perl 5.10. On the + whole, these are just syntactic alternatives for features that PCRE had + previously implemented using the Python syntax or my own invention. The + other formats are all retained for compatibility. + + (a) Named groups can now be defined as (?<name>...) or (?'name'...) as well + as (?P<name>...). The new forms, as well as being in Perl 5.10, are + also .NET compatible. + + (b) A recursion or subroutine call to a named group can now be defined as + (?&name) as well as (?P>name). + + (c) A backreference to a named group can now be defined as \k<name> or + \k'name' as well as (?P=name). The new forms, as well as being in Perl + 5.10, are also .NET compatible. + + (d) A conditional reference to a named group can now use the syntax + (?(<name>) or (?('name') as well as (?(name). + + (e) A "conditional group" of the form (?(DEFINE)...) can be used to define + groups (named and numbered) that are never evaluated inline, but can be + called as "subroutines" from elsewhere. In effect, the DEFINE condition + is always false. There may be only one alternative in such a group. + + (f) A test for recursion can be given as (?(R1).. or (?(R&name)... as well + as the simple (?(R). The condition is true only if the most recent + recursion is that of the given number or name. It does not search out + through the entire recursion stack. + + (g) The escape \gN or \g{N} has been added, where N is a positive or + negative number, specifying an absolute or relative reference. + +35. Tidied to get rid of some further signed/unsigned compiler warnings and + some "unreachable code" warnings. + +36. Updated the Unicode property tables to Unicode version 5.0.0. Amongst other + things, this adds five new scripts. + +37. Perl ignores orphaned \E escapes completely. PCRE now does the same. + There were also incompatibilities regarding the handling of \Q..\E inside + character classes, for example with patterns like [\Qa\E-\Qz\E] where the + hyphen was adjacent to \Q or \E. I hope I've cleared all this up now. + +38. Like Perl, PCRE detects when an indefinitely repeated parenthesized group + matches an empty string, and forcibly breaks the loop. There were bugs in + this code in non-simple cases. For a pattern such as ^(a()*)* matched + against aaaa the result was just "a" rather than "aaaa", for example. Two + separate and independent bugs (that affected different cases) have been + fixed. + +39. Refactored the code to abolish the use of different opcodes for small + capturing bracket numbers. This is a tidy that I avoided doing when I + removed the limit on the number of capturing brackets for 3.5 back in 2001. + The new approach is not only tidier, it makes it possible to reduce the + memory needed to fix the previous bug (38). + +40. Implemented PCRE_NEWLINE_ANY to recognize any of the Unicode newline + sequences (http://unicode.org/unicode/reports/tr18/) as "newline" when + processing dot, circumflex, or dollar metacharacters, or #-comments in /x + mode. + +41. Add \R to match any Unicode newline sequence, as suggested in the Unicode + report. + +42. Applied patch, originally from Ari Pollak, modified by Google, to allow + copy construction and assignment in the C++ wrapper. + +43. Updated pcregrep to support "--newline=any". In the process, I fixed a + couple of bugs that could have given wrong results in the "--newline=crlf" + case. + +44. Added a number of casts and did some reorganization of signed/unsigned int + variables following suggestions from Dair Grant. Also renamed the variable + "this" as "item" because it is a C++ keyword. + +45. Arranged for dftables to add + + #include "pcre_internal.h" + + to pcre_chartables.c because without it, gcc 4.x may remove the array + definition from the final binary if PCRE is built into a static library and + dead code stripping is activated. + +46. For an unanchored pattern, if a match attempt fails at the start of a + newline sequence, and the newline setting is CRLF or ANY, and the next two + characters are CRLF, advance by two characters instead of one. + + +Version 6.7 04-Jul-06 +--------------------- + + 1. In order to handle tests when input lines are enormously long, pcretest has + been re-factored so that it automatically extends its buffers when + necessary. The code is crude, but this _is_ just a test program. The + default size has been increased from 32K to 50K. + + 2. The code in pcre_study() was using the value of the re argument before + testing it for NULL. (Of course, in any sensible call of the function, it + won't be NULL.) + + 3. The memmove() emulation function in pcre_internal.h, which is used on + systems that lack both memmove() and bcopy() - that is, hardly ever - + was missing a "static" storage class specifier. + + 4. When UTF-8 mode was not set, PCRE looped when compiling certain patterns + containing an extended class (one that cannot be represented by a bitmap + because it contains high-valued characters or Unicode property items, e.g. + [\pZ]). Almost always one would set UTF-8 mode when processing such a + pattern, but PCRE should not loop if you do not (it no longer does). + [Detail: two cases were found: (a) a repeated subpattern containing an + extended class; (b) a recursive reference to a subpattern that followed a + previous extended class. It wasn't skipping over the extended class + correctly when UTF-8 mode was not set.] + + 5. A negated single-character class was not being recognized as fixed-length + in lookbehind assertions such as (?<=[^f]), leading to an incorrect + compile error "lookbehind assertion is not fixed length". + + 6. The RunPerlTest auxiliary script was showing an unexpected difference + between PCRE and Perl for UTF-8 tests. It turns out that it is hard to + write a Perl script that can interpret lines of an input file either as + byte characters or as UTF-8, which is what "perltest" was being required to + do for the non-UTF-8 and UTF-8 tests, respectively. Essentially what you + can't do is switch easily at run time between having the "use utf8;" pragma + or not. In the end, I fudged it by using the RunPerlTest script to insert + "use utf8;" explicitly for the UTF-8 tests. + + 7. In multiline (/m) mode, PCRE was matching ^ after a terminating newline at + the end of the subject string, contrary to the documentation and to what + Perl does. This was true of both matching functions. Now it matches only at + the start of the subject and immediately after *internal* newlines. + + 8. A call of pcre_fullinfo() from pcretest to get the option bits was passing + a pointer to an int instead of a pointer to an unsigned long int. This + caused problems on 64-bit systems. + + 9. Applied a patch from the folks at Google to pcrecpp.cc, to fix "another + instance of the 'standard' template library not being so standard". + +10. There was no check on the number of named subpatterns nor the maximum + length of a subpattern name. The product of these values is used to compute + the size of the memory block for a compiled pattern. By supplying a very + long subpattern name and a large number of named subpatterns, the size + computation could be caused to overflow. This is now prevented by limiting + the length of names to 32 characters, and the number of named subpatterns + to 10,000. + +11. Subpatterns that are repeated with specific counts have to be replicated in + the compiled pattern. The size of memory for this was computed from the + length of the subpattern and the repeat count. The latter is limited to + 65535, but there was no limit on the former, meaning that integer overflow + could in principle occur. The compiled length of a repeated subpattern is + now limited to 30,000 bytes in order to prevent this. + +12. Added the optional facility to have named substrings with the same name. + +13. Added the ability to use a named substring as a condition, using the + Python syntax: (?(name)yes|no). This overloads (?(R)... and names that + are numbers (not recommended). Forward references are permitted. + +14. Added forward references in named backreferences (if you see what I mean). + +15. In UTF-8 mode, with the PCRE_DOTALL option set, a quantified dot in the + pattern could run off the end of the subject. For example, the pattern + "(?s)(.{1,5})"8 did this with the subject "ab". + +16. If PCRE_DOTALL or PCRE_MULTILINE were set, pcre_dfa_exec() behaved as if + PCRE_CASELESS was set when matching characters that were quantified with ? + or *. + +17. A character class other than a single negated character that had a minimum + but no maximum quantifier - for example [ab]{6,} - was not handled + correctly by pce_dfa_exec(). It would match only one character. + +18. A valid (though odd) pattern that looked like a POSIX character + class but used an invalid character after [ (for example [[,abc,]]) caused + pcre_compile() to give the error "Failed: internal error: code overflow" or + in some cases to crash with a glibc free() error. This could even happen if + the pattern terminated after [[ but there just happened to be a sequence of + letters, a binary zero, and a closing ] in the memory that followed. + +19. Perl's treatment of octal escapes in the range \400 to \777 has changed + over the years. Originally (before any Unicode support), just the bottom 8 + bits were taken. Thus, for example, \500 really meant \100. Nowadays the + output from "man perlunicode" includes this: + + The regular expression compiler produces polymorphic opcodes. That + is, the pattern adapts to the data and automatically switches to + the Unicode character scheme when presented with Unicode data--or + instead uses a traditional byte scheme when presented with byte + data. + + Sadly, a wide octal escape does not cause a switch, and in a string with + no other multibyte characters, these octal escapes are treated as before. + Thus, in Perl, the pattern /\500/ actually matches \100 but the pattern + /\500|\x{1ff}/ matches \500 or \777 because the whole thing is treated as a + Unicode string. + + I have not perpetrated such confusion in PCRE. Up till now, it took just + the bottom 8 bits, as in old Perl. I have now made octal escapes with + values greater than \377 illegal in non-UTF-8 mode. In UTF-8 mode they + translate to the appropriate multibyte character. + +29. Applied some refactoring to reduce the number of warnings from Microsoft + and Borland compilers. This has included removing the fudge introduced + seven years ago for the OS/2 compiler (see 2.02/2 below) because it caused + a warning about an unused variable. + +21. PCRE has not included VT (character 0x0b) in the set of whitespace + characters since release 4.0, because Perl (from release 5.004) does not. + [Or at least, is documented not to: some releases seem to be in conflict + with the documentation.] However, when a pattern was studied with + pcre_study() and all its branches started with \s, PCRE still included VT + as a possible starting character. Of course, this did no harm; it just + caused an unnecessary match attempt. + +22. Removed a now-redundant internal flag bit that recorded the fact that case + dependency changed within the pattern. This was once needed for "required + byte" processing, but is no longer used. This recovers a now-scarce options + bit. Also moved the least significant internal flag bit to the most- + significant bit of the word, which was not previously used (hangover from + the days when it was an int rather than a uint) to free up another bit for + the future. + +23. Added support for CRLF line endings as well as CR and LF. As well as the + default being selectable at build time, it can now be changed at runtime + via the PCRE_NEWLINE_xxx flags. There are now options for pcregrep to + specify that it is scanning data with non-default line endings. + +24. Changed the definition of CXXLINK to make it agree with the definition of + LINK in the Makefile, by replacing LDFLAGS to CXXFLAGS. + +25. Applied Ian Taylor's patches to avoid using another stack frame for tail + recursions. This makes a big different to stack usage for some patterns. + +26. If a subpattern containing a named recursion or subroutine reference such + as (?P>B) was quantified, for example (xxx(?P>B)){3}, the calculation of + the space required for the compiled pattern went wrong and gave too small a + value. Depending on the environment, this could lead to "Failed: internal + error: code overflow at offset 49" or "glibc detected double free or + corruption" errors. + +27. Applied patches from Google (a) to support the new newline modes and (b) to + advance over multibyte UTF-8 characters in GlobalReplace. + +28. Change free() to pcre_free() in pcredemo.c. Apparently this makes a + difference for some implementation of PCRE in some Windows version. + +29. Added some extra testing facilities to pcretest: + + \q<number> in a data line sets the "match limit" value + \Q<number> in a data line sets the "match recursion limt" value + -S <number> sets the stack size, where <number> is in megabytes + + The -S option isn't available for Windows. + + +Version 6.6 06-Feb-06 +--------------------- + + 1. Change 16(a) for 6.5 broke things, because PCRE_DATA_SCOPE was not defined + in pcreposix.h. I have copied the definition from pcre.h. + + 2. Change 25 for 6.5 broke compilation in a build directory out-of-tree + because pcre.h is no longer a built file. + + 3. Added Jeff Friedl's additional debugging patches to pcregrep. These are + not normally included in the compiled code. + + +Version 6.5 01-Feb-06 +--------------------- + + 1. When using the partial match feature with pcre_dfa_exec(), it was not + anchoring the second and subsequent partial matches at the new starting + point. This could lead to incorrect results. For example, with the pattern + /1234/, partially matching against "123" and then "a4" gave a match. + + 2. Changes to pcregrep: + + (a) All non-match returns from pcre_exec() were being treated as failures + to match the line. Now, unless the error is PCRE_ERROR_NOMATCH, an + error message is output. Some extra information is given for the + PCRE_ERROR_MATCHLIMIT and PCRE_ERROR_RECURSIONLIMIT errors, which are + probably the only errors that are likely to be caused by users (by + specifying a regex that has nested indefinite repeats, for instance). + If there are more than 20 of these errors, pcregrep is abandoned. + + (b) A binary zero was treated as data while matching, but terminated the + output line if it was written out. This has been fixed: binary zeroes + are now no different to any other data bytes. + + (c) Whichever of the LC_ALL or LC_CTYPE environment variables is set is + used to set a locale for matching. The --locale=xxxx long option has + been added (no short equivalent) to specify a locale explicitly on the + pcregrep command, overriding the environment variables. + + (d) When -B was used with -n, some line numbers in the output were one less + than they should have been. + + (e) Added the -o (--only-matching) option. + + (f) If -A or -C was used with -c (count only), some lines of context were + accidentally printed for the final match. + + (g) Added the -H (--with-filename) option. + + (h) The combination of options -rh failed to suppress file names for files + that were found from directory arguments. + + (i) Added the -D (--devices) and -d (--directories) options. + + (j) Added the -F (--fixed-strings) option. + + (k) Allow "-" to be used as a file name for -f as well as for a data file. + + (l) Added the --colo(u)r option. + + (m) Added Jeffrey Friedl's -S testing option, but within #ifdefs so that it + is not present by default. + + 3. A nasty bug was discovered in the handling of recursive patterns, that is, + items such as (?R) or (?1), when the recursion could match a number of + alternatives. If it matched one of the alternatives, but subsequently, + outside the recursion, there was a failure, the code tried to back up into + the recursion. However, because of the way PCRE is implemented, this is not + possible, and the result was an incorrect result from the match. + + In order to prevent this happening, the specification of recursion has + been changed so that all such subpatterns are automatically treated as + atomic groups. Thus, for example, (?R) is treated as if it were (?>(?R)). + + 4. I had overlooked the fact that, in some locales, there are characters for + which isalpha() is true but neither isupper() nor islower() are true. In + the fr_FR locale, for instance, the \xAA and \xBA characters (ordmasculine + and ordfeminine) are like this. This affected the treatment of \w and \W + when they appeared in character classes, but not when they appeared outside + a character class. The bit map for "word" characters is now created + separately from the results of isalnum() instead of just taking it from the + upper, lower, and digit maps. (Plus the underscore character, of course.) + + 5. The above bug also affected the handling of POSIX character classes such as + [[:alpha:]] and [[:alnum:]]. These do not have their own bit maps in PCRE's + permanent tables. Instead, the bit maps for such a class were previously + created as the appropriate unions of the upper, lower, and digit bitmaps. + Now they are created by subtraction from the [[:word:]] class, which has + its own bitmap. + + 6. The [[:blank:]] character class matches horizontal, but not vertical space. + It is created by subtracting the vertical space characters (\x09, \x0a, + \x0b, \x0c) from the [[:space:]] bitmap. Previously, however, the + subtraction was done in the overall bitmap for a character class, meaning + that a class such as [\x0c[:blank:]] was incorrect because \x0c would not + be recognized. This bug has been fixed. + + 7. Patches from the folks at Google: + + (a) pcrecpp.cc: "to handle a corner case that may or may not happen in + real life, but is still worth protecting against". + + (b) pcrecpp.cc: "corrects a bug when negative radixes are used with + regular expressions". + + (c) pcre_scanner.cc: avoid use of std::count() because not all systems + have it. + + (d) Split off pcrecpparg.h from pcrecpp.h and had the former built by + "configure" and the latter not, in order to fix a problem somebody had + with compiling the Arg class on HP-UX. + + (e) Improve the error-handling of the C++ wrapper a little bit. + + (f) New tests for checking recursion limiting. + + 8. The pcre_memmove() function, which is used only if the environment does not + have a standard memmove() function (and is therefore rarely compiled), + contained two bugs: (a) use of int instead of size_t, and (b) it was not + returning a result (though PCRE never actually uses the result). + + 9. In the POSIX regexec() interface, if nmatch is specified as a ridiculously + large number - greater than INT_MAX/(3*sizeof(int)) - REG_ESPACE is + returned instead of calling malloc() with an overflowing number that would + most likely cause subsequent chaos. + +10. The debugging option of pcretest was not showing the NO_AUTO_CAPTURE flag. + +11. The POSIX flag REG_NOSUB is now supported. When a pattern that was compiled + with this option is matched, the nmatch and pmatch options of regexec() are + ignored. + +12. Added REG_UTF8 to the POSIX interface. This is not defined by POSIX, but is + provided in case anyone wants to the the POSIX interface with UTF-8 + strings. + +13. Added CXXLDFLAGS to the Makefile parameters to provide settings only on the + C++ linking (needed for some HP-UX environments). + +14. Avoid compiler warnings in get_ucpname() when compiled without UCP support + (unused parameter) and in the pcre_printint() function (omitted "default" + switch label when the default is to do nothing). + +15. Added some code to make it possible, when PCRE is compiled as a C++ + library, to replace subject pointers for pcre_exec() with a smart pointer + class, thus making it possible to process discontinuous strings. + +16. The two macros PCRE_EXPORT and PCRE_DATA_SCOPE are confusing, and perform + much the same function. They were added by different people who were trying + to make PCRE easy to compile on non-Unix systems. It has been suggested + that PCRE_EXPORT be abolished now that there is more automatic apparatus + for compiling on Windows systems. I have therefore replaced it with + PCRE_DATA_SCOPE. This is set automatically for Windows; if not set it + defaults to "extern" for C or "extern C" for C++, which works fine on + Unix-like systems. It is now possible to override the value of PCRE_DATA_ + SCOPE with something explicit in config.h. In addition: + + (a) pcreposix.h still had just "extern" instead of either of these macros; + I have replaced it with PCRE_DATA_SCOPE. + + (b) Functions such as _pcre_xclass(), which are internal to the library, + but external in the C sense, all had PCRE_EXPORT in their definitions. + This is apparently wrong for the Windows case, so I have removed it. + (It makes no difference on Unix-like systems.) + +17. Added a new limit, MATCH_LIMIT_RECURSION, which limits the depth of nesting + of recursive calls to match(). This is different to MATCH_LIMIT because + that limits the total number of calls to match(), not all of which increase + the depth of recursion. Limiting the recursion depth limits the amount of + stack (or heap if NO_RECURSE is set) that is used. The default can be set + when PCRE is compiled, and changed at run time. A patch from Google adds + this functionality to the C++ interface. + +18. Changes to the handling of Unicode character properties: + + (a) Updated the table to Unicode 4.1.0. + + (b) Recognize characters that are not in the table as "Cn" (undefined). + + (c) I revised the way the table is implemented to a much improved format + which includes recognition of ranges. It now supports the ranges that + are defined in UnicodeData.txt, and it also amalgamates other + characters into ranges. This has reduced the number of entries in the + table from around 16,000 to around 3,000, thus reducing its size + considerably. I realized I did not need to use a tree structure after + all - a binary chop search is just as efficient. Having reduced the + number of entries, I extended their size from 6 bytes to 8 bytes to + allow for more data. + + (d) Added support for Unicode script names via properties such as \p{Han}. + +19. In UTF-8 mode, a backslash followed by a non-Ascii character was not + matching that character. + +20. When matching a repeated Unicode property with a minimum greater than zero, + (for example \pL{2,}), PCRE could look past the end of the subject if it + reached it while seeking the minimum number of characters. This could + happen only if some of the characters were more than one byte long, because + there is a check for at least the minimum number of bytes. + +21. Refactored the implementation of \p and \P so as to be more general, to + allow for more different types of property in future. This has changed the + compiled form incompatibly. Anybody with saved compiled patterns that use + \p or \P will have to recompile them. + +22. Added "Any" and "L&" to the supported property types. + +23. Recognize \x{...} as a code point specifier, even when not in UTF-8 mode, + but give a compile time error if the value is greater than 0xff. + +24. The man pages for pcrepartial, pcreprecompile, and pcre_compile2 were + accidentally not being installed or uninstalled. + +25. The pcre.h file was built from pcre.h.in, but the only changes that were + made were to insert the current release number. This seemed silly, because + it made things harder for people building PCRE on systems that don't run + "configure". I have turned pcre.h into a distributed file, no longer built + by "configure", with the version identification directly included. There is + no longer a pcre.h.in file. + + However, this change necessitated a change to the pcre-config script as + well. It is built from pcre-config.in, and one of the substitutions was the + release number. I have updated configure.ac so that ./configure now finds + the release number by grepping pcre.h. + +26. Added the ability to run the tests under valgrind. + + +Version 6.4 05-Sep-05 +--------------------- + + 1. Change 6.0/10/(l) to pcregrep introduced a bug that caused separator lines + "--" to be printed when multiple files were scanned, even when none of the + -A, -B, or -C options were used. This is not compatible with Gnu grep, so I + consider it to be a bug, and have restored the previous behaviour. + + 2. A couple of code tidies to get rid of compiler warnings. + + 3. The pcretest program used to cheat by referring to symbols in the library + whose names begin with _pcre_. These are internal symbols that are not + really supposed to be visible externally, and in some environments it is + possible to suppress them. The cheating is now confined to including + certain files from the library's source, which is a bit cleaner. + + 4. Renamed pcre.in as pcre.h.in to go with pcrecpp.h.in; it also makes the + file's purpose clearer. + + 5. Reorganized pcre_ucp_findchar(). + + +Version 6.3 15-Aug-05 +--------------------- + + 1. The file libpcre.pc.in did not have general read permission in the tarball. + + 2. There were some problems when building without C++ support: + + (a) If C++ support was not built, "make install" and "make test" still + tried to test it. + + (b) There were problems when the value of CXX was explicitly set. Some + changes have been made to try to fix these, and ... + + (c) --disable-cpp can now be used to explicitly disable C++ support. + + (d) The use of @CPP_OBJ@ directly caused a blank line preceded by a + backslash in a target when C++ was disabled. This confuses some + versions of "make", apparently. Using an intermediate variable solves + this. (Same for CPP_LOBJ.) + + 3. $(LINK_FOR_BUILD) now includes $(CFLAGS_FOR_BUILD) and $(LINK) + (non-Windows) now includes $(CFLAGS) because these flags are sometimes + necessary on certain architectures. + + 4. Added a setting of -export-symbols-regex to the link command to remove + those symbols that are exported in the C sense, but actually are local + within the library, and not documented. Their names all begin with + "_pcre_". This is not a perfect job, because (a) we have to except some + symbols that pcretest ("illegally") uses, and (b) the facility isn't always + available (and never for static libraries). I have made a note to try to + find a way round (a) in the future. + + +Version 6.2 01-Aug-05 +--------------------- + + 1. There was no test for integer overflow of quantifier values. A construction + such as {1111111111111111} would give undefined results. What is worse, if + a minimum quantifier for a parenthesized subpattern overflowed and became + negative, the calculation of the memory size went wrong. This could have + led to memory overwriting. + + 2. Building PCRE using VPATH was broken. Hopefully it is now fixed. + + 3. Added "b" to the 2nd argument of fopen() in dftables.c, for non-Unix-like + operating environments where this matters. + + 4. Applied Giuseppe Maxia's patch to add additional features for controlling + PCRE options from within the C++ wrapper. + + 5. Named capturing subpatterns were not being correctly counted when a pattern + was compiled. This caused two problems: (a) If there were more than 100 + such subpatterns, the calculation of the memory needed for the whole + compiled pattern went wrong, leading to an overflow error. (b) Numerical + back references of the form \12, where the number was greater than 9, were + not recognized as back references, even though there were sufficient + previous subpatterns. + + 6. Two minor patches to pcrecpp.cc in order to allow it to compile on older + versions of gcc, e.g. 2.95.4. + + +Version 6.1 21-Jun-05 +--------------------- + + 1. There was one reference to the variable "posix" in pcretest.c that was not + surrounded by "#if !defined NOPOSIX". + + 2. Make it possible to compile pcretest without DFA support, UTF8 support, or + the cross-check on the old pcre_info() function, for the benefit of the + cut-down version of PCRE that is currently imported into Exim. + + 3. A (silly) pattern starting with (?i)(?-i) caused an internal space + allocation error. I've done the easy fix, which wastes 2 bytes for sensible + patterns that start (?i) but I don't think that matters. The use of (?i) is + just an example; this all applies to the other options as well. + + 4. Since libtool seems to echo the compile commands it is issuing, the output + from "make" can be reduced a bit by putting "@" in front of each libtool + compile command. + + 5. Patch from the folks at Google for configure.in to be a bit more thorough + in checking for a suitable C++ installation before trying to compile the + C++ stuff. This should fix a reported problem when a compiler was present, + but no suitable headers. + + 6. The man pages all had just "PCRE" as their title. I have changed them to + be the relevant file name. I have also arranged that these names are + retained in the file doc/pcre.txt, which is a concatenation in text format + of all the man pages except the little individual ones for each function. + + 7. The NON-UNIX-USE file had not been updated for the different set of source + files that come with release 6. I also added a few comments about the C++ + wrapper. + + +Version 6.0 07-Jun-05 +--------------------- + + 1. Some minor internal re-organization to help with my DFA experiments. + + 2. Some missing #ifdef SUPPORT_UCP conditionals in pcretest and printint that + didn't matter for the library itself when fully configured, but did matter + when compiling without UCP support, or within Exim, where the ucp files are + not imported. + + 3. Refactoring of the library code to split up the various functions into + different source modules. The addition of the new DFA matching code (see + below) to a single monolithic source would have made it really too + unwieldy, quite apart from causing all the code to be include in a + statically linked application, when only some functions are used. This is + relevant even without the DFA addition now that patterns can be compiled in + one application and matched in another. + + The downside of splitting up is that there have to be some external + functions and data tables that are used internally in different modules of + the library but which are not part of the API. These have all had their + names changed to start with "_pcre_" so that they are unlikely to clash + with other external names. + + 4. Added an alternate matching function, pcre_dfa_exec(), which matches using + a different (DFA) algorithm. Although it is slower than the original + function, it does have some advantages for certain types of matching + problem. + + 5. Upgrades to pcretest in order to test the features of pcre_dfa_exec(), + including restarting after a partial match. + + 6. A patch for pcregrep that defines INVALID_FILE_ATTRIBUTES if it is not + defined when compiling for Windows was sent to me. I have put it into the + code, though I have no means of testing or verifying it. + + 7. Added the pcre_refcount() auxiliary function. + + 8. Added the PCRE_FIRSTLINE option. This constrains an unanchored pattern to + match before or at the first newline in the subject string. In pcretest, + the /f option on a pattern can be used to set this. + + 9. A repeated \w when used in UTF-8 mode with characters greater than 256 + would behave wrongly. This has been present in PCRE since release 4.0. + +10. A number of changes to the pcregrep command: + + (a) Refactored how -x works; insert ^(...)$ instead of setting + PCRE_ANCHORED and checking the length, in preparation for adding + something similar for -w. + + (b) Added the -w (match as a word) option. + + (c) Refactored the way lines are read and buffered so as to have more + than one at a time available. + + (d) Implemented a pcregrep test script. + + (e) Added the -M (multiline match) option. This allows patterns to match + over several lines of the subject. The buffering ensures that at least + 8K, or the rest of the document (whichever is the shorter) is available + for matching (and similarly the previous 8K for lookbehind assertions). + + (f) Changed the --help output so that it now says + + -w, --word-regex(p) + + instead of two lines, one with "regex" and the other with "regexp" + because that confused at least one person since the short forms are the + same. (This required a bit of code, as the output is generated + automatically from a table. It wasn't just a text change.) + + (g) -- can be used to terminate pcregrep options if the next thing isn't an + option but starts with a hyphen. Could be a pattern or a path name + starting with a hyphen, for instance. + + (h) "-" can be given as a file name to represent stdin. + + (i) When file names are being printed, "(standard input)" is used for + the standard input, for compatibility with GNU grep. Previously + "<stdin>" was used. + + (j) The option --label=xxx can be used to supply a name to be used for + stdin when file names are being printed. There is no short form. + + (k) Re-factored the options decoding logic because we are going to add + two more options that take data. Such options can now be given in four + different ways, e.g. "-fname", "-f name", "--file=name", "--file name". + + (l) Added the -A, -B, and -C options for requesting that lines of context + around matches be printed. + + (m) Added the -L option to print the names of files that do not contain + any matching lines, that is, the complement of -l. + + (n) The return code is 2 if any file cannot be opened, but pcregrep does + continue to scan other files. + + (o) The -s option was incorrectly implemented. For compatibility with other + greps, it now suppresses the error message for a non-existent or non- + accessible file (but not the return code). There is a new option called + -q that suppresses the output of matching lines, which was what -s was + previously doing. + + (p) Added --include and --exclude options to specify files for inclusion + and exclusion when recursing. + +11. The Makefile was not using the Autoconf-supported LDFLAGS macro properly. + Hopefully, it now does. + +12. Missing cast in pcre_study(). + +13. Added an "uninstall" target to the makefile. + +14. Replaced "extern" in the function prototypes in Makefile.in with + "PCRE_DATA_SCOPE", which defaults to 'extern' or 'extern "C"' in the Unix + world, but is set differently for Windows. + +15. Added a second compiling function called pcre_compile2(). The only + difference is that it has an extra argument, which is a pointer to an + integer error code. When there is a compile-time failure, this is set + non-zero, in addition to the error test pointer being set to point to an + error message. The new argument may be NULL if no error number is required + (but then you may as well call pcre_compile(), which is now just a + wrapper). This facility is provided because some applications need a + numeric error indication, but it has also enabled me to tidy up the way + compile-time errors are handled in the POSIX wrapper. + +16. Added VPATH=.libs to the makefile; this should help when building with one + prefix path and installing with another. (Or so I'm told by someone who + knows more about this stuff than I do.) + +17. Added a new option, REG_DOTALL, to the POSIX function regcomp(). This + passes PCRE_DOTALL to the pcre_compile() function, making the "." character + match everything, including newlines. This is not POSIX-compatible, but + somebody wanted the feature. From pcretest it can be activated by using + both the P and the s flags. + +18. AC_PROG_LIBTOOL appeared twice in Makefile.in. Removed one. + +19. libpcre.pc was being incorrectly installed as executable. + +20. A couple of places in pcretest check for end-of-line by looking for '\n'; + it now also looks for '\r' so that it will work unmodified on Windows. + +21. Added Google's contributed C++ wrapper to the distribution. + +22. Added some untidy missing memory free() calls in pcretest, to keep + Electric Fence happy when testing. + + + +Version 5.0 13-Sep-04 +--------------------- + + 1. Internal change: literal characters are no longer packed up into items + containing multiple characters in a single byte-string. Each character + is now matched using a separate opcode. However, there may be more than one + byte in the character in UTF-8 mode. + + 2. The pcre_callout_block structure has two new fields: pattern_position and + next_item_length. These contain the offset in the pattern to the next match + item, and its length, respectively. + + 3. The PCRE_AUTO_CALLOUT option for pcre_compile() requests the automatic + insertion of callouts before each pattern item. Added the /C option to + pcretest to make use of this. + + 4. On the advice of a Windows user, the lines + + #if defined(_WIN32) || defined(WIN32) + _setmode( _fileno( stdout ), 0x8000 ); + #endif /* defined(_WIN32) || defined(WIN32) */ + + have been added to the source of pcretest. This apparently does useful + magic in relation to line terminators. + + 5. Changed "r" and "w" in the calls to fopen() in pcretest to "rb" and "wb" + for the benefit of those environments where the "b" makes a difference. + + 6. The icc compiler has the same options as gcc, but "configure" doesn't seem + to know about it. I have put a hack into configure.in that adds in code + to set GCC=yes if CC=icc. This seems to end up at a point in the + generated configure script that is early enough to affect the setting of + compiler options, which is what is needed, but I have no means of testing + whether it really works. (The user who reported this had patched the + generated configure script, which of course I cannot do.) + + LATER: After change 22 below (new libtool files), the configure script + seems to know about icc (and also ecc). Therefore, I have commented out + this hack in configure.in. + + 7. Added support for pkg-config (2 patches were sent in). + + 8. Negated POSIX character classes that used a combination of internal tables + were completely broken. These were [[:^alpha:]], [[:^alnum:]], and + [[:^ascii]]. Typically, they would match almost any characters. The other + POSIX classes were not broken in this way. + + 9. Matching the pattern "\b.*?" against "ab cd", starting at offset 1, failed + to find the match, as PCRE was deluded into thinking that the match had to + start at the start point or following a newline. The same bug applied to + patterns with negative forward assertions or any backward assertions + preceding ".*" at the start, unless the pattern required a fixed first + character. This was a failing pattern: "(?!.bcd).*". The bug is now fixed. + +10. In UTF-8 mode, when moving forwards in the subject after a failed match + starting at the last subject character, bytes beyond the end of the subject + string were read. + +11. Renamed the variable "class" as "classbits" to make life easier for C++ + users. (Previously there was a macro definition, but it apparently wasn't + enough.) + +12. Added the new field "tables" to the extra data so that tables can be passed + in at exec time, or the internal tables can be re-selected. This allows + a compiled regex to be saved and re-used at a later time by a different + program that might have everything at different addresses. + +13. Modified the pcre-config script so that, when run on Solaris, it shows a + -R library as well as a -L library. + +14. The debugging options of pcretest (-d on the command line or D on a + pattern) showed incorrect output for anything following an extended class + that contained multibyte characters and which was followed by a quantifier. + +15. Added optional support for general category Unicode character properties + via the \p, \P, and \X escapes. Unicode property support implies UTF-8 + support. It adds about 90K to the size of the library. The meanings of the + inbuilt class escapes such as \d and \s have NOT been changed. + +16. Updated pcredemo.c to include calls to free() to release the memory for the + compiled pattern. + +17. The generated file chartables.c was being created in the source directory + instead of in the building directory. This caused the build to fail if the + source directory was different from the building directory, and was + read-only. + +18. Added some sample Win commands from Mark Tetrode into the NON-UNIX-USE + file. No doubt somebody will tell me if they don't make sense... Also added + Dan Mooney's comments about building on OpenVMS. + +19. Added support for partial matching via the PCRE_PARTIAL option for + pcre_exec() and the \P data escape in pcretest. + +20. Extended pcretest with 3 new pattern features: + + (i) A pattern option of the form ">rest-of-line" causes pcretest to + write the compiled pattern to the file whose name is "rest-of-line". + This is a straight binary dump of the data, with the saved pointer to + the character tables forced to be NULL. The study data, if any, is + written too. After writing, pcretest reads a new pattern. + + (ii) If, instead of a pattern, "<rest-of-line" is given, pcretest reads a + compiled pattern from the given file. There must not be any + occurrences of "<" in the file name (pretty unlikely); if there are, + pcretest will instead treat the initial "<" as a pattern delimiter. + After reading in the pattern, pcretest goes on to read data lines as + usual. + + (iii) The F pattern option causes pcretest to flip the bytes in the 32-bit + and 16-bit fields in a compiled pattern, to simulate a pattern that + was compiled on a host of opposite endianness. + +21. The pcre-exec() function can now cope with patterns that were compiled on + hosts of opposite endianness, with this restriction: + + As for any compiled expression that is saved and used later, the tables + pointer field cannot be preserved; the extra_data field in the arguments + to pcre_exec() should be used to pass in a tables address if a value + other than the default internal tables were used at compile time. + +22. Calling pcre_exec() with a negative value of the "ovecsize" parameter is + now diagnosed as an error. Previously, most of the time, a negative number + would have been treated as zero, but if in addition "ovector" was passed as + NULL, a crash could occur. + +23. Updated the files ltmain.sh, config.sub, config.guess, and aclocal.m4 with + new versions from the libtool 1.5 distribution (the last one is a copy of + a file called libtool.m4). This seems to have fixed the need to patch + "configure" to support Darwin 1.3 (which I used to do). However, I still + had to patch ltmain.sh to ensure that ${SED} is set (it isn't on my + workstation). + +24. Changed the PCRE licence to be the more standard "BSD" licence. + + +Version 4.5 01-Dec-03 +--------------------- + + 1. There has been some re-arrangement of the code for the match() function so + that it can be compiled in a version that does not call itself recursively. + Instead, it keeps those local variables that need separate instances for + each "recursion" in a frame on the heap, and gets/frees frames whenever it + needs to "recurse". Keeping track of where control must go is done by means + of setjmp/longjmp. The whole thing is implemented by a set of macros that + hide most of the details from the main code, and operates only if + NO_RECURSE is defined while compiling pcre.c. If PCRE is built using the + "configure" mechanism, "--disable-stack-for-recursion" turns on this way of + operating. + + To make it easier for callers to provide specially tailored get/free + functions for this usage, two new functions, pcre_stack_malloc, and + pcre_stack_free, are used. They are always called in strict stacking order, + and the size of block requested is always the same. + + The PCRE_CONFIG_STACKRECURSE info parameter can be used to find out whether + PCRE has been compiled to use the stack or the heap for recursion. The + -C option of pcretest uses this to show which version is compiled. + + A new data escape \S, is added to pcretest; it causes the amounts of store + obtained and freed by both kinds of malloc/free at match time to be added + to the output. + + 2. Changed the locale test to use "fr_FR" instead of "fr" because that's + what's available on my current Linux desktop machine. + + 3. When matching a UTF-8 string, the test for a valid string at the start has + been extended. If start_offset is not zero, PCRE now checks that it points + to a byte that is the start of a UTF-8 character. If not, it returns + PCRE_ERROR_BADUTF8_OFFSET (-11). Note: the whole string is still checked; + this is necessary because there may be backward assertions in the pattern. + When matching the same subject several times, it may save resources to use + PCRE_NO_UTF8_CHECK on all but the first call if the string is long. + + 4. The code for checking the validity of UTF-8 strings has been tightened so + that it rejects (a) strings containing 0xfe or 0xff bytes and (b) strings + containing "overlong sequences". + + 5. Fixed a bug (appearing twice) that I could not find any way of exploiting! + I had written "if ((digitab[*p++] && chtab_digit) == 0)" where the "&&" + should have been "&", but it just so happened that all the cases this let + through by mistake were picked up later in the function. + + 6. I had used a variable called "isblank" - this is a C99 function, causing + some compilers to warn. To avoid this, I renamed it (as "blankclass"). + + 7. Cosmetic: (a) only output another newline at the end of pcretest if it is + prompting; (b) run "./pcretest /dev/null" at the start of the test script + so the version is shown; (c) stop "make test" echoing "./RunTest". + + 8. Added patches from David Burgess to enable PCRE to run on EBCDIC systems. + + 9. The prototype for memmove() for systems that don't have it was using + size_t, but the inclusion of the header that defines size_t was later. I've + moved the #includes for the C headers earlier to avoid this. + +10. Added some adjustments to the code to make it easier to compiler on certain + special systems: + + (a) Some "const" qualifiers were missing. + (b) Added the macro EXPORT before all exported functions; by default this + is defined to be empty. + (c) Changed the dftables auxiliary program (that builds chartables.c) so + that it reads its output file name as an argument instead of writing + to the standard output and assuming this can be redirected. + +11. In UTF-8 mode, if a recursive reference (e.g. (?1)) followed a character + class containing characters with values greater than 255, PCRE compilation + went into a loop. + +12. A recursive reference to a subpattern that was within another subpattern + that had a minimum quantifier of zero caused PCRE to crash. For example, + (x(y(?2))z)? provoked this bug with a subject that got as far as the + recursion. If the recursively-called subpattern itself had a zero repeat, + that was OK. + +13. In pcretest, the buffer for reading a data line was set at 30K, but the + buffer into which it was copied (for escape processing) was still set at + 1024, so long lines caused crashes. + +14. A pattern such as /[ab]{1,3}+/ failed to compile, giving the error + "internal error: code overflow...". This applied to any character class + that was followed by a possessive quantifier. + +15. Modified the Makefile to add libpcre.la as a prerequisite for + libpcreposix.la because I was told this is needed for a parallel build to + work. + +16. If a pattern that contained .* following optional items at the start was + studied, the wrong optimizing data was generated, leading to matching + errors. For example, studying /[ab]*.*c/ concluded, erroneously, that any + matching string must start with a or b or c. The correct conclusion for + this pattern is that a match can start with any character. + + +Version 4.4 13-Aug-03 +--------------------- + + 1. In UTF-8 mode, a character class containing characters with values between + 127 and 255 was not handled correctly if the compiled pattern was studied. + In fixing this, I have also improved the studying algorithm for such + classes (slightly). + + 2. Three internal functions had redundant arguments passed to them. Removal + might give a very teeny performance improvement. + + 3. Documentation bug: the value of the capture_top field in a callout is *one + more than* the number of the hightest numbered captured substring. + + 4. The Makefile linked pcretest and pcregrep with -lpcre, which could result + in incorrectly linking with a previously installed version. They now link + explicitly with libpcre.la. + + 5. configure.in no longer needs to recognize Cygwin specially. + + 6. A problem in pcre.in for Windows platforms is fixed. + + 7. If a pattern was successfully studied, and the -d (or /D) flag was given to + pcretest, it used to include the size of the study block as part of its + output. Unfortunately, the structure contains a field that has a different + size on different hardware architectures. This meant that the tests that + showed this size failed. As the block is currently always of a fixed size, + this information isn't actually particularly useful in pcretest output, so + I have just removed it. + + 8. Three pre-processor statements accidentally did not start in column 1. + Sadly, there are *still* compilers around that complain, even though + standard C has not required this for well over a decade. Sigh. + + 9. In pcretest, the code for checking callouts passed small integers in the + callout_data field, which is a void * field. However, some picky compilers + complained about the casts involved for this on 64-bit systems. Now + pcretest passes the address of the small integer instead, which should get + rid of the warnings. + +10. By default, when in UTF-8 mode, PCRE now checks for valid UTF-8 strings at + both compile and run time, and gives an error if an invalid UTF-8 sequence + is found. There is a option for disabling this check in cases where the + string is known to be correct and/or the maximum performance is wanted. + +11. In response to a bug report, I changed one line in Makefile.in from + + -Wl,--out-implib,.libs/lib@WIN_PREFIX@pcreposix.dll.a \ + to + -Wl,--out-implib,.libs/@WIN_PREFIX@libpcreposix.dll.a \ + + to look similar to other lines, but I have no way of telling whether this + is the right thing to do, as I do not use Windows. No doubt I'll get told + if it's wrong... + + +Version 4.3 21-May-03 +--------------------- + +1. Two instances of @WIN_PREFIX@ omitted from the Windows targets in the + Makefile. + +2. Some refactoring to improve the quality of the code: + + (i) The utf8_table... variables are now declared "const". + + (ii) The code for \cx, which used the "case flipping" table to upper case + lower case letters, now just substracts 32. This is ASCII-specific, + but the whole concept of \cx is ASCII-specific, so it seems + reasonable. + + (iii) PCRE was using its character types table to recognize decimal and + hexadecimal digits in the pattern. This is silly, because it handles + only 0-9, a-f, and A-F, but the character types table is locale- + specific, which means strange things might happen. A private + table is now used for this - though it costs 256 bytes, a table is + much faster than multiple explicit tests. Of course, the standard + character types table is still used for matching digits in subject + strings against \d. + + (iv) Strictly, the identifier ESC_t is reserved by POSIX (all identifiers + ending in _t are). So I've renamed it as ESC_tee. + +3. The first argument for regexec() in the POSIX wrapper should have been + defined as "const". + +4. Changed pcretest to use malloc() for its buffers so that they can be + Electric Fenced for debugging. + +5. There were several places in the code where, in UTF-8 mode, PCRE would try + to read one or more bytes before the start of the subject string. Often this + had no effect on PCRE's behaviour, but in some circumstances it could + provoke a segmentation fault. + +6. A lookbehind at the start of a pattern in UTF-8 mode could also cause PCRE + to try to read one or more bytes before the start of the subject string. + +7. A lookbehind in a pattern matched in non-UTF-8 mode on a PCRE compiled with + UTF-8 support could misbehave in various ways if the subject string + contained bytes with the 0x80 bit set and the 0x40 bit unset in a lookbehind + area. (PCRE was not checking for the UTF-8 mode flag, and trying to move + back over UTF-8 characters.) + + +Version 4.2 14-Apr-03 +--------------------- + +1. Typo "#if SUPPORT_UTF8" instead of "#ifdef SUPPORT_UTF8" fixed. + +2. Changes to the building process, supplied by Ronald Landheer-Cieslak + [ON_WINDOWS]: new variable, "#" on non-Windows platforms + [NOT_ON_WINDOWS]: new variable, "#" on Windows platforms + [WIN_PREFIX]: new variable, "cyg" for Cygwin + * Makefile.in: use autoconf substitution for OBJEXT, EXEEXT, BUILD_OBJEXT + and BUILD_EXEEXT + Note: automatic setting of the BUILD variables is not yet working + set CPPFLAGS and BUILD_CPPFLAGS (but don't use yet) - should be used at + compile-time but not at link-time + [LINK]: use for linking executables only + make different versions for Windows and non-Windows + [LINKLIB]: new variable, copy of UNIX-style LINK, used for linking + libraries + [LINK_FOR_BUILD]: new variable + [OBJEXT]: use throughout + [EXEEXT]: use throughout + <winshared>: new target + <wininstall>: new target + <dftables.o>: use native compiler + <dftables>: use native linker + <install>: handle Windows platform correctly + <clean>: ditto + <check>: ditto + copy DLL to top builddir before testing + + As part of these changes, -no-undefined was removed again. This was reported + to give trouble on HP-UX 11.0, so getting rid of it seems like a good idea + in any case. + +3. Some tidies to get rid of compiler warnings: + + . In the match_data structure, match_limit was an unsigned long int, whereas + match_call_count was an int. I've made them both unsigned long ints. + + . In pcretest the fact that a const uschar * doesn't automatically cast to + a void * provoked a warning. + + . Turning on some more compiler warnings threw up some "shadow" variables + and a few more missing casts. + +4. If PCRE was complied with UTF-8 support, but called without the PCRE_UTF8 + option, a class that contained a single character with a value between 128 + and 255 (e.g. /[\xFF]/) caused PCRE to crash. + +5. If PCRE was compiled with UTF-8 support, but called without the PCRE_UTF8 + option, a class that contained several characters, but with at least one + whose value was between 128 and 255 caused PCRE to crash. + + +Version 4.1 12-Mar-03 +--------------------- + +1. Compiling with gcc -pedantic found a couple of places where casts were +needed, and a string in dftables.c that was longer than standard compilers are +required to support. + +2. Compiling with Sun's compiler found a few more places where the code could +be tidied up in order to avoid warnings. + +3. The variables for cross-compiling were called HOST_CC and HOST_CFLAGS; the +first of these names is deprecated in the latest Autoconf in favour of the name +CC_FOR_BUILD, because "host" is typically used to mean the system on which the +compiled code will be run. I can't find a reference for HOST_CFLAGS, but by +analogy I have changed it to CFLAGS_FOR_BUILD. + +4. Added -no-undefined to the linking command in the Makefile, because this is +apparently helpful for Windows. To make it work, also added "-L. -lpcre" to the +linking step for the pcreposix library. + +5. PCRE was failing to diagnose the case of two named groups with the same +name. + +6. A problem with one of PCRE's optimizations was discovered. PCRE remembers a +literal character that is needed in the subject for a match, and scans along to +ensure that it is present before embarking on the full matching process. This +saves time in cases of nested unlimited repeats that are never going to match. +Problem: the scan can take a lot of time if the subject is very long (e.g. +megabytes), thus penalizing straightforward matches. It is now done only if the +amount of subject to be scanned is less than 1000 bytes. + +7. A lesser problem with the same optimization is that it was recording the +first character of an anchored pattern as "needed", thus provoking a search +right along the subject, even when the first match of the pattern was going to +fail. The "needed" character is now not set for anchored patterns, unless it +follows something in the pattern that is of non-fixed length. Thus, it still +fulfils its original purpose of finding quick non-matches in cases of nested +unlimited repeats, but isn't used for simple anchored patterns such as /^abc/. + + +Version 4.0 17-Feb-03 +--------------------- + +1. If a comment in an extended regex that started immediately after a meta-item +extended to the end of string, PCRE compiled incorrect data. This could lead to +all kinds of weird effects. Example: /#/ was bad; /()#/ was bad; /a#/ was not. + +2. Moved to autoconf 2.53 and libtool 1.4.2. + +3. Perl 5.8 no longer needs "use utf8" for doing UTF-8 things. Consequently, +the special perltest8 script is no longer needed - all the tests can be run +from a single perltest script. + +4. From 5.004, Perl has not included the VT character (0x0b) in the set defined +by \s. It has now been removed in PCRE. This means it isn't recognized as +whitespace in /x regexes too, which is the same as Perl. Note that the POSIX +class [:space:] *does* include VT, thereby creating a mess. + +5. Added the class [:blank:] (a GNU extension from Perl 5.8) to match only +space and tab. + +6. Perl 5.005 was a long time ago. It's time to amalgamate the tests that use +its new features into the main test script, reducing the number of scripts. + +7. Perl 5.8 has changed the meaning of patterns like /a(?i)b/. Earlier versions +were backward compatible, and made the (?i) apply to the whole pattern, as if +/i were given. Now it behaves more logically, and applies the option setting +only to what follows. PCRE has been changed to follow suit. However, if it +finds options settings right at the start of the pattern, it extracts them into +the global options, as before. Thus, they show up in the info data. + +8. Added support for the \Q...\E escape sequence. Characters in between are +treated as literals. This is slightly different from Perl in that $ and @ are +also handled as literals inside the quotes. In Perl, they will cause variable +interpolation. Note the following examples: + + Pattern PCRE matches Perl matches + + \Qabc$xyz\E abc$xyz abc followed by the contents of $xyz + \Qabc\$xyz\E abc\$xyz abc\$xyz + \Qabc\E\$\Qxyz\E abc$xyz abc$xyz + +For compatibility with Perl, \Q...\E sequences are recognized inside character +classes as well as outside them. + +9. Re-organized 3 code statements in pcretest to avoid "overflow in +floating-point constant arithmetic" warnings from a Microsoft compiler. Added a +(size_t) cast to one statement in pcretest and one in pcreposix to avoid +signed/unsigned warnings. + +10. SunOS4 doesn't have strtoul(). This was used only for unpicking the -o +option for pcretest, so I've replaced it by a simple function that does just +that job. + +11. pcregrep was ending with code 0 instead of 2 for the commands "pcregrep" or +"pcregrep -". + +12. Added "possessive quantifiers" ?+, *+, ++, and {,}+ which come from Sun's +Java package. This provides some syntactic sugar for simple cases of what my +documentation calls "once-only subpatterns". A pattern such as x*+ is the same +as (?>x*). In other words, if what is inside (?>...) is just a single repeated +item, you can use this simplified notation. Note that only makes sense with +greedy quantifiers. Consequently, the use of the possessive quantifier forces +greediness, whatever the setting of the PCRE_UNGREEDY option. + +13. A change of greediness default within a pattern was not taking effect at +the current level for patterns like /(b+(?U)a+)/. It did apply to parenthesized +subpatterns that followed. Patterns like /b+(?U)a+/ worked because the option +was abstracted outside. + +14. PCRE now supports the \G assertion. It is true when the current matching +position is at the start point of the match. This differs from \A when the +starting offset is non-zero. Used with the /g option of pcretest (or similar +code), it works in the same way as it does for Perl's /g option. If all +alternatives of a regex begin with \G, the expression is anchored to the start +match position, and the "anchored" flag is set in the compiled expression. + +15. Some bugs concerning the handling of certain option changes within patterns +have been fixed. These applied to options other than (?ims). For example, +"a(?x: b c )d" did not match "XabcdY" but did match "Xa b c dY". It should have +been the other way round. Some of this was related to change 7 above. + +16. PCRE now gives errors for /[.x.]/ and /[=x=]/ as unsupported POSIX +features, as Perl does. Previously, PCRE gave the warnings only for /[[.x.]]/ +and /[[=x=]]/. PCRE now also gives an error for /[:name:]/ because it supports +POSIX classes only within a class (e.g. /[[:alpha:]]/). + +17. Added support for Perl's \C escape. This matches one byte, even in UTF8 +mode. Unlike ".", it always matches newline, whatever the setting of +PCRE_DOTALL. However, PCRE does not permit \C to appear in lookbehind +assertions. Perl allows it, but it doesn't (in general) work because it can't +calculate the length of the lookbehind. At least, that's the case for Perl +5.8.0 - I've been told they are going to document that it doesn't work in +future. + +18. Added an error diagnosis for escapes that PCRE does not support: these are +\L, \l, \N, \P, \p, \U, \u, and \X. + +19. Although correctly diagnosing a missing ']' in a character class, PCRE was +reading past the end of the pattern in cases such as /[abcd/. + +20. PCRE was getting more memory than necessary for patterns with classes that +contained both POSIX named classes and other characters, e.g. /[[:space:]abc/. + +21. Added some code, conditional on #ifdef VPCOMPAT, to make life easier for +compiling PCRE for use with Virtual Pascal. + +22. Small fix to the Makefile to make it work properly if the build is done +outside the source tree. + +23. Added a new extension: a condition to go with recursion. If a conditional +subpattern starts with (?(R) the "true" branch is used if recursion has +happened, whereas the "false" branch is used only at the top level. + +24. When there was a very long string of literal characters (over 255 bytes +without UTF support, over 250 bytes with UTF support), the computation of how +much memory was required could be incorrect, leading to segfaults or other +strange effects. + +25. PCRE was incorrectly assuming anchoring (either to start of subject or to +start of line for a non-DOTALL pattern) when a pattern started with (.*) and +there was a subsequent back reference to those brackets. This meant that, for +example, /(.*)\d+\1/ failed to match "abc123bc". Unfortunately, it isn't +possible to check for precisely this case. All we can do is abandon the +optimization if .* occurs inside capturing brackets when there are any back +references whatsoever. (See below for a better fix that came later.) + +26. The handling of the optimization for finding the first character of a +non-anchored pattern, and for finding a character that is required later in the +match were failing in some cases. This didn't break the matching; it just +failed to optimize when it could. The way this is done has been re-implemented. + +27. Fixed typo in error message for invalid (?R item (it said "(?p"). + +28. Added a new feature that provides some of the functionality that Perl +provides with (?{...}). The facility is termed a "callout". The way it is done +in PCRE is for the caller to provide an optional function, by setting +pcre_callout to its entry point. Like pcre_malloc and pcre_free, this is a +global variable. By default it is unset, which disables all calling out. To get +the function called, the regex must include (?C) at appropriate points. This +is, in fact, equivalent to (?C0), and any number <= 255 may be given with (?C). +This provides a means of identifying different callout points. When PCRE +reaches such a point in the regex, if pcre_callout has been set, the external +function is called. It is provided with data in a structure called +pcre_callout_block, which is defined in pcre.h. If the function returns 0, +matching continues; if it returns a non-zero value, the match at the current +point fails. However, backtracking will occur if possible. [This was changed +later and other features added - see item 49 below.] + +29. pcretest is upgraded to test the callout functionality. It provides a +callout function that displays information. By default, it shows the start of +the match and the current position in the text. There are some new data escapes +to vary what happens: + + \C+ in addition, show current contents of captured substrings + \C- do not supply a callout function + \C!n return 1 when callout number n is reached + \C!n!m return 1 when callout number n is reached for the mth time + +30. If pcregrep was called with the -l option and just a single file name, it +output "<stdin>" if a match was found, instead of the file name. + +31. Improve the efficiency of the POSIX API to PCRE. If the number of capturing +slots is less than POSIX_MALLOC_THRESHOLD, use a block on the stack to pass to +pcre_exec(). This saves a malloc/free per call. The default value of +POSIX_MALLOC_THRESHOLD is 10; it can be changed by --with-posix-malloc-threshold +when configuring. + +32. The default maximum size of a compiled pattern is 64K. There have been a +few cases of people hitting this limit. The code now uses macros to handle the +storing of links as offsets within the compiled pattern. It defaults to 2-byte +links, but this can be changed to 3 or 4 bytes by --with-link-size when +configuring. Tests 2 and 5 work only with 2-byte links because they output +debugging information about compiled patterns. + +33. Internal code re-arrangements: + +(a) Moved the debugging function for printing out a compiled regex into + its own source file (printint.c) and used #include to pull it into + pcretest.c and, when DEBUG is defined, into pcre.c, instead of having two + separate copies. + +(b) Defined the list of op-code names for debugging as a macro in + internal.h so that it is next to the definition of the opcodes. + +(c) Defined a table of op-code lengths for simpler skipping along compiled + code. This is again a macro in internal.h so that it is next to the + definition of the opcodes. + +34. Added support for recursive calls to individual subpatterns, along the +lines of Robin Houston's patch (but implemented somewhat differently). + +35. Further mods to the Makefile to help Win32. Also, added code to pcregrep to +allow it to read and process whole directories in Win32. This code was +contributed by Lionel Fourquaux; it has not been tested by me. + +36. Added support for named subpatterns. The Python syntax (?P<name>...) is +used to name a group. Names consist of alphanumerics and underscores, and must +be unique. Back references use the syntax (?P=name) and recursive calls use +(?P>name) which is a PCRE extension to the Python extension. Groups still have +numbers. The function pcre_fullinfo() can be used after compilation to extract +a name/number map. There are three relevant calls: + + PCRE_INFO_NAMEENTRYSIZE yields the size of each entry in the map + PCRE_INFO_NAMECOUNT yields the number of entries + PCRE_INFO_NAMETABLE yields a pointer to the map. + +The map is a vector of fixed-size entries. The size of each entry depends on +the length of the longest name used. The first two bytes of each entry are the +group number, most significant byte first. There follows the corresponding +name, zero terminated. The names are in alphabetical order. + +37. Make the maximum literal string in the compiled code 250 for the non-UTF-8 +case instead of 255. Making it the same both with and without UTF-8 support +means that the same test output works with both. + +38. There was a case of malloc(0) in the POSIX testing code in pcretest. Avoid +calling malloc() with a zero argument. + +39. Change 25 above had to resort to a heavy-handed test for the .* anchoring +optimization. I've improved things by keeping a bitmap of backreferences with +numbers 1-31 so that if .* occurs inside capturing brackets that are not in +fact referenced, the optimization can be applied. It is unlikely that a +relevant occurrence of .* (i.e. one which might indicate anchoring or forcing +the match to follow \n) will appear inside brackets with a number greater than +31, but if it does, any back reference > 31 suppresses the optimization. + +40. Added a new compile-time option PCRE_NO_AUTO_CAPTURE. This has the effect +of disabling numbered capturing parentheses. Any opening parenthesis that is +not followed by ? behaves as if it were followed by ?: but named parentheses +can still be used for capturing (and they will acquire numbers in the usual +way). + +41. Redesigned the return codes from the match() function into yes/no/error so +that errors can be passed back from deep inside the nested calls. A malloc +failure while inside a recursive subpattern call now causes the +PCRE_ERROR_NOMEMORY return instead of quietly going wrong. + +42. It is now possible to set a limit on the number of times the match() +function is called in a call to pcre_exec(). This facility makes it possible to +limit the amount of recursion and backtracking, though not in a directly +obvious way, because the match() function is used in a number of different +circumstances. The count starts from zero for each position in the subject +string (for non-anchored patterns). The default limit is, for compatibility, a +large number, namely 10 000 000. You can change this in two ways: + +(a) When configuring PCRE before making, you can use --with-match-limit=n + to set a default value for the compiled library. + +(b) For each call to pcre_exec(), you can pass a pcre_extra block in which + a different value is set. See 45 below. + +If the limit is exceeded, pcre_exec() returns PCRE_ERROR_MATCHLIMIT. + +43. Added a new function pcre_config(int, void *) to enable run-time extraction +of things that can be changed at compile time. The first argument specifies +what is wanted and the second points to where the information is to be placed. +The current list of available information is: + + PCRE_CONFIG_UTF8 + +The output is an integer that is set to one if UTF-8 support is available; +otherwise it is set to zero. + + PCRE_CONFIG_NEWLINE + +The output is an integer that it set to the value of the code that is used for +newline. It is either LF (10) or CR (13). + + PCRE_CONFIG_LINK_SIZE + +The output is an integer that contains the number of bytes used for internal +linkage in compiled expressions. The value is 2, 3, or 4. See item 32 above. + + PCRE_CONFIG_POSIX_MALLOC_THRESHOLD + +The output is an integer that contains the threshold above which the POSIX +interface uses malloc() for output vectors. See item 31 above. + + PCRE_CONFIG_MATCH_LIMIT + +The output is an unsigned integer that contains the default limit of the number +of match() calls in a pcre_exec() execution. See 42 above. + +44. pcretest has been upgraded by the addition of the -C option. This causes it +to extract all the available output from the new pcre_config() function, and to +output it. The program then exits immediately. + +45. A need has arisen to pass over additional data with calls to pcre_exec() in +order to support additional features. One way would have been to define +pcre_exec2() (for example) with extra arguments, but this would not have been +extensible, and would also have required all calls to the original function to +be mapped to the new one. Instead, I have chosen to extend the mechanism that +is used for passing in "extra" data from pcre_study(). + +The pcre_extra structure is now exposed and defined in pcre.h. It currently +contains the following fields: + + flags a bitmap indicating which of the following fields are set + study_data opaque data from pcre_study() + match_limit a way of specifying a limit on match() calls for a specific + call to pcre_exec() + callout_data data for callouts (see 49 below) + +The flag bits are also defined in pcre.h, and are + + PCRE_EXTRA_STUDY_DATA + PCRE_EXTRA_MATCH_LIMIT + PCRE_EXTRA_CALLOUT_DATA + +The pcre_study() function now returns one of these new pcre_extra blocks, with +the actual study data pointed to by the study_data field, and the +PCRE_EXTRA_STUDY_DATA flag set. This can be passed directly to pcre_exec() as +before. That is, this change is entirely upwards-compatible and requires no +change to existing code. + +If you want to pass in additional data to pcre_exec(), you can either place it +in a pcre_extra block provided by pcre_study(), or create your own pcre_extra +block. + +46. pcretest has been extended to test the PCRE_EXTRA_MATCH_LIMIT feature. If a +data string contains the escape sequence \M, pcretest calls pcre_exec() several +times with different match limits, until it finds the minimum value needed for +pcre_exec() to complete. The value is then output. This can be instructive; for +most simple matches the number is quite small, but for pathological cases it +gets very large very quickly. + +47. There's a new option for pcre_fullinfo() called PCRE_INFO_STUDYSIZE. It +returns the size of the data block pointed to by the study_data field in a +pcre_extra block, that is, the value that was passed as the argument to +pcre_malloc() when PCRE was getting memory in which to place the information +created by pcre_study(). The fourth argument should point to a size_t variable. +pcretest has been extended so that this information is shown after a successful +pcre_study() call when information about the compiled regex is being displayed. + +48. Cosmetic change to Makefile: there's no need to have / after $(DESTDIR) +because what follows is always an absolute path. (Later: it turns out that this +is more than cosmetic for MinGW, because it doesn't like empty path +components.) + +49. Some changes have been made to the callout feature (see 28 above): + +(i) A callout function now has three choices for what it returns: + + 0 => success, carry on matching + > 0 => failure at this point, but backtrack if possible + < 0 => serious error, return this value from pcre_exec() + + Negative values should normally be chosen from the set of PCRE_ERROR_xxx + values. In particular, returning PCRE_ERROR_NOMATCH forces a standard + "match failed" error. The error number PCRE_ERROR_CALLOUT is reserved for + use by callout functions. It will never be used by PCRE itself. + +(ii) The pcre_extra structure (see 45 above) has a void * field called + callout_data, with corresponding flag bit PCRE_EXTRA_CALLOUT_DATA. The + pcre_callout_block structure has a field of the same name. The contents of + the field passed in the pcre_extra structure are passed to the callout + function in the corresponding field in the callout block. This makes it + easier to use the same callout-containing regex from multiple threads. For + testing, the pcretest program has a new data escape + + \C*n pass the number n (may be negative) as callout_data + + If the callout function in pcretest receives a non-zero value as + callout_data, it returns that value. + +50. Makefile wasn't handling CFLAGS properly when compiling dftables. Also, +there were some redundant $(CFLAGS) in commands that are now specified as +$(LINK), which already includes $(CFLAGS). + +51. Extensions to UTF-8 support are listed below. These all apply when (a) PCRE +has been compiled with UTF-8 support *and* pcre_compile() has been compiled +with the PCRE_UTF8 flag. Patterns that are compiled without that flag assume +one-byte characters throughout. Note that case-insensitive matching applies +only to characters whose values are less than 256. PCRE doesn't support the +notion of cases for higher-valued characters. + +(i) A character class whose characters are all within 0-255 is handled as + a bit map, and the map is inverted for negative classes. Previously, a + character > 255 always failed to match such a class; however it should + match if the class was a negative one (e.g. [^ab]). This has been fixed. + +(ii) A negated character class with a single character < 255 is coded as + "not this character" (OP_NOT). This wasn't working properly when the test + character was multibyte, either singly or repeated. + +(iii) Repeats of multibyte characters are now handled correctly in UTF-8 + mode, for example: \x{100}{2,3}. + +(iv) The character escapes \b, \B, \d, \D, \s, \S, \w, and \W (either + singly or repeated) now correctly test multibyte characters. However, + PCRE doesn't recognize any characters with values greater than 255 as + digits, spaces, or word characters. Such characters always match \D, \S, + and \W, and never match \d, \s, or \w. + +(v) Classes may now contain characters and character ranges with values + greater than 255. For example: [ab\x{100}-\x{400}]. + +(vi) pcregrep now has a --utf-8 option (synonym -u) which makes it call + PCRE in UTF-8 mode. + +52. The info request value PCRE_INFO_FIRSTCHAR has been renamed +PCRE_INFO_FIRSTBYTE because it is a byte value. However, the old name is +retained for backwards compatibility. (Note that LASTLITERAL is also a byte +value.) + +53. The single man page has become too large. I have therefore split it up into +a number of separate man pages. These also give rise to individual HTML pages; +these are now put in a separate directory, and there is an index.html page that +lists them all. Some hyperlinking between the pages has been installed. + +54. Added convenience functions for handling named capturing parentheses. + +55. Unknown escapes inside character classes (e.g. [\M]) and escapes that +aren't interpreted therein (e.g. [\C]) are literals in Perl. This is now also +true in PCRE, except when the PCRE_EXTENDED option is set, in which case they +are faulted. + +56. Introduced HOST_CC and HOST_CFLAGS which can be set in the environment when +calling configure. These values are used when compiling the dftables.c program +which is run to generate the source of the default character tables. They +default to the values of CC and CFLAGS. If you are cross-compiling PCRE, +you will need to set these values. + +57. Updated the building process for Windows DLL, as provided by Fred Cox. + + +Version 3.9 02-Jan-02 +--------------------- + +1. A bit of extraneous text had somehow crept into the pcregrep documentation. + +2. If --disable-static was given, the building process failed when trying to +build pcretest and pcregrep. (For some reason it was using libtool to compile +them, which is not right, as they aren't part of the library.) + + +Version 3.8 18-Dec-01 +--------------------- + +1. The experimental UTF-8 code was completely screwed up. It was packing the +bytes in the wrong order. How dumb can you get? + + +Version 3.7 29-Oct-01 +--------------------- + +1. In updating pcretest to check change 1 of version 3.6, I screwed up. +This caused pcretest, when used on the test data, to segfault. Unfortunately, +this didn't happen under Solaris 8, where I normally test things. + +2. The Makefile had to be changed to make it work on BSD systems, where 'make' +doesn't seem to recognize that ./xxx and xxx are the same file. (This entry +isn't in ChangeLog distributed with 3.7 because I forgot when I hastily made +this fix an hour or so after the initial 3.7 release.) + + +Version 3.6 23-Oct-01 +--------------------- + +1. Crashed with /(sens|respons)e and \1ibility/ and "sense and sensibility" if +offsets passed as NULL with zero offset count. + +2. The config.guess and config.sub files had not been updated when I moved to +the latest autoconf. + + +Version 3.5 15-Aug-01 +--------------------- + +1. Added some missing #if !defined NOPOSIX conditionals in pcretest.c that +had been forgotten. + +2. By using declared but undefined structures, we can avoid using "void" +definitions in pcre.h while keeping the internal definitions of the structures +private. + +3. The distribution is now built using autoconf 2.50 and libtool 1.4. From a +user point of view, this means that both static and shared libraries are built +by default, but this can be individually controlled. More of the work of +handling this static/shared cases is now inside libtool instead of PCRE's make +file. + +4. The pcretest utility is now installed along with pcregrep because it is +useful for users (to test regexs) and by doing this, it automatically gets +relinked by libtool. The documentation has been turned into a man page, so +there are now .1, .txt, and .html versions in /doc. + +5. Upgrades to pcregrep: + (i) Added long-form option names like gnu grep. + (ii) Added --help to list all options with an explanatory phrase. + (iii) Added -r, --recursive to recurse into sub-directories. + (iv) Added -f, --file to read patterns from a file. + +6. pcre_exec() was referring to its "code" argument before testing that +argument for NULL (and giving an error if it was NULL). + +7. Upgraded Makefile.in to allow for compiling in a different directory from +the source directory. + +8. Tiny buglet in pcretest: when pcre_fullinfo() was called to retrieve the +options bits, the pointer it was passed was to an int instead of to an unsigned +long int. This mattered only on 64-bit systems. + +9. Fixed typo (3.4/1) in pcre.h again. Sigh. I had changed pcre.h (which is +generated) instead of pcre.in, which it its source. Also made the same change +in several of the .c files. + +10. A new release of gcc defines printf() as a macro, which broke pcretest +because it had an ifdef in the middle of a string argument for printf(). Fixed +by using separate calls to printf(). + +11. Added --enable-newline-is-cr and --enable-newline-is-lf to the configure +script, to force use of CR or LF instead of \n in the source. On non-Unix +systems, the value can be set in config.h. + +12. The limit of 200 on non-capturing parentheses is a _nesting_ limit, not an +absolute limit. Changed the text of the error message to make this clear, and +likewise updated the man page. + +13. The limit of 99 on the number of capturing subpatterns has been removed. +The new limit is 65535, which I hope will not be a "real" limit. + + +Version 3.4 22-Aug-00 +--------------------- + +1. Fixed typo in pcre.h: unsigned const char * changed to const unsigned char *. + +2. Diagnose condition (?(0) as an error instead of crashing on matching. + + +Version 3.3 01-Aug-00 +--------------------- + +1. If an octal character was given, but the value was greater than \377, it +was not getting masked to the least significant bits, as documented. This could +lead to crashes in some systems. + +2. Perl 5.6 (if not earlier versions) accepts classes like [a-\d] and treats +the hyphen as a literal. PCRE used to give an error; it now behaves like Perl. + +3. Added the functions pcre_free_substring() and pcre_free_substring_list(). +These just pass their arguments on to (pcre_free)(), but they are provided +because some uses of PCRE bind it to non-C systems that can call its functions, +but cannot call free() or pcre_free() directly. + +4. Add "make test" as a synonym for "make check". Corrected some comments in +the Makefile. + +5. Add $(DESTDIR)/ in front of all the paths in the "install" target in the +Makefile. + +6. Changed the name of pgrep to pcregrep, because Solaris has introduced a +command called pgrep for grepping around the active processes. + +7. Added the beginnings of support for UTF-8 character strings. + +8. Arranged for the Makefile to pass over the settings of CC, CFLAGS, and +RANLIB to ./ltconfig so that they are used by libtool. I think these are all +the relevant ones. (AR is not passed because ./ltconfig does its own figuring +out for the ar command.) + + +Version 3.2 12-May-00 +--------------------- + +This is purely a bug fixing release. + +1. If the pattern /((Z)+|A)*/ was matched agained ZABCDEFG it matched Z instead +of ZA. This was just one example of several cases that could provoke this bug, +which was introduced by change 9 of version 2.00. The code for breaking +infinite loops after an iteration that matches an empty string was't working +correctly. + +2. The pcretest program was not imitating Perl correctly for the pattern /a*/g +when matched against abbab (for example). After matching an empty string, it +wasn't forcing anchoring when setting PCRE_NOTEMPTY for the next attempt; this +caused it to match further down the string than it should. + +3. The code contained an inclusion of sys/types.h. It isn't clear why this +was there because it doesn't seem to be needed, and it causes trouble on some +systems, as it is not a Standard C header. It has been removed. + +4. Made 4 silly changes to the source to avoid stupid compiler warnings that +were reported on the Macintosh. The changes were from + + while ((c = *(++ptr)) != 0 && c != '\n'); +to + while ((c = *(++ptr)) != 0 && c != '\n') ; + +Totally extraordinary, but if that's what it takes... + +5. PCRE is being used in one environment where neither memmove() nor bcopy() is +available. Added HAVE_BCOPY and an autoconf test for it; if neither +HAVE_MEMMOVE nor HAVE_BCOPY is set, use a built-in emulation function which +assumes the way PCRE uses memmove() (always moving upwards). + +6. PCRE is being used in one environment where strchr() is not available. There +was only one use in pcre.c, and writing it out to avoid strchr() probably gives +faster code anyway. + + +Version 3.1 09-Feb-00 +--------------------- + +The only change in this release is the fixing of some bugs in Makefile.in for +the "install" target: + +(1) It was failing to install pcreposix.h. + +(2) It was overwriting the pcre.3 man page with the pcreposix.3 man page. + + +Version 3.0 01-Feb-00 +--------------------- + +1. Add support for the /+ modifier to perltest (to output $` like it does in +pcretest). + +2. Add support for the /g modifier to perltest. + +3. Fix pcretest so that it behaves even more like Perl for /g when the pattern +matches null strings. + +4. Fix perltest so that it doesn't do unwanted things when fed an empty +pattern. Perl treats empty patterns specially - it reuses the most recent +pattern, which is not what we want. Replace // by /(?#)/ in order to avoid this +effect. + +5. The POSIX interface was broken in that it was just handing over the POSIX +captured string vector to pcre_exec(), but (since release 2.00) PCRE has +required a bigger vector, with some working space on the end. This means that +the POSIX wrapper now has to get and free some memory, and copy the results. + +6. Added some simple autoconf support, placing the test data and the +documentation in separate directories, re-organizing some of the +information files, and making it build pcre-config (a GNU standard). Also added +libtool support for building PCRE as a shared library, which is now the +default. + +7. Got rid of the leading zero in the definition of PCRE_MINOR because 08 and +09 are not valid octal constants. Single digits will be used for minor values +less than 10. + +8. Defined REG_EXTENDED and REG_NOSUB as zero in the POSIX header, so that +existing programs that set these in the POSIX interface can use PCRE without +modification. + +9. Added a new function, pcre_fullinfo() with an extensible interface. It can +return all that pcre_info() returns, plus additional data. The pcre_info() +function is retained for compatibility, but is considered to be obsolete. + +10. Added experimental recursion feature (?R) to handle one common case that +Perl 5.6 will be able to do with (?p{...}). + +11. Added support for POSIX character classes like [:alpha:], which Perl is +adopting. + + +Version 2.08 31-Aug-99 +---------------------- + +1. When startoffset was not zero and the pattern began with ".*", PCRE was not +trying to match at the startoffset position, but instead was moving forward to +the next newline as if a previous match had failed. + +2. pcretest was not making use of PCRE_NOTEMPTY when repeating for /g and /G, +and could get into a loop if a null string was matched other than at the start +of the subject. + +3. Added definitions of PCRE_MAJOR and PCRE_MINOR to pcre.h so the version can +be distinguished at compile time, and for completeness also added PCRE_DATE. + +5. Added Paul Sokolovsky's minor changes to make it easy to compile a Win32 DLL +in GnuWin32 environments. + + +Version 2.07 29-Jul-99 +---------------------- + +1. The documentation is now supplied in plain text form and HTML as well as in +the form of man page sources. + +2. C++ compilers don't like assigning (void *) values to other pointer types. +In particular this affects malloc(). Although there is no problem in Standard +C, I've put in casts to keep C++ compilers happy. + +3. Typo on pcretest.c; a cast of (unsigned char *) in the POSIX regexec() call +should be (const char *). + +4. If NOPOSIX is defined, pcretest.c compiles without POSIX support. This may +be useful for non-Unix systems who don't want to bother with the POSIX stuff. +However, I haven't made this a standard facility. The documentation doesn't +mention it, and the Makefile doesn't support it. + +5. The Makefile now contains an "install" target, with editable destinations at +the top of the file. The pcretest program is not installed. + +6. pgrep -V now gives the PCRE version number and date. + +7. Fixed bug: a zero repetition after a literal string (e.g. /abcde{0}/) was +causing the entire string to be ignored, instead of just the last character. + +8. If a pattern like /"([^\\"]+|\\.)*"/ is applied in the normal way to a +non-matching string, it can take a very, very long time, even for strings of +quite modest length, because of the nested recursion. PCRE now does better in +some of these cases. It does this by remembering the last required literal +character in the pattern, and pre-searching the subject to ensure it is present +before running the real match. In other words, it applies a heuristic to detect +some types of certain failure quickly, and in the above example, if presented +with a string that has no trailing " it gives "no match" very quickly. + +9. A new runtime option PCRE_NOTEMPTY causes null string matches to be ignored; +other alternatives are tried instead. + + +Version 2.06 09-Jun-99 +---------------------- + +1. Change pcretest's output for amount of store used to show just the code +space, because the remainder (the data block) varies in size between 32-bit and +64-bit systems. + +2. Added an extra argument to pcre_exec() to supply an offset in the subject to +start matching at. This allows lookbehinds to work when searching for multiple +occurrences in a string. + +3. Added additional options to pcretest for testing multiple occurrences: + + /+ outputs the rest of the string that follows a match + /g loops for multiple occurrences, using the new startoffset argument + /G loops for multiple occurrences by passing an incremented pointer + +4. PCRE wasn't doing the "first character" optimization for patterns starting +with \b or \B, though it was doing it for other lookbehind assertions. That is, +it wasn't noticing that a match for a pattern such as /\bxyz/ has to start with +the letter 'x'. On long subject strings, this gives a significant speed-up. + + +Version 2.05 21-Apr-99 +---------------------- + +1. Changed the type of magic_number from int to long int so that it works +properly on 16-bit systems. + +2. Fixed a bug which caused patterns starting with .* not to work correctly +when the subject string contained newline characters. PCRE was assuming +anchoring for such patterns in all cases, which is not correct because .* will +not pass a newline unless PCRE_DOTALL is set. It now assumes anchoring only if +DOTALL is set at top level; otherwise it knows that patterns starting with .* +must be retried after every newline in the subject. + + +Version 2.04 18-Feb-99 +---------------------- + +1. For parenthesized subpatterns with repeats whose minimum was zero, the +computation of the store needed to hold the pattern was incorrect (too large). +If such patterns were nested a few deep, this could multiply and become a real +problem. + +2. Added /M option to pcretest to show the memory requirement of a specific +pattern. Made -m a synonym of -s (which does this globally) for compatibility. + +3. Subpatterns of the form (regex){n,m} (i.e. limited maximum) were being +compiled in such a way that the backtracking after subsequent failure was +pessimal. Something like (a){0,3} was compiled as (a)?(a)?(a)? instead of +((a)((a)(a)?)?)? with disastrous performance if the maximum was of any size. + + +Version 2.03 02-Feb-99 +---------------------- + +1. Fixed typo and small mistake in man page. + +2. Added 4th condition (GPL supersedes if conflict) and created separate +LICENCE file containing the conditions. + +3. Updated pcretest so that patterns such as /abc\/def/ work like they do in +Perl, that is the internal \ allows the delimiter to be included in the +pattern. Locked out the use of \ as a delimiter. If \ immediately follows +the final delimiter, add \ to the end of the pattern (to test the error). + +4. Added the convenience functions for extracting substrings after a successful +match. Updated pcretest to make it able to test these functions. + + +Version 2.02 14-Jan-99 +---------------------- + +1. Initialized the working variables associated with each extraction so that +their saving and restoring doesn't refer to uninitialized store. + +2. Put dummy code into study.c in order to trick the optimizer of the IBM C +compiler for OS/2 into generating correct code. Apparently IBM isn't going to +fix the problem. + +3. Pcretest: the timing code wasn't using LOOPREPEAT for timing execution +calls, and wasn't printing the correct value for compiling calls. Increased the +default value of LOOPREPEAT, and the number of significant figures in the +times. + +4. Changed "/bin/rm" in the Makefile to "-rm" so it works on Windows NT. + +5. Renamed "deftables" as "dftables" to get it down to 8 characters, to avoid +a building problem on Windows NT with a FAT file system. + + +Version 2.01 21-Oct-98 +---------------------- + +1. Changed the API for pcre_compile() to allow for the provision of a pointer +to character tables built by pcre_maketables() in the current locale. If NULL +is passed, the default tables are used. + + +Version 2.00 24-Sep-98 +---------------------- + +1. Since the (>?) facility is in Perl 5.005, don't require PCRE_EXTRA to enable +it any more. + +2. Allow quantification of (?>) groups, and make it work correctly. + +3. The first character computation wasn't working for (?>) groups. + +4. Correct the implementation of \Z (it is permitted to match on the \n at the +end of the subject) and add 5.005's \z, which really does match only at the +very end of the subject. + +5. Remove the \X "cut" facility; Perl doesn't have it, and (?> is neater. + +6. Remove the ability to specify CASELESS, MULTILINE, DOTALL, and +DOLLAR_END_ONLY at runtime, to make it possible to implement the Perl 5.005 +localized options. All options to pcre_study() were also removed. + +7. Add other new features from 5.005: + + $(?<= positive lookbehind + $(?<! negative lookbehind + (?imsx-imsx) added the unsetting capability + such a setting is global if at outer level; local otherwise + (?imsx-imsx:) non-capturing groups with option setting + (?(cond)re|re) conditional pattern matching + + A backreference to itself in a repeated group matches the previous + captured string. + +8. General tidying up of studying (both automatic and via "study") +consequential on the addition of new assertions. + +9. As in 5.005, unlimited repeated groups that could match an empty substring +are no longer faulted at compile time. Instead, the loop is forcibly broken at +runtime if any iteration does actually match an empty substring. + +10. Include the RunTest script in the distribution. + +11. Added tests from the Perl 5.005_02 distribution. This showed up a few +discrepancies, some of which were old and were also with respect to 5.004. They +have now been fixed. + + +Version 1.09 28-Apr-98 +---------------------- + +1. A negated single character class followed by a quantifier with a minimum +value of one (e.g. [^x]{1,6} ) was not compiled correctly. This could lead to +program crashes, or just wrong answers. This did not apply to negated classes +containing more than one character, or to minima other than one. + + +Version 1.08 27-Mar-98 +---------------------- + +1. Add PCRE_UNGREEDY to invert the greediness of quantifiers. + +2. Add (?U) and (?X) to set PCRE_UNGREEDY and PCRE_EXTRA respectively. The +latter must appear before anything that relies on it in the pattern. + + +Version 1.07 16-Feb-98 +---------------------- + +1. A pattern such as /((a)*)*/ was not being diagnosed as in error (unlimited +repeat of a potentially empty string). + + +Version 1.06 23-Jan-98 +---------------------- + +1. Added Markus Oberhumer's little patches for C++. + +2. Literal strings longer than 255 characters were broken. + + +Version 1.05 23-Dec-97 +---------------------- + +1. Negated character classes containing more than one character were failing if +PCRE_CASELESS was set at run time. + + +Version 1.04 19-Dec-97 +---------------------- + +1. Corrected the man page, where some "const" qualifiers had been omitted. + +2. Made debugging output print "{0,xxx}" instead of just "{,xxx}" to agree with +input syntax. + +3. Fixed memory leak which occurred when a regex with back references was +matched with an offsets vector that wasn't big enough. The temporary memory +that is used in this case wasn't being freed if the match failed. + +4. Tidied pcretest to ensure it frees memory that it gets. + +5. Temporary memory was being obtained in the case where the passed offsets +vector was exactly big enough. + +6. Corrected definition of offsetof() from change 5 below. + +7. I had screwed up change 6 below and broken the rules for the use of +setjmp(). Now fixed. + + +Version 1.03 18-Dec-97 +---------------------- + +1. A erroneous regex with a missing opening parenthesis was correctly +diagnosed, but PCRE attempted to access brastack[-1], which could cause crashes +on some systems. + +2. Replaced offsetof(real_pcre, code) by offsetof(real_pcre, code[0]) because +it was reported that one broken compiler failed on the former because "code" is +also an independent variable. + +3. The erroneous regex a[]b caused an array overrun reference. + +4. A regex ending with a one-character negative class (e.g. /[^k]$/) did not +fail on data ending with that character. (It was going on too far, and checking +the next character, typically a binary zero.) This was specific to the +optimized code for single-character negative classes. + +5. Added a contributed patch from the TIN world which does the following: + + + Add an undef for memmove, in case the the system defines a macro for it. + + + Add a definition of offsetof(), in case there isn't one. (I don't know + the reason behind this - offsetof() is part of the ANSI standard - but + it does no harm). + + + Reduce the ifdef's in pcre.c using macro DPRINTF, thereby eliminating + most of the places where whitespace preceded '#'. I have given up and + allowed the remaining 2 cases to be at the margin. + + + Rename some variables in pcre to eliminate shadowing. This seems very + pedantic, but does no harm, of course. + +6. Moved the call to setjmp() into its own function, to get rid of warnings +from gcc -Wall, and avoided calling it at all unless PCRE_EXTRA is used. + +7. Constructs such as \d{8,} were compiling into the equivalent of +\d{8}\d{0,65527} instead of \d{8}\d* which didn't make much difference to the +outcome, but in this particular case used more store than had been allocated, +which caused the bug to be discovered because it threw up an internal error. + +8. The debugging code in both pcre and pcretest for outputting the compiled +form of a regex was going wrong in the case of back references followed by +curly-bracketed repeats. + + +Version 1.02 12-Dec-97 +---------------------- + +1. Typos in pcre.3 and comments in the source fixed. + +2. Applied a contributed patch to get rid of places where it used to remove +'const' from variables, and fixed some signed/unsigned and uninitialized +variable warnings. + +3. Added the "runtest" target to Makefile. + +4. Set default compiler flag to -O2 rather than just -O. + + +Version 1.01 19-Nov-97 +---------------------- + +1. PCRE was failing to diagnose unlimited repeat of empty string for patterns +like /([ab]*)*/, that is, for classes with more than one character in them. + +2. Likewise, it wasn't diagnosing patterns with "once-only" subpatterns, such +as /((?>a*))*/ (a PCRE_EXTRA facility). + + +Version 1.00 18-Nov-97 +---------------------- + +1. Added compile-time macros to support systems such as SunOS4 which don't have +memmove() or strerror() but have other things that can be used instead. + +2. Arranged that "make clean" removes the executables. + + +Version 0.99 27-Oct-97 +---------------------- + +1. Fixed bug in code for optimizing classes with only one character. It was +initializing a 32-byte map regardless, which could cause it to run off the end +of the memory it had got. + +2. Added, conditional on PCRE_EXTRA, the proposed (?>REGEX) construction. + + +Version 0.98 22-Oct-97 +---------------------- + +1. Fixed bug in code for handling temporary memory usage when there are more +back references than supplied space in the ovector. This could cause segfaults. + + +Version 0.97 21-Oct-97 +---------------------- + +1. Added the \X "cut" facility, conditional on PCRE_EXTRA. + +2. Optimized negated single characters not to use a bit map. + +3. Brought error texts together as macro definitions; clarified some of them; +fixed one that was wrong - it said "range out of order" when it meant "invalid +escape sequence". + +4. Changed some char * arguments to const char *. + +5. Added PCRE_NOTBOL and PCRE_NOTEOL (from POSIX). + +6. Added the POSIX-style API wrapper in pcreposix.a and testing facilities in +pcretest. + + +Version 0.96 16-Oct-97 +---------------------- + +1. Added a simple "pgrep" utility to the distribution. + +2. Fixed an incompatibility with Perl: "{" is now treated as a normal character +unless it appears in one of the precise forms "{ddd}", "{ddd,}", or "{ddd,ddd}" +where "ddd" means "one or more decimal digits". + +3. Fixed serious bug. If a pattern had a back reference, but the call to +pcre_exec() didn't supply a large enough ovector to record the related +identifying subpattern, the match always failed. PCRE now remembers the number +of the largest back reference, and gets some temporary memory in which to save +the offsets during matching if necessary, in order to ensure that +backreferences always work. + +4. Increased the compatibility with Perl in a number of ways: + + (a) . no longer matches \n by default; an option PCRE_DOTALL is provided + to request this handling. The option can be set at compile or exec time. + + (b) $ matches before a terminating newline by default; an option + PCRE_DOLLAR_ENDONLY is provided to override this (but not in multiline + mode). The option can be set at compile or exec time. + + (c) The handling of \ followed by a digit other than 0 is now supposed to be + the same as Perl's. If the decimal number it represents is less than 10 + or there aren't that many previous left capturing parentheses, an octal + escape is read. Inside a character class, it's always an octal escape, + even if it is a single digit. + + (d) An escaped but undefined alphabetic character is taken as a literal, + unless PCRE_EXTRA is set. Currently this just reserves the remaining + escapes. + + (e) {0} is now permitted. (The previous item is removed from the compiled + pattern). + +5. Changed all the names of code files so that the basic parts are no longer +than 10 characters, and abolished the teeny "globals.c" file. + +6. Changed the handling of character classes; they are now done with a 32-byte +bit map always. + +7. Added the -d and /D options to pcretest to make it possible to look at the +internals of compilation without having to recompile pcre. + + +Version 0.95 23-Sep-97 +---------------------- + +1. Fixed bug in pre-pass concerning escaped "normal" characters such as \x5c or +\x20 at the start of a run of normal characters. These were being treated as +real characters, instead of the source characters being re-checked. + + +Version 0.94 18-Sep-97 +---------------------- + +1. The functions are now thread-safe, with the caveat that the global variables +containing pointers to malloc() and free() or alternative functions are the +same for all threads. + +2. Get pcre_study() to generate a bitmap of initial characters for non- +anchored patterns when this is possible, and use it if passed to pcre_exec(). + + +Version 0.93 15-Sep-97 +---------------------- + +1. /(b)|(:+)/ was computing an incorrect first character. + +2. Add pcre_study() to the API and the passing of pcre_extra to pcre_exec(), +but not actually doing anything yet. + +3. Treat "-" characters in classes that cannot be part of ranges as literals, +as Perl does (e.g. [-az] or [az-]). + +4. Set the anchored flag if a branch starts with .* or .*? because that tests +all possible positions. + +5. Split up into different modules to avoid including unneeded functions in a +compiled binary. However, compile and exec are still in one module. The "study" +function is split off. + +6. The character tables are now in a separate module whose source is generated +by an auxiliary program - but can then be edited by hand if required. There are +now no calls to isalnum(), isspace(), isdigit(), isxdigit(), tolower() or +toupper() in the code. + +7. Turn the malloc/free funtions variables into pcre_malloc and pcre_free and +make them global. Abolish the function for setting them, as the caller can now +set them directly. + + +Version 0.92 11-Sep-97 +---------------------- + +1. A repeat with a fixed maximum and a minimum of 1 for an ordinary character +(e.g. /a{1,3}/) was broken (I mis-optimized it). + +2. Caseless matching was not working in character classes if the characters in +the pattern were in upper case. + +3. Make ranges like [W-c] work in the same way as Perl for caseless matching. + +4. Make PCRE_ANCHORED public and accept as a compile option. + +5. Add an options word to pcre_exec() and accept PCRE_ANCHORED and +PCRE_CASELESS at run time. Add escapes \A and \I to pcretest to cause it to +pass them. + +6. Give an error if bad option bits passed at compile or run time. + +7. Add PCRE_MULTILINE at compile and exec time, and (?m) as well. Add \M to +pcretest to cause it to pass that flag. + +8. Add pcre_info(), to get the number of identifying subpatterns, the stored +options, and the first character, if set. + +9. Recognize C+ or C{n,m} where n >= 1 as providing a fixed starting character. + + +Version 0.91 10-Sep-97 +---------------------- + +1. PCRE was failing to diagnose unlimited repeats of subpatterns that could +match the empty string as in /(a*)*/. It was looping and ultimately crashing. + +2. PCRE was looping on encountering an indefinitely repeated back reference to +a subpattern that had matched an empty string, e.g. /(a|)\1*/. It now does what +Perl does - treats the match as successful. + +**** diff --git a/plugins/Pcre16/docs/HACKING b/plugins/Pcre16/docs/HACKING new file mode 100644 index 0000000000..691b7a14e5 --- /dev/null +++ b/plugins/Pcre16/docs/HACKING @@ -0,0 +1,528 @@ +Technical Notes about PCRE +-------------------------- + +These are very rough technical notes that record potentially useful information +about PCRE internals. For information about testing PCRE, see the pcretest +documentation and the comment at the head of the RunTest file. + + +Historical note 1 +----------------- + +Many years ago I implemented some regular expression functions to an algorithm +suggested by Martin Richards. These were not Unix-like in form, and were quite +restricted in what they could do by comparison with Perl. The interesting part +about the algorithm was that the amount of space required to hold the compiled +form of an expression was known in advance. The code to apply an expression did +not operate by backtracking, as the original Henry Spencer code and current +Perl code does, but instead checked all possibilities simultaneously by keeping +a list of current states and checking all of them as it advanced through the +subject string. In the terminology of Jeffrey Friedl's book, it was a "DFA +algorithm", though it was not a traditional Finite State Machine (FSM). When +the pattern was all used up, all remaining states were possible matches, and +the one matching the longest subset of the subject string was chosen. This did +not necessarily maximize the individual wild portions of the pattern, as is +expected in Unix and Perl-style regular expressions. + + +Historical note 2 +----------------- + +By contrast, the code originally written by Henry Spencer (which was +subsequently heavily modified for Perl) compiles the expression twice: once in +a dummy mode in order to find out how much store will be needed, and then for +real. (The Perl version probably doesn't do this any more; I'm talking about +the original library.) The execution function operates by backtracking and +maximizing (or, optionally, minimizing in Perl) the amount of the subject that +matches individual wild portions of the pattern. This is an "NFA algorithm" in +Friedl's terminology. + + +OK, here's the real stuff +------------------------- + +For the set of functions that form the "basic" PCRE library (which are +unrelated to those mentioned above), I tried at first to invent an algorithm +that used an amount of store bounded by a multiple of the number of characters +in the pattern, to save on compiling time. However, because of the greater +complexity in Perl regular expressions, I couldn't do this. In any case, a +first pass through the pattern is helpful for other reasons. + + +Support for 16-bit and 32-bit data strings +------------------------------------------- + +From release 8.30, PCRE supports 16-bit as well as 8-bit data strings; and from +release 8.32, PCRE supports 32-bit data strings. The library can be compiled +in any combination of 8-bit, 16-bit or 32-bit modes, creating up to three +different libraries. In the description that follows, the word "short" is used +for a 16-bit data quantity, and the word "unit" is used for a quantity that is +a byte in 8-bit mode, a short in 16-bit mode and a 32-bit word in 32-bit mode. +However, so as not to over-complicate the text, the names of PCRE functions are +given in 8-bit form only. + + +Computing the memory requirement: how it was +-------------------------------------------- + +Up to and including release 6.7, PCRE worked by running a very degenerate first +pass to calculate a maximum store size, and then a second pass to do the real +compile - which might use a bit less than the predicted amount of memory. The +idea was that this would turn out faster than the Henry Spencer code because +the first pass is degenerate and the second pass can just store stuff straight +into the vector, which it knows is big enough. + + +Computing the memory requirement: how it is +------------------------------------------- + +By the time I was working on a potential 6.8 release, the degenerate first pass +had become very complicated and hard to maintain. Indeed one of the early +things I did for 6.8 was to fix Yet Another Bug in the memory computation. Then +I had a flash of inspiration as to how I could run the real compile function in +a "fake" mode that enables it to compute how much memory it would need, while +actually only ever using a few hundred bytes of working memory, and without too +many tests of the mode that might slow it down. So I refactored the compiling +functions to work this way. This got rid of about 600 lines of source. It +should make future maintenance and development easier. As this was such a major +change, I never released 6.8, instead upping the number to 7.0 (other quite +major changes were also present in the 7.0 release). + +A side effect of this work was that the previous limit of 200 on the nesting +depth of parentheses was removed. However, there is a downside: pcre_compile() +runs more slowly than before (30% or more, depending on the pattern) because it +is doing a full analysis of the pattern. My hope was that this would not be a +big issue, and in the event, nobody has commented on it. + +At release 8.34, a limit on the nesting depth of parentheses was re-introduced +(default 250, settable at build time) so as to put a limit on the amount of +system stack used by pcre_compile(). This is a safety feature for environments +with small stacks where the patterns are provided by users. + + +Traditional matching function +----------------------------- + +The "traditional", and original, matching function is called pcre_exec(), and +it implements an NFA algorithm, similar to the original Henry Spencer algorithm +and the way that Perl works. This is not surprising, since it is intended to be +as compatible with Perl as possible. This is the function most users of PCRE +will use most of the time. From release 8.20, if PCRE is compiled with +just-in-time (JIT) support, and studying a compiled pattern with JIT is +successful, the JIT code is run instead of the normal pcre_exec() code, but the +result is the same. + + +Supplementary matching function +------------------------------- + +From PCRE 6.0, there is also a supplementary matching function called +pcre_dfa_exec(). This implements a DFA matching algorithm that searches +simultaneously for all possible matches that start at one point in the subject +string. (Going back to my roots: see Historical Note 1 above.) This function +intreprets the same compiled pattern data as pcre_exec(); however, not all the +facilities are available, and those that are do not always work in quite the +same way. See the user documentation for details. + +The algorithm that is used for pcre_dfa_exec() is not a traditional FSM, +because it may have a number of states active at one time. More work would be +needed at compile time to produce a traditional FSM where only one state is +ever active at once. I believe some other regex matchers work this way. JIT +support is not available for this kind of matching. + + +Changeable options +------------------ + +The /i, /m, or /s options (PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and some +others) may change in the middle of patterns. From PCRE 8.13, their processing +is handled entirely at compile time by generating different opcodes for the +different settings. The runtime functions do not need to keep track of an +options state any more. + + +Format of compiled patterns +--------------------------- + +The compiled form of a pattern is a vector of unsigned units (bytes in 8-bit +mode, shorts in 16-bit mode, 32-bit words in 32-bit mode), containing items of +variable length. The first unit in an item contains an opcode, and the length +of the item is either implicit in the opcode or contained in the data that +follows it. + +In many cases listed below, LINK_SIZE data values are specified for offsets +within the compiled pattern. LINK_SIZE always specifies a number of bytes. The +default value for LINK_SIZE is 2, but PCRE can be compiled to use 3-byte or +4-byte values for these offsets, although this impairs the performance. (3-byte +LINK_SIZE values are available only in 8-bit mode.) Specifing a LINK_SIZE +larger than 2 is necessary only when patterns whose compiled length is greater +than 64K are going to be processed. In this description, we assume the "normal" +compilation options. Data values that are counts (e.g. quantifiers) are two +bytes long in 8-bit mode (most significant byte first), or one unit in 16-bit +and 32-bit modes. + + +Opcodes with no following data +------------------------------ + +These items are all just one unit long + + OP_END end of pattern + OP_ANY match any one character other than newline + OP_ALLANY match any one character, including newline + OP_ANYBYTE match any single unit, even in UTF-8/16 mode + OP_SOD match start of data: \A + OP_SOM, start of match (subject + offset): \G + OP_SET_SOM, set start of match (\K) + OP_CIRC ^ (start of data) + OP_CIRCM ^ multiline mode (start of data or after newline) + OP_NOT_WORD_BOUNDARY \W + OP_WORD_BOUNDARY \w + OP_NOT_DIGIT \D + OP_DIGIT \d + OP_NOT_HSPACE \H + OP_HSPACE \h + OP_NOT_WHITESPACE \S + OP_WHITESPACE \s + OP_NOT_VSPACE \V + OP_VSPACE \v + OP_NOT_WORDCHAR \W + OP_WORDCHAR \w + OP_EODN match end of data or newline at end: \Z + OP_EOD match end of data: \z + OP_DOLL $ (end of data, or before final newline) + OP_DOLLM $ multiline mode (end of data or before newline) + OP_EXTUNI match an extended Unicode grapheme cluster + OP_ANYNL match any Unicode newline sequence + + OP_ASSERT_ACCEPT ) + OP_ACCEPT ) These are Perl 5.10's "backtracking control + OP_COMMIT ) verbs". If OP_ACCEPT is inside capturing + OP_FAIL ) parentheses, it may be preceded by one or more + OP_PRUNE ) OP_CLOSE, each followed by a count that + OP_SKIP ) indicates which parentheses must be closed. + OP_THEN ) + +OP_ASSERT_ACCEPT is used when (*ACCEPT) is encountered within an assertion. +This ends the assertion, not the entire pattern match. + + +Backtracking control verbs with optional data +--------------------------------------------- + +(*THEN) without an argument generates the opcode OP_THEN and no following data. +OP_MARK is followed by the mark name, preceded by a one-unit length, and +followed by a binary zero. For (*PRUNE), (*SKIP), and (*THEN) with arguments, +the opcodes OP_PRUNE_ARG, OP_SKIP_ARG, and OP_THEN_ARG are used, with the name +following in the same format as OP_MARK. + + +Matching literal characters +--------------------------- + +The OP_CHAR opcode is followed by a single character that is to be matched +casefully. For caseless matching, OP_CHARI is used. In UTF-8 or UTF-16 modes, +the character may be more than one unit long. In UTF-32 mode, characters +are always exactly one unit long. + +If there is only one character in a character class, OP_CHAR or OP_CHARI is +used for a positive class, and OP_NOT or OP_NOTI for a negative one (that is, +for something like [^a]). + + +Repeating single characters +--------------------------- + +The common repeats (*, +, ?), when applied to a single character, use the +following opcodes, which come in caseful and caseless versions: + + Caseful Caseless + OP_STAR OP_STARI + OP_MINSTAR OP_MINSTARI + OP_POSSTAR OP_POSSTARI + OP_PLUS OP_PLUSI + OP_MINPLUS OP_MINPLUSI + OP_POSPLUS OP_POSPLUSI + OP_QUERY OP_QUERYI + OP_MINQUERY OP_MINQUERYI + OP_POSQUERY OP_POSQUERYI + +Each opcode is followed by the character that is to be repeated. In ASCII mode, +these are two-unit items; in UTF-8 or UTF-16 modes, the length is variable; in +UTF-32 mode these are one-unit items. Those with "MIN" in their names are the +minimizing versions. Those with "POS" in their names are possessive versions. +Other repeats make use of these opcodes: + + Caseful Caseless + OP_UPTO OP_UPTOI + OP_MINUPTO OP_MINUPTOI + OP_POSUPTO OP_POSUPTOI + OP_EXACT OP_EXACTI + +Each of these is followed by a count and then the repeated character. OP_UPTO +matches from 0 to the given number. A repeat with a non-zero minimum and a +fixed maximum is coded as an OP_EXACT followed by an OP_UPTO (or OP_MINUPTO or +OPT_POSUPTO). + +Another set of matching repeating opcodes (called OP_NOTSTAR, OP_NOTSTARI, +etc.) are used for repeated, negated, single-character classes such as [^a]*. +The normal single-character opcodes (OP_STAR, etc.) are used for repeated +positive single-character classes. + + +Repeating character types +------------------------- + +Repeats of things like \d are done exactly as for single characters, except +that instead of a character, the opcode for the type is stored in the data +unit. The opcodes are: + + OP_TYPESTAR + OP_TYPEMINSTAR + OP_TYPEPOSSTAR + OP_TYPEPLUS + OP_TYPEMINPLUS + OP_TYPEPOSPLUS + OP_TYPEQUERY + OP_TYPEMINQUERY + OP_TYPEPOSQUERY + OP_TYPEUPTO + OP_TYPEMINUPTO + OP_TYPEPOSUPTO + OP_TYPEEXACT + + +Match by Unicode property +------------------------- + +OP_PROP and OP_NOTPROP are used for positive and negative matches of a +character by testing its Unicode property (the \p and \P escape sequences). +Each is followed by two units that encode the desired property as a type and a +value. The types are a set of #defines of the form PT_xxx, and the values are +enumerations of the form ucp_xx, defined in the ucp.h source file. The value is +relevant only for PT_GC (General Category), PT_PC (Particular Category), and +PT_SC (Script). + +Repeats of these items use the OP_TYPESTAR etc. set of opcodes, followed by +three units: OP_PROP or OP_NOTPROP, and then the desired property type and +value. + + +Character classes +----------------- + +If there is only one character in a class, OP_CHAR or OP_CHARI is used for a +positive class, and OP_NOT or OP_NOTI for a negative one (that is, for +something like [^a]). + +A set of repeating opcodes (called OP_NOTSTAR etc.) are used for repeated, +negated, single-character classes. The normal single-character opcodes +(OP_STAR, etc.) are used for repeated positive single-character classes. + +When there is more than one character in a class, and all the code points are +less than 256, OP_CLASS is used for a positive class, and OP_NCLASS for a +negative one. In either case, the opcode is followed by a 32-byte (16-short, +8-word) bit map containing a 1 bit for every character that is acceptable. The +bits are counted from the least significant end of each unit. In caseless mode, +bits for both cases are set. + +The reason for having both OP_CLASS and OP_NCLASS is so that, in UTF-8/16/32 +mode, subject characters with values greater than 255 can be handled correctly. +For OP_CLASS they do not match, whereas for OP_NCLASS they do. + +For classes containing characters with values greater than 255 or that contain +\p or \P, OP_XCLASS is used. It optionally uses a bit map if any code points +are less than 256, followed by a list of pairs (for a range) and single +characters. In caseless mode, both cases are explicitly listed. + +OP_XCLASS is followed by a unit containing flag bits: XCL_NOT indicates that +this is a negative class, and XCL_MAP indicates that a bit map is present. +There follows the bit map, if XCL_MAP is set, and then a sequence of items +coded as follows: + + XCL_END marks the end of the list + XCL_SINGLE one character follows + XCL_RANGE two characters follow + XCL_PROP a Unicode property (type, value) follows + XCL_NOTPROP a Unicode property (type, value) follows + +If a range starts with a code point less than 256 and ends with one greater +than 256, an XCL_RANGE item is used, without setting any bits in the bit map. +This means that if no other items in the class set bits in the map, a map is +not needed. + + +Back references +--------------- + +OP_REF (caseful) or OP_REFI (caseless) is followed by a count containing the +reference number if the reference is to a unique capturing group (either by +number or by name). When named groups are used, there may be more than one +group with the same name. In this case, a reference by name generates OP_DNREF +or OP_DNREFI. These are followed by two counts: the index (not the byte offset) +in the group name table of the first entry for the requred name, followed by +the number of groups with the same name. + + +Repeating character classes and back references +----------------------------------------------- + +Single-character classes are handled specially (see above). This section +applies to other classes and also to back references. In both cases, the repeat +information follows the base item. The matching code looks at the following +opcode to see if it is one of + + OP_CRSTAR + OP_CRMINSTAR + OP_CRPOSSTAR + OP_CRPLUS + OP_CRMINPLUS + OP_CRPOSPLUS + OP_CRQUERY + OP_CRMINQUERY + OP_CRPOSQUERY + OP_CRRANGE + OP_CRMINRANGE + OP_CRPOSRANGE + +All but the last three are single-unit items, with no data. The others are +followed by the minimum and maximum repeat counts. + + +Brackets and alternation +------------------------ + +A pair of non-capturing round brackets is wrapped round each expression at +compile time, so alternation always happens in the context of brackets. + +[Note for North Americans: "bracket" to some English speakers, including +myself, can be round, square, curly, or pointy. Hence this usage rather than +"parentheses".] + +Non-capturing brackets use the opcode OP_BRA. Originally PCRE was limited to 99 +capturing brackets and it used a different opcode for each one. From release +3.5, the limit was removed by putting the bracket number into the data for +higher-numbered brackets. From release 7.0 all capturing brackets are handled +this way, using the single opcode OP_CBRA. + +A bracket opcode is followed by LINK_SIZE bytes which give the offset to the +next alternative OP_ALT or, if there aren't any branches, to the matching +OP_KET opcode. Each OP_ALT is followed by LINK_SIZE bytes giving the offset to +the next one, or to the OP_KET opcode. For capturing brackets, the bracket +number is a count that immediately follows the offset. + +OP_KET is used for subpatterns that do not repeat indefinitely, and OP_KETRMIN +and OP_KETRMAX are used for indefinite repetitions, minimally or maximally +respectively (see below for possessive repetitions). All three are followed by +LINK_SIZE bytes giving (as a positive number) the offset back to the matching +bracket opcode. + +If a subpattern is quantified such that it is permitted to match zero times, it +is preceded by one of OP_BRAZERO, OP_BRAMINZERO, or OP_SKIPZERO. These are +single-unit opcodes that tell the matcher that skipping the following +subpattern entirely is a valid branch. In the case of the first two, not +skipping the pattern is also valid (greedy and non-greedy). The third is used +when a pattern has the quantifier {0,0}. It cannot be entirely discarded, +because it may be called as a subroutine from elsewhere in the regex. + +A subpattern with an indefinite maximum repetition is replicated in the +compiled data its minimum number of times (or once with OP_BRAZERO if the +minimum is zero), with the final copy terminating with OP_KETRMIN or OP_KETRMAX +as appropriate. + +A subpattern with a bounded maximum repetition is replicated in a nested +fashion up to the maximum number of times, with OP_BRAZERO or OP_BRAMINZERO +before each replication after the minimum, so that, for example, (abc){2,5} is +compiled as (abc)(abc)((abc)((abc)(abc)?)?)?, except that each bracketed group +has the same number. + +When a repeated subpattern has an unbounded upper limit, it is checked to see +whether it could match an empty string. If this is the case, the opcode in the +final replication is changed to OP_SBRA or OP_SCBRA. This tells the matcher +that it needs to check for matching an empty string when it hits OP_KETRMIN or +OP_KETRMAX, and if so, to break the loop. + + +Possessive brackets +------------------- + +When a repeated group (capturing or non-capturing) is marked as possessive by +the "+" notation, e.g. (abc)++, different opcodes are used. Their names all +have POS on the end, e.g. OP_BRAPOS instead of OP_BRA and OP_SCPBRPOS instead +of OP_SCBRA. The end of such a group is marked by OP_KETRPOS. If the minimum +repetition is zero, the group is preceded by OP_BRAPOSZERO. + + +Once-only (atomic) groups +------------------------- + +These are just like other subpatterns, but they start with the opcode +OP_ONCE or OP_ONCE_NC. The former is used when there are no capturing brackets +within the atomic group; the latter when there are. The distinction is needed +for when there is a backtrack to before the group - any captures within the +group must be reset, so it is necessary to retain backtracking points inside +the group even after it is complete in order to do this. When there are no +captures in an atomic group, all the backtracking can be discarded when it is +complete. This is more efficient, and also uses less stack. + +The check for matching an empty string in an unbounded repeat is handled +entirely at runtime, so there are just these two opcodes for atomic groups. + + +Assertions +---------- + +Forward assertions are also just like other subpatterns, but starting with one +of the opcodes OP_ASSERT or OP_ASSERT_NOT. Backward assertions use the opcodes +OP_ASSERTBACK and OP_ASSERTBACK_NOT, and the first opcode inside the assertion +is OP_REVERSE, followed by a count of the number of characters to move back the +pointer in the subject string. In ASCII mode, the count is a number of units, +but in UTF-8/16 mode each character may occupy more than one unit; in UTF-32 +mode each character occupies exactly one unit. A separate count is present in +each alternative of a lookbehind assertion, allowing them to have different +fixed lengths. + + +Conditional subpatterns +----------------------- + +These are like other subpatterns, but they start with the opcode OP_COND, or +OP_SCOND for one that might match an empty string in an unbounded repeat. If +the condition is a back reference, this is stored at the start of the +subpattern using the opcode OP_CREF followed by a count containing the +reference number, provided that the reference is to a unique capturing group. +If the reference was by name and there is more than one group with that name, +OP_DNCREF is used instead. It is followed by two counts: the index in the group +names table, and the number of groups with the same name. + +If the condition is "in recursion" (coded as "(?(R)"), or "in recursion of +group x" (coded as "(?(Rx)"), the group number is stored at the start of the +subpattern using the opcode OP_RREF (with a value of zero for "the whole +pattern") or OP_DNRREF (with data as for OP_DNCREF). For a DEFINE condition, +just the single unit OP_DEF is used (it has no associated data). Otherwise, a +conditional subpattern always starts with one of the assertions. + + +Recursion +--------- + +Recursion either matches the current regex, or some subexpression. The opcode +OP_RECURSE is followed by aLINK_SIZE value that is the offset to the starting +bracket from the start of the whole pattern. From release 6.5, OP_RECURSE is +automatically wrapped inside OP_ONCE brackets, because otherwise some patterns +broke it. OP_RECURSE is also used for "subroutine" calls, even though they are +not strictly a recursion. + + +Callout +------- + +OP_CALLOUT is followed by one unit of data that holds a callout number in the +range 0 to 254 for manual callouts, or 255 for an automatic callout. In both +cases there follows a count giving the offset in the pattern string to the +start of the following item, and another count giving the length of this item. +These values make is possible for pcretest to output useful tracing information +using automatic callouts. + +Philip Hazel +November 2013 diff --git a/plugins/Pcre16/docs/LICENCE b/plugins/Pcre16/docs/LICENCE new file mode 100644 index 0000000000..602e4ae680 --- /dev/null +++ b/plugins/Pcre16/docs/LICENCE @@ -0,0 +1,92 @@ +PCRE LICENCE +------------ + +PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + +Release 8 of PCRE is distributed under the terms of the "BSD" licence, as +specified below. The documentation for PCRE, supplied in the "doc" +directory, is distributed under the same terms as the software itself. + +The basic library functions are written in C and are freestanding. Also +included in the distribution is a set of C++ wrapper functions, and a +just-in-time compiler that can be used to optimize pattern matching. These +are both optional features that can be omitted when the library is built. + + +THE BASIC LIBRARY FUNCTIONS +--------------------------- + +Written by: Philip Hazel +Email local part: ph10 +Email domain: cam.ac.uk + +University of Cambridge Computing Service, +Cambridge, England. + +Copyright (c) 1997-2014 University of Cambridge +All rights reserved. + + +PCRE JUST-IN-TIME COMPILATION SUPPORT +------------------------------------- + +Written by: Zoltan Herczeg +Email local part: hzmester +Emain domain: freemail.hu + +Copyright(c) 2010-2014 Zoltan Herczeg +All rights reserved. + + +STACK-LESS JUST-IN-TIME COMPILER +-------------------------------- + +Written by: Zoltan Herczeg +Email local part: hzmester +Emain domain: freemail.hu + +Copyright(c) 2009-2014 Zoltan Herczeg +All rights reserved. + + +THE C++ WRAPPER FUNCTIONS +------------------------- + +Contributed by: Google Inc. + +Copyright (c) 2007-2012, Google Inc. +All rights reserved. + + +THE "BSD" LICENCE +----------------- + +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the name of Google + Inc. nor the names of their contributors may be used to endorse or + promote products derived from this software without specific prior + written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. + +End diff --git a/plugins/Pcre16/docs/NEWS b/plugins/Pcre16/docs/NEWS new file mode 100644 index 0000000000..6331e9908d --- /dev/null +++ b/plugins/Pcre16/docs/NEWS @@ -0,0 +1,693 @@ +News about PCRE releases +------------------------ + +Release 8.35 04-April-2014 +-------------------------- + +There have been performance improvements for classes containing non-ASCII +characters and the "auto-possessification" feature has been extended. Other +minor improvements have been implemented and bugs fixed. There is a new callout +feature to enable applications to do detailed stack checks at compile time, to +avoid running out of stack for deeply nested parentheses. The JIT compiler has +been extended with experimental support for ARM-64, MIPS-64, and PPC-LE. + + +Release 8.34 15-December-2013 +----------------------------- + +As well as fixing the inevitable bugs, performance has been improved by +refactoring and extending the amount of "auto-possessification" that PCRE does. +Other notable changes: + +. Implemented PCRE_INFO_MATCH_EMPTY, which yields 1 if the pattern can match + an empty string. If it can, pcretest shows this in its information output. + +. A back reference to a named subpattern when there is more than one of the + same name now checks them in the order in which they appear in the pattern. + The first one that is set is used for the reference. Previously only the + first one was inspected. This change makes PCRE more compatible with Perl. + +. Unicode character properties were updated from Unicode 6.3.0. + +. The character VT has been added to the set of characters that match \s and + are generally treated as white space, following this same change in Perl + 5.18. There is now no difference between "Perl space" and "POSIX space". + +. Perl has changed its handling of \8 and \9. If there is no previously + encountered capturing group of those numbers, they are treated as the + literal characters 8 and 9 instead of a binary zero followed by the + literals. PCRE now does the same. + +. Following Perl, added \o{} to specify codepoints in octal, making it + possible to specify values greater than 0777 and also making them + unambiguous. + +. In UCP mode, \s was not matching two of the characters that Perl matches, + namely NEL (U+0085) and MONGOLIAN VOWEL SEPARATOR (U+180E), though they + were matched by \h. + +. Add JIT support for the 64 bit TileGX architecture. + +. Upgraded the handling of the POSIX classes [:graph:], [:print:], and + [:punct:] when PCRE_UCP is set so as to include the same characters as Perl + does in Unicode mode. + +. Perl no longer allows group names to start with digits, so I have made this + change also in PCRE. + +. Added support for [[:<:]] and [[:>:]] as used in the BSD POSIX library to + mean "start of word" and "end of word", respectively, as a transition aid. + + +Release 8.33 28-May-2013 +-------------------------- + +A number of bugs are fixed, and some performance improvements have been made. +There are also some new features, of which these are the most important: + +. The behaviour of the backtracking verbs has been rationalized and + documented in more detail. + +. JIT now supports callouts and all of the backtracking verbs. + +. Unicode validation has been updated in the light of Unicode Corrigendum #9, + which points out that "non characters" are not "characters that may not + appear in Unicode strings" but rather "characters that are reserved for + internal use and have only local meaning". + +. (*LIMIT_MATCH=d) and (*LIMIT_RECURSION=d) have been added so that the + creator of a pattern can specify lower (but not higher) limits for the + matching process. + +. The PCRE_NEVER_UTF option is available to prevent pattern-writers from using + the (*UTF) feature, as this could be a security issue. + + +Release 8.32 30-November-2012 +----------------------------- + +This release fixes a number of bugs, but also has some new features. These are +the highlights: + +. There is now support for 32-bit character strings and UTF-32. Like the + 16-bit support, this is done by compiling a separate 32-bit library. + +. \X now matches a Unicode extended grapheme cluster. + +. Case-independent matching of Unicode characters that have more than one + "other case" now makes all three (or more) characters equivalent. This + applies, for example, to Greek Sigma, which has two lowercase versions. + +. Unicode character properties are updated to Unicode 6.2.0. + +. The EBCDIC support, which had decayed, has had a spring clean. + +. A number of JIT optimizations have been added, which give faster JIT + execution speed. In addition, a new direct interface to JIT execution is + available. This bypasses some of the sanity checks of pcre_exec() to give a + noticeable speed-up. + +. A number of issues in pcregrep have been fixed, making it more compatible + with GNU grep. In particular, --exclude and --include (and variants) apply + to all files now, not just those obtained from scanning a directory + recursively. In Windows environments, the default action for directories is + now "skip" instead of "read" (which provokes an error). + +. If the --only-matching (-o) option in pcregrep is specified multiple + times, each one causes appropriate output. For example, -o1 -o2 outputs the + substrings matched by the 1st and 2nd capturing parentheses. A separating + string can be specified by --om-separator (default empty). + +. When PCRE is built via Autotools using a version of gcc that has the + "visibility" feature, it is used to hide internal library functions that are + not part of the public API. + + +Release 8.31 06-July-2012 +------------------------- + +This is mainly a bug-fixing release, with a small number of developments: + +. The JIT compiler now supports partial matching and the (*MARK) and + (*COMMIT) verbs. + +. PCRE_INFO_MAXLOOKBEHIND can be used to find the longest lookbehind in a + pattern. + +. There should be a performance improvement when using the heap instead of the + stack for recursion. + +. pcregrep can now be linked with libedit as an alternative to libreadline. + +. pcregrep now has a --file-list option where the list of files to scan is + given as a file. + +. pcregrep now recognizes binary files and there are related options. + +. The Unicode tables have been updated to 6.1.0. + +As always, the full list of changes is in the ChangeLog file. + + +Release 8.30 04-February-2012 +----------------------------- + +Release 8.30 introduces a major new feature: support for 16-bit character +strings, compiled as a separate library. There are a few changes to the +8-bit library, in addition to some bug fixes. + +. The pcre_info() function, which has been obsolete for over 10 years, has + been removed. + +. When a compiled pattern was saved to a file and later reloaded on a host + with different endianness, PCRE used automatically to swap the bytes in some + of the data fields. With the advent of the 16-bit library, where more of this + swapping is needed, it is no longer done automatically. Instead, the bad + endianness is detected and a specific error is given. The user can then call + a new function called pcre_pattern_to_host_byte_order() (or an equivalent + 16-bit function) to do the swap. + +. In UTF-8 mode, the values 0xd800 to 0xdfff are not legal Unicode + code points and are now faulted. (They are the so-called "surrogates" + that are reserved for coding high values in UTF-16.) + + +Release 8.21 12-Dec-2011 +------------------------ + +This is almost entirely a bug-fix release. The only new feature is the ability +to obtain the size of the memory used by the JIT compiler. + + +Release 8.20 21-Oct-2011 +------------------------ + +The main change in this release is the inclusion of Zoltan Herczeg's +just-in-time compiler support, which can be accessed by building PCRE with +--enable-jit. Large performance benefits can be had in many situations. 8.20 +also fixes an unfortunate bug that was introduced in 8.13 as well as tidying up +a number of infelicities and differences from Perl. + + +Release 8.13 16-Aug-2011 +------------------------ + +This is mainly a bug-fix release. There has been a lot of internal refactoring. +The Unicode tables have been updated. The only new feature in the library is +the passing of *MARK information to callouts. Some additions have been made to +pcretest to make testing easier and more comprehensive. There is a new option +for pcregrep to adjust its internal buffer size. + + +Release 8.12 15-Jan-2011 +------------------------ + +This release fixes some bugs in pcregrep, one of which caused the tests to fail +on 64-bit big-endian systems. There are no changes to the code of the library. + + +Release 8.11 10-Dec-2010 +------------------------ + +A number of bugs in the library and in pcregrep have been fixed. As always, see +ChangeLog for details. The following are the non-bug-fix changes: + +. Added --match-limit and --recursion-limit to pcregrep. + +. Added an optional parentheses number to the -o and --only-matching options + of pcregrep. + +. Changed the way PCRE_PARTIAL_HARD affects the matching of $, \z, \Z, \b, and + \B. + +. Added PCRE_ERROR_SHORTUTF8 to make it possible to distinguish between a + bad UTF-8 sequence and one that is incomplete when using PCRE_PARTIAL_HARD. + +. Recognize (*NO_START_OPT) at the start of a pattern to set the PCRE_NO_ + START_OPTIMIZE option, which is now allowed at compile time + + +Release 8.10 25-Jun-2010 +------------------------ + +There are two major additions: support for (*MARK) and friends, and the option +PCRE_UCP, which changes the behaviour of \b, \d, \s, and \w (and their +opposites) so that they make use of Unicode properties. There are also a number +of lesser new features, and several bugs have been fixed. A new option, +--line-buffered, has been added to pcregrep, for use when it is connected to +pipes. + + +Release 8.02 19-Mar-2010 +------------------------ + +Another bug-fix release. + + +Release 8.01 19-Jan-2010 +------------------------ + +This is a bug-fix release. Several bugs in the code itself and some bugs and +infelicities in the build system have been fixed. + + +Release 8.00 19-Oct-09 +---------------------- + +Bugs have been fixed in the library and in pcregrep. There are also some +enhancements. Restrictions on patterns used for partial matching have been +removed, extra information is given for partial matches, the partial matching +process has been improved, and an option to make a partial match override a +full match is available. The "study" process has been enhanced by finding a +lower bound matching length. Groups with duplicate numbers may now have +duplicated names without the use of PCRE_DUPNAMES. However, they may not have +different names. The documentation has been revised to reflect these changes. +The version number has been expanded to 3 digits as it is clear that the rate +of change is not slowing down. + + +Release 7.9 11-Apr-09 +--------------------- + +Mostly bugfixes and tidies with just a couple of minor functional additions. + + +Release 7.8 05-Sep-08 +--------------------- + +More bug fixes, plus a performance improvement in Unicode character property +lookup. + + +Release 7.7 07-May-08 +--------------------- + +This is once again mainly a bug-fix release, but there are a couple of new +features. + + +Release 7.6 28-Jan-08 +--------------------- + +The main reason for having this release so soon after 7.5 is because it fixes a +potential buffer overflow problem in pcre_compile() when run in UTF-8 mode. In +addition, the CMake configuration files have been brought up to date. + + +Release 7.5 10-Jan-08 +--------------------- + +This is mainly a bug-fix release. However the ability to link pcregrep with +libz or libbz2 and the ability to link pcretest with libreadline have been +added. Also the --line-offsets and --file-offsets options were added to +pcregrep. + + +Release 7.4 21-Sep-07 +--------------------- + +The only change of specification is the addition of options to control whether +\R matches any Unicode line ending (the default) or just CR, LF, and CRLF. +Otherwise, the changes are bug fixes and a refactoring to reduce the number of +relocations needed in a shared library. There have also been some documentation +updates, in particular, some more information about using CMake to build PCRE +has been added to the NON-UNIX-USE file. + + +Release 7.3 28-Aug-07 +--------------------- + +Most changes are bug fixes. Some that are not: + +1. There is some support for Perl 5.10's experimental "backtracking control + verbs" such as (*PRUNE). + +2. UTF-8 checking is now as per RFC 3629 instead of RFC 2279; this is more + restrictive in the strings it accepts. + +3. Checking for potential integer overflow has been made more dynamic, and as a + consequence there is no longer a hard limit on the size of a subpattern that + has a limited repeat count. + +4. When CRLF is a valid line-ending sequence, pcre_exec() and pcre_dfa_exec() + no longer advance by two characters instead of one when an unanchored match + fails at CRLF if there are explicit CR or LF matches within the pattern. + This gets rid of some anomalous effects that previously occurred. + +5. Some PCRE-specific settings for varying the newline options at the start of + a pattern have been added. + + +Release 7.2 19-Jun-07 +--------------------- + +WARNING: saved patterns that were compiled by earlier versions of PCRE must be +recompiled for use with 7.2 (necessitated by the addition of \K, \h, \H, \v, +and \V). + +Correction to the notes for 7.1: the note about shared libraries for Windows is +wrong. Previously, three libraries were built, but each could function +independently. For example, the pcreposix library also included all the +functions from the basic pcre library. The change is that the three libraries +are no longer independent. They are like the Unix libraries. To use the +pcreposix functions, for example, you need to link with both the pcreposix and +the basic pcre library. + +Some more features from Perl 5.10 have been added: + + (?-n) and (?+n) relative references for recursion and subroutines. + + (?(-n) and (?(+n) relative references as conditions. + + \k{name} and \g{name} are synonyms for \k<name>. + + \K to reset the start of the matched string; for example, (foo)\Kbar + matches bar preceded by foo, but only sets bar as the matched string. + + (?| introduces a group where the capturing parentheses in each alternative + start from the same number; for example, (?|(abc)|(xyz)) sets capturing + parentheses number 1 in both cases. + + \h, \H, \v, \V match horizontal and vertical whitespace, respectively. + + +Release 7.1 24-Apr-07 +--------------------- + +There is only one new feature in this release: a linebreak setting of +PCRE_NEWLINE_ANYCRLF. It is a cut-down version of PCRE_NEWLINE_ANY, which +recognizes only CRLF, CR, and LF as linebreaks. + +A few bugs are fixed (see ChangeLog for details), but the major change is a +complete re-implementation of the build system. This now has full Autotools +support and so is now "standard" in some sense. It should help with compiling +PCRE in a wide variety of environments. + +NOTE: when building shared libraries for Windows, three dlls are now built, +called libpcre, libpcreposix, and libpcrecpp. Previously, everything was +included in a single dll. + +Another important change is that the dftables auxiliary program is no longer +compiled and run at "make" time by default. Instead, a default set of character +tables (assuming ASCII coding) is used. If you want to use dftables to generate +the character tables as previously, add --enable-rebuild-chartables to the +"configure" command. You must do this if you are compiling PCRE to run on a +system that uses EBCDIC code. + +There is a discussion about character tables in the README file. The default is +not to use dftables so that that there is no problem when cross-compiling. + + +Release 7.0 19-Dec-06 +--------------------- + +This release has a new major number because there have been some internal +upheavals to facilitate the addition of new optimizations and other facilities, +and to make subsequent maintenance and extension easier. Compilation is likely +to be a bit slower, but there should be no major effect on runtime performance. +Previously compiled patterns are NOT upwards compatible with this release. If +you have saved compiled patterns from a previous release, you will have to +re-compile them. Important changes that are visible to users are: + +1. The Unicode property tables have been updated to Unicode 5.0.0, which adds + some more scripts. + +2. The option PCRE_NEWLINE_ANY causes PCRE to recognize any Unicode newline + sequence as a newline. + +3. The \R escape matches a single Unicode newline sequence as a single unit. + +4. New features that will appear in Perl 5.10 are now in PCRE. These include + alternative Perl syntax for named parentheses, and Perl syntax for + recursion. + +5. The C++ wrapper interface has been extended by the addition of a + QuoteMeta function and the ability to allow copy construction and + assignment. + +For a complete list of changes, see the ChangeLog file. + + +Release 6.7 04-Jul-06 +--------------------- + +The main additions to this release are the ability to use the same name for +multiple sets of parentheses, and support for CRLF line endings in both the +library and pcregrep (and in pcretest for testing). + +Thanks to Ian Taylor, the stack usage for many kinds of pattern has been +significantly reduced for certain subject strings. + + +Release 6.5 01-Feb-06 +--------------------- + +Important changes in this release: + +1. A number of new features have been added to pcregrep. + +2. The Unicode property tables have been updated to Unicode 4.1.0, and the + supported properties have been extended with script names such as "Arabic", + and the derived properties "Any" and "L&". This has necessitated a change to + the interal format of compiled patterns. Any saved compiled patterns that + use \p or \P must be recompiled. + +3. The specification of recursion in patterns has been changed so that all + recursive subpatterns are automatically treated as atomic groups. Thus, for + example, (?R) is treated as if it were (?>(?R)). This is necessary because + otherwise there are situations where recursion does not work. + +See the ChangeLog for a complete list of changes, which include a number of bug +fixes and tidies. + + +Release 6.0 07-Jun-05 +--------------------- + +The release number has been increased to 6.0 because of the addition of several +major new pieces of functionality. + +A new function, pcre_dfa_exec(), which implements pattern matching using a DFA +algorithm, has been added. This has a number of advantages for certain cases, +though it does run more slowly, and lacks the ability to capture substrings. On +the other hand, it does find all matches, not just the first, and it works +better for partial matching. The pcrematching man page discusses the +differences. + +The pcretest program has been enhanced so that it can make use of the new +pcre_dfa_exec() matching function and the extra features it provides. + +The distribution now includes a C++ wrapper library. This is built +automatically if a C++ compiler is found. The pcrecpp man page discusses this +interface. + +The code itself has been re-organized into many more files, one for each +function, so it no longer requires everything to be linked in when static +linkage is used. As a consequence, some internal functions have had to have +their names exposed. These functions all have names starting with _pcre_. They +are undocumented, and are not intended for use by outside callers. + +The pcregrep program has been enhanced with new functionality such as +multiline-matching and options for output more matching context. See the +ChangeLog for a complete list of changes to the library and the utility +programs. + + +Release 5.0 13-Sep-04 +--------------------- + +The licence under which PCRE is released has been changed to the more +conventional "BSD" licence. + +In the code, some bugs have been fixed, and there are also some major changes +in this release (which is why I've increased the number to 5.0). Some changes +are internal rearrangements, and some provide a number of new facilities. The +new features are: + +1. There's an "automatic callout" feature that inserts callouts before every + item in the regex, and there's a new callout field that gives the position + in the pattern - useful for debugging and tracing. + +2. The extra_data structure can now be used to pass in a set of character + tables at exec time. This is useful if compiled regex are saved and re-used + at a later time when the tables may not be at the same address. If the + default internal tables are used, the pointer saved with the compiled + pattern is now set to NULL, which means that you don't need to do anything + special unless you are using custom tables. + +3. It is possible, with some restrictions on the content of the regex, to + request "partial" matching. A special return code is given if all of the + subject string matched part of the regex. This could be useful for testing + an input field as it is being typed. + +4. There is now some optional support for Unicode character properties, which + means that the patterns items such as \p{Lu} and \X can now be used. Only + the general category properties are supported. If PCRE is compiled with this + support, an additional 90K data structure is include, which increases the + size of the library dramatically. + +5. There is support for saving compiled patterns and re-using them later. + +6. There is support for running regular expressions that were compiled on a + different host with the opposite endianness. + +7. The pcretest program has been extended to accommodate the new features. + +The main internal rearrangement is that sequences of literal characters are no +longer handled as strings. Instead, each character is handled on its own. This +makes some UTF-8 handling easier, and makes the support of partial matching +possible. Compiled patterns containing long literal strings will be larger as a +result of this change; I hope that performance will not be much affected. + + +Release 4.5 01-Dec-03 +--------------------- + +Again mainly a bug-fix and tidying release, with only a couple of new features: + +1. It's possible now to compile PCRE so that it does not use recursive +function calls when matching. Instead it gets memory from the heap. This slows +things down, but may be necessary on systems with limited stacks. + +2. UTF-8 string checking has been tightened to reject overlong sequences and to +check that a starting offset points to the start of a character. Failure of the +latter returns a new error code: PCRE_ERROR_BADUTF8_OFFSET. + +3. PCRE can now be compiled for systems that use EBCDIC code. + + +Release 4.4 21-Aug-03 +--------------------- + +This is mainly a bug-fix and tidying release. The only new feature is that PCRE +checks UTF-8 strings for validity by default. There is an option to suppress +this, just in case anybody wants that teeny extra bit of performance. + + +Releases 4.1 - 4.3 +------------------ + +Sorry, I forgot about updating the NEWS file for these releases. Please take a +look at ChangeLog. + + +Release 4.0 17-Feb-03 +--------------------- + +There have been a lot of changes for the 4.0 release, adding additional +functionality and mending bugs. Below is a list of the highlights of the new +functionality. For full details of these features, please consult the +documentation. For a complete list of changes, see the ChangeLog file. + +1. Support for Perl's \Q...\E escapes. + +2. "Possessive quantifiers" ?+, *+, ++, and {,}+ which come from Sun's Java +package. They provide some syntactic sugar for simple cases of "atomic +grouping". + +3. Support for the \G assertion. It is true when the current matching position +is at the start point of the match. + +4. A new feature that provides some of the functionality that Perl provides +with (?{...}). The facility is termed a "callout". The way it is done in PCRE +is for the caller to provide an optional function, by setting pcre_callout to +its entry point. To get the function called, the regex must include (?C) at +appropriate points. + +5. Support for recursive calls to individual subpatterns. This makes it really +easy to get totally confused. + +6. Support for named subpatterns. The Python syntax (?P<name>...) is used to +name a group. + +7. Several extensions to UTF-8 support; it is now fairly complete. There is an +option for pcregrep to make it operate in UTF-8 mode. + +8. The single man page has been split into a number of separate man pages. +These also give rise to individual HTML pages which are put in a separate +directory. There is an index.html page that lists them all. Some hyperlinking +between the pages has been installed. + + +Release 3.5 15-Aug-01 +--------------------- + +1. The configuring system has been upgraded to use later versions of autoconf +and libtool. By default it builds both a shared and a static library if the OS +supports it. You can use --disable-shared or --disable-static on the configure +command if you want only one of them. + +2. The pcretest utility is now installed along with pcregrep because it is +useful for users (to test regexs) and by doing this, it automatically gets +relinked by libtool. The documentation has been turned into a man page, so +there are now .1, .txt, and .html versions in /doc. + +3. Upgrades to pcregrep: + (i) Added long-form option names like gnu grep. + (ii) Added --help to list all options with an explanatory phrase. + (iii) Added -r, --recursive to recurse into sub-directories. + (iv) Added -f, --file to read patterns from a file. + +4. Added --enable-newline-is-cr and --enable-newline-is-lf to the configure +script, to force use of CR or LF instead of \n in the source. On non-Unix +systems, the value can be set in config.h. + +5. The limit of 200 on non-capturing parentheses is a _nesting_ limit, not an +absolute limit. Changed the text of the error message to make this clear, and +likewise updated the man page. + +6. The limit of 99 on the number of capturing subpatterns has been removed. +The new limit is 65535, which I hope will not be a "real" limit. + + +Release 3.3 01-Aug-00 +--------------------- + +There is some support for UTF-8 character strings. This is incomplete and +experimental. The documentation describes what is and what is not implemented. +Otherwise, this is just a bug-fixing release. + + +Release 3.0 01-Feb-00 +--------------------- + +1. A "configure" script is now used to configure PCRE for Unix systems. It +builds a Makefile, a config.h file, and the pcre-config script. + +2. PCRE is built as a shared library by default. + +3. There is support for POSIX classes such as [:alpha:]. + +5. There is an experimental recursion feature. + +---------------------------------------------------------------------------- + IMPORTANT FOR THOSE UPGRADING FROM VERSIONS BEFORE 2.00 + +Please note that there has been a change in the API such that a larger +ovector is required at matching time, to provide some additional workspace. +The new man page has details. This change was necessary in order to support +some of the new functionality in Perl 5.005. + + IMPORTANT FOR THOSE UPGRADING FROM VERSION 2.00 + +Another (I hope this is the last!) change has been made to the API for the +pcre_compile() function. An additional argument has been added to make it +possible to pass over a pointer to character tables built in the current +locale by pcre_maketables(). To use the default tables, this new argument +should be passed as NULL. + + IMPORTANT FOR THOSE UPGRADING FROM VERSION 2.05 + +Yet another (and again I hope this really is the last) change has been made +to the API for the pcre_exec() function. An additional argument has been +added to make it possible to start the match other than at the start of the +subject string. This is important if there are lookbehinds. The new man +page has the details, but you just want to convert existing programs, all +you need to do is to stick in a new fifth argument to pcre_exec(), with a +value of zero. For example, change + + pcre_exec(pattern, extra, subject, length, options, ovec, ovecsize) +to + pcre_exec(pattern, extra, subject, length, 0, options, ovec, ovecsize) + +**** diff --git a/plugins/Pcre16/docs/NON-AUTOTOOLS-BUILD b/plugins/Pcre16/docs/NON-AUTOTOOLS-BUILD new file mode 100644 index 0000000000..cddf3e0699 --- /dev/null +++ b/plugins/Pcre16/docs/NON-AUTOTOOLS-BUILD @@ -0,0 +1,764 @@ +Building PCRE without using autotools +------------------------------------- + +This document contains the following sections: + + General + Generic instructions for the PCRE C library + The C++ wrapper functions + Building for virtual Pascal + Stack size in Windows environments + Linking programs in Windows environments + Calling conventions in Windows environments + Comments about Win32 builds + Building PCRE on Windows with CMake + Use of relative paths with CMake on Windows + Testing with RunTest.bat + Building under Windows CE with Visual Studio 200x + Building under Windows with BCC5.5 + Building using Borland C++ Builder 2007 (CB2007) and higher + Building PCRE on OpenVMS + Building PCRE on Stratus OpenVOS + Building PCRE on native z/OS and z/VM + + +GENERAL + +I (Philip Hazel) have no experience of Windows or VMS sytems and how their +libraries work. The items in the PCRE distribution and Makefile that relate to +anything other than Linux systems are untested by me. + +There are some other comments and files (including some documentation in CHM +format) in the Contrib directory on the FTP site: + + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/Contrib + +The basic PCRE library consists entirely of code written in Standard C, and so +should compile successfully on any system that has a Standard C compiler and +library. The C++ wrapper functions are a separate issue (see below). + +The PCRE distribution includes a "configure" file for use by the configure/make +(autotools) build system, as found in many Unix-like environments. The README +file contains information about the options for "configure". + +There is also support for CMake, which some users prefer, especially in Windows +environments, though it can also be run in Unix-like environments. See the +section entitled "Building PCRE on Windows with CMake" below. + +Versions of config.h and pcre.h are distributed in the PCRE tarballs under the +names config.h.generic and pcre.h.generic. These are provided for those who +build PCRE without using "configure" or CMake. If you use "configure" or CMake, +the .generic versions are not used. + + +GENERIC INSTRUCTIONS FOR THE PCRE C LIBRARY + +The following are generic instructions for building the PCRE C library "by +hand". If you are going to use CMake, this section does not apply to you; you +can skip ahead to the CMake section. + + (1) Copy or rename the file config.h.generic as config.h, and edit the macro + settings that it contains to whatever is appropriate for your environment. + + In particular, you can alter the definition of the NEWLINE macro to + specify what character(s) you want to be interpreted as line terminators. + In an EBCDIC environment, you MUST change NEWLINE, because its default + value is 10, an ASCII LF. The usual EBCDIC newline character is 21 (0x15, + NL), though in some cases it may be 37 (0x25). + + When you compile any of the PCRE modules, you must specify -DHAVE_CONFIG_H + to your compiler so that config.h is included in the sources. + + An alternative approach is not to edit config.h, but to use -D on the + compiler command line to make any changes that you need to the + configuration options. In this case -DHAVE_CONFIG_H must not be set. + + NOTE: There have been occasions when the way in which certain parameters + in config.h are used has changed between releases. (In the configure/make + world, this is handled automatically.) When upgrading to a new release, + you are strongly advised to review config.h.generic before re-using what + you had previously. + + (2) Copy or rename the file pcre.h.generic as pcre.h. + + (3) EITHER: + Copy or rename file pcre_chartables.c.dist as pcre_chartables.c. + + OR: + Compile dftables.c as a stand-alone program (using -DHAVE_CONFIG_H if + you have set up config.h), and then run it with the single argument + "pcre_chartables.c". This generates a set of standard character tables + and writes them to that file. The tables are generated using the default + C locale for your system. If you want to use a locale that is specified + by LC_xxx environment variables, add the -L option to the dftables + command. You must use this method if you are building on a system that + uses EBCDIC code. + + The tables in pcre_chartables.c are defaults. The caller of PCRE can + specify alternative tables at run time. + + (4) Ensure that you have the following header files: + + pcre_internal.h + ucp.h + + (5) For an 8-bit library, compile the following source files, setting + -DHAVE_CONFIG_H as a compiler option if you have set up config.h with your + configuration, or else use other -D settings to change the configuration + as required. + + pcre_byte_order.c + pcre_chartables.c + pcre_compile.c + pcre_config.c + pcre_dfa_exec.c + pcre_exec.c + pcre_fullinfo.c + pcre_get.c + pcre_globals.c + pcre_jit_compile.c + pcre_maketables.c + pcre_newline.c + pcre_ord2utf8.c + pcre_refcount.c + pcre_string_utils.c + pcre_study.c + pcre_tables.c + pcre_ucd.c + pcre_valid_utf8.c + pcre_version.c + pcre_xclass.c + + Make sure that you include -I. in the compiler command (or equivalent for + an unusual compiler) so that all included PCRE header files are first + sought in the current directory. Otherwise you run the risk of picking up + a previously-installed file from somewhere else. + + Note that you must still compile pcre_jit_compile.c, even if you have not + defined SUPPORT_JIT in config.h, because when JIT support is not + configured, dummy functions are compiled. When JIT support IS configured, + pcre_jit_compile.c #includes sources from the sljit subdirectory, where + there should be 16 files, all of whose names begin with "sljit". + + (6) Now link all the compiled code into an object library in whichever form + your system keeps such libraries. This is the basic PCRE C 8-bit library. + If your system has static and shared libraries, you may have to do this + once for each type. + + (7) If you want to build a 16-bit library (as well as, or instead of the 8-bit + or 32-bit libraries) repeat steps 5-6 with the following files: + + pcre16_byte_order.c + pcre16_chartables.c + pcre16_compile.c + pcre16_config.c + pcre16_dfa_exec.c + pcre16_exec.c + pcre16_fullinfo.c + pcre16_get.c + pcre16_globals.c + pcre16_jit_compile.c + pcre16_maketables.c + pcre16_newline.c + pcre16_ord2utf16.c + pcre16_refcount.c + pcre16_string_utils.c + pcre16_study.c + pcre16_tables.c + pcre16_ucd.c + pcre16_utf16_utils.c + pcre16_valid_utf16.c + pcre16_version.c + pcre16_xclass.c + + (8) If you want to build a 32-bit library (as well as, or instead of the 8-bit + or 16-bit libraries) repeat steps 5-6 with the following files: + + pcre32_byte_order.c + pcre32_chartables.c + pcre32_compile.c + pcre32_config.c + pcre32_dfa_exec.c + pcre32_exec.c + pcre32_fullinfo.c + pcre32_get.c + pcre32_globals.c + pcre32_jit_compile.c + pcre32_maketables.c + pcre32_newline.c + pcre32_ord2utf32.c + pcre32_refcount.c + pcre32_string_utils.c + pcre32_study.c + pcre32_tables.c + pcre32_ucd.c + pcre32_utf32_utils.c + pcre32_valid_utf32.c + pcre32_version.c + pcre32_xclass.c + + (9) If you want to build the POSIX wrapper functions (which apply only to the + 8-bit library), ensure that you have the pcreposix.h file and then compile + pcreposix.c (remembering -DHAVE_CONFIG_H if necessary). Link the result + (on its own) as the pcreposix library. + +(10) The pcretest program can be linked with any combination of the 8-bit, + 16-bit and 32-bit libraries (depending on what you selected in config.h). + Compile pcretest.c and pcre_printint.c (again, don't forget + -DHAVE_CONFIG_H) and link them together with the appropriate library/ies. + If you compiled an 8-bit library, pcretest also needs the pcreposix + wrapper library unless you compiled it with -DNOPOSIX. + +(11) Run pcretest on the testinput files in the testdata directory, and check + that the output matches the corresponding testoutput files. There are + comments about what each test does in the section entitled "Testing PCRE" + in the README file. If you compiled more than one of the 8-bit, 16-bit and + 32-bit libraries, you need to run pcretest with the -16 option to do + 16-bit tests and with the -32 option to do 32-bit tests. + + Some tests are relevant only when certain build-time options are selected. + For example, test 4 is for UTF-8/UTF-16/UTF-32 support, and will not run + if you have built PCRE without it. See the comments at the start of each + testinput file. If you have a suitable Unix-like shell, the RunTest script + will run the appropriate tests for you. The command "RunTest list" will + output a list of all the tests. + + Note that the supplied files are in Unix format, with just LF characters + as line terminators. You may need to edit them to change this if your + system uses a different convention. If you are using Windows, you probably + should use the wintestinput3 file instead of testinput3 (and the + corresponding output file). This is a locale test; wintestinput3 sets the + locale to "french" rather than "fr_FR", and there some minor output + differences. + +(12) If you have built PCRE with SUPPORT_JIT, the JIT features will be tested + by the testdata files. However, you might also like to build and run + the freestanding JIT test program, pcre_jit_test.c. + +(13) If you want to use the pcregrep command, compile and link pcregrep.c; it + uses only the basic 8-bit PCRE library (it does not need the pcreposix + library). + + +THE C++ WRAPPER FUNCTIONS + +The PCRE distribution also contains some C++ wrapper functions and tests, +applicable to the 8-bit library, which were contributed by Google Inc. On a +system that can use "configure" and "make", the functions are automatically +built into a library called pcrecpp. It should be straightforward to compile +the .cc files manually on other systems. The files called xxx_unittest.cc are +test programs for each of the corresponding xxx.cc files. + + +BUILDING FOR VIRTUAL PASCAL + +A script for building PCRE using Borland's C++ compiler for use with VPASCAL +was contributed by Alexander Tokarev. Stefan Weber updated the script and added +additional files. The following files in the distribution are for building PCRE +for use with VP/Borland: makevp_c.txt, makevp_l.txt, makevp.bat, pcregexp.pas. + + +STACK SIZE IN WINDOWS ENVIRONMENTS + +The default processor stack size of 1Mb in some Windows environments is too +small for matching patterns that need much recursion. In particular, test 2 may +fail because of this. Normally, running out of stack causes a crash, but there +have been cases where the test program has just died silently. See your linker +documentation for how to increase stack size if you experience problems. The +Linux default of 8Mb is a reasonable choice for the stack, though even that can +be too small for some pattern/subject combinations. + +PCRE has a compile configuration option to disable the use of stack for +recursion so that heap is used instead. However, pattern matching is +significantly slower when this is done. There is more about stack usage in the +"pcrestack" documentation. + + +LINKING PROGRAMS IN WINDOWS ENVIRONMENTS + +If you want to statically link a program against a PCRE library in the form of +a non-dll .a file, you must define PCRE_STATIC before including pcre.h or +pcrecpp.h, otherwise the pcre_malloc() and pcre_free() exported functions will +be declared __declspec(dllimport), with unwanted results. + + +CALLING CONVENTIONS IN WINDOWS ENVIRONMENTS + +It is possible to compile programs to use different calling conventions using +MSVC. Search the web for "calling conventions" for more information. To make it +easier to change the calling convention for the exported functions in the +PCRE library, the macro PCRE_CALL_CONVENTION is present in all the external +definitions. It can be set externally when compiling (e.g. in CFLAGS). If it is +not set, it defaults to empty; the default calling convention is then used +(which is what is wanted most of the time). + + +COMMENTS ABOUT WIN32 BUILDS (see also "BUILDING PCRE ON WINDOWS WITH CMAKE") + +There are two ways of building PCRE using the "configure, make, make install" +paradigm on Windows systems: using MinGW or using Cygwin. These are not at all +the same thing; they are completely different from each other. There is also +support for building using CMake, which some users find a more straightforward +way of building PCRE under Windows. + +The MinGW home page (http://www.mingw.org/) says this: + + MinGW: A collection of freely available and freely distributable Windows + specific header files and import libraries combined with GNU toolsets that + allow one to produce native Windows programs that do not rely on any + 3rd-party C runtime DLLs. + +The Cygwin home page (http://www.cygwin.com/) says this: + + Cygwin is a Linux-like environment for Windows. It consists of two parts: + + . A DLL (cygwin1.dll) which acts as a Linux API emulation layer providing + substantial Linux API functionality + + . A collection of tools which provide Linux look and feel. + + The Cygwin DLL currently works with all recent, commercially released x86 32 + bit and 64 bit versions of Windows, with the exception of Windows CE. + +On both MinGW and Cygwin, PCRE should build correctly using: + + ./configure && make && make install + +This should create two libraries called libpcre and libpcreposix, and, if you +have enabled building the C++ wrapper, a third one called libpcrecpp. These are +independent libraries: when you link with libpcreposix or libpcrecpp you must +also link with libpcre, which contains the basic functions. (Some earlier +releases of PCRE included the basic libpcre functions in libpcreposix. This no +longer happens.) + +A user submitted a special-purpose patch that makes it easy to create +"pcre.dll" under mingw32 using the "msys" environment. It provides "pcre.dll" +as a special target. If you use this target, no other files are built, and in +particular, the pcretest and pcregrep programs are not built. An example of how +this might be used is: + + ./configure --enable-utf --disable-cpp CFLAGS="-03 -s"; make pcre.dll + +Using Cygwin's compiler generates libraries and executables that depend on +cygwin1.dll. If a library that is generated this way is distributed, +cygwin1.dll has to be distributed as well. Since cygwin1.dll is under the GPL +licence, this forces not only PCRE to be under the GPL, but also the entire +application. A distributor who wants to keep their own code proprietary must +purchase an appropriate Cygwin licence. + +MinGW has no such restrictions. The MinGW compiler generates a library or +executable that can run standalone on Windows without any third party dll or +licensing issues. + +But there is more complication: + +If a Cygwin user uses the -mno-cygwin Cygwin gcc flag, what that really does is +to tell Cygwin's gcc to use the MinGW gcc. Cygwin's gcc is only acting as a +front end to MinGW's gcc (if you install Cygwin's gcc, you get both Cygwin's +gcc and MinGW's gcc). So, a user can: + +. Build native binaries by using MinGW or by getting Cygwin and using + -mno-cygwin. + +. Build binaries that depend on cygwin1.dll by using Cygwin with the normal + compiler flags. + +The test files that are supplied with PCRE are in UNIX format, with LF +characters as line terminators. Unless your PCRE library uses a default newline +option that includes LF as a valid newline, it may be necessary to change the +line terminators in the test files to get some of the tests to work. + + +BUILDING PCRE ON WINDOWS WITH CMAKE + +CMake is an alternative configuration facility that can be used instead of +"configure". CMake creates project files (make files, solution files, etc.) +tailored to numerous development environments, including Visual Studio, +Borland, Msys, MinGW, NMake, and Unix. If possible, use short paths with no +spaces in the names for your CMake installation and your PCRE source and build +directories. + +The following instructions were contributed by a PCRE user. If they are not +followed exactly, errors may occur. In the event that errors do occur, it is +recommended that you delete the CMake cache before attempting to repeat the +CMake build process. In the CMake GUI, the cache can be deleted by selecting +"File > Delete Cache". + +1. Install the latest CMake version available from http://www.cmake.org/, and + ensure that cmake\bin is on your path. + +2. Unzip (retaining folder structure) the PCRE source tree into a source + directory such as C:\pcre. You should ensure your local date and time + is not earlier than the file dates in your source dir if the release is + very new. + +3. Create a new, empty build directory, preferably a subdirectory of the + source dir. For example, C:\pcre\pcre-xx\build. + +4. Run cmake-gui from the Shell envirornment of your build tool, for example, + Msys for Msys/MinGW or Visual Studio Command Prompt for VC/VC++. Do not try + to start Cmake from the Windows Start menu, as this can lead to errors. + +5. Enter C:\pcre\pcre-xx and C:\pcre\pcre-xx\build for the source and build + directories, respectively. + +6. Hit the "Configure" button. + +7. Select the particular IDE / build tool that you are using (Visual + Studio, MSYS makefiles, MinGW makefiles, etc.) + +8. The GUI will then list several configuration options. This is where + you can enable UTF-8 support or other PCRE optional features. + +9. Hit "Configure" again. The adjacent "Generate" button should now be + active. + +10. Hit "Generate". + +11. The build directory should now contain a usable build system, be it a + solution file for Visual Studio, makefiles for MinGW, etc. Exit from + cmake-gui and use the generated build system with your compiler or IDE. + E.g., for MinGW you can run "make", or for Visual Studio, open the PCRE + solution, select the desired configuration (Debug, or Release, etc.) and + build the ALL_BUILD project. + +12. If during configuration with cmake-gui you've elected to build the test + programs, you can execute them by building the test project. E.g., for + MinGW: "make test"; for Visual Studio build the RUN_TESTS project. The + most recent build configuration is targeted by the tests. A summary of + test results is presented. Complete test output is subsequently + available for review in Testing\Temporary under your build dir. + + +USE OF RELATIVE PATHS WITH CMAKE ON WINDOWS + +A PCRE user comments as follows: I thought that others may want to know the +current state of CMAKE_USE_RELATIVE_PATHS support on Windows. Here it is: + +-- AdditionalIncludeDirectories is only partially modified (only the + first path - see below) +-- Only some of the contained file paths are modified - shown below for + pcre.vcproj +-- It properly modifies + +I am sure CMake people can fix that if they want to. Until then one will +need to replace existing absolute paths in project files with relative +paths manually (e.g. from VS) - relative to project file location. I did +just that before being told to try CMAKE_USE_RELATIVE_PATHS. Not a big +deal. + +AdditionalIncludeDirectories="E:\builds\pcre\build;E:\builds\pcre\pcre-7.5;" +AdditionalIncludeDirectories=".;E:\builds\pcre\pcre-7.5;" + +RelativePath="pcre.h" +RelativePath="pcre_chartables.c" +RelativePath="pcre_chartables.c.rule" + + +TESTING WITH RUNTEST.BAT + +If configured with CMake, building the test project ("make test" or building +ALL_TESTS in Visual Studio) creates (and runs) pcre_test.bat (and depending +on your configuration options, possibly other test programs) in the build +directory. Pcre_test.bat runs RunTest.Bat with correct source and exe paths. + +For manual testing with RunTest.bat, provided the build dir is a subdirectory +of the source directory: Open command shell window. Chdir to the location +of your pcretest.exe and pcregrep.exe programs. Call RunTest.bat with +"..\RunTest.Bat" or "..\..\RunTest.bat" as appropriate. + +To run only a particular test with RunTest.Bat provide a test number argument. + +Otherwise: + +1. Copy RunTest.bat into the directory where pcretest.exe and pcregrep.exe + have been created. + +2. Edit RunTest.bat to indentify the full or relative location of + the pcre source (wherein which the testdata folder resides), e.g.: + + set srcdir=C:\pcre\pcre-8.20 + +3. In a Windows command environment, chdir to the location of your bat and + exe programs. + +4. Run RunTest.bat. Test outputs will automatically be compared to expected + results, and discrepancies will be identified in the console output. + +To independently test the just-in-time compiler, run pcre_jit_test.exe. +To test pcrecpp, run pcrecpp_unittest.exe, pcre_stringpiece_unittest.exe and +pcre_scanner_unittest.exe. + + +BUILDING UNDER WINDOWS CE WITH VISUAL STUDIO 200x + +Vincent Richomme sent a zip archive of files to help with this process. They +can be found in the file "pcre-vsbuild.zip" in the Contrib directory of the FTP +site. + + +BUILDING UNDER WINDOWS WITH BCC5.5 + +Michael Roy sent these comments about building PCRE under Windows with BCC5.5: + +Some of the core BCC libraries have a version of PCRE from 1998 built in, which +can lead to pcre_exec() giving an erroneous PCRE_ERROR_NULL from a version +mismatch. I'm including an easy workaround below, if you'd like to include it +in the non-unix instructions: + +When linking a project with BCC5.5, pcre.lib must be included before any of the +libraries cw32.lib, cw32i.lib, cw32mt.lib, and cw32mti.lib on the command line. + + +BUILDING USING BORLAND C++ BUILDER 2007 (CB2007) AND HIGHER + +A PCRE user sent these comments about this environment (see also the comment +from another user that follows them): + +The XE versions of C++ Builder come with a RegularExpressionsCore class which +contain a version of TPerlRegEx. However, direct use of the C PCRE library may +be desirable. + +The default makevp.bat, however, supplied with PCRE builds a version of PCRE +that is not usable with any version of C++ Builder because the compiler ships +with an embedded version of PCRE, version 2.01 from 1998! [See also the note +about BCC5.5 above.] If you want to use PCRE you'll need to rename the +functions (pcre_compile to pcre_compile_bcc, etc) or do as I have done and just +use the 16 bit versions. I'm using std::wstring everywhere anyway. Since the +embedded version of PCRE does not have the 16 bit function names, there is no +conflict. + +Building PCRE using a C++ Builder static library project file (recommended): + +1. Rename or remove pcre.h, pcreposi.h, and pcreposix.h from your C++ Builder +original include path. + +2. Download PCRE from pcre.org and extract to a directory. + +3. Rename pcre_chartables.c.dist to pcre_chartables.c, pcre.h.generic to +pcre.h, and config.h.generic to config.h. + +4. Edit pcre.h and pcre_config.c so that they include config.h. + +5. Edit config.h like so: + +Comment out the following lines: +#define PACKAGE "pcre" +#define PACKAGE_BUGREPORT "" +#define PACKAGE_NAME "PCRE" +#define PACKAGE_STRING "PCRE 8.32" +#define PACKAGE_TARNAME "pcre" +#define PACKAGE_URL "" +#define PACKAGE_VERSION "8.32" + +Add the following lines: +#ifndef SUPPORT_UTF +#define SUPPORT_UTF 100 // any value is fine +#endif + +#ifndef SUPPORT_UCP +#define SUPPORT_UCP 101 // any value is fine +#endif + +#ifndef SUPPORT_UCP +#define SUPPORT_PCRE16 102 // any value is fine +#endif + +#ifndef SUPPORT_UTF8 +#define SUPPORT_UTF8 103 // any value is fine +#endif + +6. Build a C++ Builder project using the IDE. Go to File / New / Other and +choose Static Library. You can name it pcre.cbproj or whatever. Now set your +paths by going to Project / Options. Set the Include path. Do this from the +"Base" option to apply to both Release and Debug builds. Now add the following +files to the project: + +pcre.h +pcre16_byte_order.c +pcre16_chartables.c +pcre16_compile.c +pcre16_config.c +pcre16_dfa_exec.c +pcre16_exec.c +pcre16_fullinfo.c +pcre16_get.c +pcre16_globals.c +pcre16_maketables.c +pcre16_newline.c +pcre16_ord2utf16.c +pcre16_printint.c +pcre16_refcount.c +pcre16_string_utils.c +pcre16_study.c +pcre16_tables.c +pcre16_ucd.c +pcre16_utf16_utils.c +pcre16_valid_utf16.c +pcre16_version.c +pcre16_xclass.c + +//Optional +pcre_version.c + +7. After compiling the .lib file, copy the .lib and header files to a project +you want to use PCRE with. Enjoy. + +Optional ... Building PCRE using the makevp.bat file: + +1. Edit makevp_c.txt and makevp_l.txt and change all the names to the 16 bit +versions. + +2. Edit makevp.bat and set the path to C++ Builder. Run makevp.bat. + +Another PCRE user added this comment: + +Another approach I successfully used for some years with BCB 5 and 6 was to +make sure that include and library paths of PCRE are configured before the +default paths of the IDE in the dialogs where one can manage those paths. +Afterwards one can open the project files using a text editor and manually add +the self created library for pcre itself, pcrecpp doesn't ship with the IDE, in +the library nodes where the IDE manages its own libraries to link against in +front of the IDE-own libraries. This way one can use the default PCRE function +names without getting access violations on runtime. + + <ALLLIB value="libpcre.lib $(LIBFILES) $(LIBRARIES) import32.lib cp32mt.lib"/> + + +BUILDING PCRE ON OPENVMS + +Stephen Hoffman sent the following, in December 2012: + +"Here <http://labs.hoffmanlabs.com/node/1847> is a very short write-up on the +OpenVMS port and here + +<http://labs.hoffmanlabs.com/labsnotes/pcre-vms-8_32.zip> + +is a zip with the OpenVMS files, and with one modified testing-related PCRE +file." This is a port of PCRE 8.32. + +Earlier, Dan Mooney sent the following comments about building PCRE on OpenVMS. +They relate to an older version of PCRE that used fewer source files, so the +exact commands will need changing. See the current list of source files above. + +"It was quite easy to compile and link the library. I don't have a formal +make file but the attached file [reproduced below] contains the OpenVMS DCL +commands I used to build the library. I had to add #define +POSIX_MALLOC_THRESHOLD 10 to pcre.h since it was not defined anywhere. + +The library was built on: +O/S: HP OpenVMS v7.3-1 +Compiler: Compaq C v6.5-001-48BCD +Linker: vA13-01 + +The test results did not match 100% due to the issues you mention in your +documentation regarding isprint(), iscntrl(), isgraph() and ispunct(). I +modified some of the character tables temporarily and was able to get the +results to match. Tests using the fr locale did not match since I don't have +that locale loaded. The study size was always reported to be 3 less than the +value in the standard test output files." + +========================= +$! This DCL procedure builds PCRE on OpenVMS +$! +$! I followed the instructions in the non-unix-use file in the distribution. +$! +$ COMPILE == "CC/LIST/NOMEMBER_ALIGNMENT/PREFIX_LIBRARY_ENTRIES=ALL_ENTRIES +$ COMPILE DFTABLES.C +$ LINK/EXE=DFTABLES.EXE DFTABLES.OBJ +$ RUN DFTABLES.EXE/OUTPUT=CHARTABLES.C +$ COMPILE MAKETABLES.C +$ COMPILE GET.C +$ COMPILE STUDY.C +$! I had to set POSIX_MALLOC_THRESHOLD to 10 in PCRE.H since the symbol +$! did not seem to be defined anywhere. +$! I edited pcre.h and added #DEFINE SUPPORT_UTF8 to enable UTF8 support. +$ COMPILE PCRE.C +$ LIB/CREATE PCRE MAKETABLES.OBJ, GET.OBJ, STUDY.OBJ, PCRE.OBJ +$! I had to set POSIX_MALLOC_THRESHOLD to 10 in PCRE.H since the symbol +$! did not seem to be defined anywhere. +$ COMPILE PCREPOSIX.C +$ LIB/CREATE PCREPOSIX PCREPOSIX.OBJ +$ COMPILE PCRETEST.C +$ LINK/EXE=PCRETEST.EXE PCRETEST.OBJ, PCRE/LIB, PCREPOSIX/LIB +$! C programs that want access to command line arguments must be +$! defined as a symbol +$ PCRETEST :== "$ SYS$ROADSUSERS:[DMOONEY.REGEXP]PCRETEST.EXE" +$! Arguments must be enclosed in quotes. +$ PCRETEST "-C" +$! Test results: +$! +$! The test results did not match 100%. The functions isprint(), iscntrl(), +$! isgraph() and ispunct() on OpenVMS must not produce the same results +$! as the system that built the test output files provided with the +$! distribution. +$! +$! The study size did not match and was always 3 less on OpenVMS. +$! +$! Locale could not be set to fr +$! +========================= + + +BUILDING PCRE ON STRATUS OPENVOS + +These notes on the port of PCRE to VOS (lightly edited) were supplied by +Ashutosh Warikoo, whose email address has the local part awarikoo and the +domain nse.co.in. The port was for version 7.9 in August 2009. + +1. Building PCRE + +I built pcre on OpenVOS Release 17.0.1at using GNU Tools 3.4a without any +problems. I used the following packages to build PCRE: + + ftp://ftp.stratus.com/pub/vos/posix/ga/posix.save.evf.gz + +Please read and follow the instructions that come with these packages. To start +the build of pcre, from the root of the package type: + + ./build.sh + +2. Installing PCRE + +Once you have successfully built PCRE, login to the SysAdmin group, switch to +the root user, and type + + [ !create_dir (master_disk)>usr --if needed ] + [ !create_dir (master_disk)>usr>local --if needed ] + !gmake install + +This installs PCRE and its man pages into /usr/local. You can add +(master_disk)>usr>local>bin to your command search paths, or if you are in +BASH, add /usr/local/bin to the PATH environment variable. + +4. Restrictions + +This port requires readline library optionally. However during the build I +faced some yet unexplored errors while linking with readline. As it was an +optional component I chose to disable it. + +5. Known Problems + +I ran the test suite, but you will have to be your own judge of whether this +command, and this port, suits your purposes. If you find any problems that +appear to be related to the port itself, please let me know. Please see the +build.log file in the root of the package also. + + +BUILDING PCRE ON NATIVE Z/OS AND Z/VM + +z/OS and z/VM are operating systems for mainframe computers, produced by IBM. +The character code used is EBCDIC, not ASCII or Unicode. In z/OS, UNIX APIs and +applications can be supported through UNIX System Services, and in such an +environment PCRE can be built in the same way as in other systems. However, in +native z/OS (without UNIX System Services) and in z/VM, special ports are +required. For details, please see this web site: + + http://www.zaconsultants.net + +There is also a mirror here: + + http://www.vsoft-software.com/downloads.html + +========================== +Last Updated: 14 May 2013 diff --git a/plugins/Pcre16/docs/NON-UNIX-USE b/plugins/Pcre16/docs/NON-UNIX-USE new file mode 100644 index 0000000000..a25546b6ff --- /dev/null +++ b/plugins/Pcre16/docs/NON-UNIX-USE @@ -0,0 +1,7 @@ +Compiling PCRE on non-Unix systems +---------------------------------- + +This has been renamed to better reflect its contents. Please see the file +NON-AUTOTOOLS-BUILD for details of how to build PCRE without using autotools. + +#### diff --git a/plugins/Pcre16/docs/README b/plugins/Pcre16/docs/README new file mode 100644 index 0000000000..88f2dfd4ef --- /dev/null +++ b/plugins/Pcre16/docs/README @@ -0,0 +1,991 @@ +README file for PCRE (Perl-compatible regular expression library) +----------------------------------------------------------------- + +The latest release of PCRE is always available in three alternative formats +from: + + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.gz + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.bz2 + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.zip + +There is a mailing list for discussion about the development of PCRE at +pcre-dev@exim.org. You can access the archives and subscribe or manage your +subscription here: + + https://lists.exim.org/mailman/listinfo/pcre-dev + +Please read the NEWS file if you are upgrading from a previous release. +The contents of this README file are: + + The PCRE APIs + Documentation for PCRE + Contributions by users of PCRE + Building PCRE on non-Unix-like systems + Building PCRE without using autotools + Building PCRE using autotools + Retrieving configuration information + Shared libraries + Cross-compiling using autotools + Using HP's ANSI C++ compiler (aCC) + Compiling in Tru64 using native compilers + Using Sun's compilers for Solaris + Using PCRE from MySQL + Making new tarballs + Testing PCRE + Character tables + File manifest + + +The PCRE APIs +------------- + +PCRE is written in C, and it has its own API. There are three sets of +functions, one for the 8-bit library, which processes strings of bytes, one for +the 16-bit library, which processes strings of 16-bit values, and one for the +32-bit library, which processes strings of 32-bit values. The distribution also +includes a set of C++ wrapper functions (see the pcrecpp man page for details), +courtesy of Google Inc., which can be used to call the 8-bit PCRE library from +C++. + +In addition, there is a set of C wrapper functions (again, just for the 8-bit +library) that are based on the POSIX regular expression API (see the pcreposix +man page). These end up in the library called libpcreposix. Note that this just +provides a POSIX calling interface to PCRE; the regular expressions themselves +still follow Perl syntax and semantics. The POSIX API is restricted, and does +not give full access to all of PCRE's facilities. + +The header file for the POSIX-style functions is called pcreposix.h. The +official POSIX name is regex.h, but I did not want to risk possible problems +with existing files of that name by distributing it that way. To use PCRE with +an existing program that uses the POSIX API, pcreposix.h will have to be +renamed or pointed at by a link. + +If you are using the POSIX interface to PCRE and there is already a POSIX regex +library installed on your system, as well as worrying about the regex.h header +file (as mentioned above), you must also take care when linking programs to +ensure that they link with PCRE's libpcreposix library. Otherwise they may pick +up the POSIX functions of the same name from the other library. + +One way of avoiding this confusion is to compile PCRE with the addition of +-Dregcomp=PCREregcomp (and similarly for the other POSIX functions) to the +compiler flags (CFLAGS if you are using "configure" -- see below). This has the +effect of renaming the functions so that the names no longer clash. Of course, +you have to do the same thing for your applications, or write them using the +new names. + + +Documentation for PCRE +---------------------- + +If you install PCRE in the normal way on a Unix-like system, you will end up +with a set of man pages whose names all start with "pcre". The one that is just +called "pcre" lists all the others. In addition to these man pages, the PCRE +documentation is supplied in two other forms: + + 1. There are files called doc/pcre.txt, doc/pcregrep.txt, and + doc/pcretest.txt in the source distribution. The first of these is a + concatenation of the text forms of all the section 3 man pages except + the listing of pcredemo.c and those that summarize individual functions. + The other two are the text forms of the section 1 man pages for the + pcregrep and pcretest commands. These text forms are provided for ease of + scanning with text editors or similar tools. They are installed in + <prefix>/share/doc/pcre, where <prefix> is the installation prefix + (defaulting to /usr/local). + + 2. A set of files containing all the documentation in HTML form, hyperlinked + in various ways, and rooted in a file called index.html, is distributed in + doc/html and installed in <prefix>/share/doc/pcre/html. + +Users of PCRE have contributed files containing the documentation for various +releases in CHM format. These can be found in the Contrib directory of the FTP +site (see next section). + + +Contributions by users of PCRE +------------------------------ + +You can find contributions from PCRE users in the directory + + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/Contrib + +There is a README file giving brief descriptions of what they are. Some are +complete in themselves; others are pointers to URLs containing relevant files. +Some of this material is likely to be well out-of-date. Several of the earlier +contributions provided support for compiling PCRE on various flavours of +Windows (I myself do not use Windows). Nowadays there is more Windows support +in the standard distribution, so these contibutions have been archived. + +A PCRE user maintains downloadable Windows binaries of the pcregrep and +pcretest programs here: + + http://www.rexegg.com/pcregrep-pcretest.html + + +Building PCRE on non-Unix-like systems +-------------------------------------- + +For a non-Unix-like system, please read the comments in the file +NON-AUTOTOOLS-BUILD, though if your system supports the use of "configure" and +"make" you may be able to build PCRE using autotools in the same way as for +many Unix-like systems. + +PCRE can also be configured using the GUI facility provided by CMake's +cmake-gui command. This creates Makefiles, solution files, etc. The file +NON-AUTOTOOLS-BUILD has information about CMake. + +PCRE has been compiled on many different operating systems. It should be +straightforward to build PCRE on any system that has a Standard C compiler and +library, because it uses only Standard C functions. + + +Building PCRE without using autotools +------------------------------------- + +The use of autotools (in particular, libtool) is problematic in some +environments, even some that are Unix or Unix-like. See the NON-AUTOTOOLS-BUILD +file for ways of building PCRE without using autotools. + + +Building PCRE using autotools +----------------------------- + +If you are using HP's ANSI C++ compiler (aCC), please see the special note +in the section entitled "Using HP's ANSI C++ compiler (aCC)" below. + +The following instructions assume the use of the widely used "configure; make; +make install" (autotools) process. + +To build PCRE on system that supports autotools, first run the "configure" +command from the PCRE distribution directory, with your current directory set +to the directory where you want the files to be created. This command is a +standard GNU "autoconf" configuration script, for which generic instructions +are supplied in the file INSTALL. + +Most commonly, people build PCRE within its own distribution directory, and in +this case, on many systems, just running "./configure" is sufficient. However, +the usual methods of changing standard defaults are available. For example: + +CFLAGS='-O2 -Wall' ./configure --prefix=/opt/local + +This command specifies that the C compiler should be run with the flags '-O2 +-Wall' instead of the default, and that "make install" should install PCRE +under /opt/local instead of the default /usr/local. + +If you want to build in a different directory, just run "configure" with that +directory as current. For example, suppose you have unpacked the PCRE source +into /source/pcre/pcre-xxx, but you want to build it in /build/pcre/pcre-xxx: + +cd /build/pcre/pcre-xxx +/source/pcre/pcre-xxx/configure + +PCRE is written in C and is normally compiled as a C library. However, it is +possible to build it as a C++ library, though the provided building apparatus +does not have any features to support this. + +There are some optional features that can be included or omitted from the PCRE +library. They are also documented in the pcrebuild man page. + +. By default, both shared and static libraries are built. You can change this + by adding one of these options to the "configure" command: + + --disable-shared + --disable-static + + (See also "Shared libraries on Unix-like systems" below.) + +. By default, only the 8-bit library is built. If you add --enable-pcre16 to + the "configure" command, the 16-bit library is also built. If you add + --enable-pcre32 to the "configure" command, the 32-bit library is also built. + If you want only the 16-bit or 32-bit library, use --disable-pcre8 to disable + building the 8-bit library. + +. If you are building the 8-bit library and want to suppress the building of + the C++ wrapper library, you can add --disable-cpp to the "configure" + command. Otherwise, when "configure" is run without --disable-pcre8, it will + try to find a C++ compiler and C++ header files, and if it succeeds, it will + try to build the C++ wrapper. + +. If you want to include support for just-in-time compiling, which can give + large performance improvements on certain platforms, add --enable-jit to the + "configure" command. This support is available only for certain hardware + architectures. If you try to enable it on an unsupported architecture, there + will be a compile time error. + +. When JIT support is enabled, pcregrep automatically makes use of it, unless + you add --disable-pcregrep-jit to the "configure" command. + +. If you want to make use of the support for UTF-8 Unicode character strings in + the 8-bit library, or UTF-16 Unicode character strings in the 16-bit library, + or UTF-32 Unicode character strings in the 32-bit library, you must add + --enable-utf to the "configure" command. Without it, the code for handling + UTF-8, UTF-16 and UTF-8 is not included in the relevant library. Even + when --enable-utf is included, the use of a UTF encoding still has to be + enabled by an option at run time. When PCRE is compiled with this option, its + input can only either be ASCII or UTF-8/16/32, even when running on EBCDIC + platforms. It is not possible to use both --enable-utf and --enable-ebcdic at + the same time. + +. There are no separate options for enabling UTF-8, UTF-16 and UTF-32 + independently because that would allow ridiculous settings such as requesting + UTF-16 support while building only the 8-bit library. However, the option + --enable-utf8 is retained for backwards compatibility with earlier releases + that did not support 16-bit or 32-bit character strings. It is synonymous with + --enable-utf. It is not possible to configure one library with UTF support + and the other without in the same configuration. + +. If, in addition to support for UTF-8/16/32 character strings, you want to + include support for the \P, \p, and \X sequences that recognize Unicode + character properties, you must add --enable-unicode-properties to the + "configure" command. This adds about 30K to the size of the library (in the + form of a property table); only the basic two-letter properties such as Lu + are supported. + +. You can build PCRE to recognize either CR or LF or the sequence CRLF or any + of the preceding, or any of the Unicode newline sequences as indicating the + end of a line. Whatever you specify at build time is the default; the caller + of PCRE can change the selection at run time. The default newline indicator + is a single LF character (the Unix standard). You can specify the default + newline indicator by adding --enable-newline-is-cr or --enable-newline-is-lf + or --enable-newline-is-crlf or --enable-newline-is-anycrlf or + --enable-newline-is-any to the "configure" command, respectively. + + If you specify --enable-newline-is-cr or --enable-newline-is-crlf, some of + the standard tests will fail, because the lines in the test files end with + LF. Even if the files are edited to change the line endings, there are likely + to be some failures. With --enable-newline-is-anycrlf or + --enable-newline-is-any, many tests should succeed, but there may be some + failures. + +. By default, the sequence \R in a pattern matches any Unicode line ending + sequence. This is independent of the option specifying what PCRE considers to + be the end of a line (see above). However, the caller of PCRE can restrict \R + to match only CR, LF, or CRLF. You can make this the default by adding + --enable-bsr-anycrlf to the "configure" command (bsr = "backslash R"). + +. When called via the POSIX interface, PCRE uses malloc() to get additional + storage for processing capturing parentheses if there are more than 10 of + them in a pattern. You can increase this threshold by setting, for example, + + --with-posix-malloc-threshold=20 + + on the "configure" command. + +. PCRE has a counter that limits the depth of nesting of parentheses in a + pattern. This limits the amount of system stack that a pattern uses when it + is compiled. The default is 250, but you can change it by setting, for + example, + + --with-parens-nest-limit=500 + +. PCRE has a counter that can be set to limit the amount of resources it uses + when matching a pattern. If the limit is exceeded during a match, the match + fails. The default is ten million. You can change the default by setting, for + example, + + --with-match-limit=500000 + + on the "configure" command. This is just the default; individual calls to + pcre_exec() can supply their own value. There is more discussion on the + pcreapi man page. + +. There is a separate counter that limits the depth of recursive function calls + during a matching process. This also has a default of ten million, which is + essentially "unlimited". You can change the default by setting, for example, + + --with-match-limit-recursion=500000 + + Recursive function calls use up the runtime stack; running out of stack can + cause programs to crash in strange ways. There is a discussion about stack + sizes in the pcrestack man page. + +. The default maximum compiled pattern size is around 64K. You can increase + this by adding --with-link-size=3 to the "configure" command. In the 8-bit + library, PCRE then uses three bytes instead of two for offsets to different + parts of the compiled pattern. In the 16-bit library, --with-link-size=3 is + the same as --with-link-size=4, which (in both libraries) uses four-byte + offsets. Increasing the internal link size reduces performance. In the 32-bit + library, the only supported link size is 4. + +. You can build PCRE so that its internal match() function that is called from + pcre_exec() does not call itself recursively. Instead, it uses memory blocks + obtained from the heap via the special functions pcre_stack_malloc() and + pcre_stack_free() to save data that would otherwise be saved on the stack. To + build PCRE like this, use + + --disable-stack-for-recursion + + on the "configure" command. PCRE runs more slowly in this mode, but it may be + necessary in environments with limited stack sizes. This applies only to the + normal execution of the pcre_exec() function; if JIT support is being + successfully used, it is not relevant. Equally, it does not apply to + pcre_dfa_exec(), which does not use deeply nested recursion. There is a + discussion about stack sizes in the pcrestack man page. + +. For speed, PCRE uses four tables for manipulating and identifying characters + whose code point values are less than 256. By default, it uses a set of + tables for ASCII encoding that is part of the distribution. If you specify + + --enable-rebuild-chartables + + a program called dftables is compiled and run in the default C locale when + you obey "make". It builds a source file called pcre_chartables.c. If you do + not specify this option, pcre_chartables.c is created as a copy of + pcre_chartables.c.dist. See "Character tables" below for further information. + +. It is possible to compile PCRE for use on systems that use EBCDIC as their + character code (as opposed to ASCII/Unicode) by specifying + + --enable-ebcdic + + This automatically implies --enable-rebuild-chartables (see above). However, + when PCRE is built this way, it always operates in EBCDIC. It cannot support + both EBCDIC and UTF-8/16/32. There is a second option, --enable-ebcdic-nl25, + which specifies that the code value for the EBCDIC NL character is 0x25 + instead of the default 0x15. + +. In environments where valgrind is installed, if you specify + + --enable-valgrind + + PCRE will use valgrind annotations to mark certain memory regions as + unaddressable. This allows it to detect invalid memory accesses, and is + mostly useful for debugging PCRE itself. + +. In environments where the gcc compiler is used and lcov version 1.6 or above + is installed, if you specify + + --enable-coverage + + the build process implements a code coverage report for the test suite. The + report is generated by running "make coverage". If ccache is installed on + your system, it must be disabled when building PCRE for coverage reporting. + You can do this by setting the environment variable CCACHE_DISABLE=1 before + running "make" to build PCRE. There is more information about coverage + reporting in the "pcrebuild" documentation. + +. The pcregrep program currently supports only 8-bit data files, and so + requires the 8-bit PCRE library. It is possible to compile pcregrep to use + libz and/or libbz2, in order to read .gz and .bz2 files (respectively), by + specifying one or both of + + --enable-pcregrep-libz + --enable-pcregrep-libbz2 + + Of course, the relevant libraries must be installed on your system. + +. The default size (in bytes) of the internal buffer used by pcregrep can be + set by, for example: + + --with-pcregrep-bufsize=51200 + + The value must be a plain integer. The default is 20480. + +. It is possible to compile pcretest so that it links with the libreadline + or libedit libraries, by specifying, respectively, + + --enable-pcretest-libreadline or --enable-pcretest-libedit + + If this is done, when pcretest's input is from a terminal, it reads it using + the readline() function. This provides line-editing and history facilities. + Note that libreadline is GPL-licenced, so if you distribute a binary of + pcretest linked in this way, there may be licensing issues. These can be + avoided by linking with libedit (which has a BSD licence) instead. + + Enabling libreadline causes the -lreadline option to be added to the pcretest + build. In many operating environments with a sytem-installed readline + library this is sufficient. However, in some environments (e.g. if an + unmodified distribution version of readline is in use), it may be necessary + to specify something like LIBS="-lncurses" as well. This is because, to quote + the readline INSTALL, "Readline uses the termcap functions, but does not link + with the termcap or curses library itself, allowing applications which link + with readline the to choose an appropriate library." If you get error + messages about missing functions tgetstr, tgetent, tputs, tgetflag, or tgoto, + this is the problem, and linking with the ncurses library should fix it. + +The "configure" script builds the following files for the basic C library: + +. Makefile the makefile that builds the library +. config.h build-time configuration options for the library +. pcre.h the public PCRE header file +. pcre-config script that shows the building settings such as CFLAGS + that were set for "configure" +. libpcre.pc ) data for the pkg-config command +. libpcre16.pc ) +. libpcre32.pc ) +. libpcreposix.pc ) +. libtool script that builds shared and/or static libraries + +Versions of config.h and pcre.h are distributed in the PCRE tarballs under the +names config.h.generic and pcre.h.generic. These are provided for those who +have to built PCRE without using "configure" or CMake. If you use "configure" +or CMake, the .generic versions are not used. + +When building the 8-bit library, if a C++ compiler is found, the following +files are also built: + +. libpcrecpp.pc data for the pkg-config command +. pcrecpparg.h header file for calling PCRE via the C++ wrapper +. pcre_stringpiece.h header for the C++ "stringpiece" functions + +The "configure" script also creates config.status, which is an executable +script that can be run to recreate the configuration, and config.log, which +contains compiler output from tests that "configure" runs. + +Once "configure" has run, you can run "make". This builds the the libraries +libpcre, libpcre16 and/or libpcre32, and a test program called pcretest. If you +enabled JIT support with --enable-jit, a test program called pcre_jit_test is +built as well. + +If the 8-bit library is built, libpcreposix and the pcregrep command are also +built, and if a C++ compiler was found on your system, and you did not disable +it with --disable-cpp, "make" builds the C++ wrapper library, which is called +libpcrecpp, as well as some test programs called pcrecpp_unittest, +pcre_scanner_unittest, and pcre_stringpiece_unittest. + +The command "make check" runs all the appropriate tests. Details of the PCRE +tests are given below in a separate section of this document. + +You can use "make install" to install PCRE into live directories on your +system. The following are installed (file names are all relative to the +<prefix> that is set when "configure" is run): + + Commands (bin): + pcretest + pcregrep (if 8-bit support is enabled) + pcre-config + + Libraries (lib): + libpcre16 (if 16-bit support is enabled) + libpcre32 (if 32-bit support is enabled) + libpcre (if 8-bit support is enabled) + libpcreposix (if 8-bit support is enabled) + libpcrecpp (if 8-bit and C++ support is enabled) + + Configuration information (lib/pkgconfig): + libpcre16.pc + libpcre32.pc + libpcre.pc + libpcreposix.pc + libpcrecpp.pc (if C++ support is enabled) + + Header files (include): + pcre.h + pcreposix.h + pcre_scanner.h ) + pcre_stringpiece.h ) if C++ support is enabled + pcrecpp.h ) + pcrecpparg.h ) + + Man pages (share/man/man{1,3}): + pcregrep.1 + pcretest.1 + pcre-config.1 + pcre.3 + pcre*.3 (lots more pages, all starting "pcre") + + HTML documentation (share/doc/pcre/html): + index.html + *.html (lots more pages, hyperlinked from index.html) + + Text file documentation (share/doc/pcre): + AUTHORS + COPYING + ChangeLog + LICENCE + NEWS + README + pcre.txt (a concatenation of the man(3) pages) + pcretest.txt the pcretest man page + pcregrep.txt the pcregrep man page + pcre-config.txt the pcre-config man page + +If you want to remove PCRE from your system, you can run "make uninstall". +This removes all the files that "make install" installed. However, it does not +remove any directories, because these are often shared with other programs. + + +Retrieving configuration information +------------------------------------ + +Running "make install" installs the command pcre-config, which can be used to +recall information about the PCRE configuration and installation. For example: + + pcre-config --version + +prints the version number, and + + pcre-config --libs + +outputs information about where the library is installed. This command can be +included in makefiles for programs that use PCRE, saving the programmer from +having to remember too many details. + +The pkg-config command is another system for saving and retrieving information +about installed libraries. Instead of separate commands for each library, a +single command is used. For example: + + pkg-config --cflags pcre + +The data is held in *.pc files that are installed in a directory called +<prefix>/lib/pkgconfig. + + +Shared libraries +---------------- + +The default distribution builds PCRE as shared libraries and static libraries, +as long as the operating system supports shared libraries. Shared library +support relies on the "libtool" script which is built as part of the +"configure" process. + +The libtool script is used to compile and link both shared and static +libraries. They are placed in a subdirectory called .libs when they are newly +built. The programs pcretest and pcregrep are built to use these uninstalled +libraries (by means of wrapper scripts in the case of shared libraries). When +you use "make install" to install shared libraries, pcregrep and pcretest are +automatically re-built to use the newly installed shared libraries before being +installed themselves. However, the versions left in the build directory still +use the uninstalled libraries. + +To build PCRE using static libraries only you must use --disable-shared when +configuring it. For example: + +./configure --prefix=/usr/gnu --disable-shared + +Then run "make" in the usual way. Similarly, you can use --disable-static to +build only shared libraries. + + +Cross-compiling using autotools +------------------------------- + +You can specify CC and CFLAGS in the normal way to the "configure" command, in +order to cross-compile PCRE for some other host. However, you should NOT +specify --enable-rebuild-chartables, because if you do, the dftables.c source +file is compiled and run on the local host, in order to generate the inbuilt +character tables (the pcre_chartables.c file). This will probably not work, +because dftables.c needs to be compiled with the local compiler, not the cross +compiler. + +When --enable-rebuild-chartables is not specified, pcre_chartables.c is created +by making a copy of pcre_chartables.c.dist, which is a default set of tables +that assumes ASCII code. Cross-compiling with the default tables should not be +a problem. + +If you need to modify the character tables when cross-compiling, you should +move pcre_chartables.c.dist out of the way, then compile dftables.c by hand and +run it on the local host to make a new version of pcre_chartables.c.dist. +Then when you cross-compile PCRE this new version of the tables will be used. + + +Using HP's ANSI C++ compiler (aCC) +---------------------------------- + +Unless C++ support is disabled by specifying the "--disable-cpp" option of the +"configure" script, you must include the "-AA" option in the CXXFLAGS +environment variable in order for the C++ components to compile correctly. + +Also, note that the aCC compiler on PA-RISC platforms may have a defect whereby +needed libraries fail to get included when specifying the "-AA" compiler +option. If you experience unresolved symbols when linking the C++ programs, +use the workaround of specifying the following environment variable prior to +running the "configure" script: + + CXXLDFLAGS="-lstd_v2 -lCsup_v2" + + +Compiling in Tru64 using native compilers +----------------------------------------- + +The following error may occur when compiling with native compilers in the Tru64 +operating system: + + CXX libpcrecpp_la-pcrecpp.lo +cxx: Error: /usr/lib/cmplrs/cxx/V7.1-006/include/cxx/iosfwd, line 58: #error + directive: "cannot include iosfwd -- define __USE_STD_IOSTREAM to + override default - see section 7.1.2 of the C++ Using Guide" +#error "cannot include iosfwd -- define __USE_STD_IOSTREAM to override default +- see section 7.1.2 of the C++ Using Guide" + +This may be followed by other errors, complaining that 'namespace "std" has no +member'. The solution to this is to add the line + +#define __USE_STD_IOSTREAM 1 + +to the config.h file. + + +Using Sun's compilers for Solaris +--------------------------------- + +A user reports that the following configurations work on Solaris 9 sparcv9 and +Solaris 9 x86 (32-bit): + + Solaris 9 sparcv9: ./configure --disable-cpp CC=/bin/cc CFLAGS="-m64 -g" + Solaris 9 x86: ./configure --disable-cpp CC=/bin/cc CFLAGS="-g" + + +Using PCRE from MySQL +--------------------- + +On systems where both PCRE and MySQL are installed, it is possible to make use +of PCRE from within MySQL, as an alternative to the built-in pattern matching. +There is a web page that tells you how to do this: + + http://www.mysqludf.org/lib_mysqludf_preg/index.php + + +Making new tarballs +------------------- + +The command "make dist" creates three PCRE tarballs, in tar.gz, tar.bz2, and +zip formats. The command "make distcheck" does the same, but then does a trial +build of the new distribution to ensure that it works. + +If you have modified any of the man page sources in the doc directory, you +should first run the PrepareRelease script before making a distribution. This +script creates the .txt and HTML forms of the documentation from the man pages. + + +Testing PCRE +------------ + +To test the basic PCRE library on a Unix-like system, run the RunTest script. +There is another script called RunGrepTest that tests the options of the +pcregrep command. If the C++ wrapper library is built, three test programs +called pcrecpp_unittest, pcre_scanner_unittest, and pcre_stringpiece_unittest +are also built. When JIT support is enabled, another test program called +pcre_jit_test is built. + +Both the scripts and all the program tests are run if you obey "make check" or +"make test". For other environments, see the instructions in +NON-AUTOTOOLS-BUILD. + +The RunTest script runs the pcretest test program (which is documented in its +own man page) on each of the relevant testinput files in the testdata +directory, and compares the output with the contents of the corresponding +testoutput files. RunTest uses a file called testtry to hold the main output +from pcretest. Other files whose names begin with "test" are used as working +files in some tests. + +Some tests are relevant only when certain build-time options were selected. For +example, the tests for UTF-8/16/32 support are run only if --enable-utf was +used. RunTest outputs a comment when it skips a test. + +Many of the tests that are not skipped are run up to three times. The second +run forces pcre_study() to be called for all patterns except for a few in some +tests that are marked "never study" (see the pcretest program for how this is +done). If JIT support is available, the non-DFA tests are run a third time, +this time with a forced pcre_study() with the PCRE_STUDY_JIT_COMPILE option. +This testing can be suppressed by putting "nojit" on the RunTest command line. + +The entire set of tests is run once for each of the 8-bit, 16-bit and 32-bit +libraries that are enabled. If you want to run just one set of tests, call +RunTest with either the -8, -16 or -32 option. + +If valgrind is installed, you can run the tests under it by putting "valgrind" +on the RunTest command line. To run pcretest on just one or more specific test +files, give their numbers as arguments to RunTest, for example: + + RunTest 2 7 11 + +You can also specify ranges of tests such as 3-6 or 3- (meaning 3 to the +end), or a number preceded by ~ to exclude a test. For example: + + Runtest 3-15 ~10 + +This runs tests 3 to 15, excluding test 10, and just ~13 runs all the tests +except test 13. Whatever order the arguments are in, the tests are always run +in numerical order. + +You can also call RunTest with the single argument "list" to cause it to output +a list of tests. + +The first test file can be fed directly into the perltest.pl script to check +that Perl gives the same results. The only difference you should see is in the +first few lines, where the Perl version is given instead of the PCRE version. + +The second set of tests check pcre_fullinfo(), pcre_study(), +pcre_copy_substring(), pcre_get_substring(), pcre_get_substring_list(), error +detection, and run-time flags that are specific to PCRE, as well as the POSIX +wrapper API. It also uses the debugging flags to check some of the internals of +pcre_compile(). + +If you build PCRE with a locale setting that is not the standard C locale, the +character tables may be different (see next paragraph). In some cases, this may +cause failures in the second set of tests. For example, in a locale where the +isprint() function yields TRUE for characters in the range 128-255, the use of +[:isascii:] inside a character class defines a different set of characters, and +this shows up in this test as a difference in the compiled code, which is being +listed for checking. Where the comparison test output contains [\x00-\x7f] the +test will contain [\x00-\xff], and similarly in some other cases. This is not a +bug in PCRE. + +The third set of tests checks pcre_maketables(), the facility for building a +set of character tables for a specific locale and using them instead of the +default tables. The tests make use of the "fr_FR" (French) locale. Before +running the test, the script checks for the presence of this locale by running +the "locale" command. If that command fails, or if it doesn't include "fr_FR" +in the list of available locales, the third test cannot be run, and a comment +is output to say why. If running this test produces instances of the error + + ** Failed to set locale "fr_FR" + +in the comparison output, it means that locale is not available on your system, +despite being listed by "locale". This does not mean that PCRE is broken. + +[If you are trying to run this test on Windows, you may be able to get it to +work by changing "fr_FR" to "french" everywhere it occurs. Alternatively, use +RunTest.bat. The version of RunTest.bat included with PCRE 7.4 and above uses +Windows versions of test 2. More info on using RunTest.bat is included in the +document entitled NON-UNIX-USE.] + +The fourth and fifth tests check the UTF-8/16/32 support and error handling and +internal UTF features of PCRE that are not relevant to Perl, respectively. The +sixth and seventh tests do the same for Unicode character properties support. + +The eighth, ninth, and tenth tests check the pcre_dfa_exec() alternative +matching function, in non-UTF-8/16/32 mode, UTF-8/16/32 mode, and UTF-8/16/32 +mode with Unicode property support, respectively. + +The eleventh test checks some internal offsets and code size features; it is +run only when the default "link size" of 2 is set (in other cases the sizes +change) and when Unicode property support is enabled. + +The twelfth test is run only when JIT support is available, and the thirteenth +test is run only when JIT support is not available. They test some JIT-specific +features such as information output from pcretest about JIT compilation. + +The fourteenth, fifteenth, and sixteenth tests are run only in 8-bit mode, and +the seventeenth, eighteenth, and nineteenth tests are run only in 16/32-bit +mode. These are tests that generate different output in the two modes. They are +for general cases, UTF-8/16/32 support, and Unicode property support, +respectively. + +The twentieth test is run only in 16/32-bit mode. It tests some specific +16/32-bit features of the DFA matching engine. + +The twenty-first and twenty-second tests are run only in 16/32-bit mode, when +the link size is set to 2 for the 16-bit library. They test reloading +pre-compiled patterns. + +The twenty-third and twenty-fourth tests are run only in 16-bit mode. They are +for general cases, and UTF-16 support, respectively. + +The twenty-fifth and twenty-sixth tests are run only in 32-bit mode. They are +for general cases, and UTF-32 support, respectively. + + +Character tables +---------------- + +For speed, PCRE uses four tables for manipulating and identifying characters +whose code point values are less than 256. The final argument of the +pcre_compile() function is a pointer to a block of memory containing the +concatenated tables. A call to pcre_maketables() can be used to generate a set +of tables in the current locale. If the final argument for pcre_compile() is +passed as NULL, a set of default tables that is built into the binary is used. + +The source file called pcre_chartables.c contains the default set of tables. By +default, this is created as a copy of pcre_chartables.c.dist, which contains +tables for ASCII coding. However, if --enable-rebuild-chartables is specified +for ./configure, a different version of pcre_chartables.c is built by the +program dftables (compiled from dftables.c), which uses the ANSI C character +handling functions such as isalnum(), isalpha(), isupper(), islower(), etc. to +build the table sources. This means that the default C locale which is set for +your system will control the contents of these default tables. You can change +the default tables by editing pcre_chartables.c and then re-building PCRE. If +you do this, you should take care to ensure that the file does not get +automatically re-generated. The best way to do this is to move +pcre_chartables.c.dist out of the way and replace it with your customized +tables. + +When the dftables program is run as a result of --enable-rebuild-chartables, +it uses the default C locale that is set on your system. It does not pay +attention to the LC_xxx environment variables. In other words, it uses the +system's default locale rather than whatever the compiling user happens to have +set. If you really do want to build a source set of character tables in a +locale that is specified by the LC_xxx variables, you can run the dftables +program by hand with the -L option. For example: + + ./dftables -L pcre_chartables.c.special + +The first two 256-byte tables provide lower casing and case flipping functions, +respectively. The next table consists of three 32-byte bit maps which identify +digits, "word" characters, and white space, respectively. These are used when +building 32-byte bit maps that represent character classes for code points less +than 256. + +The final 256-byte table has bits indicating various character types, as +follows: + + 1 white space character + 2 letter + 4 decimal digit + 8 hexadecimal digit + 16 alphanumeric or '_' + 128 regular expression metacharacter or binary zero + +You should not alter the set of characters that contain the 128 bit, as that +will cause PCRE to malfunction. + + +File manifest +------------- + +The distribution should contain the files listed below. Where a file name is +given as pcre[16|32]_xxx it means that there are three files, one with the name +pcre_xxx, one with the name pcre16_xx, and a third with the name pcre32_xxx. + +(A) Source files of the PCRE library functions and their headers: + + dftables.c auxiliary program for building pcre_chartables.c + when --enable-rebuild-chartables is specified + + pcre_chartables.c.dist a default set of character tables that assume ASCII + coding; used, unless --enable-rebuild-chartables is + specified, by copying to pcre[16]_chartables.c + + pcreposix.c ) + pcre[16|32]_byte_order.c ) + pcre[16|32]_compile.c ) + pcre[16|32]_config.c ) + pcre[16|32]_dfa_exec.c ) + pcre[16|32]_exec.c ) + pcre[16|32]_fullinfo.c ) + pcre[16|32]_get.c ) sources for the functions in the library, + pcre[16|32]_globals.c ) and some internal functions that they use + pcre[16|32]_jit_compile.c ) + pcre[16|32]_maketables.c ) + pcre[16|32]_newline.c ) + pcre[16|32]_refcount.c ) + pcre[16|32]_string_utils.c ) + pcre[16|32]_study.c ) + pcre[16|32]_tables.c ) + pcre[16|32]_ucd.c ) + pcre[16|32]_version.c ) + pcre[16|32]_xclass.c ) + pcre_ord2utf8.c ) + pcre_valid_utf8.c ) + pcre16_ord2utf16.c ) + pcre16_utf16_utils.c ) + pcre16_valid_utf16.c ) + pcre32_utf32_utils.c ) + pcre32_valid_utf32.c ) + + pcre[16|32]_printint.c ) debugging function that is used by pcretest, + ) and can also be #included in pcre_compile() + + pcre.h.in template for pcre.h when built by "configure" + pcreposix.h header for the external POSIX wrapper API + pcre_internal.h header for internal use + sljit/* 16 files that make up the JIT compiler + ucp.h header for Unicode property handling + + config.h.in template for config.h, which is built by "configure" + + pcrecpp.h public header file for the C++ wrapper + pcrecpparg.h.in template for another C++ header file + pcre_scanner.h public header file for C++ scanner functions + pcrecpp.cc ) + pcre_scanner.cc ) source for the C++ wrapper library + + pcre_stringpiece.h.in template for pcre_stringpiece.h, the header for the + C++ stringpiece functions + pcre_stringpiece.cc source for the C++ stringpiece functions + +(B) Source files for programs that use PCRE: + + pcredemo.c simple demonstration of coding calls to PCRE + pcregrep.c source of a grep utility that uses PCRE + pcretest.c comprehensive test program + +(C) Auxiliary files: + + 132html script to turn "man" pages into HTML + AUTHORS information about the author of PCRE + ChangeLog log of changes to the code + CleanTxt script to clean nroff output for txt man pages + Detrail script to remove trailing spaces + HACKING some notes about the internals of PCRE + INSTALL generic installation instructions + LICENCE conditions for the use of PCRE + COPYING the same, using GNU's standard name + Makefile.in ) template for Unix Makefile, which is built by + ) "configure" + Makefile.am ) the automake input that was used to create + ) Makefile.in + NEWS important changes in this release + NON-UNIX-USE the previous name for NON-AUTOTOOLS-BUILD + NON-AUTOTOOLS-BUILD notes on building PCRE without using autotools + PrepareRelease script to make preparations for "make dist" + README this file + RunTest a Unix shell script for running tests + RunGrepTest a Unix shell script for pcregrep tests + aclocal.m4 m4 macros (generated by "aclocal") + config.guess ) files used by libtool, + config.sub ) used only when building a shared library + configure a configuring shell script (built by autoconf) + configure.ac ) the autoconf input that was used to build + ) "configure" and config.h + depcomp ) script to find program dependencies, generated by + ) automake + doc/*.3 man page sources for PCRE + doc/*.1 man page sources for pcregrep and pcretest + doc/index.html.src the base HTML page + doc/html/* HTML documentation + doc/pcre.txt plain text version of the man pages + doc/pcretest.txt plain text documentation of test program + doc/perltest.txt plain text documentation of Perl test program + install-sh a shell script for installing files + libpcre16.pc.in template for libpcre16.pc for pkg-config + libpcre32.pc.in template for libpcre32.pc for pkg-config + libpcre.pc.in template for libpcre.pc for pkg-config + libpcreposix.pc.in template for libpcreposix.pc for pkg-config + libpcrecpp.pc.in template for libpcrecpp.pc for pkg-config + ltmain.sh file used to build a libtool script + missing ) common stub for a few missing GNU programs while + ) installing, generated by automake + mkinstalldirs script for making install directories + perltest.pl Perl test program + pcre-config.in source of script which retains PCRE information + pcre_jit_test.c test program for the JIT compiler + pcrecpp_unittest.cc ) + pcre_scanner_unittest.cc ) test programs for the C++ wrapper + pcre_stringpiece_unittest.cc ) + testdata/testinput* test data for main library tests + testdata/testoutput* expected test results + testdata/grep* input and output for pcregrep tests + testdata/* other supporting test files + +(D) Auxiliary files for cmake support + + cmake/COPYING-CMAKE-SCRIPTS + cmake/FindPackageHandleStandardArgs.cmake + cmake/FindEditline.cmake + cmake/FindReadline.cmake + CMakeLists.txt + config-cmake.h.in + +(E) Auxiliary files for VPASCAL + + makevp.bat + makevp_c.txt + makevp_l.txt + pcregexp.pas + +(F) Auxiliary files for building PCRE "by hand" + + pcre.h.generic ) a version of the public PCRE header file + ) for use in non-"configure" environments + config.h.generic ) a version of config.h for use in non-"configure" + ) environments + +(F) Miscellaneous + + RunTest.bat a script for running tests under Windows + +Philip Hazel +Email local part: ph10 +Email domain: cam.ac.uk +Last updated: 17 January 2014 diff --git a/plugins/Pcre16/docs/doc/html/NON-AUTOTOOLS-BUILD.txt b/plugins/Pcre16/docs/doc/html/NON-AUTOTOOLS-BUILD.txt new file mode 100644 index 0000000000..cddf3e0699 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/NON-AUTOTOOLS-BUILD.txt @@ -0,0 +1,764 @@ +Building PCRE without using autotools +------------------------------------- + +This document contains the following sections: + + General + Generic instructions for the PCRE C library + The C++ wrapper functions + Building for virtual Pascal + Stack size in Windows environments + Linking programs in Windows environments + Calling conventions in Windows environments + Comments about Win32 builds + Building PCRE on Windows with CMake + Use of relative paths with CMake on Windows + Testing with RunTest.bat + Building under Windows CE with Visual Studio 200x + Building under Windows with BCC5.5 + Building using Borland C++ Builder 2007 (CB2007) and higher + Building PCRE on OpenVMS + Building PCRE on Stratus OpenVOS + Building PCRE on native z/OS and z/VM + + +GENERAL + +I (Philip Hazel) have no experience of Windows or VMS sytems and how their +libraries work. The items in the PCRE distribution and Makefile that relate to +anything other than Linux systems are untested by me. + +There are some other comments and files (including some documentation in CHM +format) in the Contrib directory on the FTP site: + + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/Contrib + +The basic PCRE library consists entirely of code written in Standard C, and so +should compile successfully on any system that has a Standard C compiler and +library. The C++ wrapper functions are a separate issue (see below). + +The PCRE distribution includes a "configure" file for use by the configure/make +(autotools) build system, as found in many Unix-like environments. The README +file contains information about the options for "configure". + +There is also support for CMake, which some users prefer, especially in Windows +environments, though it can also be run in Unix-like environments. See the +section entitled "Building PCRE on Windows with CMake" below. + +Versions of config.h and pcre.h are distributed in the PCRE tarballs under the +names config.h.generic and pcre.h.generic. These are provided for those who +build PCRE without using "configure" or CMake. If you use "configure" or CMake, +the .generic versions are not used. + + +GENERIC INSTRUCTIONS FOR THE PCRE C LIBRARY + +The following are generic instructions for building the PCRE C library "by +hand". If you are going to use CMake, this section does not apply to you; you +can skip ahead to the CMake section. + + (1) Copy or rename the file config.h.generic as config.h, and edit the macro + settings that it contains to whatever is appropriate for your environment. + + In particular, you can alter the definition of the NEWLINE macro to + specify what character(s) you want to be interpreted as line terminators. + In an EBCDIC environment, you MUST change NEWLINE, because its default + value is 10, an ASCII LF. The usual EBCDIC newline character is 21 (0x15, + NL), though in some cases it may be 37 (0x25). + + When you compile any of the PCRE modules, you must specify -DHAVE_CONFIG_H + to your compiler so that config.h is included in the sources. + + An alternative approach is not to edit config.h, but to use -D on the + compiler command line to make any changes that you need to the + configuration options. In this case -DHAVE_CONFIG_H must not be set. + + NOTE: There have been occasions when the way in which certain parameters + in config.h are used has changed between releases. (In the configure/make + world, this is handled automatically.) When upgrading to a new release, + you are strongly advised to review config.h.generic before re-using what + you had previously. + + (2) Copy or rename the file pcre.h.generic as pcre.h. + + (3) EITHER: + Copy or rename file pcre_chartables.c.dist as pcre_chartables.c. + + OR: + Compile dftables.c as a stand-alone program (using -DHAVE_CONFIG_H if + you have set up config.h), and then run it with the single argument + "pcre_chartables.c". This generates a set of standard character tables + and writes them to that file. The tables are generated using the default + C locale for your system. If you want to use a locale that is specified + by LC_xxx environment variables, add the -L option to the dftables + command. You must use this method if you are building on a system that + uses EBCDIC code. + + The tables in pcre_chartables.c are defaults. The caller of PCRE can + specify alternative tables at run time. + + (4) Ensure that you have the following header files: + + pcre_internal.h + ucp.h + + (5) For an 8-bit library, compile the following source files, setting + -DHAVE_CONFIG_H as a compiler option if you have set up config.h with your + configuration, or else use other -D settings to change the configuration + as required. + + pcre_byte_order.c + pcre_chartables.c + pcre_compile.c + pcre_config.c + pcre_dfa_exec.c + pcre_exec.c + pcre_fullinfo.c + pcre_get.c + pcre_globals.c + pcre_jit_compile.c + pcre_maketables.c + pcre_newline.c + pcre_ord2utf8.c + pcre_refcount.c + pcre_string_utils.c + pcre_study.c + pcre_tables.c + pcre_ucd.c + pcre_valid_utf8.c + pcre_version.c + pcre_xclass.c + + Make sure that you include -I. in the compiler command (or equivalent for + an unusual compiler) so that all included PCRE header files are first + sought in the current directory. Otherwise you run the risk of picking up + a previously-installed file from somewhere else. + + Note that you must still compile pcre_jit_compile.c, even if you have not + defined SUPPORT_JIT in config.h, because when JIT support is not + configured, dummy functions are compiled. When JIT support IS configured, + pcre_jit_compile.c #includes sources from the sljit subdirectory, where + there should be 16 files, all of whose names begin with "sljit". + + (6) Now link all the compiled code into an object library in whichever form + your system keeps such libraries. This is the basic PCRE C 8-bit library. + If your system has static and shared libraries, you may have to do this + once for each type. + + (7) If you want to build a 16-bit library (as well as, or instead of the 8-bit + or 32-bit libraries) repeat steps 5-6 with the following files: + + pcre16_byte_order.c + pcre16_chartables.c + pcre16_compile.c + pcre16_config.c + pcre16_dfa_exec.c + pcre16_exec.c + pcre16_fullinfo.c + pcre16_get.c + pcre16_globals.c + pcre16_jit_compile.c + pcre16_maketables.c + pcre16_newline.c + pcre16_ord2utf16.c + pcre16_refcount.c + pcre16_string_utils.c + pcre16_study.c + pcre16_tables.c + pcre16_ucd.c + pcre16_utf16_utils.c + pcre16_valid_utf16.c + pcre16_version.c + pcre16_xclass.c + + (8) If you want to build a 32-bit library (as well as, or instead of the 8-bit + or 16-bit libraries) repeat steps 5-6 with the following files: + + pcre32_byte_order.c + pcre32_chartables.c + pcre32_compile.c + pcre32_config.c + pcre32_dfa_exec.c + pcre32_exec.c + pcre32_fullinfo.c + pcre32_get.c + pcre32_globals.c + pcre32_jit_compile.c + pcre32_maketables.c + pcre32_newline.c + pcre32_ord2utf32.c + pcre32_refcount.c + pcre32_string_utils.c + pcre32_study.c + pcre32_tables.c + pcre32_ucd.c + pcre32_utf32_utils.c + pcre32_valid_utf32.c + pcre32_version.c + pcre32_xclass.c + + (9) If you want to build the POSIX wrapper functions (which apply only to the + 8-bit library), ensure that you have the pcreposix.h file and then compile + pcreposix.c (remembering -DHAVE_CONFIG_H if necessary). Link the result + (on its own) as the pcreposix library. + +(10) The pcretest program can be linked with any combination of the 8-bit, + 16-bit and 32-bit libraries (depending on what you selected in config.h). + Compile pcretest.c and pcre_printint.c (again, don't forget + -DHAVE_CONFIG_H) and link them together with the appropriate library/ies. + If you compiled an 8-bit library, pcretest also needs the pcreposix + wrapper library unless you compiled it with -DNOPOSIX. + +(11) Run pcretest on the testinput files in the testdata directory, and check + that the output matches the corresponding testoutput files. There are + comments about what each test does in the section entitled "Testing PCRE" + in the README file. If you compiled more than one of the 8-bit, 16-bit and + 32-bit libraries, you need to run pcretest with the -16 option to do + 16-bit tests and with the -32 option to do 32-bit tests. + + Some tests are relevant only when certain build-time options are selected. + For example, test 4 is for UTF-8/UTF-16/UTF-32 support, and will not run + if you have built PCRE without it. See the comments at the start of each + testinput file. If you have a suitable Unix-like shell, the RunTest script + will run the appropriate tests for you. The command "RunTest list" will + output a list of all the tests. + + Note that the supplied files are in Unix format, with just LF characters + as line terminators. You may need to edit them to change this if your + system uses a different convention. If you are using Windows, you probably + should use the wintestinput3 file instead of testinput3 (and the + corresponding output file). This is a locale test; wintestinput3 sets the + locale to "french" rather than "fr_FR", and there some minor output + differences. + +(12) If you have built PCRE with SUPPORT_JIT, the JIT features will be tested + by the testdata files. However, you might also like to build and run + the freestanding JIT test program, pcre_jit_test.c. + +(13) If you want to use the pcregrep command, compile and link pcregrep.c; it + uses only the basic 8-bit PCRE library (it does not need the pcreposix + library). + + +THE C++ WRAPPER FUNCTIONS + +The PCRE distribution also contains some C++ wrapper functions and tests, +applicable to the 8-bit library, which were contributed by Google Inc. On a +system that can use "configure" and "make", the functions are automatically +built into a library called pcrecpp. It should be straightforward to compile +the .cc files manually on other systems. The files called xxx_unittest.cc are +test programs for each of the corresponding xxx.cc files. + + +BUILDING FOR VIRTUAL PASCAL + +A script for building PCRE using Borland's C++ compiler for use with VPASCAL +was contributed by Alexander Tokarev. Stefan Weber updated the script and added +additional files. The following files in the distribution are for building PCRE +for use with VP/Borland: makevp_c.txt, makevp_l.txt, makevp.bat, pcregexp.pas. + + +STACK SIZE IN WINDOWS ENVIRONMENTS + +The default processor stack size of 1Mb in some Windows environments is too +small for matching patterns that need much recursion. In particular, test 2 may +fail because of this. Normally, running out of stack causes a crash, but there +have been cases where the test program has just died silently. See your linker +documentation for how to increase stack size if you experience problems. The +Linux default of 8Mb is a reasonable choice for the stack, though even that can +be too small for some pattern/subject combinations. + +PCRE has a compile configuration option to disable the use of stack for +recursion so that heap is used instead. However, pattern matching is +significantly slower when this is done. There is more about stack usage in the +"pcrestack" documentation. + + +LINKING PROGRAMS IN WINDOWS ENVIRONMENTS + +If you want to statically link a program against a PCRE library in the form of +a non-dll .a file, you must define PCRE_STATIC before including pcre.h or +pcrecpp.h, otherwise the pcre_malloc() and pcre_free() exported functions will +be declared __declspec(dllimport), with unwanted results. + + +CALLING CONVENTIONS IN WINDOWS ENVIRONMENTS + +It is possible to compile programs to use different calling conventions using +MSVC. Search the web for "calling conventions" for more information. To make it +easier to change the calling convention for the exported functions in the +PCRE library, the macro PCRE_CALL_CONVENTION is present in all the external +definitions. It can be set externally when compiling (e.g. in CFLAGS). If it is +not set, it defaults to empty; the default calling convention is then used +(which is what is wanted most of the time). + + +COMMENTS ABOUT WIN32 BUILDS (see also "BUILDING PCRE ON WINDOWS WITH CMAKE") + +There are two ways of building PCRE using the "configure, make, make install" +paradigm on Windows systems: using MinGW or using Cygwin. These are not at all +the same thing; they are completely different from each other. There is also +support for building using CMake, which some users find a more straightforward +way of building PCRE under Windows. + +The MinGW home page (http://www.mingw.org/) says this: + + MinGW: A collection of freely available and freely distributable Windows + specific header files and import libraries combined with GNU toolsets that + allow one to produce native Windows programs that do not rely on any + 3rd-party C runtime DLLs. + +The Cygwin home page (http://www.cygwin.com/) says this: + + Cygwin is a Linux-like environment for Windows. It consists of two parts: + + . A DLL (cygwin1.dll) which acts as a Linux API emulation layer providing + substantial Linux API functionality + + . A collection of tools which provide Linux look and feel. + + The Cygwin DLL currently works with all recent, commercially released x86 32 + bit and 64 bit versions of Windows, with the exception of Windows CE. + +On both MinGW and Cygwin, PCRE should build correctly using: + + ./configure && make && make install + +This should create two libraries called libpcre and libpcreposix, and, if you +have enabled building the C++ wrapper, a third one called libpcrecpp. These are +independent libraries: when you link with libpcreposix or libpcrecpp you must +also link with libpcre, which contains the basic functions. (Some earlier +releases of PCRE included the basic libpcre functions in libpcreposix. This no +longer happens.) + +A user submitted a special-purpose patch that makes it easy to create +"pcre.dll" under mingw32 using the "msys" environment. It provides "pcre.dll" +as a special target. If you use this target, no other files are built, and in +particular, the pcretest and pcregrep programs are not built. An example of how +this might be used is: + + ./configure --enable-utf --disable-cpp CFLAGS="-03 -s"; make pcre.dll + +Using Cygwin's compiler generates libraries and executables that depend on +cygwin1.dll. If a library that is generated this way is distributed, +cygwin1.dll has to be distributed as well. Since cygwin1.dll is under the GPL +licence, this forces not only PCRE to be under the GPL, but also the entire +application. A distributor who wants to keep their own code proprietary must +purchase an appropriate Cygwin licence. + +MinGW has no such restrictions. The MinGW compiler generates a library or +executable that can run standalone on Windows without any third party dll or +licensing issues. + +But there is more complication: + +If a Cygwin user uses the -mno-cygwin Cygwin gcc flag, what that really does is +to tell Cygwin's gcc to use the MinGW gcc. Cygwin's gcc is only acting as a +front end to MinGW's gcc (if you install Cygwin's gcc, you get both Cygwin's +gcc and MinGW's gcc). So, a user can: + +. Build native binaries by using MinGW or by getting Cygwin and using + -mno-cygwin. + +. Build binaries that depend on cygwin1.dll by using Cygwin with the normal + compiler flags. + +The test files that are supplied with PCRE are in UNIX format, with LF +characters as line terminators. Unless your PCRE library uses a default newline +option that includes LF as a valid newline, it may be necessary to change the +line terminators in the test files to get some of the tests to work. + + +BUILDING PCRE ON WINDOWS WITH CMAKE + +CMake is an alternative configuration facility that can be used instead of +"configure". CMake creates project files (make files, solution files, etc.) +tailored to numerous development environments, including Visual Studio, +Borland, Msys, MinGW, NMake, and Unix. If possible, use short paths with no +spaces in the names for your CMake installation and your PCRE source and build +directories. + +The following instructions were contributed by a PCRE user. If they are not +followed exactly, errors may occur. In the event that errors do occur, it is +recommended that you delete the CMake cache before attempting to repeat the +CMake build process. In the CMake GUI, the cache can be deleted by selecting +"File > Delete Cache". + +1. Install the latest CMake version available from http://www.cmake.org/, and + ensure that cmake\bin is on your path. + +2. Unzip (retaining folder structure) the PCRE source tree into a source + directory such as C:\pcre. You should ensure your local date and time + is not earlier than the file dates in your source dir if the release is + very new. + +3. Create a new, empty build directory, preferably a subdirectory of the + source dir. For example, C:\pcre\pcre-xx\build. + +4. Run cmake-gui from the Shell envirornment of your build tool, for example, + Msys for Msys/MinGW or Visual Studio Command Prompt for VC/VC++. Do not try + to start Cmake from the Windows Start menu, as this can lead to errors. + +5. Enter C:\pcre\pcre-xx and C:\pcre\pcre-xx\build for the source and build + directories, respectively. + +6. Hit the "Configure" button. + +7. Select the particular IDE / build tool that you are using (Visual + Studio, MSYS makefiles, MinGW makefiles, etc.) + +8. The GUI will then list several configuration options. This is where + you can enable UTF-8 support or other PCRE optional features. + +9. Hit "Configure" again. The adjacent "Generate" button should now be + active. + +10. Hit "Generate". + +11. The build directory should now contain a usable build system, be it a + solution file for Visual Studio, makefiles for MinGW, etc. Exit from + cmake-gui and use the generated build system with your compiler or IDE. + E.g., for MinGW you can run "make", or for Visual Studio, open the PCRE + solution, select the desired configuration (Debug, or Release, etc.) and + build the ALL_BUILD project. + +12. If during configuration with cmake-gui you've elected to build the test + programs, you can execute them by building the test project. E.g., for + MinGW: "make test"; for Visual Studio build the RUN_TESTS project. The + most recent build configuration is targeted by the tests. A summary of + test results is presented. Complete test output is subsequently + available for review in Testing\Temporary under your build dir. + + +USE OF RELATIVE PATHS WITH CMAKE ON WINDOWS + +A PCRE user comments as follows: I thought that others may want to know the +current state of CMAKE_USE_RELATIVE_PATHS support on Windows. Here it is: + +-- AdditionalIncludeDirectories is only partially modified (only the + first path - see below) +-- Only some of the contained file paths are modified - shown below for + pcre.vcproj +-- It properly modifies + +I am sure CMake people can fix that if they want to. Until then one will +need to replace existing absolute paths in project files with relative +paths manually (e.g. from VS) - relative to project file location. I did +just that before being told to try CMAKE_USE_RELATIVE_PATHS. Not a big +deal. + +AdditionalIncludeDirectories="E:\builds\pcre\build;E:\builds\pcre\pcre-7.5;" +AdditionalIncludeDirectories=".;E:\builds\pcre\pcre-7.5;" + +RelativePath="pcre.h" +RelativePath="pcre_chartables.c" +RelativePath="pcre_chartables.c.rule" + + +TESTING WITH RUNTEST.BAT + +If configured with CMake, building the test project ("make test" or building +ALL_TESTS in Visual Studio) creates (and runs) pcre_test.bat (and depending +on your configuration options, possibly other test programs) in the build +directory. Pcre_test.bat runs RunTest.Bat with correct source and exe paths. + +For manual testing with RunTest.bat, provided the build dir is a subdirectory +of the source directory: Open command shell window. Chdir to the location +of your pcretest.exe and pcregrep.exe programs. Call RunTest.bat with +"..\RunTest.Bat" or "..\..\RunTest.bat" as appropriate. + +To run only a particular test with RunTest.Bat provide a test number argument. + +Otherwise: + +1. Copy RunTest.bat into the directory where pcretest.exe and pcregrep.exe + have been created. + +2. Edit RunTest.bat to indentify the full or relative location of + the pcre source (wherein which the testdata folder resides), e.g.: + + set srcdir=C:\pcre\pcre-8.20 + +3. In a Windows command environment, chdir to the location of your bat and + exe programs. + +4. Run RunTest.bat. Test outputs will automatically be compared to expected + results, and discrepancies will be identified in the console output. + +To independently test the just-in-time compiler, run pcre_jit_test.exe. +To test pcrecpp, run pcrecpp_unittest.exe, pcre_stringpiece_unittest.exe and +pcre_scanner_unittest.exe. + + +BUILDING UNDER WINDOWS CE WITH VISUAL STUDIO 200x + +Vincent Richomme sent a zip archive of files to help with this process. They +can be found in the file "pcre-vsbuild.zip" in the Contrib directory of the FTP +site. + + +BUILDING UNDER WINDOWS WITH BCC5.5 + +Michael Roy sent these comments about building PCRE under Windows with BCC5.5: + +Some of the core BCC libraries have a version of PCRE from 1998 built in, which +can lead to pcre_exec() giving an erroneous PCRE_ERROR_NULL from a version +mismatch. I'm including an easy workaround below, if you'd like to include it +in the non-unix instructions: + +When linking a project with BCC5.5, pcre.lib must be included before any of the +libraries cw32.lib, cw32i.lib, cw32mt.lib, and cw32mti.lib on the command line. + + +BUILDING USING BORLAND C++ BUILDER 2007 (CB2007) AND HIGHER + +A PCRE user sent these comments about this environment (see also the comment +from another user that follows them): + +The XE versions of C++ Builder come with a RegularExpressionsCore class which +contain a version of TPerlRegEx. However, direct use of the C PCRE library may +be desirable. + +The default makevp.bat, however, supplied with PCRE builds a version of PCRE +that is not usable with any version of C++ Builder because the compiler ships +with an embedded version of PCRE, version 2.01 from 1998! [See also the note +about BCC5.5 above.] If you want to use PCRE you'll need to rename the +functions (pcre_compile to pcre_compile_bcc, etc) or do as I have done and just +use the 16 bit versions. I'm using std::wstring everywhere anyway. Since the +embedded version of PCRE does not have the 16 bit function names, there is no +conflict. + +Building PCRE using a C++ Builder static library project file (recommended): + +1. Rename or remove pcre.h, pcreposi.h, and pcreposix.h from your C++ Builder +original include path. + +2. Download PCRE from pcre.org and extract to a directory. + +3. Rename pcre_chartables.c.dist to pcre_chartables.c, pcre.h.generic to +pcre.h, and config.h.generic to config.h. + +4. Edit pcre.h and pcre_config.c so that they include config.h. + +5. Edit config.h like so: + +Comment out the following lines: +#define PACKAGE "pcre" +#define PACKAGE_BUGREPORT "" +#define PACKAGE_NAME "PCRE" +#define PACKAGE_STRING "PCRE 8.32" +#define PACKAGE_TARNAME "pcre" +#define PACKAGE_URL "" +#define PACKAGE_VERSION "8.32" + +Add the following lines: +#ifndef SUPPORT_UTF +#define SUPPORT_UTF 100 // any value is fine +#endif + +#ifndef SUPPORT_UCP +#define SUPPORT_UCP 101 // any value is fine +#endif + +#ifndef SUPPORT_UCP +#define SUPPORT_PCRE16 102 // any value is fine +#endif + +#ifndef SUPPORT_UTF8 +#define SUPPORT_UTF8 103 // any value is fine +#endif + +6. Build a C++ Builder project using the IDE. Go to File / New / Other and +choose Static Library. You can name it pcre.cbproj or whatever. Now set your +paths by going to Project / Options. Set the Include path. Do this from the +"Base" option to apply to both Release and Debug builds. Now add the following +files to the project: + +pcre.h +pcre16_byte_order.c +pcre16_chartables.c +pcre16_compile.c +pcre16_config.c +pcre16_dfa_exec.c +pcre16_exec.c +pcre16_fullinfo.c +pcre16_get.c +pcre16_globals.c +pcre16_maketables.c +pcre16_newline.c +pcre16_ord2utf16.c +pcre16_printint.c +pcre16_refcount.c +pcre16_string_utils.c +pcre16_study.c +pcre16_tables.c +pcre16_ucd.c +pcre16_utf16_utils.c +pcre16_valid_utf16.c +pcre16_version.c +pcre16_xclass.c + +//Optional +pcre_version.c + +7. After compiling the .lib file, copy the .lib and header files to a project +you want to use PCRE with. Enjoy. + +Optional ... Building PCRE using the makevp.bat file: + +1. Edit makevp_c.txt and makevp_l.txt and change all the names to the 16 bit +versions. + +2. Edit makevp.bat and set the path to C++ Builder. Run makevp.bat. + +Another PCRE user added this comment: + +Another approach I successfully used for some years with BCB 5 and 6 was to +make sure that include and library paths of PCRE are configured before the +default paths of the IDE in the dialogs where one can manage those paths. +Afterwards one can open the project files using a text editor and manually add +the self created library for pcre itself, pcrecpp doesn't ship with the IDE, in +the library nodes where the IDE manages its own libraries to link against in +front of the IDE-own libraries. This way one can use the default PCRE function +names without getting access violations on runtime. + + <ALLLIB value="libpcre.lib $(LIBFILES) $(LIBRARIES) import32.lib cp32mt.lib"/> + + +BUILDING PCRE ON OPENVMS + +Stephen Hoffman sent the following, in December 2012: + +"Here <http://labs.hoffmanlabs.com/node/1847> is a very short write-up on the +OpenVMS port and here + +<http://labs.hoffmanlabs.com/labsnotes/pcre-vms-8_32.zip> + +is a zip with the OpenVMS files, and with one modified testing-related PCRE +file." This is a port of PCRE 8.32. + +Earlier, Dan Mooney sent the following comments about building PCRE on OpenVMS. +They relate to an older version of PCRE that used fewer source files, so the +exact commands will need changing. See the current list of source files above. + +"It was quite easy to compile and link the library. I don't have a formal +make file but the attached file [reproduced below] contains the OpenVMS DCL +commands I used to build the library. I had to add #define +POSIX_MALLOC_THRESHOLD 10 to pcre.h since it was not defined anywhere. + +The library was built on: +O/S: HP OpenVMS v7.3-1 +Compiler: Compaq C v6.5-001-48BCD +Linker: vA13-01 + +The test results did not match 100% due to the issues you mention in your +documentation regarding isprint(), iscntrl(), isgraph() and ispunct(). I +modified some of the character tables temporarily and was able to get the +results to match. Tests using the fr locale did not match since I don't have +that locale loaded. The study size was always reported to be 3 less than the +value in the standard test output files." + +========================= +$! This DCL procedure builds PCRE on OpenVMS +$! +$! I followed the instructions in the non-unix-use file in the distribution. +$! +$ COMPILE == "CC/LIST/NOMEMBER_ALIGNMENT/PREFIX_LIBRARY_ENTRIES=ALL_ENTRIES +$ COMPILE DFTABLES.C +$ LINK/EXE=DFTABLES.EXE DFTABLES.OBJ +$ RUN DFTABLES.EXE/OUTPUT=CHARTABLES.C +$ COMPILE MAKETABLES.C +$ COMPILE GET.C +$ COMPILE STUDY.C +$! I had to set POSIX_MALLOC_THRESHOLD to 10 in PCRE.H since the symbol +$! did not seem to be defined anywhere. +$! I edited pcre.h and added #DEFINE SUPPORT_UTF8 to enable UTF8 support. +$ COMPILE PCRE.C +$ LIB/CREATE PCRE MAKETABLES.OBJ, GET.OBJ, STUDY.OBJ, PCRE.OBJ +$! I had to set POSIX_MALLOC_THRESHOLD to 10 in PCRE.H since the symbol +$! did not seem to be defined anywhere. +$ COMPILE PCREPOSIX.C +$ LIB/CREATE PCREPOSIX PCREPOSIX.OBJ +$ COMPILE PCRETEST.C +$ LINK/EXE=PCRETEST.EXE PCRETEST.OBJ, PCRE/LIB, PCREPOSIX/LIB +$! C programs that want access to command line arguments must be +$! defined as a symbol +$ PCRETEST :== "$ SYS$ROADSUSERS:[DMOONEY.REGEXP]PCRETEST.EXE" +$! Arguments must be enclosed in quotes. +$ PCRETEST "-C" +$! Test results: +$! +$! The test results did not match 100%. The functions isprint(), iscntrl(), +$! isgraph() and ispunct() on OpenVMS must not produce the same results +$! as the system that built the test output files provided with the +$! distribution. +$! +$! The study size did not match and was always 3 less on OpenVMS. +$! +$! Locale could not be set to fr +$! +========================= + + +BUILDING PCRE ON STRATUS OPENVOS + +These notes on the port of PCRE to VOS (lightly edited) were supplied by +Ashutosh Warikoo, whose email address has the local part awarikoo and the +domain nse.co.in. The port was for version 7.9 in August 2009. + +1. Building PCRE + +I built pcre on OpenVOS Release 17.0.1at using GNU Tools 3.4a without any +problems. I used the following packages to build PCRE: + + ftp://ftp.stratus.com/pub/vos/posix/ga/posix.save.evf.gz + +Please read and follow the instructions that come with these packages. To start +the build of pcre, from the root of the package type: + + ./build.sh + +2. Installing PCRE + +Once you have successfully built PCRE, login to the SysAdmin group, switch to +the root user, and type + + [ !create_dir (master_disk)>usr --if needed ] + [ !create_dir (master_disk)>usr>local --if needed ] + !gmake install + +This installs PCRE and its man pages into /usr/local. You can add +(master_disk)>usr>local>bin to your command search paths, or if you are in +BASH, add /usr/local/bin to the PATH environment variable. + +4. Restrictions + +This port requires readline library optionally. However during the build I +faced some yet unexplored errors while linking with readline. As it was an +optional component I chose to disable it. + +5. Known Problems + +I ran the test suite, but you will have to be your own judge of whether this +command, and this port, suits your purposes. If you find any problems that +appear to be related to the port itself, please let me know. Please see the +build.log file in the root of the package also. + + +BUILDING PCRE ON NATIVE Z/OS AND Z/VM + +z/OS and z/VM are operating systems for mainframe computers, produced by IBM. +The character code used is EBCDIC, not ASCII or Unicode. In z/OS, UNIX APIs and +applications can be supported through UNIX System Services, and in such an +environment PCRE can be built in the same way as in other systems. However, in +native z/OS (without UNIX System Services) and in z/VM, special ports are +required. For details, please see this web site: + + http://www.zaconsultants.net + +There is also a mirror here: + + http://www.vsoft-software.com/downloads.html + +========================== +Last Updated: 14 May 2013 diff --git a/plugins/Pcre16/docs/doc/html/README.txt b/plugins/Pcre16/docs/doc/html/README.txt new file mode 100644 index 0000000000..88f2dfd4ef --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/README.txt @@ -0,0 +1,991 @@ +README file for PCRE (Perl-compatible regular expression library) +----------------------------------------------------------------- + +The latest release of PCRE is always available in three alternative formats +from: + + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.gz + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.bz2 + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.zip + +There is a mailing list for discussion about the development of PCRE at +pcre-dev@exim.org. You can access the archives and subscribe or manage your +subscription here: + + https://lists.exim.org/mailman/listinfo/pcre-dev + +Please read the NEWS file if you are upgrading from a previous release. +The contents of this README file are: + + The PCRE APIs + Documentation for PCRE + Contributions by users of PCRE + Building PCRE on non-Unix-like systems + Building PCRE without using autotools + Building PCRE using autotools + Retrieving configuration information + Shared libraries + Cross-compiling using autotools + Using HP's ANSI C++ compiler (aCC) + Compiling in Tru64 using native compilers + Using Sun's compilers for Solaris + Using PCRE from MySQL + Making new tarballs + Testing PCRE + Character tables + File manifest + + +The PCRE APIs +------------- + +PCRE is written in C, and it has its own API. There are three sets of +functions, one for the 8-bit library, which processes strings of bytes, one for +the 16-bit library, which processes strings of 16-bit values, and one for the +32-bit library, which processes strings of 32-bit values. The distribution also +includes a set of C++ wrapper functions (see the pcrecpp man page for details), +courtesy of Google Inc., which can be used to call the 8-bit PCRE library from +C++. + +In addition, there is a set of C wrapper functions (again, just for the 8-bit +library) that are based on the POSIX regular expression API (see the pcreposix +man page). These end up in the library called libpcreposix. Note that this just +provides a POSIX calling interface to PCRE; the regular expressions themselves +still follow Perl syntax and semantics. The POSIX API is restricted, and does +not give full access to all of PCRE's facilities. + +The header file for the POSIX-style functions is called pcreposix.h. The +official POSIX name is regex.h, but I did not want to risk possible problems +with existing files of that name by distributing it that way. To use PCRE with +an existing program that uses the POSIX API, pcreposix.h will have to be +renamed or pointed at by a link. + +If you are using the POSIX interface to PCRE and there is already a POSIX regex +library installed on your system, as well as worrying about the regex.h header +file (as mentioned above), you must also take care when linking programs to +ensure that they link with PCRE's libpcreposix library. Otherwise they may pick +up the POSIX functions of the same name from the other library. + +One way of avoiding this confusion is to compile PCRE with the addition of +-Dregcomp=PCREregcomp (and similarly for the other POSIX functions) to the +compiler flags (CFLAGS if you are using "configure" -- see below). This has the +effect of renaming the functions so that the names no longer clash. Of course, +you have to do the same thing for your applications, or write them using the +new names. + + +Documentation for PCRE +---------------------- + +If you install PCRE in the normal way on a Unix-like system, you will end up +with a set of man pages whose names all start with "pcre". The one that is just +called "pcre" lists all the others. In addition to these man pages, the PCRE +documentation is supplied in two other forms: + + 1. There are files called doc/pcre.txt, doc/pcregrep.txt, and + doc/pcretest.txt in the source distribution. The first of these is a + concatenation of the text forms of all the section 3 man pages except + the listing of pcredemo.c and those that summarize individual functions. + The other two are the text forms of the section 1 man pages for the + pcregrep and pcretest commands. These text forms are provided for ease of + scanning with text editors or similar tools. They are installed in + <prefix>/share/doc/pcre, where <prefix> is the installation prefix + (defaulting to /usr/local). + + 2. A set of files containing all the documentation in HTML form, hyperlinked + in various ways, and rooted in a file called index.html, is distributed in + doc/html and installed in <prefix>/share/doc/pcre/html. + +Users of PCRE have contributed files containing the documentation for various +releases in CHM format. These can be found in the Contrib directory of the FTP +site (see next section). + + +Contributions by users of PCRE +------------------------------ + +You can find contributions from PCRE users in the directory + + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/Contrib + +There is a README file giving brief descriptions of what they are. Some are +complete in themselves; others are pointers to URLs containing relevant files. +Some of this material is likely to be well out-of-date. Several of the earlier +contributions provided support for compiling PCRE on various flavours of +Windows (I myself do not use Windows). Nowadays there is more Windows support +in the standard distribution, so these contibutions have been archived. + +A PCRE user maintains downloadable Windows binaries of the pcregrep and +pcretest programs here: + + http://www.rexegg.com/pcregrep-pcretest.html + + +Building PCRE on non-Unix-like systems +-------------------------------------- + +For a non-Unix-like system, please read the comments in the file +NON-AUTOTOOLS-BUILD, though if your system supports the use of "configure" and +"make" you may be able to build PCRE using autotools in the same way as for +many Unix-like systems. + +PCRE can also be configured using the GUI facility provided by CMake's +cmake-gui command. This creates Makefiles, solution files, etc. The file +NON-AUTOTOOLS-BUILD has information about CMake. + +PCRE has been compiled on many different operating systems. It should be +straightforward to build PCRE on any system that has a Standard C compiler and +library, because it uses only Standard C functions. + + +Building PCRE without using autotools +------------------------------------- + +The use of autotools (in particular, libtool) is problematic in some +environments, even some that are Unix or Unix-like. See the NON-AUTOTOOLS-BUILD +file for ways of building PCRE without using autotools. + + +Building PCRE using autotools +----------------------------- + +If you are using HP's ANSI C++ compiler (aCC), please see the special note +in the section entitled "Using HP's ANSI C++ compiler (aCC)" below. + +The following instructions assume the use of the widely used "configure; make; +make install" (autotools) process. + +To build PCRE on system that supports autotools, first run the "configure" +command from the PCRE distribution directory, with your current directory set +to the directory where you want the files to be created. This command is a +standard GNU "autoconf" configuration script, for which generic instructions +are supplied in the file INSTALL. + +Most commonly, people build PCRE within its own distribution directory, and in +this case, on many systems, just running "./configure" is sufficient. However, +the usual methods of changing standard defaults are available. For example: + +CFLAGS='-O2 -Wall' ./configure --prefix=/opt/local + +This command specifies that the C compiler should be run with the flags '-O2 +-Wall' instead of the default, and that "make install" should install PCRE +under /opt/local instead of the default /usr/local. + +If you want to build in a different directory, just run "configure" with that +directory as current. For example, suppose you have unpacked the PCRE source +into /source/pcre/pcre-xxx, but you want to build it in /build/pcre/pcre-xxx: + +cd /build/pcre/pcre-xxx +/source/pcre/pcre-xxx/configure + +PCRE is written in C and is normally compiled as a C library. However, it is +possible to build it as a C++ library, though the provided building apparatus +does not have any features to support this. + +There are some optional features that can be included or omitted from the PCRE +library. They are also documented in the pcrebuild man page. + +. By default, both shared and static libraries are built. You can change this + by adding one of these options to the "configure" command: + + --disable-shared + --disable-static + + (See also "Shared libraries on Unix-like systems" below.) + +. By default, only the 8-bit library is built. If you add --enable-pcre16 to + the "configure" command, the 16-bit library is also built. If you add + --enable-pcre32 to the "configure" command, the 32-bit library is also built. + If you want only the 16-bit or 32-bit library, use --disable-pcre8 to disable + building the 8-bit library. + +. If you are building the 8-bit library and want to suppress the building of + the C++ wrapper library, you can add --disable-cpp to the "configure" + command. Otherwise, when "configure" is run without --disable-pcre8, it will + try to find a C++ compiler and C++ header files, and if it succeeds, it will + try to build the C++ wrapper. + +. If you want to include support for just-in-time compiling, which can give + large performance improvements on certain platforms, add --enable-jit to the + "configure" command. This support is available only for certain hardware + architectures. If you try to enable it on an unsupported architecture, there + will be a compile time error. + +. When JIT support is enabled, pcregrep automatically makes use of it, unless + you add --disable-pcregrep-jit to the "configure" command. + +. If you want to make use of the support for UTF-8 Unicode character strings in + the 8-bit library, or UTF-16 Unicode character strings in the 16-bit library, + or UTF-32 Unicode character strings in the 32-bit library, you must add + --enable-utf to the "configure" command. Without it, the code for handling + UTF-8, UTF-16 and UTF-8 is not included in the relevant library. Even + when --enable-utf is included, the use of a UTF encoding still has to be + enabled by an option at run time. When PCRE is compiled with this option, its + input can only either be ASCII or UTF-8/16/32, even when running on EBCDIC + platforms. It is not possible to use both --enable-utf and --enable-ebcdic at + the same time. + +. There are no separate options for enabling UTF-8, UTF-16 and UTF-32 + independently because that would allow ridiculous settings such as requesting + UTF-16 support while building only the 8-bit library. However, the option + --enable-utf8 is retained for backwards compatibility with earlier releases + that did not support 16-bit or 32-bit character strings. It is synonymous with + --enable-utf. It is not possible to configure one library with UTF support + and the other without in the same configuration. + +. If, in addition to support for UTF-8/16/32 character strings, you want to + include support for the \P, \p, and \X sequences that recognize Unicode + character properties, you must add --enable-unicode-properties to the + "configure" command. This adds about 30K to the size of the library (in the + form of a property table); only the basic two-letter properties such as Lu + are supported. + +. You can build PCRE to recognize either CR or LF or the sequence CRLF or any + of the preceding, or any of the Unicode newline sequences as indicating the + end of a line. Whatever you specify at build time is the default; the caller + of PCRE can change the selection at run time. The default newline indicator + is a single LF character (the Unix standard). You can specify the default + newline indicator by adding --enable-newline-is-cr or --enable-newline-is-lf + or --enable-newline-is-crlf or --enable-newline-is-anycrlf or + --enable-newline-is-any to the "configure" command, respectively. + + If you specify --enable-newline-is-cr or --enable-newline-is-crlf, some of + the standard tests will fail, because the lines in the test files end with + LF. Even if the files are edited to change the line endings, there are likely + to be some failures. With --enable-newline-is-anycrlf or + --enable-newline-is-any, many tests should succeed, but there may be some + failures. + +. By default, the sequence \R in a pattern matches any Unicode line ending + sequence. This is independent of the option specifying what PCRE considers to + be the end of a line (see above). However, the caller of PCRE can restrict \R + to match only CR, LF, or CRLF. You can make this the default by adding + --enable-bsr-anycrlf to the "configure" command (bsr = "backslash R"). + +. When called via the POSIX interface, PCRE uses malloc() to get additional + storage for processing capturing parentheses if there are more than 10 of + them in a pattern. You can increase this threshold by setting, for example, + + --with-posix-malloc-threshold=20 + + on the "configure" command. + +. PCRE has a counter that limits the depth of nesting of parentheses in a + pattern. This limits the amount of system stack that a pattern uses when it + is compiled. The default is 250, but you can change it by setting, for + example, + + --with-parens-nest-limit=500 + +. PCRE has a counter that can be set to limit the amount of resources it uses + when matching a pattern. If the limit is exceeded during a match, the match + fails. The default is ten million. You can change the default by setting, for + example, + + --with-match-limit=500000 + + on the "configure" command. This is just the default; individual calls to + pcre_exec() can supply their own value. There is more discussion on the + pcreapi man page. + +. There is a separate counter that limits the depth of recursive function calls + during a matching process. This also has a default of ten million, which is + essentially "unlimited". You can change the default by setting, for example, + + --with-match-limit-recursion=500000 + + Recursive function calls use up the runtime stack; running out of stack can + cause programs to crash in strange ways. There is a discussion about stack + sizes in the pcrestack man page. + +. The default maximum compiled pattern size is around 64K. You can increase + this by adding --with-link-size=3 to the "configure" command. In the 8-bit + library, PCRE then uses three bytes instead of two for offsets to different + parts of the compiled pattern. In the 16-bit library, --with-link-size=3 is + the same as --with-link-size=4, which (in both libraries) uses four-byte + offsets. Increasing the internal link size reduces performance. In the 32-bit + library, the only supported link size is 4. + +. You can build PCRE so that its internal match() function that is called from + pcre_exec() does not call itself recursively. Instead, it uses memory blocks + obtained from the heap via the special functions pcre_stack_malloc() and + pcre_stack_free() to save data that would otherwise be saved on the stack. To + build PCRE like this, use + + --disable-stack-for-recursion + + on the "configure" command. PCRE runs more slowly in this mode, but it may be + necessary in environments with limited stack sizes. This applies only to the + normal execution of the pcre_exec() function; if JIT support is being + successfully used, it is not relevant. Equally, it does not apply to + pcre_dfa_exec(), which does not use deeply nested recursion. There is a + discussion about stack sizes in the pcrestack man page. + +. For speed, PCRE uses four tables for manipulating and identifying characters + whose code point values are less than 256. By default, it uses a set of + tables for ASCII encoding that is part of the distribution. If you specify + + --enable-rebuild-chartables + + a program called dftables is compiled and run in the default C locale when + you obey "make". It builds a source file called pcre_chartables.c. If you do + not specify this option, pcre_chartables.c is created as a copy of + pcre_chartables.c.dist. See "Character tables" below for further information. + +. It is possible to compile PCRE for use on systems that use EBCDIC as their + character code (as opposed to ASCII/Unicode) by specifying + + --enable-ebcdic + + This automatically implies --enable-rebuild-chartables (see above). However, + when PCRE is built this way, it always operates in EBCDIC. It cannot support + both EBCDIC and UTF-8/16/32. There is a second option, --enable-ebcdic-nl25, + which specifies that the code value for the EBCDIC NL character is 0x25 + instead of the default 0x15. + +. In environments where valgrind is installed, if you specify + + --enable-valgrind + + PCRE will use valgrind annotations to mark certain memory regions as + unaddressable. This allows it to detect invalid memory accesses, and is + mostly useful for debugging PCRE itself. + +. In environments where the gcc compiler is used and lcov version 1.6 or above + is installed, if you specify + + --enable-coverage + + the build process implements a code coverage report for the test suite. The + report is generated by running "make coverage". If ccache is installed on + your system, it must be disabled when building PCRE for coverage reporting. + You can do this by setting the environment variable CCACHE_DISABLE=1 before + running "make" to build PCRE. There is more information about coverage + reporting in the "pcrebuild" documentation. + +. The pcregrep program currently supports only 8-bit data files, and so + requires the 8-bit PCRE library. It is possible to compile pcregrep to use + libz and/or libbz2, in order to read .gz and .bz2 files (respectively), by + specifying one or both of + + --enable-pcregrep-libz + --enable-pcregrep-libbz2 + + Of course, the relevant libraries must be installed on your system. + +. The default size (in bytes) of the internal buffer used by pcregrep can be + set by, for example: + + --with-pcregrep-bufsize=51200 + + The value must be a plain integer. The default is 20480. + +. It is possible to compile pcretest so that it links with the libreadline + or libedit libraries, by specifying, respectively, + + --enable-pcretest-libreadline or --enable-pcretest-libedit + + If this is done, when pcretest's input is from a terminal, it reads it using + the readline() function. This provides line-editing and history facilities. + Note that libreadline is GPL-licenced, so if you distribute a binary of + pcretest linked in this way, there may be licensing issues. These can be + avoided by linking with libedit (which has a BSD licence) instead. + + Enabling libreadline causes the -lreadline option to be added to the pcretest + build. In many operating environments with a sytem-installed readline + library this is sufficient. However, in some environments (e.g. if an + unmodified distribution version of readline is in use), it may be necessary + to specify something like LIBS="-lncurses" as well. This is because, to quote + the readline INSTALL, "Readline uses the termcap functions, but does not link + with the termcap or curses library itself, allowing applications which link + with readline the to choose an appropriate library." If you get error + messages about missing functions tgetstr, tgetent, tputs, tgetflag, or tgoto, + this is the problem, and linking with the ncurses library should fix it. + +The "configure" script builds the following files for the basic C library: + +. Makefile the makefile that builds the library +. config.h build-time configuration options for the library +. pcre.h the public PCRE header file +. pcre-config script that shows the building settings such as CFLAGS + that were set for "configure" +. libpcre.pc ) data for the pkg-config command +. libpcre16.pc ) +. libpcre32.pc ) +. libpcreposix.pc ) +. libtool script that builds shared and/or static libraries + +Versions of config.h and pcre.h are distributed in the PCRE tarballs under the +names config.h.generic and pcre.h.generic. These are provided for those who +have to built PCRE without using "configure" or CMake. If you use "configure" +or CMake, the .generic versions are not used. + +When building the 8-bit library, if a C++ compiler is found, the following +files are also built: + +. libpcrecpp.pc data for the pkg-config command +. pcrecpparg.h header file for calling PCRE via the C++ wrapper +. pcre_stringpiece.h header for the C++ "stringpiece" functions + +The "configure" script also creates config.status, which is an executable +script that can be run to recreate the configuration, and config.log, which +contains compiler output from tests that "configure" runs. + +Once "configure" has run, you can run "make". This builds the the libraries +libpcre, libpcre16 and/or libpcre32, and a test program called pcretest. If you +enabled JIT support with --enable-jit, a test program called pcre_jit_test is +built as well. + +If the 8-bit library is built, libpcreposix and the pcregrep command are also +built, and if a C++ compiler was found on your system, and you did not disable +it with --disable-cpp, "make" builds the C++ wrapper library, which is called +libpcrecpp, as well as some test programs called pcrecpp_unittest, +pcre_scanner_unittest, and pcre_stringpiece_unittest. + +The command "make check" runs all the appropriate tests. Details of the PCRE +tests are given below in a separate section of this document. + +You can use "make install" to install PCRE into live directories on your +system. The following are installed (file names are all relative to the +<prefix> that is set when "configure" is run): + + Commands (bin): + pcretest + pcregrep (if 8-bit support is enabled) + pcre-config + + Libraries (lib): + libpcre16 (if 16-bit support is enabled) + libpcre32 (if 32-bit support is enabled) + libpcre (if 8-bit support is enabled) + libpcreposix (if 8-bit support is enabled) + libpcrecpp (if 8-bit and C++ support is enabled) + + Configuration information (lib/pkgconfig): + libpcre16.pc + libpcre32.pc + libpcre.pc + libpcreposix.pc + libpcrecpp.pc (if C++ support is enabled) + + Header files (include): + pcre.h + pcreposix.h + pcre_scanner.h ) + pcre_stringpiece.h ) if C++ support is enabled + pcrecpp.h ) + pcrecpparg.h ) + + Man pages (share/man/man{1,3}): + pcregrep.1 + pcretest.1 + pcre-config.1 + pcre.3 + pcre*.3 (lots more pages, all starting "pcre") + + HTML documentation (share/doc/pcre/html): + index.html + *.html (lots more pages, hyperlinked from index.html) + + Text file documentation (share/doc/pcre): + AUTHORS + COPYING + ChangeLog + LICENCE + NEWS + README + pcre.txt (a concatenation of the man(3) pages) + pcretest.txt the pcretest man page + pcregrep.txt the pcregrep man page + pcre-config.txt the pcre-config man page + +If you want to remove PCRE from your system, you can run "make uninstall". +This removes all the files that "make install" installed. However, it does not +remove any directories, because these are often shared with other programs. + + +Retrieving configuration information +------------------------------------ + +Running "make install" installs the command pcre-config, which can be used to +recall information about the PCRE configuration and installation. For example: + + pcre-config --version + +prints the version number, and + + pcre-config --libs + +outputs information about where the library is installed. This command can be +included in makefiles for programs that use PCRE, saving the programmer from +having to remember too many details. + +The pkg-config command is another system for saving and retrieving information +about installed libraries. Instead of separate commands for each library, a +single command is used. For example: + + pkg-config --cflags pcre + +The data is held in *.pc files that are installed in a directory called +<prefix>/lib/pkgconfig. + + +Shared libraries +---------------- + +The default distribution builds PCRE as shared libraries and static libraries, +as long as the operating system supports shared libraries. Shared library +support relies on the "libtool" script which is built as part of the +"configure" process. + +The libtool script is used to compile and link both shared and static +libraries. They are placed in a subdirectory called .libs when they are newly +built. The programs pcretest and pcregrep are built to use these uninstalled +libraries (by means of wrapper scripts in the case of shared libraries). When +you use "make install" to install shared libraries, pcregrep and pcretest are +automatically re-built to use the newly installed shared libraries before being +installed themselves. However, the versions left in the build directory still +use the uninstalled libraries. + +To build PCRE using static libraries only you must use --disable-shared when +configuring it. For example: + +./configure --prefix=/usr/gnu --disable-shared + +Then run "make" in the usual way. Similarly, you can use --disable-static to +build only shared libraries. + + +Cross-compiling using autotools +------------------------------- + +You can specify CC and CFLAGS in the normal way to the "configure" command, in +order to cross-compile PCRE for some other host. However, you should NOT +specify --enable-rebuild-chartables, because if you do, the dftables.c source +file is compiled and run on the local host, in order to generate the inbuilt +character tables (the pcre_chartables.c file). This will probably not work, +because dftables.c needs to be compiled with the local compiler, not the cross +compiler. + +When --enable-rebuild-chartables is not specified, pcre_chartables.c is created +by making a copy of pcre_chartables.c.dist, which is a default set of tables +that assumes ASCII code. Cross-compiling with the default tables should not be +a problem. + +If you need to modify the character tables when cross-compiling, you should +move pcre_chartables.c.dist out of the way, then compile dftables.c by hand and +run it on the local host to make a new version of pcre_chartables.c.dist. +Then when you cross-compile PCRE this new version of the tables will be used. + + +Using HP's ANSI C++ compiler (aCC) +---------------------------------- + +Unless C++ support is disabled by specifying the "--disable-cpp" option of the +"configure" script, you must include the "-AA" option in the CXXFLAGS +environment variable in order for the C++ components to compile correctly. + +Also, note that the aCC compiler on PA-RISC platforms may have a defect whereby +needed libraries fail to get included when specifying the "-AA" compiler +option. If you experience unresolved symbols when linking the C++ programs, +use the workaround of specifying the following environment variable prior to +running the "configure" script: + + CXXLDFLAGS="-lstd_v2 -lCsup_v2" + + +Compiling in Tru64 using native compilers +----------------------------------------- + +The following error may occur when compiling with native compilers in the Tru64 +operating system: + + CXX libpcrecpp_la-pcrecpp.lo +cxx: Error: /usr/lib/cmplrs/cxx/V7.1-006/include/cxx/iosfwd, line 58: #error + directive: "cannot include iosfwd -- define __USE_STD_IOSTREAM to + override default - see section 7.1.2 of the C++ Using Guide" +#error "cannot include iosfwd -- define __USE_STD_IOSTREAM to override default +- see section 7.1.2 of the C++ Using Guide" + +This may be followed by other errors, complaining that 'namespace "std" has no +member'. The solution to this is to add the line + +#define __USE_STD_IOSTREAM 1 + +to the config.h file. + + +Using Sun's compilers for Solaris +--------------------------------- + +A user reports that the following configurations work on Solaris 9 sparcv9 and +Solaris 9 x86 (32-bit): + + Solaris 9 sparcv9: ./configure --disable-cpp CC=/bin/cc CFLAGS="-m64 -g" + Solaris 9 x86: ./configure --disable-cpp CC=/bin/cc CFLAGS="-g" + + +Using PCRE from MySQL +--------------------- + +On systems where both PCRE and MySQL are installed, it is possible to make use +of PCRE from within MySQL, as an alternative to the built-in pattern matching. +There is a web page that tells you how to do this: + + http://www.mysqludf.org/lib_mysqludf_preg/index.php + + +Making new tarballs +------------------- + +The command "make dist" creates three PCRE tarballs, in tar.gz, tar.bz2, and +zip formats. The command "make distcheck" does the same, but then does a trial +build of the new distribution to ensure that it works. + +If you have modified any of the man page sources in the doc directory, you +should first run the PrepareRelease script before making a distribution. This +script creates the .txt and HTML forms of the documentation from the man pages. + + +Testing PCRE +------------ + +To test the basic PCRE library on a Unix-like system, run the RunTest script. +There is another script called RunGrepTest that tests the options of the +pcregrep command. If the C++ wrapper library is built, three test programs +called pcrecpp_unittest, pcre_scanner_unittest, and pcre_stringpiece_unittest +are also built. When JIT support is enabled, another test program called +pcre_jit_test is built. + +Both the scripts and all the program tests are run if you obey "make check" or +"make test". For other environments, see the instructions in +NON-AUTOTOOLS-BUILD. + +The RunTest script runs the pcretest test program (which is documented in its +own man page) on each of the relevant testinput files in the testdata +directory, and compares the output with the contents of the corresponding +testoutput files. RunTest uses a file called testtry to hold the main output +from pcretest. Other files whose names begin with "test" are used as working +files in some tests. + +Some tests are relevant only when certain build-time options were selected. For +example, the tests for UTF-8/16/32 support are run only if --enable-utf was +used. RunTest outputs a comment when it skips a test. + +Many of the tests that are not skipped are run up to three times. The second +run forces pcre_study() to be called for all patterns except for a few in some +tests that are marked "never study" (see the pcretest program for how this is +done). If JIT support is available, the non-DFA tests are run a third time, +this time with a forced pcre_study() with the PCRE_STUDY_JIT_COMPILE option. +This testing can be suppressed by putting "nojit" on the RunTest command line. + +The entire set of tests is run once for each of the 8-bit, 16-bit and 32-bit +libraries that are enabled. If you want to run just one set of tests, call +RunTest with either the -8, -16 or -32 option. + +If valgrind is installed, you can run the tests under it by putting "valgrind" +on the RunTest command line. To run pcretest on just one or more specific test +files, give their numbers as arguments to RunTest, for example: + + RunTest 2 7 11 + +You can also specify ranges of tests such as 3-6 or 3- (meaning 3 to the +end), or a number preceded by ~ to exclude a test. For example: + + Runtest 3-15 ~10 + +This runs tests 3 to 15, excluding test 10, and just ~13 runs all the tests +except test 13. Whatever order the arguments are in, the tests are always run +in numerical order. + +You can also call RunTest with the single argument "list" to cause it to output +a list of tests. + +The first test file can be fed directly into the perltest.pl script to check +that Perl gives the same results. The only difference you should see is in the +first few lines, where the Perl version is given instead of the PCRE version. + +The second set of tests check pcre_fullinfo(), pcre_study(), +pcre_copy_substring(), pcre_get_substring(), pcre_get_substring_list(), error +detection, and run-time flags that are specific to PCRE, as well as the POSIX +wrapper API. It also uses the debugging flags to check some of the internals of +pcre_compile(). + +If you build PCRE with a locale setting that is not the standard C locale, the +character tables may be different (see next paragraph). In some cases, this may +cause failures in the second set of tests. For example, in a locale where the +isprint() function yields TRUE for characters in the range 128-255, the use of +[:isascii:] inside a character class defines a different set of characters, and +this shows up in this test as a difference in the compiled code, which is being +listed for checking. Where the comparison test output contains [\x00-\x7f] the +test will contain [\x00-\xff], and similarly in some other cases. This is not a +bug in PCRE. + +The third set of tests checks pcre_maketables(), the facility for building a +set of character tables for a specific locale and using them instead of the +default tables. The tests make use of the "fr_FR" (French) locale. Before +running the test, the script checks for the presence of this locale by running +the "locale" command. If that command fails, or if it doesn't include "fr_FR" +in the list of available locales, the third test cannot be run, and a comment +is output to say why. If running this test produces instances of the error + + ** Failed to set locale "fr_FR" + +in the comparison output, it means that locale is not available on your system, +despite being listed by "locale". This does not mean that PCRE is broken. + +[If you are trying to run this test on Windows, you may be able to get it to +work by changing "fr_FR" to "french" everywhere it occurs. Alternatively, use +RunTest.bat. The version of RunTest.bat included with PCRE 7.4 and above uses +Windows versions of test 2. More info on using RunTest.bat is included in the +document entitled NON-UNIX-USE.] + +The fourth and fifth tests check the UTF-8/16/32 support and error handling and +internal UTF features of PCRE that are not relevant to Perl, respectively. The +sixth and seventh tests do the same for Unicode character properties support. + +The eighth, ninth, and tenth tests check the pcre_dfa_exec() alternative +matching function, in non-UTF-8/16/32 mode, UTF-8/16/32 mode, and UTF-8/16/32 +mode with Unicode property support, respectively. + +The eleventh test checks some internal offsets and code size features; it is +run only when the default "link size" of 2 is set (in other cases the sizes +change) and when Unicode property support is enabled. + +The twelfth test is run only when JIT support is available, and the thirteenth +test is run only when JIT support is not available. They test some JIT-specific +features such as information output from pcretest about JIT compilation. + +The fourteenth, fifteenth, and sixteenth tests are run only in 8-bit mode, and +the seventeenth, eighteenth, and nineteenth tests are run only in 16/32-bit +mode. These are tests that generate different output in the two modes. They are +for general cases, UTF-8/16/32 support, and Unicode property support, +respectively. + +The twentieth test is run only in 16/32-bit mode. It tests some specific +16/32-bit features of the DFA matching engine. + +The twenty-first and twenty-second tests are run only in 16/32-bit mode, when +the link size is set to 2 for the 16-bit library. They test reloading +pre-compiled patterns. + +The twenty-third and twenty-fourth tests are run only in 16-bit mode. They are +for general cases, and UTF-16 support, respectively. + +The twenty-fifth and twenty-sixth tests are run only in 32-bit mode. They are +for general cases, and UTF-32 support, respectively. + + +Character tables +---------------- + +For speed, PCRE uses four tables for manipulating and identifying characters +whose code point values are less than 256. The final argument of the +pcre_compile() function is a pointer to a block of memory containing the +concatenated tables. A call to pcre_maketables() can be used to generate a set +of tables in the current locale. If the final argument for pcre_compile() is +passed as NULL, a set of default tables that is built into the binary is used. + +The source file called pcre_chartables.c contains the default set of tables. By +default, this is created as a copy of pcre_chartables.c.dist, which contains +tables for ASCII coding. However, if --enable-rebuild-chartables is specified +for ./configure, a different version of pcre_chartables.c is built by the +program dftables (compiled from dftables.c), which uses the ANSI C character +handling functions such as isalnum(), isalpha(), isupper(), islower(), etc. to +build the table sources. This means that the default C locale which is set for +your system will control the contents of these default tables. You can change +the default tables by editing pcre_chartables.c and then re-building PCRE. If +you do this, you should take care to ensure that the file does not get +automatically re-generated. The best way to do this is to move +pcre_chartables.c.dist out of the way and replace it with your customized +tables. + +When the dftables program is run as a result of --enable-rebuild-chartables, +it uses the default C locale that is set on your system. It does not pay +attention to the LC_xxx environment variables. In other words, it uses the +system's default locale rather than whatever the compiling user happens to have +set. If you really do want to build a source set of character tables in a +locale that is specified by the LC_xxx variables, you can run the dftables +program by hand with the -L option. For example: + + ./dftables -L pcre_chartables.c.special + +The first two 256-byte tables provide lower casing and case flipping functions, +respectively. The next table consists of three 32-byte bit maps which identify +digits, "word" characters, and white space, respectively. These are used when +building 32-byte bit maps that represent character classes for code points less +than 256. + +The final 256-byte table has bits indicating various character types, as +follows: + + 1 white space character + 2 letter + 4 decimal digit + 8 hexadecimal digit + 16 alphanumeric or '_' + 128 regular expression metacharacter or binary zero + +You should not alter the set of characters that contain the 128 bit, as that +will cause PCRE to malfunction. + + +File manifest +------------- + +The distribution should contain the files listed below. Where a file name is +given as pcre[16|32]_xxx it means that there are three files, one with the name +pcre_xxx, one with the name pcre16_xx, and a third with the name pcre32_xxx. + +(A) Source files of the PCRE library functions and their headers: + + dftables.c auxiliary program for building pcre_chartables.c + when --enable-rebuild-chartables is specified + + pcre_chartables.c.dist a default set of character tables that assume ASCII + coding; used, unless --enable-rebuild-chartables is + specified, by copying to pcre[16]_chartables.c + + pcreposix.c ) + pcre[16|32]_byte_order.c ) + pcre[16|32]_compile.c ) + pcre[16|32]_config.c ) + pcre[16|32]_dfa_exec.c ) + pcre[16|32]_exec.c ) + pcre[16|32]_fullinfo.c ) + pcre[16|32]_get.c ) sources for the functions in the library, + pcre[16|32]_globals.c ) and some internal functions that they use + pcre[16|32]_jit_compile.c ) + pcre[16|32]_maketables.c ) + pcre[16|32]_newline.c ) + pcre[16|32]_refcount.c ) + pcre[16|32]_string_utils.c ) + pcre[16|32]_study.c ) + pcre[16|32]_tables.c ) + pcre[16|32]_ucd.c ) + pcre[16|32]_version.c ) + pcre[16|32]_xclass.c ) + pcre_ord2utf8.c ) + pcre_valid_utf8.c ) + pcre16_ord2utf16.c ) + pcre16_utf16_utils.c ) + pcre16_valid_utf16.c ) + pcre32_utf32_utils.c ) + pcre32_valid_utf32.c ) + + pcre[16|32]_printint.c ) debugging function that is used by pcretest, + ) and can also be #included in pcre_compile() + + pcre.h.in template for pcre.h when built by "configure" + pcreposix.h header for the external POSIX wrapper API + pcre_internal.h header for internal use + sljit/* 16 files that make up the JIT compiler + ucp.h header for Unicode property handling + + config.h.in template for config.h, which is built by "configure" + + pcrecpp.h public header file for the C++ wrapper + pcrecpparg.h.in template for another C++ header file + pcre_scanner.h public header file for C++ scanner functions + pcrecpp.cc ) + pcre_scanner.cc ) source for the C++ wrapper library + + pcre_stringpiece.h.in template for pcre_stringpiece.h, the header for the + C++ stringpiece functions + pcre_stringpiece.cc source for the C++ stringpiece functions + +(B) Source files for programs that use PCRE: + + pcredemo.c simple demonstration of coding calls to PCRE + pcregrep.c source of a grep utility that uses PCRE + pcretest.c comprehensive test program + +(C) Auxiliary files: + + 132html script to turn "man" pages into HTML + AUTHORS information about the author of PCRE + ChangeLog log of changes to the code + CleanTxt script to clean nroff output for txt man pages + Detrail script to remove trailing spaces + HACKING some notes about the internals of PCRE + INSTALL generic installation instructions + LICENCE conditions for the use of PCRE + COPYING the same, using GNU's standard name + Makefile.in ) template for Unix Makefile, which is built by + ) "configure" + Makefile.am ) the automake input that was used to create + ) Makefile.in + NEWS important changes in this release + NON-UNIX-USE the previous name for NON-AUTOTOOLS-BUILD + NON-AUTOTOOLS-BUILD notes on building PCRE without using autotools + PrepareRelease script to make preparations for "make dist" + README this file + RunTest a Unix shell script for running tests + RunGrepTest a Unix shell script for pcregrep tests + aclocal.m4 m4 macros (generated by "aclocal") + config.guess ) files used by libtool, + config.sub ) used only when building a shared library + configure a configuring shell script (built by autoconf) + configure.ac ) the autoconf input that was used to build + ) "configure" and config.h + depcomp ) script to find program dependencies, generated by + ) automake + doc/*.3 man page sources for PCRE + doc/*.1 man page sources for pcregrep and pcretest + doc/index.html.src the base HTML page + doc/html/* HTML documentation + doc/pcre.txt plain text version of the man pages + doc/pcretest.txt plain text documentation of test program + doc/perltest.txt plain text documentation of Perl test program + install-sh a shell script for installing files + libpcre16.pc.in template for libpcre16.pc for pkg-config + libpcre32.pc.in template for libpcre32.pc for pkg-config + libpcre.pc.in template for libpcre.pc for pkg-config + libpcreposix.pc.in template for libpcreposix.pc for pkg-config + libpcrecpp.pc.in template for libpcrecpp.pc for pkg-config + ltmain.sh file used to build a libtool script + missing ) common stub for a few missing GNU programs while + ) installing, generated by automake + mkinstalldirs script for making install directories + perltest.pl Perl test program + pcre-config.in source of script which retains PCRE information + pcre_jit_test.c test program for the JIT compiler + pcrecpp_unittest.cc ) + pcre_scanner_unittest.cc ) test programs for the C++ wrapper + pcre_stringpiece_unittest.cc ) + testdata/testinput* test data for main library tests + testdata/testoutput* expected test results + testdata/grep* input and output for pcregrep tests + testdata/* other supporting test files + +(D) Auxiliary files for cmake support + + cmake/COPYING-CMAKE-SCRIPTS + cmake/FindPackageHandleStandardArgs.cmake + cmake/FindEditline.cmake + cmake/FindReadline.cmake + CMakeLists.txt + config-cmake.h.in + +(E) Auxiliary files for VPASCAL + + makevp.bat + makevp_c.txt + makevp_l.txt + pcregexp.pas + +(F) Auxiliary files for building PCRE "by hand" + + pcre.h.generic ) a version of the public PCRE header file + ) for use in non-"configure" environments + config.h.generic ) a version of config.h for use in non-"configure" + ) environments + +(F) Miscellaneous + + RunTest.bat a script for running tests under Windows + +Philip Hazel +Email local part: ph10 +Email domain: cam.ac.uk +Last updated: 17 January 2014 diff --git a/plugins/Pcre16/docs/doc/html/index.html b/plugins/Pcre16/docs/doc/html/index.html new file mode 100644 index 0000000000..352c55df2f --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/index.html @@ -0,0 +1,185 @@ +<html> +<!-- This is a manually maintained file that is the root of the HTML version of + the PCRE documentation. When the HTML documents are built from the man + page versions, the entire doc/html directory is emptied, this file is then + copied into doc/html/index.html, and the remaining files therein are + created by the 132html script. +--> +<head> +<title>PCRE specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>Perl-compatible Regular Expressions (PCRE)</h1> +<p> +The HTML documentation for PCRE consists of a number of pages that are listed +below in alphabetical order. If you are new to PCRE, please read the first one +first. +</p> + +<table> +<tr><td><a href="pcre.html">pcre</a></td> + <td> Introductory page</td></tr> + +<tr><td><a href="pcre-config.html">pcre-config</a></td> + <td> Information about the installation configuration</td></tr> + +<tr><td><a href="pcre16.html">pcre16</a></td> + <td> Discussion of the 16-bit PCRE library</td></tr> + +<tr><td><a href="pcre32.html">pcre32</a></td> + <td> Discussion of the 32-bit PCRE library</td></tr> + +<tr><td><a href="pcreapi.html">pcreapi</a></td> + <td> PCRE's native API</td></tr> + +<tr><td><a href="pcrebuild.html">pcrebuild</a></td> + <td> Building PCRE</td></tr> + +<tr><td><a href="pcrecallout.html">pcrecallout</a></td> + <td> The <i>callout</i> facility</td></tr> + +<tr><td><a href="pcrecompat.html">pcrecompat</a></td> + <td> Compability with Perl</td></tr> + +<tr><td><a href="pcrecpp.html">pcrecpp</a></td> + <td> The C++ wrapper for the PCRE library</td></tr> + +<tr><td><a href="pcredemo.html">pcredemo</a></td> + <td> A demonstration C program that uses the PCRE library</td></tr> + +<tr><td><a href="pcregrep.html">pcregrep</a></td> + <td> The <b>pcregrep</b> command</td></tr> + +<tr><td><a href="pcrejit.html">pcrejit</a></td> + <td> Discussion of the just-in-time optimization support</td></tr> + +<tr><td><a href="pcrelimits.html">pcrelimits</a></td> + <td> Details of size and other limits</td></tr> + +<tr><td><a href="pcrematching.html">pcrematching</a></td> + <td> Discussion of the two matching algorithms</td></tr> + +<tr><td><a href="pcrepartial.html">pcrepartial</a></td> + <td> Using PCRE for partial matching</td></tr> + +<tr><td><a href="pcrepattern.html">pcrepattern</a></td> + <td> Specification of the regular expressions supported by PCRE</td></tr> + +<tr><td><a href="pcreperform.html">pcreperform</a></td> + <td> Some comments on performance</td></tr> + +<tr><td><a href="pcreposix.html">pcreposix</a></td> + <td> The POSIX API to the PCRE 8-bit library</td></tr> + +<tr><td><a href="pcreprecompile.html">pcreprecompile</a></td> + <td> How to save and re-use compiled patterns</td></tr> + +<tr><td><a href="pcresample.html">pcresample</a></td> + <td> Discussion of the pcredemo program</td></tr> + +<tr><td><a href="pcrestack.html">pcrestack</a></td> + <td> Discussion of PCRE's stack usage</td></tr> + +<tr><td><a href="pcresyntax.html">pcresyntax</a></td> + <td> Syntax quick-reference summary</td></tr> + +<tr><td><a href="pcretest.html">pcretest</a></td> + <td> The <b>pcretest</b> command for testing PCRE</td></tr> + +<tr><td><a href="pcreunicode.html">pcreunicode</a></td> + <td> Discussion of Unicode and UTF-8/UTF-16/UTF-32 support</td></tr> +</table> + +<p> +There are also individual pages that summarize the interface for each function +in the library. There is a single page for each triple of 8-bit/16-bit/32-bit +functions. +</p> + +<table> + +<tr><td><a href="pcre_assign_jit_stack.html">pcre_assign_jit_stack</a></td> + <td> Assign stack for JIT matching</td></tr> + +<tr><td><a href="pcre_compile.html">pcre_compile</a></td> + <td> Compile a regular expression</td></tr> + +<tr><td><a href="pcre_compile2.html">pcre_compile2</a></td> + <td> Compile a regular expression (alternate interface)</td></tr> + +<tr><td><a href="pcre_config.html">pcre_config</a></td> + <td> Show build-time configuration options</td></tr> + +<tr><td><a href="pcre_copy_named_substring.html">pcre_copy_named_substring</a></td> + <td> Extract named substring into given buffer</td></tr> + +<tr><td><a href="pcre_copy_substring.html">pcre_copy_substring</a></td> + <td> Extract numbered substring into given buffer</td></tr> + +<tr><td><a href="pcre_dfa_exec.html">pcre_dfa_exec</a></td> + <td> Match a compiled pattern to a subject string + (DFA algorithm; <i>not</i> Perl compatible)</td></tr> + +<tr><td><a href="pcre_exec.html">pcre_exec</a></td> + <td> Match a compiled pattern to a subject string + (Perl compatible)</td></tr> + +<tr><td><a href="pcre_free_study.html">pcre_free_study</a></td> + <td> Free study data</td></tr> + +<tr><td><a href="pcre_free_substring.html">pcre_free_substring</a></td> + <td> Free extracted substring</td></tr> + +<tr><td><a href="pcre_free_substring_list.html">pcre_free_substring_list</a></td> + <td> Free list of extracted substrings</td></tr> + +<tr><td><a href="pcre_fullinfo.html">pcre_fullinfo</a></td> + <td> Extract information about a pattern</td></tr> + +<tr><td><a href="pcre_get_named_substring.html">pcre_get_named_substring</a></td> + <td> Extract named substring into new memory</td></tr> + +<tr><td><a href="pcre_get_stringnumber.html">pcre_get_stringnumber</a></td> + <td> Convert captured string name to number</td></tr> + +<tr><td><a href="pcre_get_stringtable_entries.html">pcre_get_stringtable_entries</a></td> + <td> Find table entries for given string name</td></tr> + +<tr><td><a href="pcre_get_substring.html">pcre_get_substring</a></td> + <td> Extract numbered substring into new memory</td></tr> + +<tr><td><a href="pcre_get_substring_list.html">pcre_get_substring_list</a></td> + <td> Extract all substrings into new memory</td></tr> + +<tr><td><a href="pcre_jit_exec.html">pcre_jit_exec</a></td> + <td> Fast path interface to JIT matching</td></tr> + +<tr><td><a href="pcre_jit_stack_alloc.html">pcre_jit_stack_alloc</a></td> + <td> Create a stack for JIT matching</td></tr> + +<tr><td><a href="pcre_jit_stack_free.html">pcre_jit_stack_free</a></td> + <td> Free a JIT matching stack</td></tr> + +<tr><td><a href="pcre_maketables.html">pcre_maketables</a></td> + <td> Build character tables in current locale</td></tr> + +<tr><td><a href="pcre_pattern_to_host_byte_order.html">pcre_pattern_to_host_byte_order</a></td> + <td> Convert compiled pattern to host byte order if necessary</td></tr> + +<tr><td><a href="pcre_refcount.html">pcre_refcount</a></td> + <td> Maintain reference count in compiled pattern</td></tr> + +<tr><td><a href="pcre_study.html">pcre_study</a></td> + <td> Study a compiled pattern</td></tr> + +<tr><td><a href="pcre_utf16_to_host_byte_order.html">pcre_utf16_to_host_byte_order</a></td> + <td> Convert UTF-16 string to host byte order if necessary</td></tr> + +<tr><td><a href="pcre_utf32_to_host_byte_order.html">pcre_utf32_to_host_byte_order</a></td> + <td> Convert UTF-32 string to host byte order if necessary</td></tr> + +<tr><td><a href="pcre_version.html">pcre_version</a></td> + <td> Return PCRE version and release date</td></tr> +</table> + +</html> diff --git a/plugins/Pcre16/docs/doc/html/pcre-config.html b/plugins/Pcre16/docs/doc/html/pcre-config.html new file mode 100644 index 0000000000..56a8060492 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre-config.html @@ -0,0 +1,109 @@ +<html> +<head> +<title>pcre-config specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre-config man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<ul> +<li><a name="TOC1" href="#SEC1">SYNOPSIS</a> +<li><a name="TOC2" href="#SEC2">DESCRIPTION</a> +<li><a name="TOC3" href="#SEC3">OPTIONS</a> +<li><a name="TOC4" href="#SEC4">SEE ALSO</a> +<li><a name="TOC5" href="#SEC5">AUTHOR</a> +<li><a name="TOC6" href="#SEC6">REVISION</a> +</ul> +<br><a name="SEC1" href="#TOC1">SYNOPSIS</a><br> +<P> +<b>pcre-config [--prefix] [--exec-prefix] [--version] [--libs]</b> +<b> [--libs16] [--libs32] [--libs-cpp] [--libs-posix]</b> +<b> [--cflags] [--cflags-posix]</b> +</P> +<br><a name="SEC2" href="#TOC1">DESCRIPTION</a><br> +<P> +<b>pcre-config</b> returns the configuration of the installed PCRE +libraries and the options required to compile a program to use them. Some of +the options apply only to the 8-bit, or 16-bit, or 32-bit libraries, +respectively, and are +not available if only one of those libraries has been built. If an unavailable +option is encountered, the "usage" information is output. +</P> +<br><a name="SEC3" href="#TOC1">OPTIONS</a><br> +<P> +<b>--prefix</b> +Writes the directory prefix used in the PCRE installation for architecture +independent files (<i>/usr</i> on many systems, <i>/usr/local</i> on some +systems) to the standard output. +</P> +<P> +<b>--exec-prefix</b> +Writes the directory prefix used in the PCRE installation for architecture +dependent files (normally the same as <b>--prefix</b>) to the standard output. +</P> +<P> +<b>--version</b> +Writes the version number of the installed PCRE libraries to the standard +output. +</P> +<P> +<b>--libs</b> +Writes to the standard output the command line options required to link +with the 8-bit PCRE library (<b>-lpcre</b> on many systems). +</P> +<P> +<b>--libs16</b> +Writes to the standard output the command line options required to link +with the 16-bit PCRE library (<b>-lpcre16</b> on many systems). +</P> +<P> +<b>--libs32</b> +Writes to the standard output the command line options required to link +with the 32-bit PCRE library (<b>-lpcre32</b> on many systems). +</P> +<P> +<b>--libs-cpp</b> +Writes to the standard output the command line options required to link with +PCRE's C++ wrapper library (<b>-lpcrecpp</b> <b>-lpcre</b> on many +systems). +</P> +<P> +<b>--libs-posix</b> +Writes to the standard output the command line options required to link with +PCRE's POSIX API wrapper library (<b>-lpcreposix</b> <b>-lpcre</b> on many +systems). +</P> +<P> +<b>--cflags</b> +Writes to the standard output the command line options required to compile +files that use PCRE (this may include some <b>-I</b> options, but is blank on +many systems). +</P> +<P> +<b>--cflags-posix</b> +Writes to the standard output the command line options required to compile +files that use PCRE's POSIX API wrapper library (this may include some <b>-I</b> +options, but is blank on many systems). +</P> +<br><a name="SEC4" href="#TOC1">SEE ALSO</a><br> +<P> +<b>pcre(3)</b> +</P> +<br><a name="SEC5" href="#TOC1">AUTHOR</a><br> +<P> +This manual page was originally written by Mark Baker for the Debian GNU/Linux +system. It has been subsequently revised as a generic PCRE man page. +</P> +<br><a name="SEC6" href="#TOC1">REVISION</a><br> +<P> +Last updated: 24 June 2012 +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre.html b/plugins/Pcre16/docs/doc/html/pcre.html new file mode 100644 index 0000000000..c2b29aa812 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre.html @@ -0,0 +1,213 @@ +<html> +<head> +<title>pcre specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<ul> +<li><a name="TOC1" href="#SEC1">INTRODUCTION</a> +<li><a name="TOC2" href="#SEC2">SECURITY CONSIDERATIONS</a> +<li><a name="TOC3" href="#SEC3">USER DOCUMENTATION</a> +<li><a name="TOC4" href="#SEC4">AUTHOR</a> +<li><a name="TOC5" href="#SEC5">REVISION</a> +</ul> +<br><a name="SEC1" href="#TOC1">INTRODUCTION</a><br> +<P> +The PCRE library is a set of functions that implement regular expression +pattern matching using the same syntax and semantics as Perl, with just a few +differences. Some features that appeared in Python and PCRE before they +appeared in Perl are also available using the Python syntax, there is some +support for one or two .NET and Oniguruma syntax items, and there is an option +for requesting some minor changes that give better JavaScript compatibility. +</P> +<P> +Starting with release 8.30, it is possible to compile two separate PCRE +libraries: the original, which supports 8-bit character strings (including +UTF-8 strings), and a second library that supports 16-bit character strings +(including UTF-16 strings). The build process allows either one or both to be +built. The majority of the work to make this possible was done by Zoltan +Herczeg. +</P> +<P> +Starting with release 8.32 it is possible to compile a third separate PCRE +library that supports 32-bit character strings (including UTF-32 strings). The +build process allows any combination of the 8-, 16- and 32-bit libraries. The +work to make this possible was done by Christian Persch. +</P> +<P> +The three libraries contain identical sets of functions, except that the names +in the 16-bit library start with <b>pcre16_</b> instead of <b>pcre_</b>, and the +names in the 32-bit library start with <b>pcre32_</b> instead of <b>pcre_</b>. To +avoid over-complication and reduce the documentation maintenance load, most of +the documentation describes the 8-bit library, with the differences for the +16-bit and 32-bit libraries described separately in the +<a href="pcre16.html"><b>pcre16</b></a> +and +<a href="pcre32.html"><b>pcre32</b></a> +pages. References to functions or structures of the form <i>pcre[16|32]_xxx</i> +should be read as meaning "<i>pcre_xxx</i> when using the 8-bit library, +<i>pcre16_xxx</i> when using the 16-bit library, or <i>pcre32_xxx</i> when using +the 32-bit library". +</P> +<P> +The current implementation of PCRE corresponds approximately with Perl 5.12, +including support for UTF-8/16/32 encoded strings and Unicode general category +properties. However, UTF-8/16/32 and Unicode support has to be explicitly +enabled; it is not the default. The Unicode tables correspond to Unicode +release 6.3.0. +</P> +<P> +In addition to the Perl-compatible matching function, PCRE contains an +alternative function that matches the same compiled patterns in a different +way. In certain circumstances, the alternative function has some advantages. +For a discussion of the two matching algorithms, see the +<a href="pcrematching.html"><b>pcrematching</b></a> +page. +</P> +<P> +PCRE is written in C and released as a C library. A number of people have +written wrappers and interfaces of various kinds. In particular, Google Inc. +have provided a comprehensive C++ wrapper for the 8-bit library. This is now +included as part of the PCRE distribution. The +<a href="pcrecpp.html"><b>pcrecpp</b></a> +page has details of this interface. Other people's contributions can be found +in the <i>Contrib</i> directory at the primary FTP site, which is: +<a href="ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre">ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre</a> +</P> +<P> +Details of exactly which Perl regular expression features are and are not +supported by PCRE are given in separate documents. See the +<a href="pcrepattern.html"><b>pcrepattern</b></a> +and +<a href="pcrecompat.html"><b>pcrecompat</b></a> +pages. There is a syntax summary in the +<a href="pcresyntax.html"><b>pcresyntax</b></a> +page. +</P> +<P> +Some features of PCRE can be included, excluded, or changed when the library is +built. The +<a href="pcre_config.html"><b>pcre_config()</b></a> +function makes it possible for a client to discover which features are +available. The features themselves are described in the +<a href="pcrebuild.html"><b>pcrebuild</b></a> +page. Documentation about building PCRE for various operating systems can be +found in the +<a href="README.txt"><b>README</b></a> +and +<a href="NON-AUTOTOOLS-BUILD.txt"><b>NON-AUTOTOOLS_BUILD</b></a> +files in the source distribution. +</P> +<P> +The libraries contains a number of undocumented internal functions and data +tables that are used by more than one of the exported external functions, but +which are not intended for use by external callers. Their names all begin with +"_pcre_" or "_pcre16_" or "_pcre32_", which hopefully will not provoke any name +clashes. In some environments, it is possible to control which external symbols +are exported when a shared library is built, and in these cases the +undocumented symbols are not exported. +</P> +<br><a name="SEC2" href="#TOC1">SECURITY CONSIDERATIONS</a><br> +<P> +If you are using PCRE in a non-UTF application that permits users to supply +arbitrary patterns for compilation, you should be aware of a feature that +allows users to turn on UTF support from within a pattern, provided that PCRE +was built with UTF support. For example, an 8-bit pattern that begins with +"(*UTF8)" or "(*UTF)" turns on UTF-8 mode, which interprets patterns and +subjects as strings of UTF-8 characters instead of individual 8-bit characters. +This causes both the pattern and any data against which it is matched to be +checked for UTF-8 validity. If the data string is very long, such a check might +use sufficiently many resources as to cause your application to lose +performance. +</P> +<P> +One way of guarding against this possibility is to use the +<b>pcre_fullinfo()</b> function to check the compiled pattern's options for UTF. +Alternatively, from release 8.33, you can set the PCRE_NEVER_UTF option at +compile time. This causes an compile time error if a pattern contains a +UTF-setting sequence. +</P> +<P> +If your application is one that supports UTF, be aware that validity checking +can take time. If the same data string is to be matched many times, you can use +the PCRE_NO_UTF[8|16|32]_CHECK option for the second and subsequent matches to +save redundant checks. +</P> +<P> +Another way that performance can be hit is by running a pattern that has a very +large search tree against a string that will never match. Nested unlimited +repeats in a pattern are a common example. PCRE provides some protection +against this: see the PCRE_EXTRA_MATCH_LIMIT feature in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page. +</P> +<br><a name="SEC3" href="#TOC1">USER DOCUMENTATION</a><br> +<P> +The user documentation for PCRE comprises a number of different sections. In +the "man" format, each of these is a separate "man page". In the HTML format, +each is a separate page, linked from the index page. In the plain text format, +the descriptions of the <b>pcregrep</b> and <b>pcretest</b> programs are in files +called <b>pcregrep.txt</b> and <b>pcretest.txt</b>, respectively. The remaining +sections, except for the <b>pcredemo</b> section (which is a program listing), +are concatenated in <b>pcre.txt</b>, for ease of searching. The sections are as +follows: +<pre> + pcre this document + pcre-config show PCRE installation configuration information + pcre16 details of the 16-bit library + pcre32 details of the 32-bit library + pcreapi details of PCRE's native C API + pcrebuild building PCRE + pcrecallout details of the callout feature + pcrecompat discussion of Perl compatibility + pcrecpp details of the C++ wrapper for the 8-bit library + pcredemo a demonstration C program that uses PCRE + pcregrep description of the <b>pcregrep</b> command (8-bit only) + pcrejit discussion of the just-in-time optimization support + pcrelimits details of size and other limits + pcrematching discussion of the two matching algorithms + pcrepartial details of the partial matching facility + pcrepattern syntax and semantics of supported regular expressions + pcreperform discussion of performance issues + pcreposix the POSIX-compatible C API for the 8-bit library + pcreprecompile details of saving and re-using precompiled patterns + pcresample discussion of the pcredemo program + pcrestack discussion of stack usage + pcresyntax quick syntax reference + pcretest description of the <b>pcretest</b> testing command + pcreunicode discussion of Unicode and UTF-8/16/32 support +</pre> +In the "man" and HTML formats, there is also a short page for each C library +function, listing its arguments and results. +</P> +<br><a name="SEC4" href="#TOC1">AUTHOR</a><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<P> +Putting an actual email address here seems to have been a spam magnet, so I've +taken it away. If you want to email me, use my two initials, followed by the +two digits 10, at the domain cam.ac.uk. +</P> +<br><a name="SEC5" href="#TOC1">REVISION</a><br> +<P> +Last updated: 08 January 2014 +<br> +Copyright © 1997-2014 University of Cambridge. +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre16.html b/plugins/Pcre16/docs/doc/html/pcre16.html new file mode 100644 index 0000000000..f00859f052 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre16.html @@ -0,0 +1,384 @@ +<html> +<head> +<title>pcre16 specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre16 man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<ul> +<li><a name="TOC1" href="#SEC1">PCRE 16-BIT API BASIC FUNCTIONS</a> +<li><a name="TOC2" href="#SEC2">PCRE 16-BIT API STRING EXTRACTION FUNCTIONS</a> +<li><a name="TOC3" href="#SEC3">PCRE 16-BIT API AUXILIARY FUNCTIONS</a> +<li><a name="TOC4" href="#SEC4">PCRE 16-BIT API INDIRECTED FUNCTIONS</a> +<li><a name="TOC5" href="#SEC5">PCRE 16-BIT API 16-BIT-ONLY FUNCTION</a> +<li><a name="TOC6" href="#SEC6">THE PCRE 16-BIT LIBRARY</a> +<li><a name="TOC7" href="#SEC7">THE HEADER FILE</a> +<li><a name="TOC8" href="#SEC8">THE LIBRARY NAME</a> +<li><a name="TOC9" href="#SEC9">STRING TYPES</a> +<li><a name="TOC10" href="#SEC10">STRUCTURE TYPES</a> +<li><a name="TOC11" href="#SEC11">16-BIT FUNCTIONS</a> +<li><a name="TOC12" href="#SEC12">SUBJECT STRING OFFSETS</a> +<li><a name="TOC13" href="#SEC13">NAMED SUBPATTERNS</a> +<li><a name="TOC14" href="#SEC14">OPTION NAMES</a> +<li><a name="TOC15" href="#SEC15">CHARACTER CODES</a> +<li><a name="TOC16" href="#SEC16">ERROR NAMES</a> +<li><a name="TOC17" href="#SEC17">ERROR TEXTS</a> +<li><a name="TOC18" href="#SEC18">CALLOUTS</a> +<li><a name="TOC19" href="#SEC19">TESTING</a> +<li><a name="TOC20" href="#SEC20">NOT SUPPORTED IN 16-BIT MODE</a> +<li><a name="TOC21" href="#SEC21">AUTHOR</a> +<li><a name="TOC22" href="#SEC22">REVISION</a> +</ul> +<P> +<b>#include <pcre.h></b> +</P> +<br><a name="SEC1" href="#TOC1">PCRE 16-BIT API BASIC FUNCTIONS</a><br> +<P> +<b>pcre16 *pcre16_compile(PCRE_SPTR16 <i>pattern</i>, int <i>options</i>,</b> +<b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b> +<b> const unsigned char *<i>tableptr</i>);</b> +<br> +<br> +<b>pcre16 *pcre16_compile2(PCRE_SPTR16 <i>pattern</i>, int <i>options</i>,</b> +<b> int *<i>errorcodeptr</i>,</b> +<b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b> +<b> const unsigned char *<i>tableptr</i>);</b> +<br> +<br> +<b>pcre16_extra *pcre16_study(const pcre16 *<i>code</i>, int <i>options</i>,</b> +<b> const char **<i>errptr</i>);</b> +<br> +<br> +<b>void pcre16_free_study(pcre16_extra *<i>extra</i>);</b> +<br> +<br> +<b>int pcre16_exec(const pcre16 *<i>code</i>, const pcre16_extra *<i>extra</i>,</b> +<b> PCRE_SPTR16 <i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b> +<br> +<br> +<b>int pcre16_dfa_exec(const pcre16 *<i>code</i>, const pcre16_extra *<i>extra</i>,</b> +<b> PCRE_SPTR16 <i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b> +<b> int *<i>workspace</i>, int <i>wscount</i>);</b> +</P> +<br><a name="SEC2" href="#TOC1">PCRE 16-BIT API STRING EXTRACTION FUNCTIONS</a><br> +<P> +<b>int pcre16_copy_named_substring(const pcre16 *<i>code</i>,</b> +<b> PCRE_SPTR16 <i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, PCRE_SPTR16 <i>stringname</i>,</b> +<b> PCRE_UCHAR16 *<i>buffer</i>, int <i>buffersize</i>);</b> +<br> +<br> +<b>int pcre16_copy_substring(PCRE_SPTR16 <i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, int <i>stringnumber</i>, PCRE_UCHAR16 *<i>buffer</i>,</b> +<b> int <i>buffersize</i>);</b> +<br> +<br> +<b>int pcre16_get_named_substring(const pcre16 *<i>code</i>,</b> +<b> PCRE_SPTR16 <i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, PCRE_SPTR16 <i>stringname</i>,</b> +<b> PCRE_SPTR16 *<i>stringptr</i>);</b> +<br> +<br> +<b>int pcre16_get_stringnumber(const pcre16 *<i>code</i>,</b> +<b>" PCRE_SPTR16 <i>name</i>);</b> +<br> +<br> +<b>int pcre16_get_stringtable_entries(const pcre16 *<i>code</i>,</b> +<b> PCRE_SPTR16 <i>name</i>, PCRE_UCHAR16 **<i>first</i>, PCRE_UCHAR16 **<i>last</i>);</b> +<br> +<br> +<b>int pcre16_get_substring(PCRE_SPTR16 <i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, int <i>stringnumber</i>,</b> +<b> PCRE_SPTR16 *<i>stringptr</i>);</b> +<br> +<br> +<b>int pcre16_get_substring_list(PCRE_SPTR16 <i>subject</i>,</b> +<b> int *<i>ovector</i>, int <i>stringcount</i>, PCRE_SPTR16 **<i>listptr</i>);</b> +<br> +<br> +<b>void pcre16_free_substring(PCRE_SPTR16 <i>stringptr</i>);</b> +<br> +<br> +<b>void pcre16_free_substring_list(PCRE_SPTR16 *<i>stringptr</i>);</b> +</P> +<br><a name="SEC3" href="#TOC1">PCRE 16-BIT API AUXILIARY FUNCTIONS</a><br> +<P> +<b>pcre16_jit_stack *pcre16_jit_stack_alloc(int <i>startsize</i>, int <i>maxsize</i>);</b> +<br> +<br> +<b>void pcre16_jit_stack_free(pcre16_jit_stack *<i>stack</i>);</b> +<br> +<br> +<b>void pcre16_assign_jit_stack(pcre16_extra *<i>extra</i>,</b> +<b> pcre16_jit_callback <i>callback</i>, void *<i>data</i>);</b> +<br> +<br> +<b>const unsigned char *pcre16_maketables(void);</b> +<br> +<br> +<b>int pcre16_fullinfo(const pcre16 *<i>code</i>, const pcre16_extra *<i>extra</i>,</b> +<b> int <i>what</i>, void *<i>where</i>);</b> +<br> +<br> +<b>int pcre16_refcount(pcre16 *<i>code</i>, int <i>adjust</i>);</b> +<br> +<br> +<b>int pcre16_config(int <i>what</i>, void *<i>where</i>);</b> +<br> +<br> +<b>const char *pcre16_version(void);</b> +<br> +<br> +<b>int pcre16_pattern_to_host_byte_order(pcre16 *<i>code</i>,</b> +<b> pcre16_extra *<i>extra</i>, const unsigned char *<i>tables</i>);</b> +</P> +<br><a name="SEC4" href="#TOC1">PCRE 16-BIT API INDIRECTED FUNCTIONS</a><br> +<P> +<b>void *(*pcre16_malloc)(size_t);</b> +<br> +<br> +<b>void (*pcre16_free)(void *);</b> +<br> +<br> +<b>void *(*pcre16_stack_malloc)(size_t);</b> +<br> +<br> +<b>void (*pcre16_stack_free)(void *);</b> +<br> +<br> +<b>int (*pcre16_callout)(pcre16_callout_block *);</b> +</P> +<br><a name="SEC5" href="#TOC1">PCRE 16-BIT API 16-BIT-ONLY FUNCTION</a><br> +<P> +<b>int pcre16_utf16_to_host_byte_order(PCRE_UCHAR16 *<i>output</i>,</b> +<b> PCRE_SPTR16 <i>input</i>, int <i>length</i>, int *<i>byte_order</i>,</b> +<b> int <i>keep_boms</i>);</b> +</P> +<br><a name="SEC6" href="#TOC1">THE PCRE 16-BIT LIBRARY</a><br> +<P> +Starting with release 8.30, it is possible to compile a PCRE library that +supports 16-bit character strings, including UTF-16 strings, as well as or +instead of the original 8-bit library. The majority of the work to make this +possible was done by Zoltan Herczeg. The two libraries contain identical sets +of functions, used in exactly the same way. Only the names of the functions and +the data types of their arguments and results are different. To avoid +over-complication and reduce the documentation maintenance load, most of the +PCRE documentation describes the 8-bit library, with only occasional references +to the 16-bit library. This page describes what is different when you use the +16-bit library. +</P> +<P> +WARNING: A single application can be linked with both libraries, but you must +take care when processing any particular pattern to use functions from just one +library. For example, if you want to study a pattern that was compiled with +<b>pcre16_compile()</b>, you must do so with <b>pcre16_study()</b>, not +<b>pcre_study()</b>, and you must free the study data with +<b>pcre16_free_study()</b>. +</P> +<br><a name="SEC7" href="#TOC1">THE HEADER FILE</a><br> +<P> +There is only one header file, <b>pcre.h</b>. It contains prototypes for all the +functions in all libraries, as well as definitions of flags, structures, error +codes, etc. +</P> +<br><a name="SEC8" href="#TOC1">THE LIBRARY NAME</a><br> +<P> +In Unix-like systems, the 16-bit library is called <b>libpcre16</b>, and can +normally be accesss by adding <b>-lpcre16</b> to the command for linking an +application that uses PCRE. +</P> +<br><a name="SEC9" href="#TOC1">STRING TYPES</a><br> +<P> +In the 8-bit library, strings are passed to PCRE library functions as vectors +of bytes with the C type "char *". In the 16-bit library, strings are passed as +vectors of unsigned 16-bit quantities. The macro PCRE_UCHAR16 specifies an +appropriate data type, and PCRE_SPTR16 is defined as "const PCRE_UCHAR16 *". In +very many environments, "short int" is a 16-bit data type. When PCRE is built, +it defines PCRE_UCHAR16 as "unsigned short int", but checks that it really is a +16-bit data type. If it is not, the build fails with an error message telling +the maintainer to modify the definition appropriately. +</P> +<br><a name="SEC10" href="#TOC1">STRUCTURE TYPES</a><br> +<P> +The types of the opaque structures that are used for compiled 16-bit patterns +and JIT stacks are <b>pcre16</b> and <b>pcre16_jit_stack</b> respectively. The +type of the user-accessible structure that is returned by <b>pcre16_study()</b> +is <b>pcre16_extra</b>, and the type of the structure that is used for passing +data to a callout function is <b>pcre16_callout_block</b>. These structures +contain the same fields, with the same names, as their 8-bit counterparts. The +only difference is that pointers to character strings are 16-bit instead of +8-bit types. +</P> +<br><a name="SEC11" href="#TOC1">16-BIT FUNCTIONS</a><br> +<P> +For every function in the 8-bit library there is a corresponding function in +the 16-bit library with a name that starts with <b>pcre16_</b> instead of +<b>pcre_</b>. The prototypes are listed above. In addition, there is one extra +function, <b>pcre16_utf16_to_host_byte_order()</b>. This is a utility function +that converts a UTF-16 character string to host byte order if necessary. The +other 16-bit functions expect the strings they are passed to be in host byte +order. +</P> +<P> +The <i>input</i> and <i>output</i> arguments of +<b>pcre16_utf16_to_host_byte_order()</b> may point to the same address, that is, +conversion in place is supported. The output buffer must be at least as long as +the input. +</P> +<P> +The <i>length</i> argument specifies the number of 16-bit data units in the +input string; a negative value specifies a zero-terminated string. +</P> +<P> +If <i>byte_order</i> is NULL, it is assumed that the string starts off in host +byte order. This may be changed by byte-order marks (BOMs) anywhere in the +string (commonly as the first character). +</P> +<P> +If <i>byte_order</i> is not NULL, a non-zero value of the integer to which it +points means that the input starts off in host byte order, otherwise the +opposite order is assumed. Again, BOMs in the string can change this. The final +byte order is passed back at the end of processing. +</P> +<P> +If <i>keep_boms</i> is not zero, byte-order mark characters (0xfeff) are copied +into the output string. Otherwise they are discarded. +</P> +<P> +The result of the function is the number of 16-bit units placed into the output +buffer, including the zero terminator if the string was zero-terminated. +</P> +<br><a name="SEC12" href="#TOC1">SUBJECT STRING OFFSETS</a><br> +<P> +The lengths and starting offsets of subject strings must be specified in 16-bit +data units, and the offsets within subject strings that are returned by the +matching functions are in also 16-bit units rather than bytes. +</P> +<br><a name="SEC13" href="#TOC1">NAMED SUBPATTERNS</a><br> +<P> +The name-to-number translation table that is maintained for named subpatterns +uses 16-bit characters. The <b>pcre16_get_stringtable_entries()</b> function +returns the length of each entry in the table as the number of 16-bit data +units. +</P> +<br><a name="SEC14" href="#TOC1">OPTION NAMES</a><br> +<P> +There are two new general option names, PCRE_UTF16 and PCRE_NO_UTF16_CHECK, +which correspond to PCRE_UTF8 and PCRE_NO_UTF8_CHECK in the 8-bit library. In +fact, these new options define the same bits in the options word. There is a +discussion about the +<a href="pcreunicode.html#utf16strings">validity of UTF-16 strings</a> +in the +<a href="pcreunicode.html"><b>pcreunicode</b></a> +page. +</P> +<P> +For the <b>pcre16_config()</b> function there is an option PCRE_CONFIG_UTF16 +that returns 1 if UTF-16 support is configured, otherwise 0. If this option is +given to <b>pcre_config()</b> or <b>pcre32_config()</b>, or if the +PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF32 option is given to <b>pcre16_config()</b>, +the result is the PCRE_ERROR_BADOPTION error. +</P> +<br><a name="SEC15" href="#TOC1">CHARACTER CODES</a><br> +<P> +In 16-bit mode, when PCRE_UTF16 is not set, character values are treated in the +same way as in 8-bit, non UTF-8 mode, except, of course, that they can range +from 0 to 0xffff instead of 0 to 0xff. Character types for characters less than +0xff can therefore be influenced by the locale in the same way as before. +Characters greater than 0xff have only one case, and no "type" (such as letter +or digit). +</P> +<P> +In UTF-16 mode, the character code is Unicode, in the range 0 to 0x10ffff, with +the exception of values in the range 0xd800 to 0xdfff because those are +"surrogate" values that are used in pairs to encode values greater than 0xffff. +</P> +<P> +A UTF-16 string can indicate its endianness by special code knows as a +byte-order mark (BOM). The PCRE functions do not handle this, expecting strings +to be in host byte order. A utility function called +<b>pcre16_utf16_to_host_byte_order()</b> is provided to help with this (see +above). +</P> +<br><a name="SEC16" href="#TOC1">ERROR NAMES</a><br> +<P> +The errors PCRE_ERROR_BADUTF16_OFFSET and PCRE_ERROR_SHORTUTF16 correspond to +their 8-bit counterparts. The error PCRE_ERROR_BADMODE is given when a compiled +pattern is passed to a function that processes patterns in the other +mode, for example, if a pattern compiled with <b>pcre_compile()</b> is passed to +<b>pcre16_exec()</b>. +</P> +<P> +There are new error codes whose names begin with PCRE_UTF16_ERR for invalid +UTF-16 strings, corresponding to the PCRE_UTF8_ERR codes for UTF-8 strings that +are described in the section entitled +<a href="pcreapi.html#badutf8reasons">"Reason codes for invalid UTF-8 strings"</a> +in the main +<a href="pcreapi.html"><b>pcreapi</b></a> +page. The UTF-16 errors are: +<pre> + PCRE_UTF16_ERR1 Missing low surrogate at end of string + PCRE_UTF16_ERR2 Invalid low surrogate follows high surrogate + PCRE_UTF16_ERR3 Isolated low surrogate + PCRE_UTF16_ERR4 Non-character +</PRE> +</P> +<br><a name="SEC17" href="#TOC1">ERROR TEXTS</a><br> +<P> +If there is an error while compiling a pattern, the error text that is passed +back by <b>pcre16_compile()</b> or <b>pcre16_compile2()</b> is still an 8-bit +character string, zero-terminated. +</P> +<br><a name="SEC18" href="#TOC1">CALLOUTS</a><br> +<P> +The <i>subject</i> and <i>mark</i> fields in the callout block that is passed to +a callout function point to 16-bit vectors. +</P> +<br><a name="SEC19" href="#TOC1">TESTING</a><br> +<P> +The <b>pcretest</b> program continues to operate with 8-bit input and output +files, but it can be used for testing the 16-bit library. If it is run with the +command line option <b>-16</b>, patterns and subject strings are converted from +8-bit to 16-bit before being passed to PCRE, and the 16-bit library functions +are used instead of the 8-bit ones. Returned 16-bit strings are converted to +8-bit for output. If both the 8-bit and the 32-bit libraries were not compiled, +<b>pcretest</b> defaults to 16-bit and the <b>-16</b> option is ignored. +</P> +<P> +When PCRE is being built, the <b>RunTest</b> script that is called by "make +check" uses the <b>pcretest</b> <b>-C</b> option to discover which of the 8-bit, +16-bit and 32-bit libraries has been built, and runs the tests appropriately. +</P> +<br><a name="SEC20" href="#TOC1">NOT SUPPORTED IN 16-BIT MODE</a><br> +<P> +Not all the features of the 8-bit library are available with the 16-bit +library. The C++ and POSIX wrapper functions support only the 8-bit library, +and the <b>pcregrep</b> program is at present 8-bit only. +</P> +<br><a name="SEC21" href="#TOC1">AUTHOR</a><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><a name="SEC22" href="#TOC1">REVISION</a><br> +<P> +Last updated: 12 May 2013 +<br> +Copyright © 1997-2013 University of Cambridge. +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre32.html b/plugins/Pcre16/docs/doc/html/pcre32.html new file mode 100644 index 0000000000..f96876e750 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre32.html @@ -0,0 +1,382 @@ +<html> +<head> +<title>pcre32 specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre32 man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<ul> +<li><a name="TOC1" href="#SEC1">PCRE 32-BIT API BASIC FUNCTIONS</a> +<li><a name="TOC2" href="#SEC2">PCRE 32-BIT API STRING EXTRACTION FUNCTIONS</a> +<li><a name="TOC3" href="#SEC3">PCRE 32-BIT API AUXILIARY FUNCTIONS</a> +<li><a name="TOC4" href="#SEC4">PCRE 32-BIT API INDIRECTED FUNCTIONS</a> +<li><a name="TOC5" href="#SEC5">PCRE 32-BIT API 32-BIT-ONLY FUNCTION</a> +<li><a name="TOC6" href="#SEC6">THE PCRE 32-BIT LIBRARY</a> +<li><a name="TOC7" href="#SEC7">THE HEADER FILE</a> +<li><a name="TOC8" href="#SEC8">THE LIBRARY NAME</a> +<li><a name="TOC9" href="#SEC9">STRING TYPES</a> +<li><a name="TOC10" href="#SEC10">STRUCTURE TYPES</a> +<li><a name="TOC11" href="#SEC11">32-BIT FUNCTIONS</a> +<li><a name="TOC12" href="#SEC12">SUBJECT STRING OFFSETS</a> +<li><a name="TOC13" href="#SEC13">NAMED SUBPATTERNS</a> +<li><a name="TOC14" href="#SEC14">OPTION NAMES</a> +<li><a name="TOC15" href="#SEC15">CHARACTER CODES</a> +<li><a name="TOC16" href="#SEC16">ERROR NAMES</a> +<li><a name="TOC17" href="#SEC17">ERROR TEXTS</a> +<li><a name="TOC18" href="#SEC18">CALLOUTS</a> +<li><a name="TOC19" href="#SEC19">TESTING</a> +<li><a name="TOC20" href="#SEC20">NOT SUPPORTED IN 32-BIT MODE</a> +<li><a name="TOC21" href="#SEC21">AUTHOR</a> +<li><a name="TOC22" href="#SEC22">REVISION</a> +</ul> +<P> +<b>#include <pcre.h></b> +</P> +<br><a name="SEC1" href="#TOC1">PCRE 32-BIT API BASIC FUNCTIONS</a><br> +<P> +<b>pcre32 *pcre32_compile(PCRE_SPTR32 <i>pattern</i>, int <i>options</i>,</b> +<b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b> +<b> const unsigned char *<i>tableptr</i>);</b> +<br> +<br> +<b>pcre32 *pcre32_compile2(PCRE_SPTR32 <i>pattern</i>, int <i>options</i>,</b> +<b> int *<i>errorcodeptr</i>,</b> +<b> const unsigned char *<i>tableptr</i>);</b> +<br> +<br> +<b>pcre32_extra *pcre32_study(const pcre32 *<i>code</i>, int <i>options</i>,</b> +<b> const char **<i>errptr</i>);</b> +<br> +<br> +<b>void pcre32_free_study(pcre32_extra *<i>extra</i>);</b> +<br> +<br> +<b>int pcre32_exec(const pcre32 *<i>code</i>, const pcre32_extra *<i>extra</i>,</b> +<b> PCRE_SPTR32 <i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b> +<br> +<br> +<b>int pcre32_dfa_exec(const pcre32 *<i>code</i>, const pcre32_extra *<i>extra</i>,</b> +<b> PCRE_SPTR32 <i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b> +<b> int *<i>workspace</i>, int <i>wscount</i>);</b> +</P> +<br><a name="SEC2" href="#TOC1">PCRE 32-BIT API STRING EXTRACTION FUNCTIONS</a><br> +<P> +<b>int pcre32_copy_named_substring(const pcre32 *<i>code</i>,</b> +<b> PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, PCRE_SPTR32 <i>stringname</i>,</b> +<b> PCRE_UCHAR32 *<i>buffer</i>, int <i>buffersize</i>);</b> +<br> +<br> +<b>int pcre32_copy_substring(PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, int <i>stringnumber</i>, PCRE_UCHAR32 *<i>buffer</i>,</b> +<b> int <i>buffersize</i>);</b> +<br> +<br> +<b>int pcre32_get_named_substring(const pcre32 *<i>code</i>,</b> +<b> PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, PCRE_SPTR32 <i>stringname</i>,</b> +<b> PCRE_SPTR32 *<i>stringptr</i>);</b> +<br> +<br> +<b>int pcre32_get_stringnumber(const pcre32 *<i>code</i>,</b> +<b> PCRE_SPTR32 <i>name</i>);</b> +<br> +<br> +<b>int pcre32_get_stringtable_entries(const pcre32 *<i>code</i>,</b> +<b> PCRE_SPTR32 <i>name</i>, PCRE_UCHAR32 **<i>first</i>, PCRE_UCHAR32 **<i>last</i>);</b> +<br> +<br> +<b>int pcre32_get_substring(PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, int <i>stringnumber</i>,</b> +<b> PCRE_SPTR32 *<i>stringptr</i>);</b> +<br> +<br> +<b>int pcre32_get_substring_list(PCRE_SPTR32 <i>subject</i>,</b> +<b> int *<i>ovector</i>, int <i>stringcount</i>, PCRE_SPTR32 **<i>listptr</i>);</b> +<br> +<br> +<b>void pcre32_free_substring(PCRE_SPTR32 <i>stringptr</i>);</b> +<br> +<br> +<b>void pcre32_free_substring_list(PCRE_SPTR32 *<i>stringptr</i>);</b> +</P> +<br><a name="SEC3" href="#TOC1">PCRE 32-BIT API AUXILIARY FUNCTIONS</a><br> +<P> +<b>pcre32_jit_stack *pcre32_jit_stack_alloc(int <i>startsize</i>, int <i>maxsize</i>);</b> +<br> +<br> +<b>void pcre32_jit_stack_free(pcre32_jit_stack *<i>stack</i>);</b> +<br> +<br> +<b>void pcre32_assign_jit_stack(pcre32_extra *<i>extra</i>,</b> +<b> pcre32_jit_callback <i>callback</i>, void *<i>data</i>);</b> +<br> +<br> +<b>const unsigned char *pcre32_maketables(void);</b> +<br> +<br> +<b>int pcre32_fullinfo(const pcre32 *<i>code</i>, const pcre32_extra *<i>extra</i>,</b> +<b> int <i>what</i>, void *<i>where</i>);</b> +<br> +<br> +<b>int pcre32_refcount(pcre32 *<i>code</i>, int <i>adjust</i>);</b> +<br> +<br> +<b>int pcre32_config(int <i>what</i>, void *<i>where</i>);</b> +<br> +<br> +<b>const char *pcre32_version(void);</b> +<br> +<br> +<b>int pcre32_pattern_to_host_byte_order(pcre32 *<i>code</i>,</b> +<b> pcre32_extra *<i>extra</i>, const unsigned char *<i>tables</i>);</b> +</P> +<br><a name="SEC4" href="#TOC1">PCRE 32-BIT API INDIRECTED FUNCTIONS</a><br> +<P> +<b>void *(*pcre32_malloc)(size_t);</b> +<br> +<br> +<b>void (*pcre32_free)(void *);</b> +<br> +<br> +<b>void *(*pcre32_stack_malloc)(size_t);</b> +<br> +<br> +<b>void (*pcre32_stack_free)(void *);</b> +<br> +<br> +<b>int (*pcre32_callout)(pcre32_callout_block *);</b> +</P> +<br><a name="SEC5" href="#TOC1">PCRE 32-BIT API 32-BIT-ONLY FUNCTION</a><br> +<P> +<b>int pcre32_utf32_to_host_byte_order(PCRE_UCHAR32 *<i>output</i>,</b> +<b> PCRE_SPTR32 <i>input</i>, int <i>length</i>, int *<i>byte_order</i>,</b> +<b> int <i>keep_boms</i>);</b> +</P> +<br><a name="SEC6" href="#TOC1">THE PCRE 32-BIT LIBRARY</a><br> +<P> +Starting with release 8.32, it is possible to compile a PCRE library that +supports 32-bit character strings, including UTF-32 strings, as well as or +instead of the original 8-bit library. This work was done by Christian Persch, +based on the work done by Zoltan Herczeg for the 16-bit library. All three +libraries contain identical sets of functions, used in exactly the same way. +Only the names of the functions and the data types of their arguments and +results are different. To avoid over-complication and reduce the documentation +maintenance load, most of the PCRE documentation describes the 8-bit library, +with only occasional references to the 16-bit and 32-bit libraries. This page +describes what is different when you use the 32-bit library. +</P> +<P> +WARNING: A single application can be linked with all or any of the three +libraries, but you must take care when processing any particular pattern +to use functions from just one library. For example, if you want to study +a pattern that was compiled with <b>pcre32_compile()</b>, you must do so +with <b>pcre32_study()</b>, not <b>pcre_study()</b>, and you must free the +study data with <b>pcre32_free_study()</b>. +</P> +<br><a name="SEC7" href="#TOC1">THE HEADER FILE</a><br> +<P> +There is only one header file, <b>pcre.h</b>. It contains prototypes for all the +functions in all libraries, as well as definitions of flags, structures, error +codes, etc. +</P> +<br><a name="SEC8" href="#TOC1">THE LIBRARY NAME</a><br> +<P> +In Unix-like systems, the 32-bit library is called <b>libpcre32</b>, and can +normally be accesss by adding <b>-lpcre32</b> to the command for linking an +application that uses PCRE. +</P> +<br><a name="SEC9" href="#TOC1">STRING TYPES</a><br> +<P> +In the 8-bit library, strings are passed to PCRE library functions as vectors +of bytes with the C type "char *". In the 32-bit library, strings are passed as +vectors of unsigned 32-bit quantities. The macro PCRE_UCHAR32 specifies an +appropriate data type, and PCRE_SPTR32 is defined as "const PCRE_UCHAR32 *". In +very many environments, "unsigned int" is a 32-bit data type. When PCRE is +built, it defines PCRE_UCHAR32 as "unsigned int", but checks that it really is +a 32-bit data type. If it is not, the build fails with an error message telling +the maintainer to modify the definition appropriately. +</P> +<br><a name="SEC10" href="#TOC1">STRUCTURE TYPES</a><br> +<P> +The types of the opaque structures that are used for compiled 32-bit patterns +and JIT stacks are <b>pcre32</b> and <b>pcre32_jit_stack</b> respectively. The +type of the user-accessible structure that is returned by <b>pcre32_study()</b> +is <b>pcre32_extra</b>, and the type of the structure that is used for passing +data to a callout function is <b>pcre32_callout_block</b>. These structures +contain the same fields, with the same names, as their 8-bit counterparts. The +only difference is that pointers to character strings are 32-bit instead of +8-bit types. +</P> +<br><a name="SEC11" href="#TOC1">32-BIT FUNCTIONS</a><br> +<P> +For every function in the 8-bit library there is a corresponding function in +the 32-bit library with a name that starts with <b>pcre32_</b> instead of +<b>pcre_</b>. The prototypes are listed above. In addition, there is one extra +function, <b>pcre32_utf32_to_host_byte_order()</b>. This is a utility function +that converts a UTF-32 character string to host byte order if necessary. The +other 32-bit functions expect the strings they are passed to be in host byte +order. +</P> +<P> +The <i>input</i> and <i>output</i> arguments of +<b>pcre32_utf32_to_host_byte_order()</b> may point to the same address, that is, +conversion in place is supported. The output buffer must be at least as long as +the input. +</P> +<P> +The <i>length</i> argument specifies the number of 32-bit data units in the +input string; a negative value specifies a zero-terminated string. +</P> +<P> +If <i>byte_order</i> is NULL, it is assumed that the string starts off in host +byte order. This may be changed by byte-order marks (BOMs) anywhere in the +string (commonly as the first character). +</P> +<P> +If <i>byte_order</i> is not NULL, a non-zero value of the integer to which it +points means that the input starts off in host byte order, otherwise the +opposite order is assumed. Again, BOMs in the string can change this. The final +byte order is passed back at the end of processing. +</P> +<P> +If <i>keep_boms</i> is not zero, byte-order mark characters (0xfeff) are copied +into the output string. Otherwise they are discarded. +</P> +<P> +The result of the function is the number of 32-bit units placed into the output +buffer, including the zero terminator if the string was zero-terminated. +</P> +<br><a name="SEC12" href="#TOC1">SUBJECT STRING OFFSETS</a><br> +<P> +The lengths and starting offsets of subject strings must be specified in 32-bit +data units, and the offsets within subject strings that are returned by the +matching functions are in also 32-bit units rather than bytes. +</P> +<br><a name="SEC13" href="#TOC1">NAMED SUBPATTERNS</a><br> +<P> +The name-to-number translation table that is maintained for named subpatterns +uses 32-bit characters. The <b>pcre32_get_stringtable_entries()</b> function +returns the length of each entry in the table as the number of 32-bit data +units. +</P> +<br><a name="SEC14" href="#TOC1">OPTION NAMES</a><br> +<P> +There are two new general option names, PCRE_UTF32 and PCRE_NO_UTF32_CHECK, +which correspond to PCRE_UTF8 and PCRE_NO_UTF8_CHECK in the 8-bit library. In +fact, these new options define the same bits in the options word. There is a +discussion about the +<a href="pcreunicode.html#utf32strings">validity of UTF-32 strings</a> +in the +<a href="pcreunicode.html"><b>pcreunicode</b></a> +page. +</P> +<P> +For the <b>pcre32_config()</b> function there is an option PCRE_CONFIG_UTF32 +that returns 1 if UTF-32 support is configured, otherwise 0. If this option is +given to <b>pcre_config()</b> or <b>pcre16_config()</b>, or if the +PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF16 option is given to <b>pcre32_config()</b>, +the result is the PCRE_ERROR_BADOPTION error. +</P> +<br><a name="SEC15" href="#TOC1">CHARACTER CODES</a><br> +<P> +In 32-bit mode, when PCRE_UTF32 is not set, character values are treated in the +same way as in 8-bit, non UTF-8 mode, except, of course, that they can range +from 0 to 0x7fffffff instead of 0 to 0xff. Character types for characters less +than 0xff can therefore be influenced by the locale in the same way as before. +Characters greater than 0xff have only one case, and no "type" (such as letter +or digit). +</P> +<P> +In UTF-32 mode, the character code is Unicode, in the range 0 to 0x10ffff, with +the exception of values in the range 0xd800 to 0xdfff because those are +"surrogate" values that are ill-formed in UTF-32. +</P> +<P> +A UTF-32 string can indicate its endianness by special code knows as a +byte-order mark (BOM). The PCRE functions do not handle this, expecting strings +to be in host byte order. A utility function called +<b>pcre32_utf32_to_host_byte_order()</b> is provided to help with this (see +above). +</P> +<br><a name="SEC16" href="#TOC1">ERROR NAMES</a><br> +<P> +The error PCRE_ERROR_BADUTF32 corresponds to its 8-bit counterpart. +The error PCRE_ERROR_BADMODE is given when a compiled +pattern is passed to a function that processes patterns in the other +mode, for example, if a pattern compiled with <b>pcre_compile()</b> is passed to +<b>pcre32_exec()</b>. +</P> +<P> +There are new error codes whose names begin with PCRE_UTF32_ERR for invalid +UTF-32 strings, corresponding to the PCRE_UTF8_ERR codes for UTF-8 strings that +are described in the section entitled +<a href="pcreapi.html#badutf8reasons">"Reason codes for invalid UTF-8 strings"</a> +in the main +<a href="pcreapi.html"><b>pcreapi</b></a> +page. The UTF-32 errors are: +<pre> + PCRE_UTF32_ERR1 Surrogate character (range from 0xd800 to 0xdfff) + PCRE_UTF32_ERR2 Non-character + PCRE_UTF32_ERR3 Character > 0x10ffff +</PRE> +</P> +<br><a name="SEC17" href="#TOC1">ERROR TEXTS</a><br> +<P> +If there is an error while compiling a pattern, the error text that is passed +back by <b>pcre32_compile()</b> or <b>pcre32_compile2()</b> is still an 8-bit +character string, zero-terminated. +</P> +<br><a name="SEC18" href="#TOC1">CALLOUTS</a><br> +<P> +The <i>subject</i> and <i>mark</i> fields in the callout block that is passed to +a callout function point to 32-bit vectors. +</P> +<br><a name="SEC19" href="#TOC1">TESTING</a><br> +<P> +The <b>pcretest</b> program continues to operate with 8-bit input and output +files, but it can be used for testing the 32-bit library. If it is run with the +command line option <b>-32</b>, patterns and subject strings are converted from +8-bit to 32-bit before being passed to PCRE, and the 32-bit library functions +are used instead of the 8-bit ones. Returned 32-bit strings are converted to +8-bit for output. If both the 8-bit and the 16-bit libraries were not compiled, +<b>pcretest</b> defaults to 32-bit and the <b>-32</b> option is ignored. +</P> +<P> +When PCRE is being built, the <b>RunTest</b> script that is called by "make +check" uses the <b>pcretest</b> <b>-C</b> option to discover which of the 8-bit, +16-bit and 32-bit libraries has been built, and runs the tests appropriately. +</P> +<br><a name="SEC20" href="#TOC1">NOT SUPPORTED IN 32-BIT MODE</a><br> +<P> +Not all the features of the 8-bit library are available with the 32-bit +library. The C++ and POSIX wrapper functions support only the 8-bit library, +and the <b>pcregrep</b> program is at present 8-bit only. +</P> +<br><a name="SEC21" href="#TOC1">AUTHOR</a><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><a name="SEC22" href="#TOC1">REVISION</a><br> +<P> +Last updated: 12 May 2013 +<br> +Copyright © 1997-2013 University of Cambridge. +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_assign_jit_stack.html b/plugins/Pcre16/docs/doc/html/pcre_assign_jit_stack.html new file mode 100644 index 0000000000..b2eef704db --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_assign_jit_stack.html @@ -0,0 +1,76 @@ +<html> +<head> +<title>pcre_assign_jit_stack specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_assign_jit_stack man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>void pcre_assign_jit_stack(pcre_extra *<i>extra</i>,</b> +<b> pcre_jit_callback <i>callback</i>, void *<i>data</i>);</b> +<br> +<br> +<b>void pcre16_assign_jit_stack(pcre16_extra *<i>extra</i>,</b> +<b> pcre16_jit_callback <i>callback</i>, void *<i>data</i>);</b> +<br> +<br> +<b>void pcre32_assign_jit_stack(pcre32_extra *<i>extra</i>,</b> +<b> pcre32_jit_callback <i>callback</i>, void *<i>data</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This function provides control over the memory used as a stack at run-time by a +call to <b>pcre[16|32]_exec()</b> with a pattern that has been successfully +compiled with JIT optimization. The arguments are: +<pre> + extra the data pointer returned by <b>pcre[16|32]_study()</b> + callback a callback function + data a JIT stack or a value to be passed to the callback + function +</PRE> +</P> +<P> +If <i>callback</i> is NULL and <i>data</i> is NULL, an internal 32K block on +the machine stack is used. +</P> +<P> +If <i>callback</i> is NULL and <i>data</i> is not NULL, <i>data</i> must +be a valid JIT stack, the result of calling <b>pcre[16|32]_jit_stack_alloc()</b>. +</P> +<P> +If <i>callback</i> not NULL, it is called with <i>data</i> as an argument at +the start of matching, in order to set up a JIT stack. If the result is NULL, +the internal 32K stack is used; otherwise the return value must be a valid JIT +stack, the result of calling <b>pcre[16|32]_jit_stack_alloc()</b>. +</P> +<P> +You may safely assign the same JIT stack to multiple patterns, as long as they +are all matched in the same thread. In a multithread application, each thread +must use its own JIT stack. For more details, see the +<a href="pcrejit.html"><b>pcrejit</b></a> +page. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_compile.html b/plugins/Pcre16/docs/doc/html/pcre_compile.html new file mode 100644 index 0000000000..95b4bec63c --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_compile.html @@ -0,0 +1,111 @@ +<html> +<head> +<title>pcre_compile specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_compile man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>pcre *pcre_compile(const char *<i>pattern</i>, int <i>options</i>,</b> +<b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b> +<b> const unsigned char *<i>tableptr</i>);</b> +<br> +<br> +<b>pcre16 *pcre16_compile(PCRE_SPTR16 <i>pattern</i>, int <i>options</i>,</b> +<b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b> +<b> const unsigned char *<i>tableptr</i>);</b> +<br> +<br> +<b>pcre32 *pcre32_compile(PCRE_SPTR32 <i>pattern</i>, int <i>options</i>,</b> +<b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b> +<b> const unsigned char *<i>tableptr</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This function compiles a regular expression into an internal form. It is the +same as <b>pcre[16|32]_compile2()</b>, except for the absence of the +<i>errorcodeptr</i> argument. Its arguments are: +<pre> + <i>pattern</i> A zero-terminated string containing the + regular expression to be compiled + <i>options</i> Zero or more option bits + <i>errptr</i> Where to put an error message + <i>erroffset</i> Offset in pattern where error was found + <i>tableptr</i> Pointer to character tables, or NULL to + use the built-in default +</pre> +The option bits are: +<pre> + PCRE_ANCHORED Force pattern anchoring + PCRE_AUTO_CALLOUT Compile automatic callouts + PCRE_BSR_ANYCRLF \R matches only CR, LF, or CRLF + PCRE_BSR_UNICODE \R matches all Unicode line endings + PCRE_CASELESS Do caseless matching + PCRE_DOLLAR_ENDONLY $ not to match newline at end + PCRE_DOTALL . matches anything including NL + PCRE_DUPNAMES Allow duplicate names for subpatterns + PCRE_EXTENDED Ignore white space and # comments + PCRE_EXTRA PCRE extra features + (not much use currently) + PCRE_FIRSTLINE Force matching to be before newline + PCRE_JAVASCRIPT_COMPAT JavaScript compatibility + PCRE_MULTILINE ^ and $ match newlines within data + PCRE_NEVER_UTF Lock out UTF, e.g. via (*UTF) + PCRE_NEWLINE_ANY Recognize any Unicode newline sequence + PCRE_NEWLINE_ANYCRLF Recognize CR, LF, and CRLF as newline + sequences + PCRE_NEWLINE_CR Set CR as the newline sequence + PCRE_NEWLINE_CRLF Set CRLF as the newline sequence + PCRE_NEWLINE_LF Set LF as the newline sequence + PCRE_NO_AUTO_CAPTURE Disable numbered capturing paren- + theses (named ones available) + PCRE_NO_AUTO_POSSESS Disable auto-possessification + PCRE_NO_START_OPTIMIZE Disable match-time start optimizations + PCRE_NO_UTF16_CHECK Do not check the pattern for UTF-16 + validity (only relevant if + PCRE_UTF16 is set) + PCRE_NO_UTF32_CHECK Do not check the pattern for UTF-32 + validity (only relevant if + PCRE_UTF32 is set) + PCRE_NO_UTF8_CHECK Do not check the pattern for UTF-8 + validity (only relevant if + PCRE_UTF8 is set) + PCRE_UCP Use Unicode properties for \d, \w, etc. + PCRE_UNGREEDY Invert greediness of quantifiers + PCRE_UTF16 Run in <b>pcre16_compile()</b> UTF-16 mode + PCRE_UTF32 Run in <b>pcre32_compile()</b> UTF-32 mode + PCRE_UTF8 Run in <b>pcre_compile()</b> UTF-8 mode +</pre> +PCRE must be built with UTF support in order to use PCRE_UTF8/16/32 and +PCRE_NO_UTF8/16/32_CHECK, and with UCP support if PCRE_UCP is used. +</P> +<P> +The yield of the function is a pointer to a private data structure that +contains the compiled pattern, or NULL if an error was detected. Note that +compiling regular expressions with one version of PCRE for use with a different +version is not guaranteed to work and may cause crashes. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_compile2.html b/plugins/Pcre16/docs/doc/html/pcre_compile2.html new file mode 100644 index 0000000000..9cd56a237b --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_compile2.html @@ -0,0 +1,115 @@ +<html> +<head> +<title>pcre_compile2 specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_compile2 man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>pcre *pcre_compile2(const char *<i>pattern</i>, int <i>options</i>,</b> +<b> int *<i>errorcodeptr</i>,</b> +<b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b> +<b> const unsigned char *<i>tableptr</i>);</b> +<br> +<br> +<b>pcre16 *pcre16_compile2(PCRE_SPTR16 <i>pattern</i>, int <i>options</i>,</b> +<b> int *<i>errorcodeptr</i>,</b> +<b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b> +<b> const unsigned char *<i>tableptr</i>);</b> +<br> +<br> +<b>pcre32 *pcre32_compile2(PCRE_SPTR32 <i>pattern</i>, int <i>options</i>,</b> +<b>" int *<i>errorcodeptr</i>,£</b> +<b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b> +<b> const unsigned char *<i>tableptr</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This function compiles a regular expression into an internal form. It is the +same as <b>pcre[16|32]_compile()</b>, except for the addition of the +<i>errorcodeptr</i> argument. The arguments are: +<pre> + <i>pattern</i> A zero-terminated string containing the + regular expression to be compiled + <i>options</i> Zero or more option bits + <i>errorcodeptr</i> Where to put an error code + <i>errptr</i> Where to put an error message + <i>erroffset</i> Offset in pattern where error was found + <i>tableptr</i> Pointer to character tables, or NULL to + use the built-in default +</pre> +The option bits are: +<pre> + PCRE_ANCHORED Force pattern anchoring + PCRE_AUTO_CALLOUT Compile automatic callouts + PCRE_BSR_ANYCRLF \R matches only CR, LF, or CRLF + PCRE_BSR_UNICODE \R matches all Unicode line endings + PCRE_CASELESS Do caseless matching + PCRE_DOLLAR_ENDONLY $ not to match newline at end + PCRE_DOTALL . matches anything including NL + PCRE_DUPNAMES Allow duplicate names for subpatterns + PCRE_EXTENDED Ignore white space and # comments + PCRE_EXTRA PCRE extra features + (not much use currently) + PCRE_FIRSTLINE Force matching to be before newline + PCRE_JAVASCRIPT_COMPAT JavaScript compatibility + PCRE_MULTILINE ^ and $ match newlines within data + PCRE_NEVER_UTF Lock out UTF, e.g. via (*UTF) + PCRE_NEWLINE_ANY Recognize any Unicode newline sequence + PCRE_NEWLINE_ANYCRLF Recognize CR, LF, and CRLF as newline + sequences + PCRE_NEWLINE_CR Set CR as the newline sequence + PCRE_NEWLINE_CRLF Set CRLF as the newline sequence + PCRE_NEWLINE_LF Set LF as the newline sequence + PCRE_NO_AUTO_CAPTURE Disable numbered capturing paren- + theses (named ones available) + PCRE_NO_AUTO_POSSESS Disable auto-possessification + PCRE_NO_START_OPTIMIZE Disable match-time start optimizations + PCRE_NO_UTF16_CHECK Do not check the pattern for UTF-16 + validity (only relevant if + PCRE_UTF16 is set) + PCRE_NO_UTF32_CHECK Do not check the pattern for UTF-32 + validity (only relevant if + PCRE_UTF32 is set) + PCRE_NO_UTF8_CHECK Do not check the pattern for UTF-8 + validity (only relevant if + PCRE_UTF8 is set) + PCRE_UCP Use Unicode properties for \d, \w, etc. + PCRE_UNGREEDY Invert greediness of quantifiers + PCRE_UTF16 Run <b>pcre16_compile()</b> in UTF-16 mode + PCRE_UTF32 Run <b>pcre32_compile()</b> in UTF-32 mode + PCRE_UTF8 Run <b>pcre_compile()</b> in UTF-8 mode +</pre> +PCRE must be built with UTF support in order to use PCRE_UTF8/16/32 and +PCRE_NO_UTF8/16/32_CHECK, and with UCP support if PCRE_UCP is used. +</P> +<P> +The yield of the function is a pointer to a private data structure that +contains the compiled pattern, or NULL if an error was detected. Note that +compiling regular expressions with one version of PCRE for use with a different +version is not guaranteed to work and may cause crashes. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_config.html b/plugins/Pcre16/docs/doc/html/pcre_config.html new file mode 100644 index 0000000000..bcdcdded70 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_config.html @@ -0,0 +1,92 @@ +<html> +<head> +<title>pcre_config specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_config man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>int pcre_config(int <i>what</i>, void *<i>where</i>);</b> +</P> +<P> +<b>int pcre16_config(int <i>what</i>, void *<i>where</i>);</b> +</P> +<P> +<b>int pcre32_config(int <i>what</i>, void *<i>where</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This function makes it possible for a client program to find out which optional +features are available in the version of the PCRE library it is using. The +arguments are as follows: +<pre> + <i>what</i> A code specifying what information is required + <i>where</i> Points to where to put the data +</pre> +The <i>where</i> argument must point to an integer variable, except for +PCRE_CONFIG_MATCH_LIMIT and PCRE_CONFIG_MATCH_LIMIT_RECURSION, when it must +point to an unsigned long integer. The available codes are: +<pre> + PCRE_CONFIG_JIT Availability of just-in-time compiler + support (1=yes 0=no) + PCRE_CONFIG_JITTARGET String containing information about the + target architecture for the JIT compiler, + or NULL if there is no JIT support + PCRE_CONFIG_LINK_SIZE Internal link size: 2, 3, or 4 + PCRE_CONFIG_PARENS_LIMIT Parentheses nesting limit + PCRE_CONFIG_MATCH_LIMIT Internal resource limit + PCRE_CONFIG_MATCH_LIMIT_RECURSION + Internal recursion depth limit + PCRE_CONFIG_NEWLINE Value of the default newline sequence: + 13 (0x000d) for CR + 10 (0x000a) for LF + 3338 (0x0d0a) for CRLF + -2 for ANYCRLF + -1 for ANY + PCRE_CONFIG_BSR Indicates what \R matches by default: + 0 all Unicode line endings + 1 CR, LF, or CRLF only + PCRE_CONFIG_POSIX_MALLOC_THRESHOLD + Threshold of return slots, above which + <b>malloc()</b> is used by the POSIX API + PCRE_CONFIG_STACKRECURSE Recursion implementation (1=stack 0=heap) + PCRE_CONFIG_UTF16 Availability of UTF-16 support (1=yes + 0=no); option for <b>pcre16_config()</b> + PCRE_CONFIG_UTF32 Availability of UTF-32 support (1=yes + 0=no); option for <b>pcre32_config()</b> + PCRE_CONFIG_UTF8 Availability of UTF-8 support (1=yes 0=no); + option for <b>pcre_config()</b> + PCRE_CONFIG_UNICODE_PROPERTIES + Availability of Unicode property support + (1=yes 0=no) +</pre> +The function yields 0 on success or PCRE_ERROR_BADOPTION otherwise. That error +is also given if PCRE_CONFIG_UTF16 or PCRE_CONFIG_UTF32 is passed to +<b>pcre_config()</b>, if PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF32 is passed to +<b>pcre16_config()</b>, or if PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF16 is passed to +<b>pcre32_config()</b>. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_copy_named_substring.html b/plugins/Pcre16/docs/doc/html/pcre_copy_named_substring.html new file mode 100644 index 0000000000..77b48043cd --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_copy_named_substring.html @@ -0,0 +1,65 @@ +<html> +<head> +<title>pcre_copy_named_substring specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_copy_named_substring man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>int pcre_copy_named_substring(const pcre *<i>code</i>,</b> +<b> const char *<i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, const char *<i>stringname</i>,</b> +<b> char *<i>buffer</i>, int <i>buffersize</i>);</b> +<br> +<br> +<b>int pcre16_copy_named_substring(const pcre16 *<i>code</i>,</b> +<b> PCRE_SPTR16 <i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, PCRE_SPTR16 <i>stringname</i>,</b> +<b> PCRE_UCHAR16 *<i>buffer</i>, int <i>buffersize</i>);</b> +<br> +<br> +<b>int pcre32_copy_named_substring(const pcre32 *<i>code</i>,</b> +<b> PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, PCRE_SPTR32 <i>stringname</i>,</b> +<b> PCRE_UCHAR32 *<i>buffer</i>, int <i>buffersize</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This is a convenience function for extracting a captured substring, identified +by name, into a given buffer. The arguments are: +<pre> + <i>code</i> Pattern that was successfully matched + <i>subject</i> Subject that has been successfully matched + <i>ovector</i> Offset vector that <b>pcre[16|32]_exec()</b> used + <i>stringcount</i> Value returned by <b>pcre[16|32]_exec()</b> + <i>stringname</i> Name of the required substring + <i>buffer</i> Buffer to receive the string + <i>buffersize</i> Size of buffer +</pre> +The yield is the length of the substring, PCRE_ERROR_NOMEMORY if the buffer was +too small, or PCRE_ERROR_NOSUBSTRING if the string name is invalid. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_copy_substring.html b/plugins/Pcre16/docs/doc/html/pcre_copy_substring.html new file mode 100644 index 0000000000..ecaebe8533 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_copy_substring.html @@ -0,0 +1,61 @@ +<html> +<head> +<title>pcre_copy_substring specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_copy_substring man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>int pcre_copy_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, int <i>stringnumber</i>, char *<i>buffer</i>,</b> +<b> int <i>buffersize</i>);</b> +<br> +<br> +<b>int pcre16_copy_substring(PCRE_SPTR16 <i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, int <i>stringnumber</i>, PCRE_UCHAR16 *<i>buffer</i>,</b> +<b> int <i>buffersize</i>);</b> +<br> +<br> +<b>int pcre32_copy_substring(PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, int <i>stringnumber</i>, PCRE_UCHAR32 *<i>buffer</i>,</b> +<b> int <i>buffersize</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This is a convenience function for extracting a captured substring into a given +buffer. The arguments are: +<pre> + <i>subject</i> Subject that has been successfully matched + <i>ovector</i> Offset vector that <b>pcre[16|32]_exec()</b> used + <i>stringcount</i> Value returned by <b>pcre[16|32]_exec()</b> + <i>stringnumber</i> Number of the required substring + <i>buffer</i> Buffer to receive the string + <i>buffersize</i> Size of buffer +</pre> +The yield is the length of the string, PCRE_ERROR_NOMEMORY if the buffer was +too small, or PCRE_ERROR_NOSUBSTRING if the string number is invalid. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_dfa_exec.html b/plugins/Pcre16/docs/doc/html/pcre_dfa_exec.html new file mode 100644 index 0000000000..5fff6a7e0a --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_dfa_exec.html @@ -0,0 +1,129 @@ +<html> +<head> +<title>pcre_dfa_exec specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_dfa_exec man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>int pcre_dfa_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b> +<b> const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b> +<b> int *<i>workspace</i>, int <i>wscount</i>);</b> +<br> +<br> +<b>int pcre16_dfa_exec(const pcre16 *<i>code</i>, const pcre16_extra *<i>extra</i>,</b> +<b> PCRE_SPTR16 <i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b> +<b> int *<i>workspace</i>, int <i>wscount</i>);</b> +<br> +<br> +<b>int pcre32_dfa_exec(const pcre32 *<i>code</i>, const pcre32_extra *<i>extra</i>,</b> +<b> PCRE_SPTR32 <i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b> +<b> int *<i>workspace</i>, int <i>wscount</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This function matches a compiled regular expression against a given subject +string, using an alternative matching algorithm that scans the subject string +just once (<i>not</i> Perl-compatible). Note that the main, Perl-compatible, +matching function is <b>pcre[16|32]_exec()</b>. The arguments for this function +are: +<pre> + <i>code</i> Points to the compiled pattern + <i>extra</i> Points to an associated <b>pcre[16|32]_extra</b> structure, + or is NULL + <i>subject</i> Points to the subject string + <i>length</i> Length of the subject string + <i>startoffset</i> Offset in the subject at which to start matching + <i>options</i> Option bits + <i>ovector</i> Points to a vector of ints for result offsets + <i>ovecsize</i> Number of elements in the vector + <i>workspace</i> Points to a vector of ints used as working space + <i>wscount</i> Number of elements in the vector +</pre> +The units for <i>length</i> and <i>startoffset</i> are bytes for +<b>pcre_exec()</b>, 16-bit data items for <b>pcre16_exec()</b>, and 32-bit items +for <b>pcre32_exec()</b>. The options are: +<pre> + PCRE_ANCHORED Match only at the first position + PCRE_BSR_ANYCRLF \R matches only CR, LF, or CRLF + PCRE_BSR_UNICODE \R matches all Unicode line endings + PCRE_NEWLINE_ANY Recognize any Unicode newline sequence + PCRE_NEWLINE_ANYCRLF Recognize CR, LF, & CRLF as newline sequences + PCRE_NEWLINE_CR Recognize CR as the only newline sequence + PCRE_NEWLINE_CRLF Recognize CRLF as the only newline sequence + PCRE_NEWLINE_LF Recognize LF as the only newline sequence + PCRE_NOTBOL Subject is not the beginning of a line + PCRE_NOTEOL Subject is not the end of a line + PCRE_NOTEMPTY An empty string is not a valid match + PCRE_NOTEMPTY_ATSTART An empty string at the start of the subject + is not a valid match + PCRE_NO_START_OPTIMIZE Do not do "start-match" optimizations + PCRE_NO_UTF16_CHECK Do not check the subject for UTF-16 + validity (only relevant if PCRE_UTF16 + was set at compile time) + PCRE_NO_UTF32_CHECK Do not check the subject for UTF-32 + validity (only relevant if PCRE_UTF32 + was set at compile time) + PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8 + validity (only relevant if PCRE_UTF8 + was set at compile time) + PCRE_PARTIAL ) Return PCRE_ERROR_PARTIAL for a partial + PCRE_PARTIAL_SOFT ) match if no full matches are found + PCRE_PARTIAL_HARD Return PCRE_ERROR_PARTIAL for a partial match + even if there is a full match as well + PCRE_DFA_SHORTEST Return only the shortest match + PCRE_DFA_RESTART Restart after a partial match +</pre> +There are restrictions on what may appear in a pattern when using this matching +function. Details are given in the +<a href="pcrematching.html"><b>pcrematching</b></a> +documentation. For details of partial matching, see the +<a href="pcrepartial.html"><b>pcrepartial</b></a> +page. +</P> +<P> +A <b>pcre[16|32]_extra</b> structure contains the following fields: +<pre> + <i>flags</i> Bits indicating which fields are set + <i>study_data</i> Opaque data from <b>pcre[16|32]_study()</b> + <i>match_limit</i> Limit on internal resource use + <i>match_limit_recursion</i> Limit on internal recursion depth + <i>callout_data</i> Opaque data passed back to callouts + <i>tables</i> Points to character tables or is NULL + <i>mark</i> For passing back a *MARK pointer + <i>executable_jit</i> Opaque data from JIT compilation +</pre> +The flag bits are PCRE_EXTRA_STUDY_DATA, PCRE_EXTRA_MATCH_LIMIT, +PCRE_EXTRA_MATCH_LIMIT_RECURSION, PCRE_EXTRA_CALLOUT_DATA, +PCRE_EXTRA_TABLES, PCRE_EXTRA_MARK and PCRE_EXTRA_EXECUTABLE_JIT. For this +matching function, the <i>match_limit</i> and <i>match_limit_recursion</i> fields +are not used, and must not be set. The PCRE_EXTRA_EXECUTABLE_JIT flag and +the corresponding variable are ignored. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_exec.html b/plugins/Pcre16/docs/doc/html/pcre_exec.html new file mode 100644 index 0000000000..18e1a13ff8 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_exec.html @@ -0,0 +1,111 @@ +<html> +<head> +<title>pcre_exec specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_exec man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>int pcre_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b> +<b> const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b> +<br> +<br> +<b>int pcre16_exec(const pcre16 *<i>code</i>, const pcre16_extra *<i>extra</i>,</b> +<b> PCRE_SPTR16 <i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b> +<br> +<br> +<b>int pcre32_exec(const pcre32 *<i>code</i>, const pcre32_extra *<i>extra</i>,</b> +<b> PCRE_SPTR32 <i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This function matches a compiled regular expression against a given subject +string, using a matching algorithm that is similar to Perl's. It returns +offsets to captured substrings. Its arguments are: +<pre> + <i>code</i> Points to the compiled pattern + <i>extra</i> Points to an associated <b>pcre[16|32]_extra</b> structure, + or is NULL + <i>subject</i> Points to the subject string + <i>length</i> Length of the subject string + <i>startoffset</i> Offset in the subject at which to start matching + <i>options</i> Option bits + <i>ovector</i> Points to a vector of ints for result offsets + <i>ovecsize</i> Number of elements in the vector (a multiple of 3) +</pre> +The units for <i>length</i> and <i>startoffset</i> are bytes for +<b>pcre_exec()</b>, 16-bit data items for <b>pcre16_exec()</b>, and 32-bit items +for <b>pcre32_exec()</b>. The options are: +<pre> + PCRE_ANCHORED Match only at the first position + PCRE_BSR_ANYCRLF \R matches only CR, LF, or CRLF + PCRE_BSR_UNICODE \R matches all Unicode line endings + PCRE_NEWLINE_ANY Recognize any Unicode newline sequence + PCRE_NEWLINE_ANYCRLF Recognize CR, LF, & CRLF as newline sequences + PCRE_NEWLINE_CR Recognize CR as the only newline sequence + PCRE_NEWLINE_CRLF Recognize CRLF as the only newline sequence + PCRE_NEWLINE_LF Recognize LF as the only newline sequence + PCRE_NOTBOL Subject string is not the beginning of a line + PCRE_NOTEOL Subject string is not the end of a line + PCRE_NOTEMPTY An empty string is not a valid match + PCRE_NOTEMPTY_ATSTART An empty string at the start of the subject + is not a valid match + PCRE_NO_START_OPTIMIZE Do not do "start-match" optimizations + PCRE_NO_UTF16_CHECK Do not check the subject for UTF-16 + validity (only relevant if PCRE_UTF16 + was set at compile time) + PCRE_NO_UTF32_CHECK Do not check the subject for UTF-32 + validity (only relevant if PCRE_UTF32 + was set at compile time) + PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8 + validity (only relevant if PCRE_UTF8 + was set at compile time) + PCRE_PARTIAL ) Return PCRE_ERROR_PARTIAL for a partial + PCRE_PARTIAL_SOFT ) match if no full matches are found + PCRE_PARTIAL_HARD Return PCRE_ERROR_PARTIAL for a partial match + if that is found before a full match +</pre> +For details of partial matching, see the +<a href="pcrepartial.html"><b>pcrepartial</b></a> +page. A <b>pcre_extra</b> structure contains the following fields: +<pre> + <i>flags</i> Bits indicating which fields are set + <i>study_data</i> Opaque data from <b>pcre[16|32]_study()</b> + <i>match_limit</i> Limit on internal resource use + <i>match_limit_recursion</i> Limit on internal recursion depth + <i>callout_data</i> Opaque data passed back to callouts + <i>tables</i> Points to character tables or is NULL + <i>mark</i> For passing back a *MARK pointer + <i>executable_jit</i> Opaque data from JIT compilation +</pre> +The flag bits are PCRE_EXTRA_STUDY_DATA, PCRE_EXTRA_MATCH_LIMIT, +PCRE_EXTRA_MATCH_LIMIT_RECURSION, PCRE_EXTRA_CALLOUT_DATA, +PCRE_EXTRA_TABLES, PCRE_EXTRA_MARK and PCRE_EXTRA_EXECUTABLE_JIT. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_free_study.html b/plugins/Pcre16/docs/doc/html/pcre_free_study.html new file mode 100644 index 0000000000..7f9e10e863 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_free_study.html @@ -0,0 +1,46 @@ +<html> +<head> +<title>pcre_free_study specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_free_study man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>void pcre_free_study(pcre_extra *<i>extra</i>);</b> +</P> +<P> +<b>void pcre16_free_study(pcre16_extra *<i>extra</i>);</b> +</P> +<P> +<b>void pcre32_free_study(pcre32_extra *<i>extra</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This function is used to free the memory used for the data generated by a call +to <b>pcre[16|32]_study()</b> when it is no longer needed. The argument must be the +result of such a call. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_free_substring.html b/plugins/Pcre16/docs/doc/html/pcre_free_substring.html new file mode 100644 index 0000000000..1fe6610746 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_free_substring.html @@ -0,0 +1,46 @@ +<html> +<head> +<title>pcre_free_substring specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_free_substring man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>void pcre_free_substring(const char *<i>stringptr</i>);</b> +</P> +<P> +<b>void pcre16_free_substring(PCRE_SPTR16 <i>stringptr</i>);</b> +</P> +<P> +<b>void pcre32_free_substring(PCRE_SPTR32 <i>stringptr</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This is a convenience function for freeing the store obtained by a previous +call to <b>pcre[16|32]_get_substring()</b> or <b>pcre[16|32]_get_named_substring()</b>. +Its only argument is a pointer to the string. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_free_substring_list.html b/plugins/Pcre16/docs/doc/html/pcre_free_substring_list.html new file mode 100644 index 0000000000..c0861780b4 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_free_substring_list.html @@ -0,0 +1,46 @@ +<html> +<head> +<title>pcre_free_substring_list specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_free_substring_list man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>void pcre_free_substring_list(const char **<i>stringptr</i>);</b> +</P> +<P> +<b>void pcre16_free_substring_list(PCRE_SPTR16 *<i>stringptr</i>);</b> +</P> +<P> +<b>void pcre32_free_substring_list(PCRE_SPTR32 *<i>stringptr</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This is a convenience function for freeing the store obtained by a previous +call to <b>pcre[16|32]_get_substring_list()</b>. Its only argument is a pointer to +the list of string pointers. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_fullinfo.html b/plugins/Pcre16/docs/doc/html/pcre_fullinfo.html new file mode 100644 index 0000000000..b88fc1155b --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_fullinfo.html @@ -0,0 +1,108 @@ +<html> +<head> +<title>pcre_fullinfo specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_fullinfo man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>int pcre_fullinfo(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b> +<b> int <i>what</i>, void *<i>where</i>);</b> +<br> +<br> +<b>int pcre16_fullinfo(const pcre16 *<i>code</i>, const pcre16_extra *<i>extra</i>,</b> +<b> int <i>what</i>, void *<i>where</i>);</b> +<br> +<br> +<b>int pcre32_fullinfo(const pcre32 *<i>code</i>, const pcre32_extra *<i>extra</i>,</b> +<b> int <i>what</i>, void *<i>where</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This function returns information about a compiled pattern. Its arguments are: +<pre> + <i>code</i> Compiled regular expression + <i>extra</i> Result of <b>pcre[16|32]_study()</b> or NULL + <i>what</i> What information is required + <i>where</i> Where to put the information +</pre> +The following information is available: +<pre> + PCRE_INFO_BACKREFMAX Number of highest back reference + PCRE_INFO_CAPTURECOUNT Number of capturing subpatterns + PCRE_INFO_DEFAULT_TABLES Pointer to default tables + PCRE_INFO_FIRSTBYTE Fixed first data unit for a match, or + -1 for start of string + or after newline, or + -2 otherwise + PCRE_INFO_FIRSTTABLE Table of first data units (after studying) + PCRE_INFO_HASCRORLF Return 1 if explicit CR or LF matches exist + PCRE_INFO_JCHANGED Return 1 if (?J) or (?-J) was used + PCRE_INFO_JIT Return 1 after successful JIT compilation + PCRE_INFO_JITSIZE Size of JIT compiled code + PCRE_INFO_LASTLITERAL Literal last data unit required + PCRE_INFO_MINLENGTH Lower bound length of matching strings + PCRE_INFO_NAMECOUNT Number of named subpatterns + PCRE_INFO_NAMEENTRYSIZE Size of name table entry + PCRE_INFO_NAMETABLE Pointer to name table + PCRE_INFO_OKPARTIAL Return 1 if partial matching can be tried + (always returns 1 after release 8.00) + PCRE_INFO_OPTIONS Option bits used for compilation + PCRE_INFO_SIZE Size of compiled pattern + PCRE_INFO_STUDYSIZE Size of study data + PCRE_INFO_FIRSTCHARACTER Fixed first data unit for a match + PCRE_INFO_FIRSTCHARACTERFLAGS Returns + 1 if there is a first data character set, which can + then be retrieved using PCRE_INFO_FIRSTCHARACTER, + 2 if the first character is at the start of the data + string or after a newline, and + 0 otherwise + PCRE_INFO_REQUIREDCHAR Literal last data unit required + PCRE_INFO_REQUIREDCHARFLAGS Returns 1 if the last data character is set (which can then + be retrieved using PCRE_INFO_REQUIREDCHAR); 0 otherwise +</pre> +The <i>where</i> argument must point to an integer variable, except for the +following <i>what</i> values: +<pre> + PCRE_INFO_DEFAULT_TABLES const unsigned char * + PCRE_INFO_FIRSTTABLE const unsigned char * + PCRE_INFO_NAMETABLE PCRE_SPTR16 (16-bit library) + PCRE_INFO_NAMETABLE PCRE_SPTR32 (32-bit library) + PCRE_INFO_NAMETABLE const unsigned char * (8-bit library) + PCRE_INFO_OPTIONS unsigned long int + PCRE_INFO_SIZE size_t + PCRE_INFO_FIRSTCHARACTER uint32_t + PCRE_INFO_REQUIREDCHAR uint32_t +</pre> +The yield of the function is zero on success or: +<pre> + PCRE_ERROR_NULL the argument <i>code</i> was NULL + the argument <i>where</i> was NULL + PCRE_ERROR_BADMAGIC the "magic number" was not found + PCRE_ERROR_BADOPTION the value of <i>what</i> was invalid +</PRE> +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_get_named_substring.html b/plugins/Pcre16/docs/doc/html/pcre_get_named_substring.html new file mode 100644 index 0000000000..72924d9b25 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_get_named_substring.html @@ -0,0 +1,68 @@ +<html> +<head> +<title>pcre_get_named_substring specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_get_named_substring man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>int pcre_get_named_substring(const pcre *<i>code</i>,</b> +<b> const char *<i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, const char *<i>stringname</i>,</b> +<b> const char **<i>stringptr</i>);</b> +<br> +<br> +<b>int pcre16_get_named_substring(const pcre16 *<i>code</i>,</b> +<b> PCRE_SPTR16 <i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, PCRE_SPTR16 <i>stringname</i>,</b> +<b> PCRE_SPTR16 *<i>stringptr</i>);</b> +<br> +<br> +<b>int pcre32_get_named_substring(const pcre32 *<i>code</i>,</b> +<b> PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, PCRE_SPTR32 <i>stringname</i>,</b> +<b> PCRE_SPTR32 *<i>stringptr</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This is a convenience function for extracting a captured substring by name. The +arguments are: +<pre> + <i>code</i> Compiled pattern + <i>subject</i> Subject that has been successfully matched + <i>ovector</i> Offset vector that <b>pcre[16|32]_exec()</b> used + <i>stringcount</i> Value returned by <b>pcre[16|32]_exec()</b> + <i>stringname</i> Name of the required substring + <i>stringptr</i> Where to put the string pointer +</pre> +The memory in which the substring is placed is obtained by calling +<b>pcre[16|32]_malloc()</b>. The convenience function +<b>pcre[16|32]_free_substring()</b> can be used to free it when it is no longer +needed. The yield of the function is the length of the extracted substring, +PCRE_ERROR_NOMEMORY if sufficient memory could not be obtained, or +PCRE_ERROR_NOSUBSTRING if the string name is invalid. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_get_stringnumber.html b/plugins/Pcre16/docs/doc/html/pcre_get_stringnumber.html new file mode 100644 index 0000000000..7324d782e7 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_get_stringnumber.html @@ -0,0 +1,57 @@ +<html> +<head> +<title>pcre_get_stringnumber specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_get_stringnumber man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>int pcre_get_stringnumber(const pcre *<i>code</i>,</b> +<b> const char *<i>name</i>);</b> +<br> +<br> +<b>int pcre16_get_stringnumber(const pcre16 *<i>code</i>,</b> +<b> PCRE_SPTR16 <i>name</i>);</b> +<br> +<br> +<b>int pcre32_get_stringnumber(const pcre32 *<i>code</i>,</b> +<b> PCRE_SPTR32 <i>name</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This convenience function finds the number of a named substring capturing +parenthesis in a compiled pattern. Its arguments are: +<pre> + <i>code</i> Compiled regular expression + <i>name</i> Name whose number is required +</pre> +The yield of the function is the number of the parenthesis if the name is +found, or PCRE_ERROR_NOSUBSTRING otherwise. When duplicate names are allowed +(PCRE_DUPNAMES is set), it is not defined which of the numbers is returned by +<b>pcre[16|32]_get_stringnumber()</b>. You can obtain the complete list by calling +<b>pcre[16|32]_get_stringtable_entries()</b>. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_get_stringtable_entries.html b/plugins/Pcre16/docs/doc/html/pcre_get_stringtable_entries.html new file mode 100644 index 0000000000..79906798e6 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_get_stringtable_entries.html @@ -0,0 +1,60 @@ +<html> +<head> +<title>pcre_get_stringtable_entries specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_get_stringtable_entries man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>int pcre_get_stringtable_entries(const pcre *<i>code</i>,</b> +<b> const char *<i>name</i>, char **<i>first</i>, char **<i>last</i>);</b> +<br> +<br> +<b>int pcre16_get_stringtable_entries(const pcre16 *<i>code</i>,</b> +<b> PCRE_SPTR16 <i>name</i>, PCRE_UCHAR16 **<i>first</i>, PCRE_UCHAR16 **<i>last</i>);</b> +<br> +<br> +<b>int pcre32_get_stringtable_entries(const pcre32 *<i>code</i>,</b> +<b> PCRE_SPTR32 <i>name</i>, PCRE_UCHAR32 **<i>first</i>, PCRE_UCHAR32 **<i>last</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This convenience function finds, for a compiled pattern, the first and last +entries for a given name in the table that translates capturing parenthesis +names into numbers. When names are required to be unique (PCRE_DUPNAMES is +<i>not</i> set), it is usually easier to use <b>pcre[16|32]_get_stringnumber()</b> +instead. +<pre> + <i>code</i> Compiled regular expression + <i>name</i> Name whose entries required + <i>first</i> Where to return a pointer to the first entry + <i>last</i> Where to return a pointer to the last entry +</pre> +The yield of the function is the length of each entry, or +PCRE_ERROR_NOSUBSTRING if none are found. +</P> +<P> +There is a complete description of the PCRE native API, including the format of +the table entries, in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page, and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_get_substring.html b/plugins/Pcre16/docs/doc/html/pcre_get_substring.html new file mode 100644 index 0000000000..1a8e4f5a49 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_get_substring.html @@ -0,0 +1,64 @@ +<html> +<head> +<title>pcre_get_substring specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_get_substring man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>int pcre_get_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, int <i>stringnumber</i>,</b> +<b> const char **<i>stringptr</i>);</b> +<br> +<br> +<b>int pcre16_get_substring(PCRE_SPTR16 <i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, int <i>stringnumber</i>,</b> +<b> PCRE_SPTR16 *<i>stringptr</i>);</b> +<br> +<br> +<b>int pcre32_get_substring(PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, int <i>stringnumber</i>,</b> +<b> PCRE_SPTR32 *<i>stringptr</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This is a convenience function for extracting a captured substring. The +arguments are: +<pre> + <i>subject</i> Subject that has been successfully matched + <i>ovector</i> Offset vector that <b>pcre[16|32]_exec()</b> used + <i>stringcount</i> Value returned by <b>pcre[16|32]_exec()</b> + <i>stringnumber</i> Number of the required substring + <i>stringptr</i> Where to put the string pointer +</pre> +The memory in which the substring is placed is obtained by calling +<b>pcre[16|32]_malloc()</b>. The convenience function +<b>pcre[16|32]_free_substring()</b> can be used to free it when it is no longer +needed. The yield of the function is the length of the substring, +PCRE_ERROR_NOMEMORY if sufficient memory could not be obtained, or +PCRE_ERROR_NOSUBSTRING if the string number is invalid. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_get_substring_list.html b/plugins/Pcre16/docs/doc/html/pcre_get_substring_list.html new file mode 100644 index 0000000000..7e8c6bc858 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_get_substring_list.html @@ -0,0 +1,61 @@ +<html> +<head> +<title>pcre_get_substring_list specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_get_substring_list man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>int pcre_get_substring_list(const char *<i>subject</i>,</b> +<b> int *<i>ovector</i>, int <i>stringcount</i>, const char ***<i>listptr</i>);</b> +<br> +<br> +<b>int pcre16_get_substring_list(PCRE_SPTR16 <i>subject</i>,</b> +<b> int *<i>ovector</i>, int <i>stringcount</i>, PCRE_SPTR16 **<i>listptr</i>);</b> +<br> +<br> +<b>int pcre32_get_substring_list(PCRE_SPTR32 <i>subject</i>,</b> +<b> int *<i>ovector</i>, int <i>stringcount</i>, PCRE_SPTR32 **<i>listptr</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This is a convenience function for extracting a list of all the captured +substrings. The arguments are: +<pre> + <i>subject</i> Subject that has been successfully matched + <i>ovector</i> Offset vector that <b>pcre[16|32]_exec</b> used + <i>stringcount</i> Value returned by <b>pcre[16|32]_exec</b> + <i>listptr</i> Where to put a pointer to the list +</pre> +The memory in which the substrings and the list are placed is obtained by +calling <b>pcre[16|32]_malloc()</b>. The convenience function +<b>pcre[16|32]_free_substring_list()</b> can be used to free it when it is no +longer needed. A pointer to a list of pointers is put in the variable whose +address is in <i>listptr</i>. The list is terminated by a NULL pointer. The +yield of the function is zero on success or PCRE_ERROR_NOMEMORY if sufficient +memory could not be obtained. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_jit_exec.html b/plugins/Pcre16/docs/doc/html/pcre_jit_exec.html new file mode 100644 index 0000000000..4ebb0cbcac --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_jit_exec.html @@ -0,0 +1,108 @@ +<html> +<head> +<title>pcre_jit_exec specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_jit_exec man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>int pcre_jit_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b> +<b> const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b> +<b> pcre_jit_stack *<i>jstack</i>);</b> +<br> +<br> +<b>int pcre16_jit_exec(const pcre16 *<i>code</i>, const pcre16_extra *<i>extra</i>,</b> +<b> PCRE_SPTR16 <i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b> +<b> pcre_jit_stack *<i>jstack</i>);</b> +<br> +<br> +<b>int pcre32_jit_exec(const pcre32 *<i>code</i>, const pcre32_extra *<i>extra</i>,</b> +<b> PCRE_SPTR32 <i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b> +<b> pcre_jit_stack *<i>jstack</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This function matches a compiled regular expression that has been successfully +studied with one of the JIT options against a given subject string, using a +matching algorithm that is similar to Perl's. It is a "fast path" interface to +JIT, and it bypasses some of the sanity checks that <b>pcre_exec()</b> applies. +It returns offsets to captured substrings. Its arguments are: +<pre> + <i>code</i> Points to the compiled pattern + <i>extra</i> Points to an associated <b>pcre[16|32]_extra</b> structure, + or is NULL + <i>subject</i> Points to the subject string + <i>length</i> Length of the subject string, in bytes + <i>startoffset</i> Offset in bytes in the subject at which to + start matching + <i>options</i> Option bits + <i>ovector</i> Points to a vector of ints for result offsets + <i>ovecsize</i> Number of elements in the vector (a multiple of 3) + <i>jstack</i> Pointer to a JIT stack +</pre> +The allowed options are: +<pre> + PCRE_NOTBOL Subject string is not the beginning of a line + PCRE_NOTEOL Subject string is not the end of a line + PCRE_NOTEMPTY An empty string is not a valid match + PCRE_NOTEMPTY_ATSTART An empty string at the start of the subject + is not a valid match + PCRE_NO_UTF16_CHECK Do not check the subject for UTF-16 + validity (only relevant if PCRE_UTF16 + was set at compile time) + PCRE_NO_UTF32_CHECK Do not check the subject for UTF-32 + validity (only relevant if PCRE_UTF32 + was set at compile time) + PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8 + validity (only relevant if PCRE_UTF8 + was set at compile time) + PCRE_PARTIAL ) Return PCRE_ERROR_PARTIAL for a partial + PCRE_PARTIAL_SOFT ) match if no full matches are found + PCRE_PARTIAL_HARD Return PCRE_ERROR_PARTIAL for a partial match + if that is found before a full match +</pre> +However, the PCRE_NO_UTF[8|16|32]_CHECK options have no effect, as this check +is never applied. For details of partial matching, see the +<a href="pcrepartial.html"><b>pcrepartial</b></a> +page. A <b>pcre_extra</b> structure contains the following fields: +<pre> + <i>flags</i> Bits indicating which fields are set + <i>study_data</i> Opaque data from <b>pcre[16|32]_study()</b> + <i>match_limit</i> Limit on internal resource use + <i>match_limit_recursion</i> Limit on internal recursion depth + <i>callout_data</i> Opaque data passed back to callouts + <i>tables</i> Points to character tables or is NULL + <i>mark</i> For passing back a *MARK pointer + <i>executable_jit</i> Opaque data from JIT compilation +</pre> +The flag bits are PCRE_EXTRA_STUDY_DATA, PCRE_EXTRA_MATCH_LIMIT, +PCRE_EXTRA_MATCH_LIMIT_RECURSION, PCRE_EXTRA_CALLOUT_DATA, +PCRE_EXTRA_TABLES, PCRE_EXTRA_MARK and PCRE_EXTRA_EXECUTABLE_JIT. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the JIT API in the +<a href="pcrejit.html"><b>pcrejit</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_jit_stack_alloc.html b/plugins/Pcre16/docs/doc/html/pcre_jit_stack_alloc.html new file mode 100644 index 0000000000..23ba450750 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_jit_stack_alloc.html @@ -0,0 +1,55 @@ +<html> +<head> +<title>pcre_jit_stack_alloc specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_jit_stack_alloc man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>pcre_jit_stack *pcre_jit_stack_alloc(int <i>startsize</i>,</b> +<b> int <i>maxsize</i>);</b> +<br> +<br> +<b>pcre16_jit_stack *pcre16_jit_stack_alloc(int <i>startsize</i>,</b> +<b> int <i>maxsize</i>);</b> +<br> +<br> +<b>pcre32_jit_stack *pcre32_jit_stack_alloc(int <i>startsize</i>,</b> +<b> int <i>maxsize</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This function is used to create a stack for use by the code compiled by the JIT +optimization of <b>pcre[16|32]_study()</b>. The arguments are a starting size for +the stack, and a maximum size to which it is allowed to grow. The result can be +passed to the JIT run-time code by <b>pcre[16|32]_assign_jit_stack()</b>, or that +function can set up a callback for obtaining a stack. A maximum stack size of +512K to 1M should be more than enough for any pattern. For more details, see +the +<a href="pcrejit.html"><b>pcrejit</b></a> +page. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_jit_stack_free.html b/plugins/Pcre16/docs/doc/html/pcre_jit_stack_free.html new file mode 100644 index 0000000000..8bd06e4655 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_jit_stack_free.html @@ -0,0 +1,48 @@ +<html> +<head> +<title>pcre_jit_stack_free specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_jit_stack_free man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>void pcre_jit_stack_free(pcre_jit_stack *<i>stack</i>);</b> +</P> +<P> +<b>void pcre16_jit_stack_free(pcre16_jit_stack *<i>stack</i>);</b> +</P> +<P> +<b>void pcre32_jit_stack_free(pcre32_jit_stack *<i>stack</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This function is used to free a JIT stack that was created by +<b>pcre[16|32]_jit_stack_alloc()</b> when it is no longer needed. For more details, +see the +<a href="pcrejit.html"><b>pcrejit</b></a> +page. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_maketables.html b/plugins/Pcre16/docs/doc/html/pcre_maketables.html new file mode 100644 index 0000000000..3a7b5ebc4a --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_maketables.html @@ -0,0 +1,48 @@ +<html> +<head> +<title>pcre_maketables specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_maketables man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>const unsigned char *pcre_maketables(void);</b> +</P> +<P> +<b>const unsigned char *pcre16_maketables(void);</b> +</P> +<P> +<b>const unsigned char *pcre32_maketables(void);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This function builds a set of character tables for character values less than +256. These can be passed to <b>pcre[16|32]_compile()</b> to override PCRE's +internal, built-in tables (which were made by <b>pcre[16|32]_maketables()</b> when +PCRE was compiled). You might want to do this if you are using a non-standard +locale. The function yields a pointer to the tables. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_pattern_to_host_byte_order.html b/plugins/Pcre16/docs/doc/html/pcre_pattern_to_host_byte_order.html new file mode 100644 index 0000000000..1b1c80372b --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_pattern_to_host_byte_order.html @@ -0,0 +1,58 @@ +<html> +<head> +<title>pcre_pattern_to_host_byte_order specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_pattern_to_host_byte_order man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>int pcre_pattern_to_host_byte_order(pcre *<i>code</i>,</b> +<b> pcre_extra *<i>extra</i>, const unsigned char *<i>tables</i>);</b> +<br> +<br> +<b>int pcre16_pattern_to_host_byte_order(pcre16 *<i>code</i>,</b> +<b> pcre16_extra *<i>extra</i>, const unsigned char *<i>tables</i>);</b> +<br> +<br> +<b>int pcre32_pattern_to_host_byte_order(pcre32 *<i>code</i>,</b> +<b> pcre32_extra *<i>extra</i>, const unsigned char *<i>tables</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This function ensures that the bytes in 2-byte and 4-byte values in a compiled +pattern are in the correct order for the current host. It is useful when a +pattern that has been compiled on one host is transferred to another that might +have different endianness. The arguments are: +<pre> + <i>code</i> A compiled regular expression + <i>extra</i> Points to an associated <b>pcre[16|32]_extra</b> structure, + or is NULL + <i>tables</i> Pointer to character tables, or NULL to + set the built-in default +</pre> +The result is 0 for success, a negative PCRE_ERROR_xxx value otherwise. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_refcount.html b/plugins/Pcre16/docs/doc/html/pcre_refcount.html new file mode 100644 index 0000000000..bfb92e6d8a --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_refcount.html @@ -0,0 +1,51 @@ +<html> +<head> +<title>pcre_refcount specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_refcount man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>int pcre_refcount(pcre *<i>code</i>, int <i>adjust</i>);</b> +</P> +<P> +<b>int pcre16_refcount(pcre16 *<i>code</i>, int <i>adjust</i>);</b> +</P> +<P> +<b>int pcre32_refcount(pcre32 *<i>code</i>, int <i>adjust</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This function is used to maintain a reference count inside a data block that +contains a compiled pattern. Its arguments are: +<pre> + <i>code</i> Compiled regular expression + <i>adjust</i> Adjustment to reference value +</pre> +The yield of the function is the adjusted reference value, which is constrained +to lie between 0 and 65535. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_study.html b/plugins/Pcre16/docs/doc/html/pcre_study.html new file mode 100644 index 0000000000..af82f11409 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_study.html @@ -0,0 +1,68 @@ +<html> +<head> +<title>pcre_study specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_study man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>pcre_extra *pcre_study(const pcre *<i>code</i>, int <i>options</i>,</b> +<b> const char **<i>errptr</i>);</b> +<br> +<br> +<b>pcre16_extra *pcre16_study(const pcre16 *<i>code</i>, int <i>options</i>,</b> +<b> const char **<i>errptr</i>);</b> +<br> +<br> +<b>pcre32_extra *pcre32_study(const pcre32 *<i>code</i>, int <i>options</i>,</b> +<b> const char **<i>errptr</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This function studies a compiled pattern, to see if additional information can +be extracted that might speed up matching. Its arguments are: +<pre> + <i>code</i> A compiled regular expression + <i>options</i> Options for <b>pcre[16|32]_study()</b> + <i>errptr</i> Where to put an error message +</pre> +If the function succeeds, it returns a value that can be passed to +<b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> via their <i>extra</i> +arguments. +</P> +<P> +If the function returns NULL, either it could not find any additional +information, or there was an error. You can tell the difference by looking at +the error value. It is NULL in first case. +</P> +<P> +The only option is PCRE_STUDY_JIT_COMPILE. It requests just-in-time compilation +if possible. If PCRE has been compiled without JIT support, this option is +ignored. See the +<a href="pcrejit.html"><b>pcrejit</b></a> +page for further details. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_utf16_to_host_byte_order.html b/plugins/Pcre16/docs/doc/html/pcre_utf16_to_host_byte_order.html new file mode 100644 index 0000000000..18e7788f68 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_utf16_to_host_byte_order.html @@ -0,0 +1,57 @@ +<html> +<head> +<title>pcre_utf16_to_host_byte_order specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_utf16_to_host_byte_order man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>int pcre16_utf16_to_host_byte_order(PCRE_UCHAR16 *<i>output</i>,</b> +<b> PCRE_SPTR16 <i>input</i>, int <i>length</i>, int *<i>host_byte_order</i>,</b> +<b> int <i>keep_boms</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This function, which exists only in the 16-bit library, converts a UTF-16 +string to the correct order for the current host, taking account of any byte +order marks (BOMs) within the string. Its arguments are: +<pre> + <i>output</i> pointer to output buffer, may be the same as <i>input</i> + <i>input</i> pointer to input buffer + <i>length</i> number of 16-bit units in the input, or negative for + a zero-terminated string + <i>host_byte_order</i> a NULL value or a non-zero value pointed to means + start in host byte order + <i>keep_boms</i> if non-zero, BOMs are copied to the output string +</pre> +The result of the function is the number of 16-bit units placed into the output +buffer, including the zero terminator if the string was zero-terminated. +</P> +<P> +If <i>host_byte_order</i> is not NULL, it is set to indicate the byte order that +is current at the end of the string. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_utf32_to_host_byte_order.html b/plugins/Pcre16/docs/doc/html/pcre_utf32_to_host_byte_order.html new file mode 100644 index 0000000000..772ae40cd9 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_utf32_to_host_byte_order.html @@ -0,0 +1,57 @@ +<html> +<head> +<title>pcre_utf32_to_host_byte_order specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_utf32_to_host_byte_order man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>int pcre32_utf32_to_host_byte_order(PCRE_UCHAR32 *<i>output</i>,</b> +<b> PCRE_SPTR32 <i>input</i>, int <i>length</i>, int *<i>host_byte_order</i>,</b> +<b> int <i>keep_boms</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This function, which exists only in the 32-bit library, converts a UTF-32 +string to the correct order for the current host, taking account of any byte +order marks (BOMs) within the string. Its arguments are: +<pre> + <i>output</i> pointer to output buffer, may be the same as <i>input</i> + <i>input</i> pointer to input buffer + <i>length</i> number of 32-bit units in the input, or negative for + a zero-terminated string + <i>host_byte_order</i> a NULL value or a non-zero value pointed to means + start in host byte order + <i>keep_boms</i> if non-zero, BOMs are copied to the output string +</pre> +The result of the function is the number of 32-bit units placed into the output +buffer, including the zero terminator if the string was zero-terminated. +</P> +<P> +If <i>host_byte_order</i> is not NULL, it is set to indicate the byte order that +is current at the end of the string. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcre_version.html b/plugins/Pcre16/docs/doc/html/pcre_version.html new file mode 100644 index 0000000000..d33e718955 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcre_version.html @@ -0,0 +1,46 @@ +<html> +<head> +<title>pcre_version specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_version man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>const char *pcre_version(void);</b> +</P> +<P> +<b>const char *pcre16_version(void);</b> +</P> +<P> +<b>const char *pcre32_version(void);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This function (even in the 16-bit and 32-bit libraries) returns a +zero-terminated, 8-bit character string that gives the version number of the +PCRE library and the date of its release. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcreapi.html b/plugins/Pcre16/docs/doc/html/pcreapi.html new file mode 100644 index 0000000000..b401ecc76d --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcreapi.html @@ -0,0 +1,2922 @@ +<html> +<head> +<title>pcreapi specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcreapi man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<ul> +<li><a name="TOC1" href="#SEC1">PCRE NATIVE API BASIC FUNCTIONS</a> +<li><a name="TOC2" href="#SEC2">PCRE NATIVE API STRING EXTRACTION FUNCTIONS</a> +<li><a name="TOC3" href="#SEC3">PCRE NATIVE API AUXILIARY FUNCTIONS</a> +<li><a name="TOC4" href="#SEC4">PCRE NATIVE API INDIRECTED FUNCTIONS</a> +<li><a name="TOC5" href="#SEC5">PCRE 8-BIT, 16-BIT, AND 32-BIT LIBRARIES</a> +<li><a name="TOC6" href="#SEC6">PCRE API OVERVIEW</a> +<li><a name="TOC7" href="#SEC7">NEWLINES</a> +<li><a name="TOC8" href="#SEC8">MULTITHREADING</a> +<li><a name="TOC9" href="#SEC9">SAVING PRECOMPILED PATTERNS FOR LATER USE</a> +<li><a name="TOC10" href="#SEC10">CHECKING BUILD-TIME OPTIONS</a> +<li><a name="TOC11" href="#SEC11">COMPILING A PATTERN</a> +<li><a name="TOC12" href="#SEC12">COMPILATION ERROR CODES</a> +<li><a name="TOC13" href="#SEC13">STUDYING A PATTERN</a> +<li><a name="TOC14" href="#SEC14">LOCALE SUPPORT</a> +<li><a name="TOC15" href="#SEC15">INFORMATION ABOUT A PATTERN</a> +<li><a name="TOC16" href="#SEC16">REFERENCE COUNTS</a> +<li><a name="TOC17" href="#SEC17">MATCHING A PATTERN: THE TRADITIONAL FUNCTION</a> +<li><a name="TOC18" href="#SEC18">EXTRACTING CAPTURED SUBSTRINGS BY NUMBER</a> +<li><a name="TOC19" href="#SEC19">EXTRACTING CAPTURED SUBSTRINGS BY NAME</a> +<li><a name="TOC20" href="#SEC20">DUPLICATE SUBPATTERN NAMES</a> +<li><a name="TOC21" href="#SEC21">FINDING ALL POSSIBLE MATCHES</a> +<li><a name="TOC22" href="#SEC22">OBTAINING AN ESTIMATE OF STACK USAGE</a> +<li><a name="TOC23" href="#SEC23">MATCHING A PATTERN: THE ALTERNATIVE FUNCTION</a> +<li><a name="TOC24" href="#SEC24">SEE ALSO</a> +<li><a name="TOC25" href="#SEC25">AUTHOR</a> +<li><a name="TOC26" href="#SEC26">REVISION</a> +</ul> +<P> +<b>#include <pcre.h></b> +</P> +<br><a name="SEC1" href="#TOC1">PCRE NATIVE API BASIC FUNCTIONS</a><br> +<P> +<b>pcre *pcre_compile(const char *<i>pattern</i>, int <i>options</i>,</b> +<b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b> +<b> const unsigned char *<i>tableptr</i>);</b> +<br> +<br> +<b>pcre *pcre_compile2(const char *<i>pattern</i>, int <i>options</i>,</b> +<b> int *<i>errorcodeptr</i>,</b> +<b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b> +<b> const unsigned char *<i>tableptr</i>);</b> +<br> +<br> +<b>pcre_extra *pcre_study(const pcre *<i>code</i>, int <i>options</i>,</b> +<b> const char **<i>errptr</i>);</b> +<br> +<br> +<b>void pcre_free_study(pcre_extra *<i>extra</i>);</b> +<br> +<br> +<b>int pcre_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b> +<b> const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b> +<br> +<br> +<b>int pcre_dfa_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b> +<b> const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b> +<b> int *<i>workspace</i>, int <i>wscount</i>);</b> +</P> +<br><a name="SEC2" href="#TOC1">PCRE NATIVE API STRING EXTRACTION FUNCTIONS</a><br> +<P> +<b>int pcre_copy_named_substring(const pcre *<i>code</i>,</b> +<b> const char *<i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, const char *<i>stringname</i>,</b> +<b> char *<i>buffer</i>, int <i>buffersize</i>);</b> +<br> +<br> +<b>int pcre_copy_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, int <i>stringnumber</i>, char *<i>buffer</i>,</b> +<b> int <i>buffersize</i>);</b> +<br> +<br> +<b>int pcre_get_named_substring(const pcre *<i>code</i>,</b> +<b> const char *<i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, const char *<i>stringname</i>,</b> +<b> const char **<i>stringptr</i>);</b> +<br> +<br> +<b>int pcre_get_stringnumber(const pcre *<i>code</i>,</b> +<b> const char *<i>name</i>);</b> +<br> +<br> +<b>int pcre_get_stringtable_entries(const pcre *<i>code</i>,</b> +<b> const char *<i>name</i>, char **<i>first</i>, char **<i>last</i>);</b> +<br> +<br> +<b>int pcre_get_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, int <i>stringnumber</i>,</b> +<b> const char **<i>stringptr</i>);</b> +<br> +<br> +<b>int pcre_get_substring_list(const char *<i>subject</i>,</b> +<b> int *<i>ovector</i>, int <i>stringcount</i>, const char ***<i>listptr</i>);</b> +<br> +<br> +<b>void pcre_free_substring(const char *<i>stringptr</i>);</b> +<br> +<br> +<b>void pcre_free_substring_list(const char **<i>stringptr</i>);</b> +</P> +<br><a name="SEC3" href="#TOC1">PCRE NATIVE API AUXILIARY FUNCTIONS</a><br> +<P> +<b>int pcre_jit_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b> +<b> const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b> +<b> pcre_jit_stack *<i>jstack</i>);</b> +<br> +<br> +<b>pcre_jit_stack *pcre_jit_stack_alloc(int <i>startsize</i>, int <i>maxsize</i>);</b> +<br> +<br> +<b>void pcre_jit_stack_free(pcre_jit_stack *<i>stack</i>);</b> +<br> +<br> +<b>void pcre_assign_jit_stack(pcre_extra *<i>extra</i>,</b> +<b> pcre_jit_callback <i>callback</i>, void *<i>data</i>);</b> +<br> +<br> +<b>const unsigned char *pcre_maketables(void);</b> +<br> +<br> +<b>int pcre_fullinfo(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b> +<b> int <i>what</i>, void *<i>where</i>);</b> +<br> +<br> +<b>int pcre_refcount(pcre *<i>code</i>, int <i>adjust</i>);</b> +<br> +<br> +<b>int pcre_config(int <i>what</i>, void *<i>where</i>);</b> +<br> +<br> +<b>const char *pcre_version(void);</b> +<br> +<br> +<b>int pcre_pattern_to_host_byte_order(pcre *<i>code</i>,</b> +<b> pcre_extra *<i>extra</i>, const unsigned char *<i>tables</i>);</b> +</P> +<br><a name="SEC4" href="#TOC1">PCRE NATIVE API INDIRECTED FUNCTIONS</a><br> +<P> +<b>void *(*pcre_malloc)(size_t);</b> +<br> +<br> +<b>void (*pcre_free)(void *);</b> +<br> +<br> +<b>void *(*pcre_stack_malloc)(size_t);</b> +<br> +<br> +<b>void (*pcre_stack_free)(void *);</b> +<br> +<br> +<b>int (*pcre_callout)(pcre_callout_block *);</b> +<br> +<br> +<b>int (*pcre_stack_guard)(void);</b> +</P> +<br><a name="SEC5" href="#TOC1">PCRE 8-BIT, 16-BIT, AND 32-BIT LIBRARIES</a><br> +<P> +As well as support for 8-bit character strings, PCRE also supports 16-bit +strings (from release 8.30) and 32-bit strings (from release 8.32), by means of +two additional libraries. They can be built as well as, or instead of, the +8-bit library. To avoid too much complication, this document describes the +8-bit versions of the functions, with only occasional references to the 16-bit +and 32-bit libraries. +</P> +<P> +The 16-bit and 32-bit functions operate in the same way as their 8-bit +counterparts; they just use different data types for their arguments and +results, and their names start with <b>pcre16_</b> or <b>pcre32_</b> instead of +<b>pcre_</b>. For every option that has UTF8 in its name (for example, +PCRE_UTF8), there are corresponding 16-bit and 32-bit names with UTF8 replaced +by UTF16 or UTF32, respectively. This facility is in fact just cosmetic; the +16-bit and 32-bit option names define the same bit values. +</P> +<P> +References to bytes and UTF-8 in this document should be read as references to +16-bit data units and UTF-16 when using the 16-bit library, or 32-bit data +units and UTF-32 when using the 32-bit library, unless specified otherwise. +More details of the specific differences for the 16-bit and 32-bit libraries +are given in the +<a href="pcre16.html"><b>pcre16</b></a> +and +<a href="pcre32.html"><b>pcre32</b></a> +pages. +</P> +<br><a name="SEC6" href="#TOC1">PCRE API OVERVIEW</a><br> +<P> +PCRE has its own native API, which is described in this document. There are +also some wrapper functions (for the 8-bit library only) that correspond to the +POSIX regular expression API, but they do not give access to all the +functionality. They are described in the +<a href="pcreposix.html"><b>pcreposix</b></a> +documentation. Both of these APIs define a set of C function calls. A C++ +wrapper (again for the 8-bit library only) is also distributed with PCRE. It is +documented in the +<a href="pcrecpp.html"><b>pcrecpp</b></a> +page. +</P> +<P> +The native API C function prototypes are defined in the header file +<b>pcre.h</b>, and on Unix-like systems the (8-bit) library itself is called +<b>libpcre</b>. It can normally be accessed by adding <b>-lpcre</b> to the +command for linking an application that uses PCRE. The header file defines the +macros PCRE_MAJOR and PCRE_MINOR to contain the major and minor release numbers +for the library. Applications can use these to include support for different +releases of PCRE. +</P> +<P> +In a Windows environment, if you want to statically link an application program +against a non-dll <b>pcre.a</b> file, you must define PCRE_STATIC before +including <b>pcre.h</b> or <b>pcrecpp.h</b>, because otherwise the +<b>pcre_malloc()</b> and <b>pcre_free()</b> exported functions will be declared +<b>__declspec(dllimport)</b>, with unwanted results. +</P> +<P> +The functions <b>pcre_compile()</b>, <b>pcre_compile2()</b>, <b>pcre_study()</b>, +and <b>pcre_exec()</b> are used for compiling and matching regular expressions +in a Perl-compatible manner. A sample program that demonstrates the simplest +way of using them is provided in the file called <i>pcredemo.c</i> in the PCRE +source distribution. A listing of this program is given in the +<a href="pcredemo.html"><b>pcredemo</b></a> +documentation, and the +<a href="pcresample.html"><b>pcresample</b></a> +documentation describes how to compile and run it. +</P> +<P> +Just-in-time compiler support is an optional feature of PCRE that can be built +in appropriate hardware environments. It greatly speeds up the matching +performance of many patterns. Simple programs can easily request that it be +used if available, by setting an option that is ignored when it is not +relevant. More complicated programs might need to make use of the functions +<b>pcre_jit_stack_alloc()</b>, <b>pcre_jit_stack_free()</b>, and +<b>pcre_assign_jit_stack()</b> in order to control the JIT code's memory usage. +</P> +<P> +From release 8.32 there is also a direct interface for JIT execution, which +gives improved performance. The JIT-specific functions are discussed in the +<a href="pcrejit.html"><b>pcrejit</b></a> +documentation. +</P> +<P> +A second matching function, <b>pcre_dfa_exec()</b>, which is not +Perl-compatible, is also provided. This uses a different algorithm for the +matching. The alternative algorithm finds all possible matches (at a given +point in the subject), and scans the subject just once (unless there are +lookbehind assertions). However, this algorithm does not return captured +substrings. A description of the two matching algorithms and their advantages +and disadvantages is given in the +<a href="pcrematching.html"><b>pcrematching</b></a> +documentation. +</P> +<P> +In addition to the main compiling and matching functions, there are convenience +functions for extracting captured substrings from a subject string that is +matched by <b>pcre_exec()</b>. They are: +<pre> + <b>pcre_copy_substring()</b> + <b>pcre_copy_named_substring()</b> + <b>pcre_get_substring()</b> + <b>pcre_get_named_substring()</b> + <b>pcre_get_substring_list()</b> + <b>pcre_get_stringnumber()</b> + <b>pcre_get_stringtable_entries()</b> +</pre> +<b>pcre_free_substring()</b> and <b>pcre_free_substring_list()</b> are also +provided, to free the memory used for extracted strings. +</P> +<P> +The function <b>pcre_maketables()</b> is used to build a set of character tables +in the current locale for passing to <b>pcre_compile()</b>, <b>pcre_exec()</b>, +or <b>pcre_dfa_exec()</b>. This is an optional facility that is provided for +specialist use. Most commonly, no special tables are passed, in which case +internal tables that are generated when PCRE is built are used. +</P> +<P> +The function <b>pcre_fullinfo()</b> is used to find out information about a +compiled pattern. The function <b>pcre_version()</b> returns a pointer to a +string containing the version of PCRE and its date of release. +</P> +<P> +The function <b>pcre_refcount()</b> maintains a reference count in a data block +containing a compiled pattern. This is provided for the benefit of +object-oriented applications. +</P> +<P> +The global variables <b>pcre_malloc</b> and <b>pcre_free</b> initially contain +the entry points of the standard <b>malloc()</b> and <b>free()</b> functions, +respectively. PCRE calls the memory management functions via these variables, +so a calling program can replace them if it wishes to intercept the calls. This +should be done before calling any PCRE functions. +</P> +<P> +The global variables <b>pcre_stack_malloc</b> and <b>pcre_stack_free</b> are also +indirections to memory management functions. These special functions are used +only when PCRE is compiled to use the heap for remembering data, instead of +recursive function calls, when running the <b>pcre_exec()</b> function. See the +<a href="pcrebuild.html"><b>pcrebuild</b></a> +documentation for details of how to do this. It is a non-standard way of +building PCRE, for use in environments that have limited stacks. Because of the +greater use of memory management, it runs more slowly. Separate functions are +provided so that special-purpose external code can be used for this case. When +used, these functions are always called in a stack-like manner (last obtained, +first freed), and always for memory blocks of the same size. There is a +discussion about PCRE's stack usage in the +<a href="pcrestack.html"><b>pcrestack</b></a> +documentation. +</P> +<P> +The global variable <b>pcre_callout</b> initially contains NULL. It can be set +by the caller to a "callout" function, which PCRE will then call at specified +points during a matching operation. Details are given in the +<a href="pcrecallout.html"><b>pcrecallout</b></a> +documentation. +</P> +<P> +The global variable <b>pcre_stack_guard</b> initially contains NULL. It can be +set by the caller to a function that is called by PCRE whenever it starts +to compile a parenthesized part of a pattern. When parentheses are nested, PCRE +uses recursive function calls, which use up the system stack. This function is +provided so that applications with restricted stacks can force a compilation +error if the stack runs out. The function should return zero if all is well, or +non-zero to force an error. +<a name="newlines"></a></P> +<br><a name="SEC7" href="#TOC1">NEWLINES</a><br> +<P> +PCRE supports five different conventions for indicating line breaks in +strings: a single CR (carriage return) character, a single LF (linefeed) +character, the two-character sequence CRLF, any of the three preceding, or any +Unicode newline sequence. The Unicode newline sequences are the three just +mentioned, plus the single characters VT (vertical tab, U+000B), FF (form feed, +U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS +(paragraph separator, U+2029). +</P> +<P> +Each of the first three conventions is used by at least one operating system as +its standard newline sequence. When PCRE is built, a default can be specified. +The default default is LF, which is the Unix standard. When PCRE is run, the +default can be overridden, either when a pattern is compiled, or when it is +matched. +</P> +<P> +At compile time, the newline convention can be specified by the <i>options</i> +argument of <b>pcre_compile()</b>, or it can be specified by special text at the +start of the pattern itself; this overrides any other settings. See the +<a href="pcrepattern.html"><b>pcrepattern</b></a> +page for details of the special character sequences. +</P> +<P> +In the PCRE documentation the word "newline" is used to mean "the character or +pair of characters that indicate a line break". The choice of newline +convention affects the handling of the dot, circumflex, and dollar +metacharacters, the handling of #-comments in /x mode, and, when CRLF is a +recognized line ending sequence, the match position advancement for a +non-anchored pattern. There is more detail about this in the +<a href="#execoptions">section on <b>pcre_exec()</b> options</a> +below. +</P> +<P> +The choice of newline convention does not affect the interpretation of +the \n or \r escape sequences, nor does it affect what \R matches, which is +controlled in a similar way, but by separate options. +</P> +<br><a name="SEC8" href="#TOC1">MULTITHREADING</a><br> +<P> +The PCRE functions can be used in multi-threading applications, with the +proviso that the memory management functions pointed to by <b>pcre_malloc</b>, +<b>pcre_free</b>, <b>pcre_stack_malloc</b>, and <b>pcre_stack_free</b>, and the +callout and stack-checking functions pointed to by <b>pcre_callout</b> and +<b>pcre_stack_guard</b>, are shared by all threads. +</P> +<P> +The compiled form of a regular expression is not altered during matching, so +the same compiled pattern can safely be used by several threads at once. +</P> +<P> +If the just-in-time optimization feature is being used, it needs separate +memory stack areas for each thread. See the +<a href="pcrejit.html"><b>pcrejit</b></a> +documentation for more details. +</P> +<br><a name="SEC9" href="#TOC1">SAVING PRECOMPILED PATTERNS FOR LATER USE</a><br> +<P> +The compiled form of a regular expression can be saved and re-used at a later +time, possibly by a different program, and even on a host other than the one on +which it was compiled. Details are given in the +<a href="pcreprecompile.html"><b>pcreprecompile</b></a> +documentation, which includes a description of the +<b>pcre_pattern_to_host_byte_order()</b> function. However, compiling a regular +expression with one version of PCRE for use with a different version is not +guaranteed to work and may cause crashes. +</P> +<br><a name="SEC10" href="#TOC1">CHECKING BUILD-TIME OPTIONS</a><br> +<P> +<b>int pcre_config(int <i>what</i>, void *<i>where</i>);</b> +</P> +<P> +The function <b>pcre_config()</b> makes it possible for a PCRE client to +discover which optional features have been compiled into the PCRE library. The +<a href="pcrebuild.html"><b>pcrebuild</b></a> +documentation has more details about these optional features. +</P> +<P> +The first argument for <b>pcre_config()</b> is an integer, specifying which +information is required; the second argument is a pointer to a variable into +which the information is placed. The returned value is zero on success, or the +negative error code PCRE_ERROR_BADOPTION if the value in the first argument is +not recognized. The following information is available: +<pre> + PCRE_CONFIG_UTF8 +</pre> +The output is an integer that is set to one if UTF-8 support is available; +otherwise it is set to zero. This value should normally be given to the 8-bit +version of this function, <b>pcre_config()</b>. If it is given to the 16-bit +or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION. +<pre> + PCRE_CONFIG_UTF16 +</pre> +The output is an integer that is set to one if UTF-16 support is available; +otherwise it is set to zero. This value should normally be given to the 16-bit +version of this function, <b>pcre16_config()</b>. If it is given to the 8-bit +or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION. +<pre> + PCRE_CONFIG_UTF32 +</pre> +The output is an integer that is set to one if UTF-32 support is available; +otherwise it is set to zero. This value should normally be given to the 32-bit +version of this function, <b>pcre32_config()</b>. If it is given to the 8-bit +or 16-bit version of this function, the result is PCRE_ERROR_BADOPTION. +<pre> + PCRE_CONFIG_UNICODE_PROPERTIES +</pre> +The output is an integer that is set to one if support for Unicode character +properties is available; otherwise it is set to zero. +<pre> + PCRE_CONFIG_JIT +</pre> +The output is an integer that is set to one if support for just-in-time +compiling is available; otherwise it is set to zero. +<pre> + PCRE_CONFIG_JITTARGET +</pre> +The output is a pointer to a zero-terminated "const char *" string. If JIT +support is available, the string contains the name of the architecture for +which the JIT compiler is configured, for example "x86 32bit (little endian + +unaligned)". If JIT support is not available, the result is NULL. +<pre> + PCRE_CONFIG_NEWLINE +</pre> +The output is an integer whose value specifies the default character sequence +that is recognized as meaning "newline". The values that are supported in +ASCII/Unicode environments are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for +ANYCRLF, and -1 for ANY. In EBCDIC environments, CR, ANYCRLF, and ANY yield the +same values. However, the value for LF is normally 21, though some EBCDIC +environments use 37. The corresponding values for CRLF are 3349 and 3365. The +default should normally correspond to the standard sequence for your operating +system. +<pre> + PCRE_CONFIG_BSR +</pre> +The output is an integer whose value indicates what character sequences the \R +escape sequence matches by default. A value of 0 means that \R matches any +Unicode line ending sequence; a value of 1 means that \R matches only CR, LF, +or CRLF. The default can be overridden when a pattern is compiled or matched. +<pre> + PCRE_CONFIG_LINK_SIZE +</pre> +The output is an integer that contains the number of bytes used for internal +linkage in compiled regular expressions. For the 8-bit library, the value can +be 2, 3, or 4. For the 16-bit library, the value is either 2 or 4 and is still +a number of bytes. For the 32-bit library, the value is either 2 or 4 and is +still a number of bytes. The default value of 2 is sufficient for all but the +most massive patterns, since it allows the compiled pattern to be up to 64K in +size. Larger values allow larger regular expressions to be compiled, at the +expense of slower matching. +<pre> + PCRE_CONFIG_POSIX_MALLOC_THRESHOLD +</pre> +The output is an integer that contains the threshold above which the POSIX +interface uses <b>malloc()</b> for output vectors. Further details are given in +the +<a href="pcreposix.html"><b>pcreposix</b></a> +documentation. +<pre> + PCRE_CONFIG_PARENS_LIMIT +</pre> +The output is a long integer that gives the maximum depth of nesting of +parentheses (of any kind) in a pattern. This limit is imposed to cap the amount +of system stack used when a pattern is compiled. It is specified when PCRE is +built; the default is 250. This limit does not take into account the stack that +may already be used by the calling application. For finer control over +compilation stack usage, you can set a pointer to an external checking function +in <b>pcre_stack_guard</b>. +<pre> + PCRE_CONFIG_MATCH_LIMIT +</pre> +The output is a long integer that gives the default limit for the number of +internal matching function calls in a <b>pcre_exec()</b> execution. Further +details are given with <b>pcre_exec()</b> below. +<pre> + PCRE_CONFIG_MATCH_LIMIT_RECURSION +</pre> +The output is a long integer that gives the default limit for the depth of +recursion when calling the internal matching function in a <b>pcre_exec()</b> +execution. Further details are given with <b>pcre_exec()</b> below. +<pre> + PCRE_CONFIG_STACKRECURSE +</pre> +The output is an integer that is set to one if internal recursion when running +<b>pcre_exec()</b> is implemented by recursive function calls that use the stack +to remember their state. This is the usual way that PCRE is compiled. The +output is zero if PCRE was compiled to use blocks of data on the heap instead +of recursive function calls. In this case, <b>pcre_stack_malloc</b> and +<b>pcre_stack_free</b> are called to manage memory blocks on the heap, thus +avoiding the use of the stack. +</P> +<br><a name="SEC11" href="#TOC1">COMPILING A PATTERN</a><br> +<P> +<b>pcre *pcre_compile(const char *<i>pattern</i>, int <i>options</i>,</b> +<b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b> +<b> const unsigned char *<i>tableptr</i>);</b> +<br> +<br> +<b>pcre *pcre_compile2(const char *<i>pattern</i>, int <i>options</i>,</b> +<b> int *<i>errorcodeptr</i>,</b> +<b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b> +<b> const unsigned char *<i>tableptr</i>);</b> +</P> +<P> +Either of the functions <b>pcre_compile()</b> or <b>pcre_compile2()</b> can be +called to compile a pattern into an internal form. The only difference between +the two interfaces is that <b>pcre_compile2()</b> has an additional argument, +<i>errorcodeptr</i>, via which a numerical error code can be returned. To avoid +too much repetition, we refer just to <b>pcre_compile()</b> below, but the +information applies equally to <b>pcre_compile2()</b>. +</P> +<P> +The pattern is a C string terminated by a binary zero, and is passed in the +<i>pattern</i> argument. A pointer to a single block of memory that is obtained +via <b>pcre_malloc</b> is returned. This contains the compiled code and related +data. The <b>pcre</b> type is defined for the returned block; this is a typedef +for a structure whose contents are not externally defined. It is up to the +caller to free the memory (via <b>pcre_free</b>) when it is no longer required. +</P> +<P> +Although the compiled code of a PCRE regex is relocatable, that is, it does not +depend on memory location, the complete <b>pcre</b> data block is not +fully relocatable, because it may contain a copy of the <i>tableptr</i> +argument, which is an address (see below). +</P> +<P> +The <i>options</i> argument contains various bit settings that affect the +compilation. It should be zero if no options are required. The available +options are described below. Some of them (in particular, those that are +compatible with Perl, but some others as well) can also be set and unset from +within the pattern (see the detailed description in the +<a href="pcrepattern.html"><b>pcrepattern</b></a> +documentation). For those options that can be different in different parts of +the pattern, the contents of the <i>options</i> argument specifies their +settings at the start of compilation and execution. The PCRE_ANCHORED, +PCRE_BSR_<i>xxx</i>, PCRE_NEWLINE_<i>xxx</i>, PCRE_NO_UTF8_CHECK, and +PCRE_NO_START_OPTIMIZE options can be set at the time of matching as well as at +compile time. +</P> +<P> +If <i>errptr</i> is NULL, <b>pcre_compile()</b> returns NULL immediately. +Otherwise, if compilation of a pattern fails, <b>pcre_compile()</b> returns +NULL, and sets the variable pointed to by <i>errptr</i> to point to a textual +error message. This is a static string that is part of the library. You must +not try to free it. Normally, the offset from the start of the pattern to the +data unit that was being processed when the error was discovered is placed in +the variable pointed to by <i>erroffset</i>, which must not be NULL (if it is, +an immediate error is given). However, for an invalid UTF-8 or UTF-16 string, +the offset is that of the first data unit of the failing character. +</P> +<P> +Some errors are not detected until the whole pattern has been scanned; in these +cases, the offset passed back is the length of the pattern. Note that the +offset is in data units, not characters, even in a UTF mode. It may sometimes +point into the middle of a UTF-8 or UTF-16 character. +</P> +<P> +If <b>pcre_compile2()</b> is used instead of <b>pcre_compile()</b>, and the +<i>errorcodeptr</i> argument is not NULL, a non-zero error code number is +returned via this argument in the event of an error. This is in addition to the +textual error message. Error codes and messages are listed below. +</P> +<P> +If the final argument, <i>tableptr</i>, is NULL, PCRE uses a default set of +character tables that are built when PCRE is compiled, using the default C +locale. Otherwise, <i>tableptr</i> must be an address that is the result of a +call to <b>pcre_maketables()</b>. This value is stored with the compiled +pattern, and used again by <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b> when the +pattern is matched. For more discussion, see the section on locale support +below. +</P> +<P> +This code fragment shows a typical straightforward call to <b>pcre_compile()</b>: +<pre> + pcre *re; + const char *error; + int erroffset; + re = pcre_compile( + "^A.*Z", /* the pattern */ + 0, /* default options */ + &error, /* for error message */ + &erroffset, /* for error offset */ + NULL); /* use default character tables */ +</pre> +The following names for option bits are defined in the <b>pcre.h</b> header +file: +<pre> + PCRE_ANCHORED +</pre> +If this bit is set, the pattern is forced to be "anchored", that is, it is +constrained to match only at the first matching point in the string that is +being searched (the "subject string"). This effect can also be achieved by +appropriate constructs in the pattern itself, which is the only way to do it in +Perl. +<pre> + PCRE_AUTO_CALLOUT +</pre> +If this bit is set, <b>pcre_compile()</b> automatically inserts callout items, +all with number 255, before each pattern item. For discussion of the callout +facility, see the +<a href="pcrecallout.html"><b>pcrecallout</b></a> +documentation. +<pre> + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE +</pre> +These options (which are mutually exclusive) control what the \R escape +sequence matches. The choice is either to match only CR, LF, or CRLF, or to +match any Unicode newline sequence. The default is specified when PCRE is +built. It can be overridden from within the pattern, or by setting an option +when a compiled pattern is matched. +<pre> + PCRE_CASELESS +</pre> +If this bit is set, letters in the pattern match both upper and lower case +letters. It is equivalent to Perl's /i option, and it can be changed within a +pattern by a (?i) option setting. In UTF-8 mode, PCRE always understands the +concept of case for characters whose values are less than 128, so caseless +matching is always possible. For characters with higher values, the concept of +case is supported if PCRE is compiled with Unicode property support, but not +otherwise. If you want to use caseless matching for characters 128 and above, +you must ensure that PCRE is compiled with Unicode property support as well as +with UTF-8 support. +<pre> + PCRE_DOLLAR_ENDONLY +</pre> +If this bit is set, a dollar metacharacter in the pattern matches only at the +end of the subject string. Without this option, a dollar also matches +immediately before a newline at the end of the string (but not before any other +newlines). The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set. +There is no equivalent to this option in Perl, and no way to set it within a +pattern. +<pre> + PCRE_DOTALL +</pre> +If this bit is set, a dot metacharacter in the pattern matches a character of +any value, including one that indicates a newline. However, it only ever +matches one character, even if newlines are coded as CRLF. Without this option, +a dot does not match when the current position is at a newline. This option is +equivalent to Perl's /s option, and it can be changed within a pattern by a +(?s) option setting. A negative class such as [^a] always matches newline +characters, independent of the setting of this option. +<pre> + PCRE_DUPNAMES +</pre> +If this bit is set, names used to identify capturing subpatterns need not be +unique. This can be helpful for certain types of pattern when it is known that +only one instance of the named subpattern can ever be matched. There are more +details of named subpatterns below; see also the +<a href="pcrepattern.html"><b>pcrepattern</b></a> +documentation. +<pre> + PCRE_EXTENDED +</pre> +If this bit is set, most white space characters in the pattern are totally +ignored except when escaped or inside a character class. However, white space +is not allowed within sequences such as (?> that introduce various +parenthesized subpatterns, nor within a numerical quantifier such as {1,3}. +However, ignorable white space is permitted between an item and a following +quantifier and between a quantifier and a following + that indicates +possessiveness. +</P> +<P> +White space did not used to include the VT character (code 11), because Perl +did not treat this character as white space. However, Perl changed at release +5.18, so PCRE followed at release 8.34, and VT is now treated as white space. +</P> +<P> +PCRE_EXTENDED also causes characters between an unescaped # outside a character +class and the next newline, inclusive, to be ignored. PCRE_EXTENDED is +equivalent to Perl's /x option, and it can be changed within a pattern by a +(?x) option setting. +</P> +<P> +Which characters are interpreted as newlines is controlled by the options +passed to <b>pcre_compile()</b> or by a special sequence at the start of the +pattern, as described in the section entitled +<a href="pcrepattern.html#newlines">"Newline conventions"</a> +in the <b>pcrepattern</b> documentation. Note that the end of this type of +comment is a literal newline sequence in the pattern; escape sequences that +happen to represent a newline do not count. +</P> +<P> +This option makes it possible to include comments inside complicated patterns. +Note, however, that this applies only to data characters. White space characters +may never appear within special character sequences in a pattern, for example +within the sequence (?( that introduces a conditional subpattern. +<pre> + PCRE_EXTRA +</pre> +This option was invented in order to turn on additional functionality of PCRE +that is incompatible with Perl, but it is currently of very little use. When +set, any backslash in a pattern that is followed by a letter that has no +special meaning causes an error, thus reserving these combinations for future +expansion. By default, as in Perl, a backslash followed by a letter with no +special meaning is treated as a literal. (Perl can, however, be persuaded to +give an error for this, by running it with the -w option.) There are at present +no other features controlled by this option. It can also be set by a (?X) +option setting within a pattern. +<pre> + PCRE_FIRSTLINE +</pre> +If this option is set, an unanchored pattern is required to match before or at +the first newline in the subject string, though the matched text may continue +over the newline. +<pre> + PCRE_JAVASCRIPT_COMPAT +</pre> +If this option is set, PCRE's behaviour is changed in some ways so that it is +compatible with JavaScript rather than Perl. The changes are as follows: +</P> +<P> +(1) A lone closing square bracket in a pattern causes a compile-time error, +because this is illegal in JavaScript (by default it is treated as a data +character). Thus, the pattern AB]CD becomes illegal when this option is set. +</P> +<P> +(2) At run time, a back reference to an unset subpattern group matches an empty +string (by default this causes the current matching alternative to fail). A +pattern such as (\1)(a) succeeds when this option is set (assuming it can find +an "a" in the subject), whereas it fails by default, for Perl compatibility. +</P> +<P> +(3) \U matches an upper case "U" character; by default \U causes a compile +time error (Perl uses \U to upper case subsequent characters). +</P> +<P> +(4) \u matches a lower case "u" character unless it is followed by four +hexadecimal digits, in which case the hexadecimal number defines the code point +to match. By default, \u causes a compile time error (Perl uses it to upper +case the following character). +</P> +<P> +(5) \x matches a lower case "x" character unless it is followed by two +hexadecimal digits, in which case the hexadecimal number defines the code point +to match. By default, as in Perl, a hexadecimal number is always expected after +\x, but it may have zero, one, or two digits (so, for example, \xz matches a +binary zero character followed by z). +<pre> + PCRE_MULTILINE +</pre> +By default, for the purposes of matching "start of line" and "end of line", +PCRE treats the subject string as consisting of a single line of characters, +even if it actually contains newlines. The "start of line" metacharacter (^) +matches only at the start of the string, and the "end of line" metacharacter +($) matches only at the end of the string, or before a terminating newline +(except when PCRE_DOLLAR_ENDONLY is set). Note, however, that unless +PCRE_DOTALL is set, the "any character" metacharacter (.) does not match at a +newline. This behaviour (for ^, $, and dot) is the same as Perl. +</P> +<P> +When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs +match immediately following or immediately before internal newlines in the +subject string, respectively, as well as at the very start and end. This is +equivalent to Perl's /m option, and it can be changed within a pattern by a +(?m) option setting. If there are no newlines in a subject string, or no +occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect. +<pre> + PCRE_NEVER_UTF +</pre> +This option locks out interpretation of the pattern as UTF-8 (or UTF-16 or +UTF-32 in the 16-bit and 32-bit libraries). In particular, it prevents the +creator of the pattern from switching to UTF interpretation by starting the +pattern with (*UTF). This may be useful in applications that process patterns +from external sources. The combination of PCRE_UTF8 and PCRE_NEVER_UTF also +causes an error. +<pre> + PCRE_NEWLINE_CR + PCRE_NEWLINE_LF + PCRE_NEWLINE_CRLF + PCRE_NEWLINE_ANYCRLF + PCRE_NEWLINE_ANY +</pre> +These options override the default newline definition that was chosen when PCRE +was built. Setting the first or the second specifies that a newline is +indicated by a single character (CR or LF, respectively). Setting +PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character +CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three +preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies +that any Unicode newline sequence should be recognized. +</P> +<P> +In an ASCII/Unicode environment, the Unicode newline sequences are the three +just mentioned, plus the single characters VT (vertical tab, U+000B), FF (form +feed, U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS +(paragraph separator, U+2029). For the 8-bit library, the last two are +recognized only in UTF-8 mode. +</P> +<P> +When PCRE is compiled to run in an EBCDIC (mainframe) environment, the code for +CR is 0x0d, the same as ASCII. However, the character code for LF is normally +0x15, though in some EBCDIC environments 0x25 is used. Whichever of these is +not LF is made to correspond to Unicode's NEL character. EBCDIC codes are all +less than 256. For more details, see the +<a href="pcrebuild.html"><b>pcrebuild</b></a> +documentation. +</P> +<P> +The newline setting in the options word uses three bits that are treated +as a number, giving eight possibilities. Currently only six are used (default +plus the five values above). This means that if you set more than one newline +option, the combination may or may not be sensible. For example, +PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but +other combinations may yield unused numbers and cause an error. +</P> +<P> +The only time that a line break in a pattern is specially recognized when +compiling is when PCRE_EXTENDED is set. CR and LF are white space characters, +and so are ignored in this mode. Also, an unescaped # outside a character class +indicates a comment that lasts until after the next line break sequence. In +other circumstances, line break sequences in patterns are treated as literal +data. +</P> +<P> +The newline option that is set at compile time becomes the default that is used +for <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b>, but it can be overridden. +<pre> + PCRE_NO_AUTO_CAPTURE +</pre> +If this option is set, it disables the use of numbered capturing parentheses in +the pattern. Any opening parenthesis that is not followed by ? behaves as if it +were followed by ?: but named parentheses can still be used for capturing (and +they acquire numbers in the usual way). There is no equivalent of this option +in Perl. +<pre> + PCRE_NO_AUTO_POSSESS +</pre> +If this option is set, it disables "auto-possessification". This is an +optimization that, for example, turns a+b into a++b in order to avoid +backtracks into a+ that can never be successful. However, if callouts are in +use, auto-possessification means that some of them are never taken. You can set +this option if you want the matching functions to do a full unoptimized search +and run all the callouts, but it is mainly provided for testing purposes. +<pre> + PCRE_NO_START_OPTIMIZE +</pre> +This is an option that acts at matching time; that is, it is really an option +for <b>pcre_exec()</b> or <b>pcre_dfa_exec()</b>. If it is set at compile time, +it is remembered with the compiled pattern and assumed at matching time. This +is necessary if you want to use JIT execution, because the JIT compiler needs +to know whether or not this option is set. For details see the discussion of +PCRE_NO_START_OPTIMIZE +<a href="#execoptions">below.</a> +<pre> + PCRE_UCP +</pre> +This option changes the way PCRE processes \B, \b, \D, \d, \S, \s, \W, +\w, and some of the POSIX character classes. By default, only ASCII characters +are recognized, but if PCRE_UCP is set, Unicode properties are used instead to +classify characters. More details are given in the section on +<a href="pcre.html#genericchartypes">generic character types</a> +in the +<a href="pcrepattern.html"><b>pcrepattern</b></a> +page. If you set PCRE_UCP, matching one of the items it affects takes much +longer. The option is available only if PCRE has been compiled with Unicode +property support. +<pre> + PCRE_UNGREEDY +</pre> +This option inverts the "greediness" of the quantifiers so that they are not +greedy by default, but become greedy if followed by "?". It is not compatible +with Perl. It can also be set by a (?U) option setting within the pattern. +<pre> + PCRE_UTF8 +</pre> +This option causes PCRE to regard both the pattern and the subject as strings +of UTF-8 characters instead of single-byte strings. However, it is available +only when PCRE is built to include UTF support. If not, the use of this option +provokes an error. Details of how this option changes the behaviour of PCRE are +given in the +<a href="pcreunicode.html"><b>pcreunicode</b></a> +page. +<pre> + PCRE_NO_UTF8_CHECK +</pre> +When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is +automatically checked. There is a discussion about the +<a href="pcreunicode.html#utf8strings">validity of UTF-8 strings</a> +in the +<a href="pcreunicode.html"><b>pcreunicode</b></a> +page. If an invalid UTF-8 sequence is found, <b>pcre_compile()</b> returns an +error. If you already know that your pattern is valid, and you want to skip +this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK option. +When it is set, the effect of passing an invalid UTF-8 string as a pattern is +undefined. It may cause your program to crash or loop. Note that this option +can also be passed to <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b>, to suppress +the validity checking of subject strings only. If the same string is being +matched many times, the option can be safely set for the second and subsequent +matchings to improve performance. +</P> +<br><a name="SEC12" href="#TOC1">COMPILATION ERROR CODES</a><br> +<P> +The following table lists the error codes than may be returned by +<b>pcre_compile2()</b>, along with the error messages that may be returned by +both compiling functions. Note that error messages are always 8-bit ASCII +strings, even in 16-bit or 32-bit mode. As PCRE has developed, some error codes +have fallen out of use. To avoid confusion, they have not been re-used. +<pre> + 0 no error + 1 \ at end of pattern + 2 \c at end of pattern + 3 unrecognized character follows \ + 4 numbers out of order in {} quantifier + 5 number too big in {} quantifier + 6 missing terminating ] for character class + 7 invalid escape sequence in character class + 8 range out of order in character class + 9 nothing to repeat + 10 [this code is not in use] + 11 internal error: unexpected repeat + 12 unrecognized character after (? or (?- + 13 POSIX named classes are supported only within a class + 14 missing ) + 15 reference to non-existent subpattern + 16 erroffset passed as NULL + 17 unknown option bit(s) set + 18 missing ) after comment + 19 [this code is not in use] + 20 regular expression is too large + 21 failed to get memory + 22 unmatched parentheses + 23 internal error: code overflow + 24 unrecognized character after (?< + 25 lookbehind assertion is not fixed length + 26 malformed number or name after (?( + 27 conditional group contains more than two branches + 28 assertion expected after (?( + 29 (?R or (?[+-]digits must be followed by ) + 30 unknown POSIX class name + 31 POSIX collating elements are not supported + 32 this version of PCRE is compiled without UTF support + 33 [this code is not in use] + 34 character value in \x{} or \o{} is too large + 35 invalid condition (?(0) + 36 \C not allowed in lookbehind assertion + 37 PCRE does not support \L, \l, \N{name}, \U, or \u + 38 number after (?C is > 255 + 39 closing ) for (?C expected + 40 recursive call could loop indefinitely + 41 unrecognized character after (?P + 42 syntax error in subpattern name (missing terminator) + 43 two named subpatterns have the same name + 44 invalid UTF-8 string (specifically UTF-8) + 45 support for \P, \p, and \X has not been compiled + 46 malformed \P or \p sequence + 47 unknown property name after \P or \p + 48 subpattern name is too long (maximum 32 characters) + 49 too many named subpatterns (maximum 10000) + 50 [this code is not in use] + 51 octal value is greater than \377 in 8-bit non-UTF-8 mode + 52 internal error: overran compiling workspace + 53 internal error: previously-checked referenced subpattern + not found + 54 DEFINE group contains more than one branch + 55 repeating a DEFINE group is not allowed + 56 inconsistent NEWLINE options + 57 \g is not followed by a braced, angle-bracketed, or quoted + name/number or by a plain number + 58 a numbered reference must not be zero + 59 an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT) + 60 (*VERB) not recognized or malformed + 61 number is too big + 62 subpattern name expected + 63 digit expected after (?+ + 64 ] is an invalid data character in JavaScript compatibility mode + 65 different names for subpatterns of the same number are + not allowed + 66 (*MARK) must have an argument + 67 this version of PCRE is not compiled with Unicode property + support + 68 \c must be followed by an ASCII character + 69 \k is not followed by a braced, angle-bracketed, or quoted name + 70 internal error: unknown opcode in find_fixedlength() + 71 \N is not supported in a class + 72 too many forward references + 73 disallowed Unicode code point (>= 0xd800 && <= 0xdfff) + 74 invalid UTF-16 string (specifically UTF-16) + 75 name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN) + 76 character value in \u.... sequence is too large + 77 invalid UTF-32 string (specifically UTF-32) + 78 setting UTF is disabled by the application + 79 non-hex character in \x{} (closing brace missing?) + 80 non-octal character in \o{} (closing brace missing?) + 81 missing opening brace after \o + 82 parentheses are too deeply nested + 83 invalid range in character class + 84 group name must start with a non-digit + 85 parentheses are too deeply nested (stack check) +</pre> +The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may +be used if the limits were changed when PCRE was built. +<a name="studyingapattern"></a></P> +<br><a name="SEC13" href="#TOC1">STUDYING A PATTERN</a><br> +<P> +<b>pcre_extra *pcre_study(const pcre *<i>code</i>, int <i>options</i>,</b> +<b> const char **<i>errptr</i>);</b> +</P> +<P> +If a compiled pattern is going to be used several times, it is worth spending +more time analyzing it in order to speed up the time taken for matching. The +function <b>pcre_study()</b> takes a pointer to a compiled pattern as its first +argument. If studying the pattern produces additional information that will +help speed up matching, <b>pcre_study()</b> returns a pointer to a +<b>pcre_extra</b> block, in which the <i>study_data</i> field points to the +results of the study. +</P> +<P> +The returned value from <b>pcre_study()</b> can be passed directly to +<b>pcre_exec()</b> or <b>pcre_dfa_exec()</b>. However, a <b>pcre_extra</b> block +also contains other fields that can be set by the caller before the block is +passed; these are described +<a href="#extradata">below</a> +in the section on matching a pattern. +</P> +<P> +If studying the pattern does not produce any useful information, +<b>pcre_study()</b> returns NULL by default. In that circumstance, if the +calling program wants to pass any of the other fields to <b>pcre_exec()</b> or +<b>pcre_dfa_exec()</b>, it must set up its own <b>pcre_extra</b> block. However, +if <b>pcre_study()</b> is called with the PCRE_STUDY_EXTRA_NEEDED option, it +returns a <b>pcre_extra</b> block even if studying did not find any additional +information. It may still return NULL, however, if an error occurs in +<b>pcre_study()</b>. +</P> +<P> +The second argument of <b>pcre_study()</b> contains option bits. There are three +further options in addition to PCRE_STUDY_EXTRA_NEEDED: +<pre> + PCRE_STUDY_JIT_COMPILE + PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE + PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE +</pre> +If any of these are set, and the just-in-time compiler is available, the +pattern is further compiled into machine code that executes much faster than +the <b>pcre_exec()</b> interpretive matching function. If the just-in-time +compiler is not available, these options are ignored. All undefined bits in the +<i>options</i> argument must be zero. +</P> +<P> +JIT compilation is a heavyweight optimization. It can take some time for +patterns to be analyzed, and for one-off matches and simple patterns the +benefit of faster execution might be offset by a much slower study time. +Not all patterns can be optimized by the JIT compiler. For those that cannot be +handled, matching automatically falls back to the <b>pcre_exec()</b> +interpreter. For more details, see the +<a href="pcrejit.html"><b>pcrejit</b></a> +documentation. +</P> +<P> +The third argument for <b>pcre_study()</b> is a pointer for an error message. If +studying succeeds (even if no data is returned), the variable it points to is +set to NULL. Otherwise it is set to point to a textual error message. This is a +static string that is part of the library. You must not try to free it. You +should test the error pointer for NULL after calling <b>pcre_study()</b>, to be +sure that it has run successfully. +</P> +<P> +When you are finished with a pattern, you can free the memory used for the +study data by calling <b>pcre_free_study()</b>. This function was added to the +API for release 8.20. For earlier versions, the memory could be freed with +<b>pcre_free()</b>, just like the pattern itself. This will still work in cases +where JIT optimization is not used, but it is advisable to change to the new +function when convenient. +</P> +<P> +This is a typical way in which <b>pcre_study</b>() is used (except that in a +real application there should be tests for errors): +<pre> + int rc; + pcre *re; + pcre_extra *sd; + re = pcre_compile("pattern", 0, &error, &erroroffset, NULL); + sd = pcre_study( + re, /* result of pcre_compile() */ + 0, /* no options */ + &error); /* set to NULL or points to a message */ + rc = pcre_exec( /* see below for details of pcre_exec() options */ + re, sd, "subject", 7, 0, 0, ovector, 30); + ... + pcre_free_study(sd); + pcre_free(re); +</pre> +Studying a pattern does two things: first, a lower bound for the length of +subject string that is needed to match the pattern is computed. This does not +mean that there are any strings of that length that match, but it does +guarantee that no shorter strings match. The value is used to avoid wasting +time by trying to match strings that are shorter than the lower bound. You can +find out the value in a calling program via the <b>pcre_fullinfo()</b> function. +</P> +<P> +Studying a pattern is also useful for non-anchored patterns that do not have a +single fixed starting character. A bitmap of possible starting bytes is +created. This speeds up finding a position in the subject at which to start +matching. (In 16-bit mode, the bitmap is used for 16-bit values less than 256. +In 32-bit mode, the bitmap is used for 32-bit values less than 256.) +</P> +<P> +These two optimizations apply to both <b>pcre_exec()</b> and +<b>pcre_dfa_exec()</b>, and the information is also used by the JIT compiler. +The optimizations can be disabled by setting the PCRE_NO_START_OPTIMIZE option. +You might want to do this if your pattern contains callouts or (*MARK) and you +want to make use of these facilities in cases where matching fails. +</P> +<P> +PCRE_NO_START_OPTIMIZE can be specified at either compile time or execution +time. However, if PCRE_NO_START_OPTIMIZE is passed to <b>pcre_exec()</b>, (that +is, after any JIT compilation has happened) JIT execution is disabled. For JIT +execution to work with PCRE_NO_START_OPTIMIZE, the option must be set at +compile time. +</P> +<P> +There is a longer discussion of PCRE_NO_START_OPTIMIZE +<a href="#execoptions">below.</a> +<a name="localesupport"></a></P> +<br><a name="SEC14" href="#TOC1">LOCALE SUPPORT</a><br> +<P> +PCRE handles caseless matching, and determines whether characters are letters, +digits, or whatever, by reference to a set of tables, indexed by character +code point. When running in UTF-8 mode, or in the 16- or 32-bit libraries, this +applies only to characters with code points less than 256. By default, +higher-valued code points never match escapes such as \w or \d. However, if +PCRE is built with Unicode property support, all characters can be tested with +\p and \P, or, alternatively, the PCRE_UCP option can be set when a pattern +is compiled; this causes \w and friends to use Unicode property support +instead of the built-in tables. +</P> +<P> +The use of locales with Unicode is discouraged. If you are handling characters +with code points greater than 128, you should either use Unicode support, or +use locales, but not try to mix the two. +</P> +<P> +PCRE contains an internal set of tables that are used when the final argument +of <b>pcre_compile()</b> is NULL. These are sufficient for many applications. +Normally, the internal tables recognize only ASCII characters. However, when +PCRE is built, it is possible to cause the internal tables to be rebuilt in the +default "C" locale of the local system, which may cause them to be different. +</P> +<P> +The internal tables can always be overridden by tables supplied by the +application that calls PCRE. These may be created in a different locale from +the default. As more and more applications change to using Unicode, the need +for this locale support is expected to die away. +</P> +<P> +External tables are built by calling the <b>pcre_maketables()</b> function, +which has no arguments, in the relevant locale. The result can then be passed +to <b>pcre_compile()</b> as often as necessary. For example, to build and use +tables that are appropriate for the French locale (where accented characters +with values greater than 128 are treated as letters), the following code could +be used: +<pre> + setlocale(LC_CTYPE, "fr_FR"); + tables = pcre_maketables(); + re = pcre_compile(..., tables); +</pre> +The locale name "fr_FR" is used on Linux and other Unix-like systems; if you +are using Windows, the name for the French locale is "french". +</P> +<P> +When <b>pcre_maketables()</b> runs, the tables are built in memory that is +obtained via <b>pcre_malloc</b>. It is the caller's responsibility to ensure +that the memory containing the tables remains available for as long as it is +needed. +</P> +<P> +The pointer that is passed to <b>pcre_compile()</b> is saved with the compiled +pattern, and the same tables are used via this pointer by <b>pcre_study()</b> +and also by <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b>. Thus, for any single +pattern, compilation, studying and matching all happen in the same locale, but +different patterns can be processed in different locales. +</P> +<P> +It is possible to pass a table pointer or NULL (indicating the use of the +internal tables) to <b>pcre_exec()</b> or <b>pcre_dfa_exec()</b> (see the +discussion below in the section on matching a pattern). This facility is +provided for use with pre-compiled patterns that have been saved and reloaded. +Character tables are not saved with patterns, so if a non-standard table was +used at compile time, it must be provided again when the reloaded pattern is +matched. Attempting to use this facility to match a pattern in a different +locale from the one in which it was compiled is likely to lead to anomalous +(usually incorrect) results. +<a name="infoaboutpattern"></a></P> +<br><a name="SEC15" href="#TOC1">INFORMATION ABOUT A PATTERN</a><br> +<P> +<b>int pcre_fullinfo(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b> +<b> int <i>what</i>, void *<i>where</i>);</b> +</P> +<P> +The <b>pcre_fullinfo()</b> function returns information about a compiled +pattern. It replaces the <b>pcre_info()</b> function, which was removed from the +library at version 8.30, after more than 10 years of obsolescence. +</P> +<P> +The first argument for <b>pcre_fullinfo()</b> is a pointer to the compiled +pattern. The second argument is the result of <b>pcre_study()</b>, or NULL if +the pattern was not studied. The third argument specifies which piece of +information is required, and the fourth argument is a pointer to a variable +to receive the data. The yield of the function is zero for success, or one of +the following negative numbers: +<pre> + PCRE_ERROR_NULL the argument <i>code</i> was NULL + the argument <i>where</i> was NULL + PCRE_ERROR_BADMAGIC the "magic number" was not found + PCRE_ERROR_BADENDIANNESS the pattern was compiled with different + endianness + PCRE_ERROR_BADOPTION the value of <i>what</i> was invalid + PCRE_ERROR_UNSET the requested field is not set +</pre> +The "magic number" is placed at the start of each compiled pattern as an simple +check against passing an arbitrary memory pointer. The endianness error can +occur if a compiled pattern is saved and reloaded on a different host. Here is +a typical call of <b>pcre_fullinfo()</b>, to obtain the length of the compiled +pattern: +<pre> + int rc; + size_t length; + rc = pcre_fullinfo( + re, /* result of pcre_compile() */ + sd, /* result of pcre_study(), or NULL */ + PCRE_INFO_SIZE, /* what is required */ + &length); /* where to put the data */ +</pre> +The possible values for the third argument are defined in <b>pcre.h</b>, and are +as follows: +<pre> + PCRE_INFO_BACKREFMAX +</pre> +Return the number of the highest back reference in the pattern. The fourth +argument should point to an <b>int</b> variable. Zero is returned if there are +no back references. +<pre> + PCRE_INFO_CAPTURECOUNT +</pre> +Return the number of capturing subpatterns in the pattern. The fourth argument +should point to an <b>int</b> variable. +<pre> + PCRE_INFO_DEFAULT_TABLES +</pre> +Return a pointer to the internal default character tables within PCRE. The +fourth argument should point to an <b>unsigned char *</b> variable. This +information call is provided for internal use by the <b>pcre_study()</b> +function. External callers can cause PCRE to use its internal tables by passing +a NULL table pointer. +<pre> + PCRE_INFO_FIRSTBYTE (deprecated) +</pre> +Return information about the first data unit of any matched string, for a +non-anchored pattern. The name of this option refers to the 8-bit library, +where data units are bytes. The fourth argument should point to an <b>int</b> +variable. Negative values are used for special cases. However, this means that +when the 32-bit library is in non-UTF-32 mode, the full 32-bit range of +characters cannot be returned. For this reason, this value is deprecated; use +PCRE_INFO_FIRSTCHARACTERFLAGS and PCRE_INFO_FIRSTCHARACTER instead. +</P> +<P> +If there is a fixed first value, for example, the letter "c" from a pattern +such as (cat|cow|coyote), its value is returned. In the 8-bit library, the +value is always less than 256. In the 16-bit library the value can be up to +0xffff. In the 32-bit library the value can be up to 0x10ffff. +</P> +<P> +If there is no fixed first value, and if either +<br> +<br> +(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch +starts with "^", or +<br> +<br> +(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set +(if it were set, the pattern would be anchored), +<br> +<br> +-1 is returned, indicating that the pattern matches only at the start of a +subject string or after any newline within the string. Otherwise -2 is +returned. For anchored patterns, -2 is returned. +<pre> + PCRE_INFO_FIRSTCHARACTER +</pre> +Return the value of the first data unit (non-UTF character) of any matched +string in the situation where PCRE_INFO_FIRSTCHARACTERFLAGS returns 1; +otherwise return 0. The fourth argument should point to an <b>uint_t</b> +variable. +</P> +<P> +In the 8-bit library, the value is always less than 256. In the 16-bit library +the value can be up to 0xffff. In the 32-bit library in UTF-32 mode the value +can be up to 0x10ffff, and up to 0xffffffff when not using UTF-32 mode. +<pre> + PCRE_INFO_FIRSTCHARACTERFLAGS +</pre> +Return information about the first data unit of any matched string, for a +non-anchored pattern. The fourth argument should point to an <b>int</b> +variable. +</P> +<P> +If there is a fixed first value, for example, the letter "c" from a pattern +such as (cat|cow|coyote), 1 is returned, and the character value can be +retrieved using PCRE_INFO_FIRSTCHARACTER. If there is no fixed first value, and +if either +<br> +<br> +(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch +starts with "^", or +<br> +<br> +(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set +(if it were set, the pattern would be anchored), +<br> +<br> +2 is returned, indicating that the pattern matches only at the start of a +subject string or after any newline within the string. Otherwise 0 is +returned. For anchored patterns, 0 is returned. +<pre> + PCRE_INFO_FIRSTTABLE +</pre> +If the pattern was studied, and this resulted in the construction of a 256-bit +table indicating a fixed set of values for the first data unit in any matching +string, a pointer to the table is returned. Otherwise NULL is returned. The +fourth argument should point to an <b>unsigned char *</b> variable. +<pre> + PCRE_INFO_HASCRORLF +</pre> +Return 1 if the pattern contains any explicit matches for CR or LF characters, +otherwise 0. The fourth argument should point to an <b>int</b> variable. An +explicit match is either a literal CR or LF character, or \r or \n. +<pre> + PCRE_INFO_JCHANGED +</pre> +Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise +0. The fourth argument should point to an <b>int</b> variable. (?J) and +(?-J) set and unset the local PCRE_DUPNAMES option, respectively. +<pre> + PCRE_INFO_JIT +</pre> +Return 1 if the pattern was studied with one of the JIT options, and +just-in-time compiling was successful. The fourth argument should point to an +<b>int</b> variable. A return value of 0 means that JIT support is not available +in this version of PCRE, or that the pattern was not studied with a JIT option, +or that the JIT compiler could not handle this particular pattern. See the +<a href="pcrejit.html"><b>pcrejit</b></a> +documentation for details of what can and cannot be handled. +<pre> + PCRE_INFO_JITSIZE +</pre> +If the pattern was successfully studied with a JIT option, return the size of +the JIT compiled code, otherwise return zero. The fourth argument should point +to a <b>size_t</b> variable. +<pre> + PCRE_INFO_LASTLITERAL +</pre> +Return the value of the rightmost literal data unit that must exist in any +matched string, other than at its start, if such a value has been recorded. The +fourth argument should point to an <b>int</b> variable. If there is no such +value, -1 is returned. For anchored patterns, a last literal value is recorded +only if it follows something of variable length. For example, for the pattern +/^a\d+z\d+/ the returned value is "z", but for /^a\dz\d/ the returned value +is -1. +</P> +<P> +Since for the 32-bit library using the non-UTF-32 mode, this function is unable +to return the full 32-bit range of characters, this value is deprecated; +instead the PCRE_INFO_REQUIREDCHARFLAGS and PCRE_INFO_REQUIREDCHAR values should +be used. +<pre> + PCRE_INFO_MATCH_EMPTY +</pre> +Return 1 if the pattern can match an empty string, otherwise 0. The fourth +argument should point to an <b>int</b> variable. +<pre> + PCRE_INFO_MATCHLIMIT +</pre> +If the pattern set a match limit by including an item of the form +(*LIMIT_MATCH=nnnn) at the start, the value is returned. The fourth argument +should point to an unsigned 32-bit integer. If no such value has been set, the +call to <b>pcre_fullinfo()</b> returns the error PCRE_ERROR_UNSET. +<pre> + PCRE_INFO_MAXLOOKBEHIND +</pre> +Return the number of characters (NB not data units) in the longest lookbehind +assertion in the pattern. This information is useful when doing multi-segment +matching using the partial matching facilities. Note that the simple assertions +\b and \B require a one-character lookbehind. \A also registers a +one-character lookbehind, though it does not actually inspect the previous +character. This is to ensure that at least one character from the old segment +is retained when a new segment is processed. Otherwise, if there are no +lookbehinds in the pattern, \A might match incorrectly at the start of a new +segment. +<pre> + PCRE_INFO_MINLENGTH +</pre> +If the pattern was studied and a minimum length for matching subject strings +was computed, its value is returned. Otherwise the returned value is -1. The +value is a number of characters, which in UTF mode may be different from the +number of data units. The fourth argument should point to an <b>int</b> +variable. A non-negative value is a lower bound to the length of any matching +string. There may not be any strings of that length that do actually match, but +every string that does match is at least that long. +<pre> + PCRE_INFO_NAMECOUNT + PCRE_INFO_NAMEENTRYSIZE + PCRE_INFO_NAMETABLE +</pre> +PCRE supports the use of named as well as numbered capturing parentheses. The +names are just an additional way of identifying the parentheses, which still +acquire numbers. Several convenience functions such as +<b>pcre_get_named_substring()</b> are provided for extracting captured +substrings by name. It is also possible to extract the data directly, by first +converting the name to a number in order to access the correct pointers in the +output vector (described with <b>pcre_exec()</b> below). To do the conversion, +you need to use the name-to-number map, which is described by these three +values. +</P> +<P> +The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT gives +the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each +entry; both of these return an <b>int</b> value. The entry size depends on the +length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first +entry of the table. This is a pointer to <b>char</b> in the 8-bit library, where +the first two bytes of each entry are the number of the capturing parenthesis, +most significant byte first. In the 16-bit library, the pointer points to +16-bit data units, the first of which contains the parenthesis number. In the +32-bit library, the pointer points to 32-bit data units, the first of which +contains the parenthesis number. The rest of the entry is the corresponding +name, zero terminated. +</P> +<P> +The names are in alphabetical order. If (?| is used to create multiple groups +with the same number, as described in the +<a href="pcrepattern.html#dupsubpatternnumber">section on duplicate subpattern numbers</a> +in the +<a href="pcrepattern.html"><b>pcrepattern</b></a> +page, the groups may be given the same name, but there is only one entry in the +table. Different names for groups of the same number are not permitted. +Duplicate names for subpatterns with different numbers are permitted, +but only if PCRE_DUPNAMES is set. They appear in the table in the order in +which they were found in the pattern. In the absence of (?| this is the order +of increasing number; when (?| is used this is not necessarily the case because +later subpatterns may have lower numbers. +</P> +<P> +As a simple example of the name/number table, consider the following pattern +after compilation by the 8-bit library (assume PCRE_EXTENDED is set, so white +space - including newlines - is ignored): +<pre> + (?<date> (?<year>(\d\d)?\d\d) - (?<month>\d\d) - (?<day>\d\d) ) +</pre> +There are four named subpatterns, so the table has four entries, and each entry +in the table is eight bytes long. The table is as follows, with non-printing +bytes shows in hexadecimal, and undefined bytes shown as ??: +<pre> + 00 01 d a t e 00 ?? + 00 05 d a y 00 ?? ?? + 00 04 m o n t h 00 + 00 02 y e a r 00 ?? +</pre> +When writing code to extract data from named subpatterns using the +name-to-number map, remember that the length of the entries is likely to be +different for each compiled pattern. +<pre> + PCRE_INFO_OKPARTIAL +</pre> +Return 1 if the pattern can be used for partial matching with +<b>pcre_exec()</b>, otherwise 0. The fourth argument should point to an +<b>int</b> variable. From release 8.00, this always returns 1, because the +restrictions that previously applied to partial matching have been lifted. The +<a href="pcrepartial.html"><b>pcrepartial</b></a> +documentation gives details of partial matching. +<pre> + PCRE_INFO_OPTIONS +</pre> +Return a copy of the options with which the pattern was compiled. The fourth +argument should point to an <b>unsigned long int</b> variable. These option bits +are those specified in the call to <b>pcre_compile()</b>, modified by any +top-level option settings at the start of the pattern itself. In other words, +they are the options that will be in force when matching starts. For example, +if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the +result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED. +</P> +<P> +A pattern is automatically anchored by PCRE if all of its top-level +alternatives begin with one of the following: +<pre> + ^ unless PCRE_MULTILINE is set + \A always + \G always + .* if PCRE_DOTALL is set and there are no back references to the subpattern in which .* appears +</pre> +For such patterns, the PCRE_ANCHORED bit is set in the options returned by +<b>pcre_fullinfo()</b>. +<pre> + PCRE_INFO_RECURSIONLIMIT +</pre> +If the pattern set a recursion limit by including an item of the form +(*LIMIT_RECURSION=nnnn) at the start, the value is returned. The fourth +argument should point to an unsigned 32-bit integer. If no such value has been +set, the call to <b>pcre_fullinfo()</b> returns the error PCRE_ERROR_UNSET. +<pre> + PCRE_INFO_SIZE +</pre> +Return the size of the compiled pattern in bytes (for all three libraries). The +fourth argument should point to a <b>size_t</b> variable. This value does not +include the size of the <b>pcre</b> structure that is returned by +<b>pcre_compile()</b>. The value that is passed as the argument to +<b>pcre_malloc()</b> when <b>pcre_compile()</b> is getting memory in which to +place the compiled data is the value returned by this option plus the size of +the <b>pcre</b> structure. Studying a compiled pattern, with or without JIT, +does not alter the value returned by this option. +<pre> + PCRE_INFO_STUDYSIZE +</pre> +Return the size in bytes (for all three libraries) of the data block pointed to +by the <i>study_data</i> field in a <b>pcre_extra</b> block. If <b>pcre_extra</b> +is NULL, or there is no study data, zero is returned. The fourth argument +should point to a <b>size_t</b> variable. The <i>study_data</i> field is set by +<b>pcre_study()</b> to record information that will speed up matching (see the +section entitled +<a href="#studyingapattern">"Studying a pattern"</a> +above). The format of the <i>study_data</i> block is private, but its length +is made available via this option so that it can be saved and restored (see the +<a href="pcreprecompile.html"><b>pcreprecompile</b></a> +documentation for details). +<pre> + PCRE_INFO_REQUIREDCHARFLAGS +</pre> +Returns 1 if there is a rightmost literal data unit that must exist in any +matched string, other than at its start. The fourth argument should point to +an <b>int</b> variable. If there is no such value, 0 is returned. If returning +1, the character value itself can be retrieved using PCRE_INFO_REQUIREDCHAR. +</P> +<P> +For anchored patterns, a last literal value is recorded only if it follows +something of variable length. For example, for the pattern /^a\d+z\d+/ the +returned value 1 (with "z" returned from PCRE_INFO_REQUIREDCHAR), but for +/^a\dz\d/ the returned value is 0. +<pre> + PCRE_INFO_REQUIREDCHAR +</pre> +Return the value of the rightmost literal data unit that must exist in any +matched string, other than at its start, if such a value has been recorded. The +fourth argument should point to an <b>uint32_t</b> variable. If there is no such +value, 0 is returned. +</P> +<br><a name="SEC16" href="#TOC1">REFERENCE COUNTS</a><br> +<P> +<b>int pcre_refcount(pcre *<i>code</i>, int <i>adjust</i>);</b> +</P> +<P> +The <b>pcre_refcount()</b> function is used to maintain a reference count in the +data block that contains a compiled pattern. It is provided for the benefit of +applications that operate in an object-oriented manner, where different parts +of the application may be using the same compiled pattern, but you want to free +the block when they are all done. +</P> +<P> +When a pattern is compiled, the reference count field is initialized to zero. +It is changed only by calling this function, whose action is to add the +<i>adjust</i> value (which may be positive or negative) to it. The yield of the +function is the new value. However, the value of the count is constrained to +lie between 0 and 65535, inclusive. If the new value is outside these limits, +it is forced to the appropriate limit value. +</P> +<P> +Except when it is zero, the reference count is not correctly preserved if a +pattern is compiled on one host and then transferred to a host whose byte-order +is different. (This seems a highly unlikely scenario.) +</P> +<br><a name="SEC17" href="#TOC1">MATCHING A PATTERN: THE TRADITIONAL FUNCTION</a><br> +<P> +<b>int pcre_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b> +<b> const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b> +</P> +<P> +The function <b>pcre_exec()</b> is called to match a subject string against a +compiled pattern, which is passed in the <i>code</i> argument. If the +pattern was studied, the result of the study should be passed in the +<i>extra</i> argument. You can call <b>pcre_exec()</b> with the same <i>code</i> +and <i>extra</i> arguments as many times as you like, in order to match +different subject strings with the same pattern. +</P> +<P> +This function is the main matching facility of the library, and it operates in +a Perl-like manner. For specialist use there is also an alternative matching +function, which is described +<a href="#dfamatch">below</a> +in the section about the <b>pcre_dfa_exec()</b> function. +</P> +<P> +In most applications, the pattern will have been compiled (and optionally +studied) in the same process that calls <b>pcre_exec()</b>. However, it is +possible to save compiled patterns and study data, and then use them later +in different processes, possibly even on different hosts. For a discussion +about this, see the +<a href="pcreprecompile.html"><b>pcreprecompile</b></a> +documentation. +</P> +<P> +Here is an example of a simple call to <b>pcre_exec()</b>: +<pre> + int rc; + int ovector[30]; + rc = pcre_exec( + re, /* result of pcre_compile() */ + NULL, /* we didn't study the pattern */ + "some string", /* the subject string */ + 11, /* the length of the subject string */ + 0, /* start at offset 0 in the subject */ + 0, /* default options */ + ovector, /* vector of integers for substring information */ + 30); /* number of elements (NOT size in bytes) */ +<a name="extradata"></a></PRE> +</P> +<br><b> +Extra data for <b>pcre_exec()</b> +</b><br> +<P> +If the <i>extra</i> argument is not NULL, it must point to a <b>pcre_extra</b> +data block. The <b>pcre_study()</b> function returns such a block (when it +doesn't return NULL), but you can also create one for yourself, and pass +additional information in it. The <b>pcre_extra</b> block contains the following +fields (not necessarily in this order): +<pre> + unsigned long int <i>flags</i>; + void *<i>study_data</i>; + void *<i>executable_jit</i>; + unsigned long int <i>match_limit</i>; + unsigned long int <i>match_limit_recursion</i>; + void *<i>callout_data</i>; + const unsigned char *<i>tables</i>; + unsigned char **<i>mark</i>; +</pre> +In the 16-bit version of this structure, the <i>mark</i> field has type +"PCRE_UCHAR16 **". +<br> +<br> +In the 32-bit version of this structure, the <i>mark</i> field has type +"PCRE_UCHAR32 **". +</P> +<P> +The <i>flags</i> field is used to specify which of the other fields are set. The +flag bits are: +<pre> + PCRE_EXTRA_CALLOUT_DATA + PCRE_EXTRA_EXECUTABLE_JIT + PCRE_EXTRA_MARK + PCRE_EXTRA_MATCH_LIMIT + PCRE_EXTRA_MATCH_LIMIT_RECURSION + PCRE_EXTRA_STUDY_DATA + PCRE_EXTRA_TABLES +</pre> +Other flag bits should be set to zero. The <i>study_data</i> field and sometimes +the <i>executable_jit</i> field are set in the <b>pcre_extra</b> block that is +returned by <b>pcre_study()</b>, together with the appropriate flag bits. You +should not set these yourself, but you may add to the block by setting other +fields and their corresponding flag bits. +</P> +<P> +The <i>match_limit</i> field provides a means of preventing PCRE from using up a +vast amount of resources when running patterns that are not going to match, +but which have a very large number of possibilities in their search trees. The +classic example is a pattern that uses nested unlimited repeats. +</P> +<P> +Internally, <b>pcre_exec()</b> uses a function called <b>match()</b>, which it +calls repeatedly (sometimes recursively). The limit set by <i>match_limit</i> is +imposed on the number of times this function is called during a match, which +has the effect of limiting the amount of backtracking that can take place. For +patterns that are not anchored, the count restarts from zero for each position +in the subject string. +</P> +<P> +When <b>pcre_exec()</b> is called with a pattern that was successfully studied +with a JIT option, the way that the matching is executed is entirely different. +However, there is still the possibility of runaway matching that goes on for a +very long time, and so the <i>match_limit</i> value is also used in this case +(but in a different way) to limit how long the matching can continue. +</P> +<P> +The default value for the limit can be set when PCRE is built; the default +default is 10 million, which handles all but the most extreme cases. You can +override the default by suppling <b>pcre_exec()</b> with a <b>pcre_extra</b> +block in which <i>match_limit</i> is set, and PCRE_EXTRA_MATCH_LIMIT is set in +the <i>flags</i> field. If the limit is exceeded, <b>pcre_exec()</b> returns +PCRE_ERROR_MATCHLIMIT. +</P> +<P> +A value for the match limit may also be supplied by an item at the start of a +pattern of the form +<pre> + (*LIMIT_MATCH=d) +</pre> +where d is a decimal number. However, such a setting is ignored unless d is +less than the limit set by the caller of <b>pcre_exec()</b> or, if no such limit +is set, less than the default. +</P> +<P> +The <i>match_limit_recursion</i> field is similar to <i>match_limit</i>, but +instead of limiting the total number of times that <b>match()</b> is called, it +limits the depth of recursion. The recursion depth is a smaller number than the +total number of calls, because not all calls to <b>match()</b> are recursive. +This limit is of use only if it is set smaller than <i>match_limit</i>. +</P> +<P> +Limiting the recursion depth limits the amount of machine stack that can be +used, or, when PCRE has been compiled to use memory on the heap instead of the +stack, the amount of heap memory that can be used. This limit is not relevant, +and is ignored, when matching is done using JIT compiled code. +</P> +<P> +The default value for <i>match_limit_recursion</i> can be set when PCRE is +built; the default default is the same value as the default for +<i>match_limit</i>. You can override the default by suppling <b>pcre_exec()</b> +with a <b>pcre_extra</b> block in which <i>match_limit_recursion</i> is set, and +PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the <i>flags</i> field. If the limit +is exceeded, <b>pcre_exec()</b> returns PCRE_ERROR_RECURSIONLIMIT. +</P> +<P> +A value for the recursion limit may also be supplied by an item at the start of +a pattern of the form +<pre> + (*LIMIT_RECURSION=d) +</pre> +where d is a decimal number. However, such a setting is ignored unless d is +less than the limit set by the caller of <b>pcre_exec()</b> or, if no such limit +is set, less than the default. +</P> +<P> +The <i>callout_data</i> field is used in conjunction with the "callout" feature, +and is described in the +<a href="pcrecallout.html"><b>pcrecallout</b></a> +documentation. +</P> +<P> +The <i>tables</i> field is provided for use with patterns that have been +pre-compiled using custom character tables, saved to disc or elsewhere, and +then reloaded, because the tables that were used to compile a pattern are not +saved with it. See the +<a href="pcreprecompile.html"><b>pcreprecompile</b></a> +documentation for a discussion of saving compiled patterns for later use. If +NULL is passed using this mechanism, it forces PCRE's internal tables to be +used. +</P> +<P> +<b>Warning:</b> The tables that <b>pcre_exec()</b> uses must be the same as those +that were used when the pattern was compiled. If this is not the case, the +behaviour of <b>pcre_exec()</b> is undefined. Therefore, when a pattern is +compiled and matched in the same process, this field should never be set. In +this (the most common) case, the correct table pointer is automatically passed +with the compiled pattern from <b>pcre_compile()</b> to <b>pcre_exec()</b>. +</P> +<P> +If PCRE_EXTRA_MARK is set in the <i>flags</i> field, the <i>mark</i> field must +be set to point to a suitable variable. If the pattern contains any +backtracking control verbs such as (*MARK:NAME), and the execution ends up with +a name to pass back, a pointer to the name string (zero terminated) is placed +in the variable pointed to by the <i>mark</i> field. The names are within the +compiled pattern; if you wish to retain such a name you must copy it before +freeing the memory of a compiled pattern. If there is no name to pass back, the +variable pointed to by the <i>mark</i> field is set to NULL. For details of the +backtracking control verbs, see the section entitled +<a href="pcrepattern#backtrackcontrol">"Backtracking control"</a> +in the +<a href="pcrepattern.html"><b>pcrepattern</b></a> +documentation. +<a name="execoptions"></a></P> +<br><b> +Option bits for <b>pcre_exec()</b> +</b><br> +<P> +The unused bits of the <i>options</i> argument for <b>pcre_exec()</b> must be +zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_<i>xxx</i>, +PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, +PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_HARD, and +PCRE_PARTIAL_SOFT. +</P> +<P> +If the pattern was successfully studied with one of the just-in-time (JIT) +compile options, the only supported options for JIT execution are +PCRE_NO_UTF8_CHECK, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, +PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and PCRE_PARTIAL_SOFT. If an +unsupported option is used, JIT execution is disabled and the normal +interpretive code in <b>pcre_exec()</b> is run. +<pre> + PCRE_ANCHORED +</pre> +The PCRE_ANCHORED option limits <b>pcre_exec()</b> to matching at the first +matching position. If a pattern was compiled with PCRE_ANCHORED, or turned out +to be anchored by virtue of its contents, it cannot be made unachored at +matching time. +<pre> + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE +</pre> +These options (which are mutually exclusive) control what the \R escape +sequence matches. The choice is either to match only CR, LF, or CRLF, or to +match any Unicode newline sequence. These options override the choice that was +made or defaulted when the pattern was compiled. +<pre> + PCRE_NEWLINE_CR + PCRE_NEWLINE_LF + PCRE_NEWLINE_CRLF + PCRE_NEWLINE_ANYCRLF + PCRE_NEWLINE_ANY +</pre> +These options override the newline definition that was chosen or defaulted when +the pattern was compiled. For details, see the description of +<b>pcre_compile()</b> above. During matching, the newline choice affects the +behaviour of the dot, circumflex, and dollar metacharacters. It may also alter +the way the match position is advanced after a match failure for an unanchored +pattern. +</P> +<P> +When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is set, and a +match attempt for an unanchored pattern fails when the current position is at a +CRLF sequence, and the pattern contains no explicit matches for CR or LF +characters, the match position is advanced by two characters instead of one, in +other words, to after the CRLF. +</P> +<P> +The above rule is a compromise that makes the most common cases work as +expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not +set), it does not match the string "\r\nA" because, after failing at the +start, it skips both the CR and the LF before retrying. However, the pattern +[\r\n]A does match that string, because it contains an explicit CR or LF +reference, and so advances only by one character after the first failure. +</P> +<P> +An explicit match for CR of LF is either a literal appearance of one of those +characters, or one of the \r or \n escape sequences. Implicit matches such as +[^X] do not count, nor does \s (which includes CR and LF in the characters +that it matches). +</P> +<P> +Notwithstanding the above, anomalous effects may still occur when CRLF is a +valid newline sequence and explicit \r or \n escapes appear in the pattern. +<pre> + PCRE_NOTBOL +</pre> +This option specifies that first character of the subject string is not the +beginning of a line, so the circumflex metacharacter should not match before +it. Setting this without PCRE_MULTILINE (at compile time) causes circumflex +never to match. This option affects only the behaviour of the circumflex +metacharacter. It does not affect \A. +<pre> + PCRE_NOTEOL +</pre> +This option specifies that the end of the subject string is not the end of a +line, so the dollar metacharacter should not match it nor (except in multiline +mode) a newline immediately before it. Setting this without PCRE_MULTILINE (at +compile time) causes dollar never to match. This option affects only the +behaviour of the dollar metacharacter. It does not affect \Z or \z. +<pre> + PCRE_NOTEMPTY +</pre> +An empty string is not considered to be a valid match if this option is set. If +there are alternatives in the pattern, they are tried. If all the alternatives +match the empty string, the entire match fails. For example, if the pattern +<pre> + a?b? +</pre> +is applied to a string not beginning with "a" or "b", it matches an empty +string at the start of the subject. With PCRE_NOTEMPTY set, this match is not +valid, so PCRE searches further into the string for occurrences of "a" or "b". +<pre> + PCRE_NOTEMPTY_ATSTART +</pre> +This is like PCRE_NOTEMPTY, except that an empty string match that is not at +the start of the subject is permitted. If the pattern is anchored, such a match +can occur only if the pattern contains \K. +</P> +<P> +Perl has no direct equivalent of PCRE_NOTEMPTY or PCRE_NOTEMPTY_ATSTART, but it +does make a special case of a pattern match of the empty string within its +<b>split()</b> function, and when using the /g modifier. It is possible to +emulate Perl's behaviour after matching a null string by first trying the match +again at the same offset with PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED, and then +if that fails, by advancing the starting offset (see below) and trying an +ordinary match again. There is some code that demonstrates how to do this in +the +<a href="pcredemo.html"><b>pcredemo</b></a> +sample program. In the most general case, you have to check to see if the +newline convention recognizes CRLF as a newline, and if so, and the current +character is CR followed by LF, advance the starting offset by two characters +instead of one. +<pre> + PCRE_NO_START_OPTIMIZE +</pre> +There are a number of optimizations that <b>pcre_exec()</b> uses at the start of +a match, in order to speed up the process. For example, if it is known that an +unanchored match must start with a specific character, it searches the subject +for that character, and fails immediately if it cannot find it, without +actually running the main matching function. This means that a special item +such as (*COMMIT) at the start of a pattern is not considered until after a +suitable starting point for the match has been found. Also, when callouts or +(*MARK) items are in use, these "start-up" optimizations can cause them to be +skipped if the pattern is never actually used. The start-up optimizations are +in effect a pre-scan of the subject that takes place before the pattern is run. +</P> +<P> +The PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, possibly +causing performance to suffer, but ensuring that in cases where the result is +"no match", the callouts do occur, and that items such as (*COMMIT) and (*MARK) +are considered at every possible starting position in the subject string. If +PCRE_NO_START_OPTIMIZE is set at compile time, it cannot be unset at matching +time. The use of PCRE_NO_START_OPTIMIZE at matching time (that is, passing it +to <b>pcre_exec()</b>) disables JIT execution; in this situation, matching is +always done using interpretively. +</P> +<P> +Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching operation. +Consider the pattern +<pre> + (*COMMIT)ABC +</pre> +When this is compiled, PCRE records the fact that a match must start with the +character "A". Suppose the subject string is "DEFABC". The start-up +optimization scans along the subject, finds "A" and runs the first match +attempt from there. The (*COMMIT) item means that the pattern must match the +current starting position, which in this case, it does. However, if the same +match is run with PCRE_NO_START_OPTIMIZE set, the initial scan along the +subject string does not happen. The first match attempt is run starting from +"D" and when this fails, (*COMMIT) prevents any further matches being tried, so +the overall result is "no match". If the pattern is studied, more start-up +optimizations may be used. For example, a minimum length for the subject may be +recorded. Consider the pattern +<pre> + (*MARK:A)(X|Y) +</pre> +The minimum length for a match is one character. If the subject is "ABC", there +will be attempts to match "ABC", "BC", "C", and then finally an empty string. +If the pattern is studied, the final attempt does not take place, because PCRE +knows that the subject is too short, and so the (*MARK) is never encountered. +In this case, studying the pattern does not affect the overall match result, +which is still "no match", but it does affect the auxiliary information that is +returned. +<pre> + PCRE_NO_UTF8_CHECK +</pre> +When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8 +string is automatically checked when <b>pcre_exec()</b> is subsequently called. +The entire string is checked before any other processing takes place. The value +of <i>startoffset</i> is also checked to ensure that it points to the start of a +UTF-8 character. There is a discussion about the +<a href="pcreunicode.html#utf8strings">validity of UTF-8 strings</a> +in the +<a href="pcreunicode.html"><b>pcreunicode</b></a> +page. If an invalid sequence of bytes is found, <b>pcre_exec()</b> returns the +error PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is a +truncated character at the end of the subject, PCRE_ERROR_SHORTUTF8. In both +cases, information about the precise nature of the error may also be returned +(see the descriptions of these errors in the section entitled \fIError return +values from\fP <b>pcre_exec()</b> +<a href="#errorlist">below).</a> +If <i>startoffset</i> contains a value that does not point to the start of a +UTF-8 character (or to the end of the subject), PCRE_ERROR_BADUTF8_OFFSET is +returned. +</P> +<P> +If you already know that your subject is valid, and you want to skip these +checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when +calling <b>pcre_exec()</b>. You might want to do this for the second and +subsequent calls to <b>pcre_exec()</b> if you are making repeated calls to find +all the matches in a single subject string. However, you should be sure that +the value of <i>startoffset</i> points to the start of a character (or the end +of the subject). When PCRE_NO_UTF8_CHECK is set, the effect of passing an +invalid string as a subject or an invalid value of <i>startoffset</i> is +undefined. Your program may crash or loop. +<pre> + PCRE_PARTIAL_HARD + PCRE_PARTIAL_SOFT +</pre> +These options turn on the partial matching feature. For backwards +compatibility, PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. A partial match +occurs if the end of the subject string is reached successfully, but there are +not enough subject characters to complete the match. If this happens when +PCRE_PARTIAL_SOFT (but not PCRE_PARTIAL_HARD) is set, matching continues by +testing any remaining alternatives. Only if no complete match can be found is +PCRE_ERROR_PARTIAL returned instead of PCRE_ERROR_NOMATCH. In other words, +PCRE_PARTIAL_SOFT says that the caller is prepared to handle a partial match, +but only if no complete match can be found. +</P> +<P> +If PCRE_PARTIAL_HARD is set, it overrides PCRE_PARTIAL_SOFT. In this case, if a +partial match is found, <b>pcre_exec()</b> immediately returns +PCRE_ERROR_PARTIAL, without considering any other alternatives. In other words, +when PCRE_PARTIAL_HARD is set, a partial match is considered to be more +important that an alternative complete match. +</P> +<P> +In both cases, the portion of the string that was inspected when the partial +match was found is set as the first matching string. There is a more detailed +discussion of partial and multi-segment matching, with examples, in the +<a href="pcrepartial.html"><b>pcrepartial</b></a> +documentation. +</P> +<br><b> +The string to be matched by <b>pcre_exec()</b> +</b><br> +<P> +The subject string is passed to <b>pcre_exec()</b> as a pointer in +<i>subject</i>, a length in <i>length</i>, and a starting offset in +<i>startoffset</i>. The units for <i>length</i> and <i>startoffset</i> are bytes +for the 8-bit library, 16-bit data items for the 16-bit library, and 32-bit +data items for the 32-bit library. +</P> +<P> +If <i>startoffset</i> is negative or greater than the length of the subject, +<b>pcre_exec()</b> returns PCRE_ERROR_BADOFFSET. When the starting offset is +zero, the search for a match starts at the beginning of the subject, and this +is by far the most common case. In UTF-8 or UTF-16 mode, the offset must point +to the start of a character, or the end of the subject (in UTF-32 mode, one +data unit equals one character, so all offsets are valid). Unlike the pattern +string, the subject may contain binary zeroes. +</P> +<P> +A non-zero starting offset is useful when searching for another match in the +same subject by calling <b>pcre_exec()</b> again after a previous success. +Setting <i>startoffset</i> differs from just passing over a shortened string and +setting PCRE_NOTBOL in the case of a pattern that begins with any kind of +lookbehind. For example, consider the pattern +<pre> + \Biss\B +</pre> +which finds occurrences of "iss" in the middle of words. (\B matches only if +the current position in the subject is not a word boundary.) When applied to +the string "Mississipi" the first call to <b>pcre_exec()</b> finds the first +occurrence. If <b>pcre_exec()</b> is called again with just the remainder of the +subject, namely "issipi", it does not match, because \B is always false at the +start of the subject, which is deemed to be a word boundary. However, if +<b>pcre_exec()</b> is passed the entire string again, but with <i>startoffset</i> +set to 4, it finds the second occurrence of "iss" because it is able to look +behind the starting point to discover that it is preceded by a letter. +</P> +<P> +Finding all the matches in a subject is tricky when the pattern can match an +empty string. It is possible to emulate Perl's /g behaviour by first trying the +match again at the same offset, with the PCRE_NOTEMPTY_ATSTART and +PCRE_ANCHORED options, and then if that fails, advancing the starting offset +and trying an ordinary match again. There is some code that demonstrates how to +do this in the +<a href="pcredemo.html"><b>pcredemo</b></a> +sample program. In the most general case, you have to check to see if the +newline convention recognizes CRLF as a newline, and if so, and the current +character is CR followed by LF, advance the starting offset by two characters +instead of one. +</P> +<P> +If a non-zero starting offset is passed when the pattern is anchored, one +attempt to match at the given offset is made. This can only succeed if the +pattern does not require the match to be at the start of the subject. +</P> +<br><b> +How <b>pcre_exec()</b> returns captured substrings +</b><br> +<P> +In general, a pattern matches a certain portion of the subject, and in +addition, further substrings from the subject may be picked out by parts of the +pattern. Following the usage in Jeffrey Friedl's book, this is called +"capturing" in what follows, and the phrase "capturing subpattern" is used for +a fragment of a pattern that picks out a substring. PCRE supports several other +kinds of parenthesized subpattern that do not cause substrings to be captured. +</P> +<P> +Captured substrings are returned to the caller via a vector of integers whose +address is passed in <i>ovector</i>. The number of elements in the vector is +passed in <i>ovecsize</i>, which must be a non-negative number. <b>Note</b>: this +argument is NOT the size of <i>ovector</i> in bytes. +</P> +<P> +The first two-thirds of the vector is used to pass back captured substrings, +each substring using a pair of integers. The remaining third of the vector is +used as workspace by <b>pcre_exec()</b> while matching capturing subpatterns, +and is not available for passing back information. The number passed in +<i>ovecsize</i> should always be a multiple of three. If it is not, it is +rounded down. +</P> +<P> +When a match is successful, information about captured substrings is returned +in pairs of integers, starting at the beginning of <i>ovector</i>, and +continuing up to two-thirds of its length at the most. The first element of +each pair is set to the offset of the first character in a substring, and the +second is set to the offset of the first character after the end of a +substring. These values are always data unit offsets, even in UTF mode. They +are byte offsets in the 8-bit library, 16-bit data item offsets in the 16-bit +library, and 32-bit data item offsets in the 32-bit library. <b>Note</b>: they +are not character counts. +</P> +<P> +The first pair of integers, <i>ovector[0]</i> and <i>ovector[1]</i>, identify the +portion of the subject string matched by the entire pattern. The next pair is +used for the first capturing subpattern, and so on. The value returned by +<b>pcre_exec()</b> is one more than the highest numbered pair that has been set. +For example, if two substrings have been captured, the returned value is 3. If +there are no capturing subpatterns, the return value from a successful match is +1, indicating that just the first pair of offsets has been set. +</P> +<P> +If a capturing subpattern is matched repeatedly, it is the last portion of the +string that it matched that is returned. +</P> +<P> +If the vector is too small to hold all the captured substring offsets, it is +used as far as possible (up to two-thirds of its length), and the function +returns a value of zero. If neither the actual string matched nor any captured +substrings are of interest, <b>pcre_exec()</b> may be called with <i>ovector</i> +passed as NULL and <i>ovecsize</i> as zero. However, if the pattern contains +back references and the <i>ovector</i> is not big enough to remember the related +substrings, PCRE has to get additional memory for use during matching. Thus it +is usually advisable to supply an <i>ovector</i> of reasonable size. +</P> +<P> +There are some cases where zero is returned (indicating vector overflow) when +in fact the vector is exactly the right size for the final match. For example, +consider the pattern +<pre> + (a)(?:(b)c|bd) +</pre> +If a vector of 6 elements (allowing for only 1 captured substring) is given +with subject string "abd", <b>pcre_exec()</b> will try to set the second +captured string, thereby recording a vector overflow, before failing to match +"c" and backing up to try the second alternative. The zero return, however, +does correctly indicate that the maximum number of slots (namely 2) have been +filled. In similar cases where there is temporary overflow, but the final +number of used slots is actually less than the maximum, a non-zero value is +returned. +</P> +<P> +The <b>pcre_fullinfo()</b> function can be used to find out how many capturing +subpatterns there are in a compiled pattern. The smallest size for +<i>ovector</i> that will allow for <i>n</i> captured substrings, in addition to +the offsets of the substring matched by the whole pattern, is (<i>n</i>+1)*3. +</P> +<P> +It is possible for capturing subpattern number <i>n+1</i> to match some part of +the subject when subpattern <i>n</i> has not been used at all. For example, if +the string "abc" is matched against the pattern (a|(z))(bc) the return from the +function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this +happens, both values in the offset pairs corresponding to unused subpatterns +are set to -1. +</P> +<P> +Offset values that correspond to unused subpatterns at the end of the +expression are also set to -1. For example, if the string "abc" is matched +against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The +return from the function is 2, because the highest used capturing subpattern +number is 1, and the offsets for for the second and third capturing subpatterns +(assuming the vector is large enough, of course) are set to -1. +</P> +<P> +<b>Note</b>: Elements in the first two-thirds of <i>ovector</i> that do not +correspond to capturing parentheses in the pattern are never changed. That is, +if a pattern contains <i>n</i> capturing parentheses, no more than +<i>ovector[0]</i> to <i>ovector[2n+1]</i> are set by <b>pcre_exec()</b>. The other +elements (in the first two-thirds) retain whatever values they previously had. +</P> +<P> +Some convenience functions are provided for extracting the captured substrings +as separate strings. These are described below. +<a name="errorlist"></a></P> +<br><b> +Error return values from <b>pcre_exec()</b> +</b><br> +<P> +If <b>pcre_exec()</b> fails, it returns a negative number. The following are +defined in the header file: +<pre> + PCRE_ERROR_NOMATCH (-1) +</pre> +The subject string did not match the pattern. +<pre> + PCRE_ERROR_NULL (-2) +</pre> +Either <i>code</i> or <i>subject</i> was passed as NULL, or <i>ovector</i> was +NULL and <i>ovecsize</i> was not zero. +<pre> + PCRE_ERROR_BADOPTION (-3) +</pre> +An unrecognized bit was set in the <i>options</i> argument. +<pre> + PCRE_ERROR_BADMAGIC (-4) +</pre> +PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch +the case when it is passed a junk pointer and to detect when a pattern that was +compiled in an environment of one endianness is run in an environment with the +other endianness. This is the error that PCRE gives when the magic number is +not present. +<pre> + PCRE_ERROR_UNKNOWN_OPCODE (-5) +</pre> +While running the pattern match, an unknown item was encountered in the +compiled pattern. This error could be caused by a bug in PCRE or by overwriting +of the compiled pattern. +<pre> + PCRE_ERROR_NOMEMORY (-6) +</pre> +If a pattern contains back references, but the <i>ovector</i> that is passed to +<b>pcre_exec()</b> is not big enough to remember the referenced substrings, PCRE +gets a block of memory at the start of matching to use for this purpose. If the +call via <b>pcre_malloc()</b> fails, this error is given. The memory is +automatically freed at the end of matching. +</P> +<P> +This error is also given if <b>pcre_stack_malloc()</b> fails in +<b>pcre_exec()</b>. This can happen only when PCRE has been compiled with +<b>--disable-stack-for-recursion</b>. +<pre> + PCRE_ERROR_NOSUBSTRING (-7) +</pre> +This error is used by the <b>pcre_copy_substring()</b>, +<b>pcre_get_substring()</b>, and <b>pcre_get_substring_list()</b> functions (see +below). It is never returned by <b>pcre_exec()</b>. +<pre> + PCRE_ERROR_MATCHLIMIT (-8) +</pre> +The backtracking limit, as specified by the <i>match_limit</i> field in a +<b>pcre_extra</b> structure (or defaulted) was reached. See the description +above. +<pre> + PCRE_ERROR_CALLOUT (-9) +</pre> +This error is never generated by <b>pcre_exec()</b> itself. It is provided for +use by callout functions that want to yield a distinctive error code. See the +<a href="pcrecallout.html"><b>pcrecallout</b></a> +documentation for details. +<pre> + PCRE_ERROR_BADUTF8 (-10) +</pre> +A string that contains an invalid UTF-8 byte sequence was passed as a subject, +and the PCRE_NO_UTF8_CHECK option was not set. If the size of the output vector +(<i>ovecsize</i>) is at least 2, the byte offset to the start of the the invalid +UTF-8 character is placed in the first element, and a reason code is placed in +the second element. The reason codes are listed in the +<a href="#badutf8reasons">following section.</a> +For backward compatibility, if PCRE_PARTIAL_HARD is set and the problem is a +truncated UTF-8 character at the end of the subject (reason codes 1 to 5), +PCRE_ERROR_SHORTUTF8 is returned instead of PCRE_ERROR_BADUTF8. +<pre> + PCRE_ERROR_BADUTF8_OFFSET (-11) +</pre> +The UTF-8 byte sequence that was passed as a subject was checked and found to +be valid (the PCRE_NO_UTF8_CHECK option was not set), but the value of +<i>startoffset</i> did not point to the beginning of a UTF-8 character or the +end of the subject. +<pre> + PCRE_ERROR_PARTIAL (-12) +</pre> +The subject string did not match, but it did match partially. See the +<a href="pcrepartial.html"><b>pcrepartial</b></a> +documentation for details of partial matching. +<pre> + PCRE_ERROR_BADPARTIAL (-13) +</pre> +This code is no longer in use. It was formerly returned when the PCRE_PARTIAL +option was used with a compiled pattern containing items that were not +supported for partial matching. From release 8.00 onwards, there are no +restrictions on partial matching. +<pre> + PCRE_ERROR_INTERNAL (-14) +</pre> +An unexpected internal error has occurred. This error could be caused by a bug +in PCRE or by overwriting of the compiled pattern. +<pre> + PCRE_ERROR_BADCOUNT (-15) +</pre> +This error is given if the value of the <i>ovecsize</i> argument is negative. +<pre> + PCRE_ERROR_RECURSIONLIMIT (-21) +</pre> +The internal recursion limit, as specified by the <i>match_limit_recursion</i> +field in a <b>pcre_extra</b> structure (or defaulted) was reached. See the +description above. +<pre> + PCRE_ERROR_BADNEWLINE (-23) +</pre> +An invalid combination of PCRE_NEWLINE_<i>xxx</i> options was given. +<pre> + PCRE_ERROR_BADOFFSET (-24) +</pre> +The value of <i>startoffset</i> was negative or greater than the length of the +subject, that is, the value in <i>length</i>. +<pre> + PCRE_ERROR_SHORTUTF8 (-25) +</pre> +This error is returned instead of PCRE_ERROR_BADUTF8 when the subject string +ends with a truncated UTF-8 character and the PCRE_PARTIAL_HARD option is set. +Information about the failure is returned as for PCRE_ERROR_BADUTF8. It is in +fact sufficient to detect this case, but this special error code for +PCRE_PARTIAL_HARD precedes the implementation of returned information; it is +retained for backwards compatibility. +<pre> + PCRE_ERROR_RECURSELOOP (-26) +</pre> +This error is returned when <b>pcre_exec()</b> detects a recursion loop within +the pattern. Specifically, it means that either the whole pattern or a +subpattern has been called recursively for the second time at the same position +in the subject string. Some simple patterns that might do this are detected and +faulted at compile time, but more complicated cases, in particular mutual +recursions between two different subpatterns, cannot be detected until run +time. +<pre> + PCRE_ERROR_JIT_STACKLIMIT (-27) +</pre> +This error is returned when a pattern that was successfully studied using a +JIT compile option is being matched, but the memory available for the +just-in-time processing stack is not large enough. See the +<a href="pcrejit.html"><b>pcrejit</b></a> +documentation for more details. +<pre> + PCRE_ERROR_BADMODE (-28) +</pre> +This error is given if a pattern that was compiled by the 8-bit library is +passed to a 16-bit or 32-bit library function, or vice versa. +<pre> + PCRE_ERROR_BADENDIANNESS (-29) +</pre> +This error is given if a pattern that was compiled and saved is reloaded on a +host with different endianness. The utility function +<b>pcre_pattern_to_host_byte_order()</b> can be used to convert such a pattern +so that it runs on the new host. +<pre> + PCRE_ERROR_JIT_BADOPTION +</pre> +This error is returned when a pattern that was successfully studied using a JIT +compile option is being matched, but the matching mode (partial or complete +match) does not correspond to any JIT compilation mode. When the JIT fast path +function is used, this error may be also given for invalid options. See the +<a href="pcrejit.html"><b>pcrejit</b></a> +documentation for more details. +<pre> + PCRE_ERROR_BADLENGTH (-32) +</pre> +This error is given if <b>pcre_exec()</b> is called with a negative value for +the <i>length</i> argument. +</P> +<P> +Error numbers -16 to -20, -22, and 30 are not used by <b>pcre_exec()</b>. +<a name="badutf8reasons"></a></P> +<br><b> +Reason codes for invalid UTF-8 strings +</b><br> +<P> +This section applies only to the 8-bit library. The corresponding information +for the 16-bit and 32-bit libraries is given in the +<a href="pcre16.html"><b>pcre16</b></a> +and +<a href="pcre32.html"><b>pcre32</b></a> +pages. +</P> +<P> +When <b>pcre_exec()</b> returns either PCRE_ERROR_BADUTF8 or +PCRE_ERROR_SHORTUTF8, and the size of the output vector (<i>ovecsize</i>) is at +least 2, the offset of the start of the invalid UTF-8 character is placed in +the first output vector element (<i>ovector[0]</i>) and a reason code is placed +in the second element (<i>ovector[1]</i>). The reason codes are given names in +the <b>pcre.h</b> header file: +<pre> + PCRE_UTF8_ERR1 + PCRE_UTF8_ERR2 + PCRE_UTF8_ERR3 + PCRE_UTF8_ERR4 + PCRE_UTF8_ERR5 +</pre> +The string ends with a truncated UTF-8 character; the code specifies how many +bytes are missing (1 to 5). Although RFC 3629 restricts UTF-8 characters to be +no longer than 4 bytes, the encoding scheme (originally defined by RFC 2279) +allows for up to 6 bytes, and this is checked first; hence the possibility of +4 or 5 missing bytes. +<pre> + PCRE_UTF8_ERR6 + PCRE_UTF8_ERR7 + PCRE_UTF8_ERR8 + PCRE_UTF8_ERR9 + PCRE_UTF8_ERR10 +</pre> +The two most significant bits of the 2nd, 3rd, 4th, 5th, or 6th byte of the +character do not have the binary value 0b10 (that is, either the most +significant bit is 0, or the next bit is 1). +<pre> + PCRE_UTF8_ERR11 + PCRE_UTF8_ERR12 +</pre> +A character that is valid by the RFC 2279 rules is either 5 or 6 bytes long; +these code points are excluded by RFC 3629. +<pre> + PCRE_UTF8_ERR13 +</pre> +A 4-byte character has a value greater than 0x10fff; these code points are +excluded by RFC 3629. +<pre> + PCRE_UTF8_ERR14 +</pre> +A 3-byte character has a value in the range 0xd800 to 0xdfff; this range of +code points are reserved by RFC 3629 for use with UTF-16, and so are excluded +from UTF-8. +<pre> + PCRE_UTF8_ERR15 + PCRE_UTF8_ERR16 + PCRE_UTF8_ERR17 + PCRE_UTF8_ERR18 + PCRE_UTF8_ERR19 +</pre> +A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes for a +value that can be represented by fewer bytes, which is invalid. For example, +the two bytes 0xc0, 0xae give the value 0x2e, whose correct coding uses just +one byte. +<pre> + PCRE_UTF8_ERR20 +</pre> +The two most significant bits of the first byte of a character have the binary +value 0b10 (that is, the most significant bit is 1 and the second is 0). Such a +byte can only validly occur as the second or subsequent byte of a multi-byte +character. +<pre> + PCRE_UTF8_ERR21 +</pre> +The first byte of a character has the value 0xfe or 0xff. These values can +never occur in a valid UTF-8 string. +<pre> + PCRE_UTF8_ERR22 +</pre> +This error code was formerly used when the presence of a so-called +"non-character" caused an error. Unicode corrigendum #9 makes it clear that +such characters should not cause a string to be rejected, and so this code is +no longer in use and is never returned. +</P> +<br><a name="SEC18" href="#TOC1">EXTRACTING CAPTURED SUBSTRINGS BY NUMBER</a><br> +<P> +<b>int pcre_copy_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, int <i>stringnumber</i>, char *<i>buffer</i>,</b> +<b> int <i>buffersize</i>);</b> +<br> +<br> +<b>int pcre_get_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, int <i>stringnumber</i>,</b> +<b> const char **<i>stringptr</i>);</b> +<br> +<br> +<b>int pcre_get_substring_list(const char *<i>subject</i>,</b> +<b> int *<i>ovector</i>, int <i>stringcount</i>, const char ***<i>listptr</i>);</b> +</P> +<P> +Captured substrings can be accessed directly by using the offsets returned by +<b>pcre_exec()</b> in <i>ovector</i>. For convenience, the functions +<b>pcre_copy_substring()</b>, <b>pcre_get_substring()</b>, and +<b>pcre_get_substring_list()</b> are provided for extracting captured substrings +as new, separate, zero-terminated strings. These functions identify substrings +by number. The next section describes functions for extracting named +substrings. +</P> +<P> +A substring that contains a binary zero is correctly extracted and has a +further zero added on the end, but the result is not, of course, a C string. +However, you can process such a string by referring to the length that is +returned by <b>pcre_copy_substring()</b> and <b>pcre_get_substring()</b>. +Unfortunately, the interface to <b>pcre_get_substring_list()</b> is not adequate +for handling strings containing binary zeros, because the end of the final +string is not independently indicated. +</P> +<P> +The first three arguments are the same for all three of these functions: +<i>subject</i> is the subject string that has just been successfully matched, +<i>ovector</i> is a pointer to the vector of integer offsets that was passed to +<b>pcre_exec()</b>, and <i>stringcount</i> is the number of substrings that were +captured by the match, including the substring that matched the entire regular +expression. This is the value returned by <b>pcre_exec()</b> if it is greater +than zero. If <b>pcre_exec()</b> returned zero, indicating that it ran out of +space in <i>ovector</i>, the value passed as <i>stringcount</i> should be the +number of elements in the vector divided by three. +</P> +<P> +The functions <b>pcre_copy_substring()</b> and <b>pcre_get_substring()</b> +extract a single substring, whose number is given as <i>stringnumber</i>. A +value of zero extracts the substring that matched the entire pattern, whereas +higher values extract the captured substrings. For <b>pcre_copy_substring()</b>, +the string is placed in <i>buffer</i>, whose length is given by +<i>buffersize</i>, while for <b>pcre_get_substring()</b> a new block of memory is +obtained via <b>pcre_malloc</b>, and its address is returned via +<i>stringptr</i>. The yield of the function is the length of the string, not +including the terminating zero, or one of these error codes: +<pre> + PCRE_ERROR_NOMEMORY (-6) +</pre> +The buffer was too small for <b>pcre_copy_substring()</b>, or the attempt to get +memory failed for <b>pcre_get_substring()</b>. +<pre> + PCRE_ERROR_NOSUBSTRING (-7) +</pre> +There is no substring whose number is <i>stringnumber</i>. +</P> +<P> +The <b>pcre_get_substring_list()</b> function extracts all available substrings +and builds a list of pointers to them. All this is done in a single block of +memory that is obtained via <b>pcre_malloc</b>. The address of the memory block +is returned via <i>listptr</i>, which is also the start of the list of string +pointers. The end of the list is marked by a NULL pointer. The yield of the +function is zero if all went well, or the error code +<pre> + PCRE_ERROR_NOMEMORY (-6) +</pre> +if the attempt to get the memory block failed. +</P> +<P> +When any of these functions encounter a substring that is unset, which can +happen when capturing subpattern number <i>n+1</i> matches some part of the +subject, but subpattern <i>n</i> has not been used at all, they return an empty +string. This can be distinguished from a genuine zero-length substring by +inspecting the appropriate offset in <i>ovector</i>, which is negative for unset +substrings. +</P> +<P> +The two convenience functions <b>pcre_free_substring()</b> and +<b>pcre_free_substring_list()</b> can be used to free the memory returned by +a previous call of <b>pcre_get_substring()</b> or +<b>pcre_get_substring_list()</b>, respectively. They do nothing more than call +the function pointed to by <b>pcre_free</b>, which of course could be called +directly from a C program. However, PCRE is used in some situations where it is +linked via a special interface to another programming language that cannot use +<b>pcre_free</b> directly; it is for these cases that the functions are +provided. +</P> +<br><a name="SEC19" href="#TOC1">EXTRACTING CAPTURED SUBSTRINGS BY NAME</a><br> +<P> +<b>int pcre_get_stringnumber(const pcre *<i>code</i>,</b> +<b> const char *<i>name</i>);</b> +<br> +<br> +<b>int pcre_copy_named_substring(const pcre *<i>code</i>,</b> +<b> const char *<i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, const char *<i>stringname</i>,</b> +<b> char *<i>buffer</i>, int <i>buffersize</i>);</b> +<br> +<br> +<b>int pcre_get_named_substring(const pcre *<i>code</i>,</b> +<b> const char *<i>subject</i>, int *<i>ovector</i>,</b> +<b> int <i>stringcount</i>, const char *<i>stringname</i>,</b> +<b> const char **<i>stringptr</i>);</b> +</P> +<P> +To extract a substring by name, you first have to find associated number. +For example, for this pattern +<pre> + (a+)b(?<xxx>\d+)... +</pre> +the number of the subpattern called "xxx" is 2. If the name is known to be +unique (PCRE_DUPNAMES was not set), you can find the number from the name by +calling <b>pcre_get_stringnumber()</b>. The first argument is the compiled +pattern, and the second is the name. The yield of the function is the +subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no subpattern of +that name. +</P> +<P> +Given the number, you can extract the substring directly, or use one of the +functions described in the previous section. For convenience, there are also +two functions that do the whole job. +</P> +<P> +Most of the arguments of <b>pcre_copy_named_substring()</b> and +<b>pcre_get_named_substring()</b> are the same as those for the similarly named +functions that extract by number. As these are described in the previous +section, they are not re-described here. There are just two differences: +</P> +<P> +First, instead of a substring number, a substring name is given. Second, there +is an extra argument, given at the start, which is a pointer to the compiled +pattern. This is needed in order to gain access to the name-to-number +translation table. +</P> +<P> +These functions call <b>pcre_get_stringnumber()</b>, and if it succeeds, they +then call <b>pcre_copy_substring()</b> or <b>pcre_get_substring()</b>, as +appropriate. <b>NOTE:</b> If PCRE_DUPNAMES is set and there are duplicate names, +the behaviour may not be what you want (see the next section). +</P> +<P> +<b>Warning:</b> If the pattern uses the (?| feature to set up multiple +subpatterns with the same number, as described in the +<a href="pcrepattern.html#dupsubpatternnumber">section on duplicate subpattern numbers</a> +in the +<a href="pcrepattern.html"><b>pcrepattern</b></a> +page, you cannot use names to distinguish the different subpatterns, because +names are not included in the compiled code. The matching process uses only +numbers. For this reason, the use of different names for subpatterns of the +same number causes an error at compile time. +</P> +<br><a name="SEC20" href="#TOC1">DUPLICATE SUBPATTERN NAMES</a><br> +<P> +<b>int pcre_get_stringtable_entries(const pcre *<i>code</i>,</b> +<b> const char *<i>name</i>, char **<i>first</i>, char **<i>last</i>);</b> +</P> +<P> +When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns +are not required to be unique. (Duplicate names are always allowed for +subpatterns with the same number, created by using the (?| feature. Indeed, if +such subpatterns are named, they are required to use the same names.) +</P> +<P> +Normally, patterns with duplicate names are such that in any one match, only +one of the named subpatterns participates. An example is shown in the +<a href="pcrepattern.html"><b>pcrepattern</b></a> +documentation. +</P> +<P> +When duplicates are present, <b>pcre_copy_named_substring()</b> and +<b>pcre_get_named_substring()</b> return the first substring corresponding to +the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING (-7) is +returned; no data is returned. The <b>pcre_get_stringnumber()</b> function +returns one of the numbers that are associated with the name, but it is not +defined which it is. +</P> +<P> +If you want to get full details of all captured substrings for a given name, +you must use the <b>pcre_get_stringtable_entries()</b> function. The first +argument is the compiled pattern, and the second is the name. The third and +fourth are pointers to variables which are updated by the function. After it +has run, they point to the first and last entries in the name-to-number table +for the given name. The function itself returns the length of each entry, or +PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is +described above in the section entitled <i>Information about a pattern</i> +<a href="#infoaboutpattern">above.</a> +Given all the relevant entries for the name, you can extract each of their +numbers, and hence the captured data, if any. +</P> +<br><a name="SEC21" href="#TOC1">FINDING ALL POSSIBLE MATCHES</a><br> +<P> +The traditional matching function uses a similar algorithm to Perl, which stops +when it finds the first match, starting at a given point in the subject. If you +want to find all possible matches, or the longest possible match, consider +using the alternative matching function (see below) instead. If you cannot use +the alternative function, but still need to find all possible matches, you +can kludge it up by making use of the callout facility, which is described in +the +<a href="pcrecallout.html"><b>pcrecallout</b></a> +documentation. +</P> +<P> +What you have to do is to insert a callout right at the end of the pattern. +When your callout function is called, extract and save the current matched +substring. Then return 1, which forces <b>pcre_exec()</b> to backtrack and try +other alternatives. Ultimately, when it runs out of matches, <b>pcre_exec()</b> +will yield PCRE_ERROR_NOMATCH. +</P> +<br><a name="SEC22" href="#TOC1">OBTAINING AN ESTIMATE OF STACK USAGE</a><br> +<P> +Matching certain patterns using <b>pcre_exec()</b> can use a lot of process +stack, which in certain environments can be rather limited in size. Some users +find it helpful to have an estimate of the amount of stack that is used by +<b>pcre_exec()</b>, to help them set recursion limits, as described in the +<a href="pcrestack.html"><b>pcrestack</b></a> +documentation. The estimate that is output by <b>pcretest</b> when called with +the <b>-m</b> and <b>-C</b> options is obtained by calling <b>pcre_exec</b> with +the values NULL, NULL, NULL, -999, and -999 for its first five arguments. +</P> +<P> +Normally, if its first argument is NULL, <b>pcre_exec()</b> immediately returns +the negative error code PCRE_ERROR_NULL, but with this special combination of +arguments, it returns instead a negative number whose absolute value is the +approximate stack frame size in bytes. (A negative number is used so that it is +clear that no match has happened.) The value is approximate because in some +cases, recursive calls to <b>pcre_exec()</b> occur when there are one or two +additional variables on the stack. +</P> +<P> +If PCRE has been compiled to use the heap instead of the stack for recursion, +the value returned is the size of each block that is obtained from the heap. +<a name="dfamatch"></a></P> +<br><a name="SEC23" href="#TOC1">MATCHING A PATTERN: THE ALTERNATIVE FUNCTION</a><br> +<P> +<b>int pcre_dfa_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b> +<b> const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b> +<b> int *<i>workspace</i>, int <i>wscount</i>);</b> +</P> +<P> +The function <b>pcre_dfa_exec()</b> is called to match a subject string against +a compiled pattern, using a matching algorithm that scans the subject string +just once, and does not backtrack. This has different characteristics to the +normal algorithm, and is not compatible with Perl. Some of the features of PCRE +patterns are not supported. Nevertheless, there are times when this kind of +matching can be useful. For a discussion of the two matching algorithms, and a +list of features that <b>pcre_dfa_exec()</b> does not support, see the +<a href="pcrematching.html"><b>pcrematching</b></a> +documentation. +</P> +<P> +The arguments for the <b>pcre_dfa_exec()</b> function are the same as for +<b>pcre_exec()</b>, plus two extras. The <i>ovector</i> argument is used in a +different way, and this is described below. The other common arguments are used +in the same way as for <b>pcre_exec()</b>, so their description is not repeated +here. +</P> +<P> +The two additional arguments provide workspace for the function. The workspace +vector should contain at least 20 elements. It is used for keeping track of +multiple paths through the pattern tree. More workspace will be needed for +patterns and subjects where there are a lot of potential matches. +</P> +<P> +Here is an example of a simple call to <b>pcre_dfa_exec()</b>: +<pre> + int rc; + int ovector[10]; + int wspace[20]; + rc = pcre_dfa_exec( + re, /* result of pcre_compile() */ + NULL, /* we didn't study the pattern */ + "some string", /* the subject string */ + 11, /* the length of the subject string */ + 0, /* start at offset 0 in the subject */ + 0, /* default options */ + ovector, /* vector of integers for substring information */ + 10, /* number of elements (NOT size in bytes) */ + wspace, /* working space vector */ + 20); /* number of elements (NOT size in bytes) */ +</PRE> +</P> +<br><b> +Option bits for <b>pcre_dfa_exec()</b> +</b><br> +<P> +The unused bits of the <i>options</i> argument for <b>pcre_dfa_exec()</b> must be +zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_<i>xxx</i>, +PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, +PCRE_NO_UTF8_CHECK, PCRE_BSR_ANYCRLF, PCRE_BSR_UNICODE, PCRE_NO_START_OPTIMIZE, +PCRE_PARTIAL_HARD, PCRE_PARTIAL_SOFT, PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. +All but the last four of these are exactly the same as for <b>pcre_exec()</b>, +so their description is not repeated here. +<pre> + PCRE_PARTIAL_HARD + PCRE_PARTIAL_SOFT +</pre> +These have the same general effect as they do for <b>pcre_exec()</b>, but the +details are slightly different. When PCRE_PARTIAL_HARD is set for +<b>pcre_dfa_exec()</b>, it returns PCRE_ERROR_PARTIAL if the end of the subject +is reached and there is still at least one matching possibility that requires +additional characters. This happens even if some complete matches have also +been found. When PCRE_PARTIAL_SOFT is set, the return code PCRE_ERROR_NOMATCH +is converted into PCRE_ERROR_PARTIAL if the end of the subject is reached, +there have been no complete matches, but there is still at least one matching +possibility. The portion of the string that was inspected when the longest +partial match was found is set as the first matching string in both cases. +There is a more detailed discussion of partial and multi-segment matching, with +examples, in the +<a href="pcrepartial.html"><b>pcrepartial</b></a> +documentation. +<pre> + PCRE_DFA_SHORTEST +</pre> +Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as +soon as it has found one match. Because of the way the alternative algorithm +works, this is necessarily the shortest possible match at the first possible +matching point in the subject string. +<pre> + PCRE_DFA_RESTART +</pre> +When <b>pcre_dfa_exec()</b> returns a partial match, it is possible to call it +again, with additional subject characters, and have it continue with the same +match. The PCRE_DFA_RESTART option requests this action; when it is set, the +<i>workspace</i> and <i>wscount</i> options must reference the same vector as +before because data about the match so far is left in them after a partial +match. There is more discussion of this facility in the +<a href="pcrepartial.html"><b>pcrepartial</b></a> +documentation. +</P> +<br><b> +Successful returns from <b>pcre_dfa_exec()</b> +</b><br> +<P> +When <b>pcre_dfa_exec()</b> succeeds, it may have matched more than one +substring in the subject. Note, however, that all the matches from one run of +the function start at the same point in the subject. The shorter matches are +all initial substrings of the longer matches. For example, if the pattern +<pre> + <.*> +</pre> +is matched against the string +<pre> + This is <something> <something else> <something further> no more +</pre> +the three matched strings are +<pre> + <something> + <something> <something else> + <something> <something else> <something further> +</pre> +On success, the yield of the function is a number greater than zero, which is +the number of matched substrings. The substrings themselves are returned in +<i>ovector</i>. Each string uses two elements; the first is the offset to the +start, and the second is the offset to the end. In fact, all the strings have +the same start offset. (Space could have been saved by giving this only once, +but it was decided to retain some compatibility with the way <b>pcre_exec()</b> +returns data, even though the meaning of the strings is different.) +</P> +<P> +The strings are returned in reverse order of length; that is, the longest +matching string is given first. If there were too many matches to fit into +<i>ovector</i>, the yield of the function is zero, and the vector is filled with +the longest matches. Unlike <b>pcre_exec()</b>, <b>pcre_dfa_exec()</b> can use +the entire <i>ovector</i> for returning matched strings. +</P> +<P> +NOTE: PCRE's "auto-possessification" optimization usually applies to character +repeats at the end of a pattern (as well as internally). For example, the +pattern "a\d+" is compiled as if it were "a\d++" because there is no point +even considering the possibility of backtracking into the repeated digits. For +DFA matching, this means that only one possible match is found. If you really +do want multiple matches in such cases, either use an ungreedy repeat +("a\d+?") or set the PCRE_NO_AUTO_POSSESS option when compiling. +</P> +<br><b> +Error returns from <b>pcre_dfa_exec()</b> +</b><br> +<P> +The <b>pcre_dfa_exec()</b> function returns a negative number when it fails. +Many of the errors are the same as for <b>pcre_exec()</b>, and these are +described +<a href="#errorlist">above.</a> +There are in addition the following errors that are specific to +<b>pcre_dfa_exec()</b>: +<pre> + PCRE_ERROR_DFA_UITEM (-16) +</pre> +This return is given if <b>pcre_dfa_exec()</b> encounters an item in the pattern +that it does not support, for instance, the use of \C or a back reference. +<pre> + PCRE_ERROR_DFA_UCOND (-17) +</pre> +This return is given if <b>pcre_dfa_exec()</b> encounters a condition item that +uses a back reference for the condition, or a test for recursion in a specific +group. These are not supported. +<pre> + PCRE_ERROR_DFA_UMLIMIT (-18) +</pre> +This return is given if <b>pcre_dfa_exec()</b> is called with an <i>extra</i> +block that contains a setting of the <i>match_limit</i> or +<i>match_limit_recursion</i> fields. This is not supported (these fields are +meaningless for DFA matching). +<pre> + PCRE_ERROR_DFA_WSSIZE (-19) +</pre> +This return is given if <b>pcre_dfa_exec()</b> runs out of space in the +<i>workspace</i> vector. +<pre> + PCRE_ERROR_DFA_RECURSE (-20) +</pre> +When a recursive subpattern is processed, the matching function calls itself +recursively, using private vectors for <i>ovector</i> and <i>workspace</i>. This +error is given if the output vector is not large enough. This should be +extremely rare, as a vector of size 1000 is used. +<pre> + PCRE_ERROR_DFA_BADRESTART (-30) +</pre> +When <b>pcre_dfa_exec()</b> is called with the <b>PCRE_DFA_RESTART</b> option, +some plausibility checks are made on the contents of the workspace, which +should contain data about the previous partial match. If any of these checks +fail, this error is given. +</P> +<br><a name="SEC24" href="#TOC1">SEE ALSO</a><br> +<P> +<b>pcre16</b>(3), <b>pcre32</b>(3), <b>pcrebuild</b>(3), <b>pcrecallout</b>(3), +<b>pcrecpp(3)</b>(3), <b>pcrematching</b>(3), <b>pcrepartial</b>(3), +<b>pcreposix</b>(3), <b>pcreprecompile</b>(3), <b>pcresample</b>(3), +<b>pcrestack</b>(3). +</P> +<br><a name="SEC25" href="#TOC1">AUTHOR</a><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><a name="SEC26" href="#TOC1">REVISION</a><br> +<P> +Last updated: 09 February 2014 +<br> +Copyright © 1997-2014 University of Cambridge. +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcrebuild.html b/plugins/Pcre16/docs/doc/html/pcrebuild.html new file mode 100644 index 0000000000..03c8cbe0b2 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcrebuild.html @@ -0,0 +1,534 @@ +<html> +<head> +<title>pcrebuild specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcrebuild man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<ul> +<li><a name="TOC1" href="#SEC1">BUILDING PCRE</a> +<li><a name="TOC2" href="#SEC2">PCRE BUILD-TIME OPTIONS</a> +<li><a name="TOC3" href="#SEC3">BUILDING 8-BIT, 16-BIT AND 32-BIT LIBRARIES</a> +<li><a name="TOC4" href="#SEC4">BUILDING SHARED AND STATIC LIBRARIES</a> +<li><a name="TOC5" href="#SEC5">C++ SUPPORT</a> +<li><a name="TOC6" href="#SEC6">UTF-8, UTF-16 AND UTF-32 SUPPORT</a> +<li><a name="TOC7" href="#SEC7">UNICODE CHARACTER PROPERTY SUPPORT</a> +<li><a name="TOC8" href="#SEC8">JUST-IN-TIME COMPILER SUPPORT</a> +<li><a name="TOC9" href="#SEC9">CODE VALUE OF NEWLINE</a> +<li><a name="TOC10" href="#SEC10">WHAT \R MATCHES</a> +<li><a name="TOC11" href="#SEC11">POSIX MALLOC USAGE</a> +<li><a name="TOC12" href="#SEC12">HANDLING VERY LARGE PATTERNS</a> +<li><a name="TOC13" href="#SEC13">AVOIDING EXCESSIVE STACK USAGE</a> +<li><a name="TOC14" href="#SEC14">LIMITING PCRE RESOURCE USAGE</a> +<li><a name="TOC15" href="#SEC15">CREATING CHARACTER TABLES AT BUILD TIME</a> +<li><a name="TOC16" href="#SEC16">USING EBCDIC CODE</a> +<li><a name="TOC17" href="#SEC17">PCREGREP OPTIONS FOR COMPRESSED FILE SUPPORT</a> +<li><a name="TOC18" href="#SEC18">PCREGREP BUFFER SIZE</a> +<li><a name="TOC19" href="#SEC19">PCRETEST OPTION FOR LIBREADLINE SUPPORT</a> +<li><a name="TOC20" href="#SEC20">DEBUGGING WITH VALGRIND SUPPORT</a> +<li><a name="TOC21" href="#SEC21">CODE COVERAGE REPORTING</a> +<li><a name="TOC22" href="#SEC22">SEE ALSO</a> +<li><a name="TOC23" href="#SEC23">AUTHOR</a> +<li><a name="TOC24" href="#SEC24">REVISION</a> +</ul> +<br><a name="SEC1" href="#TOC1">BUILDING PCRE</a><br> +<P> +PCRE is distributed with a <b>configure</b> script that can be used to build the +library in Unix-like environments using the applications known as Autotools. +Also in the distribution are files to support building using <b>CMake</b> +instead of <b>configure</b>. The text file +<a href="README.txt"><b>README</b></a> +contains general information about building with Autotools (some of which is +repeated below), and also has some comments about building on various operating +systems. There is a lot more information about building PCRE without using +Autotools (including information about using <b>CMake</b> and building "by +hand") in the text file called +<a href="NON-AUTOTOOLS-BUILD.txt"><b>NON-AUTOTOOLS-BUILD</b>.</a> +You should consult this file as well as the +<a href="README.txt"><b>README</b></a> +file if you are building in a non-Unix-like environment. +</P> +<br><a name="SEC2" href="#TOC1">PCRE BUILD-TIME OPTIONS</a><br> +<P> +The rest of this document describes the optional features of PCRE that can be +selected when the library is compiled. It assumes use of the <b>configure</b> +script, where the optional features are selected or deselected by providing +options to <b>configure</b> before running the <b>make</b> command. However, the +same options can be selected in both Unix-like and non-Unix-like environments +using the GUI facility of <b>cmake-gui</b> if you are using <b>CMake</b> instead +of <b>configure</b> to build PCRE. +</P> +<P> +If you are not using Autotools or <b>CMake</b>, option selection can be done by +editing the <b>config.h</b> file, or by passing parameter settings to the +compiler, as described in +<a href="NON-AUTOTOOLS-BUILD.txt"><b>NON-AUTOTOOLS-BUILD</b>.</a> +</P> +<P> +The complete list of options for <b>configure</b> (which includes the standard +ones such as the selection of the installation directory) can be obtained by +running +<pre> + ./configure --help +</pre> +The following sections include descriptions of options whose names begin with +--enable or --disable. These settings specify changes to the defaults for the +<b>configure</b> command. Because of the way that <b>configure</b> works, +--enable and --disable always come in pairs, so the complementary option always +exists as well, but as it specifies the default, it is not described. +</P> +<br><a name="SEC3" href="#TOC1">BUILDING 8-BIT, 16-BIT AND 32-BIT LIBRARIES</a><br> +<P> +By default, a library called <b>libpcre</b> is built, containing functions that +take string arguments contained in vectors of bytes, either as single-byte +characters, or interpreted as UTF-8 strings. You can also build a separate +library, called <b>libpcre16</b>, in which strings are contained in vectors of +16-bit data units and interpreted either as single-unit characters or UTF-16 +strings, by adding +<pre> + --enable-pcre16 +</pre> +to the <b>configure</b> command. You can also build yet another separate +library, called <b>libpcre32</b>, in which strings are contained in vectors of +32-bit data units and interpreted either as single-unit characters or UTF-32 +strings, by adding +<pre> + --enable-pcre32 +</pre> +to the <b>configure</b> command. If you do not want the 8-bit library, add +<pre> + --disable-pcre8 +</pre> +as well. At least one of the three libraries must be built. Note that the C++ +and POSIX wrappers are for the 8-bit library only, and that <b>pcregrep</b> is +an 8-bit program. None of these are built if you select only the 16-bit or +32-bit libraries. +</P> +<br><a name="SEC4" href="#TOC1">BUILDING SHARED AND STATIC LIBRARIES</a><br> +<P> +The Autotools PCRE building process uses <b>libtool</b> to build both shared and +static libraries by default. You can suppress one of these by adding one of +<pre> + --disable-shared + --disable-static +</pre> +to the <b>configure</b> command, as required. +</P> +<br><a name="SEC5" href="#TOC1">C++ SUPPORT</a><br> +<P> +By default, if the 8-bit library is being built, the <b>configure</b> script +will search for a C++ compiler and C++ header files. If it finds them, it +automatically builds the C++ wrapper library (which supports only 8-bit +strings). You can disable this by adding +<pre> + --disable-cpp +</pre> +to the <b>configure</b> command. +</P> +<br><a name="SEC6" href="#TOC1">UTF-8, UTF-16 AND UTF-32 SUPPORT</a><br> +<P> +To build PCRE with support for UTF Unicode character strings, add +<pre> + --enable-utf +</pre> +to the <b>configure</b> command. This setting applies to all three libraries, +adding support for UTF-8 to the 8-bit library, support for UTF-16 to the 16-bit +library, and support for UTF-32 to the to the 32-bit library. There are no +separate options for enabling UTF-8, UTF-16 and UTF-32 independently because +that would allow ridiculous settings such as requesting UTF-16 support while +building only the 8-bit library. It is not possible to build one library with +UTF support and another without in the same configuration. (For backwards +compatibility, --enable-utf8 is a synonym of --enable-utf.) +</P> +<P> +Of itself, this setting does not make PCRE treat strings as UTF-8, UTF-16 or +UTF-32. As well as compiling PCRE with this option, you also have have to set +the PCRE_UTF8, PCRE_UTF16 or PCRE_UTF32 option (as appropriate) when you call +one of the pattern compiling functions. +</P> +<P> +If you set --enable-utf when compiling in an EBCDIC environment, PCRE expects +its input to be either ASCII or UTF-8 (depending on the run-time option). It is +not possible to support both EBCDIC and UTF-8 codes in the same version of the +library. Consequently, --enable-utf and --enable-ebcdic are mutually +exclusive. +</P> +<br><a name="SEC7" href="#TOC1">UNICODE CHARACTER PROPERTY SUPPORT</a><br> +<P> +UTF support allows the libraries to process character codepoints up to 0x10ffff +in the strings that they handle. On its own, however, it does not provide any +facilities for accessing the properties of such characters. If you want to be +able to use the pattern escapes \P, \p, and \X, which refer to Unicode +character properties, you must add +<pre> + --enable-unicode-properties +</pre> +to the <b>configure</b> command. This implies UTF support, even if you have +not explicitly requested it. +</P> +<P> +Including Unicode property support adds around 30K of tables to the PCRE +library. Only the general category properties such as <i>Lu</i> and <i>Nd</i> are +supported. Details are given in the +<a href="pcrepattern.html"><b>pcrepattern</b></a> +documentation. +</P> +<br><a name="SEC8" href="#TOC1">JUST-IN-TIME COMPILER SUPPORT</a><br> +<P> +Just-in-time compiler support is included in the build by specifying +<pre> + --enable-jit +</pre> +This support is available only for certain hardware architectures. If this +option is set for an unsupported architecture, a compile time error occurs. +See the +<a href="pcrejit.html"><b>pcrejit</b></a> +documentation for a discussion of JIT usage. When JIT support is enabled, +pcregrep automatically makes use of it, unless you add +<pre> + --disable-pcregrep-jit +</pre> +to the "configure" command. +</P> +<br><a name="SEC9" href="#TOC1">CODE VALUE OF NEWLINE</a><br> +<P> +By default, PCRE interprets the linefeed (LF) character as indicating the end +of a line. This is the normal newline character on Unix-like systems. You can +compile PCRE to use carriage return (CR) instead, by adding +<pre> + --enable-newline-is-cr +</pre> +to the <b>configure</b> command. There is also a --enable-newline-is-lf option, +which explicitly specifies linefeed as the newline character. +<br> +<br> +Alternatively, you can specify that line endings are to be indicated by the two +character sequence CRLF. If you want this, add +<pre> + --enable-newline-is-crlf +</pre> +to the <b>configure</b> command. There is a fourth option, specified by +<pre> + --enable-newline-is-anycrlf +</pre> +which causes PCRE to recognize any of the three sequences CR, LF, or CRLF as +indicating a line ending. Finally, a fifth option, specified by +<pre> + --enable-newline-is-any +</pre> +causes PCRE to recognize any Unicode newline sequence. +</P> +<P> +Whatever line ending convention is selected when PCRE is built can be +overridden when the library functions are called. At build time it is +conventional to use the standard for your operating system. +</P> +<br><a name="SEC10" href="#TOC1">WHAT \R MATCHES</a><br> +<P> +By default, the sequence \R in a pattern matches any Unicode newline sequence, +whatever has been selected as the line ending sequence. If you specify +<pre> + --enable-bsr-anycrlf +</pre> +the default is changed so that \R matches only CR, LF, or CRLF. Whatever is +selected when PCRE is built can be overridden when the library functions are +called. +</P> +<br><a name="SEC11" href="#TOC1">POSIX MALLOC USAGE</a><br> +<P> +When the 8-bit library is called through the POSIX interface (see the +<a href="pcreposix.html"><b>pcreposix</b></a> +documentation), additional working storage is required for holding the pointers +to capturing substrings, because PCRE requires three integers per substring, +whereas the POSIX interface provides only two. If the number of expected +substrings is small, the wrapper function uses space on the stack, because this +is faster than using <b>malloc()</b> for each call. The default threshold above +which the stack is no longer used is 10; it can be changed by adding a setting +such as +<pre> + --with-posix-malloc-threshold=20 +</pre> +to the <b>configure</b> command. +</P> +<br><a name="SEC12" href="#TOC1">HANDLING VERY LARGE PATTERNS</a><br> +<P> +Within a compiled pattern, offset values are used to point from one part to +another (for example, from an opening parenthesis to an alternation +metacharacter). By default, in the 8-bit and 16-bit libraries, two-byte values +are used for these offsets, leading to a maximum size for a compiled pattern of +around 64K. This is sufficient to handle all but the most gigantic patterns. +Nevertheless, some people do want to process truly enormous patterns, so it is +possible to compile PCRE to use three-byte or four-byte offsets by adding a +setting such as +<pre> + --with-link-size=3 +</pre> +to the <b>configure</b> command. The value given must be 2, 3, or 4. For the +16-bit library, a value of 3 is rounded up to 4. In these libraries, using +longer offsets slows down the operation of PCRE because it has to load +additional data when handling them. For the 32-bit library the value is always +4 and cannot be overridden; the value of --with-link-size is ignored. +</P> +<br><a name="SEC13" href="#TOC1">AVOIDING EXCESSIVE STACK USAGE</a><br> +<P> +When matching with the <b>pcre_exec()</b> function, PCRE implements backtracking +by making recursive calls to an internal function called <b>match()</b>. In +environments where the size of the stack is limited, this can severely limit +PCRE's operation. (The Unix environment does not usually suffer from this +problem, but it may sometimes be necessary to increase the maximum stack size. +There is a discussion in the +<a href="pcrestack.html"><b>pcrestack</b></a> +documentation.) An alternative approach to recursion that uses memory from the +heap to remember data, instead of using recursive function calls, has been +implemented to work round the problem of limited stack size. If you want to +build a version of PCRE that works this way, add +<pre> + --disable-stack-for-recursion +</pre> +to the <b>configure</b> command. With this configuration, PCRE will use the +<b>pcre_stack_malloc</b> and <b>pcre_stack_free</b> variables to call memory +management functions. By default these point to <b>malloc()</b> and +<b>free()</b>, but you can replace the pointers so that your own functions are +used instead. +</P> +<P> +Separate functions are provided rather than using <b>pcre_malloc</b> and +<b>pcre_free</b> because the usage is very predictable: the block sizes +requested are always the same, and the blocks are always freed in reverse +order. A calling program might be able to implement optimized functions that +perform better than <b>malloc()</b> and <b>free()</b>. PCRE runs noticeably more +slowly when built in this way. This option affects only the <b>pcre_exec()</b> +function; it is not relevant for <b>pcre_dfa_exec()</b>. +</P> +<br><a name="SEC14" href="#TOC1">LIMITING PCRE RESOURCE USAGE</a><br> +<P> +Internally, PCRE has a function called <b>match()</b>, which it calls repeatedly +(sometimes recursively) when matching a pattern with the <b>pcre_exec()</b> +function. By controlling the maximum number of times this function may be +called during a single matching operation, a limit can be placed on the +resources used by a single call to <b>pcre_exec()</b>. The limit can be changed +at run time, as described in the +<a href="pcreapi.html"><b>pcreapi</b></a> +documentation. The default is 10 million, but this can be changed by adding a +setting such as +<pre> + --with-match-limit=500000 +</pre> +to the <b>configure</b> command. This setting has no effect on the +<b>pcre_dfa_exec()</b> matching function. +</P> +<P> +In some environments it is desirable to limit the depth of recursive calls of +<b>match()</b> more strictly than the total number of calls, in order to +restrict the maximum amount of stack (or heap, if --disable-stack-for-recursion +is specified) that is used. A second limit controls this; it defaults to the +value that is set for --with-match-limit, which imposes no additional +constraints. However, you can set a lower limit by adding, for example, +<pre> + --with-match-limit-recursion=10000 +</pre> +to the <b>configure</b> command. This value can also be overridden at run time. +</P> +<br><a name="SEC15" href="#TOC1">CREATING CHARACTER TABLES AT BUILD TIME</a><br> +<P> +PCRE uses fixed tables for processing characters whose code values are less +than 256. By default, PCRE is built with a set of tables that are distributed +in the file <i>pcre_chartables.c.dist</i>. These tables are for ASCII codes +only. If you add +<pre> + --enable-rebuild-chartables +</pre> +to the <b>configure</b> command, the distributed tables are no longer used. +Instead, a program called <b>dftables</b> is compiled and run. This outputs the +source for new set of tables, created in the default locale of your C run-time +system. (This method of replacing the tables does not work if you are cross +compiling, because <b>dftables</b> is run on the local host. If you need to +create alternative tables when cross compiling, you will have to do so "by +hand".) +</P> +<br><a name="SEC16" href="#TOC1">USING EBCDIC CODE</a><br> +<P> +PCRE assumes by default that it will run in an environment where the character +code is ASCII (or Unicode, which is a superset of ASCII). This is the case for +most computer operating systems. PCRE can, however, be compiled to run in an +EBCDIC environment by adding +<pre> + --enable-ebcdic +</pre> +to the <b>configure</b> command. This setting implies +--enable-rebuild-chartables. You should only use it if you know that you are in +an EBCDIC environment (for example, an IBM mainframe operating system). The +--enable-ebcdic option is incompatible with --enable-utf. +</P> +<P> +The EBCDIC character that corresponds to an ASCII LF is assumed to have the +value 0x15 by default. However, in some EBCDIC environments, 0x25 is used. In +such an environment you should use +<pre> + --enable-ebcdic-nl25 +</pre> +as well as, or instead of, --enable-ebcdic. The EBCDIC character for CR has the +same value as in ASCII, namely, 0x0d. Whichever of 0x15 and 0x25 is <i>not</i> +chosen as LF is made to correspond to the Unicode NEL character (which, in +Unicode, is 0x85). +</P> +<P> +The options that select newline behaviour, such as --enable-newline-is-cr, +and equivalent run-time options, refer to these character values in an EBCDIC +environment. +</P> +<br><a name="SEC17" href="#TOC1">PCREGREP OPTIONS FOR COMPRESSED FILE SUPPORT</a><br> +<P> +By default, <b>pcregrep</b> reads all files as plain text. You can build it so +that it recognizes files whose names end in <b>.gz</b> or <b>.bz2</b>, and reads +them with <b>libz</b> or <b>libbz2</b>, respectively, by adding one or both of +<pre> + --enable-pcregrep-libz + --enable-pcregrep-libbz2 +</pre> +to the <b>configure</b> command. These options naturally require that the +relevant libraries are installed on your system. Configuration will fail if +they are not. +</P> +<br><a name="SEC18" href="#TOC1">PCREGREP BUFFER SIZE</a><br> +<P> +<b>pcregrep</b> uses an internal buffer to hold a "window" on the file it is +scanning, in order to be able to output "before" and "after" lines when it +finds a match. The size of the buffer is controlled by a parameter whose +default value is 20K. The buffer itself is three times this size, but because +of the way it is used for holding "before" lines, the longest line that is +guaranteed to be processable is the parameter size. You can change the default +parameter value by adding, for example, +<pre> + --with-pcregrep-bufsize=50K +</pre> +to the <b>configure</b> command. The caller of \fPpcregrep\fP can, however, +override this value by specifying a run-time option. +</P> +<br><a name="SEC19" href="#TOC1">PCRETEST OPTION FOR LIBREADLINE SUPPORT</a><br> +<P> +If you add +<pre> + --enable-pcretest-libreadline +</pre> +to the <b>configure</b> command, <b>pcretest</b> is linked with the +<b>libreadline</b> library, and when its input is from a terminal, it reads it +using the <b>readline()</b> function. This provides line-editing and history +facilities. Note that <b>libreadline</b> is GPL-licensed, so if you distribute a +binary of <b>pcretest</b> linked in this way, there may be licensing issues. +</P> +<P> +Setting this option causes the <b>-lreadline</b> option to be added to the +<b>pcretest</b> build. In many operating environments with a sytem-installed +<b>libreadline</b> this is sufficient. However, in some environments (e.g. +if an unmodified distribution version of readline is in use), some extra +configuration may be necessary. The INSTALL file for <b>libreadline</b> says +this: +<pre> + "Readline uses the termcap functions, but does not link with the + termcap or curses library itself, allowing applications which link + with readline the to choose an appropriate library." +</pre> +If your environment has not been set up so that an appropriate library is +automatically included, you may need to add something like +<pre> + LIBS="-ncurses" +</pre> +immediately before the <b>configure</b> command. +</P> +<br><a name="SEC20" href="#TOC1">DEBUGGING WITH VALGRIND SUPPORT</a><br> +<P> +By adding the +<pre> + --enable-valgrind +</pre> +option to to the <b>configure</b> command, PCRE will use valgrind annotations +to mark certain memory regions as unaddressable. This allows it to detect +invalid memory accesses, and is mostly useful for debugging PCRE itself. +</P> +<br><a name="SEC21" href="#TOC1">CODE COVERAGE REPORTING</a><br> +<P> +If your C compiler is gcc, you can build a version of PCRE that can generate a +code coverage report for its test suite. To enable this, you must install +<b>lcov</b> version 1.6 or above. Then specify +<pre> + --enable-coverage +</pre> +to the <b>configure</b> command and build PCRE in the usual way. +</P> +<P> +Note that using <b>ccache</b> (a caching C compiler) is incompatible with code +coverage reporting. If you have configured <b>ccache</b> to run automatically +on your system, you must set the environment variable +<pre> + CCACHE_DISABLE=1 +</pre> +before running <b>make</b> to build PCRE, so that <b>ccache</b> is not used. +</P> +<P> +When --enable-coverage is used, the following addition targets are added to the +<i>Makefile</i>: +<pre> + make coverage +</pre> +This creates a fresh coverage report for the PCRE test suite. It is equivalent +to running "make coverage-reset", "make coverage-baseline", "make check", and +then "make coverage-report". +<pre> + make coverage-reset +</pre> +This zeroes the coverage counters, but does nothing else. +<pre> + make coverage-baseline +</pre> +This captures baseline coverage information. +<pre> + make coverage-report +</pre> +This creates the coverage report. +<pre> + make coverage-clean-report +</pre> +This removes the generated coverage report without cleaning the coverage data +itself. +<pre> + make coverage-clean-data +</pre> +This removes the captured coverage data without removing the coverage files +created at compile time (*.gcno). +<pre> + make coverage-clean +</pre> +This cleans all coverage data including the generated coverage report. For more +information about code coverage, see the <b>gcov</b> and <b>lcov</b> +documentation. +</P> +<br><a name="SEC22" href="#TOC1">SEE ALSO</a><br> +<P> +<b>pcreapi</b>(3), <b>pcre16</b>, <b>pcre32</b>, <b>pcre_config</b>(3). +</P> +<br><a name="SEC23" href="#TOC1">AUTHOR</a><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><a name="SEC24" href="#TOC1">REVISION</a><br> +<P> +Last updated: 12 May 2013 +<br> +Copyright © 1997-2013 University of Cambridge. +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcrecallout.html b/plugins/Pcre16/docs/doc/html/pcrecallout.html new file mode 100644 index 0000000000..53a937f52d --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcrecallout.html @@ -0,0 +1,286 @@ +<html> +<head> +<title>pcrecallout specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcrecallout man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<ul> +<li><a name="TOC1" href="#SEC1">SYNOPSIS</a> +<li><a name="TOC2" href="#SEC2">DESCRIPTION</a> +<li><a name="TOC3" href="#SEC3">MISSING CALLOUTS</a> +<li><a name="TOC4" href="#SEC4">THE CALLOUT INTERFACE</a> +<li><a name="TOC5" href="#SEC5">RETURN VALUES</a> +<li><a name="TOC6" href="#SEC6">AUTHOR</a> +<li><a name="TOC7" href="#SEC7">REVISION</a> +</ul> +<br><a name="SEC1" href="#TOC1">SYNOPSIS</a><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>int (*pcre_callout)(pcre_callout_block *);</b> +</P> +<P> +<b>int (*pcre16_callout)(pcre16_callout_block *);</b> +</P> +<P> +<b>int (*pcre32_callout)(pcre32_callout_block *);</b> +</P> +<br><a name="SEC2" href="#TOC1">DESCRIPTION</a><br> +<P> +PCRE provides a feature called "callout", which is a means of temporarily +passing control to the caller of PCRE in the middle of pattern matching. The +caller of PCRE provides an external function by putting its entry point in the +global variable <i>pcre_callout</i> (<i>pcre16_callout</i> for the 16-bit +library, <i>pcre32_callout</i> for the 32-bit library). By default, this +variable contains NULL, which disables all calling out. +</P> +<P> +Within a regular expression, (?C) indicates the points at which the external +function is to be called. Different callout points can be identified by putting +a number less than 256 after the letter C. The default value is zero. +For example, this pattern has two callout points: +<pre> + (?C1)abc(?C2)def +</pre> +If the PCRE_AUTO_CALLOUT option bit is set when a pattern is compiled, PCRE +automatically inserts callouts, all with number 255, before each item in the +pattern. For example, if PCRE_AUTO_CALLOUT is used with the pattern +<pre> + A(\d{2}|--) +</pre> +it is processed as if it were +<br> +<br> +(?C255)A(?C255)((?C255)\d{2}(?C255)|(?C255)-(?C255)-(?C255))(?C255) +<br> +<br> +Notice that there is a callout before and after each parenthesis and +alternation bar. If the pattern contains a conditional group whose condition is +an assertion, an automatic callout is inserted immediately before the +condition. Such a callout may also be inserted explicitly, for example: +<pre> + (?(?C9)(?=a)ab|de) +</pre> +This applies only to assertion conditions (because they are themselves +independent groups). +</P> +<P> +Automatic callouts can be used for tracking the progress of pattern matching. +The +<a href="pcretest.html"><b>pcretest</b></a> +program has a pattern qualifier (/C) that sets automatic callouts; when it is +used, the output indicates how the pattern is being matched. This is useful +information when you are trying to optimize the performance of a particular +pattern. +</P> +<br><a name="SEC3" href="#TOC1">MISSING CALLOUTS</a><br> +<P> +You should be aware that, because of optimizations in the way PCRE compiles and +matches patterns, callouts sometimes do not happen exactly as you might expect. +</P> +<P> +At compile time, PCRE "auto-possessifies" repeated items when it knows that +what follows cannot be part of the repeat. For example, a+[bc] is compiled as +if it were a++[bc]. The <b>pcretest</b> output when this pattern is anchored and +then applied with automatic callouts to the string "aaaa" is: +<pre> + --->aaaa + +0 ^ ^ + +1 ^ a+ + +3 ^ ^ [bc] + No match +</pre> +This indicates that when matching [bc] fails, there is no backtracking into a+ +and therefore the callouts that would be taken for the backtracks do not occur. +You can disable the auto-possessify feature by passing PCRE_NO_AUTO_POSSESS +to <b>pcre_compile()</b>, or starting the pattern with (*NO_AUTO_POSSESS). If +this is done in <b>pcretest</b> (using the /O qualifier), the output changes to +this: +<pre> + --->aaaa + +0 ^ ^ + +1 ^ a+ + +3 ^ ^ [bc] + +3 ^ ^ [bc] + +3 ^ ^ [bc] + +3 ^^ [bc] + No match +</pre> +This time, when matching [bc] fails, the matcher backtracks into a+ and tries +again, repeatedly, until a+ itself fails. +</P> +<P> +Other optimizations that provide fast "no match" results also affect callouts. +For example, if the pattern is +<pre> + ab(?C4)cd +</pre> +PCRE knows that any matching string must contain the letter "d". If the subject +string is "abyz", the lack of "d" means that matching doesn't ever start, and +the callout is never reached. However, with "abyd", though the result is still +no match, the callout is obeyed. +</P> +<P> +If the pattern is studied, PCRE knows the minimum length of a matching string, +and will immediately give a "no match" return without actually running a match +if the subject is not long enough, or, for unanchored patterns, if it has +been scanned far enough. +</P> +<P> +You can disable these optimizations by passing the PCRE_NO_START_OPTIMIZE +option to the matching function, or by starting the pattern with +(*NO_START_OPT). This slows down the matching process, but does ensure that +callouts such as the example above are obeyed. +</P> +<br><a name="SEC4" href="#TOC1">THE CALLOUT INTERFACE</a><br> +<P> +During matching, when PCRE reaches a callout point, the external function +defined by <i>pcre_callout</i> or <i>pcre[16|32]_callout</i> is called (if it is +set). This applies to both normal and DFA matching. The only argument to the +callout function is a pointer to a <b>pcre_callout</b> or +<b>pcre[16|32]_callout</b> block. These structures contains the following +fields: +<pre> + int <i>version</i>; + int <i>callout_number</i>; + int *<i>offset_vector</i>; + const char *<i>subject</i>; (8-bit version) + PCRE_SPTR16 <i>subject</i>; (16-bit version) + PCRE_SPTR32 <i>subject</i>; (32-bit version) + int <i>subject_length</i>; + int <i>start_match</i>; + int <i>current_position</i>; + int <i>capture_top</i>; + int <i>capture_last</i>; + void *<i>callout_data</i>; + int <i>pattern_position</i>; + int <i>next_item_length</i>; + const unsigned char *<i>mark</i>; (8-bit version) + const PCRE_UCHAR16 *<i>mark</i>; (16-bit version) + const PCRE_UCHAR32 *<i>mark</i>; (32-bit version) +</pre> +The <i>version</i> field is an integer containing the version number of the +block format. The initial version was 0; the current version is 2. The version +number will change again in future if additional fields are added, but the +intention is never to remove any of the existing fields. +</P> +<P> +The <i>callout_number</i> field contains the number of the callout, as compiled +into the pattern (that is, the number after ?C for manual callouts, and 255 for +automatically generated callouts). +</P> +<P> +The <i>offset_vector</i> field is a pointer to the vector of offsets that was +passed by the caller to the matching function. When <b>pcre_exec()</b> or +<b>pcre[16|32]_exec()</b> is used, the contents can be inspected, in order to +extract substrings that have been matched so far, in the same way as for +extracting substrings after a match has completed. For the DFA matching +functions, this field is not useful. +</P> +<P> +The <i>subject</i> and <i>subject_length</i> fields contain copies of the values +that were passed to the matching function. +</P> +<P> +The <i>start_match</i> field normally contains the offset within the subject at +which the current match attempt started. However, if the escape sequence \K +has been encountered, this value is changed to reflect the modified starting +point. If the pattern is not anchored, the callout function may be called +several times from the same point in the pattern for different starting points +in the subject. +</P> +<P> +The <i>current_position</i> field contains the offset within the subject of the +current match pointer. +</P> +<P> +When the <b>pcre_exec()</b> or <b>pcre[16|32]_exec()</b> is used, the +<i>capture_top</i> field contains one more than the number of the highest +numbered captured substring so far. If no substrings have been captured, the +value of <i>capture_top</i> is one. This is always the case when the DFA +functions are used, because they do not support captured substrings. +</P> +<P> +The <i>capture_last</i> field contains the number of the most recently captured +substring. However, when a recursion exits, the value reverts to what it was +outside the recursion, as do the values of all captured substrings. If no +substrings have been captured, the value of <i>capture_last</i> is -1. This is +always the case for the DFA matching functions. +</P> +<P> +The <i>callout_data</i> field contains a value that is passed to a matching +function specifically so that it can be passed back in callouts. It is passed +in the <i>callout_data</i> field of a <b>pcre_extra</b> or <b>pcre[16|32]_extra</b> +data structure. If no such data was passed, the value of <i>callout_data</i> in +a callout block is NULL. There is a description of the <b>pcre_extra</b> +structure in the +<a href="pcreapi.html"><b>pcreapi</b></a> +documentation. +</P> +<P> +The <i>pattern_position</i> field is present from version 1 of the callout +structure. It contains the offset to the next item to be matched in the pattern +string. +</P> +<P> +The <i>next_item_length</i> field is present from version 1 of the callout +structure. It contains the length of the next item to be matched in the pattern +string. When the callout immediately precedes an alternation bar, a closing +parenthesis, or the end of the pattern, the length is zero. When the callout +precedes an opening parenthesis, the length is that of the entire subpattern. +</P> +<P> +The <i>pattern_position</i> and <i>next_item_length</i> fields are intended to +help in distinguishing between different automatic callouts, which all have the +same callout number. However, they are set for all callouts. +</P> +<P> +The <i>mark</i> field is present from version 2 of the callout structure. In +callouts from <b>pcre_exec()</b> or <b>pcre[16|32]_exec()</b> it contains a +pointer to the zero-terminated name of the most recently passed (*MARK), +(*PRUNE), or (*THEN) item in the match, or NULL if no such items have been +passed. Instances of (*PRUNE) or (*THEN) without a name do not obliterate a +previous (*MARK). In callouts from the DFA matching functions this field always +contains NULL. +</P> +<br><a name="SEC5" href="#TOC1">RETURN VALUES</a><br> +<P> +The external callout function returns an integer to PCRE. If the value is zero, +matching proceeds as normal. If the value is greater than zero, matching fails +at the current point, but the testing of other matching possibilities goes +ahead, just as if a lookahead assertion had failed. If the value is less than +zero, the match is abandoned, the matching function returns the negative value. +</P> +<P> +Negative values should normally be chosen from the set of PCRE_ERROR_xxx +values. In particular, PCRE_ERROR_NOMATCH forces a standard "no match" failure. +The error number PCRE_ERROR_CALLOUT is reserved for use by callout functions; +it will never be used by PCRE itself. +</P> +<br><a name="SEC6" href="#TOC1">AUTHOR</a><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><a name="SEC7" href="#TOC1">REVISION</a><br> +<P> +Last updated: 12 November 2013 +<br> +Copyright © 1997-2013 University of Cambridge. +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcrecompat.html b/plugins/Pcre16/docs/doc/html/pcrecompat.html new file mode 100644 index 0000000000..3e6226692e --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcrecompat.html @@ -0,0 +1,235 @@ +<html> +<head> +<title>pcrecompat specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcrecompat man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +DIFFERENCES BETWEEN PCRE AND PERL +</b><br> +<P> +This document describes the differences in the ways that PCRE and Perl handle +regular expressions. The differences described here are with respect to Perl +versions 5.10 and above. +</P> +<P> +1. PCRE has only a subset of Perl's Unicode support. Details of what it does +have are given in the +<a href="pcreunicode.html"><b>pcreunicode</b></a> +page. +</P> +<P> +2. PCRE allows repeat quantifiers only on parenthesized assertions, but they do +not mean what you might think. For example, (?!a){3} does not assert that the +next three characters are not "a". It just asserts that the next character is +not "a" three times (in principle: PCRE optimizes this to run the assertion +just once). Perl allows repeat quantifiers on other assertions such as \b, but +these do not seem to have any use. +</P> +<P> +3. Capturing subpatterns that occur inside negative lookahead assertions are +counted, but their entries in the offsets vector are never set. Perl sometimes +(but not always) sets its numerical variables from inside negative assertions. +</P> +<P> +4. Though binary zero characters are supported in the subject string, they are +not allowed in a pattern string because it is passed as a normal C string, +terminated by zero. The escape sequence \0 can be used in the pattern to +represent a binary zero. +</P> +<P> +5. The following Perl escape sequences are not supported: \l, \u, \L, +\U, and \N when followed by a character name or Unicode value. (\N on its +own, matching a non-newline character, is supported.) In fact these are +implemented by Perl's general string-handling and are not part of its pattern +matching engine. If any of these are encountered by PCRE, an error is +generated by default. However, if the PCRE_JAVASCRIPT_COMPAT option is set, +\U and \u are interpreted as JavaScript interprets them. +</P> +<P> +6. The Perl escape sequences \p, \P, and \X are supported only if PCRE is +built with Unicode character property support. The properties that can be +tested with \p and \P are limited to the general category properties such as +Lu and Nd, script names such as Greek or Han, and the derived properties Any +and L&. PCRE does support the Cs (surrogate) property, which Perl does not; the +Perl documentation says "Because Perl hides the need for the user to understand +the internal representation of Unicode characters, there is no need to +implement the somewhat messy concept of surrogates." +</P> +<P> +7. PCRE does support the \Q...\E escape for quoting substrings. Characters in +between are treated as literals. This is slightly different from Perl in that $ +and @ are also handled as literals inside the quotes. In Perl, they cause +variable interpolation (but of course PCRE does not have variables). Note the +following examples: +<pre> + Pattern PCRE matches Perl matches + + \Qabc$xyz\E abc$xyz abc followed by the contents of $xyz + \Qabc\$xyz\E abc\$xyz abc\$xyz + \Qabc\E\$\Qxyz\E abc$xyz abc$xyz +</pre> +The \Q...\E sequence is recognized both inside and outside character classes. +</P> +<P> +8. Fairly obviously, PCRE does not support the (?{code}) and (??{code}) +constructions. However, there is support for recursive patterns. This is not +available in Perl 5.8, but it is in Perl 5.10. Also, the PCRE "callout" +feature allows an external function to be called during pattern matching. See +the +<a href="pcrecallout.html"><b>pcrecallout</b></a> +documentation for details. +</P> +<P> +9. Subpatterns that are called as subroutines (whether or not recursively) are +always treated as atomic groups in PCRE. This is like Python, but unlike Perl. +Captured values that are set outside a subroutine call can be reference from +inside in PCRE, but not in Perl. There is a discussion that explains these +differences in more detail in the +<a href="pcrepattern.html#recursiondifference">section on recursion differences from Perl</a> +in the +<a href="pcrepattern.html"><b>pcrepattern</b></a> +page. +</P> +<P> +10. If any of the backtracking control verbs are used in a subpattern that is +called as a subroutine (whether or not recursively), their effect is confined +to that subpattern; it does not extend to the surrounding pattern. This is not +always the case in Perl. In particular, if (*THEN) is present in a group that +is called as a subroutine, its action is limited to that group, even if the +group does not contain any | characters. Note that such subpatterns are +processed as anchored at the point where they are tested. +</P> +<P> +11. If a pattern contains more than one backtracking control verb, the first +one that is backtracked onto acts. For example, in the pattern +A(*COMMIT)B(*PRUNE)C a failure in B triggers (*COMMIT), but a failure in C +triggers (*PRUNE). Perl's behaviour is more complex; in many cases it is the +same as PCRE, but there are examples where it differs. +</P> +<P> +12. Most backtracking verbs in assertions have their normal actions. They are +not confined to the assertion. +</P> +<P> +13. There are some differences that are concerned with the settings of captured +strings when part of a pattern is repeated. For example, matching "aba" against +the pattern /^(a(b)?)+$/ in Perl leaves $2 unset, but in PCRE it is set to "b". +</P> +<P> +14. PCRE's handling of duplicate subpattern numbers and duplicate subpattern +names is not as general as Perl's. This is a consequence of the fact the PCRE +works internally just with numbers, using an external table to translate +between numbers and names. In particular, a pattern such as (?|(?<a>A)|(?<b)B), +where the two capturing parentheses have the same number but different names, +is not supported, and causes an error at compile time. If it were allowed, it +would not be possible to distinguish which parentheses matched, because both +names map to capturing subpattern number 1. To avoid this confusing situation, +an error is given at compile time. +</P> +<P> +15. Perl recognizes comments in some places that PCRE does not, for example, +between the ( and ? at the start of a subpattern. If the /x modifier is set, +Perl allows white space between ( and ? (though current Perls warn that this is +deprecated) but PCRE never does, even if the PCRE_EXTENDED option is set. +</P> +<P> +16. Perl, when in warning mode, gives warnings for character classes such as +[A-\d] or [a-[:digit:]]. It then treats the hyphens as literals. PCRE has no +warning features, so it gives an error in these cases because they are almost +certainly user mistakes. +</P> +<P> +17. In PCRE, the upper/lower case character properties Lu and Ll are not +affected when case-independent matching is specified. For example, \p{Lu} +always matches an upper case letter. I think Perl has changed in this respect; +in the release at the time of writing (5.16), \p{Lu} and \p{Ll} match all +letters, regardless of case, when case independence is specified. +</P> +<P> +18. PCRE provides some extensions to the Perl regular expression facilities. +Perl 5.10 includes new features that are not in earlier versions of Perl, some +of which (such as named parentheses) have been in PCRE for some time. This list +is with respect to Perl 5.10: +<br> +<br> +(a) Although lookbehind assertions in PCRE must match fixed length strings, +each alternative branch of a lookbehind assertion can match a different length +of string. Perl requires them all to have the same length. +<br> +<br> +(b) If PCRE_DOLLAR_ENDONLY is set and PCRE_MULTILINE is not set, the $ +meta-character matches only at the very end of the string. +<br> +<br> +(c) If PCRE_EXTRA is set, a backslash followed by a letter with no special +meaning is faulted. Otherwise, like Perl, the backslash is quietly ignored. +(Perl can be made to issue a warning.) +<br> +<br> +(d) If PCRE_UNGREEDY is set, the greediness of the repetition quantifiers is +inverted, that is, by default they are not greedy, but if followed by a +question mark they are. +<br> +<br> +(e) PCRE_ANCHORED can be used at matching time to force a pattern to be tried +only at the first matching position in the subject string. +<br> +<br> +(f) The PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, and +PCRE_NO_AUTO_CAPTURE options for <b>pcre_exec()</b> have no Perl equivalents. +<br> +<br> +(g) The \R escape sequence can be restricted to match only CR, LF, or CRLF +by the PCRE_BSR_ANYCRLF option. +<br> +<br> +(h) The callout facility is PCRE-specific. +<br> +<br> +(i) The partial matching facility is PCRE-specific. +<br> +<br> +(j) Patterns compiled by PCRE can be saved and re-used at a later time, even on +different hosts that have the other endianness. However, this does not apply to +optimized data created by the just-in-time compiler. +<br> +<br> +(k) The alternative matching functions (<b>pcre_dfa_exec()</b>, +<b>pcre16_dfa_exec()</b> and <b>pcre32_dfa_exec()</b>,) match in a different way +and are not Perl-compatible. +<br> +<br> +(l) PCRE recognizes some special sequences such as (*CR) at the start of +a pattern that set overall options that cannot be changed within the pattern. +</P> +<br><b> +AUTHOR +</b><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><b> +REVISION +</b><br> +<P> +Last updated: 10 November 2013 +<br> +Copyright © 1997-2013 University of Cambridge. +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcrecpp.html b/plugins/Pcre16/docs/doc/html/pcrecpp.html new file mode 100644 index 0000000000..b7eac3a3d7 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcrecpp.html @@ -0,0 +1,368 @@ +<html> +<head> +<title>pcrecpp specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcrecpp man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<ul> +<li><a name="TOC1" href="#SEC1">SYNOPSIS OF C++ WRAPPER</a> +<li><a name="TOC2" href="#SEC2">DESCRIPTION</a> +<li><a name="TOC3" href="#SEC3">MATCHING INTERFACE</a> +<li><a name="TOC4" href="#SEC4">QUOTING METACHARACTERS</a> +<li><a name="TOC5" href="#SEC5">PARTIAL MATCHES</a> +<li><a name="TOC6" href="#SEC6">UTF-8 AND THE MATCHING INTERFACE</a> +<li><a name="TOC7" href="#SEC7">PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE</a> +<li><a name="TOC8" href="#SEC8">SCANNING TEXT INCREMENTALLY</a> +<li><a name="TOC9" href="#SEC9">PARSING HEX/OCTAL/C-RADIX NUMBERS</a> +<li><a name="TOC10" href="#SEC10">REPLACING PARTS OF STRINGS</a> +<li><a name="TOC11" href="#SEC11">AUTHOR</a> +<li><a name="TOC12" href="#SEC12">REVISION</a> +</ul> +<br><a name="SEC1" href="#TOC1">SYNOPSIS OF C++ WRAPPER</a><br> +<P> +<b>#include <pcrecpp.h></b> +</P> +<br><a name="SEC2" href="#TOC1">DESCRIPTION</a><br> +<P> +The C++ wrapper for PCRE was provided by Google Inc. Some additional +functionality was added by Giuseppe Maxia. This brief man page was constructed +from the notes in the <i>pcrecpp.h</i> file, which should be consulted for +further details. Note that the C++ wrapper supports only the original 8-bit +PCRE library. There is no 16-bit or 32-bit support at present. +</P> +<br><a name="SEC3" href="#TOC1">MATCHING INTERFACE</a><br> +<P> +The "FullMatch" operation checks that supplied text matches a supplied pattern +exactly. If pointer arguments are supplied, it copies matched sub-strings that +match sub-patterns into them. +<pre> + Example: successful match + pcrecpp::RE re("h.*o"); + re.FullMatch("hello"); + + Example: unsuccessful match (requires full match): + pcrecpp::RE re("e"); + !re.FullMatch("hello"); + + Example: creating a temporary RE object: + pcrecpp::RE("h.*o").FullMatch("hello"); +</pre> +You can pass in a "const char*" or a "string" for "text". The examples below +tend to use a const char*. You can, as in the different examples above, store +the RE object explicitly in a variable or use a temporary RE object. The +examples below use one mode or the other arbitrarily. Either could correctly be +used for any of these examples. +</P> +<P> +You must supply extra pointer arguments to extract matched subpieces. +<pre> + Example: extracts "ruby" into "s" and 1234 into "i" + int i; + string s; + pcrecpp::RE re("(\\w+):(\\d+)"); + re.FullMatch("ruby:1234", &s, &i); + + Example: does not try to extract any extra sub-patterns + re.FullMatch("ruby:1234", &s); + + Example: does not try to extract into NULL + re.FullMatch("ruby:1234", NULL, &i); + + Example: integer overflow causes failure + !re.FullMatch("ruby:1234567891234", NULL, &i); + + Example: fails because there aren't enough sub-patterns: + !pcrecpp::RE("\\w+:\\d+").FullMatch("ruby:1234", &s); + + Example: fails because string cannot be stored in integer + !pcrecpp::RE("(.*)").FullMatch("ruby", &i); +</pre> +The provided pointer arguments can be pointers to any scalar numeric +type, or one of: +<pre> + string (matched piece is copied to string) + StringPiece (StringPiece is mutated to point to matched piece) + T (where "bool T::ParseFrom(const char*, int)" exists) + NULL (the corresponding matched sub-pattern is not copied) +</pre> +The function returns true iff all of the following conditions are satisfied: +<pre> + a. "text" matches "pattern" exactly; + + b. The number of matched sub-patterns is >= number of supplied + pointers; + + c. The "i"th argument has a suitable type for holding the + string captured as the "i"th sub-pattern. If you pass in + void * NULL for the "i"th argument, or a non-void * NULL + of the correct type, or pass fewer arguments than the + number of sub-patterns, "i"th captured sub-pattern is + ignored. +</pre> +CAVEAT: An optional sub-pattern that does not exist in the matched +string is assigned the empty string. Therefore, the following will +return false (because the empty string is not a valid number): +<pre> + int number; + pcrecpp::RE::FullMatch("abc", "[a-z]+(\\d+)?", &number); +</pre> +The matching interface supports at most 16 arguments per call. +If you need more, consider using the more general interface +<b>pcrecpp::RE::DoMatch</b>. See <b>pcrecpp.h</b> for the signature for +<b>DoMatch</b>. +</P> +<P> +NOTE: Do not use <b>no_arg</b>, which is used internally to mark the end of a +list of optional arguments, as a placeholder for missing arguments, as this can +lead to segfaults. +</P> +<br><a name="SEC4" href="#TOC1">QUOTING METACHARACTERS</a><br> +<P> +You can use the "QuoteMeta" operation to insert backslashes before all +potentially meaningful characters in a string. The returned string, used as a +regular expression, will exactly match the original string. +<pre> + Example: + string quoted = RE::QuoteMeta(unquoted); +</pre> +Note that it's legal to escape a character even if it has no special meaning in +a regular expression -- so this function does that. (This also makes it +identical to the perl function of the same name; see "perldoc -f quotemeta".) +For example, "1.5-2.0?" becomes "1\.5\-2\.0\?". +</P> +<br><a name="SEC5" href="#TOC1">PARTIAL MATCHES</a><br> +<P> +You can use the "PartialMatch" operation when you want the pattern +to match any substring of the text. +<pre> + Example: simple search for a string: + pcrecpp::RE("ell").PartialMatch("hello"); + + Example: find first number in a string: + int number; + pcrecpp::RE re("(\\d+)"); + re.PartialMatch("x*100 + 20", &number); + assert(number == 100); +</PRE> +</P> +<br><a name="SEC6" href="#TOC1">UTF-8 AND THE MATCHING INTERFACE</a><br> +<P> +By default, pattern and text are plain text, one byte per character. The UTF8 +flag, passed to the constructor, causes both pattern and string to be treated +as UTF-8 text, still a byte stream but potentially multiple bytes per +character. In practice, the text is likelier to be UTF-8 than the pattern, but +the match returned may depend on the UTF8 flag, so always use it when matching +UTF8 text. For example, "." will match one byte normally but with UTF8 set may +match up to three bytes of a multi-byte character. +<pre> + Example: + pcrecpp::RE_Options options; + options.set_utf8(); + pcrecpp::RE re(utf8_pattern, options); + re.FullMatch(utf8_string); + + Example: using the convenience function UTF8(): + pcrecpp::RE re(utf8_pattern, pcrecpp::UTF8()); + re.FullMatch(utf8_string); +</pre> +NOTE: The UTF8 flag is ignored if pcre was not configured with the +<pre> + --enable-utf8 flag. +</PRE> +</P> +<br><a name="SEC7" href="#TOC1">PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE</a><br> +<P> +PCRE defines some modifiers to change the behavior of the regular expression +engine. The C++ wrapper defines an auxiliary class, RE_Options, as a vehicle to +pass such modifiers to a RE class. Currently, the following modifiers are +supported: +<pre> + modifier description Perl corresponding + + PCRE_CASELESS case insensitive match /i + PCRE_MULTILINE multiple lines match /m + PCRE_DOTALL dot matches newlines /s + PCRE_DOLLAR_ENDONLY $ matches only at end N/A + PCRE_EXTRA strict escape parsing N/A + PCRE_EXTENDED ignore white spaces /x + PCRE_UTF8 handles UTF8 chars built-in + PCRE_UNGREEDY reverses * and *? N/A + PCRE_NO_AUTO_CAPTURE disables capturing parens N/A (*) +</pre> +(*) Both Perl and PCRE allow non capturing parentheses by means of the +"?:" modifier within the pattern itself. e.g. (?:ab|cd) does not +capture, while (ab|cd) does. +</P> +<P> +For a full account on how each modifier works, please check the +PCRE API reference page. +</P> +<P> +For each modifier, there are two member functions whose name is made +out of the modifier in lowercase, without the "PCRE_" prefix. For +instance, PCRE_CASELESS is handled by +<pre> + bool caseless() +</pre> +which returns true if the modifier is set, and +<pre> + RE_Options & set_caseless(bool) +</pre> +which sets or unsets the modifier. Moreover, PCRE_EXTRA_MATCH_LIMIT can be +accessed through the <b>set_match_limit()</b> and <b>match_limit()</b> member +functions. Setting <i>match_limit</i> to a non-zero value will limit the +execution of pcre to keep it from doing bad things like blowing the stack or +taking an eternity to return a result. A value of 5000 is good enough to stop +stack blowup in a 2MB thread stack. Setting <i>match_limit</i> to zero disables +match limiting. Alternatively, you can call <b>match_limit_recursion()</b> +which uses PCRE_EXTRA_MATCH_LIMIT_RECURSION to limit how much PCRE +recurses. <b>match_limit()</b> limits the number of matches PCRE does; +<b>match_limit_recursion()</b> limits the depth of internal recursion, and +therefore the amount of stack that is used. +</P> +<P> +Normally, to pass one or more modifiers to a RE class, you declare +a <i>RE_Options</i> object, set the appropriate options, and pass this +object to a RE constructor. Example: +<pre> + RE_Options opt; + opt.set_caseless(true); + if (RE("HELLO", opt).PartialMatch("hello world")) ... +</pre> +RE_options has two constructors. The default constructor takes no arguments and +creates a set of flags that are off by default. The optional parameter +<i>option_flags</i> is to facilitate transfer of legacy code from C programs. +This lets you do +<pre> + RE(pattern, + RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str); +</pre> +However, new code is better off doing +<pre> + RE(pattern, + RE_Options().set_caseless(true).set_multiline(true)) + .PartialMatch(str); +</pre> +If you are going to pass one of the most used modifiers, there are some +convenience functions that return a RE_Options class with the +appropriate modifier already set: <b>CASELESS()</b>, <b>UTF8()</b>, +<b>MULTILINE()</b>, <b>DOTALL</b>(), and <b>EXTENDED()</b>. +</P> +<P> +If you need to set several options at once, and you don't want to go through +the pains of declaring a RE_Options object and setting several options, there +is a parallel method that give you such ability on the fly. You can concatenate +several <b>set_xxxxx()</b> member functions, since each of them returns a +reference to its class object. For example, to pass PCRE_CASELESS, +PCRE_EXTENDED, and PCRE_MULTILINE to a RE with one statement, you may write: +<pre> + RE(" ^ xyz \\s+ .* blah$", + RE_Options() + .set_caseless(true) + .set_extended(true) + .set_multiline(true)).PartialMatch(sometext); + +</PRE> +</P> +<br><a name="SEC8" href="#TOC1">SCANNING TEXT INCREMENTALLY</a><br> +<P> +The "Consume" operation may be useful if you want to repeatedly +match regular expressions at the front of a string and skip over +them as they match. This requires use of the "StringPiece" type, +which represents a sub-range of a real string. Like RE, StringPiece +is defined in the pcrecpp namespace. +<pre> + Example: read lines of the form "var = value" from a string. + string contents = ...; // Fill string somehow + pcrecpp::StringPiece input(contents); // Wrap in a StringPiece + + string var; + int value; + pcrecpp::RE re("(\\w+) = (\\d+)\n"); + while (re.Consume(&input, &var, &value)) { + ...; + } +</pre> +Each successful call to "Consume" will set "var/value", and also +advance "input" so it points past the matched text. +</P> +<P> +The "FindAndConsume" operation is similar to "Consume" but does not +anchor your match at the beginning of the string. For example, you +could extract all words from a string by repeatedly calling +<pre> + pcrecpp::RE("(\\w+)").FindAndConsume(&input, &word) +</PRE> +</P> +<br><a name="SEC9" href="#TOC1">PARSING HEX/OCTAL/C-RADIX NUMBERS</a><br> +<P> +By default, if you pass a pointer to a numeric value, the +corresponding text is interpreted as a base-10 number. You can +instead wrap the pointer with a call to one of the operators Hex(), +Octal(), or CRadix() to interpret the text in another base. The +CRadix operator interprets C-style "0" (base-8) and "0x" (base-16) +prefixes, but defaults to base-10. +<pre> + Example: + int a, b, c, d; + pcrecpp::RE re("(.*) (.*) (.*) (.*)"); + re.FullMatch("100 40 0100 0x40", + pcrecpp::Octal(&a), pcrecpp::Hex(&b), + pcrecpp::CRadix(&c), pcrecpp::CRadix(&d)); +</pre> +will leave 64 in a, b, c, and d. +</P> +<br><a name="SEC10" href="#TOC1">REPLACING PARTS OF STRINGS</a><br> +<P> +You can replace the first match of "pattern" in "str" with "rewrite". +Within "rewrite", backslash-escaped digits (\1 to \9) can be +used to insert text matching corresponding parenthesized group +from the pattern. \0 in "rewrite" refers to the entire matching +text. For example: +<pre> + string s = "yabba dabba doo"; + pcrecpp::RE("b+").Replace("d", &s); +</pre> +will leave "s" containing "yada dabba doo". The result is true if the pattern +matches and a replacement occurs, false otherwise. +</P> +<P> +<b>GlobalReplace</b> is like <b>Replace</b> except that it replaces all +occurrences of the pattern in the string with the rewrite. Replacements are +not subject to re-matching. For example: +<pre> + string s = "yabba dabba doo"; + pcrecpp::RE("b+").GlobalReplace("d", &s); +</pre> +will leave "s" containing "yada dada doo". It returns the number of +replacements made. +</P> +<P> +<b>Extract</b> is like <b>Replace</b>, except that if the pattern matches, +"rewrite" is copied into "out" (an additional argument) with substitutions. +The non-matching portions of "text" are ignored. Returns true iff a match +occurred and the extraction happened successfully; if no match occurs, the +string is left unaffected. +</P> +<br><a name="SEC11" href="#TOC1">AUTHOR</a><br> +<P> +The C++ wrapper was contributed by Google Inc. +<br> +Copyright © 2007 Google Inc. +<br> +</P> +<br><a name="SEC12" href="#TOC1">REVISION</a><br> +<P> +Last updated: 08 January 2012 +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcredemo.html b/plugins/Pcre16/docs/doc/html/pcredemo.html new file mode 100644 index 0000000000..894a930826 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcredemo.html @@ -0,0 +1,426 @@ +<html> +<head> +<title>pcredemo specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcredemo man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<ul> +</ul> +<PRE> +/************************************************* +* PCRE DEMONSTRATION PROGRAM * +*************************************************/ + +/* This is a demonstration program to illustrate the most straightforward ways +of calling the PCRE regular expression library from a C program. See the +pcresample documentation for a short discussion ("man pcresample" if you have +the PCRE man pages installed). + +In Unix-like environments, if PCRE is installed in your standard system +libraries, you should be able to compile this program using this command: + +gcc -Wall pcredemo.c -lpcre -o pcredemo + +If PCRE is not installed in a standard place, it is likely to be installed with +support for the pkg-config mechanism. If you have pkg-config, you can compile +this program using this command: + +gcc -Wall pcredemo.c `pkg-config --cflags --libs libpcre` -o pcredemo + +If you do not have pkg-config, you may have to use this: + +gcc -Wall pcredemo.c -I/usr/local/include -L/usr/local/lib \ + -R/usr/local/lib -lpcre -o pcredemo + +Replace "/usr/local/include" and "/usr/local/lib" with wherever the include and +library files for PCRE are installed on your system. Only some operating +systems (e.g. Solaris) use the -R option. + +Building under Windows: + +If you want to statically link this program against a non-dll .a file, you must +define PCRE_STATIC before including pcre.h, otherwise the pcre_malloc() and +pcre_free() exported functions will be declared __declspec(dllimport), with +unwanted results. So in this environment, uncomment the following line. */ + +/* #define PCRE_STATIC */ + +#include <stdio.h> +#include <string.h> +#include <pcre.h> + +#define OVECCOUNT 30 /* should be a multiple of 3 */ + + +int main(int argc, char **argv) +{ +pcre *re; +const char *error; +char *pattern; +char *subject; +unsigned char *name_table; +unsigned int option_bits; +int erroffset; +int find_all; +int crlf_is_newline; +int namecount; +int name_entry_size; +int ovector[OVECCOUNT]; +int subject_length; +int rc, i; +int utf8; + + +/************************************************************************** +* First, sort out the command line. There is only one possible option at * +* the moment, "-g" to request repeated matching to find all occurrences, * +* like Perl's /g option. We set the variable find_all to a non-zero value * +* if the -g option is present. Apart from that, there must be exactly two * +* arguments. * +**************************************************************************/ + +find_all = 0; +for (i = 1; i < argc; i++) + { + if (strcmp(argv[i], "-g") == 0) find_all = 1; + else break; + } + +/* After the options, we require exactly two arguments, which are the pattern, +and the subject string. */ + +if (argc - i != 2) + { + printf("Two arguments required: a regex and a subject string\n"); + return 1; + } + +pattern = argv[i]; +subject = argv[i+1]; +subject_length = (int)strlen(subject); + + +/************************************************************************* +* Now we are going to compile the regular expression pattern, and handle * +* and errors that are detected. * +*************************************************************************/ + +re = pcre_compile( + pattern, /* the pattern */ + 0, /* default options */ + &error, /* for error message */ + &erroffset, /* for error offset */ + NULL); /* use default character tables */ + +/* Compilation failed: print the error message and exit */ + +if (re == NULL) + { + printf("PCRE compilation failed at offset %d: %s\n", erroffset, error); + return 1; + } + + +/************************************************************************* +* If the compilation succeeded, we call PCRE again, in order to do a * +* pattern match against the subject string. This does just ONE match. If * +* further matching is needed, it will be done below. * +*************************************************************************/ + +rc = pcre_exec( + re, /* the compiled pattern */ + NULL, /* no extra data - we didn't study the pattern */ + subject, /* the subject string */ + subject_length, /* the length of the subject */ + 0, /* start at offset 0 in the subject */ + 0, /* default options */ + ovector, /* output vector for substring information */ + OVECCOUNT); /* number of elements in the output vector */ + +/* Matching failed: handle error cases */ + +if (rc < 0) + { + switch(rc) + { + case PCRE_ERROR_NOMATCH: printf("No match\n"); break; + /* + Handle other special cases if you like + */ + default: printf("Matching error %d\n", rc); break; + } + pcre_free(re); /* Release memory used for the compiled pattern */ + return 1; + } + +/* Match succeded */ + +printf("\nMatch succeeded at offset %d\n", ovector[0]); + + +/************************************************************************* +* We have found the first match within the subject string. If the output * +* vector wasn't big enough, say so. Then output any substrings that were * +* captured. * +*************************************************************************/ + +/* The output vector wasn't big enough */ + +if (rc == 0) + { + rc = OVECCOUNT/3; + printf("ovector only has room for %d captured substrings\n", rc - 1); + } + +/* Show substrings stored in the output vector by number. Obviously, in a real +application you might want to do things other than print them. */ + +for (i = 0; i < rc; i++) + { + char *substring_start = subject + ovector[2*i]; + int substring_length = ovector[2*i+1] - ovector[2*i]; + printf("%2d: %.*s\n", i, substring_length, substring_start); + } + + +/************************************************************************** +* That concludes the basic part of this demonstration program. We have * +* compiled a pattern, and performed a single match. The code that follows * +* shows first how to access named substrings, and then how to code for * +* repeated matches on the same subject. * +**************************************************************************/ + +/* See if there are any named substrings, and if so, show them by name. First +we have to extract the count of named parentheses from the pattern. */ + +(void)pcre_fullinfo( + re, /* the compiled pattern */ + NULL, /* no extra data - we didn't study the pattern */ + PCRE_INFO_NAMECOUNT, /* number of named substrings */ + &namecount); /* where to put the answer */ + +if (namecount <= 0) printf("No named substrings\n"); else + { + unsigned char *tabptr; + printf("Named substrings\n"); + + /* Before we can access the substrings, we must extract the table for + translating names to numbers, and the size of each entry in the table. */ + + (void)pcre_fullinfo( + re, /* the compiled pattern */ + NULL, /* no extra data - we didn't study the pattern */ + PCRE_INFO_NAMETABLE, /* address of the table */ + &name_table); /* where to put the answer */ + + (void)pcre_fullinfo( + re, /* the compiled pattern */ + NULL, /* no extra data - we didn't study the pattern */ + PCRE_INFO_NAMEENTRYSIZE, /* size of each entry in the table */ + &name_entry_size); /* where to put the answer */ + + /* Now we can scan the table and, for each entry, print the number, the name, + and the substring itself. */ + + tabptr = name_table; + for (i = 0; i < namecount; i++) + { + int n = (tabptr[0] << 8) | tabptr[1]; + printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2, + ovector[2*n+1] - ovector[2*n], subject + ovector[2*n]); + tabptr += name_entry_size; + } + } + + +/************************************************************************* +* If the "-g" option was given on the command line, we want to continue * +* to search for additional matches in the subject string, in a similar * +* way to the /g option in Perl. This turns out to be trickier than you * +* might think because of the possibility of matching an empty string. * +* What happens is as follows: * +* * +* If the previous match was NOT for an empty string, we can just start * +* the next match at the end of the previous one. * +* * +* If the previous match WAS for an empty string, we can't do that, as it * +* would lead to an infinite loop. Instead, a special call of pcre_exec() * +* is made with the PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED flags set. * +* The first of these tells PCRE that an empty string at the start of the * +* subject is not a valid match; other possibilities must be tried. The * +* second flag restricts PCRE to one match attempt at the initial string * +* position. If this match succeeds, an alternative to the empty string * +* match has been found, and we can print it and proceed round the loop, * +* advancing by the length of whatever was found. If this match does not * +* succeed, we still stay in the loop, advancing by just one character. * +* In UTF-8 mode, which can be set by (*UTF8) in the pattern, this may be * +* more than one byte. * +* * +* However, there is a complication concerned with newlines. When the * +* newline convention is such that CRLF is a valid newline, we must * +* advance by two characters rather than one. The newline convention can * +* be set in the regex by (*CR), etc.; if not, we must find the default. * +*************************************************************************/ + +if (!find_all) /* Check for -g */ + { + pcre_free(re); /* Release the memory used for the compiled pattern */ + return 0; /* Finish unless -g was given */ + } + +/* Before running the loop, check for UTF-8 and whether CRLF is a valid newline +sequence. First, find the options with which the regex was compiled; extract +the UTF-8 state, and mask off all but the newline options. */ + +(void)pcre_fullinfo(re, NULL, PCRE_INFO_OPTIONS, &option_bits); +utf8 = option_bits & PCRE_UTF8; +option_bits &= PCRE_NEWLINE_CR|PCRE_NEWLINE_LF|PCRE_NEWLINE_CRLF| + PCRE_NEWLINE_ANY|PCRE_NEWLINE_ANYCRLF; + +/* If no newline options were set, find the default newline convention from the +build configuration. */ + +if (option_bits == 0) + { + int d; + (void)pcre_config(PCRE_CONFIG_NEWLINE, &d); + /* Note that these values are always the ASCII ones, even in + EBCDIC environments. CR = 13, NL = 10. */ + option_bits = (d == 13)? PCRE_NEWLINE_CR : + (d == 10)? PCRE_NEWLINE_LF : + (d == (13<<8 | 10))? PCRE_NEWLINE_CRLF : + (d == -2)? PCRE_NEWLINE_ANYCRLF : + (d == -1)? PCRE_NEWLINE_ANY : 0; + } + +/* See if CRLF is a valid newline sequence. */ + +crlf_is_newline = + option_bits == PCRE_NEWLINE_ANY || + option_bits == PCRE_NEWLINE_CRLF || + option_bits == PCRE_NEWLINE_ANYCRLF; + +/* Loop for second and subsequent matches */ + +for (;;) + { + int options = 0; /* Normally no options */ + int start_offset = ovector[1]; /* Start at end of previous match */ + + /* If the previous match was for an empty string, we are finished if we are + at the end of the subject. Otherwise, arrange to run another match at the + same point to see if a non-empty match can be found. */ + + if (ovector[0] == ovector[1]) + { + if (ovector[0] == subject_length) break; + options = PCRE_NOTEMPTY_ATSTART | PCRE_ANCHORED; + } + + /* Run the next matching operation */ + + rc = pcre_exec( + re, /* the compiled pattern */ + NULL, /* no extra data - we didn't study the pattern */ + subject, /* the subject string */ + subject_length, /* the length of the subject */ + start_offset, /* starting offset in the subject */ + options, /* options */ + ovector, /* output vector for substring information */ + OVECCOUNT); /* number of elements in the output vector */ + + /* This time, a result of NOMATCH isn't an error. If the value in "options" + is zero, it just means we have found all possible matches, so the loop ends. + Otherwise, it means we have failed to find a non-empty-string match at a + point where there was a previous empty-string match. In this case, we do what + Perl does: advance the matching position by one character, and continue. We + do this by setting the "end of previous match" offset, because that is picked + up at the top of the loop as the point at which to start again. + + There are two complications: (a) When CRLF is a valid newline sequence, and + the current position is just before it, advance by an extra byte. (b) + Otherwise we must ensure that we skip an entire UTF-8 character if we are in + UTF-8 mode. */ + + if (rc == PCRE_ERROR_NOMATCH) + { + if (options == 0) break; /* All matches found */ + ovector[1] = start_offset + 1; /* Advance one byte */ + if (crlf_is_newline && /* If CRLF is newline & */ + start_offset < subject_length - 1 && /* we are at CRLF, */ + subject[start_offset] == '\r' && + subject[start_offset + 1] == '\n') + ovector[1] += 1; /* Advance by one more. */ + else if (utf8) /* Otherwise, ensure we */ + { /* advance a whole UTF-8 */ + while (ovector[1] < subject_length) /* character. */ + { + if ((subject[ovector[1]] & 0xc0) != 0x80) break; + ovector[1] += 1; + } + } + continue; /* Go round the loop again */ + } + + /* Other matching errors are not recoverable. */ + + if (rc < 0) + { + printf("Matching error %d\n", rc); + pcre_free(re); /* Release memory used for the compiled pattern */ + return 1; + } + + /* Match succeded */ + + printf("\nMatch succeeded again at offset %d\n", ovector[0]); + + /* The match succeeded, but the output vector wasn't big enough. */ + + if (rc == 0) + { + rc = OVECCOUNT/3; + printf("ovector only has room for %d captured substrings\n", rc - 1); + } + + /* As before, show substrings stored in the output vector by number, and then + also any named substrings. */ + + for (i = 0; i < rc; i++) + { + char *substring_start = subject + ovector[2*i]; + int substring_length = ovector[2*i+1] - ovector[2*i]; + printf("%2d: %.*s\n", i, substring_length, substring_start); + } + + if (namecount <= 0) printf("No named substrings\n"); else + { + unsigned char *tabptr = name_table; + printf("Named substrings\n"); + for (i = 0; i < namecount; i++) + { + int n = (tabptr[0] << 8) | tabptr[1]; + printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2, + ovector[2*n+1] - ovector[2*n], subject + ovector[2*n]); + tabptr += name_entry_size; + } + } + } /* End of loop to find second and subsequent matches */ + +printf("\n"); +pcre_free(re); /* Release memory used for the compiled pattern */ +return 0; +} + +/* End of pcredemo.c */ +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcregrep.html b/plugins/Pcre16/docs/doc/html/pcregrep.html new file mode 100644 index 0000000000..dacbb4998f --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcregrep.html @@ -0,0 +1,759 @@ +<html> +<head> +<title>pcregrep specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcregrep man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<ul> +<li><a name="TOC1" href="#SEC1">SYNOPSIS</a> +<li><a name="TOC2" href="#SEC2">DESCRIPTION</a> +<li><a name="TOC3" href="#SEC3">SUPPORT FOR COMPRESSED FILES</a> +<li><a name="TOC4" href="#SEC4">BINARY FILES</a> +<li><a name="TOC5" href="#SEC5">OPTIONS</a> +<li><a name="TOC6" href="#SEC6">ENVIRONMENT VARIABLES</a> +<li><a name="TOC7" href="#SEC7">NEWLINES</a> +<li><a name="TOC8" href="#SEC8">OPTIONS COMPATIBILITY</a> +<li><a name="TOC9" href="#SEC9">OPTIONS WITH DATA</a> +<li><a name="TOC10" href="#SEC10">MATCHING ERRORS</a> +<li><a name="TOC11" href="#SEC11">DIAGNOSTICS</a> +<li><a name="TOC12" href="#SEC12">SEE ALSO</a> +<li><a name="TOC13" href="#SEC13">AUTHOR</a> +<li><a name="TOC14" href="#SEC14">REVISION</a> +</ul> +<br><a name="SEC1" href="#TOC1">SYNOPSIS</a><br> +<P> +<b>pcregrep [options] [long options] [pattern] [path1 path2 ...]</b> +</P> +<br><a name="SEC2" href="#TOC1">DESCRIPTION</a><br> +<P> +<b>pcregrep</b> searches files for character patterns, in the same way as other +grep commands do, but it uses the PCRE regular expression library to support +patterns that are compatible with the regular expressions of Perl 5. See +<a href="pcresyntax.html"><b>pcresyntax</b>(3)</a> +for a quick-reference summary of pattern syntax, or +<a href="pcrepattern.html"><b>pcrepattern</b>(3)</a> +for a full description of the syntax and semantics of the regular expressions +that PCRE supports. +</P> +<P> +Patterns, whether supplied on the command line or in a separate file, are given +without delimiters. For example: +<pre> + pcregrep Thursday /etc/motd +</pre> +If you attempt to use delimiters (for example, by surrounding a pattern with +slashes, as is common in Perl scripts), they are interpreted as part of the +pattern. Quotes can of course be used to delimit patterns on the command line +because they are interpreted by the shell, and indeed quotes are required if a +pattern contains white space or shell metacharacters. +</P> +<P> +The first argument that follows any option settings is treated as the single +pattern to be matched when neither <b>-e</b> nor <b>-f</b> is present. +Conversely, when one or both of these options are used to specify patterns, all +arguments are treated as path names. At least one of <b>-e</b>, <b>-f</b>, or an +argument pattern must be provided. +</P> +<P> +If no files are specified, <b>pcregrep</b> reads the standard input. The +standard input can also be referenced by a name consisting of a single hyphen. +For example: +<pre> + pcregrep some-pattern /file1 - /file3 +</pre> +By default, each line that matches a pattern is copied to the standard +output, and if there is more than one file, the file name is output at the +start of each line, followed by a colon. However, there are options that can +change how <b>pcregrep</b> behaves. In particular, the <b>-M</b> option makes it +possible to search for patterns that span line boundaries. What defines a line +boundary is controlled by the <b>-N</b> (<b>--newline</b>) option. +</P> +<P> +The amount of memory used for buffering files that are being scanned is +controlled by a parameter that can be set by the <b>--buffer-size</b> option. +The default value for this parameter is specified when <b>pcregrep</b> is built, +with the default default being 20K. A block of memory three times this size is +used (to allow for buffering "before" and "after" lines). An error occurs if a +line overflows the buffer. +</P> +<P> +Patterns can be no longer than 8K or BUFSIZ bytes, whichever is the greater. +BUFSIZ is defined in <b><stdio.h></b>. When there is more than one pattern +(specified by the use of <b>-e</b> and/or <b>-f</b>), each pattern is applied to +each line in the order in which they are defined, except that all the <b>-e</b> +patterns are tried before the <b>-f</b> patterns. +</P> +<P> +By default, as soon as one pattern matches a line, no further patterns are +considered. However, if <b>--colour</b> (or <b>--color</b>) is used to colour the +matching substrings, or if <b>--only-matching</b>, <b>--file-offsets</b>, or +<b>--line-offsets</b> is used to output only the part of the line that matched +(either shown literally, or as an offset), scanning resumes immediately +following the match, so that further matches on the same line can be found. If +there are multiple patterns, they are all tried on the remainder of the line, +but patterns that follow the one that matched are not tried on the earlier part +of the line. +</P> +<P> +This behaviour means that the order in which multiple patterns are specified +can affect the output when one of the above options is used. This is no longer +the same behaviour as GNU grep, which now manages to display earlier matches +for later patterns (as long as there is no overlap). +</P> +<P> +Patterns that can match an empty string are accepted, but empty string +matches are never recognized. An example is the pattern "(super)?(man)?", in +which all components are optional. This pattern finds all occurrences of both +"super" and "man"; the output differs from matching with "super|man" when only +the matching substrings are being shown. +</P> +<P> +If the <b>LC_ALL</b> or <b>LC_CTYPE</b> environment variable is set, +<b>pcregrep</b> uses the value to set a locale when calling the PCRE library. +The <b>--locale</b> option can be used to override this. +</P> +<br><a name="SEC3" href="#TOC1">SUPPORT FOR COMPRESSED FILES</a><br> +<P> +It is possible to compile <b>pcregrep</b> so that it uses <b>libz</b> or +<b>libbz2</b> to read files whose names end in <b>.gz</b> or <b>.bz2</b>, +respectively. You can find out whether your binary has support for one or both +of these file types by running it with the <b>--help</b> option. If the +appropriate support is not present, files are treated as plain text. The +standard input is always so treated. +</P> +<br><a name="SEC4" href="#TOC1">BINARY FILES</a><br> +<P> +By default, a file that contains a binary zero byte within the first 1024 bytes +is identified as a binary file, and is processed specially. (GNU grep also +identifies binary files in this manner.) See the <b>--binary-files</b> option +for a means of changing the way binary files are handled. +</P> +<br><a name="SEC5" href="#TOC1">OPTIONS</a><br> +<P> +The order in which some of the options appear can affect the output. For +example, both the <b>-h</b> and <b>-l</b> options affect the printing of file +names. Whichever comes later in the command line will be the one that takes +effect. Similarly, except where noted below, if an option is given twice, the +later setting is used. Numerical values for options may be followed by K or M, +to signify multiplication by 1024 or 1024*1024 respectively. +</P> +<P> +<b>--</b> +This terminates the list of options. It is useful if the next item on the +command line starts with a hyphen but is not an option. This allows for the +processing of patterns and filenames that start with hyphens. +</P> +<P> +<b>-A</b> <i>number</i>, <b>--after-context=</b><i>number</i> +Output <i>number</i> lines of context after each matching line. If filenames +and/or line numbers are being output, a hyphen separator is used instead of a +colon for the context lines. A line containing "--" is output between each +group of lines, unless they are in fact contiguous in the input file. The value +of <i>number</i> is expected to be relatively small. However, <b>pcregrep</b> +guarantees to have up to 8K of following text available for context output. +</P> +<P> +<b>-a</b>, <b>--text</b> +Treat binary files as text. This is equivalent to +<b>--binary-files</b>=<i>text</i>. +</P> +<P> +<b>-B</b> <i>number</i>, <b>--before-context=</b><i>number</i> +Output <i>number</i> lines of context before each matching line. If filenames +and/or line numbers are being output, a hyphen separator is used instead of a +colon for the context lines. A line containing "--" is output between each +group of lines, unless they are in fact contiguous in the input file. The value +of <i>number</i> is expected to be relatively small. However, <b>pcregrep</b> +guarantees to have up to 8K of preceding text available for context output. +</P> +<P> +<b>--binary-files=</b><i>word</i> +Specify how binary files are to be processed. If the word is "binary" (the +default), pattern matching is performed on binary files, but the only output is +"Binary file <name> matches" when a match succeeds. If the word is "text", +which is equivalent to the <b>-a</b> or <b>--text</b> option, binary files are +processed in the same way as any other file. In this case, when a match +succeeds, the output may be binary garbage, which can have nasty effects if +sent to a terminal. If the word is "without-match", which is equivalent to the +<b>-I</b> option, binary files are not processed at all; they are assumed not to +be of interest. +</P> +<P> +<b>--buffer-size=</b><i>number</i> +Set the parameter that controls how much memory is used for buffering files +that are being scanned. +</P> +<P> +<b>-C</b> <i>number</i>, <b>--context=</b><i>number</i> +Output <i>number</i> lines of context both before and after each matching line. +This is equivalent to setting both <b>-A</b> and <b>-B</b> to the same value. +</P> +<P> +<b>-c</b>, <b>--count</b> +Do not output individual lines from the files that are being scanned; instead +output the number of lines that would otherwise have been shown. If no lines +are selected, the number zero is output. If several files are are being +scanned, a count is output for each of them. However, if the +<b>--files-with-matches</b> option is also used, only those files whose counts +are greater than zero are listed. When <b>-c</b> is used, the <b>-A</b>, +<b>-B</b>, and <b>-C</b> options are ignored. +</P> +<P> +<b>--colour</b>, <b>--color</b> +If this option is given without any data, it is equivalent to "--colour=auto". +If data is required, it must be given in the same shell item, separated by an +equals sign. +</P> +<P> +<b>--colour=</b><i>value</i>, <b>--color=</b><i>value</i> +This option specifies under what circumstances the parts of a line that matched +a pattern should be coloured in the output. By default, the output is not +coloured. The value (which is optional, see above) may be "never", "always", or +"auto". In the latter case, colouring happens only if the standard output is +connected to a terminal. More resources are used when colouring is enabled, +because <b>pcregrep</b> has to search for all possible matches in a line, not +just one, in order to colour them all. +<br> +<br> +The colour that is used can be specified by setting the environment variable +PCREGREP_COLOUR or PCREGREP_COLOR. The value of this variable should be a +string of two numbers, separated by a semicolon. They are copied directly into +the control string for setting colour on a terminal, so it is your +responsibility to ensure that they make sense. If neither of the environment +variables is set, the default is "1;31", which gives red. +</P> +<P> +<b>-D</b> <i>action</i>, <b>--devices=</b><i>action</i> +If an input path is not a regular file or a directory, "action" specifies how +it is to be processed. Valid values are "read" (the default) or "skip" +(silently skip the path). +</P> +<P> +<b>-d</b> <i>action</i>, <b>--directories=</b><i>action</i> +If an input path is a directory, "action" specifies how it is to be processed. +Valid values are "read" (the default in non-Windows environments, for +compatibility with GNU grep), "recurse" (equivalent to the <b>-r</b> option), or +"skip" (silently skip the path, the default in Windows environments). In the +"read" case, directories are read as if they were ordinary files. In some +operating systems the effect of reading a directory like this is an immediate +end-of-file; in others it may provoke an error. +</P> +<P> +<b>-e</b> <i>pattern</i>, <b>--regex=</b><i>pattern</i>, <b>--regexp=</b><i>pattern</i> +Specify a pattern to be matched. This option can be used multiple times in +order to specify several patterns. It can also be used as a way of specifying a +single pattern that starts with a hyphen. When <b>-e</b> is used, no argument +pattern is taken from the command line; all arguments are treated as file +names. There is no limit to the number of patterns. They are applied to each +line in the order in which they are defined until one matches. +<br> +<br> +If <b>-f</b> is used with <b>-e</b>, the command line patterns are matched first, +followed by the patterns from the file(s), independent of the order in which +these options are specified. Note that multiple use of <b>-e</b> is not the same +as a single pattern with alternatives. For example, X|Y finds the first +character in a line that is X or Y, whereas if the two patterns are given +separately, with X first, <b>pcregrep</b> finds X if it is present, even if it +follows Y in the line. It finds Y only if there is no X in the line. This +matters only if you are using <b>-o</b> or <b>--colo(u)r</b> to show the part(s) +of the line that matched. +</P> +<P> +<b>--exclude</b>=<i>pattern</i> +Files (but not directories) whose names match the pattern are skipped without +being processed. This applies to all files, whether listed on the command line, +obtained from <b>--file-list</b>, or by scanning a directory. The pattern is a +PCRE regular expression, and is matched against the final component of the file +name, not the entire path. The <b>-F</b>, <b>-w</b>, and <b>-x</b> options do not +apply to this pattern. The option may be given any number of times in order to +specify multiple patterns. If a file name matches both an <b>--include</b> +and an <b>--exclude</b> pattern, it is excluded. There is no short form for this +option. +</P> +<P> +<b>--exclude-from=</b><i>filename</i> +Treat each non-empty line of the file as the data for an <b>--exclude</b> +option. What constitutes a newline when reading the file is the operating +system's default. The <b>--newline</b> option has no effect on this option. This +option may be given more than once in order to specify a number of files to +read. +</P> +<P> +<b>--exclude-dir</b>=<i>pattern</i> +Directories whose names match the pattern are skipped without being processed, +whatever the setting of the <b>--recursive</b> option. This applies to all +directories, whether listed on the command line, obtained from +<b>--file-list</b>, or by scanning a parent directory. The pattern is a PCRE +regular expression, and is matched against the final component of the directory +name, not the entire path. The <b>-F</b>, <b>-w</b>, and <b>-x</b> options do not +apply to this pattern. The option may be given any number of times in order to +specify more than one pattern. If a directory matches both <b>--include-dir</b> +and <b>--exclude-dir</b>, it is excluded. There is no short form for this +option. +</P> +<P> +<b>-F</b>, <b>--fixed-strings</b> +Interpret each data-matching pattern as a list of fixed strings, separated by +newlines, instead of as a regular expression. What constitutes a newline for +this purpose is controlled by the <b>--newline</b> option. The <b>-w</b> (match +as a word) and <b>-x</b> (match whole line) options can be used with <b>-F</b>. +They apply to each of the fixed strings. A line is selected if any of the fixed +strings are found in it (subject to <b>-w</b> or <b>-x</b>, if present). This +option applies only to the patterns that are matched against the contents of +files; it does not apply to patterns specified by any of the <b>--include</b> or +<b>--exclude</b> options. +</P> +<P> +<b>-f</b> <i>filename</i>, <b>--file=</b><i>filename</i> +Read patterns from the file, one per line, and match them against +each line of input. What constitutes a newline when reading the file is the +operating system's default. The <b>--newline</b> option has no effect on this +option. Trailing white space is removed from each line, and blank lines are +ignored. An empty file contains no patterns and therefore matches nothing. See +also the comments about multiple patterns versus a single pattern with +alternatives in the description of <b>-e</b> above. +<br> +<br> +If this option is given more than once, all the specified files are +read. A data line is output if any of the patterns match it. A filename can +be given as "-" to refer to the standard input. When <b>-f</b> is used, patterns +specified on the command line using <b>-e</b> may also be present; they are +tested before the file's patterns. However, no other pattern is taken from the +command line; all arguments are treated as the names of paths to be searched. +</P> +<P> +<b>--file-list</b>=<i>filename</i> +Read a list of files and/or directories that are to be scanned from the given +file, one per line. Trailing white space is removed from each line, and blank +lines are ignored. These paths are processed before any that are listed on the +command line. The filename can be given as "-" to refer to the standard input. +If <b>--file</b> and <b>--file-list</b> are both specified as "-", patterns are +read first. This is useful only when the standard input is a terminal, from +which further lines (the list of files) can be read after an end-of-file +indication. If this option is given more than once, all the specified files are +read. +</P> +<P> +<b>--file-offsets</b> +Instead of showing lines or parts of lines that match, show each match as an +offset from the start of the file and a length, separated by a comma. In this +mode, no context is shown. That is, the <b>-A</b>, <b>-B</b>, and <b>-C</b> +options are ignored. If there is more than one match in a line, each of them is +shown separately. This option is mutually exclusive with <b>--line-offsets</b> +and <b>--only-matching</b>. +</P> +<P> +<b>-H</b>, <b>--with-filename</b> +Force the inclusion of the filename at the start of output lines when searching +a single file. By default, the filename is not shown in this case. For matching +lines, the filename is followed by a colon; for context lines, a hyphen +separator is used. If a line number is also being output, it follows the file +name. +</P> +<P> +<b>-h</b>, <b>--no-filename</b> +Suppress the output filenames when searching multiple files. By default, +filenames are shown when multiple files are searched. For matching lines, the +filename is followed by a colon; for context lines, a hyphen separator is used. +If a line number is also being output, it follows the file name. +</P> +<P> +<b>--help</b> +Output a help message, giving brief details of the command options and file +type support, and then exit. Anything else on the command line is +ignored. +</P> +<P> +<b>-I</b> +Treat binary files as never matching. This is equivalent to +<b>--binary-files</b>=<i>without-match</i>. +</P> +<P> +<b>-i</b>, <b>--ignore-case</b> +Ignore upper/lower case distinctions during comparisons. +</P> +<P> +<b>--include</b>=<i>pattern</i> +If any <b>--include</b> patterns are specified, the only files that are +processed are those that match one of the patterns (and do not match an +<b>--exclude</b> pattern). This option does not affect directories, but it +applies to all files, whether listed on the command line, obtained from +<b>--file-list</b>, or by scanning a directory. The pattern is a PCRE regular +expression, and is matched against the final component of the file name, not +the entire path. The <b>-F</b>, <b>-w</b>, and <b>-x</b> options do not apply to +this pattern. The option may be given any number of times. If a file name +matches both an <b>--include</b> and an <b>--exclude</b> pattern, it is excluded. +There is no short form for this option. +</P> +<P> +<b>--include-from=</b><i>filename</i> +Treat each non-empty line of the file as the data for an <b>--include</b> +option. What constitutes a newline for this purpose is the operating system's +default. The <b>--newline</b> option has no effect on this option. This option +may be given any number of times; all the files are read. +</P> +<P> +<b>--include-dir</b>=<i>pattern</i> +If any <b>--include-dir</b> patterns are specified, the only directories that +are processed are those that match one of the patterns (and do not match an +<b>--exclude-dir</b> pattern). This applies to all directories, whether listed +on the command line, obtained from <b>--file-list</b>, or by scanning a parent +directory. The pattern is a PCRE regular expression, and is matched against the +final component of the directory name, not the entire path. The <b>-F</b>, +<b>-w</b>, and <b>-x</b> options do not apply to this pattern. The option may be +given any number of times. If a directory matches both <b>--include-dir</b> and +<b>--exclude-dir</b>, it is excluded. There is no short form for this option. +</P> +<P> +<b>-L</b>, <b>--files-without-match</b> +Instead of outputting lines from the files, just output the names of the files +that do not contain any lines that would have been output. Each file name is +output once, on a separate line. +</P> +<P> +<b>-l</b>, <b>--files-with-matches</b> +Instead of outputting lines from the files, just output the names of the files +containing lines that would have been output. Each file name is output +once, on a separate line. Searching normally stops as soon as a matching line +is found in a file. However, if the <b>-c</b> (count) option is also used, +matching continues in order to obtain the correct count, and those files that +have at least one match are listed along with their counts. Using this option +with <b>-c</b> is a way of suppressing the listing of files with no matches. +</P> +<P> +<b>--label</b>=<i>name</i> +This option supplies a name to be used for the standard input when file names +are being output. If not supplied, "(standard input)" is used. There is no +short form for this option. +</P> +<P> +<b>--line-buffered</b> +When this option is given, input is read and processed line by line, and the +output is flushed after each write. By default, input is read in large chunks, +unless <b>pcregrep</b> can determine that it is reading from a terminal (which +is currently possible only in Unix-like environments). Output to terminal is +normally automatically flushed by the operating system. This option can be +useful when the input or output is attached to a pipe and you do not want +<b>pcregrep</b> to buffer up large amounts of data. However, its use will affect +performance, and the <b>-M</b> (multiline) option ceases to work. +</P> +<P> +<b>--line-offsets</b> +Instead of showing lines or parts of lines that match, show each match as a +line number, the offset from the start of the line, and a length. The line +number is terminated by a colon (as usual; see the <b>-n</b> option), and the +offset and length are separated by a comma. In this mode, no context is shown. +That is, the <b>-A</b>, <b>-B</b>, and <b>-C</b> options are ignored. If there is +more than one match in a line, each of them is shown separately. This option is +mutually exclusive with <b>--file-offsets</b> and <b>--only-matching</b>. +</P> +<P> +<b>--locale</b>=<i>locale-name</i> +This option specifies a locale to be used for pattern matching. It overrides +the value in the <b>LC_ALL</b> or <b>LC_CTYPE</b> environment variables. If no +locale is specified, the PCRE library's default (usually the "C" locale) is +used. There is no short form for this option. +</P> +<P> +<b>--match-limit</b>=<i>number</i> +Processing some regular expression patterns can require a very large amount of +memory, leading in some cases to a program crash if not enough is available. +Other patterns may take a very long time to search for all possible matching +strings. The <b>pcre_exec()</b> function that is called by <b>pcregrep</b> to do +the matching has two parameters that can limit the resources that it uses. +<br> +<br> +The <b>--match-limit</b> option provides a means of limiting resource usage +when processing patterns that are not going to match, but which have a very +large number of possibilities in their search trees. The classic example is a +pattern that uses nested unlimited repeats. Internally, PCRE uses a function +called <b>match()</b> which it calls repeatedly (sometimes recursively). The +limit set by <b>--match-limit</b> is imposed on the number of times this +function is called during a match, which has the effect of limiting the amount +of backtracking that can take place. +<br> +<br> +The <b>--recursion-limit</b> option is similar to <b>--match-limit</b>, but +instead of limiting the total number of times that <b>match()</b> is called, it +limits the depth of recursive calls, which in turn limits the amount of memory +that can be used. The recursion depth is a smaller number than the total number +of calls, because not all calls to <b>match()</b> are recursive. This limit is +of use only if it is set smaller than <b>--match-limit</b>. +<br> +<br> +There are no short forms for these options. The default settings are specified +when the PCRE library is compiled, with the default default being 10 million. +</P> +<P> +<b>-M</b>, <b>--multiline</b> +Allow patterns to match more than one line. When this option is given, patterns +may usefully contain literal newline characters and internal occurrences of ^ +and $ characters. The output for a successful match may consist of more than +one line, the last of which is the one in which the match ended. If the matched +string ends with a newline sequence the output ends at the end of that line. +<br> +<br> +When this option is set, the PCRE library is called in "multiline" mode. +There is a limit to the number of lines that can be matched, imposed by the way +that <b>pcregrep</b> buffers the input file as it scans it. However, +<b>pcregrep</b> ensures that at least 8K characters or the rest of the document +(whichever is the shorter) are available for forward matching, and similarly +the previous 8K characters (or all the previous characters, if fewer than 8K) +are guaranteed to be available for lookbehind assertions. This option does not +work when input is read line by line (see \fP--line-buffered\fP.) +</P> +<P> +<b>-N</b> <i>newline-type</i>, <b>--newline</b>=<i>newline-type</i> +The PCRE library supports five different conventions for indicating +the ends of lines. They are the single-character sequences CR (carriage return) +and LF (linefeed), the two-character sequence CRLF, an "anycrlf" convention, +which recognizes any of the preceding three types, and an "any" convention, in +which any Unicode line ending sequence is assumed to end a line. The Unicode +sequences are the three just mentioned, plus VT (vertical tab, U+000B), FF +(form feed, U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and +PS (paragraph separator, U+2029). +<br> +<br> +When the PCRE library is built, a default line-ending sequence is specified. +This is normally the standard sequence for the operating system. Unless +otherwise specified by this option, <b>pcregrep</b> uses the library's default. +The possible values for this option are CR, LF, CRLF, ANYCRLF, or ANY. This +makes it possible to use <b>pcregrep</b> to scan files that have come from other +environments without having to modify their line endings. If the data that is +being scanned does not agree with the convention set by this option, +<b>pcregrep</b> may behave in strange ways. Note that this option does not +apply to files specified by the <b>-f</b>, <b>--exclude-from</b>, or +<b>--include-from</b> options, which are expected to use the operating system's +standard newline sequence. +</P> +<P> +<b>-n</b>, <b>--line-number</b> +Precede each output line by its line number in the file, followed by a colon +for matching lines or a hyphen for context lines. If the filename is also being +output, it precedes the line number. This option is forced if +<b>--line-offsets</b> is used. +</P> +<P> +<b>--no-jit</b> +If the PCRE library is built with support for just-in-time compiling (which +speeds up matching), <b>pcregrep</b> automatically makes use of this, unless it +was explicitly disabled at build time. This option can be used to disable the +use of JIT at run time. It is provided for testing and working round problems. +It should never be needed in normal use. +</P> +<P> +<b>-o</b>, <b>--only-matching</b> +Show only the part of the line that matched a pattern instead of the whole +line. In this mode, no context is shown. That is, the <b>-A</b>, <b>-B</b>, and +<b>-C</b> options are ignored. If there is more than one match in a line, each +of them is shown separately. If <b>-o</b> is combined with <b>-v</b> (invert the +sense of the match to find non-matching lines), no output is generated, but the +return code is set appropriately. If the matched portion of the line is empty, +nothing is output unless the file name or line number are being printed, in +which case they are shown on an otherwise empty line. This option is mutually +exclusive with <b>--file-offsets</b> and <b>--line-offsets</b>. +</P> +<P> +<b>-o</b><i>number</i>, <b>--only-matching</b>=<i>number</i> +Show only the part of the line that matched the capturing parentheses of the +given number. Up to 32 capturing parentheses are supported, and -o0 is +equivalent to <b>-o</b> without a number. Because these options can be given +without an argument (see above), if an argument is present, it must be given in +the same shell item, for example, -o3 or --only-matching=2. The comments given +for the non-argument case above also apply to this case. If the specified +capturing parentheses do not exist in the pattern, or were not set in the +match, nothing is output unless the file name or line number are being printed. +<br> +<br> +If this option is given multiple times, multiple substrings are output, in the +order the options are given. For example, -o3 -o1 -o3 causes the substrings +matched by capturing parentheses 3 and 1 and then 3 again to be output. By +default, there is no separator (but see the next option). +</P> +<P> +<b>--om-separator</b>=<i>text</i> +Specify a separating string for multiple occurrences of <b>-o</b>. The default +is an empty string. Separating strings are never coloured. +</P> +<P> +<b>-q</b>, <b>--quiet</b> +Work quietly, that is, display nothing except error messages. The exit +status indicates whether or not any matches were found. +</P> +<P> +<b>-r</b>, <b>--recursive</b> +If any given path is a directory, recursively scan the files it contains, +taking note of any <b>--include</b> and <b>--exclude</b> settings. By default, a +directory is read as a normal file; in some operating systems this gives an +immediate end-of-file. This option is a shorthand for setting the <b>-d</b> +option to "recurse". +</P> +<P> +<b>--recursion-limit</b>=<i>number</i> +See <b>--match-limit</b> above. +</P> +<P> +<b>-s</b>, <b>--no-messages</b> +Suppress error messages about non-existent or unreadable files. Such files are +quietly skipped. However, the return code is still 2, even if matches were +found in other files. +</P> +<P> +<b>-u</b>, <b>--utf-8</b> +Operate in UTF-8 mode. This option is available only if PCRE has been compiled +with UTF-8 support. All patterns (including those for any <b>--exclude</b> and +<b>--include</b> options) and all subject lines that are scanned must be valid +strings of UTF-8 characters. +</P> +<P> +<b>-V</b>, <b>--version</b> +Write the version numbers of <b>pcregrep</b> and the PCRE library to the +standard output and then exit. Anything else on the command line is +ignored. +</P> +<P> +<b>-v</b>, <b>--invert-match</b> +Invert the sense of the match, so that lines which do <i>not</i> match any of +the patterns are the ones that are found. +</P> +<P> +<b>-w</b>, <b>--word-regex</b>, <b>--word-regexp</b> +Force the patterns to match only whole words. This is equivalent to having \b +at the start and end of the pattern. This option applies only to the patterns +that are matched against the contents of files; it does not apply to patterns +specified by any of the <b>--include</b> or <b>--exclude</b> options. +</P> +<P> +<b>-x</b>, <b>--line-regex</b>, <b>--line-regexp</b> +Force the patterns to be anchored (each must start matching at the beginning of +a line) and in addition, require them to match entire lines. This is equivalent +to having ^ and $ characters at the start and end of each alternative branch in +every pattern. This option applies only to the patterns that are matched +against the contents of files; it does not apply to patterns specified by any +of the <b>--include</b> or <b>--exclude</b> options. +</P> +<br><a name="SEC6" href="#TOC1">ENVIRONMENT VARIABLES</a><br> +<P> +The environment variables <b>LC_ALL</b> and <b>LC_CTYPE</b> are examined, in that +order, for a locale. The first one that is set is used. This can be overridden +by the <b>--locale</b> option. If no locale is set, the PCRE library's default +(usually the "C" locale) is used. +</P> +<br><a name="SEC7" href="#TOC1">NEWLINES</a><br> +<P> +The <b>-N</b> (<b>--newline</b>) option allows <b>pcregrep</b> to scan files with +different newline conventions from the default. Any parts of the input files +that are written to the standard output are copied identically, with whatever +newline sequences they have in the input. However, the setting of this option +does not affect the interpretation of files specified by the <b>-f</b>, +<b>--exclude-from</b>, or <b>--include-from</b> options, which are assumed to use +the operating system's standard newline sequence, nor does it affect the way in +which <b>pcregrep</b> writes informational messages to the standard error and +output streams. For these it uses the string "\n" to indicate newlines, +relying on the C I/O library to convert this to an appropriate sequence. +</P> +<br><a name="SEC8" href="#TOC1">OPTIONS COMPATIBILITY</a><br> +<P> +Many of the short and long forms of <b>pcregrep</b>'s options are the same +as in the GNU <b>grep</b> program. Any long option of the form +<b>--xxx-regexp</b> (GNU terminology) is also available as <b>--xxx-regex</b> +(PCRE terminology). However, the <b>--file-list</b>, <b>--file-offsets</b>, +<b>--include-dir</b>, <b>--line-offsets</b>, <b>--locale</b>, <b>--match-limit</b>, +<b>-M</b>, <b>--multiline</b>, <b>-N</b>, <b>--newline</b>, <b>--om-separator</b>, +<b>--recursion-limit</b>, <b>-u</b>, and <b>--utf-8</b> options are specific to +<b>pcregrep</b>, as is the use of the <b>--only-matching</b> option with a +capturing parentheses number. +</P> +<P> +Although most of the common options work the same way, a few are different in +<b>pcregrep</b>. For example, the <b>--include</b> option's argument is a glob +for GNU <b>grep</b>, but a regular expression for <b>pcregrep</b>. If both the +<b>-c</b> and <b>-l</b> options are given, GNU grep lists only file names, +without counts, but <b>pcregrep</b> gives the counts. +</P> +<br><a name="SEC9" href="#TOC1">OPTIONS WITH DATA</a><br> +<P> +There are four different ways in which an option with data can be specified. +If a short form option is used, the data may follow immediately, or (with one +exception) in the next command line item. For example: +<pre> + -f/some/file + -f /some/file +</pre> +The exception is the <b>-o</b> option, which may appear with or without data. +Because of this, if data is present, it must follow immediately in the same +item, for example -o3. +</P> +<P> +If a long form option is used, the data may appear in the same command line +item, separated by an equals character, or (with two exceptions) it may appear +in the next command line item. For example: +<pre> + --file=/some/file + --file /some/file +</pre> +Note, however, that if you want to supply a file name beginning with ~ as data +in a shell command, and have the shell expand ~ to a home directory, you must +separate the file name from the option, because the shell does not treat ~ +specially unless it is at the start of an item. +</P> +<P> +The exceptions to the above are the <b>--colour</b> (or <b>--color</b>) and +<b>--only-matching</b> options, for which the data is optional. If one of these +options does have data, it must be given in the first form, using an equals +character. Otherwise <b>pcregrep</b> will assume that it has no data. +</P> +<br><a name="SEC10" href="#TOC1">MATCHING ERRORS</a><br> +<P> +It is possible to supply a regular expression that takes a very long time to +fail to match certain lines. Such patterns normally involve nested indefinite +repeats, for example: (a+)*\d when matched against a line of a's with no final +digit. The PCRE matching function has a resource limit that causes it to abort +in these circumstances. If this happens, <b>pcregrep</b> outputs an error +message and the line that caused the problem to the standard error stream. If +there are more than 20 such errors, <b>pcregrep</b> gives up. +</P> +<P> +The <b>--match-limit</b> option of <b>pcregrep</b> can be used to set the overall +resource limit; there is a second option called <b>--recursion-limit</b> that +sets a limit on the amount of memory (usually stack) that is used (see the +discussion of these options above). +</P> +<br><a name="SEC11" href="#TOC1">DIAGNOSTICS</a><br> +<P> +Exit status is 0 if any matches were found, 1 if no matches were found, and 2 +for syntax errors, overlong lines, non-existent or inaccessible files (even if +matches were found in other files) or too many matching errors. Using the +<b>-s</b> option to suppress error messages about inaccessible files does not +affect the return code. +</P> +<br><a name="SEC12" href="#TOC1">SEE ALSO</a><br> +<P> +<b>pcrepattern</b>(3), <b>pcresyntax</b>(3), <b>pcretest</b>(1). +</P> +<br><a name="SEC13" href="#TOC1">AUTHOR</a><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><a name="SEC14" href="#TOC1">REVISION</a><br> +<P> +Last updated: 03 April 2014 +<br> +Copyright © 1997-2014 University of Cambridge. +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcrejit.html b/plugins/Pcre16/docs/doc/html/pcrejit.html new file mode 100644 index 0000000000..210f1da026 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcrejit.html @@ -0,0 +1,452 @@ +<html> +<head> +<title>pcrejit specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcrejit man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<ul> +<li><a name="TOC1" href="#SEC1">PCRE JUST-IN-TIME COMPILER SUPPORT</a> +<li><a name="TOC2" href="#SEC2">8-BIT, 16-BIT AND 32-BIT SUPPORT</a> +<li><a name="TOC3" href="#SEC3">AVAILABILITY OF JIT SUPPORT</a> +<li><a name="TOC4" href="#SEC4">SIMPLE USE OF JIT</a> +<li><a name="TOC5" href="#SEC5">UNSUPPORTED OPTIONS AND PATTERN ITEMS</a> +<li><a name="TOC6" href="#SEC6">RETURN VALUES FROM JIT EXECUTION</a> +<li><a name="TOC7" href="#SEC7">SAVING AND RESTORING COMPILED PATTERNS</a> +<li><a name="TOC8" href="#SEC8">CONTROLLING THE JIT STACK</a> +<li><a name="TOC9" href="#SEC9">JIT STACK FAQ</a> +<li><a name="TOC10" href="#SEC10">EXAMPLE CODE</a> +<li><a name="TOC11" href="#SEC11">JIT FAST PATH API</a> +<li><a name="TOC12" href="#SEC12">SEE ALSO</a> +<li><a name="TOC13" href="#SEC13">AUTHOR</a> +<li><a name="TOC14" href="#SEC14">REVISION</a> +</ul> +<br><a name="SEC1" href="#TOC1">PCRE JUST-IN-TIME COMPILER SUPPORT</a><br> +<P> +Just-in-time compiling is a heavyweight optimization that can greatly speed up +pattern matching. However, it comes at the cost of extra processing before the +match is performed. Therefore, it is of most benefit when the same pattern is +going to be matched many times. This does not necessarily mean many calls of a +matching function; if the pattern is not anchored, matching attempts may take +place many times at various positions in the subject, even for a single call. +Therefore, if the subject string is very long, it may still pay to use JIT for +one-off matches. +</P> +<P> +JIT support applies only to the traditional Perl-compatible matching function. +It does not apply when the DFA matching function is being used. The code for +this support was written by Zoltan Herczeg. +</P> +<br><a name="SEC2" href="#TOC1">8-BIT, 16-BIT AND 32-BIT SUPPORT</a><br> +<P> +JIT support is available for all of the 8-bit, 16-bit and 32-bit PCRE +libraries. To keep this documentation simple, only the 8-bit interface is +described in what follows. If you are using the 16-bit library, substitute the +16-bit functions and 16-bit structures (for example, <i>pcre16_jit_stack</i> +instead of <i>pcre_jit_stack</i>). If you are using the 32-bit library, +substitute the 32-bit functions and 32-bit structures (for example, +<i>pcre32_jit_stack</i> instead of <i>pcre_jit_stack</i>). +</P> +<br><a name="SEC3" href="#TOC1">AVAILABILITY OF JIT SUPPORT</a><br> +<P> +JIT support is an optional feature of PCRE. The "configure" option --enable-jit +(or equivalent CMake option) must be set when PCRE is built if you want to use +JIT. The support is limited to the following hardware platforms: +<pre> + ARM v5, v7, and Thumb2 + Intel x86 32-bit and 64-bit + MIPS 32-bit + Power PC 32-bit and 64-bit + SPARC 32-bit (experimental) +</pre> +If --enable-jit is set on an unsupported platform, compilation fails. +</P> +<P> +A program that is linked with PCRE 8.20 or later can tell if JIT support is +available by calling <b>pcre_config()</b> with the PCRE_CONFIG_JIT option. The +result is 1 when JIT is available, and 0 otherwise. However, a simple program +does not need to check this in order to use JIT. The normal API is implemented +in a way that falls back to the interpretive code if JIT is not available. For +programs that need the best possible performance, there is also a "fast path" +API that is JIT-specific. +</P> +<P> +If your program may sometimes be linked with versions of PCRE that are older +than 8.20, but you want to use JIT when it is available, you can test +the values of PCRE_MAJOR and PCRE_MINOR, or the existence of a JIT macro such +as PCRE_CONFIG_JIT, for compile-time control of your code. +</P> +<br><a name="SEC4" href="#TOC1">SIMPLE USE OF JIT</a><br> +<P> +You have to do two things to make use of the JIT support in the simplest way: +<pre> + (1) Call <b>pcre_study()</b> with the PCRE_STUDY_JIT_COMPILE option for + each compiled pattern, and pass the resulting <b>pcre_extra</b> block to + <b>pcre_exec()</b>. + + (2) Use <b>pcre_free_study()</b> to free the <b>pcre_extra</b> block when it is + no longer needed, instead of just freeing it yourself. This ensures that + any JIT data is also freed. +</pre> +For a program that may be linked with pre-8.20 versions of PCRE, you can insert +<pre> + #ifndef PCRE_STUDY_JIT_COMPILE + #define PCRE_STUDY_JIT_COMPILE 0 + #endif +</pre> +so that no option is passed to <b>pcre_study()</b>, and then use something like +this to free the study data: +<pre> + #ifdef PCRE_CONFIG_JIT + pcre_free_study(study_ptr); + #else + pcre_free(study_ptr); + #endif +</pre> +PCRE_STUDY_JIT_COMPILE requests the JIT compiler to generate code for complete +matches. If you want to run partial matches using the PCRE_PARTIAL_HARD or +PCRE_PARTIAL_SOFT options of <b>pcre_exec()</b>, you should set one or both of +the following options in addition to, or instead of, PCRE_STUDY_JIT_COMPILE +when you call <b>pcre_study()</b>: +<pre> + PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE + PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE +</pre> +The JIT compiler generates different optimized code for each of the three +modes (normal, soft partial, hard partial). When <b>pcre_exec()</b> is called, +the appropriate code is run if it is available. Otherwise, the pattern is +matched using interpretive code. +</P> +<P> +In some circumstances you may need to call additional functions. These are +described in the section entitled +<a href="#stackcontrol">"Controlling the JIT stack"</a> +below. +</P> +<P> +If JIT support is not available, PCRE_STUDY_JIT_COMPILE etc. are ignored, and +no JIT data is created. Otherwise, the compiled pattern is passed to the JIT +compiler, which turns it into machine code that executes much faster than the +normal interpretive code. When <b>pcre_exec()</b> is passed a <b>pcre_extra</b> +block containing a pointer to JIT code of the appropriate mode (normal or +hard/soft partial), it obeys that code instead of running the interpreter. The +result is identical, but the compiled JIT code runs much faster. +</P> +<P> +There are some <b>pcre_exec()</b> options that are not supported for JIT +execution. There are also some pattern items that JIT cannot handle. Details +are given below. In both cases, execution automatically falls back to the +interpretive code. If you want to know whether JIT was actually used for a +particular match, you should arrange for a JIT callback function to be set up +as described in the section entitled +<a href="#stackcontrol">"Controlling the JIT stack"</a> +below, even if you do not need to supply a non-default JIT stack. Such a +callback function is called whenever JIT code is about to be obeyed. If the +execution options are not right for JIT execution, the callback function is not +obeyed. +</P> +<P> +If the JIT compiler finds an unsupported item, no JIT data is generated. You +can find out if JIT execution is available after studying a pattern by calling +<b>pcre_fullinfo()</b> with the PCRE_INFO_JIT option. A result of 1 means that +JIT compilation was successful. A result of 0 means that JIT support is not +available, or the pattern was not studied with PCRE_STUDY_JIT_COMPILE etc., or +the JIT compiler was not able to handle the pattern. +</P> +<P> +Once a pattern has been studied, with or without JIT, it can be used as many +times as you like for matching different subject strings. +</P> +<br><a name="SEC5" href="#TOC1">UNSUPPORTED OPTIONS AND PATTERN ITEMS</a><br> +<P> +The only <b>pcre_exec()</b> options that are supported for JIT execution are +PCRE_NO_UTF8_CHECK, PCRE_NO_UTF16_CHECK, PCRE_NO_UTF32_CHECK, PCRE_NOTBOL, +PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and +PCRE_PARTIAL_SOFT. +</P> +<P> +The only unsupported pattern items are \C (match a single data unit) when +running in a UTF mode, and a callout immediately before an assertion condition +in a conditional group. +</P> +<br><a name="SEC6" href="#TOC1">RETURN VALUES FROM JIT EXECUTION</a><br> +<P> +When a pattern is matched using JIT execution, the return values are the same +as those given by the interpretive <b>pcre_exec()</b> code, with the addition of +one new error code: PCRE_ERROR_JIT_STACKLIMIT. This means that the memory used +for the JIT stack was insufficient. See +<a href="#stackcontrol">"Controlling the JIT stack"</a> +below for a discussion of JIT stack usage. For compatibility with the +interpretive <b>pcre_exec()</b> code, no more than two-thirds of the +<i>ovector</i> argument is used for passing back captured substrings. +</P> +<P> +The error code PCRE_ERROR_MATCHLIMIT is returned by the JIT code if searching a +very large pattern tree goes on for too long, as it is in the same circumstance +when JIT is not used, but the details of exactly what is counted are not the +same. The PCRE_ERROR_RECURSIONLIMIT error code is never returned by JIT +execution. +</P> +<br><a name="SEC7" href="#TOC1">SAVING AND RESTORING COMPILED PATTERNS</a><br> +<P> +The code that is generated by the JIT compiler is architecture-specific, and is +also position dependent. For those reasons it cannot be saved (in a file or +database) and restored later like the bytecode and other data of a compiled +pattern. Saving and restoring compiled patterns is not something many people +do. More detail about this facility is given in the +<a href="pcreprecompile.html"><b>pcreprecompile</b></a> +documentation. It should be possible to run <b>pcre_study()</b> on a saved and +restored pattern, and thereby recreate the JIT data, but because JIT +compilation uses significant resources, it is probably not worth doing this; +you might as well recompile the original pattern. +<a name="stackcontrol"></a></P> +<br><a name="SEC8" href="#TOC1">CONTROLLING THE JIT STACK</a><br> +<P> +When the compiled JIT code runs, it needs a block of memory to use as a stack. +By default, it uses 32K on the machine stack. However, some large or +complicated patterns need more than this. The error PCRE_ERROR_JIT_STACKLIMIT +is given when there is not enough stack. Three functions are provided for +managing blocks of memory for use as JIT stacks. There is further discussion +about the use of JIT stacks in the section entitled +<a href="#stackcontrol">"JIT stack FAQ"</a> +below. +</P> +<P> +The <b>pcre_jit_stack_alloc()</b> function creates a JIT stack. Its arguments +are a starting size and a maximum size, and it returns a pointer to an opaque +structure of type <b>pcre_jit_stack</b>, or NULL if there is an error. The +<b>pcre_jit_stack_free()</b> function can be used to free a stack that is no +longer needed. (For the technically minded: the address space is allocated by +mmap or VirtualAlloc.) +</P> +<P> +JIT uses far less memory for recursion than the interpretive code, +and a maximum stack size of 512K to 1M should be more than enough for any +pattern. +</P> +<P> +The <b>pcre_assign_jit_stack()</b> function specifies which stack JIT code +should use. Its arguments are as follows: +<pre> + pcre_extra *extra + pcre_jit_callback callback + void *data +</pre> +The <i>extra</i> argument must be the result of studying a pattern with +PCRE_STUDY_JIT_COMPILE etc. There are three cases for the values of the other +two options: +<pre> + (1) If <i>callback</i> is NULL and <i>data</i> is NULL, an internal 32K block + on the machine stack is used. + + (2) If <i>callback</i> is NULL and <i>data</i> is not NULL, <i>data</i> must be + a valid JIT stack, the result of calling <b>pcre_jit_stack_alloc()</b>. + + (3) If <i>callback</i> is not NULL, it must point to a function that is + called with <i>data</i> as an argument at the start of matching, in + order to set up a JIT stack. If the return from the callback + function is NULL, the internal 32K stack is used; otherwise the + return value must be a valid JIT stack, the result of calling + <b>pcre_jit_stack_alloc()</b>. +</pre> +A callback function is obeyed whenever JIT code is about to be run; it is not +obeyed when <b>pcre_exec()</b> is called with options that are incompatible for +JIT execution. A callback function can therefore be used to determine whether a +match operation was executed by JIT or by the interpreter. +</P> +<P> +You may safely use the same JIT stack for more than one pattern (either by +assigning directly or by callback), as long as the patterns are all matched +sequentially in the same thread. In a multithread application, if you do not +specify a JIT stack, or if you assign or pass back NULL from a callback, that +is thread-safe, because each thread has its own machine stack. However, if you +assign or pass back a non-NULL JIT stack, this must be a different stack for +each thread so that the application is thread-safe. +</P> +<P> +Strictly speaking, even more is allowed. You can assign the same non-NULL stack +to any number of patterns as long as they are not used for matching by multiple +threads at the same time. For example, you can assign the same stack to all +compiled patterns, and use a global mutex in the callback to wait until the +stack is available for use. However, this is an inefficient solution, and not +recommended. +</P> +<P> +This is a suggestion for how a multithreaded program that needs to set up +non-default JIT stacks might operate: +<pre> + During thread initalization + thread_local_var = pcre_jit_stack_alloc(...) + + During thread exit + pcre_jit_stack_free(thread_local_var) + + Use a one-line callback function + return thread_local_var +</pre> +All the functions described in this section do nothing if JIT is not available, +and <b>pcre_assign_jit_stack()</b> does nothing unless the <b>extra</b> argument +is non-NULL and points to a <b>pcre_extra</b> block that is the result of a +successful study with PCRE_STUDY_JIT_COMPILE etc. +<a name="stackfaq"></a></P> +<br><a name="SEC9" href="#TOC1">JIT STACK FAQ</a><br> +<P> +(1) Why do we need JIT stacks? +<br> +<br> +PCRE (and JIT) is a recursive, depth-first engine, so it needs a stack where +the local data of the current node is pushed before checking its child nodes. +Allocating real machine stack on some platforms is difficult. For example, the +stack chain needs to be updated every time if we extend the stack on PowerPC. +Although it is possible, its updating time overhead decreases performance. So +we do the recursion in memory. +</P> +<P> +(2) Why don't we simply allocate blocks of memory with <b>malloc()</b>? +<br> +<br> +Modern operating systems have a nice feature: they can reserve an address space +instead of allocating memory. We can safely allocate memory pages inside this +address space, so the stack could grow without moving memory data (this is +important because of pointers). Thus we can allocate 1M address space, and use +only a single memory page (usually 4K) if that is enough. However, we can still +grow up to 1M anytime if needed. +</P> +<P> +(3) Who "owns" a JIT stack? +<br> +<br> +The owner of the stack is the user program, not the JIT studied pattern or +anything else. The user program must ensure that if a stack is used by +<b>pcre_exec()</b>, (that is, it is assigned to the pattern currently running), +that stack must not be used by any other threads (to avoid overwriting the same +memory area). The best practice for multithreaded programs is to allocate a +stack for each thread, and return this stack through the JIT callback function. +</P> +<P> +(4) When should a JIT stack be freed? +<br> +<br> +You can free a JIT stack at any time, as long as it will not be used by +<b>pcre_exec()</b> again. When you assign the stack to a pattern, only a pointer +is set. There is no reference counting or any other magic. You can free the +patterns and stacks in any order, anytime. Just <i>do not</i> call +<b>pcre_exec()</b> with a pattern pointing to an already freed stack, as that +will cause SEGFAULT. (Also, do not free a stack currently used by +<b>pcre_exec()</b> in another thread). You can also replace the stack for a +pattern at any time. You can even free the previous stack before assigning a +replacement. +</P> +<P> +(5) Should I allocate/free a stack every time before/after calling +<b>pcre_exec()</b>? +<br> +<br> +No, because this is too costly in terms of resources. However, you could +implement some clever idea which release the stack if it is not used in let's +say two minutes. The JIT callback can help to achieve this without keeping a +list of the currently JIT studied patterns. +</P> +<P> +(6) OK, the stack is for long term memory allocation. But what happens if a +pattern causes stack overflow with a stack of 1M? Is that 1M kept until the +stack is freed? +<br> +<br> +Especially on embedded sytems, it might be a good idea to release memory +sometimes without freeing the stack. There is no API for this at the moment. +Probably a function call which returns with the currently allocated memory for +any stack and another which allows releasing memory (shrinking the stack) would +be a good idea if someone needs this. +</P> +<P> +(7) This is too much of a headache. Isn't there any better solution for JIT +stack handling? +<br> +<br> +No, thanks to Windows. If POSIX threads were used everywhere, we could throw +out this complicated API. +</P> +<br><a name="SEC10" href="#TOC1">EXAMPLE CODE</a><br> +<P> +This is a single-threaded example that specifies a JIT stack without using a +callback. +<pre> + int rc; + int ovector[30]; + pcre *re; + pcre_extra *extra; + pcre_jit_stack *jit_stack; + + re = pcre_compile(pattern, 0, &error, &erroffset, NULL); + /* Check for errors */ + extra = pcre_study(re, PCRE_STUDY_JIT_COMPILE, &error); + jit_stack = pcre_jit_stack_alloc(32*1024, 512*1024); + /* Check for error (NULL) */ + pcre_assign_jit_stack(extra, NULL, jit_stack); + rc = pcre_exec(re, extra, subject, length, 0, 0, ovector, 30); + /* Check results */ + pcre_free(re); + pcre_free_study(extra); + pcre_jit_stack_free(jit_stack); + +</PRE> +</P> +<br><a name="SEC11" href="#TOC1">JIT FAST PATH API</a><br> +<P> +Because the API described above falls back to interpreted execution when JIT is +not available, it is convenient for programs that are written for general use +in many environments. However, calling JIT via <b>pcre_exec()</b> does have a +performance impact. Programs that are written for use where JIT is known to be +available, and which need the best possible performance, can instead use a +"fast path" API to call JIT execution directly instead of calling +<b>pcre_exec()</b> (obviously only for patterns that have been successfully +studied by JIT). +</P> +<P> +The fast path function is called <b>pcre_jit_exec()</b>, and it takes exactly +the same arguments as <b>pcre_exec()</b>, plus one additional argument that +must point to a JIT stack. The JIT stack arrangements described above do not +apply. The return values are the same as for <b>pcre_exec()</b>. +</P> +<P> +When you call <b>pcre_exec()</b>, as well as testing for invalid options, a +number of other sanity checks are performed on the arguments. For example, if +the subject pointer is NULL, or its length is negative, an immediate error is +given. Also, unless PCRE_NO_UTF[8|16|32] is set, a UTF subject string is tested +for validity. In the interests of speed, these checks do not happen on the JIT +fast path, and if invalid data is passed, the result is undefined. +</P> +<P> +Bypassing the sanity checks and the <b>pcre_exec()</b> wrapping can give +speedups of more than 10%. +</P> +<br><a name="SEC12" href="#TOC1">SEE ALSO</a><br> +<P> +<b>pcreapi</b>(3) +</P> +<br><a name="SEC13" href="#TOC1">AUTHOR</a><br> +<P> +Philip Hazel (FAQ by Zoltan Herczeg) +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><a name="SEC14" href="#TOC1">REVISION</a><br> +<P> +Last updated: 17 March 2013 +<br> +Copyright © 1997-2013 University of Cambridge. +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcrelimits.html b/plugins/Pcre16/docs/doc/html/pcrelimits.html new file mode 100644 index 0000000000..ee5ebf033d --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcrelimits.html @@ -0,0 +1,90 @@ +<html> +<head> +<title>pcrelimits specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcrelimits man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SIZE AND OTHER LIMITATIONS +</b><br> +<P> +There are some size limitations in PCRE but it is hoped that they will never in +practice be relevant. +</P> +<P> +The maximum length of a compiled pattern is approximately 64K data units (bytes +for the 8-bit library, 16-bit units for the 16-bit library, and 32-bit units for +the 32-bit library) if PCRE is compiled with the default internal linkage size, +which is 2 bytes for the 8-bit and 16-bit libraries, and 4 bytes for the 32-bit +library. If you want to process regular expressions that are truly enormous, +you can compile PCRE with an internal linkage size of 3 or 4 (when building the +16-bit or 32-bit library, 3 is rounded up to 4). See the <b>README</b> file in +the source distribution and the +<a href="pcrebuild.html"><b>pcrebuild</b></a> +documentation for details. In these cases the limit is substantially larger. +However, the speed of execution is slower. +</P> +<P> +All values in repeating quantifiers must be less than 65536. +</P> +<P> +There is no limit to the number of parenthesized subpatterns, but there can be +no more than 65535 capturing subpatterns. There is, however, a limit to the +depth of nesting of parenthesized subpatterns of all kinds. This is imposed in +order to limit the amount of system stack used at compile time. The limit can +be specified when PCRE is built; the default is 250. +</P> +<P> +There is a limit to the number of forward references to subsequent subpatterns +of around 200,000. Repeated forward references with fixed upper limits, for +example, (?2){0,100} when subpattern number 2 is to the right, are included in +the count. There is no limit to the number of backward references. +</P> +<P> +The maximum length of name for a named subpattern is 32 characters, and the +maximum number of named subpatterns is 10000. +</P> +<P> +The maximum length of a name in a (*MARK), (*PRUNE), (*SKIP), or (*THEN) verb +is 255 for the 8-bit library and 65535 for the 16-bit and 32-bit libraries. +</P> +<P> +The maximum length of a subject string is the largest positive number that an +integer variable can hold. However, when using the traditional matching +function, PCRE uses recursion to handle subpatterns and indefinite repetition. +This means that the available stack space may limit the size of a subject +string that can be processed by certain patterns. For a discussion of stack +issues, see the +<a href="pcrestack.html"><b>pcrestack</b></a> +documentation. +</P> +<br><b> +AUTHOR +</b><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><b> +REVISION +</b><br> +<P> +Last updated: 05 November 2013 +<br> +Copyright © 1997-2013 University of Cambridge. +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcrematching.html b/plugins/Pcre16/docs/doc/html/pcrematching.html new file mode 100644 index 0000000000..a1af39b68d --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcrematching.html @@ -0,0 +1,242 @@ +<html> +<head> +<title>pcrematching specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcrematching man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<ul> +<li><a name="TOC1" href="#SEC1">PCRE MATCHING ALGORITHMS</a> +<li><a name="TOC2" href="#SEC2">REGULAR EXPRESSIONS AS TREES</a> +<li><a name="TOC3" href="#SEC3">THE STANDARD MATCHING ALGORITHM</a> +<li><a name="TOC4" href="#SEC4">THE ALTERNATIVE MATCHING ALGORITHM</a> +<li><a name="TOC5" href="#SEC5">ADVANTAGES OF THE ALTERNATIVE ALGORITHM</a> +<li><a name="TOC6" href="#SEC6">DISADVANTAGES OF THE ALTERNATIVE ALGORITHM</a> +<li><a name="TOC7" href="#SEC7">AUTHOR</a> +<li><a name="TOC8" href="#SEC8">REVISION</a> +</ul> +<br><a name="SEC1" href="#TOC1">PCRE MATCHING ALGORITHMS</a><br> +<P> +This document describes the two different algorithms that are available in PCRE +for matching a compiled regular expression against a given subject string. The +"standard" algorithm is the one provided by the <b>pcre_exec()</b>, +<b>pcre16_exec()</b> and <b>pcre32_exec()</b> functions. These work in the same +as as Perl's matching function, and provide a Perl-compatible matching operation. +The just-in-time (JIT) optimization that is described in the +<a href="pcrejit.html"><b>pcrejit</b></a> +documentation is compatible with these functions. +</P> +<P> +An alternative algorithm is provided by the <b>pcre_dfa_exec()</b>, +<b>pcre16_dfa_exec()</b> and <b>pcre32_dfa_exec()</b> functions; they operate in +a different way, and are not Perl-compatible. This alternative has advantages +and disadvantages compared with the standard algorithm, and these are described +below. +</P> +<P> +When there is only one possible way in which a given subject string can match a +pattern, the two algorithms give the same answer. A difference arises, however, +when there are multiple possibilities. For example, if the pattern +<pre> + ^<.*> +</pre> +is matched against the string +<pre> + <something> <something else> <something further> +</pre> +there are three possible answers. The standard algorithm finds only one of +them, whereas the alternative algorithm finds all three. +</P> +<br><a name="SEC2" href="#TOC1">REGULAR EXPRESSIONS AS TREES</a><br> +<P> +The set of strings that are matched by a regular expression can be represented +as a tree structure. An unlimited repetition in the pattern makes the tree of +infinite size, but it is still a tree. Matching the pattern to a given subject +string (from a given starting point) can be thought of as a search of the tree. +There are two ways to search a tree: depth-first and breadth-first, and these +correspond to the two matching algorithms provided by PCRE. +</P> +<br><a name="SEC3" href="#TOC1">THE STANDARD MATCHING ALGORITHM</a><br> +<P> +In the terminology of Jeffrey Friedl's book "Mastering Regular +Expressions", the standard algorithm is an "NFA algorithm". It conducts a +depth-first search of the pattern tree. That is, it proceeds along a single +path through the tree, checking that the subject matches what is required. When +there is a mismatch, the algorithm tries any alternatives at the current point, +and if they all fail, it backs up to the previous branch point in the tree, and +tries the next alternative branch at that level. This often involves backing up +(moving to the left) in the subject string as well. The order in which +repetition branches are tried is controlled by the greedy or ungreedy nature of +the quantifier. +</P> +<P> +If a leaf node is reached, a matching string has been found, and at that point +the algorithm stops. Thus, if there is more than one possible match, this +algorithm returns the first one that it finds. Whether this is the shortest, +the longest, or some intermediate length depends on the way the greedy and +ungreedy repetition quantifiers are specified in the pattern. +</P> +<P> +Because it ends up with a single path through the tree, it is relatively +straightforward for this algorithm to keep track of the substrings that are +matched by portions of the pattern in parentheses. This provides support for +capturing parentheses and back references. +</P> +<br><a name="SEC4" href="#TOC1">THE ALTERNATIVE MATCHING ALGORITHM</a><br> +<P> +This algorithm conducts a breadth-first search of the tree. Starting from the +first matching point in the subject, it scans the subject string from left to +right, once, character by character, and as it does this, it remembers all the +paths through the tree that represent valid matches. In Friedl's terminology, +this is a kind of "DFA algorithm", though it is not implemented as a +traditional finite state machine (it keeps multiple states active +simultaneously). +</P> +<P> +Although the general principle of this matching algorithm is that it scans the +subject string only once, without backtracking, there is one exception: when a +lookaround assertion is encountered, the characters following or preceding the +current point have to be independently inspected. +</P> +<P> +The scan continues until either the end of the subject is reached, or there are +no more unterminated paths. At this point, terminated paths represent the +different matching possibilities (if there are none, the match has failed). +Thus, if there is more than one possible match, this algorithm finds all of +them, and in particular, it finds the longest. The matches are returned in +decreasing order of length. There is an option to stop the algorithm after the +first match (which is necessarily the shortest) is found. +</P> +<P> +Note that all the matches that are found start at the same point in the +subject. If the pattern +<pre> + cat(er(pillar)?)? +</pre> +is matched against the string "the caterpillar catchment", the result will be +the three strings "caterpillar", "cater", and "cat" that start at the fifth +character of the subject. The algorithm does not automatically move on to find +matches that start at later positions. +</P> +<P> +PCRE's "auto-possessification" optimization usually applies to character +repeats at the end of a pattern (as well as internally). For example, the +pattern "a\d+" is compiled as if it were "a\d++" because there is no point +even considering the possibility of backtracking into the repeated digits. For +DFA matching, this means that only one possible match is found. If you really +do want multiple matches in such cases, either use an ungreedy repeat +("a\d+?") or set the PCRE_NO_AUTO_POSSESS option when compiling. +</P> +<P> +There are a number of features of PCRE regular expressions that are not +supported by the alternative matching algorithm. They are as follows: +</P> +<P> +1. Because the algorithm finds all possible matches, the greedy or ungreedy +nature of repetition quantifiers is not relevant. Greedy and ungreedy +quantifiers are treated in exactly the same way. However, possessive +quantifiers can make a difference when what follows could also match what is +quantified, for example in a pattern like this: +<pre> + ^a++\w! +</pre> +This pattern matches "aaab!" but not "aaa!", which would be matched by a +non-possessive quantifier. Similarly, if an atomic group is present, it is +matched as if it were a standalone pattern at the current point, and the +longest match is then "locked in" for the rest of the overall pattern. +</P> +<P> +2. When dealing with multiple paths through the tree simultaneously, it is not +straightforward to keep track of captured substrings for the different matching +possibilities, and PCRE's implementation of this algorithm does not attempt to +do this. This means that no captured substrings are available. +</P> +<P> +3. Because no substrings are captured, back references within the pattern are +not supported, and cause errors if encountered. +</P> +<P> +4. For the same reason, conditional expressions that use a backreference as the +condition or test for a specific group recursion are not supported. +</P> +<P> +5. Because many paths through the tree may be active, the \K escape sequence, +which resets the start of the match when encountered (but may be on some paths +and not on others), is not supported. It causes an error if encountered. +</P> +<P> +6. Callouts are supported, but the value of the <i>capture_top</i> field is +always 1, and the value of the <i>capture_last</i> field is always -1. +</P> +<P> +7. The \C escape sequence, which (in the standard algorithm) always matches a +single data unit, even in UTF-8, UTF-16 or UTF-32 modes, is not supported in +these modes, because the alternative algorithm moves through the subject string +one character (not data unit) at a time, for all active paths through the tree. +</P> +<P> +8. Except for (*FAIL), the backtracking control verbs such as (*PRUNE) are not +supported. (*FAIL) is supported, and behaves like a failing negative assertion. +</P> +<br><a name="SEC5" href="#TOC1">ADVANTAGES OF THE ALTERNATIVE ALGORITHM</a><br> +<P> +Using the alternative matching algorithm provides the following advantages: +</P> +<P> +1. All possible matches (at a single point in the subject) are automatically +found, and in particular, the longest match is found. To find more than one +match using the standard algorithm, you have to do kludgy things with +callouts. +</P> +<P> +2. Because the alternative algorithm scans the subject string just once, and +never needs to backtrack (except for lookbehinds), it is possible to pass very +long subject strings to the matching function in several pieces, checking for +partial matching each time. Although it is possible to do multi-segment +matching using the standard algorithm by retaining partially matched +substrings, it is more complicated. The +<a href="pcrepartial.html"><b>pcrepartial</b></a> +documentation gives details of partial matching and discusses multi-segment +matching. +</P> +<br><a name="SEC6" href="#TOC1">DISADVANTAGES OF THE ALTERNATIVE ALGORITHM</a><br> +<P> +The alternative algorithm suffers from a number of disadvantages: +</P> +<P> +1. It is substantially slower than the standard algorithm. This is partly +because it has to search for all possible matches, but is also because it is +less susceptible to optimization. +</P> +<P> +2. Capturing parentheses and back references are not supported. +</P> +<P> +3. Although atomic groups are supported, their use does not provide the +performance advantage that it does for the standard algorithm. +</P> +<br><a name="SEC7" href="#TOC1">AUTHOR</a><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><a name="SEC8" href="#TOC1">REVISION</a><br> +<P> +Last updated: 12 November 2013 +<br> +Copyright © 1997-2012 University of Cambridge. +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcrepartial.html b/plugins/Pcre16/docs/doc/html/pcrepartial.html new file mode 100644 index 0000000000..4faeafcb68 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcrepartial.html @@ -0,0 +1,509 @@ +<html> +<head> +<title>pcrepartial specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcrepartial man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<ul> +<li><a name="TOC1" href="#SEC1">PARTIAL MATCHING IN PCRE</a> +<li><a name="TOC2" href="#SEC2">PARTIAL MATCHING USING pcre_exec() OR pcre[16|32]_exec()</a> +<li><a name="TOC3" href="#SEC3">PARTIAL MATCHING USING pcre_dfa_exec() OR pcre[16|32]_dfa_exec()</a> +<li><a name="TOC4" href="#SEC4">PARTIAL MATCHING AND WORD BOUNDARIES</a> +<li><a name="TOC5" href="#SEC5">FORMERLY RESTRICTED PATTERNS</a> +<li><a name="TOC6" href="#SEC6">EXAMPLE OF PARTIAL MATCHING USING PCRETEST</a> +<li><a name="TOC7" href="#SEC7">MULTI-SEGMENT MATCHING WITH pcre_dfa_exec() OR pcre[16|32]_dfa_exec()</a> +<li><a name="TOC8" href="#SEC8">MULTI-SEGMENT MATCHING WITH pcre_exec() OR pcre[16|32]_exec()</a> +<li><a name="TOC9" href="#SEC9">ISSUES WITH MULTI-SEGMENT MATCHING</a> +<li><a name="TOC10" href="#SEC10">AUTHOR</a> +<li><a name="TOC11" href="#SEC11">REVISION</a> +</ul> +<br><a name="SEC1" href="#TOC1">PARTIAL MATCHING IN PCRE</a><br> +<P> +In normal use of PCRE, if the subject string that is passed to a matching +function matches as far as it goes, but is too short to match the entire +pattern, PCRE_ERROR_NOMATCH is returned. There are circumstances where it might +be helpful to distinguish this case from other cases in which there is no +match. +</P> +<P> +Consider, for example, an application where a human is required to type in data +for a field with specific formatting requirements. An example might be a date +in the form <i>ddmmmyy</i>, defined by this pattern: +<pre> + ^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$ +</pre> +If the application sees the user's keystrokes one by one, and can check that +what has been typed so far is potentially valid, it is able to raise an error +as soon as a mistake is made, by beeping and not reflecting the character that +has been typed, for example. This immediate feedback is likely to be a better +user interface than a check that is delayed until the entire string has been +entered. Partial matching can also be useful when the subject string is very +long and is not all available at once. +</P> +<P> +PCRE supports partial matching by means of the PCRE_PARTIAL_SOFT and +PCRE_PARTIAL_HARD options, which can be set when calling any of the matching +functions. For backwards compatibility, PCRE_PARTIAL is a synonym for +PCRE_PARTIAL_SOFT. The essential difference between the two options is whether +or not a partial match is preferred to an alternative complete match, though +the details differ between the two types of matching function. If both options +are set, PCRE_PARTIAL_HARD takes precedence. +</P> +<P> +If you want to use partial matching with just-in-time optimized code, you must +call <b>pcre_study()</b>, <b>pcre16_study()</b> or <b>pcre32_study()</b> with one +or both of these options: +<pre> + PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE + PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE +</pre> +PCRE_STUDY_JIT_COMPILE should also be set if you are going to run non-partial +matches on the same pattern. If the appropriate JIT study mode has not been set +for a match, the interpretive matching code is used. +</P> +<P> +Setting a partial matching option disables two of PCRE's standard +optimizations. PCRE remembers the last literal data unit in a pattern, and +abandons matching immediately if it is not present in the subject string. This +optimization cannot be used for a subject string that might match only +partially. If the pattern was studied, PCRE knows the minimum length of a +matching string, and does not bother to run the matching function on shorter +strings. This optimization is also disabled for partial matching. +</P> +<br><a name="SEC2" href="#TOC1">PARTIAL MATCHING USING pcre_exec() OR pcre[16|32]_exec()</a><br> +<P> +A partial match occurs during a call to <b>pcre_exec()</b> or +<b>pcre[16|32]_exec()</b> when the end of the subject string is reached +successfully, but matching cannot continue because more characters are needed. +However, at least one character in the subject must have been inspected. This +character need not form part of the final matched string; lookbehind assertions +and the \K escape sequence provide ways of inspecting characters before the +start of a matched substring. The requirement for inspecting at least one +character exists because an empty string can always be matched; without such a +restriction there would always be a partial match of an empty string at the end +of the subject. +</P> +<P> +If there are at least two slots in the offsets vector when a partial match is +returned, the first slot is set to the offset of the earliest character that +was inspected. For convenience, the second offset points to the end of the +subject so that a substring can easily be identified. If there are at least +three slots in the offsets vector, the third slot is set to the offset of the +character where matching started. +</P> +<P> +For the majority of patterns, the contents of the first and third slots will be +the same. However, for patterns that contain lookbehind assertions, or begin +with \b or \B, characters before the one where matching started may have been +inspected while carrying out the match. For example, consider this pattern: +<pre> + /(?<=abc)123/ +</pre> +This pattern matches "123", but only if it is preceded by "abc". If the subject +string is "xyzabc12", the first two offsets after a partial match are for the +substring "abc12", because all these characters were inspected. However, the +third offset is set to 6, because that is the offset where matching began. +</P> +<P> +What happens when a partial match is identified depends on which of the two +partial matching options are set. +</P> +<br><b> +PCRE_PARTIAL_SOFT WITH pcre_exec() OR pcre[16|32]_exec() +</b><br> +<P> +If PCRE_PARTIAL_SOFT is set when <b>pcre_exec()</b> or <b>pcre[16|32]_exec()</b> +identifies a partial match, the partial match is remembered, but matching +continues as normal, and other alternatives in the pattern are tried. If no +complete match can be found, PCRE_ERROR_PARTIAL is returned instead of +PCRE_ERROR_NOMATCH. +</P> +<P> +This option is "soft" because it prefers a complete match over a partial match. +All the various matching items in a pattern behave as if the subject string is +potentially complete. For example, \z, \Z, and $ match at the end of the +subject, as normal, and for \b and \B the end of the subject is treated as a +non-alphanumeric. +</P> +<P> +If there is more than one partial match, the first one that was found provides +the data that is returned. Consider this pattern: +<pre> + /123\w+X|dogY/ +</pre> +If this is matched against the subject string "abc123dog", both +alternatives fail to match, but the end of the subject is reached during +matching, so PCRE_ERROR_PARTIAL is returned. The offsets are set to 3 and 9, +identifying "123dog" as the first partial match that was found. (In this +example, there are two partial matches, because "dog" on its own partially +matches the second alternative.) +</P> +<br><b> +PCRE_PARTIAL_HARD WITH pcre_exec() OR pcre[16|32]_exec() +</b><br> +<P> +If PCRE_PARTIAL_HARD is set for <b>pcre_exec()</b> or <b>pcre[16|32]_exec()</b>, +PCRE_ERROR_PARTIAL is returned as soon as a partial match is found, without +continuing to search for possible complete matches. This option is "hard" +because it prefers an earlier partial match over a later complete match. For +this reason, the assumption is made that the end of the supplied subject string +may not be the true end of the available data, and so, if \z, \Z, \b, \B, +or $ are encountered at the end of the subject, the result is +PCRE_ERROR_PARTIAL, provided that at least one character in the subject has +been inspected. +</P> +<P> +Setting PCRE_PARTIAL_HARD also affects the way UTF-8 and UTF-16 +subject strings are checked for validity. Normally, an invalid sequence +causes the error PCRE_ERROR_BADUTF8 or PCRE_ERROR_BADUTF16. However, in the +special case of a truncated character at the end of the subject, +PCRE_ERROR_SHORTUTF8 or PCRE_ERROR_SHORTUTF16 is returned when +PCRE_PARTIAL_HARD is set. +</P> +<br><b> +Comparing hard and soft partial matching +</b><br> +<P> +The difference between the two partial matching options can be illustrated by a +pattern such as: +<pre> + /dog(sbody)?/ +</pre> +This matches either "dog" or "dogsbody", greedily (that is, it prefers the +longer string if possible). If it is matched against the string "dog" with +PCRE_PARTIAL_SOFT, it yields a complete match for "dog". However, if +PCRE_PARTIAL_HARD is set, the result is PCRE_ERROR_PARTIAL. On the other hand, +if the pattern is made ungreedy the result is different: +<pre> + /dog(sbody)??/ +</pre> +In this case the result is always a complete match because that is found first, +and matching never continues after finding a complete match. It might be easier +to follow this explanation by thinking of the two patterns like this: +<pre> + /dog(sbody)?/ is the same as /dogsbody|dog/ + /dog(sbody)??/ is the same as /dog|dogsbody/ +</pre> +The second pattern will never match "dogsbody", because it will always find the +shorter match first. +</P> +<br><a name="SEC3" href="#TOC1">PARTIAL MATCHING USING pcre_dfa_exec() OR pcre[16|32]_dfa_exec()</a><br> +<P> +The DFA functions move along the subject string character by character, without +backtracking, searching for all possible matches simultaneously. If the end of +the subject is reached before the end of the pattern, there is the possibility +of a partial match, again provided that at least one character has been +inspected. +</P> +<P> +When PCRE_PARTIAL_SOFT is set, PCRE_ERROR_PARTIAL is returned only if there +have been no complete matches. Otherwise, the complete matches are returned. +However, if PCRE_PARTIAL_HARD is set, a partial match takes precedence over any +complete matches. The portion of the string that was inspected when the longest +partial match was found is set as the first matching string, provided there are +at least two slots in the offsets vector. +</P> +<P> +Because the DFA functions always search for all possible matches, and there is +no difference between greedy and ungreedy repetition, their behaviour is +different from the standard functions when PCRE_PARTIAL_HARD is set. Consider +the string "dog" matched against the ungreedy pattern shown above: +<pre> + /dog(sbody)??/ +</pre> +Whereas the standard functions stop as soon as they find the complete match for +"dog", the DFA functions also find the partial match for "dogsbody", and so +return that when PCRE_PARTIAL_HARD is set. +</P> +<br><a name="SEC4" href="#TOC1">PARTIAL MATCHING AND WORD BOUNDARIES</a><br> +<P> +If a pattern ends with one of sequences \b or \B, which test for word +boundaries, partial matching with PCRE_PARTIAL_SOFT can give counter-intuitive +results. Consider this pattern: +<pre> + /\bcat\b/ +</pre> +This matches "cat", provided there is a word boundary at either end. If the +subject string is "the cat", the comparison of the final "t" with a following +character cannot take place, so a partial match is found. However, normal +matching carries on, and \b matches at the end of the subject when the last +character is a letter, so a complete match is found. The result, therefore, is +<i>not</i> PCRE_ERROR_PARTIAL. Using PCRE_PARTIAL_HARD in this case does yield +PCRE_ERROR_PARTIAL, because then the partial match takes precedence. +</P> +<br><a name="SEC5" href="#TOC1">FORMERLY RESTRICTED PATTERNS</a><br> +<P> +For releases of PCRE prior to 8.00, because of the way certain internal +optimizations were implemented in the <b>pcre_exec()</b> function, the +PCRE_PARTIAL option (predecessor of PCRE_PARTIAL_SOFT) could not be used with +all patterns. From release 8.00 onwards, the restrictions no longer apply, and +partial matching with can be requested for any pattern. +</P> +<P> +Items that were formerly restricted were repeated single characters and +repeated metasequences. If PCRE_PARTIAL was set for a pattern that did not +conform to the restrictions, <b>pcre_exec()</b> returned the error code +PCRE_ERROR_BADPARTIAL (-13). This error code is no longer in use. The +PCRE_INFO_OKPARTIAL call to <b>pcre_fullinfo()</b> to find out if a compiled +pattern can be used for partial matching now always returns 1. +</P> +<br><a name="SEC6" href="#TOC1">EXAMPLE OF PARTIAL MATCHING USING PCRETEST</a><br> +<P> +If the escape sequence \P is present in a <b>pcretest</b> data line, the +PCRE_PARTIAL_SOFT option is used for the match. Here is a run of <b>pcretest</b> +that uses the date example quoted above: +<pre> + re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ + data> 25jun04\P + 0: 25jun04 + 1: jun + data> 25dec3\P + Partial match: 23dec3 + data> 3ju\P + Partial match: 3ju + data> 3juj\P + No match + data> j\P + No match +</pre> +The first data string is matched completely, so <b>pcretest</b> shows the +matched substrings. The remaining four strings do not match the complete +pattern, but the first two are partial matches. Similar output is obtained +if DFA matching is used. +</P> +<P> +If the escape sequence \P is present more than once in a <b>pcretest</b> data +line, the PCRE_PARTIAL_HARD option is set for the match. +</P> +<br><a name="SEC7" href="#TOC1">MULTI-SEGMENT MATCHING WITH pcre_dfa_exec() OR pcre[16|32]_dfa_exec()</a><br> +<P> +When a partial match has been found using a DFA matching function, it is +possible to continue the match by providing additional subject data and calling +the function again with the same compiled regular expression, this time setting +the PCRE_DFA_RESTART option. You must pass the same working space as before, +because this is where details of the previous partial match are stored. Here is +an example using <b>pcretest</b>, using the \R escape sequence to set the +PCRE_DFA_RESTART option (\D specifies the use of the DFA matching function): +<pre> + re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ + data> 23ja\P\D + Partial match: 23ja + data> n05\R\D + 0: n05 +</pre> +The first call has "23ja" as the subject, and requests partial matching; the +second call has "n05" as the subject for the continued (restarted) match. +Notice that when the match is complete, only the last part is shown; PCRE does +not retain the previously partially-matched string. It is up to the calling +program to do that if it needs to. +</P> +<P> +That means that, for an unanchored pattern, if a continued match fails, it is +not possible to try again at a new starting point. All this facility is capable +of doing is continuing with the previous match attempt. In the previous +example, if the second set of data is "ug23" the result is no match, even +though there would be a match for "aug23" if the entire string were given at +once. Depending on the application, this may or may not be what you want. +The only way to allow for starting again at the next character is to retain the +matched part of the subject and try a new complete match. +</P> +<P> +You can set the PCRE_PARTIAL_SOFT or PCRE_PARTIAL_HARD options with +PCRE_DFA_RESTART to continue partial matching over multiple segments. This +facility can be used to pass very long subject strings to the DFA matching +functions. +</P> +<br><a name="SEC8" href="#TOC1">MULTI-SEGMENT MATCHING WITH pcre_exec() OR pcre[16|32]_exec()</a><br> +<P> +From release 8.00, the standard matching functions can also be used to do +multi-segment matching. Unlike the DFA functions, it is not possible to +restart the previous match with a new segment of data. Instead, new data must +be added to the previous subject string, and the entire match re-run, starting +from the point where the partial match occurred. Earlier data can be discarded. +</P> +<P> +It is best to use PCRE_PARTIAL_HARD in this situation, because it does not +treat the end of a segment as the end of the subject when matching \z, \Z, +\b, \B, and $. Consider an unanchored pattern that matches dates: +<pre> + re> /\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d/ + data> The date is 23ja\P\P + Partial match: 23ja +</pre> +At this stage, an application could discard the text preceding "23ja", add on +text from the next segment, and call the matching function again. Unlike the +DFA matching functions, the entire matching string must always be available, +and the complete matching process occurs for each call, so more memory and more +processing time is needed. +</P> +<P> +<b>Note:</b> If the pattern contains lookbehind assertions, or \K, or starts +with \b or \B, the string that is returned for a partial match includes +characters that precede the start of what would be returned for a complete +match, because it contains all the characters that were inspected during the +partial match. +</P> +<br><a name="SEC9" href="#TOC1">ISSUES WITH MULTI-SEGMENT MATCHING</a><br> +<P> +Certain types of pattern may give problems with multi-segment matching, +whichever matching function is used. +</P> +<P> +1. If the pattern contains a test for the beginning of a line, you need to pass +the PCRE_NOTBOL option when the subject string for any call does start at the +beginning of a line. There is also a PCRE_NOTEOL option, but in practice when +doing multi-segment matching you should be using PCRE_PARTIAL_HARD, which +includes the effect of PCRE_NOTEOL. +</P> +<P> +2. Lookbehind assertions that have already been obeyed are catered for in the +offsets that are returned for a partial match. However a lookbehind assertion +later in the pattern could require even earlier characters to be inspected. You +can handle this case by using the PCRE_INFO_MAXLOOKBEHIND option of the +<b>pcre_fullinfo()</b> or <b>pcre[16|32]_fullinfo()</b> functions to obtain the +length of the longest lookbehind in the pattern. This length is given in +characters, not bytes. If you always retain at least that many characters +before the partially matched string, all should be well. (Of course, near the +start of the subject, fewer characters may be present; in that case all +characters should be retained.) +</P> +<P> +From release 8.33, there is a more accurate way of deciding which characters to +retain. Instead of subtracting the length of the longest lookbehind from the +earliest inspected character (<i>offsets[0]</i>), the match start position +(<i>offsets[2]</i>) should be used, and the next match attempt started at the +<i>offsets[2]</i> character by setting the <i>startoffset</i> argument of +<b>pcre_exec()</b> or <b>pcre_dfa_exec()</b>. +</P> +<P> +For example, if the pattern "(?<=123)abc" is partially +matched against the string "xx123a", the three offset values returned are 2, 6, +and 5. This indicates that the matching process that gave a partial match +started at offset 5, but the characters "123a" were all inspected. The maximum +lookbehind for that pattern is 3, so taking that away from 5 shows that we need +only keep "123a", and the next match attempt can be started at offset 3 (that +is, at "a") when further characters have been added. When the match start is +not the earliest inspected character, <b>pcretest</b> shows it explicitly: +<pre> + re> "(?<=123)abc" + data> xx123a\P\P + Partial match at offset 5: 123a +</PRE> +</P> +<P> +3. Because a partial match must always contain at least one character, what +might be considered a partial match of an empty string actually gives a "no +match" result. For example: +<pre> + re> /c(?<=abc)x/ + data> ab\P + No match +</pre> +If the next segment begins "cx", a match should be found, but this will only +happen if characters from the previous segment are retained. For this reason, a +"no match" result should be interpreted as "partial match of an empty string" +when the pattern contains lookbehinds. +</P> +<P> +4. Matching a subject string that is split into multiple segments may not +always produce exactly the same result as matching over one single long string, +especially when PCRE_PARTIAL_SOFT is used. The section "Partial Matching and +Word Boundaries" above describes an issue that arises if the pattern ends with +\b or \B. Another kind of difference may occur when there are multiple +matching possibilities, because (for PCRE_PARTIAL_SOFT) a partial match result +is given only when there are no completed matches. This means that as soon as +the shortest match has been found, continuation to a new subject segment is no +longer possible. Consider again this <b>pcretest</b> example: +<pre> + re> /dog(sbody)?/ + data> dogsb\P + 0: dog + data> do\P\D + Partial match: do + data> gsb\R\P\D + 0: g + data> dogsbody\D + 0: dogsbody + 1: dog +</pre> +The first data line passes the string "dogsb" to a standard matching function, +setting the PCRE_PARTIAL_SOFT option. Although the string is a partial match +for "dogsbody", the result is not PCRE_ERROR_PARTIAL, because the shorter +string "dog" is a complete match. Similarly, when the subject is presented to +a DFA matching function in several parts ("do" and "gsb" being the first two) +the match stops when "dog" has been found, and it is not possible to continue. +On the other hand, if "dogsbody" is presented as a single string, a DFA +matching function finds both matches. +</P> +<P> +Because of these problems, it is best to use PCRE_PARTIAL_HARD when matching +multi-segment data. The example above then behaves differently: +<pre> + re> /dog(sbody)?/ + data> dogsb\P\P + Partial match: dogsb + data> do\P\D + Partial match: do + data> gsb\R\P\P\D + Partial match: gsb +</pre> +5. Patterns that contain alternatives at the top level which do not all start +with the same pattern item may not work as expected when PCRE_DFA_RESTART is +used. For example, consider this pattern: +<pre> + 1234|3789 +</pre> +If the first part of the subject is "ABC123", a partial match of the first +alternative is found at offset 3. There is no partial match for the second +alternative, because such a match does not start at the same point in the +subject string. Attempting to continue with the string "7890" does not yield a +match because only those alternatives that match at one point in the subject +are remembered. The problem arises because the start of the second alternative +matches within the first alternative. There is no problem with anchored +patterns or patterns such as: +<pre> + 1234|ABCD +</pre> +where no string can be a partial match for both alternatives. This is not a +problem if a standard matching function is used, because the entire match has +to be rerun each time: +<pre> + re> /1234|3789/ + data> ABC123\P\P + Partial match: 123 + data> 1237890 + 0: 3789 +</pre> +Of course, instead of using PCRE_DFA_RESTART, the same technique of re-running +the entire match can also be used with the DFA matching functions. Another +possibility is to work with two buffers. If a partial match at offset <i>n</i> +in the first buffer is followed by "no match" when PCRE_DFA_RESTART is used on +the second buffer, you can then try a new match starting at offset <i>n+1</i> in +the first buffer. +</P> +<br><a name="SEC10" href="#TOC1">AUTHOR</a><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><a name="SEC11" href="#TOC1">REVISION</a><br> +<P> +Last updated: 02 July 2013 +<br> +Copyright © 1997-2013 University of Cambridge. +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcrepattern.html b/plugins/Pcre16/docs/doc/html/pcrepattern.html new file mode 100644 index 0000000000..c06d1e03f1 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcrepattern.html @@ -0,0 +1,3235 @@ +<html> +<head> +<title>pcrepattern specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcrepattern man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<ul> +<li><a name="TOC1" href="#SEC1">PCRE REGULAR EXPRESSION DETAILS</a> +<li><a name="TOC2" href="#SEC2">SPECIAL START-OF-PATTERN ITEMS</a> +<li><a name="TOC3" href="#SEC3">EBCDIC CHARACTER CODES</a> +<li><a name="TOC4" href="#SEC4">CHARACTERS AND METACHARACTERS</a> +<li><a name="TOC5" href="#SEC5">BACKSLASH</a> +<li><a name="TOC6" href="#SEC6">CIRCUMFLEX AND DOLLAR</a> +<li><a name="TOC7" href="#SEC7">FULL STOP (PERIOD, DOT) AND \N</a> +<li><a name="TOC8" href="#SEC8">MATCHING A SINGLE DATA UNIT</a> +<li><a name="TOC9" href="#SEC9">SQUARE BRACKETS AND CHARACTER CLASSES</a> +<li><a name="TOC10" href="#SEC10">POSIX CHARACTER CLASSES</a> +<li><a name="TOC11" href="#SEC11">COMPATIBILITY FEATURE FOR WORD BOUNDARIES</a> +<li><a name="TOC12" href="#SEC12">VERTICAL BAR</a> +<li><a name="TOC13" href="#SEC13">INTERNAL OPTION SETTING</a> +<li><a name="TOC14" href="#SEC14">SUBPATTERNS</a> +<li><a name="TOC15" href="#SEC15">DUPLICATE SUBPATTERN NUMBERS</a> +<li><a name="TOC16" href="#SEC16">NAMED SUBPATTERNS</a> +<li><a name="TOC17" href="#SEC17">REPETITION</a> +<li><a name="TOC18" href="#SEC18">ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS</a> +<li><a name="TOC19" href="#SEC19">BACK REFERENCES</a> +<li><a name="TOC20" href="#SEC20">ASSERTIONS</a> +<li><a name="TOC21" href="#SEC21">CONDITIONAL SUBPATTERNS</a> +<li><a name="TOC22" href="#SEC22">COMMENTS</a> +<li><a name="TOC23" href="#SEC23">RECURSIVE PATTERNS</a> +<li><a name="TOC24" href="#SEC24">SUBPATTERNS AS SUBROUTINES</a> +<li><a name="TOC25" href="#SEC25">ONIGURUMA SUBROUTINE SYNTAX</a> +<li><a name="TOC26" href="#SEC26">CALLOUTS</a> +<li><a name="TOC27" href="#SEC27">BACKTRACKING CONTROL</a> +<li><a name="TOC28" href="#SEC28">SEE ALSO</a> +<li><a name="TOC29" href="#SEC29">AUTHOR</a> +<li><a name="TOC30" href="#SEC30">REVISION</a> +</ul> +<br><a name="SEC1" href="#TOC1">PCRE REGULAR EXPRESSION DETAILS</a><br> +<P> +The syntax and semantics of the regular expressions that are supported by PCRE +are described in detail below. There is a quick-reference syntax summary in the +<a href="pcresyntax.html"><b>pcresyntax</b></a> +page. PCRE tries to match Perl syntax and semantics as closely as it can. PCRE +also supports some alternative regular expression syntax (which does not +conflict with the Perl syntax) in order to provide some compatibility with +regular expressions in Python, .NET, and Oniguruma. +</P> +<P> +Perl's regular expressions are described in its own documentation, and +regular expressions in general are covered in a number of books, some of which +have copious examples. Jeffrey Friedl's "Mastering Regular Expressions", +published by O'Reilly, covers regular expressions in great detail. This +description of PCRE's regular expressions is intended as reference material. +</P> +<P> +This document discusses the patterns that are supported by PCRE when one its +main matching functions, <b>pcre_exec()</b> (8-bit) or <b>pcre[16|32]_exec()</b> +(16- or 32-bit), is used. PCRE also has alternative matching functions, +<b>pcre_dfa_exec()</b> and <b>pcre[16|32_dfa_exec()</b>, which match using a +different algorithm that is not Perl-compatible. Some of the features discussed +below are not available when DFA matching is used. The advantages and +disadvantages of the alternative functions, and how they differ from the normal +functions, are discussed in the +<a href="pcrematching.html"><b>pcrematching</b></a> +page. +</P> +<br><a name="SEC2" href="#TOC1">SPECIAL START-OF-PATTERN ITEMS</a><br> +<P> +A number of options that can be passed to <b>pcre_compile()</b> can also be set +by special items at the start of a pattern. These are not Perl-compatible, but +are provided to make these options accessible to pattern writers who are not +able to change the program that processes the pattern. Any number of these +items may appear, but they must all be together right at the start of the +pattern string, and the letters must be in upper case. +</P> +<br><b> +UTF support +</b><br> +<P> +The original operation of PCRE was on strings of one-byte characters. However, +there is now also support for UTF-8 strings in the original library, an +extra library that supports 16-bit and UTF-16 character strings, and a +third library that supports 32-bit and UTF-32 character strings. To use these +features, PCRE must be built to include appropriate support. When using UTF +strings you must either call the compiling function with the PCRE_UTF8, +PCRE_UTF16, or PCRE_UTF32 option, or the pattern must start with one of +these special sequences: +<pre> + (*UTF8) + (*UTF16) + (*UTF32) + (*UTF) +</pre> +(*UTF) is a generic sequence that can be used with any of the libraries. +Starting a pattern with such a sequence is equivalent to setting the relevant +option. How setting a UTF mode affects pattern matching is mentioned in several +places below. There is also a summary of features in the +<a href="pcreunicode.html"><b>pcreunicode</b></a> +page. +</P> +<P> +Some applications that allow their users to supply patterns may wish to +restrict them to non-UTF data for security reasons. If the PCRE_NEVER_UTF +option is set at compile time, (*UTF) etc. are not allowed, and their +appearance causes an error. +</P> +<br><b> +Unicode property support +</b><br> +<P> +Another special sequence that may appear at the start of a pattern is (*UCP). +This has the same effect as setting the PCRE_UCP option: it causes sequences +such as \d and \w to use Unicode properties to determine character types, +instead of recognizing only characters with codes less than 128 via a lookup +table. +</P> +<br><b> +Disabling auto-possessification +</b><br> +<P> +If a pattern starts with (*NO_AUTO_POSSESS), it has the same effect as setting +the PCRE_NO_AUTO_POSSESS option at compile time. This stops PCRE from making +quantifiers possessive when what follows cannot match the repeated item. For +example, by default a+b is treated as a++b. For more details, see the +<a href="pcreapi.html"><b>pcreapi</b></a> +documentation. +</P> +<br><b> +Disabling start-up optimizations +</b><br> +<P> +If a pattern starts with (*NO_START_OPT), it has the same effect as setting the +PCRE_NO_START_OPTIMIZE option either at compile or matching time. This disables +several optimizations for quickly reaching "no match" results. For more +details, see the +<a href="pcreapi.html"><b>pcreapi</b></a> +documentation. +<a name="newlines"></a></P> +<br><b> +Newline conventions +</b><br> +<P> +PCRE supports five different conventions for indicating line breaks in +strings: a single CR (carriage return) character, a single LF (linefeed) +character, the two-character sequence CRLF, any of the three preceding, or any +Unicode newline sequence. The +<a href="pcreapi.html"><b>pcreapi</b></a> +page has +<a href="pcreapi.html#newlines">further discussion</a> +about newlines, and shows how to set the newline convention in the +<i>options</i> arguments for the compiling and matching functions. +</P> +<P> +It is also possible to specify a newline convention by starting a pattern +string with one of the following five sequences: +<pre> + (*CR) carriage return + (*LF) linefeed + (*CRLF) carriage return, followed by linefeed + (*ANYCRLF) any of the three above + (*ANY) all Unicode newline sequences +</pre> +These override the default and the options given to the compiling function. For +example, on a Unix system where LF is the default newline sequence, the pattern +<pre> + (*CR)a.b +</pre> +changes the convention to CR. That pattern matches "a\nb" because LF is no +longer a newline. If more than one of these settings is present, the last one +is used. +</P> +<P> +The newline convention affects where the circumflex and dollar assertions are +true. It also affects the interpretation of the dot metacharacter when +PCRE_DOTALL is not set, and the behaviour of \N. However, it does not affect +what the \R escape sequence matches. By default, this is any Unicode newline +sequence, for Perl compatibility. However, this can be changed; see the +description of \R in the section entitled +<a href="#newlineseq">"Newline sequences"</a> +below. A change of \R setting can be combined with a change of newline +convention. +</P> +<br><b> +Setting match and recursion limits +</b><br> +<P> +The caller of <b>pcre_exec()</b> can set a limit on the number of times the +internal <b>match()</b> function is called and on the maximum depth of +recursive calls. These facilities are provided to catch runaway matches that +are provoked by patterns with huge matching trees (a typical example is a +pattern with nested unlimited repeats) and to avoid running out of system stack +by too much recursion. When one of these limits is reached, <b>pcre_exec()</b> +gives an error return. The limits can also be set by items at the start of the +pattern of the form +<pre> + (*LIMIT_MATCH=d) + (*LIMIT_RECURSION=d) +</pre> +where d is any number of decimal digits. However, the value of the setting must +be less than the value set (or defaulted) by the caller of <b>pcre_exec()</b> +for it to have any effect. In other words, the pattern writer can lower the +limits set by the programmer, but not raise them. If there is more than one +setting of one of these limits, the lower value is used. +</P> +<br><a name="SEC3" href="#TOC1">EBCDIC CHARACTER CODES</a><br> +<P> +PCRE can be compiled to run in an environment that uses EBCDIC as its character +code rather than ASCII or Unicode (typically a mainframe system). In the +sections below, character code values are ASCII or Unicode; in an EBCDIC +environment these characters may have different code values, and there are no +code points greater than 255. +</P> +<br><a name="SEC4" href="#TOC1">CHARACTERS AND METACHARACTERS</a><br> +<P> +A regular expression is a pattern that is matched against a subject string from +left to right. Most characters stand for themselves in a pattern, and match the +corresponding characters in the subject. As a trivial example, the pattern +<pre> + The quick brown fox +</pre> +matches a portion of a subject string that is identical to itself. When +caseless matching is specified (the PCRE_CASELESS option), letters are matched +independently of case. In a UTF mode, PCRE always understands the concept of +case for characters whose values are less than 128, so caseless matching is +always possible. For characters with higher values, the concept of case is +supported if PCRE is compiled with Unicode property support, but not otherwise. +If you want to use caseless matching for characters 128 and above, you must +ensure that PCRE is compiled with Unicode property support as well as with +UTF support. +</P> +<P> +The power of regular expressions comes from the ability to include alternatives +and repetitions in the pattern. These are encoded in the pattern by the use of +<i>metacharacters</i>, which do not stand for themselves but instead are +interpreted in some special way. +</P> +<P> +There are two different sets of metacharacters: those that are recognized +anywhere in the pattern except within square brackets, and those that are +recognized within square brackets. Outside square brackets, the metacharacters +are as follows: +<pre> + \ general escape character with several uses + ^ assert start of string (or line, in multiline mode) + $ assert end of string (or line, in multiline mode) + . match any character except newline (by default) + [ start character class definition + | start of alternative branch + ( start subpattern + ) end subpattern + ? extends the meaning of ( + also 0 or 1 quantifier + also quantifier minimizer + * 0 or more quantifier + + 1 or more quantifier + also "possessive quantifier" + { start min/max quantifier +</pre> +Part of a pattern that is in square brackets is called a "character class". In +a character class the only metacharacters are: +<pre> + \ general escape character + ^ negate the class, but only if the first character + - indicates character range + [ POSIX character class (only if followed by POSIX syntax) + ] terminates the character class +</pre> +The following sections describe the use of each of the metacharacters. +</P> +<br><a name="SEC5" href="#TOC1">BACKSLASH</a><br> +<P> +The backslash character has several uses. Firstly, if it is followed by a +character that is not a number or a letter, it takes away any special meaning +that character may have. This use of backslash as an escape character applies +both inside and outside character classes. +</P> +<P> +For example, if you want to match a * character, you write \* in the pattern. +This escaping action applies whether or not the following character would +otherwise be interpreted as a metacharacter, so it is always safe to precede a +non-alphanumeric with backslash to specify that it stands for itself. In +particular, if you want to match a backslash, you write \\. +</P> +<P> +In a UTF mode, only ASCII numbers and letters have any special meaning after a +backslash. All other characters (in particular, those whose codepoints are +greater than 127) are treated as literals. +</P> +<P> +If a pattern is compiled with the PCRE_EXTENDED option, most white space in the +pattern (other than in a character class), and characters between a # outside a +character class and the next newline, inclusive, are ignored. An escaping +backslash can be used to include a white space or # character as part of the +pattern. +</P> +<P> +If you want to remove the special meaning from a sequence of characters, you +can do so by putting them between \Q and \E. This is different from Perl in +that $ and @ are handled as literals in \Q...\E sequences in PCRE, whereas in +Perl, $ and @ cause variable interpolation. Note the following examples: +<pre> + Pattern PCRE matches Perl matches + + \Qabc$xyz\E abc$xyz abc followed by the contents of $xyz + \Qabc\$xyz\E abc\$xyz abc\$xyz + \Qabc\E\$\Qxyz\E abc$xyz abc$xyz +</pre> +The \Q...\E sequence is recognized both inside and outside character classes. +An isolated \E that is not preceded by \Q is ignored. If \Q is not followed +by \E later in the pattern, the literal interpretation continues to the end of +the pattern (that is, \E is assumed at the end). If the isolated \Q is inside +a character class, this causes an error, because the character class is not +terminated. +<a name="digitsafterbackslash"></a></P> +<br><b> +Non-printing characters +</b><br> +<P> +A second use of backslash provides a way of encoding non-printing characters +in patterns in a visible manner. There is no restriction on the appearance of +non-printing characters, apart from the binary zero that terminates a pattern, +but when a pattern is being prepared by text editing, it is often easier to use +one of the following escape sequences than the binary character it represents: +<pre> + \a alarm, that is, the BEL character (hex 07) + \cx "control-x", where x is any ASCII character + \e escape (hex 1B) + \f form feed (hex 0C) + \n linefeed (hex 0A) + \r carriage return (hex 0D) + \t tab (hex 09) + \0dd character with octal code 0dd + \ddd character with octal code ddd, or back reference + \o{ddd..} character with octal code ddd.. + \xhh character with hex code hh + \x{hhh..} character with hex code hhh.. (non-JavaScript mode) + \uhhhh character with hex code hhhh (JavaScript mode only) +</pre> +The precise effect of \cx on ASCII characters is as follows: if x is a lower +case letter, it is converted to upper case. Then bit 6 of the character (hex +40) is inverted. Thus \cA to \cZ become hex 01 to hex 1A (A is 41, Z is 5A), +but \c{ becomes hex 3B ({ is 7B), and \c; becomes hex 7B (; is 3B). If the +data item (byte or 16-bit value) following \c has a value greater than 127, a +compile-time error occurs. This locks out non-ASCII characters in all modes. +</P> +<P> +The \c facility was designed for use with ASCII characters, but with the +extension to Unicode it is even less useful than it once was. It is, however, +recognized when PCRE is compiled in EBCDIC mode, where data items are always +bytes. In this mode, all values are valid after \c. If the next character is a +lower case letter, it is converted to upper case. Then the 0xc0 bits of the +byte are inverted. Thus \cA becomes hex 01, as in ASCII (A is C1), but because +the EBCDIC letters are disjoint, \cZ becomes hex 29 (Z is E9), and other +characters also generate different values. +</P> +<P> +After \0 up to two further octal digits are read. If there are fewer than two +digits, just those that are present are used. Thus the sequence \0\x\07 +specifies two binary zeros followed by a BEL character (code value 7). Make +sure you supply two digits after the initial zero if the pattern character that +follows is itself an octal digit. +</P> +<P> +The escape \o must be followed by a sequence of octal digits, enclosed in +braces. An error occurs if this is not the case. This escape is a recent +addition to Perl; it provides way of specifying character code points as octal +numbers greater than 0777, and it also allows octal numbers and back references +to be unambiguously specified. +</P> +<P> +For greater clarity and unambiguity, it is best to avoid following \ by a +digit greater than zero. Instead, use \o{} or \x{} to specify character +numbers, and \g{} to specify back references. The following paragraphs +describe the old, ambiguous syntax. +</P> +<P> +The handling of a backslash followed by a digit other than 0 is complicated, +and Perl has changed in recent releases, causing PCRE also to change. Outside a +character class, PCRE reads the digit and any following digits as a decimal +number. If the number is less than 8, or if there have been at least that many +previous capturing left parentheses in the expression, the entire sequence is +taken as a <i>back reference</i>. A description of how this works is given +<a href="#backreferences">later,</a> +following the discussion of +<a href="#subpattern">parenthesized subpatterns.</a> +</P> +<P> +Inside a character class, or if the decimal number following \ is greater than +7 and there have not been that many capturing subpatterns, PCRE handles \8 and +\9 as the literal characters "8" and "9", and otherwise re-reads up to three +octal digits following the backslash, using them to generate a data character. +Any subsequent digits stand for themselves. For example: +<pre> + \040 is another way of writing an ASCII space + \40 is the same, provided there are fewer than 40 previous capturing subpatterns + \7 is always a back reference + \11 might be a back reference, or another way of writing a tab + \011 is always a tab + \0113 is a tab followed by the character "3" + \113 might be a back reference, otherwise the character with octal code 113 + \377 might be a back reference, otherwise the value 255 (decimal) + \81 is either a back reference, or the two characters "8" and "1" +</pre> +Note that octal values of 100 or greater that are specified using this syntax +must not be introduced by a leading zero, because no more than three octal +digits are ever read. +</P> +<P> +By default, after \x that is not followed by {, from zero to two hexadecimal +digits are read (letters can be in upper or lower case). Any number of +hexadecimal digits may appear between \x{ and }. If a character other than +a hexadecimal digit appears between \x{ and }, or if there is no terminating +}, an error occurs. +</P> +<P> +If the PCRE_JAVASCRIPT_COMPAT option is set, the interpretation of \x is +as just described only when it is followed by two hexadecimal digits. +Otherwise, it matches a literal "x" character. In JavaScript mode, support for +code points greater than 256 is provided by \u, which must be followed by +four hexadecimal digits; otherwise it matches a literal "u" character. +</P> +<P> +Characters whose value is less than 256 can be defined by either of the two +syntaxes for \x (or by \u in JavaScript mode). There is no difference in the +way they are handled. For example, \xdc is exactly the same as \x{dc} (or +\u00dc in JavaScript mode). +</P> +<br><b> +Constraints on character values +</b><br> +<P> +Characters that are specified using octal or hexadecimal numbers are +limited to certain values, as follows: +<pre> + 8-bit non-UTF mode less than 0x100 + 8-bit UTF-8 mode less than 0x10ffff and a valid codepoint + 16-bit non-UTF mode less than 0x10000 + 16-bit UTF-16 mode less than 0x10ffff and a valid codepoint + 32-bit non-UTF mode less than 0x100000000 + 32-bit UTF-32 mode less than 0x10ffff and a valid codepoint +</pre> +Invalid Unicode codepoints are the range 0xd800 to 0xdfff (the so-called +"surrogate" codepoints), and 0xffef. +</P> +<br><b> +Escape sequences in character classes +</b><br> +<P> +All the sequences that define a single character value can be used both inside +and outside character classes. In addition, inside a character class, \b is +interpreted as the backspace character (hex 08). +</P> +<P> +\N is not allowed in a character class. \B, \R, and \X are not special +inside a character class. Like other unrecognized escape sequences, they are +treated as the literal characters "B", "R", and "X" by default, but cause an +error if the PCRE_EXTRA option is set. Outside a character class, these +sequences have different meanings. +</P> +<br><b> +Unsupported escape sequences +</b><br> +<P> +In Perl, the sequences \l, \L, \u, and \U are recognized by its string +handler and used to modify the case of following characters. By default, PCRE +does not support these escape sequences. However, if the PCRE_JAVASCRIPT_COMPAT +option is set, \U matches a "U" character, and \u can be used to define a +character by code point, as described in the previous section. +</P> +<br><b> +Absolute and relative back references +</b><br> +<P> +The sequence \g followed by an unsigned or a negative number, optionally +enclosed in braces, is an absolute or relative back reference. A named back +reference can be coded as \g{name}. Back references are discussed +<a href="#backreferences">later,</a> +following the discussion of +<a href="#subpattern">parenthesized subpatterns.</a> +</P> +<br><b> +Absolute and relative subroutine calls +</b><br> +<P> +For compatibility with Oniguruma, the non-Perl syntax \g followed by a name or +a number enclosed either in angle brackets or single quotes, is an alternative +syntax for referencing a subpattern as a "subroutine". Details are discussed +<a href="#onigurumasubroutines">later.</a> +Note that \g{...} (Perl syntax) and \g<...> (Oniguruma syntax) are <i>not</i> +synonymous. The former is a back reference; the latter is a +<a href="#subpatternsassubroutines">subroutine</a> +call. +<a name="genericchartypes"></a></P> +<br><b> +Generic character types +</b><br> +<P> +Another use of backslash is for specifying generic character types: +<pre> + \d any decimal digit + \D any character that is not a decimal digit + \h any horizontal white space character + \H any character that is not a horizontal white space character + \s any white space character + \S any character that is not a white space character + \v any vertical white space character + \V any character that is not a vertical white space character + \w any "word" character + \W any "non-word" character +</pre> +There is also the single sequence \N, which matches a non-newline character. +This is the same as +<a href="#fullstopdot">the "." metacharacter</a> +when PCRE_DOTALL is not set. Perl also uses \N to match characters by name; +PCRE does not support this. +</P> +<P> +Each pair of lower and upper case escape sequences partitions the complete set +of characters into two disjoint sets. Any given character matches one, and only +one, of each pair. The sequences can appear both inside and outside character +classes. They each match one character of the appropriate type. If the current +matching point is at the end of the subject string, all of them fail, because +there is no character to match. +</P> +<P> +For compatibility with Perl, \s did not used to match the VT character (code +11), which made it different from the the POSIX "space" class. However, Perl +added VT at release 5.18, and PCRE followed suit at release 8.34. The default +\s characters are now HT (9), LF (10), VT (11), FF (12), CR (13), and space +(32), which are defined as white space in the "C" locale. This list may vary if +locale-specific matching is taking place. For example, in some locales the +"non-breaking space" character (\xA0) is recognized as white space, and in +others the VT character is not. +</P> +<P> +A "word" character is an underscore or any character that is a letter or digit. +By default, the definition of letters and digits is controlled by PCRE's +low-valued character tables, and may vary if locale-specific matching is taking +place (see +<a href="pcreapi.html#localesupport">"Locale support"</a> +in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page). For example, in a French locale such as "fr_FR" in Unix-like systems, +or "french" in Windows, some character codes greater than 127 are used for +accented letters, and these are then matched by \w. The use of locales with +Unicode is discouraged. +</P> +<P> +By default, characters whose code points are greater than 127 never match \d, +\s, or \w, and always match \D, \S, and \W, although this may vary for +characters in the range 128-255 when locale-specific matching is happening. +These escape sequences retain their original meanings from before Unicode +support was available, mainly for efficiency reasons. If PCRE is compiled with +Unicode property support, and the PCRE_UCP option is set, the behaviour is +changed so that Unicode properties are used to determine character types, as +follows: +<pre> + \d any character that matches \p{Nd} (decimal digit) + \s any character that matches \p{Z} or \h or \v + \w any character that matches \p{L} or \p{N}, plus underscore +</pre> +The upper case escapes match the inverse sets of characters. Note that \d +matches only decimal digits, whereas \w matches any Unicode digit, as well as +any Unicode letter, and underscore. Note also that PCRE_UCP affects \b, and +\B because they are defined in terms of \w and \W. Matching these sequences +is noticeably slower when PCRE_UCP is set. +</P> +<P> +The sequences \h, \H, \v, and \V are features that were added to Perl at +release 5.10. In contrast to the other sequences, which match only ASCII +characters by default, these always match certain high-valued code points, +whether or not PCRE_UCP is set. The horizontal space characters are: +<pre> + U+0009 Horizontal tab (HT) + U+0020 Space + U+00A0 Non-break space + U+1680 Ogham space mark + U+180E Mongolian vowel separator + U+2000 En quad + U+2001 Em quad + U+2002 En space + U+2003 Em space + U+2004 Three-per-em space + U+2005 Four-per-em space + U+2006 Six-per-em space + U+2007 Figure space + U+2008 Punctuation space + U+2009 Thin space + U+200A Hair space + U+202F Narrow no-break space + U+205F Medium mathematical space + U+3000 Ideographic space +</pre> +The vertical space characters are: +<pre> + U+000A Linefeed (LF) + U+000B Vertical tab (VT) + U+000C Form feed (FF) + U+000D Carriage return (CR) + U+0085 Next line (NEL) + U+2028 Line separator + U+2029 Paragraph separator +</pre> +In 8-bit, non-UTF-8 mode, only the characters with codepoints less than 256 are +relevant. +<a name="newlineseq"></a></P> +<br><b> +Newline sequences +</b><br> +<P> +Outside a character class, by default, the escape sequence \R matches any +Unicode newline sequence. In 8-bit non-UTF-8 mode \R is equivalent to the +following: +<pre> + (?>\r\n|\n|\x0b|\f|\r|\x85) +</pre> +This is an example of an "atomic group", details of which are given +<a href="#atomicgroup">below.</a> +This particular group matches either the two-character sequence CR followed by +LF, or one of the single characters LF (linefeed, U+000A), VT (vertical tab, +U+000B), FF (form feed, U+000C), CR (carriage return, U+000D), or NEL (next +line, U+0085). The two-character sequence is treated as a single unit that +cannot be split. +</P> +<P> +In other modes, two additional characters whose codepoints are greater than 255 +are added: LS (line separator, U+2028) and PS (paragraph separator, U+2029). +Unicode character property support is not needed for these characters to be +recognized. +</P> +<P> +It is possible to restrict \R to match only CR, LF, or CRLF (instead of the +complete set of Unicode line endings) by setting the option PCRE_BSR_ANYCRLF +either at compile time or when the pattern is matched. (BSR is an abbrevation +for "backslash R".) This can be made the default when PCRE is built; if this is +the case, the other behaviour can be requested via the PCRE_BSR_UNICODE option. +It is also possible to specify these settings by starting a pattern string with +one of the following sequences: +<pre> + (*BSR_ANYCRLF) CR, LF, or CRLF only + (*BSR_UNICODE) any Unicode newline sequence +</pre> +These override the default and the options given to the compiling function, but +they can themselves be overridden by options given to a matching function. Note +that these special settings, which are not Perl-compatible, are recognized only +at the very start of a pattern, and that they must be in upper case. If more +than one of them is present, the last one is used. They can be combined with a +change of newline convention; for example, a pattern can start with: +<pre> + (*ANY)(*BSR_ANYCRLF) +</pre> +They can also be combined with the (*UTF8), (*UTF16), (*UTF32), (*UTF) or +(*UCP) special sequences. Inside a character class, \R is treated as an +unrecognized escape sequence, and so matches the letter "R" by default, but +causes an error if PCRE_EXTRA is set. +<a name="uniextseq"></a></P> +<br><b> +Unicode character properties +</b><br> +<P> +When PCRE is built with Unicode character property support, three additional +escape sequences that match characters with specific properties are available. +When in 8-bit non-UTF-8 mode, these sequences are of course limited to testing +characters whose codepoints are less than 256, but they do work in this mode. +The extra escape sequences are: +<pre> + \p{<i>xx</i>} a character with the <i>xx</i> property + \P{<i>xx</i>} a character without the <i>xx</i> property + \X a Unicode extended grapheme cluster +</pre> +The property names represented by <i>xx</i> above are limited to the Unicode +script names, the general category properties, "Any", which matches any +character (including newline), and some special PCRE properties (described +in the +<a href="#extraprops">next section).</a> +Other Perl properties such as "InMusicalSymbols" are not currently supported by +PCRE. Note that \P{Any} does not match any characters, so always causes a +match failure. +</P> +<P> +Sets of Unicode characters are defined as belonging to certain scripts. A +character from one of these sets can be matched using a script name. For +example: +<pre> + \p{Greek} + \P{Han} +</pre> +Those that are not part of an identified script are lumped together as +"Common". The current list of scripts is: +</P> +<P> +Arabic, +Armenian, +Avestan, +Balinese, +Bamum, +Batak, +Bengali, +Bopomofo, +Brahmi, +Braille, +Buginese, +Buhid, +Canadian_Aboriginal, +Carian, +Chakma, +Cham, +Cherokee, +Common, +Coptic, +Cuneiform, +Cypriot, +Cyrillic, +Deseret, +Devanagari, +Egyptian_Hieroglyphs, +Ethiopic, +Georgian, +Glagolitic, +Gothic, +Greek, +Gujarati, +Gurmukhi, +Han, +Hangul, +Hanunoo, +Hebrew, +Hiragana, +Imperial_Aramaic, +Inherited, +Inscriptional_Pahlavi, +Inscriptional_Parthian, +Javanese, +Kaithi, +Kannada, +Katakana, +Kayah_Li, +Kharoshthi, +Khmer, +Lao, +Latin, +Lepcha, +Limbu, +Linear_B, +Lisu, +Lycian, +Lydian, +Malayalam, +Mandaic, +Meetei_Mayek, +Meroitic_Cursive, +Meroitic_Hieroglyphs, +Miao, +Mongolian, +Myanmar, +New_Tai_Lue, +Nko, +Ogham, +Old_Italic, +Old_Persian, +Old_South_Arabian, +Old_Turkic, +Ol_Chiki, +Oriya, +Osmanya, +Phags_Pa, +Phoenician, +Rejang, +Runic, +Samaritan, +Saurashtra, +Sharada, +Shavian, +Sinhala, +Sora_Sompeng, +Sundanese, +Syloti_Nagri, +Syriac, +Tagalog, +Tagbanwa, +Tai_Le, +Tai_Tham, +Tai_Viet, +Takri, +Tamil, +Telugu, +Thaana, +Thai, +Tibetan, +Tifinagh, +Ugaritic, +Vai, +Yi. +</P> +<P> +Each character has exactly one Unicode general category property, specified by +a two-letter abbreviation. For compatibility with Perl, negation can be +specified by including a circumflex between the opening brace and the property +name. For example, \p{^Lu} is the same as \P{Lu}. +</P> +<P> +If only one letter is specified with \p or \P, it includes all the general +category properties that start with that letter. In this case, in the absence +of negation, the curly brackets in the escape sequence are optional; these two +examples have the same effect: +<pre> + \p{L} + \pL +</pre> +The following general category property codes are supported: +<pre> + C Other + Cc Control + Cf Format + Cn Unassigned + Co Private use + Cs Surrogate + + L Letter + Ll Lower case letter + Lm Modifier letter + Lo Other letter + Lt Title case letter + Lu Upper case letter + + M Mark + Mc Spacing mark + Me Enclosing mark + Mn Non-spacing mark + + N Number + Nd Decimal number + Nl Letter number + No Other number + + P Punctuation + Pc Connector punctuation + Pd Dash punctuation + Pe Close punctuation + Pf Final punctuation + Pi Initial punctuation + Po Other punctuation + Ps Open punctuation + + S Symbol + Sc Currency symbol + Sk Modifier symbol + Sm Mathematical symbol + So Other symbol + + Z Separator + Zl Line separator + Zp Paragraph separator + Zs Space separator +</pre> +The special property L& is also supported: it matches a character that has +the Lu, Ll, or Lt property, in other words, a letter that is not classified as +a modifier or "other". +</P> +<P> +The Cs (Surrogate) property applies only to characters in the range U+D800 to +U+DFFF. Such characters are not valid in Unicode strings and so +cannot be tested by PCRE, unless UTF validity checking has been turned off +(see the discussion of PCRE_NO_UTF8_CHECK, PCRE_NO_UTF16_CHECK and +PCRE_NO_UTF32_CHECK in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page). Perl does not support the Cs property. +</P> +<P> +The long synonyms for property names that Perl supports (such as \p{Letter}) +are not supported by PCRE, nor is it permitted to prefix any of these +properties with "Is". +</P> +<P> +No character that is in the Unicode table has the Cn (unassigned) property. +Instead, this property is assumed for any code point that is not in the +Unicode table. +</P> +<P> +Specifying caseless matching does not affect these escape sequences. For +example, \p{Lu} always matches only upper case letters. This is different from +the behaviour of current versions of Perl. +</P> +<P> +Matching characters by Unicode property is not fast, because PCRE has to do a +multistage table lookup in order to find a character's property. That is why +the traditional escape sequences such as \d and \w do not use Unicode +properties in PCRE by default, though you can make them do so by setting the +PCRE_UCP option or by starting the pattern with (*UCP). +</P> +<br><b> +Extended grapheme clusters +</b><br> +<P> +The \X escape matches any number of Unicode characters that form an "extended +grapheme cluster", and treats the sequence as an atomic group +<a href="#atomicgroup">(see below).</a> +Up to and including release 8.31, PCRE matched an earlier, simpler definition +that was equivalent to +<pre> + (?>\PM\pM*) +</pre> +That is, it matched a character without the "mark" property, followed by zero +or more characters with the "mark" property. Characters with the "mark" +property are typically non-spacing accents that affect the preceding character. +</P> +<P> +This simple definition was extended in Unicode to include more complicated +kinds of composite character by giving each character a grapheme breaking +property, and creating rules that use these properties to define the boundaries +of extended grapheme clusters. In releases of PCRE later than 8.31, \X matches +one of these clusters. +</P> +<P> +\X always matches at least one character. Then it decides whether to add +additional characters according to the following rules for ending a cluster: +</P> +<P> +1. End at the end of the subject string. +</P> +<P> +2. Do not end between CR and LF; otherwise end after any control character. +</P> +<P> +3. Do not break Hangul (a Korean script) syllable sequences. Hangul characters +are of five types: L, V, T, LV, and LVT. An L character may be followed by an +L, V, LV, or LVT character; an LV or V character may be followed by a V or T +character; an LVT or T character may be follwed only by a T character. +</P> +<P> +4. Do not end before extending characters or spacing marks. Characters with +the "mark" property always have the "extend" grapheme breaking property. +</P> +<P> +5. Do not end after prepend characters. +</P> +<P> +6. Otherwise, end the cluster. +<a name="extraprops"></a></P> +<br><b> +PCRE's additional properties +</b><br> +<P> +As well as the standard Unicode properties described above, PCRE supports four +more that make it possible to convert traditional escape sequences such as \w +and \s to use Unicode properties. PCRE uses these non-standard, non-Perl +properties internally when PCRE_UCP is set. However, they may also be used +explicitly. These properties are: +<pre> + Xan Any alphanumeric character + Xps Any POSIX space character + Xsp Any Perl space character + Xwd Any Perl "word" character +</pre> +Xan matches characters that have either the L (letter) or the N (number) +property. Xps matches the characters tab, linefeed, vertical tab, form feed, or +carriage return, and any other character that has the Z (separator) property. +Xsp is the same as Xps; it used to exclude vertical tab, for Perl +compatibility, but Perl changed, and so PCRE followed at release 8.34. Xwd +matches the same characters as Xan, plus underscore. +</P> +<P> +There is another non-standard property, Xuc, which matches any character that +can be represented by a Universal Character Name in C++ and other programming +languages. These are the characters $, @, ` (grave accent), and all characters +with Unicode code points greater than or equal to U+00A0, except for the +surrogates U+D800 to U+DFFF. Note that most base (ASCII) characters are +excluded. (Universal Character Names are of the form \uHHHH or \UHHHHHHHH +where H is a hexadecimal digit. Note that the Xuc property does not match these +sequences but the characters that they represent.) +<a name="resetmatchstart"></a></P> +<br><b> +Resetting the match start +</b><br> +<P> +The escape sequence \K causes any previously matched characters not to be +included in the final matched sequence. For example, the pattern: +<pre> + foo\Kbar +</pre> +matches "foobar", but reports that it has matched "bar". This feature is +similar to a lookbehind assertion +<a href="#lookbehind">(described below).</a> +However, in this case, the part of the subject before the real match does not +have to be of fixed length, as lookbehind assertions do. The use of \K does +not interfere with the setting of +<a href="#subpattern">captured substrings.</a> +For example, when the pattern +<pre> + (foo)\Kbar +</pre> +matches "foobar", the first substring is still set to "foo". +</P> +<P> +Perl documents that the use of \K within assertions is "not well defined". In +PCRE, \K is acted upon when it occurs inside positive assertions, but is +ignored in negative assertions. Note that when a pattern such as (?=ab\K) +matches, the reported start of the match can be greater than the end of the +match. +<a name="smallassertions"></a></P> +<br><b> +Simple assertions +</b><br> +<P> +The final use of backslash is for certain simple assertions. An assertion +specifies a condition that has to be met at a particular point in a match, +without consuming any characters from the subject string. The use of +subpatterns for more complicated assertions is described +<a href="#bigassertions">below.</a> +The backslashed assertions are: +<pre> + \b matches at a word boundary + \B matches when not at a word boundary + \A matches at the start of the subject + \Z matches at the end of the subject + also matches before a newline at the end of the subject + \z matches only at the end of the subject + \G matches at the first matching position in the subject +</pre> +Inside a character class, \b has a different meaning; it matches the backspace +character. If any other of these assertions appears in a character class, by +default it matches the corresponding literal character (for example, \B +matches the letter B). However, if the PCRE_EXTRA option is set, an "invalid +escape sequence" error is generated instead. +</P> +<P> +A word boundary is a position in the subject string where the current character +and the previous character do not both match \w or \W (i.e. one matches +\w and the other matches \W), or the start or end of the string if the +first or last character matches \w, respectively. In a UTF mode, the meanings +of \w and \W can be changed by setting the PCRE_UCP option. When this is +done, it also affects \b and \B. Neither PCRE nor Perl has a separate "start +of word" or "end of word" metasequence. However, whatever follows \b normally +determines which it is. For example, the fragment \ba matches "a" at the start +of a word. +</P> +<P> +The \A, \Z, and \z assertions differ from the traditional circumflex and +dollar (described in the next section) in that they only ever match at the very +start and end of the subject string, whatever options are set. Thus, they are +independent of multiline mode. These three assertions are not affected by the +PCRE_NOTBOL or PCRE_NOTEOL options, which affect only the behaviour of the +circumflex and dollar metacharacters. However, if the <i>startoffset</i> +argument of <b>pcre_exec()</b> is non-zero, indicating that matching is to start +at a point other than the beginning of the subject, \A can never match. The +difference between \Z and \z is that \Z matches before a newline at the end +of the string as well as at the very end, whereas \z matches only at the end. +</P> +<P> +The \G assertion is true only when the current matching position is at the +start point of the match, as specified by the <i>startoffset</i> argument of +<b>pcre_exec()</b>. It differs from \A when the value of <i>startoffset</i> is +non-zero. By calling <b>pcre_exec()</b> multiple times with appropriate +arguments, you can mimic Perl's /g option, and it is in this kind of +implementation where \G can be useful. +</P> +<P> +Note, however, that PCRE's interpretation of \G, as the start of the current +match, is subtly different from Perl's, which defines it as the end of the +previous match. In Perl, these can be different when the previously matched +string was empty. Because PCRE does just one match at a time, it cannot +reproduce this behaviour. +</P> +<P> +If all the alternatives of a pattern begin with \G, the expression is anchored +to the starting match position, and the "anchored" flag is set in the compiled +regular expression. +</P> +<br><a name="SEC6" href="#TOC1">CIRCUMFLEX AND DOLLAR</a><br> +<P> +The circumflex and dollar metacharacters are zero-width assertions. That is, +they test for a particular condition being true without consuming any +characters from the subject string. +</P> +<P> +Outside a character class, in the default matching mode, the circumflex +character is an assertion that is true only if the current matching point is at +the start of the subject string. If the <i>startoffset</i> argument of +<b>pcre_exec()</b> is non-zero, circumflex can never match if the PCRE_MULTILINE +option is unset. Inside a character class, circumflex has an entirely different +meaning +<a href="#characterclass">(see below).</a> +</P> +<P> +Circumflex need not be the first character of the pattern if a number of +alternatives are involved, but it should be the first thing in each alternative +in which it appears if the pattern is ever to match that branch. If all +possible alternatives start with a circumflex, that is, if the pattern is +constrained to match only at the start of the subject, it is said to be an +"anchored" pattern. (There are also other constructs that can cause a pattern +to be anchored.) +</P> +<P> +The dollar character is an assertion that is true only if the current matching +point is at the end of the subject string, or immediately before a newline at +the end of the string (by default). Note, however, that it does not actually +match the newline. Dollar need not be the last character of the pattern if a +number of alternatives are involved, but it should be the last item in any +branch in which it appears. Dollar has no special meaning in a character class. +</P> +<P> +The meaning of dollar can be changed so that it matches only at the very end of +the string, by setting the PCRE_DOLLAR_ENDONLY option at compile time. This +does not affect the \Z assertion. +</P> +<P> +The meanings of the circumflex and dollar characters are changed if the +PCRE_MULTILINE option is set. When this is the case, a circumflex matches +immediately after internal newlines as well as at the start of the subject +string. It does not match after a newline that ends the string. A dollar +matches before any newlines in the string, as well as at the very end, when +PCRE_MULTILINE is set. When newline is specified as the two-character +sequence CRLF, isolated CR and LF characters do not indicate newlines. +</P> +<P> +For example, the pattern /^abc$/ matches the subject string "def\nabc" (where +\n represents a newline) in multiline mode, but not otherwise. Consequently, +patterns that are anchored in single line mode because all branches start with +^ are not anchored in multiline mode, and a match for circumflex is possible +when the <i>startoffset</i> argument of <b>pcre_exec()</b> is non-zero. The +PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set. +</P> +<P> +Note that the sequences \A, \Z, and \z can be used to match the start and +end of the subject in both modes, and if all branches of a pattern start with +\A it is always anchored, whether or not PCRE_MULTILINE is set. +<a name="fullstopdot"></a></P> +<br><a name="SEC7" href="#TOC1">FULL STOP (PERIOD, DOT) AND \N</a><br> +<P> +Outside a character class, a dot in the pattern matches any one character in +the subject string except (by default) a character that signifies the end of a +line. +</P> +<P> +When a line ending is defined as a single character, dot never matches that +character; when the two-character sequence CRLF is used, dot does not match CR +if it is immediately followed by LF, but otherwise it matches all characters +(including isolated CRs and LFs). When any Unicode line endings are being +recognized, dot does not match CR or LF or any of the other line ending +characters. +</P> +<P> +The behaviour of dot with regard to newlines can be changed. If the PCRE_DOTALL +option is set, a dot matches any one character, without exception. If the +two-character sequence CRLF is present in the subject string, it takes two dots +to match it. +</P> +<P> +The handling of dot is entirely independent of the handling of circumflex and +dollar, the only relationship being that they both involve newlines. Dot has no +special meaning in a character class. +</P> +<P> +The escape sequence \N behaves like a dot, except that it is not affected by +the PCRE_DOTALL option. In other words, it matches any character except one +that signifies the end of a line. Perl also uses \N to match characters by +name; PCRE does not support this. +</P> +<br><a name="SEC8" href="#TOC1">MATCHING A SINGLE DATA UNIT</a><br> +<P> +Outside a character class, the escape sequence \C matches any one data unit, +whether or not a UTF mode is set. In the 8-bit library, one data unit is one +byte; in the 16-bit library it is a 16-bit unit; in the 32-bit library it is +a 32-bit unit. Unlike a dot, \C always +matches line-ending characters. The feature is provided in Perl in order to +match individual bytes in UTF-8 mode, but it is unclear how it can usefully be +used. Because \C breaks up characters into individual data units, matching one +unit with \C in a UTF mode means that the rest of the string may start with a +malformed UTF character. This has undefined results, because PCRE assumes that +it is dealing with valid UTF strings (and by default it checks this at the +start of processing unless the PCRE_NO_UTF8_CHECK, PCRE_NO_UTF16_CHECK or +PCRE_NO_UTF32_CHECK option is used). +</P> +<P> +PCRE does not allow \C to appear in lookbehind assertions +<a href="#lookbehind">(described below)</a> +in a UTF mode, because this would make it impossible to calculate the length of +the lookbehind. +</P> +<P> +In general, the \C escape sequence is best avoided. However, one +way of using it that avoids the problem of malformed UTF characters is to use a +lookahead to check the length of the next character, as in this pattern, which +could be used with a UTF-8 string (ignore white space and line breaks): +<pre> + (?| (?=[\x00-\x7f])(\C) | + (?=[\x80-\x{7ff}])(\C)(\C) | + (?=[\x{800}-\x{ffff}])(\C)(\C)(\C) | + (?=[\x{10000}-\x{1fffff}])(\C)(\C)(\C)(\C)) +</pre> +A group that starts with (?| resets the capturing parentheses numbers in each +alternative (see +<a href="#dupsubpatternnumber">"Duplicate Subpattern Numbers"</a> +below). The assertions at the start of each branch check the next UTF-8 +character for values whose encoding uses 1, 2, 3, or 4 bytes, respectively. The +character's individual bytes are then captured by the appropriate number of +groups. +<a name="characterclass"></a></P> +<br><a name="SEC9" href="#TOC1">SQUARE BRACKETS AND CHARACTER CLASSES</a><br> +<P> +An opening square bracket introduces a character class, terminated by a closing +square bracket. A closing square bracket on its own is not special by default. +However, if the PCRE_JAVASCRIPT_COMPAT option is set, a lone closing square +bracket causes a compile-time error. If a closing square bracket is required as +a member of the class, it should be the first data character in the class +(after an initial circumflex, if present) or escaped with a backslash. +</P> +<P> +A character class matches a single character in the subject. In a UTF mode, the +character may be more than one data unit long. A matched character must be in +the set of characters defined by the class, unless the first character in the +class definition is a circumflex, in which case the subject character must not +be in the set defined by the class. If a circumflex is actually required as a +member of the class, ensure it is not the first character, or escape it with a +backslash. +</P> +<P> +For example, the character class [aeiou] matches any lower case vowel, while +[^aeiou] matches any character that is not a lower case vowel. Note that a +circumflex is just a convenient notation for specifying the characters that +are in the class by enumerating those that are not. A class that starts with a +circumflex is not an assertion; it still consumes a character from the subject +string, and therefore it fails if the current pointer is at the end of the +string. +</P> +<P> +In UTF-8 (UTF-16, UTF-32) mode, characters with values greater than 255 (0xffff) +can be included in a class as a literal string of data units, or by using the +\x{ escaping mechanism. +</P> +<P> +When caseless matching is set, any letters in a class represent both their +upper case and lower case versions, so for example, a caseless [aeiou] matches +"A" as well as "a", and a caseless [^aeiou] does not match "A", whereas a +caseful version would. In a UTF mode, PCRE always understands the concept of +case for characters whose values are less than 128, so caseless matching is +always possible. For characters with higher values, the concept of case is +supported if PCRE is compiled with Unicode property support, but not otherwise. +If you want to use caseless matching in a UTF mode for characters 128 and +above, you must ensure that PCRE is compiled with Unicode property support as +well as with UTF support. +</P> +<P> +Characters that might indicate line breaks are never treated in any special way +when matching character classes, whatever line-ending sequence is in use, and +whatever setting of the PCRE_DOTALL and PCRE_MULTILINE options is used. A class +such as [^a] always matches one of these characters. +</P> +<P> +The minus (hyphen) character can be used to specify a range of characters in a +character class. For example, [d-m] matches any letter between d and m, +inclusive. If a minus character is required in a class, it must be escaped with +a backslash or appear in a position where it cannot be interpreted as +indicating a range, typically as the first or last character in the class, or +immediately after a range. For example, [b-d-z] matches letters in the range b +to d, a hyphen character, or z. +</P> +<P> +It is not possible to have the literal character "]" as the end character of a +range. A pattern such as [W-]46] is interpreted as a class of two characters +("W" and "-") followed by a literal string "46]", so it would match "W46]" or +"-46]". However, if the "]" is escaped with a backslash it is interpreted as +the end of range, so [W-\]46] is interpreted as a class containing a range +followed by two other characters. The octal or hexadecimal representation of +"]" can also be used to end a range. +</P> +<P> +An error is generated if a POSIX character class (see below) or an escape +sequence other than one that defines a single character appears at a point +where a range ending character is expected. For example, [z-\xff] is valid, +but [A-\d] and [A-[:digit:]] are not. +</P> +<P> +Ranges operate in the collating sequence of character values. They can also be +used for characters specified numerically, for example [\000-\037]. Ranges +can include any characters that are valid for the current mode. +</P> +<P> +If a range that includes letters is used when caseless matching is set, it +matches the letters in either case. For example, [W-c] is equivalent to +[][\\^_`wxyzabc], matched caselessly, and in a non-UTF mode, if character +tables for a French locale are in use, [\xc8-\xcb] matches accented E +characters in both cases. In UTF modes, PCRE supports the concept of case for +characters with values greater than 128 only when it is compiled with Unicode +property support. +</P> +<P> +The character escape sequences \d, \D, \h, \H, \p, \P, \s, \S, \v, +\V, \w, and \W may appear in a character class, and add the characters that +they match to the class. For example, [\dABCDEF] matches any hexadecimal +digit. In UTF modes, the PCRE_UCP option affects the meanings of \d, \s, \w +and their upper case partners, just as it does when they appear outside a +character class, as described in the section entitled +<a href="#genericchartypes">"Generic character types"</a> +above. The escape sequence \b has a different meaning inside a character +class; it matches the backspace character. The sequences \B, \N, \R, and \X +are not special inside a character class. Like any other unrecognized escape +sequences, they are treated as the literal characters "B", "N", "R", and "X" by +default, but cause an error if the PCRE_EXTRA option is set. +</P> +<P> +A circumflex can conveniently be used with the upper case character types to +specify a more restricted set of characters than the matching lower case type. +For example, the class [^\W_] matches any letter or digit, but not underscore, +whereas [\w] includes underscore. A positive character class should be read as +"something OR something OR ..." and a negative class as "NOT something AND NOT +something AND NOT ...". +</P> +<P> +The only metacharacters that are recognized in character classes are backslash, +hyphen (only where it can be interpreted as specifying a range), circumflex +(only at the start), opening square bracket (only when it can be interpreted as +introducing a POSIX class name, or for a special compatibility feature - see +the next two sections), and the terminating closing square bracket. However, +escaping other non-alphanumeric characters does no harm. +</P> +<br><a name="SEC10" href="#TOC1">POSIX CHARACTER CLASSES</a><br> +<P> +Perl supports the POSIX notation for character classes. This uses names +enclosed by [: and :] within the enclosing square brackets. PCRE also supports +this notation. For example, +<pre> + [01[:alpha:]%] +</pre> +matches "0", "1", any alphabetic character, or "%". The supported class names +are: +<pre> + alnum letters and digits + alpha letters + ascii character codes 0 - 127 + blank space or tab only + cntrl control characters + digit decimal digits (same as \d) + graph printing characters, excluding space + lower lower case letters + print printing characters, including space + punct printing characters, excluding letters and digits and space + space white space (the same as \s from PCRE 8.34) + upper upper case letters + word "word" characters (same as \w) + xdigit hexadecimal digits +</pre> +The default "space" characters are HT (9), LF (10), VT (11), FF (12), CR (13), +and space (32). If locale-specific matching is taking place, the list of space +characters may be different; there may be fewer or more of them. "Space" used +to be different to \s, which did not include VT, for Perl compatibility. +However, Perl changed at release 5.18, and PCRE followed at release 8.34. +"Space" and \s now match the same set of characters. +</P> +<P> +The name "word" is a Perl extension, and "blank" is a GNU extension from Perl +5.8. Another Perl extension is negation, which is indicated by a ^ character +after the colon. For example, +<pre> + [12[:^digit:]] +</pre> +matches "1", "2", or any non-digit. PCRE (and Perl) also recognize the POSIX +syntax [.ch.] and [=ch=] where "ch" is a "collating element", but these are not +supported, and an error is given if they are encountered. +</P> +<P> +By default, characters with values greater than 128 do not match any of the +POSIX character classes. However, if the PCRE_UCP option is passed to +<b>pcre_compile()</b>, some of the classes are changed so that Unicode character +properties are used. This is achieved by replacing certain POSIX classes by +other sequences, as follows: +<pre> + [:alnum:] becomes \p{Xan} + [:alpha:] becomes \p{L} + [:blank:] becomes \h + [:digit:] becomes \p{Nd} + [:lower:] becomes \p{Ll} + [:space:] becomes \p{Xps} + [:upper:] becomes \p{Lu} + [:word:] becomes \p{Xwd} +</pre> +Negated versions, such as [:^alpha:] use \P instead of \p. Three other POSIX +classes are handled specially in UCP mode: +</P> +<P> +[:graph:] +This matches characters that have glyphs that mark the page when printed. In +Unicode property terms, it matches all characters with the L, M, N, P, S, or Cf +properties, except for: +<pre> + U+061C Arabic Letter Mark + U+180E Mongolian Vowel Separator + U+2066 - U+2069 Various "isolate"s + +</PRE> +</P> +<P> +[:print:] +This matches the same characters as [:graph:] plus space characters that are +not controls, that is, characters with the Zs property. +</P> +<P> +[:punct:] +This matches all characters that have the Unicode P (punctuation) property, +plus those characters whose code points are less than 128 that have the S +(Symbol) property. +</P> +<P> +The other POSIX classes are unchanged, and match only characters with code +points less than 128. +</P> +<br><a name="SEC11" href="#TOC1">COMPATIBILITY FEATURE FOR WORD BOUNDARIES</a><br> +<P> +In the POSIX.2 compliant library that was included in 4.4BSD Unix, the ugly +syntax [[:<:]] and [[:>:]] is used for matching "start of word" and "end of +word". PCRE treats these items as follows: +<pre> + [[:<:]] is converted to \b(?=\w) + [[:>:]] is converted to \b(?<=\w) +</pre> +Only these exact character sequences are recognized. A sequence such as +[a[:<:]b] provokes error for an unrecognized POSIX class name. This support is +not compatible with Perl. It is provided to help migrations from other +environments, and is best not used in any new patterns. Note that \b matches +at the start and the end of a word (see +<a href="#smallassertions">"Simple assertions"</a> +above), and in a Perl-style pattern the preceding or following character +normally shows which is wanted, without the need for the assertions that are +used above in order to give exactly the POSIX behaviour. +</P> +<br><a name="SEC12" href="#TOC1">VERTICAL BAR</a><br> +<P> +Vertical bar characters are used to separate alternative patterns. For example, +the pattern +<pre> + gilbert|sullivan +</pre> +matches either "gilbert" or "sullivan". Any number of alternatives may appear, +and an empty alternative is permitted (matching the empty string). The matching +process tries each alternative in turn, from left to right, and the first one +that succeeds is used. If the alternatives are within a subpattern +<a href="#subpattern">(defined below),</a> +"succeeds" means matching the rest of the main pattern as well as the +alternative in the subpattern. +</P> +<br><a name="SEC13" href="#TOC1">INTERNAL OPTION SETTING</a><br> +<P> +The settings of the PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and +PCRE_EXTENDED options (which are Perl-compatible) can be changed from within +the pattern by a sequence of Perl option letters enclosed between "(?" and ")". +The option letters are +<pre> + i for PCRE_CASELESS + m for PCRE_MULTILINE + s for PCRE_DOTALL + x for PCRE_EXTENDED +</pre> +For example, (?im) sets caseless, multiline matching. It is also possible to +unset these options by preceding the letter with a hyphen, and a combined +setting and unsetting such as (?im-sx), which sets PCRE_CASELESS and +PCRE_MULTILINE while unsetting PCRE_DOTALL and PCRE_EXTENDED, is also +permitted. If a letter appears both before and after the hyphen, the option is +unset. +</P> +<P> +The PCRE-specific options PCRE_DUPNAMES, PCRE_UNGREEDY, and PCRE_EXTRA can be +changed in the same way as the Perl-compatible options by using the characters +J, U and X respectively. +</P> +<P> +When one of these option changes occurs at top level (that is, not inside +subpattern parentheses), the change applies to the remainder of the pattern +that follows. If the change is placed right at the start of a pattern, PCRE +extracts it into the global options (and it will therefore show up in data +extracted by the <b>pcre_fullinfo()</b> function). +</P> +<P> +An option change within a subpattern (see below for a description of +subpatterns) affects only that part of the subpattern that follows it, so +<pre> + (a(?i)b)c +</pre> +matches abc and aBc and no other strings (assuming PCRE_CASELESS is not used). +By this means, options can be made to have different settings in different +parts of the pattern. Any changes made in one alternative do carry on +into subsequent branches within the same subpattern. For example, +<pre> + (a(?i)b|c) +</pre> +matches "ab", "aB", "c", and "C", even though when matching "C" the first +branch is abandoned before the option setting. This is because the effects of +option settings happen at compile time. There would be some very weird +behaviour otherwise. +</P> +<P> +<b>Note:</b> There are other PCRE-specific options that can be set by the +application when the compiling or matching functions are called. In some cases +the pattern can contain special leading sequences such as (*CRLF) to override +what the application has set or what has been defaulted. Details are given in +the section entitled +<a href="#newlineseq">"Newline sequences"</a> +above. There are also the (*UTF8), (*UTF16),(*UTF32), and (*UCP) leading +sequences that can be used to set UTF and Unicode property modes; they are +equivalent to setting the PCRE_UTF8, PCRE_UTF16, PCRE_UTF32 and the PCRE_UCP +options, respectively. The (*UTF) sequence is a generic version that can be +used with any of the libraries. However, the application can set the +PCRE_NEVER_UTF option, which locks out the use of the (*UTF) sequences. +<a name="subpattern"></a></P> +<br><a name="SEC14" href="#TOC1">SUBPATTERNS</a><br> +<P> +Subpatterns are delimited by parentheses (round brackets), which can be nested. +Turning part of a pattern into a subpattern does two things: +<br> +<br> +1. It localizes a set of alternatives. For example, the pattern +<pre> + cat(aract|erpillar|) +</pre> +matches "cataract", "caterpillar", or "cat". Without the parentheses, it would +match "cataract", "erpillar" or an empty string. +<br> +<br> +2. It sets up the subpattern as a capturing subpattern. This means that, when +the whole pattern matches, that portion of the subject string that matched the +subpattern is passed back to the caller via the <i>ovector</i> argument of the +matching function. (This applies only to the traditional matching functions; +the DFA matching functions do not support capturing.) +</P> +<P> +Opening parentheses are counted from left to right (starting from 1) to obtain +numbers for the capturing subpatterns. For example, if the string "the red +king" is matched against the pattern +<pre> + the ((red|white) (king|queen)) +</pre> +the captured substrings are "red king", "red", and "king", and are numbered 1, +2, and 3, respectively. +</P> +<P> +The fact that plain parentheses fulfil two functions is not always helpful. +There are often times when a grouping subpattern is required without a +capturing requirement. If an opening parenthesis is followed by a question mark +and a colon, the subpattern does not do any capturing, and is not counted when +computing the number of any subsequent capturing subpatterns. For example, if +the string "the white queen" is matched against the pattern +<pre> + the ((?:red|white) (king|queen)) +</pre> +the captured substrings are "white queen" and "queen", and are numbered 1 and +2. The maximum number of capturing subpatterns is 65535. +</P> +<P> +As a convenient shorthand, if any option settings are required at the start of +a non-capturing subpattern, the option letters may appear between the "?" and +the ":". Thus the two patterns +<pre> + (?i:saturday|sunday) + (?:(?i)saturday|sunday) +</pre> +match exactly the same set of strings. Because alternative branches are tried +from left to right, and options are not reset until the end of the subpattern +is reached, an option setting in one branch does affect subsequent branches, so +the above patterns match "SUNDAY" as well as "Saturday". +<a name="dupsubpatternnumber"></a></P> +<br><a name="SEC15" href="#TOC1">DUPLICATE SUBPATTERN NUMBERS</a><br> +<P> +Perl 5.10 introduced a feature whereby each alternative in a subpattern uses +the same numbers for its capturing parentheses. Such a subpattern starts with +(?| and is itself a non-capturing subpattern. For example, consider this +pattern: +<pre> + (?|(Sat)ur|(Sun))day +</pre> +Because the two alternatives are inside a (?| group, both sets of capturing +parentheses are numbered one. Thus, when the pattern matches, you can look +at captured substring number one, whichever alternative matched. This construct +is useful when you want to capture part, but not all, of one of a number of +alternatives. Inside a (?| group, parentheses are numbered as usual, but the +number is reset at the start of each branch. The numbers of any capturing +parentheses that follow the subpattern start after the highest number used in +any branch. The following example is taken from the Perl documentation. The +numbers underneath show in which buffer the captured content will be stored. +<pre> + # before ---------------branch-reset----------- after + / ( a ) (?| x ( y ) z | (p (q) r) | (t) u (v) ) ( z ) /x + # 1 2 2 3 2 3 4 +</pre> +A back reference to a numbered subpattern uses the most recent value that is +set for that number by any subpattern. The following pattern matches "abcabc" +or "defdef": +<pre> + /(?|(abc)|(def))\1/ +</pre> +In contrast, a subroutine call to a numbered subpattern always refers to the +first one in the pattern with the given number. The following pattern matches +"abcabc" or "defabc": +<pre> + /(?|(abc)|(def))(?1)/ +</pre> +If a +<a href="#conditions">condition test</a> +for a subpattern's having matched refers to a non-unique number, the test is +true if any of the subpatterns of that number have matched. +</P> +<P> +An alternative approach to using this "branch reset" feature is to use +duplicate named subpatterns, as described in the next section. +</P> +<br><a name="SEC16" href="#TOC1">NAMED SUBPATTERNS</a><br> +<P> +Identifying capturing parentheses by number is simple, but it can be very hard +to keep track of the numbers in complicated regular expressions. Furthermore, +if an expression is modified, the numbers may change. To help with this +difficulty, PCRE supports the naming of subpatterns. This feature was not +added to Perl until release 5.10. Python had the feature earlier, and PCRE +introduced it at release 4.0, using the Python syntax. PCRE now supports both +the Perl and the Python syntax. Perl allows identically numbered subpatterns to +have different names, but PCRE does not. +</P> +<P> +In PCRE, a subpattern can be named in one of three ways: (?<name>...) or +(?'name'...) as in Perl, or (?P<name>...) as in Python. References to capturing +parentheses from other parts of the pattern, such as +<a href="#backreferences">back references,</a> +<a href="#recursion">recursion,</a> +and +<a href="#conditions">conditions,</a> +can be made by name as well as by number. +</P> +<P> +Names consist of up to 32 alphanumeric characters and underscores, but must +start with a non-digit. Named capturing parentheses are still allocated numbers +as well as names, exactly as if the names were not present. The PCRE API +provides function calls for extracting the name-to-number translation table +from a compiled pattern. There is also a convenience function for extracting a +captured substring by name. +</P> +<P> +By default, a name must be unique within a pattern, but it is possible to relax +this constraint by setting the PCRE_DUPNAMES option at compile time. (Duplicate +names are also always permitted for subpatterns with the same number, set up as +described in the previous section.) Duplicate names can be useful for patterns +where only one instance of the named parentheses can match. Suppose you want to +match the name of a weekday, either as a 3-letter abbreviation or as the full +name, and in both cases you want to extract the abbreviation. This pattern +(ignoring the line breaks) does the job: +<pre> + (?<DN>Mon|Fri|Sun)(?:day)?| + (?<DN>Tue)(?:sday)?| + (?<DN>Wed)(?:nesday)?| + (?<DN>Thu)(?:rsday)?| + (?<DN>Sat)(?:urday)? +</pre> +There are five capturing substrings, but only one is ever set after a match. +(An alternative way of solving this problem is to use a "branch reset" +subpattern, as described in the previous section.) +</P> +<P> +The convenience function for extracting the data by name returns the substring +for the first (and in this example, the only) subpattern of that name that +matched. This saves searching to find which numbered subpattern it was. +</P> +<P> +If you make a back reference to a non-unique named subpattern from elsewhere in +the pattern, the subpatterns to which the name refers are checked in the order +in which they appear in the overall pattern. The first one that is set is used +for the reference. For example, this pattern matches both "foofoo" and +"barbar" but not "foobar" or "barfoo": +<pre> + (?:(?<n>foo)|(?<n>bar))\k<n> + +</PRE> +</P> +<P> +If you make a subroutine call to a non-unique named subpattern, the one that +corresponds to the first occurrence of the name is used. In the absence of +duplicate numbers (see the previous section) this is the one with the lowest +number. +</P> +<P> +If you use a named reference in a condition +test (see the +<a href="#conditions">section about conditions</a> +below), either to check whether a subpattern has matched, or to check for +recursion, all subpatterns with the same name are tested. If the condition is +true for any one of them, the overall condition is true. This is the same +behaviour as testing by number. For further details of the interfaces for +handling named subpatterns, see the +<a href="pcreapi.html"><b>pcreapi</b></a> +documentation. +</P> +<P> +<b>Warning:</b> You cannot use different names to distinguish between two +subpatterns with the same number because PCRE uses only the numbers when +matching. For this reason, an error is given at compile time if different names +are given to subpatterns with the same number. However, you can always give the +same name to subpatterns with the same number, even when PCRE_DUPNAMES is not +set. +</P> +<br><a name="SEC17" href="#TOC1">REPETITION</a><br> +<P> +Repetition is specified by quantifiers, which can follow any of the following +items: +<pre> + a literal data character + the dot metacharacter + the \C escape sequence + the \X escape sequence + the \R escape sequence + an escape such as \d or \pL that matches a single character + a character class + a back reference (see next section) + a parenthesized subpattern (including assertions) + a subroutine call to a subpattern (recursive or otherwise) +</pre> +The general repetition quantifier specifies a minimum and maximum number of +permitted matches, by giving the two numbers in curly brackets (braces), +separated by a comma. The numbers must be less than 65536, and the first must +be less than or equal to the second. For example: +<pre> + z{2,4} +</pre> +matches "zz", "zzz", or "zzzz". A closing brace on its own is not a special +character. If the second number is omitted, but the comma is present, there is +no upper limit; if the second number and the comma are both omitted, the +quantifier specifies an exact number of required matches. Thus +<pre> + [aeiou]{3,} +</pre> +matches at least 3 successive vowels, but may match many more, while +<pre> + \d{8} +</pre> +matches exactly 8 digits. An opening curly bracket that appears in a position +where a quantifier is not allowed, or one that does not match the syntax of a +quantifier, is taken as a literal character. For example, {,6} is not a +quantifier, but a literal string of four characters. +</P> +<P> +In UTF modes, quantifiers apply to characters rather than to individual data +units. Thus, for example, \x{100}{2} matches two characters, each of +which is represented by a two-byte sequence in a UTF-8 string. Similarly, +\X{3} matches three Unicode extended grapheme clusters, each of which may be +several data units long (and they may be of different lengths). +</P> +<P> +The quantifier {0} is permitted, causing the expression to behave as if the +previous item and the quantifier were not present. This may be useful for +subpatterns that are referenced as +<a href="#subpatternsassubroutines">subroutines</a> +from elsewhere in the pattern (but see also the section entitled +<a href="#subdefine">"Defining subpatterns for use by reference only"</a> +below). Items other than subpatterns that have a {0} quantifier are omitted +from the compiled pattern. +</P> +<P> +For convenience, the three most common quantifiers have single-character +abbreviations: +<pre> + * is equivalent to {0,} + + is equivalent to {1,} + ? is equivalent to {0,1} +</pre> +It is possible to construct infinite loops by following a subpattern that can +match no characters with a quantifier that has no upper limit, for example: +<pre> + (a?)* +</pre> +Earlier versions of Perl and PCRE used to give an error at compile time for +such patterns. However, because there are cases where this can be useful, such +patterns are now accepted, but if any repetition of the subpattern does in fact +match no characters, the loop is forcibly broken. +</P> +<P> +By default, the quantifiers are "greedy", that is, they match as much as +possible (up to the maximum number of permitted times), without causing the +rest of the pattern to fail. The classic example of where this gives problems +is in trying to match comments in C programs. These appear between /* and */ +and within the comment, individual * and / characters may appear. An attempt to +match C comments by applying the pattern +<pre> + /\*.*\*/ +</pre> +to the string +<pre> + /* first comment */ not comment /* second comment */ +</pre> +fails, because it matches the entire string owing to the greediness of the .* +item. +</P> +<P> +However, if a quantifier is followed by a question mark, it ceases to be +greedy, and instead matches the minimum number of times possible, so the +pattern +<pre> + /\*.*?\*/ +</pre> +does the right thing with the C comments. The meaning of the various +quantifiers is not otherwise changed, just the preferred number of matches. +Do not confuse this use of question mark with its use as a quantifier in its +own right. Because it has two uses, it can sometimes appear doubled, as in +<pre> + \d??\d +</pre> +which matches one digit by preference, but can match two if that is the only +way the rest of the pattern matches. +</P> +<P> +If the PCRE_UNGREEDY option is set (an option that is not available in Perl), +the quantifiers are not greedy by default, but individual ones can be made +greedy by following them with a question mark. In other words, it inverts the +default behaviour. +</P> +<P> +When a parenthesized subpattern is quantified with a minimum repeat count that +is greater than 1 or with a limited maximum, more memory is required for the +compiled pattern, in proportion to the size of the minimum or maximum. +</P> +<P> +If a pattern starts with .* or .{0,} and the PCRE_DOTALL option (equivalent +to Perl's /s) is set, thus allowing the dot to match newlines, the pattern is +implicitly anchored, because whatever follows will be tried against every +character position in the subject string, so there is no point in retrying the +overall match at any position after the first. PCRE normally treats such a +pattern as though it were preceded by \A. +</P> +<P> +In cases where it is known that the subject string contains no newlines, it is +worth setting PCRE_DOTALL in order to obtain this optimization, or +alternatively using ^ to indicate anchoring explicitly. +</P> +<P> +However, there are some cases where the optimization cannot be used. When .* +is inside capturing parentheses that are the subject of a back reference +elsewhere in the pattern, a match at the start may fail where a later one +succeeds. Consider, for example: +<pre> + (.*)abc\1 +</pre> +If the subject is "xyz123abc123" the match point is the fourth character. For +this reason, such a pattern is not implicitly anchored. +</P> +<P> +Another case where implicit anchoring is not applied is when the leading .* is +inside an atomic group. Once again, a match at the start may fail where a later +one succeeds. Consider this pattern: +<pre> + (?>.*?a)b +</pre> +It matches "ab" in the subject "aab". The use of the backtracking control verbs +(*PRUNE) and (*SKIP) also disable this optimization. +</P> +<P> +When a capturing subpattern is repeated, the value captured is the substring +that matched the final iteration. For example, after +<pre> + (tweedle[dume]{3}\s*)+ +</pre> +has matched "tweedledum tweedledee" the value of the captured substring is +"tweedledee". However, if there are nested capturing subpatterns, the +corresponding captured values may have been set in previous iterations. For +example, after +<pre> + /(a|(b))+/ +</pre> +matches "aba" the value of the second captured substring is "b". +<a name="atomicgroup"></a></P> +<br><a name="SEC18" href="#TOC1">ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS</a><br> +<P> +With both maximizing ("greedy") and minimizing ("ungreedy" or "lazy") +repetition, failure of what follows normally causes the repeated item to be +re-evaluated to see if a different number of repeats allows the rest of the +pattern to match. Sometimes it is useful to prevent this, either to change the +nature of the match, or to cause it fail earlier than it otherwise might, when +the author of the pattern knows there is no point in carrying on. +</P> +<P> +Consider, for example, the pattern \d+foo when applied to the subject line +<pre> + 123456bar +</pre> +After matching all 6 digits and then failing to match "foo", the normal +action of the matcher is to try again with only 5 digits matching the \d+ +item, and then with 4, and so on, before ultimately failing. "Atomic grouping" +(a term taken from Jeffrey Friedl's book) provides the means for specifying +that once a subpattern has matched, it is not to be re-evaluated in this way. +</P> +<P> +If we use atomic grouping for the previous example, the matcher gives up +immediately on failing to match "foo" the first time. The notation is a kind of +special parenthesis, starting with (?> as in this example: +<pre> + (?>\d+)foo +</pre> +This kind of parenthesis "locks up" the part of the pattern it contains once +it has matched, and a failure further into the pattern is prevented from +backtracking into it. Backtracking past it to previous items, however, works as +normal. +</P> +<P> +An alternative description is that a subpattern of this type matches the string +of characters that an identical standalone pattern would match, if anchored at +the current point in the subject string. +</P> +<P> +Atomic grouping subpatterns are not capturing subpatterns. Simple cases such as +the above example can be thought of as a maximizing repeat that must swallow +everything it can. So, while both \d+ and \d+? are prepared to adjust the +number of digits they match in order to make the rest of the pattern match, +(?>\d+) can only match an entire sequence of digits. +</P> +<P> +Atomic groups in general can of course contain arbitrarily complicated +subpatterns, and can be nested. However, when the subpattern for an atomic +group is just a single repeated item, as in the example above, a simpler +notation, called a "possessive quantifier" can be used. This consists of an +additional + character following a quantifier. Using this notation, the +previous example can be rewritten as +<pre> + \d++foo +</pre> +Note that a possessive quantifier can be used with an entire group, for +example: +<pre> + (abc|xyz){2,3}+ +</pre> +Possessive quantifiers are always greedy; the setting of the PCRE_UNGREEDY +option is ignored. They are a convenient notation for the simpler forms of +atomic group. However, there is no difference in the meaning of a possessive +quantifier and the equivalent atomic group, though there may be a performance +difference; possessive quantifiers should be slightly faster. +</P> +<P> +The possessive quantifier syntax is an extension to the Perl 5.8 syntax. +Jeffrey Friedl originated the idea (and the name) in the first edition of his +book. Mike McCloskey liked it, so implemented it when he built Sun's Java +package, and PCRE copied it from there. It ultimately found its way into Perl +at release 5.10. +</P> +<P> +PCRE has an optimization that automatically "possessifies" certain simple +pattern constructs. For example, the sequence A+B is treated as A++B because +there is no point in backtracking into a sequence of A's when B must follow. +</P> +<P> +When a pattern contains an unlimited repeat inside a subpattern that can itself +be repeated an unlimited number of times, the use of an atomic group is the +only way to avoid some failing matches taking a very long time indeed. The +pattern +<pre> + (\D+|<\d+>)*[!?] +</pre> +matches an unlimited number of substrings that either consist of non-digits, or +digits enclosed in <>, followed by either ! or ?. When it matches, it runs +quickly. However, if it is applied to +<pre> + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +</pre> +it takes a long time before reporting failure. This is because the string can +be divided between the internal \D+ repeat and the external * repeat in a +large number of ways, and all have to be tried. (The example uses [!?] rather +than a single character at the end, because both PCRE and Perl have an +optimization that allows for fast failure when a single character is used. They +remember the last single character that is required for a match, and fail early +if it is not present in the string.) If the pattern is changed so that it uses +an atomic group, like this: +<pre> + ((?>\D+)|<\d+>)*[!?] +</pre> +sequences of non-digits cannot be broken, and failure happens quickly. +<a name="backreferences"></a></P> +<br><a name="SEC19" href="#TOC1">BACK REFERENCES</a><br> +<P> +Outside a character class, a backslash followed by a digit greater than 0 (and +possibly further digits) is a back reference to a capturing subpattern earlier +(that is, to its left) in the pattern, provided there have been that many +previous capturing left parentheses. +</P> +<P> +However, if the decimal number following the backslash is less than 10, it is +always taken as a back reference, and causes an error only if there are not +that many capturing left parentheses in the entire pattern. In other words, the +parentheses that are referenced need not be to the left of the reference for +numbers less than 10. A "forward back reference" of this type can make sense +when a repetition is involved and the subpattern to the right has participated +in an earlier iteration. +</P> +<P> +It is not possible to have a numerical "forward back reference" to a subpattern +whose number is 10 or more using this syntax because a sequence such as \50 is +interpreted as a character defined in octal. See the subsection entitled +"Non-printing characters" +<a href="#digitsafterbackslash">above</a> +for further details of the handling of digits following a backslash. There is +no such problem when named parentheses are used. A back reference to any +subpattern is possible using named parentheses (see below). +</P> +<P> +Another way of avoiding the ambiguity inherent in the use of digits following a +backslash is to use the \g escape sequence. This escape must be followed by an +unsigned number or a negative number, optionally enclosed in braces. These +examples are all identical: +<pre> + (ring), \1 + (ring), \g1 + (ring), \g{1} +</pre> +An unsigned number specifies an absolute reference without the ambiguity that +is present in the older syntax. It is also useful when literal digits follow +the reference. A negative number is a relative reference. Consider this +example: +<pre> + (abc(def)ghi)\g{-1} +</pre> +The sequence \g{-1} is a reference to the most recently started capturing +subpattern before \g, that is, is it equivalent to \2 in this example. +Similarly, \g{-2} would be equivalent to \1. The use of relative references +can be helpful in long patterns, and also in patterns that are created by +joining together fragments that contain references within themselves. +</P> +<P> +A back reference matches whatever actually matched the capturing subpattern in +the current subject string, rather than anything matching the subpattern +itself (see +<a href="#subpatternsassubroutines">"Subpatterns as subroutines"</a> +below for a way of doing that). So the pattern +<pre> + (sens|respons)e and \1ibility +</pre> +matches "sense and sensibility" and "response and responsibility", but not +"sense and responsibility". If caseful matching is in force at the time of the +back reference, the case of letters is relevant. For example, +<pre> + ((?i)rah)\s+\1 +</pre> +matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original +capturing subpattern is matched caselessly. +</P> +<P> +There are several different ways of writing back references to named +subpatterns. The .NET syntax \k{name} and the Perl syntax \k<name> or +\k'name' are supported, as is the Python syntax (?P=name). Perl 5.10's unified +back reference syntax, in which \g can be used for both numeric and named +references, is also supported. We could rewrite the above example in any of +the following ways: +<pre> + (?<p1>(?i)rah)\s+\k<p1> + (?'p1'(?i)rah)\s+\k{p1} + (?P<p1>(?i)rah)\s+(?P=p1) + (?<p1>(?i)rah)\s+\g{p1} +</pre> +A subpattern that is referenced by name may appear in the pattern before or +after the reference. +</P> +<P> +There may be more than one back reference to the same subpattern. If a +subpattern has not actually been used in a particular match, any back +references to it always fail by default. For example, the pattern +<pre> + (a|(bc))\2 +</pre> +always fails if it starts to match "a" rather than "bc". However, if the +PCRE_JAVASCRIPT_COMPAT option is set at compile time, a back reference to an +unset value matches an empty string. +</P> +<P> +Because there may be many capturing parentheses in a pattern, all digits +following a backslash are taken as part of a potential back reference number. +If the pattern continues with a digit character, some delimiter must be used to +terminate the back reference. If the PCRE_EXTENDED option is set, this can be +white space. Otherwise, the \g{ syntax or an empty comment (see +<a href="#comments">"Comments"</a> +below) can be used. +</P> +<br><b> +Recursive back references +</b><br> +<P> +A back reference that occurs inside the parentheses to which it refers fails +when the subpattern is first used, so, for example, (a\1) never matches. +However, such references can be useful inside repeated subpatterns. For +example, the pattern +<pre> + (a|b\1)+ +</pre> +matches any number of "a"s and also "aba", "ababbaa" etc. At each iteration of +the subpattern, the back reference matches the character string corresponding +to the previous iteration. In order for this to work, the pattern must be such +that the first iteration does not need to match the back reference. This can be +done using alternation, as in the example above, or by a quantifier with a +minimum of zero. +</P> +<P> +Back references of this type cause the group that they reference to be treated +as an +<a href="#atomicgroup">atomic group.</a> +Once the whole group has been matched, a subsequent matching failure cannot +cause backtracking into the middle of the group. +<a name="bigassertions"></a></P> +<br><a name="SEC20" href="#TOC1">ASSERTIONS</a><br> +<P> +An assertion is a test on the characters following or preceding the current +matching point that does not actually consume any characters. The simple +assertions coded as \b, \B, \A, \G, \Z, \z, ^ and $ are described +<a href="#smallassertions">above.</a> +</P> +<P> +More complicated assertions are coded as subpatterns. There are two kinds: +those that look ahead of the current position in the subject string, and those +that look behind it. An assertion subpattern is matched in the normal way, +except that it does not cause the current matching position to be changed. +</P> +<P> +Assertion subpatterns are not capturing subpatterns. If such an assertion +contains capturing subpatterns within it, these are counted for the purposes of +numbering the capturing subpatterns in the whole pattern. However, substring +capturing is carried out only for positive assertions. (Perl sometimes, but not +always, does do capturing in negative assertions.) +</P> +<P> +For compatibility with Perl, assertion subpatterns may be repeated; though +it makes no sense to assert the same thing several times, the side effect of +capturing parentheses may occasionally be useful. In practice, there only three +cases: +<br> +<br> +(1) If the quantifier is {0}, the assertion is never obeyed during matching. +However, it may contain internal capturing parenthesized groups that are called +from elsewhere via the +<a href="#subpatternsassubroutines">subroutine mechanism.</a> +<br> +<br> +(2) If quantifier is {0,n} where n is greater than zero, it is treated as if it +were {0,1}. At run time, the rest of the pattern match is tried with and +without the assertion, the order depending on the greediness of the quantifier. +<br> +<br> +(3) If the minimum repetition is greater than zero, the quantifier is ignored. +The assertion is obeyed just once when encountered during matching. +</P> +<br><b> +Lookahead assertions +</b><br> +<P> +Lookahead assertions start with (?= for positive assertions and (?! for +negative assertions. For example, +<pre> + \w+(?=;) +</pre> +matches a word followed by a semicolon, but does not include the semicolon in +the match, and +<pre> + foo(?!bar) +</pre> +matches any occurrence of "foo" that is not followed by "bar". Note that the +apparently similar pattern +<pre> + (?!foo)bar +</pre> +does not find an occurrence of "bar" that is preceded by something other than +"foo"; it finds any occurrence of "bar" whatsoever, because the assertion +(?!foo) is always true when the next three characters are "bar". A +lookbehind assertion is needed to achieve the other effect. +</P> +<P> +If you want to force a matching failure at some point in a pattern, the most +convenient way to do it is with (?!) because an empty string always matches, so +an assertion that requires there not to be an empty string must always fail. +The backtracking control verb (*FAIL) or (*F) is a synonym for (?!). +<a name="lookbehind"></a></P> +<br><b> +Lookbehind assertions +</b><br> +<P> +Lookbehind assertions start with (?<= for positive assertions and (?<! for +negative assertions. For example, +<pre> + (?<!foo)bar +</pre> +does find an occurrence of "bar" that is not preceded by "foo". The contents of +a lookbehind assertion are restricted such that all the strings it matches must +have a fixed length. However, if there are several top-level alternatives, they +do not all have to have the same fixed length. Thus +<pre> + (?<=bullock|donkey) +</pre> +is permitted, but +<pre> + (?<!dogs?|cats?) +</pre> +causes an error at compile time. Branches that match different length strings +are permitted only at the top level of a lookbehind assertion. This is an +extension compared with Perl, which requires all branches to match the same +length of string. An assertion such as +<pre> + (?<=ab(c|de)) +</pre> +is not permitted, because its single top-level branch can match two different +lengths, but it is acceptable to PCRE if rewritten to use two top-level +branches: +<pre> + (?<=abc|abde) +</pre> +In some cases, the escape sequence \K +<a href="#resetmatchstart">(see above)</a> +can be used instead of a lookbehind assertion to get round the fixed-length +restriction. +</P> +<P> +The implementation of lookbehind assertions is, for each alternative, to +temporarily move the current position back by the fixed length and then try to +match. If there are insufficient characters before the current position, the +assertion fails. +</P> +<P> +In a UTF mode, PCRE does not allow the \C escape (which matches a single data +unit even in a UTF mode) to appear in lookbehind assertions, because it makes +it impossible to calculate the length of the lookbehind. The \X and \R +escapes, which can match different numbers of data units, are also not +permitted. +</P> +<P> +<a href="#subpatternsassubroutines">"Subroutine"</a> +calls (see below) such as (?2) or (?&X) are permitted in lookbehinds, as long +as the subpattern matches a fixed-length string. +<a href="#recursion">Recursion,</a> +however, is not supported. +</P> +<P> +Possessive quantifiers can be used in conjunction with lookbehind assertions to +specify efficient matching of fixed-length strings at the end of subject +strings. Consider a simple pattern such as +<pre> + abcd$ +</pre> +when applied to a long string that does not match. Because matching proceeds +from left to right, PCRE will look for each "a" in the subject and then see if +what follows matches the rest of the pattern. If the pattern is specified as +<pre> + ^.*abcd$ +</pre> +the initial .* matches the entire string at first, but when this fails (because +there is no following "a"), it backtracks to match all but the last character, +then all but the last two characters, and so on. Once again the search for "a" +covers the entire string, from right to left, so we are no better off. However, +if the pattern is written as +<pre> + ^.*+(?<=abcd) +</pre> +there can be no backtracking for the .*+ item; it can match only the entire +string. The subsequent lookbehind assertion does a single test on the last four +characters. If it fails, the match fails immediately. For long strings, this +approach makes a significant difference to the processing time. +</P> +<br><b> +Using multiple assertions +</b><br> +<P> +Several assertions (of any sort) may occur in succession. For example, +<pre> + (?<=\d{3})(?<!999)foo +</pre> +matches "foo" preceded by three digits that are not "999". Notice that each of +the assertions is applied independently at the same point in the subject +string. First there is a check that the previous three characters are all +digits, and then there is a check that the same three characters are not "999". +This pattern does <i>not</i> match "foo" preceded by six characters, the first +of which are digits and the last three of which are not "999". For example, it +doesn't match "123abcfoo". A pattern to do that is +<pre> + (?<=\d{3}...)(?<!999)foo +</pre> +This time the first assertion looks at the preceding six characters, checking +that the first three are digits, and then the second assertion checks that the +preceding three characters are not "999". +</P> +<P> +Assertions can be nested in any combination. For example, +<pre> + (?<=(?<!foo)bar)baz +</pre> +matches an occurrence of "baz" that is preceded by "bar" which in turn is not +preceded by "foo", while +<pre> + (?<=\d{3}(?!999)...)foo +</pre> +is another pattern that matches "foo" preceded by three digits and any three +characters that are not "999". +<a name="conditions"></a></P> +<br><a name="SEC21" href="#TOC1">CONDITIONAL SUBPATTERNS</a><br> +<P> +It is possible to cause the matching process to obey a subpattern +conditionally or to choose between two alternative subpatterns, depending on +the result of an assertion, or whether a specific capturing subpattern has +already been matched. The two possible forms of conditional subpattern are: +<pre> + (?(condition)yes-pattern) + (?(condition)yes-pattern|no-pattern) +</pre> +If the condition is satisfied, the yes-pattern is used; otherwise the +no-pattern (if present) is used. If there are more than two alternatives in the +subpattern, a compile-time error occurs. Each of the two alternatives may +itself contain nested subpatterns of any form, including conditional +subpatterns; the restriction to two alternatives applies only at the level of +the condition. This pattern fragment is an example where the alternatives are +complex: +<pre> + (?(1) (A|B|C) | (D | (?(2)E|F) | E) ) + +</PRE> +</P> +<P> +There are four kinds of condition: references to subpatterns, references to +recursion, a pseudo-condition called DEFINE, and assertions. +</P> +<br><b> +Checking for a used subpattern by number +</b><br> +<P> +If the text between the parentheses consists of a sequence of digits, the +condition is true if a capturing subpattern of that number has previously +matched. If there is more than one capturing subpattern with the same number +(see the earlier +<a href="#recursion">section about duplicate subpattern numbers),</a> +the condition is true if any of them have matched. An alternative notation is +to precede the digits with a plus or minus sign. In this case, the subpattern +number is relative rather than absolute. The most recently opened parentheses +can be referenced by (?(-1), the next most recent by (?(-2), and so on. Inside +loops it can also make sense to refer to subsequent groups. The next +parentheses to be opened can be referenced as (?(+1), and so on. (The value +zero in any of these forms is not used; it provokes a compile-time error.) +</P> +<P> +Consider the following pattern, which contains non-significant white space to +make it more readable (assume the PCRE_EXTENDED option) and to divide it into +three parts for ease of discussion: +<pre> + ( \( )? [^()]+ (?(1) \) ) +</pre> +The first part matches an optional opening parenthesis, and if that +character is present, sets it as the first captured substring. The second part +matches one or more characters that are not parentheses. The third part is a +conditional subpattern that tests whether or not the first set of parentheses +matched. If they did, that is, if subject started with an opening parenthesis, +the condition is true, and so the yes-pattern is executed and a closing +parenthesis is required. Otherwise, since no-pattern is not present, the +subpattern matches nothing. In other words, this pattern matches a sequence of +non-parentheses, optionally enclosed in parentheses. +</P> +<P> +If you were embedding this pattern in a larger one, you could use a relative +reference: +<pre> + ...other stuff... ( \( )? [^()]+ (?(-1) \) ) ... +</pre> +This makes the fragment independent of the parentheses in the larger pattern. +</P> +<br><b> +Checking for a used subpattern by name +</b><br> +<P> +Perl uses the syntax (?(<name>)...) or (?('name')...) to test for a used +subpattern by name. For compatibility with earlier versions of PCRE, which had +this facility before Perl, the syntax (?(name)...) is also recognized. +</P> +<P> +Rewriting the above example to use a named subpattern gives this: +<pre> + (?<OPEN> \( )? [^()]+ (?(<OPEN>) \) ) +</pre> +If the name used in a condition of this kind is a duplicate, the test is +applied to all subpatterns of the same name, and is true if any one of them has +matched. +</P> +<br><b> +Checking for pattern recursion +</b><br> +<P> +If the condition is the string (R), and there is no subpattern with the name R, +the condition is true if a recursive call to the whole pattern or any +subpattern has been made. If digits or a name preceded by ampersand follow the +letter R, for example: +<pre> + (?(R3)...) or (?(R&name)...) +</pre> +the condition is true if the most recent recursion is into a subpattern whose +number or name is given. This condition does not check the entire recursion +stack. If the name used in a condition of this kind is a duplicate, the test is +applied to all subpatterns of the same name, and is true if any one of them is +the most recent recursion. +</P> +<P> +At "top level", all these recursion test conditions are false. +<a href="#recursion">The syntax for recursive patterns</a> +is described below. +<a name="subdefine"></a></P> +<br><b> +Defining subpatterns for use by reference only +</b><br> +<P> +If the condition is the string (DEFINE), and there is no subpattern with the +name DEFINE, the condition is always false. In this case, there may be only one +alternative in the subpattern. It is always skipped if control reaches this +point in the pattern; the idea of DEFINE is that it can be used to define +subroutines that can be referenced from elsewhere. (The use of +<a href="#subpatternsassubroutines">subroutines</a> +is described below.) For example, a pattern to match an IPv4 address such as +"192.168.23.245" could be written like this (ignore white space and line +breaks): +<pre> + (?(DEFINE) (?<byte> 2[0-4]\d | 25[0-5] | 1\d\d | [1-9]?\d) ) + \b (?&byte) (\.(?&byte)){3} \b +</pre> +The first part of the pattern is a DEFINE group inside which a another group +named "byte" is defined. This matches an individual component of an IPv4 +address (a number less than 256). When matching takes place, this part of the +pattern is skipped because DEFINE acts like a false condition. The rest of the +pattern uses references to the named group to match the four dot-separated +components of an IPv4 address, insisting on a word boundary at each end. +</P> +<br><b> +Assertion conditions +</b><br> +<P> +If the condition is not in any of the above formats, it must be an assertion. +This may be a positive or negative lookahead or lookbehind assertion. Consider +this pattern, again containing non-significant white space, and with the two +alternatives on the second line: +<pre> + (?(?=[^a-z]*[a-z]) + \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) +</pre> +The condition is a positive lookahead assertion that matches an optional +sequence of non-letters followed by a letter. In other words, it tests for the +presence of at least one letter in the subject. If a letter is found, the +subject is matched against the first alternative; otherwise it is matched +against the second. This pattern matches strings in one of the two forms +dd-aaa-dd or dd-dd-dd, where aaa are letters and dd are digits. +<a name="comments"></a></P> +<br><a name="SEC22" href="#TOC1">COMMENTS</a><br> +<P> +There are two ways of including comments in patterns that are processed by +PCRE. In both cases, the start of the comment must not be in a character class, +nor in the middle of any other sequence of related characters such as (?: or a +subpattern name or number. The characters that make up a comment play no part +in the pattern matching. +</P> +<P> +The sequence (?# marks the start of a comment that continues up to the next +closing parenthesis. Nested parentheses are not permitted. If the PCRE_EXTENDED +option is set, an unescaped # character also introduces a comment, which in +this case continues to immediately after the next newline character or +character sequence in the pattern. Which characters are interpreted as newlines +is controlled by the options passed to a compiling function or by a special +sequence at the start of the pattern, as described in the section entitled +<a href="#newlines">"Newline conventions"</a> +above. Note that the end of this type of comment is a literal newline sequence +in the pattern; escape sequences that happen to represent a newline do not +count. For example, consider this pattern when PCRE_EXTENDED is set, and the +default newline convention is in force: +<pre> + abc #comment \n still comment +</pre> +On encountering the # character, <b>pcre_compile()</b> skips along, looking for +a newline in the pattern. The sequence \n is still literal at this stage, so +it does not terminate the comment. Only an actual character with the code value +0x0a (the default newline) does so. +<a name="recursion"></a></P> +<br><a name="SEC23" href="#TOC1">RECURSIVE PATTERNS</a><br> +<P> +Consider the problem of matching a string in parentheses, allowing for +unlimited nested parentheses. Without the use of recursion, the best that can +be done is to use a pattern that matches up to some fixed depth of nesting. It +is not possible to handle an arbitrary nesting depth. +</P> +<P> +For some time, Perl has provided a facility that allows regular expressions to +recurse (amongst other things). It does this by interpolating Perl code in the +expression at run time, and the code can refer to the expression itself. A Perl +pattern using code interpolation to solve the parentheses problem can be +created like this: +<pre> + $re = qr{\( (?: (?>[^()]+) | (?p{$re}) )* \)}x; +</pre> +The (?p{...}) item interpolates Perl code at run time, and in this case refers +recursively to the pattern in which it appears. +</P> +<P> +Obviously, PCRE cannot support the interpolation of Perl code. Instead, it +supports special syntax for recursion of the entire pattern, and also for +individual subpattern recursion. After its introduction in PCRE and Python, +this kind of recursion was subsequently introduced into Perl at release 5.10. +</P> +<P> +A special item that consists of (? followed by a number greater than zero and a +closing parenthesis is a recursive subroutine call of the subpattern of the +given number, provided that it occurs inside that subpattern. (If not, it is a +<a href="#subpatternsassubroutines">non-recursive subroutine</a> +call, which is described in the next section.) The special item (?R) or (?0) is +a recursive call of the entire regular expression. +</P> +<P> +This PCRE pattern solves the nested parentheses problem (assume the +PCRE_EXTENDED option is set so that white space is ignored): +<pre> + \( ( [^()]++ | (?R) )* \) +</pre> +First it matches an opening parenthesis. Then it matches any number of +substrings which can either be a sequence of non-parentheses, or a recursive +match of the pattern itself (that is, a correctly parenthesized substring). +Finally there is a closing parenthesis. Note the use of a possessive quantifier +to avoid backtracking into sequences of non-parentheses. +</P> +<P> +If this were part of a larger pattern, you would not want to recurse the entire +pattern, so instead you could use this: +<pre> + ( \( ( [^()]++ | (?1) )* \) ) +</pre> +We have put the pattern into parentheses, and caused the recursion to refer to +them instead of the whole pattern. +</P> +<P> +In a larger pattern, keeping track of parenthesis numbers can be tricky. This +is made easier by the use of relative references. Instead of (?1) in the +pattern above you can write (?-2) to refer to the second most recently opened +parentheses preceding the recursion. In other words, a negative number counts +capturing parentheses leftwards from the point at which it is encountered. +</P> +<P> +It is also possible to refer to subsequently opened parentheses, by writing +references such as (?+2). However, these cannot be recursive because the +reference is not inside the parentheses that are referenced. They are always +<a href="#subpatternsassubroutines">non-recursive subroutine</a> +calls, as described in the next section. +</P> +<P> +An alternative approach is to use named parentheses instead. The Perl syntax +for this is (?&name); PCRE's earlier syntax (?P>name) is also supported. We +could rewrite the above example as follows: +<pre> + (?<pn> \( ( [^()]++ | (?&pn) )* \) ) +</pre> +If there is more than one subpattern with the same name, the earliest one is +used. +</P> +<P> +This particular example pattern that we have been looking at contains nested +unlimited repeats, and so the use of a possessive quantifier for matching +strings of non-parentheses is important when applying the pattern to strings +that do not match. For example, when this pattern is applied to +<pre> + (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa() +</pre> +it yields "no match" quickly. However, if a possessive quantifier is not used, +the match runs for a very long time indeed because there are so many different +ways the + and * repeats can carve up the subject, and all have to be tested +before failure can be reported. +</P> +<P> +At the end of a match, the values of capturing parentheses are those from +the outermost level. If you want to obtain intermediate values, a callout +function can be used (see below and the +<a href="pcrecallout.html"><b>pcrecallout</b></a> +documentation). If the pattern above is matched against +<pre> + (ab(cd)ef) +</pre> +the value for the inner capturing parentheses (numbered 2) is "ef", which is +the last value taken on at the top level. If a capturing subpattern is not +matched at the top level, its final captured value is unset, even if it was +(temporarily) set at a deeper level during the matching process. +</P> +<P> +If there are more than 15 capturing parentheses in a pattern, PCRE has to +obtain extra memory to store data during a recursion, which it does by using +<b>pcre_malloc</b>, freeing it via <b>pcre_free</b> afterwards. If no memory can +be obtained, the match fails with the PCRE_ERROR_NOMEMORY error. +</P> +<P> +Do not confuse the (?R) item with the condition (R), which tests for recursion. +Consider this pattern, which matches text in angle brackets, allowing for +arbitrary nesting. Only digits are allowed in nested brackets (that is, when +recursing), whereas any characters are permitted at the outer level. +<pre> + < (?: (?(R) \d++ | [^<>]*+) | (?R)) * > +</pre> +In this pattern, (?(R) is the start of a conditional subpattern, with two +different alternatives for the recursive and non-recursive cases. The (?R) item +is the actual recursive call. +<a name="recursiondifference"></a></P> +<br><b> +Differences in recursion processing between PCRE and Perl +</b><br> +<P> +Recursion processing in PCRE differs from Perl in two important ways. In PCRE +(like Python, but unlike Perl), a recursive subpattern call is always treated +as an atomic group. That is, once it has matched some of the subject string, it +is never re-entered, even if it contains untried alternatives and there is a +subsequent matching failure. This can be illustrated by the following pattern, +which purports to match a palindromic string that contains an odd number of +characters (for example, "a", "aba", "abcba", "abcdcba"): +<pre> + ^(.|(.)(?1)\2)$ +</pre> +The idea is that it either matches a single character, or two identical +characters surrounding a sub-palindrome. In Perl, this pattern works; in PCRE +it does not if the pattern is longer than three characters. Consider the +subject string "abcba": +</P> +<P> +At the top level, the first character is matched, but as it is not at the end +of the string, the first alternative fails; the second alternative is taken +and the recursion kicks in. The recursive call to subpattern 1 successfully +matches the next character ("b"). (Note that the beginning and end of line +tests are not part of the recursion). +</P> +<P> +Back at the top level, the next character ("c") is compared with what +subpattern 2 matched, which was "a". This fails. Because the recursion is +treated as an atomic group, there are now no backtracking points, and so the +entire match fails. (Perl is able, at this point, to re-enter the recursion and +try the second alternative.) However, if the pattern is written with the +alternatives in the other order, things are different: +<pre> + ^((.)(?1)\2|.)$ +</pre> +This time, the recursing alternative is tried first, and continues to recurse +until it runs out of characters, at which point the recursion fails. But this +time we do have another alternative to try at the higher level. That is the big +difference: in the previous case the remaining alternative is at a deeper +recursion level, which PCRE cannot use. +</P> +<P> +To change the pattern so that it matches all palindromic strings, not just +those with an odd number of characters, it is tempting to change the pattern to +this: +<pre> + ^((.)(?1)\2|.?)$ +</pre> +Again, this works in Perl, but not in PCRE, and for the same reason. When a +deeper recursion has matched a single character, it cannot be entered again in +order to match an empty string. The solution is to separate the two cases, and +write out the odd and even cases as alternatives at the higher level: +<pre> + ^(?:((.)(?1)\2|)|((.)(?3)\4|.)) +</pre> +If you want to match typical palindromic phrases, the pattern has to ignore all +non-word characters, which can be done like this: +<pre> + ^\W*+(?:((.)\W*+(?1)\W*+\2|)|((.)\W*+(?3)\W*+\4|\W*+.\W*+))\W*+$ +</pre> +If run with the PCRE_CASELESS option, this pattern matches phrases such as "A +man, a plan, a canal: Panama!" and it works well in both PCRE and Perl. Note +the use of the possessive quantifier *+ to avoid backtracking into sequences of +non-word characters. Without this, PCRE takes a great deal longer (ten times or +more) to match typical phrases, and Perl takes so long that you think it has +gone into a loop. +</P> +<P> +<b>WARNING</b>: The palindrome-matching patterns above work only if the subject +string does not start with a palindrome that is shorter than the entire string. +For example, although "abcba" is correctly matched, if the subject is "ababa", +PCRE finds the palindrome "aba" at the start, then fails at top level because +the end of the string does not follow. Once again, it cannot jump back into the +recursion to try other alternatives, so the entire match fails. +</P> +<P> +The second way in which PCRE and Perl differ in their recursion processing is +in the handling of captured values. In Perl, when a subpattern is called +recursively or as a subpattern (see the next section), it has no access to any +values that were captured outside the recursion, whereas in PCRE these values +can be referenced. Consider this pattern: +<pre> + ^(.)(\1|a(?2)) +</pre> +In PCRE, this pattern matches "bab". The first capturing parentheses match "b", +then in the second group, when the back reference \1 fails to match "b", the +second alternative matches "a" and then recurses. In the recursion, \1 does +now match "b" and so the whole match succeeds. In Perl, the pattern fails to +match because inside the recursive call \1 cannot access the externally set +value. +<a name="subpatternsassubroutines"></a></P> +<br><a name="SEC24" href="#TOC1">SUBPATTERNS AS SUBROUTINES</a><br> +<P> +If the syntax for a recursive subpattern call (either by number or by +name) is used outside the parentheses to which it refers, it operates like a +subroutine in a programming language. The called subpattern may be defined +before or after the reference. A numbered reference can be absolute or +relative, as in these examples: +<pre> + (...(absolute)...)...(?2)... + (...(relative)...)...(?-1)... + (...(?+1)...(relative)... +</pre> +An earlier example pointed out that the pattern +<pre> + (sens|respons)e and \1ibility +</pre> +matches "sense and sensibility" and "response and responsibility", but not +"sense and responsibility". If instead the pattern +<pre> + (sens|respons)e and (?1)ibility +</pre> +is used, it does match "sense and responsibility" as well as the other two +strings. Another example is given in the discussion of DEFINE above. +</P> +<P> +All subroutine calls, whether recursive or not, are always treated as atomic +groups. That is, once a subroutine has matched some of the subject string, it +is never re-entered, even if it contains untried alternatives and there is a +subsequent matching failure. Any capturing parentheses that are set during the +subroutine call revert to their previous values afterwards. +</P> +<P> +Processing options such as case-independence are fixed when a subpattern is +defined, so if it is used as a subroutine, such options cannot be changed for +different calls. For example, consider this pattern: +<pre> + (abc)(?i:(?-1)) +</pre> +It matches "abcabc". It does not match "abcABC" because the change of +processing option does not affect the called subpattern. +<a name="onigurumasubroutines"></a></P> +<br><a name="SEC25" href="#TOC1">ONIGURUMA SUBROUTINE SYNTAX</a><br> +<P> +For compatibility with Oniguruma, the non-Perl syntax \g followed by a name or +a number enclosed either in angle brackets or single quotes, is an alternative +syntax for referencing a subpattern as a subroutine, possibly recursively. Here +are two of the examples used above, rewritten using this syntax: +<pre> + (?<pn> \( ( (?>[^()]+) | \g<pn> )* \) ) + (sens|respons)e and \g'1'ibility +</pre> +PCRE supports an extension to Oniguruma: if a number is preceded by a +plus or a minus sign it is taken as a relative reference. For example: +<pre> + (abc)(?i:\g<-1>) +</pre> +Note that \g{...} (Perl syntax) and \g<...> (Oniguruma syntax) are <i>not</i> +synonymous. The former is a back reference; the latter is a subroutine call. +</P> +<br><a name="SEC26" href="#TOC1">CALLOUTS</a><br> +<P> +Perl has a feature whereby using the sequence (?{...}) causes arbitrary Perl +code to be obeyed in the middle of matching a regular expression. This makes it +possible, amongst other things, to extract different substrings that match the +same pair of parentheses when there is a repetition. +</P> +<P> +PCRE provides a similar feature, but of course it cannot obey arbitrary Perl +code. The feature is called "callout". The caller of PCRE provides an external +function by putting its entry point in the global variable <i>pcre_callout</i> +(8-bit library) or <i>pcre[16|32]_callout</i> (16-bit or 32-bit library). +By default, this variable contains NULL, which disables all calling out. +</P> +<P> +Within a regular expression, (?C) indicates the points at which the external +function is to be called. If you want to identify different callout points, you +can put a number less than 256 after the letter C. The default value is zero. +For example, this pattern has two callout points: +<pre> + (?C1)abc(?C2)def +</pre> +If the PCRE_AUTO_CALLOUT flag is passed to a compiling function, callouts are +automatically installed before each item in the pattern. They are all numbered +255. If there is a conditional group in the pattern whose condition is an +assertion, an additional callout is inserted just before the condition. An +explicit callout may also be set at this position, as in this example: +<pre> + (?(?C9)(?=a)abc|def) +</pre> +Note that this applies only to assertion conditions, not to other types of +condition. +</P> +<P> +During matching, when PCRE reaches a callout point, the external function is +called. It is provided with the number of the callout, the position in the +pattern, and, optionally, one item of data originally supplied by the caller of +the matching function. The callout function may cause matching to proceed, to +backtrack, or to fail altogether. +</P> +<P> +By default, PCRE implements a number of optimizations at compile time and +matching time, and one side-effect is that sometimes callouts are skipped. If +you need all possible callouts to happen, you need to set options that disable +the relevant optimizations. More details, and a complete description of the +interface to the callout function, are given in the +<a href="pcrecallout.html"><b>pcrecallout</b></a> +documentation. +<a name="backtrackcontrol"></a></P> +<br><a name="SEC27" href="#TOC1">BACKTRACKING CONTROL</a><br> +<P> +Perl 5.10 introduced a number of "Special Backtracking Control Verbs", which +are still described in the Perl documentation as "experimental and subject to +change or removal in a future version of Perl". It goes on to say: "Their usage +in production code should be noted to avoid problems during upgrades." The same +remarks apply to the PCRE features described in this section. +</P> +<P> +The new verbs make use of what was previously invalid syntax: an opening +parenthesis followed by an asterisk. They are generally of the form +(*VERB) or (*VERB:NAME). Some may take either form, possibly behaving +differently depending on whether or not a name is present. A name is any +sequence of characters that does not include a closing parenthesis. The maximum +length of name is 255 in the 8-bit library and 65535 in the 16-bit and 32-bit +libraries. If the name is empty, that is, if the closing parenthesis +immediately follows the colon, the effect is as if the colon were not there. +Any number of these verbs may occur in a pattern. +</P> +<P> +Since these verbs are specifically related to backtracking, most of them can be +used only when the pattern is to be matched using one of the traditional +matching functions, because these use a backtracking algorithm. With the +exception of (*FAIL), which behaves like a failing negative assertion, the +backtracking control verbs cause an error if encountered by a DFA matching +function. +</P> +<P> +The behaviour of these verbs in +<a href="#btrepeat">repeated groups,</a> +<a href="#btassert">assertions,</a> +and in +<a href="#btsub">subpatterns called as subroutines</a> +(whether or not recursively) is documented below. +<a name="nooptimize"></a></P> +<br><b> +Optimizations that affect backtracking verbs +</b><br> +<P> +PCRE contains some optimizations that are used to speed up matching by running +some checks at the start of each match attempt. For example, it may know the +minimum length of matching subject, or that a particular character must be +present. When one of these optimizations bypasses the running of a match, any +included backtracking verbs will not, of course, be processed. You can suppress +the start-of-match optimizations by setting the PCRE_NO_START_OPTIMIZE option +when calling <b>pcre_compile()</b> or <b>pcre_exec()</b>, or by starting the +pattern with (*NO_START_OPT). There is more discussion of this option in the +section entitled +<a href="pcreapi.html#execoptions">"Option bits for <b>pcre_exec()</b>"</a> +in the +<a href="pcreapi.html"><b>pcreapi</b></a> +documentation. +</P> +<P> +Experiments with Perl suggest that it too has similar optimizations, sometimes +leading to anomalous results. +</P> +<br><b> +Verbs that act immediately +</b><br> +<P> +The following verbs act as soon as they are encountered. They may not be +followed by a name. +<pre> + (*ACCEPT) +</pre> +This verb causes the match to end successfully, skipping the remainder of the +pattern. However, when it is inside a subpattern that is called as a +subroutine, only that subpattern is ended successfully. Matching then continues +at the outer level. If (*ACCEPT) in triggered in a positive assertion, the +assertion succeeds; in a negative assertion, the assertion fails. +</P> +<P> +If (*ACCEPT) is inside capturing parentheses, the data so far is captured. For +example: +<pre> + A((?:A|B(*ACCEPT)|C)D) +</pre> +This matches "AB", "AAD", or "ACD"; when it matches "AB", "B" is captured by +the outer parentheses. +<pre> + (*FAIL) or (*F) +</pre> +This verb causes a matching failure, forcing backtracking to occur. It is +equivalent to (?!) but easier to read. The Perl documentation notes that it is +probably useful only when combined with (?{}) or (??{}). Those are, of course, +Perl features that are not present in PCRE. The nearest equivalent is the +callout feature, as for example in this pattern: +<pre> + a+(?C)(*FAIL) +</pre> +A match with the string "aaaa" always fails, but the callout is taken before +each backtrack happens (in this example, 10 times). +</P> +<br><b> +Recording which path was taken +</b><br> +<P> +There is one verb whose main purpose is to track how a match was arrived at, +though it also has a secondary use in conjunction with advancing the match +starting point (see (*SKIP) below). +<pre> + (*MARK:NAME) or (*:NAME) +</pre> +A name is always required with this verb. There may be as many instances of +(*MARK) as you like in a pattern, and their names do not have to be unique. +</P> +<P> +When a match succeeds, the name of the last-encountered (*MARK:NAME), +(*PRUNE:NAME), or (*THEN:NAME) on the matching path is passed back to the +caller as described in the section entitled +<a href="pcreapi.html#extradata">"Extra data for <b>pcre_exec()</b>"</a> +in the +<a href="pcreapi.html"><b>pcreapi</b></a> +documentation. Here is an example of <b>pcretest</b> output, where the /K +modifier requests the retrieval and outputting of (*MARK) data: +<pre> + re> /X(*MARK:A)Y|X(*MARK:B)Z/K + data> XY + 0: XY + MK: A + XZ + 0: XZ + MK: B +</pre> +The (*MARK) name is tagged with "MK:" in this output, and in this example it +indicates which of the two alternatives matched. This is a more efficient way +of obtaining this information than putting each alternative in its own +capturing parentheses. +</P> +<P> +If a verb with a name is encountered in a positive assertion that is true, the +name is recorded and passed back if it is the last-encountered. This does not +happen for negative assertions or failing positive assertions. +</P> +<P> +After a partial match or a failed match, the last encountered name in the +entire match process is returned. For example: +<pre> + re> /X(*MARK:A)Y|X(*MARK:B)Z/K + data> XP + No match, mark = B +</pre> +Note that in this unanchored example the mark is retained from the match +attempt that started at the letter "X" in the subject. Subsequent match +attempts starting at "P" and then with an empty string do not get as far as the +(*MARK) item, but nevertheless do not reset it. +</P> +<P> +If you are interested in (*MARK) values after failed matches, you should +probably set the PCRE_NO_START_OPTIMIZE option +<a href="#nooptimize">(see above)</a> +to ensure that the match is always attempted. +</P> +<br><b> +Verbs that act after backtracking +</b><br> +<P> +The following verbs do nothing when they are encountered. Matching continues +with what follows, but if there is no subsequent match, causing a backtrack to +the verb, a failure is forced. That is, backtracking cannot pass to the left of +the verb. However, when one of these verbs appears inside an atomic group or an +assertion that is true, its effect is confined to that group, because once the +group has been matched, there is never any backtracking into it. In this +situation, backtracking can "jump back" to the left of the entire atomic group +or assertion. (Remember also, as stated above, that this localization also +applies in subroutine calls.) +</P> +<P> +These verbs differ in exactly what kind of failure occurs when backtracking +reaches them. The behaviour described below is what happens when the verb is +not in a subroutine or an assertion. Subsequent sections cover these special +cases. +<pre> + (*COMMIT) +</pre> +This verb, which may not be followed by a name, causes the whole match to fail +outright if there is a later matching failure that causes backtracking to reach +it. Even if the pattern is unanchored, no further attempts to find a match by +advancing the starting point take place. If (*COMMIT) is the only backtracking +verb that is encountered, once it has been passed <b>pcre_exec()</b> is +committed to finding a match at the current starting point, or not at all. For +example: +<pre> + a+(*COMMIT)b +</pre> +This matches "xxaab" but not "aacaab". It can be thought of as a kind of +dynamic anchor, or "I've started, so I must finish." The name of the most +recently passed (*MARK) in the path is passed back when (*COMMIT) forces a +match failure. +</P> +<P> +If there is more than one backtracking verb in a pattern, a different one that +follows (*COMMIT) may be triggered first, so merely passing (*COMMIT) during a +match does not always guarantee that a match must be at this starting point. +</P> +<P> +Note that (*COMMIT) at the start of a pattern is not the same as an anchor, +unless PCRE's start-of-match optimizations are turned off, as shown in this +output from <b>pcretest</b>: +<pre> + re> /(*COMMIT)abc/ + data> xyzabc + 0: abc + data> xyzabc\Y + No match +</pre> +For this pattern, PCRE knows that any match must start with "a", so the +optimization skips along the subject to "a" before applying the pattern to the +first set of data. The match attempt then succeeds. In the second set of data, +the escape sequence \Y is interpreted by the <b>pcretest</b> program. It causes +the PCRE_NO_START_OPTIMIZE option to be set when <b>pcre_exec()</b> is called. +This disables the optimization that skips along to the first character. The +pattern is now applied starting at "x", and so the (*COMMIT) causes the match +to fail without trying any other starting points. +<pre> + (*PRUNE) or (*PRUNE:NAME) +</pre> +This verb causes the match to fail at the current starting position in the +subject if there is a later matching failure that causes backtracking to reach +it. If the pattern is unanchored, the normal "bumpalong" advance to the next +starting character then happens. Backtracking can occur as usual to the left of +(*PRUNE), before it is reached, or when matching to the right of (*PRUNE), but +if there is no match to the right, backtracking cannot cross (*PRUNE). In +simple cases, the use of (*PRUNE) is just an alternative to an atomic group or +possessive quantifier, but there are some uses of (*PRUNE) that cannot be +expressed in any other way. In an anchored pattern (*PRUNE) has the same effect +as (*COMMIT). +</P> +<P> +The behaviour of (*PRUNE:NAME) is the not the same as (*MARK:NAME)(*PRUNE). +It is like (*MARK:NAME) in that the name is remembered for passing back to the +caller. However, (*SKIP:NAME) searches only for names set with (*MARK). +<pre> + (*SKIP) +</pre> +This verb, when given without a name, is like (*PRUNE), except that if the +pattern is unanchored, the "bumpalong" advance is not to the next character, +but to the position in the subject where (*SKIP) was encountered. (*SKIP) +signifies that whatever text was matched leading up to it cannot be part of a +successful match. Consider: +<pre> + a+(*SKIP)b +</pre> +If the subject is "aaaac...", after the first match attempt fails (starting at +the first character in the string), the starting point skips on to start the +next attempt at "c". Note that a possessive quantifer does not have the same +effect as this example; although it would suppress backtracking during the +first match attempt, the second attempt would start at the second character +instead of skipping on to "c". +<pre> + (*SKIP:NAME) +</pre> +When (*SKIP) has an associated name, its behaviour is modified. When it is +triggered, the previous path through the pattern is searched for the most +recent (*MARK) that has the same name. If one is found, the "bumpalong" advance +is to the subject position that corresponds to that (*MARK) instead of to where +(*SKIP) was encountered. If no (*MARK) with a matching name is found, the +(*SKIP) is ignored. +</P> +<P> +Note that (*SKIP:NAME) searches only for names set by (*MARK:NAME). It ignores +names that are set by (*PRUNE:NAME) or (*THEN:NAME). +<pre> + (*THEN) or (*THEN:NAME) +</pre> +This verb causes a skip to the next innermost alternative when backtracking +reaches it. That is, it cancels any further backtracking within the current +alternative. Its name comes from the observation that it can be used for a +pattern-based if-then-else block: +<pre> + ( COND1 (*THEN) FOO | COND2 (*THEN) BAR | COND3 (*THEN) BAZ ) ... +</pre> +If the COND1 pattern matches, FOO is tried (and possibly further items after +the end of the group if FOO succeeds); on failure, the matcher skips to the +second alternative and tries COND2, without backtracking into COND1. If that +succeeds and BAR fails, COND3 is tried. If subsequently BAZ fails, there are no +more alternatives, so there is a backtrack to whatever came before the entire +group. If (*THEN) is not inside an alternation, it acts like (*PRUNE). +</P> +<P> +The behaviour of (*THEN:NAME) is the not the same as (*MARK:NAME)(*THEN). +It is like (*MARK:NAME) in that the name is remembered for passing back to the +caller. However, (*SKIP:NAME) searches only for names set with (*MARK). +</P> +<P> +A subpattern that does not contain a | character is just a part of the +enclosing alternative; it is not a nested alternation with only one +alternative. The effect of (*THEN) extends beyond such a subpattern to the +enclosing alternative. Consider this pattern, where A, B, etc. are complex +pattern fragments that do not contain any | characters at this level: +<pre> + A (B(*THEN)C) | D +</pre> +If A and B are matched, but there is a failure in C, matching does not +backtrack into A; instead it moves to the next alternative, that is, D. +However, if the subpattern containing (*THEN) is given an alternative, it +behaves differently: +<pre> + A (B(*THEN)C | (*FAIL)) | D +</pre> +The effect of (*THEN) is now confined to the inner subpattern. After a failure +in C, matching moves to (*FAIL), which causes the whole subpattern to fail +because there are no more alternatives to try. In this case, matching does now +backtrack into A. +</P> +<P> +Note that a conditional subpattern is not considered as having two +alternatives, because only one is ever used. In other words, the | character in +a conditional subpattern has a different meaning. Ignoring white space, +consider: +<pre> + ^.*? (?(?=a) a | b(*THEN)c ) +</pre> +If the subject is "ba", this pattern does not match. Because .*? is ungreedy, +it initially matches zero characters. The condition (?=a) then fails, the +character "b" is matched, but "c" is not. At this point, matching does not +backtrack to .*? as might perhaps be expected from the presence of the | +character. The conditional subpattern is part of the single alternative that +comprises the whole pattern, and so the match fails. (If there was a backtrack +into .*?, allowing it to match "b", the match would succeed.) +</P> +<P> +The verbs just described provide four different "strengths" of control when +subsequent matching fails. (*THEN) is the weakest, carrying on the match at the +next alternative. (*PRUNE) comes next, failing the match at the current +starting position, but allowing an advance to the next character (for an +unanchored pattern). (*SKIP) is similar, except that the advance may be more +than one character. (*COMMIT) is the strongest, causing the entire match to +fail. +</P> +<br><b> +More than one backtracking verb +</b><br> +<P> +If more than one backtracking verb is present in a pattern, the one that is +backtracked onto first acts. For example, consider this pattern, where A, B, +etc. are complex pattern fragments: +<pre> + (A(*COMMIT)B(*THEN)C|ABD) +</pre> +If A matches but B fails, the backtrack to (*COMMIT) causes the entire match to +fail. However, if A and B match, but C fails, the backtrack to (*THEN) causes +the next alternative (ABD) to be tried. This behaviour is consistent, but is +not always the same as Perl's. It means that if two or more backtracking verbs +appear in succession, all the the last of them has no effect. Consider this +example: +<pre> + ...(*COMMIT)(*PRUNE)... +</pre> +If there is a matching failure to the right, backtracking onto (*PRUNE) causes +it to be triggered, and its action is taken. There can never be a backtrack +onto (*COMMIT). +<a name="btrepeat"></a></P> +<br><b> +Backtracking verbs in repeated groups +</b><br> +<P> +PCRE differs from Perl in its handling of backtracking verbs in repeated +groups. For example, consider: +<pre> + /(a(*COMMIT)b)+ac/ +</pre> +If the subject is "abac", Perl matches, but PCRE fails because the (*COMMIT) in +the second repeat of the group acts. +<a name="btassert"></a></P> +<br><b> +Backtracking verbs in assertions +</b><br> +<P> +(*FAIL) in an assertion has its normal effect: it forces an immediate backtrack. +</P> +<P> +(*ACCEPT) in a positive assertion causes the assertion to succeed without any +further processing. In a negative assertion, (*ACCEPT) causes the assertion to +fail without any further processing. +</P> +<P> +The other backtracking verbs are not treated specially if they appear in a +positive assertion. In particular, (*THEN) skips to the next alternative in the +innermost enclosing group that has alternations, whether or not this is within +the assertion. +</P> +<P> +Negative assertions are, however, different, in order to ensure that changing a +positive assertion into a negative assertion changes its result. Backtracking +into (*COMMIT), (*SKIP), or (*PRUNE) causes a negative assertion to be true, +without considering any further alternative branches in the assertion. +Backtracking into (*THEN) causes it to skip to the next enclosing alternative +within the assertion (the normal behaviour), but if the assertion does not have +such an alternative, (*THEN) behaves like (*PRUNE). +<a name="btsub"></a></P> +<br><b> +Backtracking verbs in subroutines +</b><br> +<P> +These behaviours occur whether or not the subpattern is called recursively. +Perl's treatment of subroutines is different in some cases. +</P> +<P> +(*FAIL) in a subpattern called as a subroutine has its normal effect: it forces +an immediate backtrack. +</P> +<P> +(*ACCEPT) in a subpattern called as a subroutine causes the subroutine match to +succeed without any further processing. Matching then continues after the +subroutine call. +</P> +<P> +(*COMMIT), (*SKIP), and (*PRUNE) in a subpattern called as a subroutine cause +the subroutine match to fail. +</P> +<P> +(*THEN) skips to the next alternative in the innermost enclosing group within +the subpattern that has alternatives. If there is no such group within the +subpattern, (*THEN) causes the subroutine match to fail. +</P> +<br><a name="SEC28" href="#TOC1">SEE ALSO</a><br> +<P> +<b>pcreapi</b>(3), <b>pcrecallout</b>(3), <b>pcrematching</b>(3), +<b>pcresyntax</b>(3), <b>pcre</b>(3), <b>pcre16(3)</b>, <b>pcre32(3)</b>. +</P> +<br><a name="SEC29" href="#TOC1">AUTHOR</a><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><a name="SEC30" href="#TOC1">REVISION</a><br> +<P> +Last updated: 08 January 2014 +<br> +Copyright © 1997-2014 University of Cambridge. +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcreperform.html b/plugins/Pcre16/docs/doc/html/pcreperform.html new file mode 100644 index 0000000000..dda207f901 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcreperform.html @@ -0,0 +1,195 @@ +<html> +<head> +<title>pcreperform specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcreperform man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +PCRE PERFORMANCE +</b><br> +<P> +Two aspects of performance are discussed below: memory usage and processing +time. The way you express your pattern as a regular expression can affect both +of them. +</P> +<br><b> +COMPILED PATTERN MEMORY USAGE +</b><br> +<P> +Patterns are compiled by PCRE into a reasonably efficient interpretive code, so +that most simple patterns do not use much memory. However, there is one case +where the memory usage of a compiled pattern can be unexpectedly large. If a +parenthesized subpattern has a quantifier with a minimum greater than 1 and/or +a limited maximum, the whole subpattern is repeated in the compiled code. For +example, the pattern +<pre> + (abc|def){2,4} +</pre> +is compiled as if it were +<pre> + (abc|def)(abc|def)((abc|def)(abc|def)?)? +</pre> +(Technical aside: It is done this way so that backtrack points within each of +the repetitions can be independently maintained.) +</P> +<P> +For regular expressions whose quantifiers use only small numbers, this is not +usually a problem. However, if the numbers are large, and particularly if such +repetitions are nested, the memory usage can become an embarrassment. For +example, the very simple pattern +<pre> + ((ab){1,1000}c){1,3} +</pre> +uses 51K bytes when compiled using the 8-bit library. When PCRE is compiled +with its default internal pointer size of two bytes, the size limit on a +compiled pattern is 64K data units, and this is reached with the above pattern +if the outer repetition is increased from 3 to 4. PCRE can be compiled to use +larger internal pointers and thus handle larger compiled patterns, but it is +better to try to rewrite your pattern to use less memory if you can. +</P> +<P> +One way of reducing the memory usage for such patterns is to make use of PCRE's +<a href="pcrepattern.html#subpatternsassubroutines">"subroutine"</a> +facility. Re-writing the above pattern as +<pre> + ((ab)(?2){0,999}c)(?1){0,2} +</pre> +reduces the memory requirements to 18K, and indeed it remains under 20K even +with the outer repetition increased to 100. However, this pattern is not +exactly equivalent, because the "subroutine" calls are treated as +<a href="pcrepattern.html#atomicgroup">atomic groups</a> +into which there can be no backtracking if there is a subsequent matching +failure. Therefore, PCRE cannot do this kind of rewriting automatically. +Furthermore, there is a noticeable loss of speed when executing the modified +pattern. Nevertheless, if the atomic grouping is not a problem and the loss of +speed is acceptable, this kind of rewriting will allow you to process patterns +that PCRE cannot otherwise handle. +</P> +<br><b> +STACK USAGE AT RUN TIME +</b><br> +<P> +When <b>pcre_exec()</b> or <b>pcre[16|32]_exec()</b> is used for matching, certain +kinds of pattern can cause it to use large amounts of the process stack. In +some environments the default process stack is quite small, and if it runs out +the result is often SIGSEGV. This issue is probably the most frequently raised +problem with PCRE. Rewriting your pattern can often help. The +<a href="pcrestack.html"><b>pcrestack</b></a> +documentation discusses this issue in detail. +</P> +<br><b> +PROCESSING TIME +</b><br> +<P> +Certain items in regular expression patterns are processed more efficiently +than others. It is more efficient to use a character class like [aeiou] than a +set of single-character alternatives such as (a|e|i|o|u). In general, the +simplest construction that provides the required behaviour is usually the most +efficient. Jeffrey Friedl's book contains a lot of useful general discussion +about optimizing regular expressions for efficient performance. This document +contains a few observations about PCRE. +</P> +<P> +Using Unicode character properties (the \p, \P, and \X escapes) is slow, +because PCRE has to use a multi-stage table lookup whenever it needs a +character's property. If you can find an alternative pattern that does not use +character properties, it will probably be faster. +</P> +<P> +By default, the escape sequences \b, \d, \s, and \w, and the POSIX +character classes such as [:alpha:] do not use Unicode properties, partly for +backwards compatibility, and partly for performance reasons. However, you can +set PCRE_UCP if you want Unicode character properties to be used. This can +double the matching time for items such as \d, when matched with +a traditional matching function; the performance loss is less with +a DFA matching function, and in both cases there is not much difference for +\b. +</P> +<P> +When a pattern begins with .* not in parentheses, or in parentheses that are +not the subject of a backreference, and the PCRE_DOTALL option is set, the +pattern is implicitly anchored by PCRE, since it can match only at the start of +a subject string. However, if PCRE_DOTALL is not set, PCRE cannot make this +optimization, because the . metacharacter does not then match a newline, and if +the subject string contains newlines, the pattern may match from the character +immediately following one of them instead of from the very start. For example, +the pattern +<pre> + .*second +</pre> +matches the subject "first\nand second" (where \n stands for a newline +character), with the match starting at the seventh character. In order to do +this, PCRE has to retry the match starting after every newline in the subject. +</P> +<P> +If you are using such a pattern with subject strings that do not contain +newlines, the best performance is obtained by setting PCRE_DOTALL, or starting +the pattern with ^.* or ^.*? to indicate explicit anchoring. That saves PCRE +from having to scan along the subject looking for a newline to restart at. +</P> +<P> +Beware of patterns that contain nested indefinite repeats. These can take a +long time to run when applied to a string that does not match. Consider the +pattern fragment +<pre> + ^(a+)* +</pre> +This can match "aaaa" in 16 different ways, and this number increases very +rapidly as the string gets longer. (The * repeat can match 0, 1, 2, 3, or 4 +times, and for each of those cases other than 0 or 4, the + repeats can match +different numbers of times.) When the remainder of the pattern is such that the +entire match is going to fail, PCRE has in principle to try every possible +variation, and this can take an extremely long time, even for relatively short +strings. +</P> +<P> +An optimization catches some of the more simple cases such as +<pre> + (a+)*b +</pre> +where a literal character follows. Before embarking on the standard matching +procedure, PCRE checks that there is a "b" later in the subject string, and if +there is not, it fails the match immediately. However, when there is no +following literal this optimization cannot be used. You can see the difference +by comparing the behaviour of +<pre> + (a+)*\d +</pre> +with the pattern above. The former gives a failure almost instantly when +applied to a whole line of "a" characters, whereas the latter takes an +appreciable time with strings longer than about 20 characters. +</P> +<P> +In many cases, the solution to this kind of performance issue is to use an +atomic group or a possessive quantifier. +</P> +<br><b> +AUTHOR +</b><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><b> +REVISION +</b><br> +<P> +Last updated: 25 August 2012 +<br> +Copyright © 1997-2012 University of Cambridge. +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcreposix.html b/plugins/Pcre16/docs/doc/html/pcreposix.html new file mode 100644 index 0000000000..18924cf7f9 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcreposix.html @@ -0,0 +1,290 @@ +<html> +<head> +<title>pcreposix specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcreposix man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<ul> +<li><a name="TOC1" href="#SEC1">SYNOPSIS</a> +<li><a name="TOC2" href="#SEC2">DESCRIPTION</a> +<li><a name="TOC3" href="#SEC3">COMPILING A PATTERN</a> +<li><a name="TOC4" href="#SEC4">MATCHING NEWLINE CHARACTERS</a> +<li><a name="TOC5" href="#SEC5">MATCHING A PATTERN</a> +<li><a name="TOC6" href="#SEC6">ERROR MESSAGES</a> +<li><a name="TOC7" href="#SEC7">MEMORY USAGE</a> +<li><a name="TOC8" href="#SEC8">AUTHOR</a> +<li><a name="TOC9" href="#SEC9">REVISION</a> +</ul> +<br><a name="SEC1" href="#TOC1">SYNOPSIS</a><br> +<P> +<b>#include <pcreposix.h></b> +</P> +<P> +<b>int regcomp(regex_t *<i>preg</i>, const char *<i>pattern</i>,</b> +<b> int <i>cflags</i>);</b> +<br> +<br> +<b>int regexec(regex_t *<i>preg</i>, const char *<i>string</i>,</b> +<b> size_t <i>nmatch</i>, regmatch_t <i>pmatch</i>[], int <i>eflags</i>);</b> +<b> size_t regerror(int <i>errcode</i>, const regex_t *<i>preg</i>,</b> +<b> char *<i>errbuf</i>, size_t <i>errbuf_size</i>);</b> +<br> +<br> +<b>void regfree(regex_t *<i>preg</i>);</b> +</P> +<br><a name="SEC2" href="#TOC1">DESCRIPTION</a><br> +<P> +This set of functions provides a POSIX-style API for the PCRE regular +expression 8-bit library. See the +<a href="pcreapi.html"><b>pcreapi</b></a> +documentation for a description of PCRE's native API, which contains much +additional functionality. There is no POSIX-style wrapper for PCRE's 16-bit +and 32-bit library. +</P> +<P> +The functions described here are just wrapper functions that ultimately call +the PCRE native API. Their prototypes are defined in the <b>pcreposix.h</b> +header file, and on Unix systems the library itself is called +<b>pcreposix.a</b>, so can be accessed by adding <b>-lpcreposix</b> to the +command for linking an application that uses them. Because the POSIX functions +call the native ones, it is also necessary to add <b>-lpcre</b>. +</P> +<P> +I have implemented only those POSIX option bits that can be reasonably mapped +to PCRE native options. In addition, the option REG_EXTENDED is defined with +the value zero. This has no effect, but since programs that are written to the +POSIX interface often use it, this makes it easier to slot in PCRE as a +replacement library. Other POSIX options are not even defined. +</P> +<P> +There are also some other options that are not defined by POSIX. These have +been added at the request of users who want to make use of certain +PCRE-specific features via the POSIX calling interface. +</P> +<P> +When PCRE is called via these functions, it is only the API that is POSIX-like +in style. The syntax and semantics of the regular expressions themselves are +still those of Perl, subject to the setting of various PCRE options, as +described below. "POSIX-like in style" means that the API approximates to the +POSIX definition; it is not fully POSIX-compatible, and in multi-byte encoding +domains it is probably even less compatible. +</P> +<P> +The header for these functions is supplied as <b>pcreposix.h</b> to avoid any +potential clash with other POSIX libraries. It can, of course, be renamed or +aliased as <b>regex.h</b>, which is the "correct" name. It provides two +structure types, <i>regex_t</i> for compiled internal forms, and +<i>regmatch_t</i> for returning captured substrings. It also defines some +constants whose names start with "REG_"; these are used for setting options and +identifying error codes. +</P> +<br><a name="SEC3" href="#TOC1">COMPILING A PATTERN</a><br> +<P> +The function <b>regcomp()</b> is called to compile a pattern into an +internal form. The pattern is a C string terminated by a binary zero, and +is passed in the argument <i>pattern</i>. The <i>preg</i> argument is a pointer +to a <b>regex_t</b> structure that is used as a base for storing information +about the compiled regular expression. +</P> +<P> +The argument <i>cflags</i> is either zero, or contains one or more of the bits +defined by the following macros: +<pre> + REG_DOTALL +</pre> +The PCRE_DOTALL option is set when the regular expression is passed for +compilation to the native function. Note that REG_DOTALL is not part of the +POSIX standard. +<pre> + REG_ICASE +</pre> +The PCRE_CASELESS option is set when the regular expression is passed for +compilation to the native function. +<pre> + REG_NEWLINE +</pre> +The PCRE_MULTILINE option is set when the regular expression is passed for +compilation to the native function. Note that this does <i>not</i> mimic the +defined POSIX behaviour for REG_NEWLINE (see the following section). +<pre> + REG_NOSUB +</pre> +The PCRE_NO_AUTO_CAPTURE option is set when the regular expression is passed +for compilation to the native function. In addition, when a pattern that is +compiled with this flag is passed to <b>regexec()</b> for matching, the +<i>nmatch</i> and <i>pmatch</i> arguments are ignored, and no captured strings +are returned. +<pre> + REG_UCP +</pre> +The PCRE_UCP option is set when the regular expression is passed for +compilation to the native function. This causes PCRE to use Unicode properties +when matchine \d, \w, etc., instead of just recognizing ASCII values. Note +that REG_UTF8 is not part of the POSIX standard. +<pre> + REG_UNGREEDY +</pre> +The PCRE_UNGREEDY option is set when the regular expression is passed for +compilation to the native function. Note that REG_UNGREEDY is not part of the +POSIX standard. +<pre> + REG_UTF8 +</pre> +The PCRE_UTF8 option is set when the regular expression is passed for +compilation to the native function. This causes the pattern itself and all data +strings used for matching it to be treated as UTF-8 strings. Note that REG_UTF8 +is not part of the POSIX standard. +</P> +<P> +In the absence of these flags, no options are passed to the native function. +This means the the regex is compiled with PCRE default semantics. In +particular, the way it handles newline characters in the subject string is the +Perl way, not the POSIX way. Note that setting PCRE_MULTILINE has only +<i>some</i> of the effects specified for REG_NEWLINE. It does not affect the way +newlines are matched by . (they are not) or by a negative class such as [^a] +(they are). +</P> +<P> +The yield of <b>regcomp()</b> is zero on success, and non-zero otherwise. The +<i>preg</i> structure is filled in on success, and one member of the structure +is public: <i>re_nsub</i> contains the number of capturing subpatterns in +the regular expression. Various error codes are defined in the header file. +</P> +<P> +NOTE: If the yield of <b>regcomp()</b> is non-zero, you must not attempt to +use the contents of the <i>preg</i> structure. If, for example, you pass it to +<b>regexec()</b>, the result is undefined and your program is likely to crash. +</P> +<br><a name="SEC4" href="#TOC1">MATCHING NEWLINE CHARACTERS</a><br> +<P> +This area is not simple, because POSIX and Perl take different views of things. +It is not possible to get PCRE to obey POSIX semantics, but then PCRE was never +intended to be a POSIX engine. The following table lists the different +possibilities for matching newline characters in PCRE: +<pre> + Default Change with + + . matches newline no PCRE_DOTALL + newline matches [^a] yes not changeable + $ matches \n at end yes PCRE_DOLLARENDONLY + $ matches \n in middle no PCRE_MULTILINE + ^ matches \n in middle no PCRE_MULTILINE +</pre> +This is the equivalent table for POSIX: +<pre> + Default Change with + + . matches newline yes REG_NEWLINE + newline matches [^a] yes REG_NEWLINE + $ matches \n at end no REG_NEWLINE + $ matches \n in middle no REG_NEWLINE + ^ matches \n in middle no REG_NEWLINE +</pre> +PCRE's behaviour is the same as Perl's, except that there is no equivalent for +PCRE_DOLLAR_ENDONLY in Perl. In both PCRE and Perl, there is no way to stop +newline from matching [^a]. +</P> +<P> +The default POSIX newline handling can be obtained by setting PCRE_DOTALL and +PCRE_DOLLAR_ENDONLY, but there is no way to make PCRE behave exactly as for the +REG_NEWLINE action. +</P> +<br><a name="SEC5" href="#TOC1">MATCHING A PATTERN</a><br> +<P> +The function <b>regexec()</b> is called to match a compiled pattern <i>preg</i> +against a given <i>string</i>, which is by default terminated by a zero byte +(but see REG_STARTEND below), subject to the options in <i>eflags</i>. These can +be: +<pre> + REG_NOTBOL +</pre> +The PCRE_NOTBOL option is set when calling the underlying PCRE matching +function. +<pre> + REG_NOTEMPTY +</pre> +The PCRE_NOTEMPTY option is set when calling the underlying PCRE matching +function. Note that REG_NOTEMPTY is not part of the POSIX standard. However, +setting this option can give more POSIX-like behaviour in some situations. +<pre> + REG_NOTEOL +</pre> +The PCRE_NOTEOL option is set when calling the underlying PCRE matching +function. +<pre> + REG_STARTEND +</pre> +The string is considered to start at <i>string</i> + <i>pmatch[0].rm_so</i> and +to have a terminating NUL located at <i>string</i> + <i>pmatch[0].rm_eo</i> +(there need not actually be a NUL at that location), regardless of the value of +<i>nmatch</i>. This is a BSD extension, compatible with but not specified by +IEEE Standard 1003.2 (POSIX.2), and should be used with caution in software +intended to be portable to other systems. Note that a non-zero <i>rm_so</i> does +not imply REG_NOTBOL; REG_STARTEND affects only the location of the string, not +how it is matched. +</P> +<P> +If the pattern was compiled with the REG_NOSUB flag, no data about any matched +strings is returned. The <i>nmatch</i> and <i>pmatch</i> arguments of +<b>regexec()</b> are ignored. +</P> +<P> +If the value of <i>nmatch</i> is zero, or if the value <i>pmatch</i> is NULL, +no data about any matched strings is returned. +</P> +<P> +Otherwise,the portion of the string that was matched, and also any captured +substrings, are returned via the <i>pmatch</i> argument, which points to an +array of <i>nmatch</i> structures of type <i>regmatch_t</i>, containing the +members <i>rm_so</i> and <i>rm_eo</i>. These contain the offset to the first +character of each substring and the offset to the first character after the end +of each substring, respectively. The 0th element of the vector relates to the +entire portion of <i>string</i> that was matched; subsequent elements relate to +the capturing subpatterns of the regular expression. Unused entries in the +array have both structure members set to -1. +</P> +<P> +A successful match yields a zero return; various error codes are defined in the +header file, of which REG_NOMATCH is the "expected" failure code. +</P> +<br><a name="SEC6" href="#TOC1">ERROR MESSAGES</a><br> +<P> +The <b>regerror()</b> function maps a non-zero errorcode from either +<b>regcomp()</b> or <b>regexec()</b> to a printable message. If <i>preg</i> is not +NULL, the error should have arisen from the use of that structure. A message +terminated by a binary zero is placed in <i>errbuf</i>. The length of the +message, including the zero, is limited to <i>errbuf_size</i>. The yield of the +function is the size of buffer needed to hold the whole message. +</P> +<br><a name="SEC7" href="#TOC1">MEMORY USAGE</a><br> +<P> +Compiling a regular expression causes memory to be allocated and associated +with the <i>preg</i> structure. The function <b>regfree()</b> frees all such +memory, after which <i>preg</i> may no longer be used as a compiled expression. +</P> +<br><a name="SEC8" href="#TOC1">AUTHOR</a><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><a name="SEC9" href="#TOC1">REVISION</a><br> +<P> +Last updated: 09 January 2012 +<br> +Copyright © 1997-2012 University of Cambridge. +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcreprecompile.html b/plugins/Pcre16/docs/doc/html/pcreprecompile.html new file mode 100644 index 0000000000..decb1d6ce0 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcreprecompile.html @@ -0,0 +1,163 @@ +<html> +<head> +<title>pcreprecompile specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcreprecompile man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<ul> +<li><a name="TOC1" href="#SEC1">SAVING AND RE-USING PRECOMPILED PCRE PATTERNS</a> +<li><a name="TOC2" href="#SEC2">SAVING A COMPILED PATTERN</a> +<li><a name="TOC3" href="#SEC3">RE-USING A PRECOMPILED PATTERN</a> +<li><a name="TOC4" href="#SEC4">COMPATIBILITY WITH DIFFERENT PCRE RELEASES</a> +<li><a name="TOC5" href="#SEC5">AUTHOR</a> +<li><a name="TOC6" href="#SEC6">REVISION</a> +</ul> +<br><a name="SEC1" href="#TOC1">SAVING AND RE-USING PRECOMPILED PCRE PATTERNS</a><br> +<P> +If you are running an application that uses a large number of regular +expression patterns, it may be useful to store them in a precompiled form +instead of having to compile them every time the application is run. +If you are not using any private character tables (see the +<a href="pcre_maketables.html"><b>pcre_maketables()</b></a> +documentation), this is relatively straightforward. If you are using private +tables, it is a little bit more complicated. However, if you are using the +just-in-time optimization feature, it is not possible to save and reload the +JIT data. +</P> +<P> +If you save compiled patterns to a file, you can copy them to a different host +and run them there. If the two hosts have different endianness (byte order), +you should run the <b>pcre[16|32]_pattern_to_host_byte_order()</b> function on the +new host before trying to match the pattern. The matching functions return +PCRE_ERROR_BADENDIANNESS if they detect a pattern with the wrong endianness. +</P> +<P> +Compiling regular expressions with one version of PCRE for use with a different +version is not guaranteed to work and may cause crashes, and saving and +restoring a compiled pattern loses any JIT optimization data. +</P> +<br><a name="SEC2" href="#TOC1">SAVING A COMPILED PATTERN</a><br> +<P> +The value returned by <b>pcre[16|32]_compile()</b> points to a single block of +memory that holds the compiled pattern and associated data. You can find the +length of this block in bytes by calling <b>pcre[16|32]_fullinfo()</b> with an +argument of PCRE_INFO_SIZE. You can then save the data in any appropriate +manner. Here is sample code for the 8-bit library that compiles a pattern and +writes it to a file. It assumes that the variable <i>fd</i> refers to a file +that is open for output: +<pre> + int erroroffset, rc, size; + char *error; + pcre *re; + + re = pcre_compile("my pattern", 0, &error, &erroroffset, NULL); + if (re == NULL) { ... handle errors ... } + rc = pcre_fullinfo(re, NULL, PCRE_INFO_SIZE, &size); + if (rc < 0) { ... handle errors ... } + rc = fwrite(re, 1, size, fd); + if (rc != size) { ... handle errors ... } +</pre> +In this example, the bytes that comprise the compiled pattern are copied +exactly. Note that this is binary data that may contain any of the 256 possible +byte values. On systems that make a distinction between binary and non-binary +data, be sure that the file is opened for binary output. +</P> +<P> +If you want to write more than one pattern to a file, you will have to devise a +way of separating them. For binary data, preceding each pattern with its length +is probably the most straightforward approach. Another possibility is to write +out the data in hexadecimal instead of binary, one pattern to a line. +</P> +<P> +Saving compiled patterns in a file is only one possible way of storing them for +later use. They could equally well be saved in a database, or in the memory of +some daemon process that passes them via sockets to the processes that want +them. +</P> +<P> +If the pattern has been studied, it is also possible to save the normal study +data in a similar way to the compiled pattern itself. However, if the +PCRE_STUDY_JIT_COMPILE was used, the just-in-time data that is created cannot +be saved because it is too dependent on the current environment. When studying +generates additional information, <b>pcre[16|32]_study()</b> returns a pointer to a +<b>pcre[16|32]_extra</b> data block. Its format is defined in the +<a href="pcreapi.html#extradata">section on matching a pattern</a> +in the +<a href="pcreapi.html"><b>pcreapi</b></a> +documentation. The <i>study_data</i> field points to the binary study data, and +this is what you must save (not the <b>pcre[16|32]_extra</b> block itself). The +length of the study data can be obtained by calling <b>pcre[16|32]_fullinfo()</b> +with an argument of PCRE_INFO_STUDYSIZE. Remember to check that +<b>pcre[16|32]_study()</b> did return a non-NULL value before trying to save the +study data. +</P> +<br><a name="SEC3" href="#TOC1">RE-USING A PRECOMPILED PATTERN</a><br> +<P> +Re-using a precompiled pattern is straightforward. Having reloaded it into main +memory, called <b>pcre[16|32]_pattern_to_host_byte_order()</b> if necessary, you +pass its pointer to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> in +the usual way. +</P> +<P> +However, if you passed a pointer to custom character tables when the pattern +was compiled (the <i>tableptr</i> argument of <b>pcre[16|32]_compile()</b>), you +must now pass a similar pointer to <b>pcre[16|32]_exec()</b> or +<b>pcre[16|32]_dfa_exec()</b>, because the value saved with the compiled pattern +will obviously be nonsense. A field in a <b>pcre[16|32]_extra()</b> block is used +to pass this data, as described in the +<a href="pcreapi.html#extradata">section on matching a pattern</a> +in the +<a href="pcreapi.html"><b>pcreapi</b></a> +documentation. +</P> +<P> +<b>Warning:</b> The tables that <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b> use +must be the same as those that were used when the pattern was compiled. If this +is not the case, the behaviour is undefined. +</P> +<P> +If you did not provide custom character tables when the pattern was compiled, +the pointer in the compiled pattern is NULL, which causes the matching +functions to use PCRE's internal tables. Thus, you do not need to take any +special action at run time in this case. +</P> +<P> +If you saved study data with the compiled pattern, you need to create your own +<b>pcre[16|32]_extra</b> data block and set the <i>study_data</i> field to point +to the reloaded study data. You must also set the PCRE_EXTRA_STUDY_DATA bit in +the <i>flags</i> field to indicate that study data is present. Then pass the +<b>pcre[16|32]_extra</b> block to the matching function in the usual way. If the +pattern was studied for just-in-time optimization, that data cannot be saved, +and so is lost by a save/restore cycle. +</P> +<br><a name="SEC4" href="#TOC1">COMPATIBILITY WITH DIFFERENT PCRE RELEASES</a><br> +<P> +In general, it is safest to recompile all saved patterns when you update to a +new PCRE release, though not all updates actually require this. +</P> +<br><a name="SEC5" href="#TOC1">AUTHOR</a><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><a name="SEC6" href="#TOC1">REVISION</a><br> +<P> +Last updated: 12 November 2013 +<br> +Copyright © 1997-2013 University of Cambridge. +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcresample.html b/plugins/Pcre16/docs/doc/html/pcresample.html new file mode 100644 index 0000000000..aca9184e00 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcresample.html @@ -0,0 +1,110 @@ +<html> +<head> +<title>pcresample specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcresample man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +PCRE SAMPLE PROGRAM +</b><br> +<P> +A simple, complete demonstration program, to get you started with using PCRE, +is supplied in the file <i>pcredemo.c</i> in the PCRE distribution. A listing of +this program is given in the +<a href="pcredemo.html"><b>pcredemo</b></a> +documentation. If you do not have a copy of the PCRE distribution, you can save +this listing to re-create <i>pcredemo.c</i>. +</P> +<P> +The demonstration program, which uses the original PCRE 8-bit library, compiles +the regular expression that is its first argument, and matches it against the +subject string in its second argument. No PCRE options are set, and default +character tables are used. If matching succeeds, the program outputs the +portion of the subject that matched, together with the contents of any captured +substrings. +</P> +<P> +If the -g option is given on the command line, the program then goes on to +check for further matches of the same regular expression in the same subject +string. The logic is a little bit tricky because of the possibility of matching +an empty string. Comments in the code explain what is going on. +</P> +<P> +If PCRE is installed in the standard include and library directories for your +operating system, you should be able to compile the demonstration program using +this command: +<pre> + gcc -o pcredemo pcredemo.c -lpcre +</pre> +If PCRE is installed elsewhere, you may need to add additional options to the +command line. For example, on a Unix-like system that has PCRE installed in +<i>/usr/local</i>, you can compile the demonstration program using a command +like this: +<pre> + gcc -o pcredemo -I/usr/local/include pcredemo.c -L/usr/local/lib -lpcre +</pre> +In a Windows environment, if you want to statically link the program against a +non-dll <b>pcre.a</b> file, you must uncomment the line that defines PCRE_STATIC +before including <b>pcre.h</b>, because otherwise the <b>pcre_malloc()</b> and +<b>pcre_free()</b> exported functions will be declared +<b>__declspec(dllimport)</b>, with unwanted results. +</P> +<P> +Once you have compiled and linked the demonstration program, you can run simple +tests like this: +<pre> + ./pcredemo 'cat|dog' 'the cat sat on the mat' + ./pcredemo -g 'cat|dog' 'the dog sat on the cat' +</pre> +Note that there is a much more comprehensive test program, called +<a href="pcretest.html"><b>pcretest</b>,</a> +which supports many more facilities for testing regular expressions and both +PCRE libraries. The +<a href="pcredemo.html"><b>pcredemo</b></a> +program is provided as a simple coding example. +</P> +<P> +If you try to run +<a href="pcredemo.html"><b>pcredemo</b></a> +when PCRE is not installed in the standard library directory, you may get an +error like this on some operating systems (e.g. Solaris): +<pre> + ld.so.1: a.out: fatal: libpcre.so.0: open failed: No such file or directory +</pre> +This is caused by the way shared library support works on those systems. You +need to add +<pre> + -R/usr/local/lib +</pre> +(for example) to the compile command to get round this problem. +</P> +<br><b> +AUTHOR +</b><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><b> +REVISION +</b><br> +<P> +Last updated: 10 January 2012 +<br> +Copyright © 1997-2012 University of Cambridge. +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcrestack.html b/plugins/Pcre16/docs/doc/html/pcrestack.html new file mode 100644 index 0000000000..af6406d070 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcrestack.html @@ -0,0 +1,225 @@ +<html> +<head> +<title>pcrestack specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcrestack man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +PCRE DISCUSSION OF STACK USAGE +</b><br> +<P> +When you call <b>pcre[16|32]_exec()</b>, it makes use of an internal function +called <b>match()</b>. This calls itself recursively at branch points in the +pattern, in order to remember the state of the match so that it can back up and +try a different alternative if the first one fails. As matching proceeds deeper +and deeper into the tree of possibilities, the recursion depth increases. The +<b>match()</b> function is also called in other circumstances, for example, +whenever a parenthesized sub-pattern is entered, and in certain cases of +repetition. +</P> +<P> +Not all calls of <b>match()</b> increase the recursion depth; for an item such +as a* it may be called several times at the same level, after matching +different numbers of a's. Furthermore, in a number of cases where the result of +the recursive call would immediately be passed back as the result of the +current call (a "tail recursion"), the function is just restarted instead. +</P> +<P> +The above comments apply when <b>pcre[16|32]_exec()</b> is run in its normal +interpretive manner. If the pattern was studied with the +PCRE_STUDY_JIT_COMPILE option, and just-in-time compiling was successful, and +the options passed to <b>pcre[16|32]_exec()</b> were not incompatible, the matching +process uses the JIT-compiled code instead of the <b>match()</b> function. In +this case, the memory requirements are handled entirely differently. See the +<a href="pcrejit.html"><b>pcrejit</b></a> +documentation for details. +</P> +<P> +The <b>pcre[16|32]_dfa_exec()</b> function operates in an entirely different way, +and uses recursion only when there is a regular expression recursion or +subroutine call in the pattern. This includes the processing of assertion and +"once-only" subpatterns, which are handled like subroutine calls. Normally, +these are never very deep, and the limit on the complexity of +<b>pcre[16|32]_dfa_exec()</b> is controlled by the amount of workspace it is given. +However, it is possible to write patterns with runaway infinite recursions; +such patterns will cause <b>pcre[16|32]_dfa_exec()</b> to run out of stack. At +present, there is no protection against this. +</P> +<P> +The comments that follow do NOT apply to <b>pcre[16|32]_dfa_exec()</b>; they are +relevant only for <b>pcre[16|32]_exec()</b> without the JIT optimization. +</P> +<br><b> +Reducing <b>pcre[16|32]_exec()</b>'s stack usage +</b><br> +<P> +Each time that <b>match()</b> is actually called recursively, it uses memory +from the process stack. For certain kinds of pattern and data, very large +amounts of stack may be needed, despite the recognition of "tail recursion". +You can often reduce the amount of recursion, and therefore the amount of stack +used, by modifying the pattern that is being matched. Consider, for example, +this pattern: +<pre> + ([^<]|<(?!inet))+ +</pre> +It matches from wherever it starts until it encounters "<inet" or the end of +the data, and is the kind of pattern that might be used when processing an XML +file. Each iteration of the outer parentheses matches either one character that +is not "<" or a "<" that is not followed by "inet". However, each time a +parenthesis is processed, a recursion occurs, so this formulation uses a stack +frame for each matched character. For a long string, a lot of stack is +required. Consider now this rewritten pattern, which matches exactly the same +strings: +<pre> + ([^<]++|<(?!inet))+ +</pre> +This uses very much less stack, because runs of characters that do not contain +"<" are "swallowed" in one item inside the parentheses. Recursion happens only +when a "<" character that is not followed by "inet" is encountered (and we +assume this is relatively rare). A possessive quantifier is used to stop any +backtracking into the runs of non-"<" characters, but that is not related to +stack usage. +</P> +<P> +This example shows that one way of avoiding stack problems when matching long +subject strings is to write repeated parenthesized subpatterns to match more +than one character whenever possible. +</P> +<br><b> +Compiling PCRE to use heap instead of stack for <b>pcre[16|32]_exec()</b> +</b><br> +<P> +In environments where stack memory is constrained, you might want to compile +PCRE to use heap memory instead of stack for remembering back-up points when +<b>pcre[16|32]_exec()</b> is running. This makes it run a lot more slowly, however. +Details of how to do this are given in the +<a href="pcrebuild.html"><b>pcrebuild</b></a> +documentation. When built in this way, instead of using the stack, PCRE obtains +and frees memory by calling the functions that are pointed to by the +<b>pcre[16|32]_stack_malloc</b> and <b>pcre[16|32]_stack_free</b> variables. By +default, these point to <b>malloc()</b> and <b>free()</b>, but you can replace +the pointers to cause PCRE to use your own functions. Since the block sizes are +always the same, and are always freed in reverse order, it may be possible to +implement customized memory handlers that are more efficient than the standard +functions. +</P> +<br><b> +Limiting <b>pcre[16|32]_exec()</b>'s stack usage +</b><br> +<P> +You can set limits on the number of times that <b>match()</b> is called, both in +total and recursively. If a limit is exceeded, <b>pcre[16|32]_exec()</b> returns an +error code. Setting suitable limits should prevent it from running out of +stack. The default values of the limits are very large, and unlikely ever to +operate. They can be changed when PCRE is built, and they can also be set when +<b>pcre[16|32]_exec()</b> is called. For details of these interfaces, see the +<a href="pcrebuild.html"><b>pcrebuild</b></a> +documentation and the +<a href="pcreapi.html#extradata">section on extra data for <b>pcre[16|32]_exec()</b></a> +in the +<a href="pcreapi.html"><b>pcreapi</b></a> +documentation. +</P> +<P> +As a very rough rule of thumb, you should reckon on about 500 bytes per +recursion. Thus, if you want to limit your stack usage to 8Mb, you should set +the limit at 16000 recursions. A 64Mb stack, on the other hand, can support +around 128000 recursions. +</P> +<P> +In Unix-like environments, the <b>pcretest</b> test program has a command line +option (<b>-S</b>) that can be used to increase the size of its stack. As long +as the stack is large enough, another option (<b>-M</b>) can be used to find the +smallest limits that allow a particular pattern to match a given subject +string. This is done by calling <b>pcre[16|32]_exec()</b> repeatedly with different +limits. +</P> +<br><b> +Obtaining an estimate of stack usage +</b><br> +<P> +The actual amount of stack used per recursion can vary quite a lot, depending +on the compiler that was used to build PCRE and the optimization or debugging +options that were set for it. The rule of thumb value of 500 bytes mentioned +above may be larger or smaller than what is actually needed. A better +approximation can be obtained by running this command: +<pre> + pcretest -m -C +</pre> +The <b>-C</b> option causes <b>pcretest</b> to output information about the +options with which PCRE was compiled. When <b>-m</b> is also given (before +<b>-C</b>), information about stack use is given in a line like this: +<pre> + Match recursion uses stack: approximate frame size = 640 bytes +</pre> +The value is approximate because some recursions need a bit more (up to perhaps +16 more bytes). +</P> +<P> +If the above command is given when PCRE is compiled to use the heap instead of +the stack for recursion, the value that is output is the size of each block +that is obtained from the heap. +</P> +<br><b> +Changing stack size in Unix-like systems +</b><br> +<P> +In Unix-like environments, there is not often a problem with the stack unless +very long strings are involved, though the default limit on stack size varies +from system to system. Values from 8Mb to 64Mb are common. You can find your +default limit by running the command: +<pre> + ulimit -s +</pre> +Unfortunately, the effect of running out of stack is often SIGSEGV, though +sometimes a more explicit error message is given. You can normally increase the +limit on stack size by code such as this: +<pre> + struct rlimit rlim; + getrlimit(RLIMIT_STACK, &rlim); + rlim.rlim_cur = 100*1024*1024; + setrlimit(RLIMIT_STACK, &rlim); +</pre> +This reads the current limits (soft and hard) using <b>getrlimit()</b>, then +attempts to increase the soft limit to 100Mb using <b>setrlimit()</b>. You must +do this before calling <b>pcre[16|32]_exec()</b>. +</P> +<br><b> +Changing stack size in Mac OS X +</b><br> +<P> +Using <b>setrlimit()</b>, as described above, should also work on Mac OS X. It +is also possible to set a stack size when linking a program. There is a +discussion about stack sizes in Mac OS X at this web site: +<a href="http://developer.apple.com/qa/qa2005/qa1419.html">http://developer.apple.com/qa/qa2005/qa1419.html.</a> +</P> +<br><b> +AUTHOR +</b><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><b> +REVISION +</b><br> +<P> +Last updated: 24 June 2012 +<br> +Copyright © 1997-2012 University of Cambridge. +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcresyntax.html b/plugins/Pcre16/docs/doc/html/pcresyntax.html new file mode 100644 index 0000000000..89f35737b4 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcresyntax.html @@ -0,0 +1,538 @@ +<html> +<head> +<title>pcresyntax specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcresyntax man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<ul> +<li><a name="TOC1" href="#SEC1">PCRE REGULAR EXPRESSION SYNTAX SUMMARY</a> +<li><a name="TOC2" href="#SEC2">QUOTING</a> +<li><a name="TOC3" href="#SEC3">CHARACTERS</a> +<li><a name="TOC4" href="#SEC4">CHARACTER TYPES</a> +<li><a name="TOC5" href="#SEC5">GENERAL CATEGORY PROPERTIES FOR \p and \P</a> +<li><a name="TOC6" href="#SEC6">PCRE SPECIAL CATEGORY PROPERTIES FOR \p and \P</a> +<li><a name="TOC7" href="#SEC7">SCRIPT NAMES FOR \p AND \P</a> +<li><a name="TOC8" href="#SEC8">CHARACTER CLASSES</a> +<li><a name="TOC9" href="#SEC9">QUANTIFIERS</a> +<li><a name="TOC10" href="#SEC10">ANCHORS AND SIMPLE ASSERTIONS</a> +<li><a name="TOC11" href="#SEC11">MATCH POINT RESET</a> +<li><a name="TOC12" href="#SEC12">ALTERNATION</a> +<li><a name="TOC13" href="#SEC13">CAPTURING</a> +<li><a name="TOC14" href="#SEC14">ATOMIC GROUPS</a> +<li><a name="TOC15" href="#SEC15">COMMENT</a> +<li><a name="TOC16" href="#SEC16">OPTION SETTING</a> +<li><a name="TOC17" href="#SEC17">NEWLINE CONVENTION</a> +<li><a name="TOC18" href="#SEC18">WHAT \R MATCHES</a> +<li><a name="TOC19" href="#SEC19">LOOKAHEAD AND LOOKBEHIND ASSERTIONS</a> +<li><a name="TOC20" href="#SEC20">BACKREFERENCES</a> +<li><a name="TOC21" href="#SEC21">SUBROUTINE REFERENCES (POSSIBLY RECURSIVE)</a> +<li><a name="TOC22" href="#SEC22">CONDITIONAL PATTERNS</a> +<li><a name="TOC23" href="#SEC23">BACKTRACKING CONTROL</a> +<li><a name="TOC24" href="#SEC24">CALLOUTS</a> +<li><a name="TOC25" href="#SEC25">SEE ALSO</a> +<li><a name="TOC26" href="#SEC26">AUTHOR</a> +<li><a name="TOC27" href="#SEC27">REVISION</a> +</ul> +<br><a name="SEC1" href="#TOC1">PCRE REGULAR EXPRESSION SYNTAX SUMMARY</a><br> +<P> +The full syntax and semantics of the regular expressions that are supported by +PCRE are described in the +<a href="pcrepattern.html"><b>pcrepattern</b></a> +documentation. This document contains a quick-reference summary of the syntax. +</P> +<br><a name="SEC2" href="#TOC1">QUOTING</a><br> +<P> +<pre> + \x where x is non-alphanumeric is a literal x + \Q...\E treat enclosed characters as literal +</PRE> +</P> +<br><a name="SEC3" href="#TOC1">CHARACTERS</a><br> +<P> +<pre> + \a alarm, that is, the BEL character (hex 07) + \cx "control-x", where x is any ASCII character + \e escape (hex 1B) + \f form feed (hex 0C) + \n newline (hex 0A) + \r carriage return (hex 0D) + \t tab (hex 09) + \0dd character with octal code 0dd + \ddd character with octal code ddd, or backreference + \o{ddd..} character with octal code ddd.. + \xhh character with hex code hh + \x{hhh..} character with hex code hhh.. +</pre> +Note that \0dd is always an octal code, and that \8 and \9 are the literal +characters "8" and "9". +</P> +<br><a name="SEC4" href="#TOC1">CHARACTER TYPES</a><br> +<P> +<pre> + . any character except newline; + in dotall mode, any character whatsoever + \C one data unit, even in UTF mode (best avoided) + \d a decimal digit + \D a character that is not a decimal digit + \h a horizontal white space character + \H a character that is not a horizontal white space character + \N a character that is not a newline + \p{<i>xx</i>} a character with the <i>xx</i> property + \P{<i>xx</i>} a character without the <i>xx</i> property + \R a newline sequence + \s a white space character + \S a character that is not a white space character + \v a vertical white space character + \V a character that is not a vertical white space character + \w a "word" character + \W a "non-word" character + \X a Unicode extended grapheme cluster +</pre> +By default, \d, \s, and \w match only ASCII characters, even in UTF-8 mode +or in the 16- bit and 32-bit libraries. However, if locale-specific matching is +happening, \s and \w may also match characters with code points in the range +128-255. If the PCRE_UCP option is set, the behaviour of these escape sequences +is changed to use Unicode properties and they match many more characters. +</P> +<br><a name="SEC5" href="#TOC1">GENERAL CATEGORY PROPERTIES FOR \p and \P</a><br> +<P> +<pre> + C Other + Cc Control + Cf Format + Cn Unassigned + Co Private use + Cs Surrogate + + L Letter + Ll Lower case letter + Lm Modifier letter + Lo Other letter + Lt Title case letter + Lu Upper case letter + L& Ll, Lu, or Lt + + M Mark + Mc Spacing mark + Me Enclosing mark + Mn Non-spacing mark + + N Number + Nd Decimal number + Nl Letter number + No Other number + + P Punctuation + Pc Connector punctuation + Pd Dash punctuation + Pe Close punctuation + Pf Final punctuation + Pi Initial punctuation + Po Other punctuation + Ps Open punctuation + + S Symbol + Sc Currency symbol + Sk Modifier symbol + Sm Mathematical symbol + So Other symbol + + Z Separator + Zl Line separator + Zp Paragraph separator + Zs Space separator +</PRE> +</P> +<br><a name="SEC6" href="#TOC1">PCRE SPECIAL CATEGORY PROPERTIES FOR \p and \P</a><br> +<P> +<pre> + Xan Alphanumeric: union of properties L and N + Xps POSIX space: property Z or tab, NL, VT, FF, CR + Xsp Perl space: property Z or tab, NL, VT, FF, CR + Xuc Univerally-named character: one that can be + represented by a Universal Character Name + Xwd Perl word: property Xan or underscore +</pre> +Perl and POSIX space are now the same. Perl added VT to its space character set +at release 5.18 and PCRE changed at release 8.34. +</P> +<br><a name="SEC7" href="#TOC1">SCRIPT NAMES FOR \p AND \P</a><br> +<P> +Arabic, +Armenian, +Avestan, +Balinese, +Bamum, +Batak, +Bengali, +Bopomofo, +Brahmi, +Braille, +Buginese, +Buhid, +Canadian_Aboriginal, +Carian, +Chakma, +Cham, +Cherokee, +Common, +Coptic, +Cuneiform, +Cypriot, +Cyrillic, +Deseret, +Devanagari, +Egyptian_Hieroglyphs, +Ethiopic, +Georgian, +Glagolitic, +Gothic, +Greek, +Gujarati, +Gurmukhi, +Han, +Hangul, +Hanunoo, +Hebrew, +Hiragana, +Imperial_Aramaic, +Inherited, +Inscriptional_Pahlavi, +Inscriptional_Parthian, +Javanese, +Kaithi, +Kannada, +Katakana, +Kayah_Li, +Kharoshthi, +Khmer, +Lao, +Latin, +Lepcha, +Limbu, +Linear_B, +Lisu, +Lycian, +Lydian, +Malayalam, +Mandaic, +Meetei_Mayek, +Meroitic_Cursive, +Meroitic_Hieroglyphs, +Miao, +Mongolian, +Myanmar, +New_Tai_Lue, +Nko, +Ogham, +Old_Italic, +Old_Persian, +Old_South_Arabian, +Old_Turkic, +Ol_Chiki, +Oriya, +Osmanya, +Phags_Pa, +Phoenician, +Rejang, +Runic, +Samaritan, +Saurashtra, +Sharada, +Shavian, +Sinhala, +Sora_Sompeng, +Sundanese, +Syloti_Nagri, +Syriac, +Tagalog, +Tagbanwa, +Tai_Le, +Tai_Tham, +Tai_Viet, +Takri, +Tamil, +Telugu, +Thaana, +Thai, +Tibetan, +Tifinagh, +Ugaritic, +Vai, +Yi. +</P> +<br><a name="SEC8" href="#TOC1">CHARACTER CLASSES</a><br> +<P> +<pre> + [...] positive character class + [^...] negative character class + [x-y] range (can be used for hex characters) + [[:xxx:]] positive POSIX named set + [[:^xxx:]] negative POSIX named set + + alnum alphanumeric + alpha alphabetic + ascii 0-127 + blank space or tab + cntrl control character + digit decimal digit + graph printing, excluding space + lower lower case letter + print printing, including space + punct printing, excluding alphanumeric + space white space + upper upper case letter + word same as \w + xdigit hexadecimal digit +</pre> +In PCRE, POSIX character set names recognize only ASCII characters by default, +but some of them use Unicode properties if PCRE_UCP is set. You can use +\Q...\E inside a character class. +</P> +<br><a name="SEC9" href="#TOC1">QUANTIFIERS</a><br> +<P> +<pre> + ? 0 or 1, greedy + ?+ 0 or 1, possessive + ?? 0 or 1, lazy + * 0 or more, greedy + *+ 0 or more, possessive + *? 0 or more, lazy + + 1 or more, greedy + ++ 1 or more, possessive + +? 1 or more, lazy + {n} exactly n + {n,m} at least n, no more than m, greedy + {n,m}+ at least n, no more than m, possessive + {n,m}? at least n, no more than m, lazy + {n,} n or more, greedy + {n,}+ n or more, possessive + {n,}? n or more, lazy +</PRE> +</P> +<br><a name="SEC10" href="#TOC1">ANCHORS AND SIMPLE ASSERTIONS</a><br> +<P> +<pre> + \b word boundary + \B not a word boundary + ^ start of subject + also after internal newline in multiline mode + \A start of subject + $ end of subject + also before newline at end of subject + also before internal newline in multiline mode + \Z end of subject + also before newline at end of subject + \z end of subject + \G first matching position in subject +</PRE> +</P> +<br><a name="SEC11" href="#TOC1">MATCH POINT RESET</a><br> +<P> +<pre> + \K reset start of match +</pre> +\K is honoured in positive assertions, but ignored in negative ones. +</P> +<br><a name="SEC12" href="#TOC1">ALTERNATION</a><br> +<P> +<pre> + expr|expr|expr... +</PRE> +</P> +<br><a name="SEC13" href="#TOC1">CAPTURING</a><br> +<P> +<pre> + (...) capturing group + (?<name>...) named capturing group (Perl) + (?'name'...) named capturing group (Perl) + (?P<name>...) named capturing group (Python) + (?:...) non-capturing group + (?|...) non-capturing group; reset group numbers for + capturing groups in each alternative +</PRE> +</P> +<br><a name="SEC14" href="#TOC1">ATOMIC GROUPS</a><br> +<P> +<pre> + (?>...) atomic, non-capturing group +</PRE> +</P> +<br><a name="SEC15" href="#TOC1">COMMENT</a><br> +<P> +<pre> + (?#....) comment (not nestable) +</PRE> +</P> +<br><a name="SEC16" href="#TOC1">OPTION SETTING</a><br> +<P> +<pre> + (?i) caseless + (?J) allow duplicate names + (?m) multiline + (?s) single line (dotall) + (?U) default ungreedy (lazy) + (?x) extended (ignore white space) + (?-...) unset option(s) +</pre> +The following are recognized only at the very start of a pattern or after one +of the newline or \R options with similar syntax. More than one of them may +appear. +<pre> + (*LIMIT_MATCH=d) set the match limit to d (decimal number) + (*LIMIT_RECURSION=d) set the recursion limit to d (decimal number) + (*NO_AUTO_POSSESS) no auto-possessification (PCRE_NO_AUTO_POSSESS) + (*NO_START_OPT) no start-match optimization (PCRE_NO_START_OPTIMIZE) + (*UTF8) set UTF-8 mode: 8-bit library (PCRE_UTF8) + (*UTF16) set UTF-16 mode: 16-bit library (PCRE_UTF16) + (*UTF32) set UTF-32 mode: 32-bit library (PCRE_UTF32) + (*UTF) set appropriate UTF mode for the library in use + (*UCP) set PCRE_UCP (use Unicode properties for \d etc) +</pre> +Note that LIMIT_MATCH and LIMIT_RECURSION can only reduce the value of the +limits set by the caller of pcre_exec(), not increase them. +</P> +<br><a name="SEC17" href="#TOC1">NEWLINE CONVENTION</a><br> +<P> +These are recognized only at the very start of the pattern or after option +settings with a similar syntax. +<pre> + (*CR) carriage return only + (*LF) linefeed only + (*CRLF) carriage return followed by linefeed + (*ANYCRLF) all three of the above + (*ANY) any Unicode newline sequence +</PRE> +</P> +<br><a name="SEC18" href="#TOC1">WHAT \R MATCHES</a><br> +<P> +These are recognized only at the very start of the pattern or after option +setting with a similar syntax. +<pre> + (*BSR_ANYCRLF) CR, LF, or CRLF + (*BSR_UNICODE) any Unicode newline sequence +</PRE> +</P> +<br><a name="SEC19" href="#TOC1">LOOKAHEAD AND LOOKBEHIND ASSERTIONS</a><br> +<P> +<pre> + (?=...) positive look ahead + (?!...) negative look ahead + (?<=...) positive look behind + (?<!...) negative look behind +</pre> +Each top-level branch of a look behind must be of a fixed length. +</P> +<br><a name="SEC20" href="#TOC1">BACKREFERENCES</a><br> +<P> +<pre> + \n reference by number (can be ambiguous) + \gn reference by number + \g{n} reference by number + \g{-n} relative reference by number + \k<name> reference by name (Perl) + \k'name' reference by name (Perl) + \g{name} reference by name (Perl) + \k{name} reference by name (.NET) + (?P=name) reference by name (Python) +</PRE> +</P> +<br><a name="SEC21" href="#TOC1">SUBROUTINE REFERENCES (POSSIBLY RECURSIVE)</a><br> +<P> +<pre> + (?R) recurse whole pattern + (?n) call subpattern by absolute number + (?+n) call subpattern by relative number + (?-n) call subpattern by relative number + (?&name) call subpattern by name (Perl) + (?P>name) call subpattern by name (Python) + \g<name> call subpattern by name (Oniguruma) + \g'name' call subpattern by name (Oniguruma) + \g<n> call subpattern by absolute number (Oniguruma) + \g'n' call subpattern by absolute number (Oniguruma) + \g<+n> call subpattern by relative number (PCRE extension) + \g'+n' call subpattern by relative number (PCRE extension) + \g<-n> call subpattern by relative number (PCRE extension) + \g'-n' call subpattern by relative number (PCRE extension) +</PRE> +</P> +<br><a name="SEC22" href="#TOC1">CONDITIONAL PATTERNS</a><br> +<P> +<pre> + (?(condition)yes-pattern) + (?(condition)yes-pattern|no-pattern) + + (?(n)... absolute reference condition + (?(+n)... relative reference condition + (?(-n)... relative reference condition + (?(<name>)... named reference condition (Perl) + (?('name')... named reference condition (Perl) + (?(name)... named reference condition (PCRE) + (?(R)... overall recursion condition + (?(Rn)... specific group recursion condition + (?(R&name)... specific recursion condition + (?(DEFINE)... define subpattern for reference + (?(assert)... assertion condition +</PRE> +</P> +<br><a name="SEC23" href="#TOC1">BACKTRACKING CONTROL</a><br> +<P> +The following act immediately they are reached: +<pre> + (*ACCEPT) force successful match + (*FAIL) force backtrack; synonym (*F) + (*MARK:NAME) set name to be passed back; synonym (*:NAME) +</pre> +The following act only when a subsequent match failure causes a backtrack to +reach them. They all force a match failure, but they differ in what happens +afterwards. Those that advance the start-of-match point do so only if the +pattern is not anchored. +<pre> + (*COMMIT) overall failure, no advance of starting point + (*PRUNE) advance to next starting character + (*PRUNE:NAME) equivalent to (*MARK:NAME)(*PRUNE) + (*SKIP) advance to current matching position + (*SKIP:NAME) advance to position corresponding to an earlier + (*MARK:NAME); if not found, the (*SKIP) is ignored + (*THEN) local failure, backtrack to next alternation + (*THEN:NAME) equivalent to (*MARK:NAME)(*THEN) +</PRE> +</P> +<br><a name="SEC24" href="#TOC1">CALLOUTS</a><br> +<P> +<pre> + (?C) callout + (?Cn) callout with data n +</PRE> +</P> +<br><a name="SEC25" href="#TOC1">SEE ALSO</a><br> +<P> +<b>pcrepattern</b>(3), <b>pcreapi</b>(3), <b>pcrecallout</b>(3), +<b>pcrematching</b>(3), <b>pcre</b>(3). +</P> +<br><a name="SEC26" href="#TOC1">AUTHOR</a><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><a name="SEC27" href="#TOC1">REVISION</a><br> +<P> +Last updated: 08 January 2014 +<br> +Copyright © 1997-2014 University of Cambridge. +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcretest.html b/plugins/Pcre16/docs/doc/html/pcretest.html new file mode 100644 index 0000000000..839fabf189 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcretest.html @@ -0,0 +1,1158 @@ +<html> +<head> +<title>pcretest specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcretest man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<ul> +<li><a name="TOC1" href="#SEC1">SYNOPSIS</a> +<li><a name="TOC2" href="#SEC2">INPUT DATA FORMAT</a> +<li><a name="TOC3" href="#SEC3">PCRE's 8-BIT, 16-BIT AND 32-BIT LIBRARIES</a> +<li><a name="TOC4" href="#SEC4">COMMAND LINE OPTIONS</a> +<li><a name="TOC5" href="#SEC5">DESCRIPTION</a> +<li><a name="TOC6" href="#SEC6">PATTERN MODIFIERS</a> +<li><a name="TOC7" href="#SEC7">DATA LINES</a> +<li><a name="TOC8" href="#SEC8">THE ALTERNATIVE MATCHING FUNCTION</a> +<li><a name="TOC9" href="#SEC9">DEFAULT OUTPUT FROM PCRETEST</a> +<li><a name="TOC10" href="#SEC10">OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION</a> +<li><a name="TOC11" href="#SEC11">RESTARTING AFTER A PARTIAL MATCH</a> +<li><a name="TOC12" href="#SEC12">CALLOUTS</a> +<li><a name="TOC13" href="#SEC13">NON-PRINTING CHARACTERS</a> +<li><a name="TOC14" href="#SEC14">SAVING AND RELOADING COMPILED PATTERNS</a> +<li><a name="TOC15" href="#SEC15">SEE ALSO</a> +<li><a name="TOC16" href="#SEC16">AUTHOR</a> +<li><a name="TOC17" href="#SEC17">REVISION</a> +</ul> +<br><a name="SEC1" href="#TOC1">SYNOPSIS</a><br> +<P> +<b>pcretest [options] [input file [output file]]</b> +<br> +<br> +<b>pcretest</b> was written as a test program for the PCRE regular expression +library itself, but it can also be used for experimenting with regular +expressions. This document describes the features of the test program; for +details of the regular expressions themselves, see the +<a href="pcrepattern.html"><b>pcrepattern</b></a> +documentation. For details of the PCRE library function calls and their +options, see the +<a href="pcreapi.html"><b>pcreapi</b></a> +, +<a href="pcre16.html"><b>pcre16</b></a> +and +<a href="pcre32.html"><b>pcre32</b></a> +documentation. +</P> +<P> +The input for <b>pcretest</b> is a sequence of regular expression patterns and +strings to be matched, as described below. The output shows the result of each +match. Options on the command line and the patterns control PCRE options and +exactly what is output. +</P> +<P> +As PCRE has evolved, it has acquired many different features, and as a result, +<b>pcretest</b> now has rather a lot of obscure options for testing every +possible feature. Some of these options are specifically designed for use in +conjunction with the test script and data files that are distributed as part of +PCRE, and are unlikely to be of use otherwise. They are all documented here, +but without much justification. +</P> +<br><a name="SEC2" href="#TOC1">INPUT DATA FORMAT</a><br> +<P> +Input to <b>pcretest</b> is processed line by line, either by calling the C +library's <b>fgets()</b> function, or via the <b>libreadline</b> library (see +below). In Unix-like environments, <b>fgets()</b> treats any bytes other than +newline as data characters. However, in some Windows environments character 26 +(hex 1A) causes an immediate end of file, and no further data is read. For +maximum portability, therefore, it is safest to use only ASCII characters in +<b>pcretest</b> input files. +</P> +<br><a name="SEC3" href="#TOC1">PCRE's 8-BIT, 16-BIT AND 32-BIT LIBRARIES</a><br> +<P> +From release 8.30, two separate PCRE libraries can be built. The original one +supports 8-bit character strings, whereas the newer 16-bit library supports +character strings encoded in 16-bit units. From release 8.32, a third library +can be built, supporting character strings encoded in 32-bit units. The +<b>pcretest</b> program can be used to test all three libraries. However, it is +itself still an 8-bit program, reading 8-bit input and writing 8-bit output. +When testing the 16-bit or 32-bit library, the patterns and data strings are +converted to 16- or 32-bit format before being passed to the PCRE library +functions. Results are converted to 8-bit for output. +</P> +<P> +References to functions and structures of the form <b>pcre[16|32]_xx</b> below +mean "<b>pcre_xx</b> when using the 8-bit library, <b>pcre16_xx</b> when using +the 16-bit library, or <b>pcre32_xx</b> when using the 32-bit library". +</P> +<br><a name="SEC4" href="#TOC1">COMMAND LINE OPTIONS</a><br> +<P> +<b>-8</b> +If both the 8-bit library has been built, this option causes the 8-bit library +to be used (which is the default); if the 8-bit library has not been built, +this option causes an error. +</P> +<P> +<b>-16</b> +If both the 8-bit or the 32-bit, and the 16-bit libraries have been built, this +option causes the 16-bit library to be used. If only the 16-bit library has been +built, this is the default (so has no effect). If only the 8-bit or the 32-bit +library has been built, this option causes an error. +</P> +<P> +<b>-32</b> +If both the 8-bit or the 16-bit, and the 32-bit libraries have been built, this +option causes the 32-bit library to be used. If only the 32-bit library has been +built, this is the default (so has no effect). If only the 8-bit or the 16-bit +library has been built, this option causes an error. +</P> +<P> +<b>-b</b> +Behave as if each pattern has the <b>/B</b> (show byte code) modifier; the +internal form is output after compilation. +</P> +<P> +<b>-C</b> +Output the version number of the PCRE library, and all available information +about the optional features that are included, and then exit with zero exit +code. All other options are ignored. +</P> +<P> +<b>-C</b> <i>option</i> +Output information about a specific build-time option, then exit. This +functionality is intended for use in scripts such as <b>RunTest</b>. The +following options output the value and set the exit code as indicated: +<pre> + ebcdic-nl the code for LF (= NL) in an EBCDIC environment: + 0x15 or 0x25 + 0 if used in an ASCII environment + exit code is always 0 + linksize the configured internal link size (2, 3, or 4) + exit code is set to the link size + newline the default newline setting: + CR, LF, CRLF, ANYCRLF, or ANY + exit code is always 0 + bsr the default setting for what \R matches: + ANYCRLF or ANY + exit code is always 0 +</pre> +The following options output 1 for true or 0 for false, and set the exit code +to the same value: +<pre> + ebcdic compiled for an EBCDIC environment + jit just-in-time support is available + pcre16 the 16-bit library was built + pcre32 the 32-bit library was built + pcre8 the 8-bit library was built + ucp Unicode property support is available + utf UTF-8 and/or UTF-16 and/or UTF-32 support + is available +</pre> +If an unknown option is given, an error message is output; the exit code is 0. +</P> +<P> +<b>-d</b> +Behave as if each pattern has the <b>/D</b> (debug) modifier; the internal +form and information about the compiled pattern is output after compilation; +<b>-d</b> is equivalent to <b>-b -i</b>. +</P> +<P> +<b>-dfa</b> +Behave as if each data line contains the \D escape sequence; this causes the +alternative matching function, <b>pcre[16|32]_dfa_exec()</b>, to be used instead +of the standard <b>pcre[16|32]_exec()</b> function (more detail is given below). +</P> +<P> +<b>-help</b> +Output a brief summary these options and then exit. +</P> +<P> +<b>-i</b> +Behave as if each pattern has the <b>/I</b> modifier; information about the +compiled pattern is given after compilation. +</P> +<P> +<b>-M</b> +Behave as if each data line contains the \M escape sequence; this causes +PCRE to discover the minimum MATCH_LIMIT and MATCH_LIMIT_RECURSION settings by +calling <b>pcre[16|32]_exec()</b> repeatedly with different limits. +</P> +<P> +<b>-m</b> +Output the size of each compiled pattern after it has been compiled. This is +equivalent to adding <b>/M</b> to each regular expression. The size is given in +bytes for both libraries. +</P> +<P> +<b>-O</b> +Behave as if each pattern has the <b>/O</b> modifier, that is disable +auto-possessification for all patterns. +</P> +<P> +<b>-o</b> <i>osize</i> +Set the number of elements in the output vector that is used when calling +<b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> to be <i>osize</i>. The +default value is 45, which is enough for 14 capturing subexpressions for +<b>pcre[16|32]_exec()</b> or 22 different matches for +<b>pcre[16|32]_dfa_exec()</b>. +The vector size can be changed for individual matching calls by including \O +in the data line (see below). +</P> +<P> +<b>-p</b> +Behave as if each pattern has the <b>/P</b> modifier; the POSIX wrapper API is +used to call PCRE. None of the other options has any effect when <b>-p</b> is +set. This option can be used only with the 8-bit library. +</P> +<P> +<b>-q</b> +Do not output the version number of <b>pcretest</b> at the start of execution. +</P> +<P> +<b>-S</b> <i>size</i> +On Unix-like systems, set the size of the run-time stack to <i>size</i> +megabytes. +</P> +<P> +<b>-s</b> or <b>-s+</b> +Behave as if each pattern has the <b>/S</b> modifier; in other words, force each +pattern to be studied. If <b>-s+</b> is used, all the JIT compile options are +passed to <b>pcre[16|32]_study()</b>, causing just-in-time optimization to be set +up if it is available, for both full and partial matching. Specific JIT compile +options can be selected by following <b>-s+</b> with a digit in the range 1 to +7, which selects the JIT compile modes as follows: +<pre> + 1 normal match only + 2 soft partial match only + 3 normal match and soft partial match + 4 hard partial match only + 6 soft and hard partial match + 7 all three modes (default) +</pre> +If <b>-s++</b> is used instead of <b>-s+</b> (with or without a following digit), +the text "(JIT)" is added to the first output line after a match or no match +when JIT-compiled code was actually used. +<br> +<br> +Note that there are pattern options that can override <b>-s</b>, either +specifying no studying at all, or suppressing JIT compilation. +<br> +<br> +If the <b>/I</b> or <b>/D</b> option is present on a pattern (requesting output +about the compiled pattern), information about the result of studying is not +included when studying is caused only by <b>-s</b> and neither <b>-i</b> nor +<b>-d</b> is present on the command line. This behaviour means that the output +from tests that are run with and without <b>-s</b> should be identical, except +when options that output information about the actual running of a match are +set. +<br> +<br> +The <b>-M</b>, <b>-t</b>, and <b>-tm</b> options, which give information about +resources used, are likely to produce different output with and without +<b>-s</b>. Output may also differ if the <b>/C</b> option is present on an +individual pattern. This uses callouts to trace the the matching process, and +this may be different between studied and non-studied patterns. If the pattern +contains (*MARK) items there may also be differences, for the same reason. The +<b>-s</b> command line option can be overridden for specific patterns that +should never be studied (see the <b>/S</b> pattern modifier below). +</P> +<P> +<b>-t</b> +Run each compile, study, and match many times with a timer, and output the +resulting times per compile, study, or match (in milliseconds). Do not set +<b>-m</b> with <b>-t</b>, because you will then get the size output a zillion +times, and the timing will be distorted. You can control the number of +iterations that are used for timing by following <b>-t</b> with a number (as a +separate item on the command line). For example, "-t 1000" iterates 1000 times. +The default is to iterate 500000 times. +</P> +<P> +<b>-tm</b> +This is like <b>-t</b> except that it times only the matching phase, not the +compile or study phases. +</P> +<P> +<b>-T</b> <b>-TM</b> +These behave like <b>-t</b> and <b>-tm</b>, but in addition, at the end of a run, +the total times for all compiles, studies, and matches are output. +</P> +<br><a name="SEC5" href="#TOC1">DESCRIPTION</a><br> +<P> +If <b>pcretest</b> is given two filename arguments, it reads from the first and +writes to the second. If it is given only one filename argument, it reads from +that file and writes to stdout. Otherwise, it reads from stdin and writes to +stdout, and prompts for each line of input, using "re>" to prompt for regular +expressions, and "data>" to prompt for data lines. +</P> +<P> +When <b>pcretest</b> is built, a configuration option can specify that it should +be linked with the <b>libreadline</b> library. When this is done, if the input +is from a terminal, it is read using the <b>readline()</b> function. This +provides line-editing and history facilities. The output from the <b>-help</b> +option states whether or not <b>readline()</b> will be used. +</P> +<P> +The program handles any number of sets of input on a single input file. Each +set starts with a regular expression, and continues with any number of data +lines to be matched against that pattern. +</P> +<P> +Each data line is matched separately and independently. If you want to do +multi-line matches, you have to use the \n escape sequence (or \r or \r\n, +etc., depending on the newline setting) in a single line of input to encode the +newline sequences. There is no limit on the length of data lines; the input +buffer is automatically extended if it is too small. +</P> +<P> +An empty line signals the end of the data lines, at which point a new regular +expression is read. The regular expressions are given enclosed in any +non-alphanumeric delimiters other than backslash, for example: +<pre> + /(a|bc)x+yz/ +</pre> +White space before the initial delimiter is ignored. A regular expression may +be continued over several input lines, in which case the newline characters are +included within it. It is possible to include the delimiter within the pattern +by escaping it, for example +<pre> + /abc\/def/ +</pre> +If you do so, the escape and the delimiter form part of the pattern, but since +delimiters are always non-alphanumeric, this does not affect its interpretation. +If the terminating delimiter is immediately followed by a backslash, for +example, +<pre> + /abc/\ +</pre> +then a backslash is added to the end of the pattern. This is done to provide a +way of testing the error condition that arises if a pattern finishes with a +backslash, because +<pre> + /abc\/ +</pre> +is interpreted as the first line of a pattern that starts with "abc/", causing +pcretest to read the next line as a continuation of the regular expression. +</P> +<br><a name="SEC6" href="#TOC1">PATTERN MODIFIERS</a><br> +<P> +A pattern may be followed by any number of modifiers, which are mostly single +characters, though some of these can be qualified by further characters. +Following Perl usage, these are referred to below as, for example, "the +<b>/i</b> modifier", even though the delimiter of the pattern need not always be +a slash, and no slash is used when writing modifiers. White space may appear +between the final pattern delimiter and the first modifier, and between the +modifiers themselves. For reference, here is a complete list of modifiers. They +fall into several groups that are described in detail in the following +sections. +<pre> + <b>/8</b> set UTF mode + <b>/9</b> set PCRE_NEVER_UTF (locks out UTF mode) + <b>/?</b> disable UTF validity check + <b>/+</b> show remainder of subject after match + <b>/=</b> show all captures (not just those that are set) + + <b>/A</b> set PCRE_ANCHORED + <b>/B</b> show compiled code + <b>/C</b> set PCRE_AUTO_CALLOUT + <b>/D</b> same as <b>/B</b> plus <b>/I</b> + <b>/E</b> set PCRE_DOLLAR_ENDONLY + <b>/F</b> flip byte order in compiled pattern + <b>/f</b> set PCRE_FIRSTLINE + <b>/G</b> find all matches (shorten string) + <b>/g</b> find all matches (use startoffset) + <b>/I</b> show information about pattern + <b>/i</b> set PCRE_CASELESS + <b>/J</b> set PCRE_DUPNAMES + <b>/K</b> show backtracking control names + <b>/L</b> set locale + <b>/M</b> show compiled memory size + <b>/m</b> set PCRE_MULTILINE + <b>/N</b> set PCRE_NO_AUTO_CAPTURE + <b>/O</b> set PCRE_NO_AUTO_POSSESS + <b>/P</b> use the POSIX wrapper + <b>/Q</b> test external stack check function + <b>/S</b> study the pattern after compilation + <b>/s</b> set PCRE_DOTALL + <b>/T</b> select character tables + <b>/U</b> set PCRE_UNGREEDY + <b>/W</b> set PCRE_UCP + <b>/X</b> set PCRE_EXTRA + <b>/x</b> set PCRE_EXTENDED + <b>/Y</b> set PCRE_NO_START_OPTIMIZE + <b>/Z</b> don't show lengths in <b>/B</b> output + + <b>/<any></b> set PCRE_NEWLINE_ANY + <b>/<anycrlf></b> set PCRE_NEWLINE_ANYCRLF + <b>/<cr></b> set PCRE_NEWLINE_CR + <b>/<crlf></b> set PCRE_NEWLINE_CRLF + <b>/<lf></b> set PCRE_NEWLINE_LF + <b>/<bsr_anycrlf></b> set PCRE_BSR_ANYCRLF + <b>/<bsr_unicode></b> set PCRE_BSR_UNICODE + <b>/<JS></b> set PCRE_JAVASCRIPT_COMPAT + +</PRE> +</P> +<br><b> +Perl-compatible modifiers +</b><br> +<P> +The <b>/i</b>, <b>/m</b>, <b>/s</b>, and <b>/x</b> modifiers set the PCRE_CASELESS, +PCRE_MULTILINE, PCRE_DOTALL, or PCRE_EXTENDED options, respectively, when +<b>pcre[16|32]_compile()</b> is called. These four modifier letters have the same +effect as they do in Perl. For example: +<pre> + /caseless/i + +</PRE> +</P> +<br><b> +Modifiers for other PCRE options +</b><br> +<P> +The following table shows additional modifiers for setting PCRE compile-time +options that do not correspond to anything in Perl: +<pre> + <b>/8</b> PCRE_UTF8 ) when using the 8-bit + <b>/?</b> PCRE_NO_UTF8_CHECK ) library + + <b>/8</b> PCRE_UTF16 ) when using the 16-bit + <b>/?</b> PCRE_NO_UTF16_CHECK ) library + + <b>/8</b> PCRE_UTF32 ) when using the 32-bit + <b>/?</b> PCRE_NO_UTF32_CHECK ) library + + <b>/9</b> PCRE_NEVER_UTF + <b>/A</b> PCRE_ANCHORED + <b>/C</b> PCRE_AUTO_CALLOUT + <b>/E</b> PCRE_DOLLAR_ENDONLY + <b>/f</b> PCRE_FIRSTLINE + <b>/J</b> PCRE_DUPNAMES + <b>/N</b> PCRE_NO_AUTO_CAPTURE + <b>/O</b> PCRE_NO_AUTO_POSSESS + <b>/U</b> PCRE_UNGREEDY + <b>/W</b> PCRE_UCP + <b>/X</b> PCRE_EXTRA + <b>/Y</b> PCRE_NO_START_OPTIMIZE + <b>/<any></b> PCRE_NEWLINE_ANY + <b>/<anycrlf></b> PCRE_NEWLINE_ANYCRLF + <b>/<cr></b> PCRE_NEWLINE_CR + <b>/<crlf></b> PCRE_NEWLINE_CRLF + <b>/<lf></b> PCRE_NEWLINE_LF + <b>/<bsr_anycrlf></b> PCRE_BSR_ANYCRLF + <b>/<bsr_unicode></b> PCRE_BSR_UNICODE + <b>/<JS></b> PCRE_JAVASCRIPT_COMPAT +</pre> +The modifiers that are enclosed in angle brackets are literal strings as shown, +including the angle brackets, but the letters within can be in either case. +This example sets multiline matching with CRLF as the line ending sequence: +<pre> + /^abc/m<CRLF> +</pre> +As well as turning on the PCRE_UTF8/16/32 option, the <b>/8</b> modifier causes +all non-printing characters in output strings to be printed using the +\x{hh...} notation. Otherwise, those less than 0x100 are output in hex without +the curly brackets. +</P> +<P> +Full details of the PCRE options are given in the +<a href="pcreapi.html"><b>pcreapi</b></a> +documentation. +</P> +<br><b> +Finding all matches in a string +</b><br> +<P> +Searching for all possible matches within each subject string can be requested +by the <b>/g</b> or <b>/G</b> modifier. After finding a match, PCRE is called +again to search the remainder of the subject string. The difference between +<b>/g</b> and <b>/G</b> is that the former uses the <i>startoffset</i> argument to +<b>pcre[16|32]_exec()</b> to start searching at a new point within the entire +string (which is in effect what Perl does), whereas the latter passes over a +shortened substring. This makes a difference to the matching process if the +pattern begins with a lookbehind assertion (including \b or \B). +</P> +<P> +If any call to <b>pcre[16|32]_exec()</b> in a <b>/g</b> or <b>/G</b> sequence matches +an empty string, the next call is done with the PCRE_NOTEMPTY_ATSTART and +PCRE_ANCHORED flags set in order to search for another, non-empty, match at the +same point. If this second match fails, the start offset is advanced, and the +normal match is retried. This imitates the way Perl handles such cases when +using the <b>/g</b> modifier or the <b>split()</b> function. Normally, the start +offset is advanced by one character, but if the newline convention recognizes +CRLF as a newline, and the current character is CR followed by LF, an advance +of two is used. +</P> +<br><b> +Other modifiers +</b><br> +<P> +There are yet more modifiers for controlling the way <b>pcretest</b> +operates. +</P> +<P> +The <b>/+</b> modifier requests that as well as outputting the substring that +matched the entire pattern, <b>pcretest</b> should in addition output the +remainder of the subject string. This is useful for tests where the subject +contains multiple copies of the same substring. If the <b>+</b> modifier appears +twice, the same action is taken for captured substrings. In each case the +remainder is output on the following line with a plus character following the +capture number. Note that this modifier must not immediately follow the /S +modifier because /S+ and /S++ have other meanings. +</P> +<P> +The <b>/=</b> modifier requests that the values of all potential captured +parentheses be output after a match. By default, only those up to the highest +one actually used in the match are output (corresponding to the return code +from <b>pcre[16|32]_exec()</b>). Values in the offsets vector corresponding to +higher numbers should be set to -1, and these are output as "<unset>". This +modifier gives a way of checking that this is happening. +</P> +<P> +The <b>/B</b> modifier is a debugging feature. It requests that <b>pcretest</b> +output a representation of the compiled code after compilation. Normally this +information contains length and offset values; however, if <b>/Z</b> is also +present, this data is replaced by spaces. This is a special feature for use in +the automatic test scripts; it ensures that the same output is generated for +different internal link sizes. +</P> +<P> +The <b>/D</b> modifier is a PCRE debugging feature, and is equivalent to +<b>/BI</b>, that is, both the <b>/B</b> and the <b>/I</b> modifiers. +</P> +<P> +The <b>/F</b> modifier causes <b>pcretest</b> to flip the byte order of the +2-byte and 4-byte fields in the compiled pattern. This facility is for testing +the feature in PCRE that allows it to execute patterns that were compiled on a +host with a different endianness. This feature is not available when the POSIX +interface to PCRE is being used, that is, when the <b>/P</b> pattern modifier is +specified. See also the section about saving and reloading compiled patterns +below. +</P> +<P> +The <b>/I</b> modifier requests that <b>pcretest</b> output information about the +compiled pattern (whether it is anchored, has a fixed first character, and +so on). It does this by calling <b>pcre[16|32]_fullinfo()</b> after compiling a +pattern. If the pattern is studied, the results of that are also output. In +this output, the word "char" means a non-UTF character, that is, the value of a +single data item (8-bit, 16-bit, or 32-bit, depending on the library that is +being tested). +</P> +<P> +The <b>/K</b> modifier requests <b>pcretest</b> to show names from backtracking +control verbs that are returned from calls to <b>pcre[16|32]_exec()</b>. It causes +<b>pcretest</b> to create a <b>pcre[16|32]_extra</b> block if one has not already +been created by a call to <b>pcre[16|32]_study()</b>, and to set the +PCRE_EXTRA_MARK flag and the <b>mark</b> field within it, every time that +<b>pcre[16|32]_exec()</b> is called. If the variable that the <b>mark</b> field +points to is non-NULL for a match, non-match, or partial match, <b>pcretest</b> +prints the string to which it points. For a match, this is shown on a line by +itself, tagged with "MK:". For a non-match it is added to the message. +</P> +<P> +The <b>/L</b> modifier must be followed directly by the name of a locale, for +example, +<pre> + /pattern/Lfr_FR +</pre> +For this reason, it must be the last modifier. The given locale is set, +<b>pcre[16|32]_maketables()</b> is called to build a set of character tables for +the locale, and this is then passed to <b>pcre[16|32]_compile()</b> when compiling +the regular expression. Without an <b>/L</b> (or <b>/T</b>) modifier, NULL is +passed as the tables pointer; that is, <b>/L</b> applies only to the expression +on which it appears. +</P> +<P> +The <b>/M</b> modifier causes the size in bytes of the memory block used to hold +the compiled pattern to be output. This does not include the size of the +<b>pcre[16|32]</b> block; it is just the actual compiled data. If the pattern is +successfully studied with the PCRE_STUDY_JIT_COMPILE option, the size of the +JIT compiled code is also output. +</P> +<P> +The <b>/Q</b> modifier is used to test the use of <b>pcre_stack_guard</b>. It +must be followed by '0' or '1', specifying the return code to be given from an +external function that is passed to PCRE and used for stack checking during +compilation (see the +<a href="pcreapi.html"><b>pcreapi</b></a> +documentation for details). +</P> +<P> +The <b>/S</b> modifier causes <b>pcre[16|32]_study()</b> to be called after the +expression has been compiled, and the results used when the expression is +matched. There are a number of qualifying characters that may follow <b>/S</b>. +They may appear in any order. +</P> +<P> +If <b>/S</b> is followed by an exclamation mark, <b>pcre[16|32]_study()</b> is +called with the PCRE_STUDY_EXTRA_NEEDED option, causing it always to return a +<b>pcre_extra</b> block, even when studying discovers no useful information. +</P> +<P> +If <b>/S</b> is followed by a second S character, it suppresses studying, even +if it was requested externally by the <b>-s</b> command line option. This makes +it possible to specify that certain patterns are always studied, and others are +never studied, independently of <b>-s</b>. This feature is used in the test +files in a few cases where the output is different when the pattern is studied. +</P> +<P> +If the <b>/S</b> modifier is followed by a + character, the call to +<b>pcre[16|32]_study()</b> is made with all the JIT study options, requesting +just-in-time optimization support if it is available, for both normal and +partial matching. If you want to restrict the JIT compiling modes, you can +follow <b>/S+</b> with a digit in the range 1 to 7: +<pre> + 1 normal match only + 2 soft partial match only + 3 normal match and soft partial match + 4 hard partial match only + 6 soft and hard partial match + 7 all three modes (default) +</pre> +If <b>/S++</b> is used instead of <b>/S+</b> (with or without a following digit), +the text "(JIT)" is added to the first output line after a match or no match +when JIT-compiled code was actually used. +</P> +<P> +Note that there is also an independent <b>/+</b> modifier; it must not be given +immediately after <b>/S</b> or <b>/S+</b> because this will be misinterpreted. +</P> +<P> +If JIT studying is successful, the compiled JIT code will automatically be used +when <b>pcre[16|32]_exec()</b> is run, except when incompatible run-time options +are specified. For more details, see the +<a href="pcrejit.html"><b>pcrejit</b></a> +documentation. See also the <b>\J</b> escape sequence below for a way of +setting the size of the JIT stack. +</P> +<P> +Finally, if <b>/S</b> is followed by a minus character, JIT compilation is +suppressed, even if it was requested externally by the <b>-s</b> command line +option. This makes it possible to specify that JIT is never to be used for +certain patterns. +</P> +<P> +The <b>/T</b> modifier must be followed by a single digit. It causes a specific +set of built-in character tables to be passed to <b>pcre[16|32]_compile()</b>. It +is used in the standard PCRE tests to check behaviour with different character +tables. The digit specifies the tables as follows: +<pre> + 0 the default ASCII tables, as distributed in + pcre_chartables.c.dist + 1 a set of tables defining ISO 8859 characters +</pre> +In table 1, some characters whose codes are greater than 128 are identified as +letters, digits, spaces, etc. +</P> +<br><b> +Using the POSIX wrapper API +</b><br> +<P> +The <b>/P</b> modifier causes <b>pcretest</b> to call PCRE via the POSIX wrapper +API rather than its native API. This supports only the 8-bit library. When +<b>/P</b> is set, the following modifiers set options for the <b>regcomp()</b> +function: +<pre> + /i REG_ICASE + /m REG_NEWLINE + /N REG_NOSUB + /s REG_DOTALL ) + /U REG_UNGREEDY ) These options are not part of + /W REG_UCP ) the POSIX standard + /8 REG_UTF8 ) +</pre> +The <b>/+</b> modifier works as described above. All other modifiers are +ignored. +</P> +<br><b> +Locking out certain modifiers +</b><br> +<P> +PCRE can be compiled with or without support for certain features such as +UTF-8/16/32 or Unicode properties. Accordingly, the standard tests are split up +into a number of different files that are selected for running depending on +which features are available. When updating the tests, it is all too easy to +put a new test into the wrong file by mistake; for example, to put a test that +requires UTF support into a file that is used when it is not available. To help +detect such mistakes as early as possible, there is a facility for locking out +specific modifiers. If an input line for <b>pcretest</b> starts with the string +"< forbid " the following sequence of characters is taken as a list of +forbidden modifiers. For example, in the test files that must not use UTF or +Unicode property support, this line appears: +<pre> + < forbid 8W +</pre> +This locks out the /8 and /W modifiers. An immediate error is given if they are +subsequently encountered. If the character string contains < but not >, all the +multi-character modifiers that begin with < are locked out. Otherwise, such +modifiers must be explicitly listed, for example: +<pre> + < forbid <JS><cr> +</pre> +There must be a single space between < and "forbid" for this feature to be +recognised. If there is not, the line is interpreted either as a request to +re-load a pre-compiled pattern (see "SAVING AND RELOADING COMPILED PATTERNS" +below) or, if there is a another < character, as a pattern that uses < as its +delimiter. +</P> +<br><a name="SEC7" href="#TOC1">DATA LINES</a><br> +<P> +Before each data line is passed to <b>pcre[16|32]_exec()</b>, leading and trailing +white space is removed, and it is then scanned for \ escapes. Some of these +are pretty esoteric features, intended for checking out some of the more +complicated features of PCRE. If you are just testing "ordinary" regular +expressions, you probably don't need any of these. The following escapes are +recognized: +<pre> + \a alarm (BEL, \x07) + \b backspace (\x08) + \e escape (\x27) + \f form feed (\x0c) + \n newline (\x0a) + \qdd set the PCRE_MATCH_LIMIT limit to dd (any number of digits) + \r carriage return (\x0d) + \t tab (\x09) + \v vertical tab (\x0b) + \nnn octal character (up to 3 octal digits); always + a byte unless > 255 in UTF-8 or 16-bit or 32-bit mode + \o{dd...} octal character (any number of octal digits} + \xhh hexadecimal byte (up to 2 hex digits) + \x{hh...} hexadecimal character (any number of hex digits) + \A pass the PCRE_ANCHORED option to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> + \B pass the PCRE_NOTBOL option to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> + \Cdd call pcre[16|32]_copy_substring() for substring dd after a successful match (number less than 32) + \Cname call pcre[16|32]_copy_named_substring() for substring "name" after a successful match (name termin- + ated by next non alphanumeric character) + \C+ show the current captured substrings at callout time + \C- do not supply a callout function + \C!n return 1 instead of 0 when callout number n is reached + \C!n!m return 1 instead of 0 when callout number n is reached for the nth time + \C*n pass the number n (may be negative) as callout data; this is used as the callout return value + \D use the <b>pcre[16|32]_dfa_exec()</b> match function + \F only shortest match for <b>pcre[16|32]_dfa_exec()</b> + \Gdd call pcre[16|32]_get_substring() for substring dd after a successful match (number less than 32) + \Gname call pcre[16|32]_get_named_substring() for substring "name" after a successful match (name termin- + ated by next non-alphanumeric character) + \Jdd set up a JIT stack of dd kilobytes maximum (any number of digits) + \L call pcre[16|32]_get_substringlist() after a successful match + \M discover the minimum MATCH_LIMIT and MATCH_LIMIT_RECURSION settings + \N pass the PCRE_NOTEMPTY option to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b>; if used twice, pass the + PCRE_NOTEMPTY_ATSTART option + \Odd set the size of the output vector passed to <b>pcre[16|32]_exec()</b> to dd (any number of digits) + \P pass the PCRE_PARTIAL_SOFT option to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b>; if used twice, pass the + PCRE_PARTIAL_HARD option + \Qdd set the PCRE_MATCH_LIMIT_RECURSION limit to dd (any number of digits) + \R pass the PCRE_DFA_RESTART option to <b>pcre[16|32]_dfa_exec()</b> + \S output details of memory get/free calls during matching + \Y pass the PCRE_NO_START_OPTIMIZE option to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> + \Z pass the PCRE_NOTEOL option to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> + \? pass the PCRE_NO_UTF[8|16|32]_CHECK option to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> + \>dd start the match at offset dd (optional "-"; then any number of digits); this sets the <i>startoffset</i> + argument for <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> + \<cr> pass the PCRE_NEWLINE_CR option to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> + \<lf> pass the PCRE_NEWLINE_LF option to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> + \<crlf> pass the PCRE_NEWLINE_CRLF option to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> + \<anycrlf> pass the PCRE_NEWLINE_ANYCRLF option to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> + \<any> pass the PCRE_NEWLINE_ANY option to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> +</pre> +The use of \x{hh...} is not dependent on the use of the <b>/8</b> modifier on +the pattern. It is recognized always. There may be any number of hexadecimal +digits inside the braces; invalid values provoke error messages. +</P> +<P> +Note that \xhh specifies one byte rather than one character in UTF-8 mode; +this makes it possible to construct invalid UTF-8 sequences for testing +purposes. On the other hand, \x{hh} is interpreted as a UTF-8 character in +UTF-8 mode, generating more than one byte if the value is greater than 127. +When testing the 8-bit library not in UTF-8 mode, \x{hh} generates one byte +for values less than 256, and causes an error for greater values. +</P> +<P> +In UTF-16 mode, all 4-digit \x{hhhh} values are accepted. This makes it +possible to construct invalid UTF-16 sequences for testing purposes. +</P> +<P> +In UTF-32 mode, all 4- to 8-digit \x{...} values are accepted. This makes it +possible to construct invalid UTF-32 sequences for testing purposes. +</P> +<P> +The escapes that specify line ending sequences are literal strings, exactly as +shown. No more than one newline setting should be present in any data line. +</P> +<P> +A backslash followed by anything else just escapes the anything else. If +the very last character is a backslash, it is ignored. This gives a way of +passing an empty line as data, since a real empty line terminates the data +input. +</P> +<P> +The <b>\J</b> escape provides a way of setting the maximum stack size that is +used by the just-in-time optimization code. It is ignored if JIT optimization +is not being used. Providing a stack that is larger than the default 32K is +necessary only for very complicated patterns. +</P> +<P> +If \M is present, <b>pcretest</b> calls <b>pcre[16|32]_exec()</b> several times, +with different values in the <i>match_limit</i> and <i>match_limit_recursion</i> +fields of the <b>pcre[16|32]_extra</b> data structure, until it finds the minimum +numbers for each parameter that allow <b>pcre[16|32]_exec()</b> to complete without +error. Because this is testing a specific feature of the normal interpretive +<b>pcre[16|32]_exec()</b> execution, the use of any JIT optimization that might +have been set up by the <b>/S+</b> qualifier of <b>-s+</b> option is disabled. +</P> +<P> +The <i>match_limit</i> number is a measure of the amount of backtracking +that takes place, and checking it out can be instructive. For most simple +matches, the number is quite small, but for patterns with very large numbers of +matching possibilities, it can become large very quickly with increasing length +of subject string. The <i>match_limit_recursion</i> number is a measure of how +much stack (or, if PCRE is compiled with NO_RECURSE, how much heap) memory is +needed to complete the match attempt. +</P> +<P> +When \O is used, the value specified may be higher or lower than the size set +by the <b>-O</b> command line option (or defaulted to 45); \O applies only to +the call of <b>pcre[16|32]_exec()</b> for the line in which it appears. +</P> +<P> +If the <b>/P</b> modifier was present on the pattern, causing the POSIX wrapper +API to be used, the only option-setting sequences that have any effect are \B, +\N, and \Z, causing REG_NOTBOL, REG_NOTEMPTY, and REG_NOTEOL, respectively, +to be passed to <b>regexec()</b>. +</P> +<br><a name="SEC8" href="#TOC1">THE ALTERNATIVE MATCHING FUNCTION</a><br> +<P> +By default, <b>pcretest</b> uses the standard PCRE matching function, +<b>pcre[16|32]_exec()</b> to match each data line. PCRE also supports an +alternative matching function, <b>pcre[16|32]_dfa_test()</b>, which operates in a +different way, and has some restrictions. The differences between the two +functions are described in the +<a href="pcrematching.html"><b>pcrematching</b></a> +documentation. +</P> +<P> +If a data line contains the \D escape sequence, or if the command line +contains the <b>-dfa</b> option, the alternative matching function is used. +This function finds all possible matches at a given point. If, however, the \F +escape sequence is present in the data line, it stops after the first match is +found. This is always the shortest possible match. +</P> +<br><a name="SEC9" href="#TOC1">DEFAULT OUTPUT FROM PCRETEST</a><br> +<P> +This section describes the output when the normal matching function, +<b>pcre[16|32]_exec()</b>, is being used. +</P> +<P> +When a match succeeds, <b>pcretest</b> outputs the list of captured substrings +that <b>pcre[16|32]_exec()</b> returns, starting with number 0 for the string that +matched the whole pattern. Otherwise, it outputs "No match" when the return is +PCRE_ERROR_NOMATCH, and "Partial match:" followed by the partially matching +substring when <b>pcre[16|32]_exec()</b> returns PCRE_ERROR_PARTIAL. (Note that +this is the entire substring that was inspected during the partial match; it +may include characters before the actual match start if a lookbehind assertion, +\K, \b, or \B was involved.) For any other return, <b>pcretest</b> outputs +the PCRE negative error number and a short descriptive phrase. If the error is +a failed UTF string check, the offset of the start of the failing character and +the reason code are also output, provided that the size of the output vector is +at least two. Here is an example of an interactive <b>pcretest</b> run. +<pre> + $ pcretest + PCRE version 8.13 2011-04-30 + + re> /^abc(\d+)/ + data> abc123 + 0: abc123 + 1: 123 + data> xyz + No match +</pre> +Unset capturing substrings that are not followed by one that is set are not +returned by <b>pcre[16|32]_exec()</b>, and are not shown by <b>pcretest</b>. In the +following example, there are two capturing substrings, but when the first data +line is matched, the second, unset substring is not shown. An "internal" unset +substring is shown as "<unset>", as for the second data line. +<pre> + re> /(a)|(b)/ + data> a + 0: a + 1: a + data> b + 0: b + 1: <unset> + 2: b +</pre> +If the strings contain any non-printing characters, they are output as \xhh +escapes if the value is less than 256 and UTF mode is not set. Otherwise they +are output as \x{hh...} escapes. See below for the definition of non-printing +characters. If the pattern has the <b>/+</b> modifier, the output for substring +0 is followed by the the rest of the subject string, identified by "0+" like +this: +<pre> + re> /cat/+ + data> cataract + 0: cat + 0+ aract +</pre> +If the pattern has the <b>/g</b> or <b>/G</b> modifier, the results of successive +matching attempts are output in sequence, like this: +<pre> + re> /\Bi(\w\w)/g + data> Mississippi + 0: iss + 1: ss + 0: iss + 1: ss + 0: ipp + 1: pp +</pre> +"No match" is output only if the first match attempt fails. Here is an example +of a failure message (the offset 4 that is specified by \>4 is past the end of +the subject string): +<pre> + re> /xyz/ + data> xyz\>4 + Error -24 (bad offset value) +</PRE> +</P> +<P> +If any of the sequences <b>\C</b>, <b>\G</b>, or <b>\L</b> are present in a +data line that is successfully matched, the substrings extracted by the +convenience functions are output with C, G, or L after the string number +instead of a colon. This is in addition to the normal full list. The string +length (that is, the return from the extraction function) is given in +parentheses after each string for <b>\C</b> and <b>\G</b>. +</P> +<P> +Note that whereas patterns can be continued over several lines (a plain ">" +prompt is used for continuations), data lines may not. However newlines can be +included in data by means of the \n escape (or \r, \r\n, etc., depending on +the newline sequence setting). +</P> +<br><a name="SEC10" href="#TOC1">OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION</a><br> +<P> +When the alternative matching function, <b>pcre[16|32]_dfa_exec()</b>, is used (by +means of the \D escape sequence or the <b>-dfa</b> command line option), the +output consists of a list of all the matches that start at the first point in +the subject where there is at least one match. For example: +<pre> + re> /(tang|tangerine|tan)/ + data> yellow tangerine\D + 0: tangerine + 1: tang + 2: tan +</pre> +(Using the normal matching function on this data finds only "tang".) The +longest matching string is always given first (and numbered zero). After a +PCRE_ERROR_PARTIAL return, the output is "Partial match:", followed by the +partially matching substring. (Note that this is the entire substring that was +inspected during the partial match; it may include characters before the actual +match start if a lookbehind assertion, \K, \b, or \B was involved.) +</P> +<P> +If <b>/g</b> is present on the pattern, the search for further matches resumes +at the end of the longest match. For example: +<pre> + re> /(tang|tangerine|tan)/g + data> yellow tangerine and tangy sultana\D + 0: tangerine + 1: tang + 2: tan + 0: tang + 1: tan + 0: tan +</pre> +Since the matching function does not support substring capture, the escape +sequences that are concerned with captured substrings are not relevant. +</P> +<br><a name="SEC11" href="#TOC1">RESTARTING AFTER A PARTIAL MATCH</a><br> +<P> +When the alternative matching function has given the PCRE_ERROR_PARTIAL return, +indicating that the subject partially matched the pattern, you can restart the +match with additional subject data by means of the \R escape sequence. For +example: +<pre> + re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ + data> 23ja\P\D + Partial match: 23ja + data> n05\R\D + 0: n05 +</pre> +For further information about partial matching, see the +<a href="pcrepartial.html"><b>pcrepartial</b></a> +documentation. +</P> +<br><a name="SEC12" href="#TOC1">CALLOUTS</a><br> +<P> +If the pattern contains any callout requests, <b>pcretest</b>'s callout function +is called during matching. This works with both matching functions. By default, +the called function displays the callout number, the start and current +positions in the text at the callout time, and the next pattern item to be +tested. For example: +<pre> + --->pqrabcdef + 0 ^ ^ \d +</pre> +This output indicates that callout number 0 occurred for a match attempt +starting at the fourth character of the subject string, when the pointer was at +the seventh character of the data, and when the next pattern item was \d. Just +one circumflex is output if the start and current positions are the same. +</P> +<P> +Callouts numbered 255 are assumed to be automatic callouts, inserted as a +result of the <b>/C</b> pattern modifier. In this case, instead of showing the +callout number, the offset in the pattern, preceded by a plus, is output. For +example: +<pre> + re> /\d?[A-E]\*/C + data> E* + --->E* + +0 ^ \d? + +3 ^ [A-E] + +8 ^^ \* + +10 ^ ^ + 0: E* +</pre> +If a pattern contains (*MARK) items, an additional line is output whenever +a change of latest mark is passed to the callout function. For example: +<pre> + re> /a(*MARK:X)bc/C + data> abc + --->abc + +0 ^ a + +1 ^^ (*MARK:X) + +10 ^^ b + Latest Mark: X + +11 ^ ^ c + +12 ^ ^ + 0: abc +</pre> +The mark changes between matching "a" and "b", but stays the same for the rest +of the match, so nothing more is output. If, as a result of backtracking, the +mark reverts to being unset, the text "<unset>" is output. +</P> +<P> +The callout function in <b>pcretest</b> returns zero (carry on matching) by +default, but you can use a \C item in a data line (as described above) to +change this and other parameters of the callout. +</P> +<P> +Inserting callouts can be helpful when using <b>pcretest</b> to check +complicated regular expressions. For further information about callouts, see +the +<a href="pcrecallout.html"><b>pcrecallout</b></a> +documentation. +</P> +<br><a name="SEC13" href="#TOC1">NON-PRINTING CHARACTERS</a><br> +<P> +When <b>pcretest</b> is outputting text in the compiled version of a pattern, +bytes other than 32-126 are always treated as non-printing characters are are +therefore shown as hex escapes. +</P> +<P> +When <b>pcretest</b> is outputting text that is a matched part of a subject +string, it behaves in the same way, unless a different locale has been set for +the pattern (using the <b>/L</b> modifier). In this case, the <b>isprint()</b> +function to distinguish printing and non-printing characters. +</P> +<br><a name="SEC14" href="#TOC1">SAVING AND RELOADING COMPILED PATTERNS</a><br> +<P> +The facilities described in this section are not available when the POSIX +interface to PCRE is being used, that is, when the <b>/P</b> pattern modifier is +specified. +</P> +<P> +When the POSIX interface is not in use, you can cause <b>pcretest</b> to write a +compiled pattern to a file, by following the modifiers with > and a file name. +For example: +<pre> + /pattern/im >/some/file +</pre> +See the +<a href="pcreprecompile.html"><b>pcreprecompile</b></a> +documentation for a discussion about saving and re-using compiled patterns. +Note that if the pattern was successfully studied with JIT optimization, the +JIT data cannot be saved. +</P> +<P> +The data that is written is binary. The first eight bytes are the length of the +compiled pattern data followed by the length of the optional study data, each +written as four bytes in big-endian order (most significant byte first). If +there is no study data (either the pattern was not studied, or studying did not +return any data), the second length is zero. The lengths are followed by an +exact copy of the compiled pattern. If there is additional study data, this +(excluding any JIT data) follows immediately after the compiled pattern. After +writing the file, <b>pcretest</b> expects to read a new pattern. +</P> +<P> +A saved pattern can be reloaded into <b>pcretest</b> by specifying < and a file +name instead of a pattern. There must be no space between < and the file name, +which must not contain a < character, as otherwise <b>pcretest</b> will +interpret the line as a pattern delimited by < characters. For example: +<pre> + re> </some/file + Compiled pattern loaded from /some/file + No study data +</pre> +If the pattern was previously studied with the JIT optimization, the JIT +information cannot be saved and restored, and so is lost. When the pattern has +been loaded, <b>pcretest</b> proceeds to read data lines in the usual way. +</P> +<P> +You can copy a file written by <b>pcretest</b> to a different host and reload it +there, even if the new host has opposite endianness to the one on which the +pattern was compiled. For example, you can compile on an i86 machine and run on +a SPARC machine. When a pattern is reloaded on a host with different +endianness, the confirmation message is changed to: +<pre> + Compiled pattern (byte-inverted) loaded from /some/file +</pre> +The test suite contains some saved pre-compiled patterns with different +endianness. These are reloaded using "<!" instead of just "<". This suppresses +the "(byte-inverted)" text so that the output is the same on all hosts. It also +forces debugging output once the pattern has been reloaded. +</P> +<P> +File names for saving and reloading can be absolute or relative, but note that +the shell facility of expanding a file name that starts with a tilde (~) is not +available. +</P> +<P> +The ability to save and reload files in <b>pcretest</b> is intended for testing +and experimentation. It is not intended for production use because only a +single pattern can be written to a file. Furthermore, there is no facility for +supplying custom character tables for use with a reloaded pattern. If the +original pattern was compiled with custom tables, an attempt to match a subject +string using a reloaded pattern is likely to cause <b>pcretest</b> to crash. +Finally, if you attempt to load a file that is not in the correct format, the +result is undefined. +</P> +<br><a name="SEC15" href="#TOC1">SEE ALSO</a><br> +<P> +<b>pcre</b>(3), <b>pcre16</b>(3), <b>pcre32</b>(3), <b>pcreapi</b>(3), +<b>pcrecallout</b>(3), +<b>pcrejit</b>, <b>pcrematching</b>(3), <b>pcrepartial</b>(d), +<b>pcrepattern</b>(3), <b>pcreprecompile</b>(3). +</P> +<br><a name="SEC16" href="#TOC1">AUTHOR</a><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><a name="SEC17" href="#TOC1">REVISION</a><br> +<P> +Last updated: 09 February 2014 +<br> +Copyright © 1997-2014 University of Cambridge. +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/html/pcreunicode.html b/plugins/Pcre16/docs/doc/html/pcreunicode.html new file mode 100644 index 0000000000..ab36bc61e3 --- /dev/null +++ b/plugins/Pcre16/docs/doc/html/pcreunicode.html @@ -0,0 +1,262 @@ +<html> +<head> +<title>pcreunicode specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcreunicode man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +UTF-8, UTF-16, UTF-32, AND UNICODE PROPERTY SUPPORT +</b><br> +<P> +As well as UTF-8 support, PCRE also supports UTF-16 (from release 8.30) and +UTF-32 (from release 8.32), by means of two additional libraries. They can be +built as well as, or instead of, the 8-bit library. +</P> +<br><b> +UTF-8 SUPPORT +</b><br> +<P> +In order process UTF-8 strings, you must build PCRE's 8-bit library with UTF +support, and, in addition, you must call +<a href="pcre_compile.html"><b>pcre_compile()</b></a> +with the PCRE_UTF8 option flag, or the pattern must start with the sequence +(*UTF8) or (*UTF). When either of these is the case, both the pattern and any +subject strings that are matched against it are treated as UTF-8 strings +instead of strings of individual 1-byte characters. +</P> +<br><b> +UTF-16 AND UTF-32 SUPPORT +</b><br> +<P> +In order process UTF-16 or UTF-32 strings, you must build PCRE's 16-bit or +32-bit library with UTF support, and, in addition, you must call +<a href="pcre16_compile.html"><b>pcre16_compile()</b></a> +or +<a href="pcre32_compile.html"><b>pcre32_compile()</b></a> +with the PCRE_UTF16 or PCRE_UTF32 option flag, as appropriate. Alternatively, +the pattern must start with the sequence (*UTF16), (*UTF32), as appropriate, or +(*UTF), which can be used with either library. When UTF mode is set, both the +pattern and any subject strings that are matched against it are treated as +UTF-16 or UTF-32 strings instead of strings of individual 16-bit or 32-bit +characters. +</P> +<br><b> +UTF SUPPORT OVERHEAD +</b><br> +<P> +If you compile PCRE with UTF support, but do not use it at run time, the +library will be a bit bigger, but the additional run time overhead is limited +to testing the PCRE_UTF[8|16|32] flag occasionally, so should not be very big. +</P> +<br><b> +UNICODE PROPERTY SUPPORT +</b><br> +<P> +If PCRE is built with Unicode character property support (which implies UTF +support), the escape sequences \p{..}, \P{..}, and \X can be used. +The available properties that can be tested are limited to the general +category properties such as Lu for an upper case letter or Nd for a decimal +number, the Unicode script names such as Arabic or Han, and the derived +properties Any and L&. Full lists is given in the +<a href="pcrepattern.html"><b>pcrepattern</b></a> +and +<a href="pcresyntax.html"><b>pcresyntax</b></a> +documentation. Only the short names for properties are supported. For example, +\p{L} matches a letter. Its Perl synonym, \p{Letter}, is not supported. +Furthermore, in Perl, many properties may optionally be prefixed by "Is", for +compatibility with Perl 5.6. PCRE does not support this. +<a name="utf8strings"></a></P> +<br><b> +Validity of UTF-8 strings +</b><br> +<P> +When you set the PCRE_UTF8 flag, the byte strings passed as patterns and +subjects are (by default) checked for validity on entry to the relevant +functions. The entire string is checked before any other processing takes +place. From release 7.3 of PCRE, the check is according the rules of RFC 3629, +which are themselves derived from the Unicode specification. Earlier releases +of PCRE followed the rules of RFC 2279, which allows the full range of 31-bit +values (0 to 0x7FFFFFFF). The current check allows only values in the range U+0 +to U+10FFFF, excluding the surrogate area. (From release 8.33 the so-called +"non-character" code points are no longer excluded because Unicode corrigendum +#9 makes it clear that they should not be.) +</P> +<P> +Characters in the "Surrogate Area" of Unicode are reserved for use by UTF-16, +where they are used in pairs to encode codepoints with values greater than +0xFFFF. The code points that are encoded by UTF-16 pairs are available +independently in the UTF-8 and UTF-32 encodings. (In other words, the whole +surrogate thing is a fudge for UTF-16 which unfortunately messes up UTF-8 and +UTF-32.) +</P> +<P> +If an invalid UTF-8 string is passed to PCRE, an error return is given. At +compile time, the only additional information is the offset to the first byte +of the failing character. The run-time functions <b>pcre_exec()</b> and +<b>pcre_dfa_exec()</b> also pass back this information, as well as a more +detailed reason code if the caller has provided memory in which to do this. +</P> +<P> +In some situations, you may already know that your strings are valid, and +therefore want to skip these checks in order to improve performance, for +example in the case of a long subject string that is being scanned repeatedly. +If you set the PCRE_NO_UTF8_CHECK flag at compile time or at run time, PCRE +assumes that the pattern or subject it is given (respectively) contains only +valid UTF-8 codes. In this case, it does not diagnose an invalid UTF-8 string. +</P> +<P> +Note that passing PCRE_NO_UTF8_CHECK to <b>pcre_compile()</b> just disables the +check for the pattern; it does not also apply to subject strings. If you want +to disable the check for a subject string you must pass this option to +<b>pcre_exec()</b> or <b>pcre_dfa_exec()</b>. +</P> +<P> +If you pass an invalid UTF-8 string when PCRE_NO_UTF8_CHECK is set, the result +is undefined and your program may crash. +<a name="utf16strings"></a></P> +<br><b> +Validity of UTF-16 strings +</b><br> +<P> +When you set the PCRE_UTF16 flag, the strings of 16-bit data units that are +passed as patterns and subjects are (by default) checked for validity on entry +to the relevant functions. Values other than those in the surrogate range +U+D800 to U+DFFF are independent code points. Values in the surrogate range +must be used in pairs in the correct manner. +</P> +<P> +If an invalid UTF-16 string is passed to PCRE, an error return is given. At +compile time, the only additional information is the offset to the first data +unit of the failing character. The run-time functions <b>pcre16_exec()</b> and +<b>pcre16_dfa_exec()</b> also pass back this information, as well as a more +detailed reason code if the caller has provided memory in which to do this. +</P> +<P> +In some situations, you may already know that your strings are valid, and +therefore want to skip these checks in order to improve performance. If you set +the PCRE_NO_UTF16_CHECK flag at compile time or at run time, PCRE assumes that +the pattern or subject it is given (respectively) contains only valid UTF-16 +sequences. In this case, it does not diagnose an invalid UTF-16 string. +However, if an invalid string is passed, the result is undefined. +<a name="utf32strings"></a></P> +<br><b> +Validity of UTF-32 strings +</b><br> +<P> +When you set the PCRE_UTF32 flag, the strings of 32-bit data units that are +passed as patterns and subjects are (by default) checked for validity on entry +to the relevant functions. This check allows only values in the range U+0 +to U+10FFFF, excluding the surrogate area U+D800 to U+DFFF. +</P> +<P> +If an invalid UTF-32 string is passed to PCRE, an error return is given. At +compile time, the only additional information is the offset to the first data +unit of the failing character. The run-time functions <b>pcre32_exec()</b> and +<b>pcre32_dfa_exec()</b> also pass back this information, as well as a more +detailed reason code if the caller has provided memory in which to do this. +</P> +<P> +In some situations, you may already know that your strings are valid, and +therefore want to skip these checks in order to improve performance. If you set +the PCRE_NO_UTF32_CHECK flag at compile time or at run time, PCRE assumes that +the pattern or subject it is given (respectively) contains only valid UTF-32 +sequences. In this case, it does not diagnose an invalid UTF-32 string. +However, if an invalid string is passed, the result is undefined. +</P> +<br><b> +General comments about UTF modes +</b><br> +<P> +1. Codepoints less than 256 can be specified in patterns by either braced or +unbraced hexadecimal escape sequences (for example, \x{b3} or \xb3). Larger +values have to use braced sequences. +</P> +<P> +2. Octal numbers up to \777 are recognized, and in UTF-8 mode they match +two-byte characters for values greater than \177. +</P> +<P> +3. Repeat quantifiers apply to complete UTF characters, not to individual +data units, for example: \x{100}{3}. +</P> +<P> +4. The dot metacharacter matches one UTF character instead of a single data +unit. +</P> +<P> +5. The escape sequence \C can be used to match a single byte in UTF-8 mode, or +a single 16-bit data unit in UTF-16 mode, or a single 32-bit data unit in +UTF-32 mode, but its use can lead to some strange effects because it breaks up +multi-unit characters (see the description of \C in the +<a href="pcrepattern.html"><b>pcrepattern</b></a> +documentation). The use of \C is not supported in the alternative matching +function <b>pcre[16|32]_dfa_exec()</b>, nor is it supported in UTF mode by the +JIT optimization of <b>pcre[16|32]_exec()</b>. If JIT optimization is requested +for a UTF pattern that contains \C, it will not succeed, and so the matching +will be carried out by the normal interpretive function. +</P> +<P> +6. The character escapes \b, \B, \d, \D, \s, \S, \w, and \W correctly +test characters of any code value, but, by default, the characters that PCRE +recognizes as digits, spaces, or word characters remain the same set as in +non-UTF mode, all with values less than 256. This remains true even when PCRE +is built to include Unicode property support, because to do otherwise would +slow down PCRE in many common cases. Note in particular that this applies to +\b and \B, because they are defined in terms of \w and \W. If you really +want to test for a wider sense of, say, "digit", you can use explicit Unicode +property tests such as \p{Nd}. Alternatively, if you set the PCRE_UCP option, +the way that the character escapes work is changed so that Unicode properties +are used to determine which characters match. There are more details in the +section on +<a href="pcrepattern.html#genericchartypes">generic character types</a> +in the +<a href="pcrepattern.html"><b>pcrepattern</b></a> +documentation. +</P> +<P> +7. Similarly, characters that match the POSIX named character classes are all +low-valued characters, unless the PCRE_UCP option is set. +</P> +<P> +8. However, the horizontal and vertical white space matching escapes (\h, \H, +\v, and \V) do match all the appropriate Unicode characters, whether or not +PCRE_UCP is set. +</P> +<P> +9. Case-insensitive matching applies only to characters whose values are less +than 128, unless PCRE is built with Unicode property support. A few Unicode +characters such as Greek sigma have more than two codepoints that are +case-equivalent. Up to and including PCRE release 8.31, only one-to-one case +mappings were supported, but later releases (with Unicode property support) do +treat as case-equivalent all versions of characters such as Greek sigma. +</P> +<br><b> +AUTHOR +</b><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><b> +REVISION +</b><br> +<P> +Last updated: 27 February 2013 +<br> +Copyright © 1997-2013 University of Cambridge. +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/plugins/Pcre16/docs/doc/index.html.src b/plugins/Pcre16/docs/doc/index.html.src new file mode 100644 index 0000000000..887f4d7507 --- /dev/null +++ b/plugins/Pcre16/docs/doc/index.html.src @@ -0,0 +1,185 @@ +<html> +<!-- This is a manually maintained file that is the root of the HTML version of + the PCRE documentation. When the HTML documents are built from the man + page versions, the entire doc/html directory is emptied, this file is then + copied into doc/html/index.html, and the remaining files therein are + created by the 132html script. +--> +<head> +<title>PCRE specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>Perl-compatible Regular Expressions (PCRE)</h1> +<p> +The HTML documentation for PCRE consists of a number of pages that are listed +below in alphabetical order. If you are new to PCRE, please read the first one +first. +</p> + +<table> +<tr><td><a href="pcre.html">pcre</a></td> + <td> Introductory page</td></tr> + +<tr><td><a href="pcre-config.html">pcre-config</a></td> + <td> Information about the installation configuration</td></tr> + +<tr><td><a href="pcre16.html">pcre16</a></td> + <td> Discussion of the 16-bit PCRE library</td></tr> + +<tr><td><a href="pcre32.html">pcre32</a></td> + <td> Discussion of the 32-bit PCRE library</td></tr> + +<tr><td><a href="pcreapi.html">pcreapi</a></td> + <td> PCRE's native API</td></tr> + +<tr><td><a href="pcrebuild.html">pcrebuild</a></td> + <td> Building PCRE</td></tr> + +<tr><td><a href="pcrecallout.html">pcrecallout</a></td> + <td> The <i>callout</i> facility</td></tr> + +<tr><td><a href="pcrecompat.html">pcrecompat</a></td> + <td> Compability with Perl</td></tr> + +<tr><td><a href="pcrecpp.html">pcrecpp</a></td> + <td> The C++ wrapper for the PCRE library</td></tr> + +<tr><td><a href="pcredemo.html">pcredemo</a></td> + <td> A demonstration C program that uses the PCRE library</td></tr> + +<tr><td><a href="pcregrep.html">pcregrep</a></td> + <td> The <b>pcregrep</b> command</td></tr> + +<tr><td><a href="pcrejit.html">pcrejit</a></td> + <td> Discussion of the just-in-time optimization support</td></tr> + +<tr><td><a href="pcrelimits.html">pcrelimits</a></td> + <td> Details of size and other limits</td></tr> + +<tr><td><a href="pcrematching.html">pcrematching</a></td> + <td> Discussion of the two matching algorithms</td></tr> + +<tr><td><a href="pcrepartial.html">pcrepartial</a></td> + <td> Using PCRE for partial matching</td></tr> + +<tr><td><a href="pcrepattern.html">pcrepattern</a></td> + <td> Specification of the regular expressions supported by PCRE</td></tr> + +<tr><td><a href="pcreperform.html">pcreperform</a></td> + <td> Some comments on performance</td></tr> + +<tr><td><a href="pcreposix.html">pcreposix</a></td> + <td> The POSIX API to the PCRE 8-bit library</td></tr> + +<tr><td><a href="pcreprecompile.html">pcreprecompile</a></td> + <td> How to save and re-use compiled patterns</td></tr> + +<tr><td><a href="pcresample.html">pcresample</a></td> + <td> Discussion of the pcredemo program</td></tr> + +<tr><td><a href="pcrestack.html">pcrestack</a></td> + <td> Discussion of PCRE's stack usage</td></tr> + +<tr><td><a href="pcresyntax.html">pcresyntax</a></td> + <td> Syntax quick-reference summary</td></tr> + +<tr><td><a href="pcretest.html">pcretest</a></td> + <td> The <b>pcretest</b> command for testing PCRE</td></tr> + +<tr><td><a href="pcreunicode.html">pcreunicode</a></td> + <td> Discussion of Unicode and UTF-8/UTF-16/UTF-32 support</td></tr> +</table> + +<p> +There are also individual pages that summarize the interface for each function +in the library. There is a single page for each triple of 8-bit/16-bit/32-bit +functions. +</p> + +<table> + +<tr><td><a href="pcre_assign_jit_stack.html">pcre_assign_jit_stack</a></td> + <td> Assign stack for JIT matching</td></tr> + +<tr><td><a href="pcre_compile.html">pcre_compile</a></td> + <td> Compile a regular expression</td></tr> + +<tr><td><a href="pcre_compile2.html">pcre_compile2</a></td> + <td> Compile a regular expression (alternate interface)</td></tr> + +<tr><td><a href="pcre_config.html">pcre_config</a></td> + <td> Show build-time configuration options</td></tr> + +<tr><td><a href="pcre_copy_named_substring.html">pcre_copy_named_substring</a></td> + <td> Extract named substring into given buffer</td></tr> + +<tr><td><a href="pcre_copy_substring.html">pcre_copy_substring</a></td> + <td> Extract numbered substring into given buffer</td></tr> + +<tr><td><a href="pcre_dfa_exec.html">pcre_dfa_exec</a></td> + <td> Match a compiled pattern to a subject string + (DFA algorithm; <i>not</i> Perl compatible)</td></tr> + +<tr><td><a href="pcre_exec.html">pcre_exec</a></td> + <td> Match a compiled pattern to a subject string + (Perl compatible)</td></tr> + +<tr><td><a href="pcre_free_study.html">pcre_free_study</a></td> + <td> Free study data</td></tr> + +<tr><td><a href="pcre_free_substring.html">pcre_free_substring</a></td> + <td> Free extracted substring</td></tr> + +<tr><td><a href="pcre_free_substring_list.html">pcre_free_substring_list</a></td> + <td> Free list of extracted substrings</td></tr> + +<tr><td><a href="pcre_fullinfo.html">pcre_fullinfo</a></td> + <td> Extract information about a pattern</td></tr> + +<tr><td><a href="pcre_get_named_substring.html">pcre_get_named_substring</a></td> + <td> Extract named substring into new memory</td></tr> + +<tr><td><a href="pcre_get_stringnumber.html">pcre_get_stringnumber</a></td> + <td> Convert captured string name to number</td></tr> + +<tr><td><a href="pcre_get_stringtable_entries.html">pcre_get_stringtable_entries</a></td> + <td> Find table entries for given string name</td></tr> + +<tr><td><a href="pcre_get_substring.html">pcre_get_substring</a></td> + <td> Extract numbered substring into new memory</td></tr> + +<tr><td><a href="pcre_get_substring_list.html">pcre_get_substring_list</a></td> + <td> Extract all substrings into new memory</td></tr> + +<tr><td><a href="pcre_jit_exec.html">pcre_jit_exec</a></td> + <td> Fast path interface to JIT matching</td></tr> + +<tr><td><a href="pcre_jit_stack_alloc.html">pcre_jit_stack_alloc</a></td> + <td> Create a stack for JIT matching</td></tr> + +<tr><td><a href="pcre_jit_stack_free.html">pcre_jit_stack_free</a></td> + <td> Free a JIT matching stack</td></tr> + +<tr><td><a href="pcre_maketables.html">pcre_maketables</a></td> + <td> Build character tables in current locale</td></tr> + +<tr><td><a href="pcre_pattern_to_host_byte_order.html">pcre_pattern_to_host_byte_order</a></td> + <td> Convert compiled pattern to host byte order if necessary</td></tr> + +<tr><td><a href="pcre_refcount.html">pcre_refcount</a></td> + <td> Maintain reference count in compiled pattern</td></tr> + +<tr><td><a href="pcre_study.html">pcre_study</a></td> + <td> Study a compiled pattern</td></tr> + +<tr><td><a href="pcre_utf16_to_host_byte_order.html">pcre_utf16_to_host_byte_order</a></td> + <td> Convert UTF-16 string to host byte order if necessary</td></tr> + +<tr><td><a href="pcre_utf32_to_host_byte_order.html">pcre_utf32_to_host_byte_order</a></td> + <td> Convert UTF-32 string to host byte order if necessary</td></tr> + +<tr><td><a href="pcre_version.html">pcre_version</a></td> + <td> Return PCRE version and release date</td></tr> +</table> + +</html> diff --git a/plugins/Pcre16/docs/doc/pcre-config.1 b/plugins/Pcre16/docs/doc/pcre-config.1 new file mode 100644 index 0000000000..52eb4fb226 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre-config.1 @@ -0,0 +1,92 @@ +.TH PCRE-CONFIG 1 "01 January 2012" "PCRE 8.30" +.SH NAME +pcre-config - program to return PCRE configuration +.SH SYNOPSIS +.rs +.sp +.nf +.B pcre-config [--prefix] [--exec-prefix] [--version] [--libs] +.B " [--libs16] [--libs32] [--libs-cpp] [--libs-posix]" +.B " [--cflags] [--cflags-posix]" +.fi +. +. +.SH DESCRIPTION +.rs +.sp +\fBpcre-config\fP returns the configuration of the installed PCRE +libraries and the options required to compile a program to use them. Some of +the options apply only to the 8-bit, or 16-bit, or 32-bit libraries, +respectively, and are +not available if only one of those libraries has been built. If an unavailable +option is encountered, the "usage" information is output. +. +. +.SH OPTIONS +.rs +.TP 10 +\fB--prefix\fP +Writes the directory prefix used in the PCRE installation for architecture +independent files (\fI/usr\fP on many systems, \fI/usr/local\fP on some +systems) to the standard output. +.TP 10 +\fB--exec-prefix\fP +Writes the directory prefix used in the PCRE installation for architecture +dependent files (normally the same as \fB--prefix\fP) to the standard output. +.TP 10 +\fB--version\fP +Writes the version number of the installed PCRE libraries to the standard +output. +.TP 10 +\fB--libs\fP +Writes to the standard output the command line options required to link +with the 8-bit PCRE library (\fB-lpcre\fP on many systems). +.TP 10 +\fB--libs16\fP +Writes to the standard output the command line options required to link +with the 16-bit PCRE library (\fB-lpcre16\fP on many systems). +.TP 10 +\fB--libs32\fP +Writes to the standard output the command line options required to link +with the 32-bit PCRE library (\fB-lpcre32\fP on many systems). +.TP 10 +\fB--libs-cpp\fP +Writes to the standard output the command line options required to link with +PCRE's C++ wrapper library (\fB-lpcrecpp\fP \fB-lpcre\fP on many +systems). +.TP 10 +\fB--libs-posix\fP +Writes to the standard output the command line options required to link with +PCRE's POSIX API wrapper library (\fB-lpcreposix\fP \fB-lpcre\fP on many +systems). +.TP 10 +\fB--cflags\fP +Writes to the standard output the command line options required to compile +files that use PCRE (this may include some \fB-I\fP options, but is blank on +many systems). +.TP 10 +\fB--cflags-posix\fP +Writes to the standard output the command line options required to compile +files that use PCRE's POSIX API wrapper library (this may include some \fB-I\fP +options, but is blank on many systems). +. +. +.SH "SEE ALSO" +.rs +.sp +\fBpcre(3)\fP +. +. +.SH AUTHOR +.rs +.sp +This manual page was originally written by Mark Baker for the Debian GNU/Linux +system. It has been subsequently revised as a generic PCRE man page. +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 24 June 2012 +.fi diff --git a/plugins/Pcre16/docs/doc/pcre-config.txt b/plugins/Pcre16/docs/doc/pcre-config.txt new file mode 100644 index 0000000000..8503ab0ef0 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre-config.txt @@ -0,0 +1,86 @@ +PCRE-CONFIG(1) General Commands Manual PCRE-CONFIG(1) + + + +NAME + pcre-config - program to return PCRE configuration + +SYNOPSIS + + pcre-config [--prefix] [--exec-prefix] [--version] [--libs] + [--libs16] [--libs32] [--libs-cpp] [--libs-posix] + [--cflags] [--cflags-posix] + + +DESCRIPTION + + pcre-config returns the configuration of the installed PCRE libraries + and the options required to compile a program to use them. Some of the + options apply only to the 8-bit, or 16-bit, or 32-bit libraries, + respectively, and are not available if only one of those libraries has + been built. If an unavailable option is encountered, the "usage" infor- + mation is output. + + +OPTIONS + + --prefix Writes the directory prefix used in the PCRE installation for + architecture independent files (/usr on many systems, + /usr/local on some systems) to the standard output. + + --exec-prefix + Writes the directory prefix used in the PCRE installation for + architecture dependent files (normally the same as --prefix) + to the standard output. + + --version Writes the version number of the installed PCRE libraries to + the standard output. + + --libs Writes to the standard output the command line options + required to link with the 8-bit PCRE library (-lpcre on many + systems). + + --libs16 Writes to the standard output the command line options + required to link with the 16-bit PCRE library (-lpcre16 on + many systems). + + --libs32 Writes to the standard output the command line options + required to link with the 32-bit PCRE library (-lpcre32 on + many systems). + + --libs-cpp + Writes to the standard output the command line options + required to link with PCRE's C++ wrapper library (-lpcrecpp + -lpcre on many systems). + + --libs-posix + Writes to the standard output the command line options + required to link with PCRE's POSIX API wrapper library + (-lpcreposix -lpcre on many systems). + + --cflags Writes to the standard output the command line options + required to compile files that use PCRE (this may include + some -I options, but is blank on many systems). + + --cflags-posix + Writes to the standard output the command line options + required to compile files that use PCRE's POSIX API wrapper + library (this may include some -I options, but is blank on + many systems). + + +SEE ALSO + + pcre(3) + + +AUTHOR + + This manual page was originally written by Mark Baker for the Debian + GNU/Linux system. It has been subsequently revised as a generic PCRE + man page. + + +REVISION + + Last updated: 24 June 2012 diff --git a/plugins/Pcre16/docs/doc/pcre.3 b/plugins/Pcre16/docs/doc/pcre.3 new file mode 100644 index 0000000000..4eda404ccf --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre.3 @@ -0,0 +1,218 @@ +.TH PCRE 3 "08 January 2014" "PCRE 8.35" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH INTRODUCTION +.rs +.sp +The PCRE library is a set of functions that implement regular expression +pattern matching using the same syntax and semantics as Perl, with just a few +differences. Some features that appeared in Python and PCRE before they +appeared in Perl are also available using the Python syntax, there is some +support for one or two .NET and Oniguruma syntax items, and there is an option +for requesting some minor changes that give better JavaScript compatibility. +.P +Starting with release 8.30, it is possible to compile two separate PCRE +libraries: the original, which supports 8-bit character strings (including +UTF-8 strings), and a second library that supports 16-bit character strings +(including UTF-16 strings). The build process allows either one or both to be +built. The majority of the work to make this possible was done by Zoltan +Herczeg. +.P +Starting with release 8.32 it is possible to compile a third separate PCRE +library that supports 32-bit character strings (including UTF-32 strings). The +build process allows any combination of the 8-, 16- and 32-bit libraries. The +work to make this possible was done by Christian Persch. +.P +The three libraries contain identical sets of functions, except that the names +in the 16-bit library start with \fBpcre16_\fP instead of \fBpcre_\fP, and the +names in the 32-bit library start with \fBpcre32_\fP instead of \fBpcre_\fP. To +avoid over-complication and reduce the documentation maintenance load, most of +the documentation describes the 8-bit library, with the differences for the +16-bit and 32-bit libraries described separately in the +.\" HREF +\fBpcre16\fP +and +.\" HREF +\fBpcre32\fP +.\" +pages. References to functions or structures of the form \fIpcre[16|32]_xxx\fP +should be read as meaning "\fIpcre_xxx\fP when using the 8-bit library, +\fIpcre16_xxx\fP when using the 16-bit library, or \fIpcre32_xxx\fP when using +the 32-bit library". +.P +The current implementation of PCRE corresponds approximately with Perl 5.12, +including support for UTF-8/16/32 encoded strings and Unicode general category +properties. However, UTF-8/16/32 and Unicode support has to be explicitly +enabled; it is not the default. The Unicode tables correspond to Unicode +release 6.3.0. +.P +In addition to the Perl-compatible matching function, PCRE contains an +alternative function that matches the same compiled patterns in a different +way. In certain circumstances, the alternative function has some advantages. +For a discussion of the two matching algorithms, see the +.\" HREF +\fBpcrematching\fP +.\" +page. +.P +PCRE is written in C and released as a C library. A number of people have +written wrappers and interfaces of various kinds. In particular, Google Inc. +have provided a comprehensive C++ wrapper for the 8-bit library. This is now +included as part of the PCRE distribution. The +.\" HREF +\fBpcrecpp\fP +.\" +page has details of this interface. Other people's contributions can be found +in the \fIContrib\fP directory at the primary FTP site, which is: +.sp +.\" HTML <a href="ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre"> +.\" </a> +ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre +.\" +.P +Details of exactly which Perl regular expression features are and are not +supported by PCRE are given in separate documents. See the +.\" HREF +\fBpcrepattern\fP +.\" +and +.\" HREF +\fBpcrecompat\fP +.\" +pages. There is a syntax summary in the +.\" HREF +\fBpcresyntax\fP +.\" +page. +.P +Some features of PCRE can be included, excluded, or changed when the library is +built. The +.\" HREF +\fBpcre_config()\fP +.\" +function makes it possible for a client to discover which features are +available. The features themselves are described in the +.\" HREF +\fBpcrebuild\fP +.\" +page. Documentation about building PCRE for various operating systems can be +found in the +.\" HTML <a href="README.txt"> +.\" </a> +\fBREADME\fP +.\" +and +.\" HTML <a href="NON-AUTOTOOLS-BUILD.txt"> +.\" </a> +\fBNON-AUTOTOOLS_BUILD\fP +.\" +files in the source distribution. +.P +The libraries contains a number of undocumented internal functions and data +tables that are used by more than one of the exported external functions, but +which are not intended for use by external callers. Their names all begin with +"_pcre_" or "_pcre16_" or "_pcre32_", which hopefully will not provoke any name +clashes. In some environments, it is possible to control which external symbols +are exported when a shared library is built, and in these cases the +undocumented symbols are not exported. +. +. +.SH "SECURITY CONSIDERATIONS" +.rs +.sp +If you are using PCRE in a non-UTF application that permits users to supply +arbitrary patterns for compilation, you should be aware of a feature that +allows users to turn on UTF support from within a pattern, provided that PCRE +was built with UTF support. For example, an 8-bit pattern that begins with +"(*UTF8)" or "(*UTF)" turns on UTF-8 mode, which interprets patterns and +subjects as strings of UTF-8 characters instead of individual 8-bit characters. +This causes both the pattern and any data against which it is matched to be +checked for UTF-8 validity. If the data string is very long, such a check might +use sufficiently many resources as to cause your application to lose +performance. +.P +One way of guarding against this possibility is to use the +\fBpcre_fullinfo()\fP function to check the compiled pattern's options for UTF. +Alternatively, from release 8.33, you can set the PCRE_NEVER_UTF option at +compile time. This causes an compile time error if a pattern contains a +UTF-setting sequence. +.P +If your application is one that supports UTF, be aware that validity checking +can take time. If the same data string is to be matched many times, you can use +the PCRE_NO_UTF[8|16|32]_CHECK option for the second and subsequent matches to +save redundant checks. +.P +Another way that performance can be hit is by running a pattern that has a very +large search tree against a string that will never match. Nested unlimited +repeats in a pattern are a common example. PCRE provides some protection +against this: see the PCRE_EXTRA_MATCH_LIMIT feature in the +.\" HREF +\fBpcreapi\fP +.\" +page. +. +. +.SH "USER DOCUMENTATION" +.rs +.sp +The user documentation for PCRE comprises a number of different sections. In +the "man" format, each of these is a separate "man page". In the HTML format, +each is a separate page, linked from the index page. In the plain text format, +the descriptions of the \fBpcregrep\fP and \fBpcretest\fP programs are in files +called \fBpcregrep.txt\fP and \fBpcretest.txt\fP, respectively. The remaining +sections, except for the \fBpcredemo\fP section (which is a program listing), +are concatenated in \fBpcre.txt\fP, for ease of searching. The sections are as +follows: +.sp + pcre this document + pcre-config show PCRE installation configuration information + pcre16 details of the 16-bit library + pcre32 details of the 32-bit library + pcreapi details of PCRE's native C API + pcrebuild building PCRE + pcrecallout details of the callout feature + pcrecompat discussion of Perl compatibility + pcrecpp details of the C++ wrapper for the 8-bit library + pcredemo a demonstration C program that uses PCRE + pcregrep description of the \fBpcregrep\fP command (8-bit only) + pcrejit discussion of the just-in-time optimization support + pcrelimits details of size and other limits + pcrematching discussion of the two matching algorithms + pcrepartial details of the partial matching facility +.\" JOIN + pcrepattern syntax and semantics of supported + regular expressions + pcreperform discussion of performance issues + pcreposix the POSIX-compatible C API for the 8-bit library + pcreprecompile details of saving and re-using precompiled patterns + pcresample discussion of the pcredemo program + pcrestack discussion of stack usage + pcresyntax quick syntax reference + pcretest description of the \fBpcretest\fP testing command + pcreunicode discussion of Unicode and UTF-8/16/32 support +.sp +In the "man" and HTML formats, there is also a short page for each C library +function, listing its arguments and results. +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +.P +Putting an actual email address here seems to have been a spam magnet, so I've +taken it away. If you want to email me, use my two initials, followed by the +two digits 10, at the domain cam.ac.uk. +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 08 January 2014 +Copyright (c) 1997-2014 University of Cambridge. +.fi diff --git a/plugins/Pcre16/docs/doc/pcre.txt b/plugins/Pcre16/docs/doc/pcre.txt new file mode 100644 index 0000000000..14cbb8bf2b --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre.txt @@ -0,0 +1,10423 @@ +----------------------------------------------------------------------------- +This file contains a concatenation of the PCRE man pages, converted to plain +text format for ease of searching with a text editor, or for use on systems +that do not have a man page processor. The small individual files that give +synopses of each function in the library have not been included. Neither has +the pcredemo program. There are separate text files for the pcregrep and +pcretest commands. +----------------------------------------------------------------------------- + + +PCRE(3) Library Functions Manual PCRE(3) + + + +NAME + PCRE - Perl-compatible regular expressions + +INTRODUCTION + + The PCRE library is a set of functions that implement regular expres- + sion pattern matching using the same syntax and semantics as Perl, with + just a few differences. Some features that appeared in Python and PCRE + before they appeared in Perl are also available using the Python syn- + tax, there is some support for one or two .NET and Oniguruma syntax + items, and there is an option for requesting some minor changes that + give better JavaScript compatibility. + + Starting with release 8.30, it is possible to compile two separate PCRE + libraries: the original, which supports 8-bit character strings + (including UTF-8 strings), and a second library that supports 16-bit + character strings (including UTF-16 strings). The build process allows + either one or both to be built. The majority of the work to make this + possible was done by Zoltan Herczeg. + + Starting with release 8.32 it is possible to compile a third separate + PCRE library that supports 32-bit character strings (including UTF-32 + strings). The build process allows any combination of the 8-, 16- and + 32-bit libraries. The work to make this possible was done by Christian + Persch. + + The three libraries contain identical sets of functions, except that + the names in the 16-bit library start with pcre16_ instead of pcre_, + and the names in the 32-bit library start with pcre32_ instead of + pcre_. To avoid over-complication and reduce the documentation mainte- + nance load, most of the documentation describes the 8-bit library, with + the differences for the 16-bit and 32-bit libraries described sepa- + rately in the pcre16 and pcre32 pages. References to functions or + structures of the form pcre[16|32]_xxx should be read as meaning + "pcre_xxx when using the 8-bit library, pcre16_xxx when using the + 16-bit library, or pcre32_xxx when using the 32-bit library". + + The current implementation of PCRE corresponds approximately with Perl + 5.12, including support for UTF-8/16/32 encoded strings and Unicode + general category properties. However, UTF-8/16/32 and Unicode support + has to be explicitly enabled; it is not the default. The Unicode tables + correspond to Unicode release 6.3.0. + + In addition to the Perl-compatible matching function, PCRE contains an + alternative function that matches the same compiled patterns in a dif- + ferent way. In certain circumstances, the alternative function has some + advantages. For a discussion of the two matching algorithms, see the + pcrematching page. + + PCRE is written in C and released as a C library. A number of people + have written wrappers and interfaces of various kinds. In particular, + Google Inc. have provided a comprehensive C++ wrapper for the 8-bit + library. This is now included as part of the PCRE distribution. The + pcrecpp page has details of this interface. Other people's contribu- + tions can be found in the Contrib directory at the primary FTP site, + which is: + + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre + + Details of exactly which Perl regular expression features are and are + not supported by PCRE are given in separate documents. See the pcrepat- + tern and pcrecompat pages. There is a syntax summary in the pcresyntax + page. + + Some features of PCRE can be included, excluded, or changed when the + library is built. The pcre_config() function makes it possible for a + client to discover which features are available. The features them- + selves are described in the pcrebuild page. Documentation about build- + ing PCRE for various operating systems can be found in the README and + NON-AUTOTOOLS_BUILD files in the source distribution. + + The libraries contains a number of undocumented internal functions and + data tables that are used by more than one of the exported external + functions, but which are not intended for use by external callers. + Their names all begin with "_pcre_" or "_pcre16_" or "_pcre32_", which + hopefully will not provoke any name clashes. In some environments, it + is possible to control which external symbols are exported when a + shared library is built, and in these cases the undocumented symbols + are not exported. + + +SECURITY CONSIDERATIONS + + If you are using PCRE in a non-UTF application that permits users to + supply arbitrary patterns for compilation, you should be aware of a + feature that allows users to turn on UTF support from within a pattern, + provided that PCRE was built with UTF support. For example, an 8-bit + pattern that begins with "(*UTF8)" or "(*UTF)" turns on UTF-8 mode, + which interprets patterns and subjects as strings of UTF-8 characters + instead of individual 8-bit characters. This causes both the pattern + and any data against which it is matched to be checked for UTF-8 valid- + ity. If the data string is very long, such a check might use suffi- + ciently many resources as to cause your application to lose perfor- + mance. + + One way of guarding against this possibility is to use the + pcre_fullinfo() function to check the compiled pattern's options for + UTF. Alternatively, from release 8.33, you can set the PCRE_NEVER_UTF + option at compile time. This causes an compile time error if a pattern + contains a UTF-setting sequence. + + If your application is one that supports UTF, be aware that validity + checking can take time. If the same data string is to be matched many + times, you can use the PCRE_NO_UTF[8|16|32]_CHECK option for the second + and subsequent matches to save redundant checks. + + Another way that performance can be hit is by running a pattern that + has a very large search tree against a string that will never match. + Nested unlimited repeats in a pattern are a common example. PCRE pro- + vides some protection against this: see the PCRE_EXTRA_MATCH_LIMIT fea- + ture in the pcreapi page. + + +USER DOCUMENTATION + + The user documentation for PCRE comprises a number of different sec- + tions. In the "man" format, each of these is a separate "man page". In + the HTML format, each is a separate page, linked from the index page. + In the plain text format, the descriptions of the pcregrep and pcretest + programs are in files called pcregrep.txt and pcretest.txt, respec- + tively. The remaining sections, except for the pcredemo section (which + is a program listing), are concatenated in pcre.txt, for ease of + searching. The sections are as follows: + + pcre this document + pcre-config show PCRE installation configuration information + pcre16 details of the 16-bit library + pcre32 details of the 32-bit library + pcreapi details of PCRE's native C API + pcrebuild building PCRE + pcrecallout details of the callout feature + pcrecompat discussion of Perl compatibility + pcrecpp details of the C++ wrapper for the 8-bit library + pcredemo a demonstration C program that uses PCRE + pcregrep description of the pcregrep command (8-bit only) + pcrejit discussion of the just-in-time optimization support + pcrelimits details of size and other limits + pcrematching discussion of the two matching algorithms + pcrepartial details of the partial matching facility + pcrepattern syntax and semantics of supported + regular expressions + pcreperform discussion of performance issues + pcreposix the POSIX-compatible C API for the 8-bit library + pcreprecompile details of saving and re-using precompiled patterns + pcresample discussion of the pcredemo program + pcrestack discussion of stack usage + pcresyntax quick syntax reference + pcretest description of the pcretest testing command + pcreunicode discussion of Unicode and UTF-8/16/32 support + + In the "man" and HTML formats, there is also a short page for each C + library function, listing its arguments and results. + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + Putting an actual email address here seems to have been a spam magnet, + so I've taken it away. If you want to email me, use my two initials, + followed by the two digits 10, at the domain cam.ac.uk. + + +REVISION + + Last updated: 08 January 2014 + Copyright (c) 1997-2014 University of Cambridge. +------------------------------------------------------------------------------ + + +PCRE(3) Library Functions Manual PCRE(3) + + + +NAME + PCRE - Perl-compatible regular expressions + + #include <pcre.h> + + +PCRE 16-BIT API BASIC FUNCTIONS + + pcre16 *pcre16_compile(PCRE_SPTR16 pattern, int options, + const char **errptr, int *erroffset, + const unsigned char *tableptr); + + pcre16 *pcre16_compile2(PCRE_SPTR16 pattern, int options, + int *errorcodeptr, + const char **errptr, int *erroffset, + const unsigned char *tableptr); + + pcre16_extra *pcre16_study(const pcre16 *code, int options, + const char **errptr); + + void pcre16_free_study(pcre16_extra *extra); + + int pcre16_exec(const pcre16 *code, const pcre16_extra *extra, + PCRE_SPTR16 subject, int length, int startoffset, + int options, int *ovector, int ovecsize); + + int pcre16_dfa_exec(const pcre16 *code, const pcre16_extra *extra, + PCRE_SPTR16 subject, int length, int startoffset, + int options, int *ovector, int ovecsize, + int *workspace, int wscount); + + +PCRE 16-BIT API STRING EXTRACTION FUNCTIONS + + int pcre16_copy_named_substring(const pcre16 *code, + PCRE_SPTR16 subject, int *ovector, + int stringcount, PCRE_SPTR16 stringname, + PCRE_UCHAR16 *buffer, int buffersize); + + int pcre16_copy_substring(PCRE_SPTR16 subject, int *ovector, + int stringcount, int stringnumber, PCRE_UCHAR16 *buffer, + int buffersize); + + int pcre16_get_named_substring(const pcre16 *code, + PCRE_SPTR16 subject, int *ovector, + int stringcount, PCRE_SPTR16 stringname, + PCRE_SPTR16 *stringptr); + + int pcre16_get_stringnumber(const pcre16 *code, + PCRE_SPTR16 name); + + int pcre16_get_stringtable_entries(const pcre16 *code, + PCRE_SPTR16 name, PCRE_UCHAR16 **first, PCRE_UCHAR16 **last); + + int pcre16_get_substring(PCRE_SPTR16 subject, int *ovector, + int stringcount, int stringnumber, + PCRE_SPTR16 *stringptr); + + int pcre16_get_substring_list(PCRE_SPTR16 subject, + int *ovector, int stringcount, PCRE_SPTR16 **listptr); + + void pcre16_free_substring(PCRE_SPTR16 stringptr); + + void pcre16_free_substring_list(PCRE_SPTR16 *stringptr); + + +PCRE 16-BIT API AUXILIARY FUNCTIONS + + pcre16_jit_stack *pcre16_jit_stack_alloc(int startsize, int maxsize); + + void pcre16_jit_stack_free(pcre16_jit_stack *stack); + + void pcre16_assign_jit_stack(pcre16_extra *extra, + pcre16_jit_callback callback, void *data); + + const unsigned char *pcre16_maketables(void); + + int pcre16_fullinfo(const pcre16 *code, const pcre16_extra *extra, + int what, void *where); + + int pcre16_refcount(pcre16 *code, int adjust); + + int pcre16_config(int what, void *where); + + const char *pcre16_version(void); + + int pcre16_pattern_to_host_byte_order(pcre16 *code, + pcre16_extra *extra, const unsigned char *tables); + + +PCRE 16-BIT API INDIRECTED FUNCTIONS + + void *(*pcre16_malloc)(size_t); + + void (*pcre16_free)(void *); + + void *(*pcre16_stack_malloc)(size_t); + + void (*pcre16_stack_free)(void *); + + int (*pcre16_callout)(pcre16_callout_block *); + + +PCRE 16-BIT API 16-BIT-ONLY FUNCTION + + int pcre16_utf16_to_host_byte_order(PCRE_UCHAR16 *output, + PCRE_SPTR16 input, int length, int *byte_order, + int keep_boms); + + +THE PCRE 16-BIT LIBRARY + + Starting with release 8.30, it is possible to compile a PCRE library + that supports 16-bit character strings, including UTF-16 strings, as + well as or instead of the original 8-bit library. The majority of the + work to make this possible was done by Zoltan Herczeg. The two + libraries contain identical sets of functions, used in exactly the same + way. Only the names of the functions and the data types of their argu- + ments and results are different. To avoid over-complication and reduce + the documentation maintenance load, most of the PCRE documentation + describes the 8-bit library, with only occasional references to the + 16-bit library. This page describes what is different when you use the + 16-bit library. + + WARNING: A single application can be linked with both libraries, but + you must take care when processing any particular pattern to use func- + tions from just one library. For example, if you want to study a pat- + tern that was compiled with pcre16_compile(), you must do so with + pcre16_study(), not pcre_study(), and you must free the study data with + pcre16_free_study(). + + +THE HEADER FILE + + There is only one header file, pcre.h. It contains prototypes for all + the functions in all libraries, as well as definitions of flags, struc- + tures, error codes, etc. + + +THE LIBRARY NAME + + In Unix-like systems, the 16-bit library is called libpcre16, and can + normally be accesss by adding -lpcre16 to the command for linking an + application that uses PCRE. + + +STRING TYPES + + In the 8-bit library, strings are passed to PCRE library functions as + vectors of bytes with the C type "char *". In the 16-bit library, + strings are passed as vectors of unsigned 16-bit quantities. The macro + PCRE_UCHAR16 specifies an appropriate data type, and PCRE_SPTR16 is + defined as "const PCRE_UCHAR16 *". In very many environments, "short + int" is a 16-bit data type. When PCRE is built, it defines PCRE_UCHAR16 + as "unsigned short int", but checks that it really is a 16-bit data + type. If it is not, the build fails with an error message telling the + maintainer to modify the definition appropriately. + + +STRUCTURE TYPES + + The types of the opaque structures that are used for compiled 16-bit + patterns and JIT stacks are pcre16 and pcre16_jit_stack respectively. + The type of the user-accessible structure that is returned by + pcre16_study() is pcre16_extra, and the type of the structure that is + used for passing data to a callout function is pcre16_callout_block. + These structures contain the same fields, with the same names, as their + 8-bit counterparts. The only difference is that pointers to character + strings are 16-bit instead of 8-bit types. + + +16-BIT FUNCTIONS + + For every function in the 8-bit library there is a corresponding func- + tion in the 16-bit library with a name that starts with pcre16_ instead + of pcre_. The prototypes are listed above. In addition, there is one + extra function, pcre16_utf16_to_host_byte_order(). This is a utility + function that converts a UTF-16 character string to host byte order if + necessary. The other 16-bit functions expect the strings they are + passed to be in host byte order. + + The input and output arguments of pcre16_utf16_to_host_byte_order() may + point to the same address, that is, conversion in place is supported. + The output buffer must be at least as long as the input. + + The length argument specifies the number of 16-bit data units in the + input string; a negative value specifies a zero-terminated string. + + If byte_order is NULL, it is assumed that the string starts off in host + byte order. This may be changed by byte-order marks (BOMs) anywhere in + the string (commonly as the first character). + + If byte_order is not NULL, a non-zero value of the integer to which it + points means that the input starts off in host byte order, otherwise + the opposite order is assumed. Again, BOMs in the string can change + this. The final byte order is passed back at the end of processing. + + If keep_boms is not zero, byte-order mark characters (0xfeff) are + copied into the output string. Otherwise they are discarded. + + The result of the function is the number of 16-bit units placed into + the output buffer, including the zero terminator if the string was + zero-terminated. + + +SUBJECT STRING OFFSETS + + The lengths and starting offsets of subject strings must be specified + in 16-bit data units, and the offsets within subject strings that are + returned by the matching functions are in also 16-bit units rather than + bytes. + + +NAMED SUBPATTERNS + + The name-to-number translation table that is maintained for named sub- + patterns uses 16-bit characters. The pcre16_get_stringtable_entries() + function returns the length of each entry in the table as the number of + 16-bit data units. + + +OPTION NAMES + + There are two new general option names, PCRE_UTF16 and + PCRE_NO_UTF16_CHECK, which correspond to PCRE_UTF8 and + PCRE_NO_UTF8_CHECK in the 8-bit library. In fact, these new options + define the same bits in the options word. There is a discussion about + the validity of UTF-16 strings in the pcreunicode page. + + For the pcre16_config() function there is an option PCRE_CONFIG_UTF16 + that returns 1 if UTF-16 support is configured, otherwise 0. If this + option is given to pcre_config() or pcre32_config(), or if the + PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF32 option is given to pcre16_con- + fig(), the result is the PCRE_ERROR_BADOPTION error. + + +CHARACTER CODES + + In 16-bit mode, when PCRE_UTF16 is not set, character values are + treated in the same way as in 8-bit, non UTF-8 mode, except, of course, + that they can range from 0 to 0xffff instead of 0 to 0xff. Character + types for characters less than 0xff can therefore be influenced by the + locale in the same way as before. Characters greater than 0xff have + only one case, and no "type" (such as letter or digit). + + In UTF-16 mode, the character code is Unicode, in the range 0 to + 0x10ffff, with the exception of values in the range 0xd800 to 0xdfff + because those are "surrogate" values that are used in pairs to encode + values greater than 0xffff. + + A UTF-16 string can indicate its endianness by special code knows as a + byte-order mark (BOM). The PCRE functions do not handle this, expecting + strings to be in host byte order. A utility function called + pcre16_utf16_to_host_byte_order() is provided to help with this (see + above). + + +ERROR NAMES + + The errors PCRE_ERROR_BADUTF16_OFFSET and PCRE_ERROR_SHORTUTF16 corre- + spond to their 8-bit counterparts. The error PCRE_ERROR_BADMODE is + given when a compiled pattern is passed to a function that processes + patterns in the other mode, for example, if a pattern compiled with + pcre_compile() is passed to pcre16_exec(). + + There are new error codes whose names begin with PCRE_UTF16_ERR for + invalid UTF-16 strings, corresponding to the PCRE_UTF8_ERR codes for + UTF-8 strings that are described in the section entitled "Reason codes + for invalid UTF-8 strings" in the main pcreapi page. The UTF-16 errors + are: + + PCRE_UTF16_ERR1 Missing low surrogate at end of string + PCRE_UTF16_ERR2 Invalid low surrogate follows high surrogate + PCRE_UTF16_ERR3 Isolated low surrogate + PCRE_UTF16_ERR4 Non-character + + +ERROR TEXTS + + If there is an error while compiling a pattern, the error text that is + passed back by pcre16_compile() or pcre16_compile2() is still an 8-bit + character string, zero-terminated. + + +CALLOUTS + + The subject and mark fields in the callout block that is passed to a + callout function point to 16-bit vectors. + + +TESTING + + The pcretest program continues to operate with 8-bit input and output + files, but it can be used for testing the 16-bit library. If it is run + with the command line option -16, patterns and subject strings are con- + verted from 8-bit to 16-bit before being passed to PCRE, and the 16-bit + library functions are used instead of the 8-bit ones. Returned 16-bit + strings are converted to 8-bit for output. If both the 8-bit and the + 32-bit libraries were not compiled, pcretest defaults to 16-bit and the + -16 option is ignored. + + When PCRE is being built, the RunTest script that is called by "make + check" uses the pcretest -C option to discover which of the 8-bit, + 16-bit and 32-bit libraries has been built, and runs the tests appro- + priately. + + +NOT SUPPORTED IN 16-BIT MODE + + Not all the features of the 8-bit library are available with the 16-bit + library. The C++ and POSIX wrapper functions support only the 8-bit + library, and the pcregrep program is at present 8-bit only. + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 12 May 2013 + Copyright (c) 1997-2013 University of Cambridge. +------------------------------------------------------------------------------ + + +PCRE(3) Library Functions Manual PCRE(3) + + + +NAME + PCRE - Perl-compatible regular expressions + + #include <pcre.h> + + +PCRE 32-BIT API BASIC FUNCTIONS + + pcre32 *pcre32_compile(PCRE_SPTR32 pattern, int options, + const char **errptr, int *erroffset, + const unsigned char *tableptr); + + pcre32 *pcre32_compile2(PCRE_SPTR32 pattern, int options, + int *errorcodeptr, + const unsigned char *tableptr); + + pcre32_extra *pcre32_study(const pcre32 *code, int options, + const char **errptr); + + void pcre32_free_study(pcre32_extra *extra); + + int pcre32_exec(const pcre32 *code, const pcre32_extra *extra, + PCRE_SPTR32 subject, int length, int startoffset, + int options, int *ovector, int ovecsize); + + int pcre32_dfa_exec(const pcre32 *code, const pcre32_extra *extra, + PCRE_SPTR32 subject, int length, int startoffset, + int options, int *ovector, int ovecsize, + int *workspace, int wscount); + + +PCRE 32-BIT API STRING EXTRACTION FUNCTIONS + + int pcre32_copy_named_substring(const pcre32 *code, + PCRE_SPTR32 subject, int *ovector, + int stringcount, PCRE_SPTR32 stringname, + PCRE_UCHAR32 *buffer, int buffersize); + + int pcre32_copy_substring(PCRE_SPTR32 subject, int *ovector, + int stringcount, int stringnumber, PCRE_UCHAR32 *buffer, + int buffersize); + + int pcre32_get_named_substring(const pcre32 *code, + PCRE_SPTR32 subject, int *ovector, + int stringcount, PCRE_SPTR32 stringname, + PCRE_SPTR32 *stringptr); + + int pcre32_get_stringnumber(const pcre32 *code, + PCRE_SPTR32 name); + + int pcre32_get_stringtable_entries(const pcre32 *code, + PCRE_SPTR32 name, PCRE_UCHAR32 **first, PCRE_UCHAR32 **last); + + int pcre32_get_substring(PCRE_SPTR32 subject, int *ovector, + int stringcount, int stringnumber, + PCRE_SPTR32 *stringptr); + + int pcre32_get_substring_list(PCRE_SPTR32 subject, + int *ovector, int stringcount, PCRE_SPTR32 **listptr); + + void pcre32_free_substring(PCRE_SPTR32 stringptr); + + void pcre32_free_substring_list(PCRE_SPTR32 *stringptr); + + +PCRE 32-BIT API AUXILIARY FUNCTIONS + + pcre32_jit_stack *pcre32_jit_stack_alloc(int startsize, int maxsize); + + void pcre32_jit_stack_free(pcre32_jit_stack *stack); + + void pcre32_assign_jit_stack(pcre32_extra *extra, + pcre32_jit_callback callback, void *data); + + const unsigned char *pcre32_maketables(void); + + int pcre32_fullinfo(const pcre32 *code, const pcre32_extra *extra, + int what, void *where); + + int pcre32_refcount(pcre32 *code, int adjust); + + int pcre32_config(int what, void *where); + + const char *pcre32_version(void); + + int pcre32_pattern_to_host_byte_order(pcre32 *code, + pcre32_extra *extra, const unsigned char *tables); + + +PCRE 32-BIT API INDIRECTED FUNCTIONS + + void *(*pcre32_malloc)(size_t); + + void (*pcre32_free)(void *); + + void *(*pcre32_stack_malloc)(size_t); + + void (*pcre32_stack_free)(void *); + + int (*pcre32_callout)(pcre32_callout_block *); + + +PCRE 32-BIT API 32-BIT-ONLY FUNCTION + + int pcre32_utf32_to_host_byte_order(PCRE_UCHAR32 *output, + PCRE_SPTR32 input, int length, int *byte_order, + int keep_boms); + + +THE PCRE 32-BIT LIBRARY + + Starting with release 8.32, it is possible to compile a PCRE library + that supports 32-bit character strings, including UTF-32 strings, as + well as or instead of the original 8-bit library. This work was done by + Christian Persch, based on the work done by Zoltan Herczeg for the + 16-bit library. All three libraries contain identical sets of func- + tions, used in exactly the same way. Only the names of the functions + and the data types of their arguments and results are different. To + avoid over-complication and reduce the documentation maintenance load, + most of the PCRE documentation describes the 8-bit library, with only + occasional references to the 16-bit and 32-bit libraries. This page + describes what is different when you use the 32-bit library. + + WARNING: A single application can be linked with all or any of the + three libraries, but you must take care when processing any particular + pattern to use functions from just one library. For example, if you + want to study a pattern that was compiled with pcre32_compile(), you + must do so with pcre32_study(), not pcre_study(), and you must free the + study data with pcre32_free_study(). + + +THE HEADER FILE + + There is only one header file, pcre.h. It contains prototypes for all + the functions in all libraries, as well as definitions of flags, struc- + tures, error codes, etc. + + +THE LIBRARY NAME + + In Unix-like systems, the 32-bit library is called libpcre32, and can + normally be accesss by adding -lpcre32 to the command for linking an + application that uses PCRE. + + +STRING TYPES + + In the 8-bit library, strings are passed to PCRE library functions as + vectors of bytes with the C type "char *". In the 32-bit library, + strings are passed as vectors of unsigned 32-bit quantities. The macro + PCRE_UCHAR32 specifies an appropriate data type, and PCRE_SPTR32 is + defined as "const PCRE_UCHAR32 *". In very many environments, "unsigned + int" is a 32-bit data type. When PCRE is built, it defines PCRE_UCHAR32 + as "unsigned int", but checks that it really is a 32-bit data type. If + it is not, the build fails with an error message telling the maintainer + to modify the definition appropriately. + + +STRUCTURE TYPES + + The types of the opaque structures that are used for compiled 32-bit + patterns and JIT stacks are pcre32 and pcre32_jit_stack respectively. + The type of the user-accessible structure that is returned by + pcre32_study() is pcre32_extra, and the type of the structure that is + used for passing data to a callout function is pcre32_callout_block. + These structures contain the same fields, with the same names, as their + 8-bit counterparts. The only difference is that pointers to character + strings are 32-bit instead of 8-bit types. + + +32-BIT FUNCTIONS + + For every function in the 8-bit library there is a corresponding func- + tion in the 32-bit library with a name that starts with pcre32_ instead + of pcre_. The prototypes are listed above. In addition, there is one + extra function, pcre32_utf32_to_host_byte_order(). This is a utility + function that converts a UTF-32 character string to host byte order if + necessary. The other 32-bit functions expect the strings they are + passed to be in host byte order. + + The input and output arguments of pcre32_utf32_to_host_byte_order() may + point to the same address, that is, conversion in place is supported. + The output buffer must be at least as long as the input. + + The length argument specifies the number of 32-bit data units in the + input string; a negative value specifies a zero-terminated string. + + If byte_order is NULL, it is assumed that the string starts off in host + byte order. This may be changed by byte-order marks (BOMs) anywhere in + the string (commonly as the first character). + + If byte_order is not NULL, a non-zero value of the integer to which it + points means that the input starts off in host byte order, otherwise + the opposite order is assumed. Again, BOMs in the string can change + this. The final byte order is passed back at the end of processing. + + If keep_boms is not zero, byte-order mark characters (0xfeff) are + copied into the output string. Otherwise they are discarded. + + The result of the function is the number of 32-bit units placed into + the output buffer, including the zero terminator if the string was + zero-terminated. + + +SUBJECT STRING OFFSETS + + The lengths and starting offsets of subject strings must be specified + in 32-bit data units, and the offsets within subject strings that are + returned by the matching functions are in also 32-bit units rather than + bytes. + + +NAMED SUBPATTERNS + + The name-to-number translation table that is maintained for named sub- + patterns uses 32-bit characters. The pcre32_get_stringtable_entries() + function returns the length of each entry in the table as the number of + 32-bit data units. + + +OPTION NAMES + + There are two new general option names, PCRE_UTF32 and + PCRE_NO_UTF32_CHECK, which correspond to PCRE_UTF8 and + PCRE_NO_UTF8_CHECK in the 8-bit library. In fact, these new options + define the same bits in the options word. There is a discussion about + the validity of UTF-32 strings in the pcreunicode page. + + For the pcre32_config() function there is an option PCRE_CONFIG_UTF32 + that returns 1 if UTF-32 support is configured, otherwise 0. If this + option is given to pcre_config() or pcre16_config(), or if the + PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF16 option is given to pcre32_con- + fig(), the result is the PCRE_ERROR_BADOPTION error. + + +CHARACTER CODES + + In 32-bit mode, when PCRE_UTF32 is not set, character values are + treated in the same way as in 8-bit, non UTF-8 mode, except, of course, + that they can range from 0 to 0x7fffffff instead of 0 to 0xff. Charac- + ter types for characters less than 0xff can therefore be influenced by + the locale in the same way as before. Characters greater than 0xff + have only one case, and no "type" (such as letter or digit). + + In UTF-32 mode, the character code is Unicode, in the range 0 to + 0x10ffff, with the exception of values in the range 0xd800 to 0xdfff + because those are "surrogate" values that are ill-formed in UTF-32. + + A UTF-32 string can indicate its endianness by special code knows as a + byte-order mark (BOM). The PCRE functions do not handle this, expecting + strings to be in host byte order. A utility function called + pcre32_utf32_to_host_byte_order() is provided to help with this (see + above). + + +ERROR NAMES + + The error PCRE_ERROR_BADUTF32 corresponds to its 8-bit counterpart. + The error PCRE_ERROR_BADMODE is given when a compiled pattern is passed + to a function that processes patterns in the other mode, for example, + if a pattern compiled with pcre_compile() is passed to pcre32_exec(). + + There are new error codes whose names begin with PCRE_UTF32_ERR for + invalid UTF-32 strings, corresponding to the PCRE_UTF8_ERR codes for + UTF-8 strings that are described in the section entitled "Reason codes + for invalid UTF-8 strings" in the main pcreapi page. The UTF-32 errors + are: + + PCRE_UTF32_ERR1 Surrogate character (range from 0xd800 to 0xdfff) + PCRE_UTF32_ERR2 Non-character + PCRE_UTF32_ERR3 Character > 0x10ffff + + +ERROR TEXTS + + If there is an error while compiling a pattern, the error text that is + passed back by pcre32_compile() or pcre32_compile2() is still an 8-bit + character string, zero-terminated. + + +CALLOUTS + + The subject and mark fields in the callout block that is passed to a + callout function point to 32-bit vectors. + + +TESTING + + The pcretest program continues to operate with 8-bit input and output + files, but it can be used for testing the 32-bit library. If it is run + with the command line option -32, patterns and subject strings are con- + verted from 8-bit to 32-bit before being passed to PCRE, and the 32-bit + library functions are used instead of the 8-bit ones. Returned 32-bit + strings are converted to 8-bit for output. If both the 8-bit and the + 16-bit libraries were not compiled, pcretest defaults to 32-bit and the + -32 option is ignored. + + When PCRE is being built, the RunTest script that is called by "make + check" uses the pcretest -C option to discover which of the 8-bit, + 16-bit and 32-bit libraries has been built, and runs the tests appro- + priately. + + +NOT SUPPORTED IN 32-BIT MODE + + Not all the features of the 8-bit library are available with the 32-bit + library. The C++ and POSIX wrapper functions support only the 8-bit + library, and the pcregrep program is at present 8-bit only. + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 12 May 2013 + Copyright (c) 1997-2013 University of Cambridge. +------------------------------------------------------------------------------ + + +PCREBUILD(3) Library Functions Manual PCREBUILD(3) + + + +NAME + PCRE - Perl-compatible regular expressions + +BUILDING PCRE + + PCRE is distributed with a configure script that can be used to build + the library in Unix-like environments using the applications known as + Autotools. Also in the distribution are files to support building + using CMake instead of configure. The text file README contains general + information about building with Autotools (some of which is repeated + below), and also has some comments about building on various operating + systems. There is a lot more information about building PCRE without + using Autotools (including information about using CMake and building + "by hand") in the text file called NON-AUTOTOOLS-BUILD. You should + consult this file as well as the README file if you are building in a + non-Unix-like environment. + + +PCRE BUILD-TIME OPTIONS + + The rest of this document describes the optional features of PCRE that + can be selected when the library is compiled. It assumes use of the + configure script, where the optional features are selected or dese- + lected by providing options to configure before running the make com- + mand. However, the same options can be selected in both Unix-like and + non-Unix-like environments using the GUI facility of cmake-gui if you + are using CMake instead of configure to build PCRE. + + If you are not using Autotools or CMake, option selection can be done + by editing the config.h file, or by passing parameter settings to the + compiler, as described in NON-AUTOTOOLS-BUILD. + + The complete list of options for configure (which includes the standard + ones such as the selection of the installation directory) can be + obtained by running + + ./configure --help + + The following sections include descriptions of options whose names + begin with --enable or --disable. These settings specify changes to the + defaults for the configure command. Because of the way that configure + works, --enable and --disable always come in pairs, so the complemen- + tary option always exists as well, but as it specifies the default, it + is not described. + + +BUILDING 8-BIT, 16-BIT AND 32-BIT LIBRARIES + + By default, a library called libpcre is built, containing functions + that take string arguments contained in vectors of bytes, either as + single-byte characters, or interpreted as UTF-8 strings. You can also + build a separate library, called libpcre16, in which strings are con- + tained in vectors of 16-bit data units and interpreted either as sin- + gle-unit characters or UTF-16 strings, by adding + + --enable-pcre16 + + to the configure command. You can also build yet another separate + library, called libpcre32, in which strings are contained in vectors of + 32-bit data units and interpreted either as single-unit characters or + UTF-32 strings, by adding + + --enable-pcre32 + + to the configure command. If you do not want the 8-bit library, add + + --disable-pcre8 + + as well. At least one of the three libraries must be built. Note that + the C++ and POSIX wrappers are for the 8-bit library only, and that + pcregrep is an 8-bit program. None of these are built if you select + only the 16-bit or 32-bit libraries. + + +BUILDING SHARED AND STATIC LIBRARIES + + The Autotools PCRE building process uses libtool to build both shared + and static libraries by default. You can suppress one of these by + adding one of + + --disable-shared + --disable-static + + to the configure command, as required. + + +C++ SUPPORT + + By default, if the 8-bit library is being built, the configure script + will search for a C++ compiler and C++ header files. If it finds them, + it automatically builds the C++ wrapper library (which supports only + 8-bit strings). You can disable this by adding + + --disable-cpp + + to the configure command. + + +UTF-8, UTF-16 AND UTF-32 SUPPORT + + To build PCRE with support for UTF Unicode character strings, add + + --enable-utf + + to the configure command. This setting applies to all three libraries, + adding support for UTF-8 to the 8-bit library, support for UTF-16 to + the 16-bit library, and support for UTF-32 to the to the 32-bit + library. There are no separate options for enabling UTF-8, UTF-16 and + UTF-32 independently because that would allow ridiculous settings such + as requesting UTF-16 support while building only the 8-bit library. It + is not possible to build one library with UTF support and another with- + out in the same configuration. (For backwards compatibility, --enable- + utf8 is a synonym of --enable-utf.) + + Of itself, this setting does not make PCRE treat strings as UTF-8, + UTF-16 or UTF-32. As well as compiling PCRE with this option, you also + have have to set the PCRE_UTF8, PCRE_UTF16 or PCRE_UTF32 option (as + appropriate) when you call one of the pattern compiling functions. + + If you set --enable-utf when compiling in an EBCDIC environment, PCRE + expects its input to be either ASCII or UTF-8 (depending on the run- + time option). It is not possible to support both EBCDIC and UTF-8 codes + in the same version of the library. Consequently, --enable-utf and + --enable-ebcdic are mutually exclusive. + + +UNICODE CHARACTER PROPERTY SUPPORT + + UTF support allows the libraries to process character codepoints up to + 0x10ffff in the strings that they handle. On its own, however, it does + not provide any facilities for accessing the properties of such charac- + ters. If you want to be able to use the pattern escapes \P, \p, and \X, + which refer to Unicode character properties, you must add + + --enable-unicode-properties + + to the configure command. This implies UTF support, even if you have + not explicitly requested it. + + Including Unicode property support adds around 30K of tables to the + PCRE library. Only the general category properties such as Lu and Nd + are supported. Details are given in the pcrepattern documentation. + + +JUST-IN-TIME COMPILER SUPPORT + + Just-in-time compiler support is included in the build by specifying + + --enable-jit + + This support is available only for certain hardware architectures. If + this option is set for an unsupported architecture, a compile time + error occurs. See the pcrejit documentation for a discussion of JIT + usage. When JIT support is enabled, pcregrep automatically makes use of + it, unless you add + + --disable-pcregrep-jit + + to the "configure" command. + + +CODE VALUE OF NEWLINE + + By default, PCRE interprets the linefeed (LF) character as indicating + the end of a line. This is the normal newline character on Unix-like + systems. You can compile PCRE to use carriage return (CR) instead, by + adding + + --enable-newline-is-cr + + to the configure command. There is also a --enable-newline-is-lf + option, which explicitly specifies linefeed as the newline character. + + Alternatively, you can specify that line endings are to be indicated by + the two character sequence CRLF. If you want this, add + + --enable-newline-is-crlf + + to the configure command. There is a fourth option, specified by + + --enable-newline-is-anycrlf + + which causes PCRE to recognize any of the three sequences CR, LF, or + CRLF as indicating a line ending. Finally, a fifth option, specified by + + --enable-newline-is-any + + causes PCRE to recognize any Unicode newline sequence. + + Whatever line ending convention is selected when PCRE is built can be + overridden when the library functions are called. At build time it is + conventional to use the standard for your operating system. + + +WHAT \R MATCHES + + By default, the sequence \R in a pattern matches any Unicode newline + sequence, whatever has been selected as the line ending sequence. If + you specify + + --enable-bsr-anycrlf + + the default is changed so that \R matches only CR, LF, or CRLF. What- + ever is selected when PCRE is built can be overridden when the library + functions are called. + + +POSIX MALLOC USAGE + + When the 8-bit library is called through the POSIX interface (see the + pcreposix documentation), additional working storage is required for + holding the pointers to capturing substrings, because PCRE requires + three integers per substring, whereas the POSIX interface provides only + two. If the number of expected substrings is small, the wrapper func- + tion uses space on the stack, because this is faster than using mal- + loc() for each call. The default threshold above which the stack is no + longer used is 10; it can be changed by adding a setting such as + + --with-posix-malloc-threshold=20 + + to the configure command. + + +HANDLING VERY LARGE PATTERNS + + Within a compiled pattern, offset values are used to point from one + part to another (for example, from an opening parenthesis to an alter- + nation metacharacter). By default, in the 8-bit and 16-bit libraries, + two-byte values are used for these offsets, leading to a maximum size + for a compiled pattern of around 64K. This is sufficient to handle all + but the most gigantic patterns. Nevertheless, some people do want to + process truly enormous patterns, so it is possible to compile PCRE to + use three-byte or four-byte offsets by adding a setting such as + + --with-link-size=3 + + to the configure command. The value given must be 2, 3, or 4. For the + 16-bit library, a value of 3 is rounded up to 4. In these libraries, + using longer offsets slows down the operation of PCRE because it has to + load additional data when handling them. For the 32-bit library the + value is always 4 and cannot be overridden; the value of --with-link- + size is ignored. + + +AVOIDING EXCESSIVE STACK USAGE + + When matching with the pcre_exec() function, PCRE implements backtrack- + ing by making recursive calls to an internal function called match(). + In environments where the size of the stack is limited, this can se- + verely limit PCRE's operation. (The Unix environment does not usually + suffer from this problem, but it may sometimes be necessary to increase + the maximum stack size. There is a discussion in the pcrestack docu- + mentation.) An alternative approach to recursion that uses memory from + the heap to remember data, instead of using recursive function calls, + has been implemented to work round the problem of limited stack size. + If you want to build a version of PCRE that works this way, add + + --disable-stack-for-recursion + + to the configure command. With this configuration, PCRE will use the + pcre_stack_malloc and pcre_stack_free variables to call memory manage- + ment functions. By default these point to malloc() and free(), but you + can replace the pointers so that your own functions are used instead. + + Separate functions are provided rather than using pcre_malloc and + pcre_free because the usage is very predictable: the block sizes + requested are always the same, and the blocks are always freed in + reverse order. A calling program might be able to implement optimized + functions that perform better than malloc() and free(). PCRE runs + noticeably more slowly when built in this way. This option affects only + the pcre_exec() function; it is not relevant for pcre_dfa_exec(). + + +LIMITING PCRE RESOURCE USAGE + + Internally, PCRE has a function called match(), which it calls repeat- + edly (sometimes recursively) when matching a pattern with the + pcre_exec() function. By controlling the maximum number of times this + function may be called during a single matching operation, a limit can + be placed on the resources used by a single call to pcre_exec(). The + limit can be changed at run time, as described in the pcreapi documen- + tation. The default is 10 million, but this can be changed by adding a + setting such as + + --with-match-limit=500000 + + to the configure command. This setting has no effect on the + pcre_dfa_exec() matching function. + + In some environments it is desirable to limit the depth of recursive + calls of match() more strictly than the total number of calls, in order + to restrict the maximum amount of stack (or heap, if --disable-stack- + for-recursion is specified) that is used. A second limit controls this; + it defaults to the value that is set for --with-match-limit, which + imposes no additional constraints. However, you can set a lower limit + by adding, for example, + + --with-match-limit-recursion=10000 + + to the configure command. This value can also be overridden at run + time. + + +CREATING CHARACTER TABLES AT BUILD TIME + + PCRE uses fixed tables for processing characters whose code values are + less than 256. By default, PCRE is built with a set of tables that are + distributed in the file pcre_chartables.c.dist. These tables are for + ASCII codes only. If you add + + --enable-rebuild-chartables + + to the configure command, the distributed tables are no longer used. + Instead, a program called dftables is compiled and run. This outputs + the source for new set of tables, created in the default locale of your + C run-time system. (This method of replacing the tables does not work + if you are cross compiling, because dftables is run on the local host. + If you need to create alternative tables when cross compiling, you will + have to do so "by hand".) + + +USING EBCDIC CODE + + PCRE assumes by default that it will run in an environment where the + character code is ASCII (or Unicode, which is a superset of ASCII). + This is the case for most computer operating systems. PCRE can, how- + ever, be compiled to run in an EBCDIC environment by adding + + --enable-ebcdic + + to the configure command. This setting implies --enable-rebuild-charta- + bles. You should only use it if you know that you are in an EBCDIC + environment (for example, an IBM mainframe operating system). The + --enable-ebcdic option is incompatible with --enable-utf. + + The EBCDIC character that corresponds to an ASCII LF is assumed to have + the value 0x15 by default. However, in some EBCDIC environments, 0x25 + is used. In such an environment you should use + + --enable-ebcdic-nl25 + + as well as, or instead of, --enable-ebcdic. The EBCDIC character for CR + has the same value as in ASCII, namely, 0x0d. Whichever of 0x15 and + 0x25 is not chosen as LF is made to correspond to the Unicode NEL char- + acter (which, in Unicode, is 0x85). + + The options that select newline behaviour, such as --enable-newline-is- + cr, and equivalent run-time options, refer to these character values in + an EBCDIC environment. + + +PCREGREP OPTIONS FOR COMPRESSED FILE SUPPORT + + By default, pcregrep reads all files as plain text. You can build it so + that it recognizes files whose names end in .gz or .bz2, and reads them + with libz or libbz2, respectively, by adding one or both of + + --enable-pcregrep-libz + --enable-pcregrep-libbz2 + + to the configure command. These options naturally require that the rel- + evant libraries are installed on your system. Configuration will fail + if they are not. + + +PCREGREP BUFFER SIZE + + pcregrep uses an internal buffer to hold a "window" on the file it is + scanning, in order to be able to output "before" and "after" lines when + it finds a match. The size of the buffer is controlled by a parameter + whose default value is 20K. The buffer itself is three times this size, + but because of the way it is used for holding "before" lines, the long- + est line that is guaranteed to be processable is the parameter size. + You can change the default parameter value by adding, for example, + + --with-pcregrep-bufsize=50K + + to the configure command. The caller of pcregrep can, however, override + this value by specifying a run-time option. + + +PCRETEST OPTION FOR LIBREADLINE SUPPORT + + If you add + + --enable-pcretest-libreadline + + to the configure command, pcretest is linked with the libreadline + library, and when its input is from a terminal, it reads it using the + readline() function. This provides line-editing and history facilities. + Note that libreadline is GPL-licensed, so if you distribute a binary of + pcretest linked in this way, there may be licensing issues. + + Setting this option causes the -lreadline option to be added to the + pcretest build. In many operating environments with a sytem-installed + libreadline this is sufficient. However, in some environments (e.g. if + an unmodified distribution version of readline is in use), some extra + configuration may be necessary. The INSTALL file for libreadline says + this: + + "Readline uses the termcap functions, but does not link with the + termcap or curses library itself, allowing applications which link + with readline the to choose an appropriate library." + + If your environment has not been set up so that an appropriate library + is automatically included, you may need to add something like + + LIBS="-ncurses" + + immediately before the configure command. + + +DEBUGGING WITH VALGRIND SUPPORT + + By adding the + + --enable-valgrind + + option to to the configure command, PCRE will use valgrind annotations + to mark certain memory regions as unaddressable. This allows it to + detect invalid memory accesses, and is mostly useful for debugging PCRE + itself. + + +CODE COVERAGE REPORTING + + If your C compiler is gcc, you can build a version of PCRE that can + generate a code coverage report for its test suite. To enable this, you + must install lcov version 1.6 or above. Then specify + + --enable-coverage + + to the configure command and build PCRE in the usual way. + + Note that using ccache (a caching C compiler) is incompatible with code + coverage reporting. If you have configured ccache to run automatically + on your system, you must set the environment variable + + CCACHE_DISABLE=1 + + before running make to build PCRE, so that ccache is not used. + + When --enable-coverage is used, the following addition targets are + added to the Makefile: + + make coverage + + This creates a fresh coverage report for the PCRE test suite. It is + equivalent to running "make coverage-reset", "make coverage-baseline", + "make check", and then "make coverage-report". + + make coverage-reset + + This zeroes the coverage counters, but does nothing else. + + make coverage-baseline + + This captures baseline coverage information. + + make coverage-report + + This creates the coverage report. + + make coverage-clean-report + + This removes the generated coverage report without cleaning the cover- + age data itself. + + make coverage-clean-data + + This removes the captured coverage data without removing the coverage + files created at compile time (*.gcno). + + make coverage-clean + + This cleans all coverage data including the generated coverage report. + For more information about code coverage, see the gcov and lcov docu- + mentation. + + +SEE ALSO + + pcreapi(3), pcre16, pcre32, pcre_config(3). + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 12 May 2013 + Copyright (c) 1997-2013 University of Cambridge. +------------------------------------------------------------------------------ + + +PCREMATCHING(3) Library Functions Manual PCREMATCHING(3) + + + +NAME + PCRE - Perl-compatible regular expressions + +PCRE MATCHING ALGORITHMS + + This document describes the two different algorithms that are available + in PCRE for matching a compiled regular expression against a given sub- + ject string. The "standard" algorithm is the one provided by the + pcre_exec(), pcre16_exec() and pcre32_exec() functions. These work in + the same as as Perl's matching function, and provide a Perl-compatible + matching operation. The just-in-time (JIT) optimization that is + described in the pcrejit documentation is compatible with these func- + tions. + + An alternative algorithm is provided by the pcre_dfa_exec(), + pcre16_dfa_exec() and pcre32_dfa_exec() functions; they operate in a + different way, and are not Perl-compatible. This alternative has advan- + tages and disadvantages compared with the standard algorithm, and these + are described below. + + When there is only one possible way in which a given subject string can + match a pattern, the two algorithms give the same answer. A difference + arises, however, when there are multiple possibilities. For example, if + the pattern + + ^<.*> + + is matched against the string + + <something> <something else> <something further> + + there are three possible answers. The standard algorithm finds only one + of them, whereas the alternative algorithm finds all three. + + +REGULAR EXPRESSIONS AS TREES + + The set of strings that are matched by a regular expression can be rep- + resented as a tree structure. An unlimited repetition in the pattern + makes the tree of infinite size, but it is still a tree. Matching the + pattern to a given subject string (from a given starting point) can be + thought of as a search of the tree. There are two ways to search a + tree: depth-first and breadth-first, and these correspond to the two + matching algorithms provided by PCRE. + + +THE STANDARD MATCHING ALGORITHM + + In the terminology of Jeffrey Friedl's book "Mastering Regular Expres- + sions", the standard algorithm is an "NFA algorithm". It conducts a + depth-first search of the pattern tree. That is, it proceeds along a + single path through the tree, checking that the subject matches what is + required. When there is a mismatch, the algorithm tries any alterna- + tives at the current point, and if they all fail, it backs up to the + previous branch point in the tree, and tries the next alternative + branch at that level. This often involves backing up (moving to the + left) in the subject string as well. The order in which repetition + branches are tried is controlled by the greedy or ungreedy nature of + the quantifier. + + If a leaf node is reached, a matching string has been found, and at + that point the algorithm stops. Thus, if there is more than one possi- + ble match, this algorithm returns the first one that it finds. Whether + this is the shortest, the longest, or some intermediate length depends + on the way the greedy and ungreedy repetition quantifiers are specified + in the pattern. + + Because it ends up with a single path through the tree, it is rela- + tively straightforward for this algorithm to keep track of the sub- + strings that are matched by portions of the pattern in parentheses. + This provides support for capturing parentheses and back references. + + +THE ALTERNATIVE MATCHING ALGORITHM + + This algorithm conducts a breadth-first search of the tree. Starting + from the first matching point in the subject, it scans the subject + string from left to right, once, character by character, and as it does + this, it remembers all the paths through the tree that represent valid + matches. In Friedl's terminology, this is a kind of "DFA algorithm", + though it is not implemented as a traditional finite state machine (it + keeps multiple states active simultaneously). + + Although the general principle of this matching algorithm is that it + scans the subject string only once, without backtracking, there is one + exception: when a lookaround assertion is encountered, the characters + following or preceding the current point have to be independently + inspected. + + The scan continues until either the end of the subject is reached, or + there are no more unterminated paths. At this point, terminated paths + represent the different matching possibilities (if there are none, the + match has failed). Thus, if there is more than one possible match, + this algorithm finds all of them, and in particular, it finds the long- + est. The matches are returned in decreasing order of length. There is + an option to stop the algorithm after the first match (which is neces- + sarily the shortest) is found. + + Note that all the matches that are found start at the same point in the + subject. If the pattern + + cat(er(pillar)?)? + + is matched against the string "the caterpillar catchment", the result + will be the three strings "caterpillar", "cater", and "cat" that start + at the fifth character of the subject. The algorithm does not automati- + cally move on to find matches that start at later positions. + + PCRE's "auto-possessification" optimization usually applies to charac- + ter repeats at the end of a pattern (as well as internally). For exam- + ple, the pattern "a\d+" is compiled as if it were "a\d++" because there + is no point even considering the possibility of backtracking into the + repeated digits. For DFA matching, this means that only one possible + match is found. If you really do want multiple matches in such cases, + either use an ungreedy repeat ("a\d+?") or set the PCRE_NO_AUTO_POSSESS + option when compiling. + + There are a number of features of PCRE regular expressions that are not + supported by the alternative matching algorithm. They are as follows: + + 1. Because the algorithm finds all possible matches, the greedy or + ungreedy nature of repetition quantifiers is not relevant. Greedy and + ungreedy quantifiers are treated in exactly the same way. However, pos- + sessive quantifiers can make a difference when what follows could also + match what is quantified, for example in a pattern like this: + + ^a++\w! + + This pattern matches "aaab!" but not "aaa!", which would be matched by + a non-possessive quantifier. Similarly, if an atomic group is present, + it is matched as if it were a standalone pattern at the current point, + and the longest match is then "locked in" for the rest of the overall + pattern. + + 2. When dealing with multiple paths through the tree simultaneously, it + is not straightforward to keep track of captured substrings for the + different matching possibilities, and PCRE's implementation of this + algorithm does not attempt to do this. This means that no captured sub- + strings are available. + + 3. Because no substrings are captured, back references within the pat- + tern are not supported, and cause errors if encountered. + + 4. For the same reason, conditional expressions that use a backrefer- + ence as the condition or test for a specific group recursion are not + supported. + + 5. Because many paths through the tree may be active, the \K escape + sequence, which resets the start of the match when encountered (but may + be on some paths and not on others), is not supported. It causes an + error if encountered. + + 6. Callouts are supported, but the value of the capture_top field is + always 1, and the value of the capture_last field is always -1. + + 7. The \C escape sequence, which (in the standard algorithm) always + matches a single data unit, even in UTF-8, UTF-16 or UTF-32 modes, is + not supported in these modes, because the alternative algorithm moves + through the subject string one character (not data unit) at a time, for + all active paths through the tree. + + 8. Except for (*FAIL), the backtracking control verbs such as (*PRUNE) + are not supported. (*FAIL) is supported, and behaves like a failing + negative assertion. + + +ADVANTAGES OF THE ALTERNATIVE ALGORITHM + + Using the alternative matching algorithm provides the following advan- + tages: + + 1. All possible matches (at a single point in the subject) are automat- + ically found, and in particular, the longest match is found. To find + more than one match using the standard algorithm, you have to do kludgy + things with callouts. + + 2. Because the alternative algorithm scans the subject string just + once, and never needs to backtrack (except for lookbehinds), it is pos- + sible to pass very long subject strings to the matching function in + several pieces, checking for partial matching each time. Although it is + possible to do multi-segment matching using the standard algorithm by + retaining partially matched substrings, it is more complicated. The + pcrepartial documentation gives details of partial matching and dis- + cusses multi-segment matching. + + +DISADVANTAGES OF THE ALTERNATIVE ALGORITHM + + The alternative algorithm suffers from a number of disadvantages: + + 1. It is substantially slower than the standard algorithm. This is + partly because it has to search for all possible matches, but is also + because it is less susceptible to optimization. + + 2. Capturing parentheses and back references are not supported. + + 3. Although atomic groups are supported, their use does not provide the + performance advantage that it does for the standard algorithm. + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 12 November 2013 + Copyright (c) 1997-2012 University of Cambridge. +------------------------------------------------------------------------------ + + +PCREAPI(3) Library Functions Manual PCREAPI(3) + + + +NAME + PCRE - Perl-compatible regular expressions + + #include <pcre.h> + + +PCRE NATIVE API BASIC FUNCTIONS + + pcre *pcre_compile(const char *pattern, int options, + const char **errptr, int *erroffset, + const unsigned char *tableptr); + + pcre *pcre_compile2(const char *pattern, int options, + int *errorcodeptr, + const char **errptr, int *erroffset, + const unsigned char *tableptr); + + pcre_extra *pcre_study(const pcre *code, int options, + const char **errptr); + + void pcre_free_study(pcre_extra *extra); + + int pcre_exec(const pcre *code, const pcre_extra *extra, + const char *subject, int length, int startoffset, + int options, int *ovector, int ovecsize); + + int pcre_dfa_exec(const pcre *code, const pcre_extra *extra, + const char *subject, int length, int startoffset, + int options, int *ovector, int ovecsize, + int *workspace, int wscount); + + +PCRE NATIVE API STRING EXTRACTION FUNCTIONS + + int pcre_copy_named_substring(const pcre *code, + const char *subject, int *ovector, + int stringcount, const char *stringname, + char *buffer, int buffersize); + + int pcre_copy_substring(const char *subject, int *ovector, + int stringcount, int stringnumber, char *buffer, + int buffersize); + + int pcre_get_named_substring(const pcre *code, + const char *subject, int *ovector, + int stringcount, const char *stringname, + const char **stringptr); + + int pcre_get_stringnumber(const pcre *code, + const char *name); + + int pcre_get_stringtable_entries(const pcre *code, + const char *name, char **first, char **last); + + int pcre_get_substring(const char *subject, int *ovector, + int stringcount, int stringnumber, + const char **stringptr); + + int pcre_get_substring_list(const char *subject, + int *ovector, int stringcount, const char ***listptr); + + void pcre_free_substring(const char *stringptr); + + void pcre_free_substring_list(const char **stringptr); + + +PCRE NATIVE API AUXILIARY FUNCTIONS + + int pcre_jit_exec(const pcre *code, const pcre_extra *extra, + const char *subject, int length, int startoffset, + int options, int *ovector, int ovecsize, + pcre_jit_stack *jstack); + + pcre_jit_stack *pcre_jit_stack_alloc(int startsize, int maxsize); + + void pcre_jit_stack_free(pcre_jit_stack *stack); + + void pcre_assign_jit_stack(pcre_extra *extra, + pcre_jit_callback callback, void *data); + + const unsigned char *pcre_maketables(void); + + int pcre_fullinfo(const pcre *code, const pcre_extra *extra, + int what, void *where); + + int pcre_refcount(pcre *code, int adjust); + + int pcre_config(int what, void *where); + + const char *pcre_version(void); + + int pcre_pattern_to_host_byte_order(pcre *code, + pcre_extra *extra, const unsigned char *tables); + + +PCRE NATIVE API INDIRECTED FUNCTIONS + + void *(*pcre_malloc)(size_t); + + void (*pcre_free)(void *); + + void *(*pcre_stack_malloc)(size_t); + + void (*pcre_stack_free)(void *); + + int (*pcre_callout)(pcre_callout_block *); + + int (*pcre_stack_guard)(void); + + +PCRE 8-BIT, 16-BIT, AND 32-BIT LIBRARIES + + As well as support for 8-bit character strings, PCRE also supports + 16-bit strings (from release 8.30) and 32-bit strings (from release + 8.32), by means of two additional libraries. They can be built as well + as, or instead of, the 8-bit library. To avoid too much complication, + this document describes the 8-bit versions of the functions, with only + occasional references to the 16-bit and 32-bit libraries. + + The 16-bit and 32-bit functions operate in the same way as their 8-bit + counterparts; they just use different data types for their arguments + and results, and their names start with pcre16_ or pcre32_ instead of + pcre_. For every option that has UTF8 in its name (for example, + PCRE_UTF8), there are corresponding 16-bit and 32-bit names with UTF8 + replaced by UTF16 or UTF32, respectively. This facility is in fact just + cosmetic; the 16-bit and 32-bit option names define the same bit val- + ues. + + References to bytes and UTF-8 in this document should be read as refer- + ences to 16-bit data units and UTF-16 when using the 16-bit library, or + 32-bit data units and UTF-32 when using the 32-bit library, unless + specified otherwise. More details of the specific differences for the + 16-bit and 32-bit libraries are given in the pcre16 and pcre32 pages. + + +PCRE API OVERVIEW + + PCRE has its own native API, which is described in this document. There + are also some wrapper functions (for the 8-bit library only) that cor- + respond to the POSIX regular expression API, but they do not give + access to all the functionality. They are described in the pcreposix + documentation. Both of these APIs define a set of C function calls. A + C++ wrapper (again for the 8-bit library only) is also distributed with + PCRE. It is documented in the pcrecpp page. + + The native API C function prototypes are defined in the header file + pcre.h, and on Unix-like systems the (8-bit) library itself is called + libpcre. It can normally be accessed by adding -lpcre to the command + for linking an application that uses PCRE. The header file defines the + macros PCRE_MAJOR and PCRE_MINOR to contain the major and minor release + numbers for the library. Applications can use these to include support + for different releases of PCRE. + + In a Windows environment, if you want to statically link an application + program against a non-dll pcre.a file, you must define PCRE_STATIC + before including pcre.h or pcrecpp.h, because otherwise the pcre_mal- + loc() and pcre_free() exported functions will be declared + __declspec(dllimport), with unwanted results. + + The functions pcre_compile(), pcre_compile2(), pcre_study(), and + pcre_exec() are used for compiling and matching regular expressions in + a Perl-compatible manner. A sample program that demonstrates the sim- + plest way of using them is provided in the file called pcredemo.c in + the PCRE source distribution. A listing of this program is given in the + pcredemo documentation, and the pcresample documentation describes how + to compile and run it. + + Just-in-time compiler support is an optional feature of PCRE that can + be built in appropriate hardware environments. It greatly speeds up the + matching performance of many patterns. Simple programs can easily + request that it be used if available, by setting an option that is + ignored when it is not relevant. More complicated programs might need + to make use of the functions pcre_jit_stack_alloc(), + pcre_jit_stack_free(), and pcre_assign_jit_stack() in order to control + the JIT code's memory usage. + + From release 8.32 there is also a direct interface for JIT execution, + which gives improved performance. The JIT-specific functions are dis- + cussed in the pcrejit documentation. + + A second matching function, pcre_dfa_exec(), which is not Perl-compati- + ble, is also provided. This uses a different algorithm for the match- + ing. The alternative algorithm finds all possible matches (at a given + point in the subject), and scans the subject just once (unless there + are lookbehind assertions). However, this algorithm does not return + captured substrings. A description of the two matching algorithms and + their advantages and disadvantages is given in the pcrematching docu- + mentation. + + In addition to the main compiling and matching functions, there are + convenience functions for extracting captured substrings from a subject + string that is matched by pcre_exec(). They are: + + pcre_copy_substring() + pcre_copy_named_substring() + pcre_get_substring() + pcre_get_named_substring() + pcre_get_substring_list() + pcre_get_stringnumber() + pcre_get_stringtable_entries() + + pcre_free_substring() and pcre_free_substring_list() are also provided, + to free the memory used for extracted strings. + + The function pcre_maketables() is used to build a set of character + tables in the current locale for passing to pcre_compile(), + pcre_exec(), or pcre_dfa_exec(). This is an optional facility that is + provided for specialist use. Most commonly, no special tables are + passed, in which case internal tables that are generated when PCRE is + built are used. + + The function pcre_fullinfo() is used to find out information about a + compiled pattern. The function pcre_version() returns a pointer to a + string containing the version of PCRE and its date of release. + + The function pcre_refcount() maintains a reference count in a data + block containing a compiled pattern. This is provided for the benefit + of object-oriented applications. + + The global variables pcre_malloc and pcre_free initially contain the + entry points of the standard malloc() and free() functions, respec- + tively. PCRE calls the memory management functions via these variables, + so a calling program can replace them if it wishes to intercept the + calls. This should be done before calling any PCRE functions. + + The global variables pcre_stack_malloc and pcre_stack_free are also + indirections to memory management functions. These special functions + are used only when PCRE is compiled to use the heap for remembering + data, instead of recursive function calls, when running the pcre_exec() + function. See the pcrebuild documentation for details of how to do + this. It is a non-standard way of building PCRE, for use in environ- + ments that have limited stacks. Because of the greater use of memory + management, it runs more slowly. Separate functions are provided so + that special-purpose external code can be used for this case. When + used, these functions are always called in a stack-like manner (last + obtained, first freed), and always for memory blocks of the same size. + There is a discussion about PCRE's stack usage in the pcrestack docu- + mentation. + + The global variable pcre_callout initially contains NULL. It can be set + by the caller to a "callout" function, which PCRE will then call at + specified points during a matching operation. Details are given in the + pcrecallout documentation. + + The global variable pcre_stack_guard initially contains NULL. It can be + set by the caller to a function that is called by PCRE whenever it + starts to compile a parenthesized part of a pattern. When parentheses + are nested, PCRE uses recursive function calls, which use up the system + stack. This function is provided so that applications with restricted + stacks can force a compilation error if the stack runs out. The func- + tion should return zero if all is well, or non-zero to force an error. + + +NEWLINES + + PCRE supports five different conventions for indicating line breaks in + strings: a single CR (carriage return) character, a single LF (line- + feed) character, the two-character sequence CRLF, any of the three pre- + ceding, or any Unicode newline sequence. The Unicode newline sequences + are the three just mentioned, plus the single characters VT (vertical + tab, U+000B), FF (form feed, U+000C), NEL (next line, U+0085), LS (line + separator, U+2028), and PS (paragraph separator, U+2029). + + Each of the first three conventions is used by at least one operating + system as its standard newline sequence. When PCRE is built, a default + can be specified. The default default is LF, which is the Unix stan- + dard. When PCRE is run, the default can be overridden, either when a + pattern is compiled, or when it is matched. + + At compile time, the newline convention can be specified by the options + argument of pcre_compile(), or it can be specified by special text at + the start of the pattern itself; this overrides any other settings. See + the pcrepattern page for details of the special character sequences. + + In the PCRE documentation the word "newline" is used to mean "the char- + acter or pair of characters that indicate a line break". The choice of + newline convention affects the handling of the dot, circumflex, and + dollar metacharacters, the handling of #-comments in /x mode, and, when + CRLF is a recognized line ending sequence, the match position advance- + ment for a non-anchored pattern. There is more detail about this in the + section on pcre_exec() options below. + + The choice of newline convention does not affect the interpretation of + the \n or \r escape sequences, nor does it affect what \R matches, + which is controlled in a similar way, but by separate options. + + +MULTITHREADING + + The PCRE functions can be used in multi-threading applications, with + the proviso that the memory management functions pointed to by + pcre_malloc, pcre_free, pcre_stack_malloc, and pcre_stack_free, and the + callout and stack-checking functions pointed to by pcre_callout and + pcre_stack_guard, are shared by all threads. + + The compiled form of a regular expression is not altered during match- + ing, so the same compiled pattern can safely be used by several threads + at once. + + If the just-in-time optimization feature is being used, it needs sepa- + rate memory stack areas for each thread. See the pcrejit documentation + for more details. + + +SAVING PRECOMPILED PATTERNS FOR LATER USE + + The compiled form of a regular expression can be saved and re-used at a + later time, possibly by a different program, and even on a host other + than the one on which it was compiled. Details are given in the + pcreprecompile documentation, which includes a description of the + pcre_pattern_to_host_byte_order() function. However, compiling a regu- + lar expression with one version of PCRE for use with a different ver- + sion is not guaranteed to work and may cause crashes. + + +CHECKING BUILD-TIME OPTIONS + + int pcre_config(int what, void *where); + + The function pcre_config() makes it possible for a PCRE client to dis- + cover which optional features have been compiled into the PCRE library. + The pcrebuild documentation has more details about these optional fea- + tures. + + The first argument for pcre_config() is an integer, specifying which + information is required; the second argument is a pointer to a variable + into which the information is placed. The returned value is zero on + success, or the negative error code PCRE_ERROR_BADOPTION if the value + in the first argument is not recognized. The following information is + available: + + PCRE_CONFIG_UTF8 + + The output is an integer that is set to one if UTF-8 support is avail- + able; otherwise it is set to zero. This value should normally be given + to the 8-bit version of this function, pcre_config(). If it is given to + the 16-bit or 32-bit version of this function, the result is + PCRE_ERROR_BADOPTION. + + PCRE_CONFIG_UTF16 + + The output is an integer that is set to one if UTF-16 support is avail- + able; otherwise it is set to zero. This value should normally be given + to the 16-bit version of this function, pcre16_config(). If it is given + to the 8-bit or 32-bit version of this function, the result is + PCRE_ERROR_BADOPTION. + + PCRE_CONFIG_UTF32 + + The output is an integer that is set to one if UTF-32 support is avail- + able; otherwise it is set to zero. This value should normally be given + to the 32-bit version of this function, pcre32_config(). If it is given + to the 8-bit or 16-bit version of this function, the result is + PCRE_ERROR_BADOPTION. + + PCRE_CONFIG_UNICODE_PROPERTIES + + The output is an integer that is set to one if support for Unicode + character properties is available; otherwise it is set to zero. + + PCRE_CONFIG_JIT + + The output is an integer that is set to one if support for just-in-time + compiling is available; otherwise it is set to zero. + + PCRE_CONFIG_JITTARGET + + The output is a pointer to a zero-terminated "const char *" string. If + JIT support is available, the string contains the name of the architec- + ture for which the JIT compiler is configured, for example "x86 32bit + (little endian + unaligned)". If JIT support is not available, the + result is NULL. + + PCRE_CONFIG_NEWLINE + + The output is an integer whose value specifies the default character + sequence that is recognized as meaning "newline". The values that are + supported in ASCII/Unicode environments are: 10 for LF, 13 for CR, 3338 + for CRLF, -2 for ANYCRLF, and -1 for ANY. In EBCDIC environments, CR, + ANYCRLF, and ANY yield the same values. However, the value for LF is + normally 21, though some EBCDIC environments use 37. The corresponding + values for CRLF are 3349 and 3365. The default should normally corre- + spond to the standard sequence for your operating system. + + PCRE_CONFIG_BSR + + The output is an integer whose value indicates what character sequences + the \R escape sequence matches by default. A value of 0 means that \R + matches any Unicode line ending sequence; a value of 1 means that \R + matches only CR, LF, or CRLF. The default can be overridden when a pat- + tern is compiled or matched. + + PCRE_CONFIG_LINK_SIZE + + The output is an integer that contains the number of bytes used for + internal linkage in compiled regular expressions. For the 8-bit + library, the value can be 2, 3, or 4. For the 16-bit library, the value + is either 2 or 4 and is still a number of bytes. For the 32-bit + library, the value is either 2 or 4 and is still a number of bytes. The + default value of 2 is sufficient for all but the most massive patterns, + since it allows the compiled pattern to be up to 64K in size. Larger + values allow larger regular expressions to be compiled, at the expense + of slower matching. + + PCRE_CONFIG_POSIX_MALLOC_THRESHOLD + + The output is an integer that contains the threshold above which the + POSIX interface uses malloc() for output vectors. Further details are + given in the pcreposix documentation. + + PCRE_CONFIG_PARENS_LIMIT + + The output is a long integer that gives the maximum depth of nesting of + parentheses (of any kind) in a pattern. This limit is imposed to cap + the amount of system stack used when a pattern is compiled. It is spec- + ified when PCRE is built; the default is 250. This limit does not take + into account the stack that may already be used by the calling applica- + tion. For finer control over compilation stack usage, you can set a + pointer to an external checking function in pcre_stack_guard. + + PCRE_CONFIG_MATCH_LIMIT + + The output is a long integer that gives the default limit for the num- + ber of internal matching function calls in a pcre_exec() execution. + Further details are given with pcre_exec() below. + + PCRE_CONFIG_MATCH_LIMIT_RECURSION + + The output is a long integer that gives the default limit for the depth + of recursion when calling the internal matching function in a + pcre_exec() execution. Further details are given with pcre_exec() + below. + + PCRE_CONFIG_STACKRECURSE + + The output is an integer that is set to one if internal recursion when + running pcre_exec() is implemented by recursive function calls that use + the stack to remember their state. This is the usual way that PCRE is + compiled. The output is zero if PCRE was compiled to use blocks of data + on the heap instead of recursive function calls. In this case, + pcre_stack_malloc and pcre_stack_free are called to manage memory + blocks on the heap, thus avoiding the use of the stack. + + +COMPILING A PATTERN + + pcre *pcre_compile(const char *pattern, int options, + const char **errptr, int *erroffset, + const unsigned char *tableptr); + + pcre *pcre_compile2(const char *pattern, int options, + int *errorcodeptr, + const char **errptr, int *erroffset, + const unsigned char *tableptr); + + Either of the functions pcre_compile() or pcre_compile2() can be called + to compile a pattern into an internal form. The only difference between + the two interfaces is that pcre_compile2() has an additional argument, + errorcodeptr, via which a numerical error code can be returned. To + avoid too much repetition, we refer just to pcre_compile() below, but + the information applies equally to pcre_compile2(). + + The pattern is a C string terminated by a binary zero, and is passed in + the pattern argument. A pointer to a single block of memory that is + obtained via pcre_malloc is returned. This contains the compiled code + and related data. The pcre type is defined for the returned block; this + is a typedef for a structure whose contents are not externally defined. + It is up to the caller to free the memory (via pcre_free) when it is no + longer required. + + Although the compiled code of a PCRE regex is relocatable, that is, it + does not depend on memory location, the complete pcre data block is not + fully relocatable, because it may contain a copy of the tableptr argu- + ment, which is an address (see below). + + The options argument contains various bit settings that affect the com- + pilation. It should be zero if no options are required. The available + options are described below. Some of them (in particular, those that + are compatible with Perl, but some others as well) can also be set and + unset from within the pattern (see the detailed description in the + pcrepattern documentation). For those options that can be different in + different parts of the pattern, the contents of the options argument + specifies their settings at the start of compilation and execution. The + PCRE_ANCHORED, PCRE_BSR_xxx, PCRE_NEWLINE_xxx, PCRE_NO_UTF8_CHECK, and + PCRE_NO_START_OPTIMIZE options can be set at the time of matching as + well as at compile time. + + If errptr is NULL, pcre_compile() returns NULL immediately. Otherwise, + if compilation of a pattern fails, pcre_compile() returns NULL, and + sets the variable pointed to by errptr to point to a textual error mes- + sage. This is a static string that is part of the library. You must not + try to free it. Normally, the offset from the start of the pattern to + the data unit that was being processed when the error was discovered is + placed in the variable pointed to by erroffset, which must not be NULL + (if it is, an immediate error is given). However, for an invalid UTF-8 + or UTF-16 string, the offset is that of the first data unit of the + failing character. + + Some errors are not detected until the whole pattern has been scanned; + in these cases, the offset passed back is the length of the pattern. + Note that the offset is in data units, not characters, even in a UTF + mode. It may sometimes point into the middle of a UTF-8 or UTF-16 char- + acter. + + If pcre_compile2() is used instead of pcre_compile(), and the error- + codeptr argument is not NULL, a non-zero error code number is returned + via this argument in the event of an error. This is in addition to the + textual error message. Error codes and messages are listed below. + + If the final argument, tableptr, is NULL, PCRE uses a default set of + character tables that are built when PCRE is compiled, using the + default C locale. Otherwise, tableptr must be an address that is the + result of a call to pcre_maketables(). This value is stored with the + compiled pattern, and used again by pcre_exec() and pcre_dfa_exec() + when the pattern is matched. For more discussion, see the section on + locale support below. + + This code fragment shows a typical straightforward call to pcre_com- + pile(): + + pcre *re; + const char *error; + int erroffset; + re = pcre_compile( + "^A.*Z", /* the pattern */ + 0, /* default options */ + &error, /* for error message */ + &erroffset, /* for error offset */ + NULL); /* use default character tables */ + + The following names for option bits are defined in the pcre.h header + file: + + PCRE_ANCHORED + + If this bit is set, the pattern is forced to be "anchored", that is, it + is constrained to match only at the first matching point in the string + that is being searched (the "subject string"). This effect can also be + achieved by appropriate constructs in the pattern itself, which is the + only way to do it in Perl. + + PCRE_AUTO_CALLOUT + + If this bit is set, pcre_compile() automatically inserts callout items, + all with number 255, before each pattern item. For discussion of the + callout facility, see the pcrecallout documentation. + + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE + + These options (which are mutually exclusive) control what the \R escape + sequence matches. The choice is either to match only CR, LF, or CRLF, + or to match any Unicode newline sequence. The default is specified when + PCRE is built. It can be overridden from within the pattern, or by set- + ting an option when a compiled pattern is matched. + + PCRE_CASELESS + + If this bit is set, letters in the pattern match both upper and lower + case letters. It is equivalent to Perl's /i option, and it can be + changed within a pattern by a (?i) option setting. In UTF-8 mode, PCRE + always understands the concept of case for characters whose values are + less than 128, so caseless matching is always possible. For characters + with higher values, the concept of case is supported if PCRE is com- + piled with Unicode property support, but not otherwise. If you want to + use caseless matching for characters 128 and above, you must ensure + that PCRE is compiled with Unicode property support as well as with + UTF-8 support. + + PCRE_DOLLAR_ENDONLY + + If this bit is set, a dollar metacharacter in the pattern matches only + at the end of the subject string. Without this option, a dollar also + matches immediately before a newline at the end of the string (but not + before any other newlines). The PCRE_DOLLAR_ENDONLY option is ignored + if PCRE_MULTILINE is set. There is no equivalent to this option in + Perl, and no way to set it within a pattern. + + PCRE_DOTALL + + If this bit is set, a dot metacharacter in the pattern matches a char- + acter of any value, including one that indicates a newline. However, it + only ever matches one character, even if newlines are coded as CRLF. + Without this option, a dot does not match when the current position is + at a newline. This option is equivalent to Perl's /s option, and it can + be changed within a pattern by a (?s) option setting. A negative class + such as [^a] always matches newline characters, independent of the set- + ting of this option. + + PCRE_DUPNAMES + + If this bit is set, names used to identify capturing subpatterns need + not be unique. This can be helpful for certain types of pattern when it + is known that only one instance of the named subpattern can ever be + matched. There are more details of named subpatterns below; see also + the pcrepattern documentation. + + PCRE_EXTENDED + + If this bit is set, most white space characters in the pattern are + totally ignored except when escaped or inside a character class. How- + ever, white space is not allowed within sequences such as (?> that + introduce various parenthesized subpatterns, nor within a numerical + quantifier such as {1,3}. However, ignorable white space is permitted + between an item and a following quantifier and between a quantifier and + a following + that indicates possessiveness. + + White space did not used to include the VT character (code 11), because + Perl did not treat this character as white space. However, Perl changed + at release 5.18, so PCRE followed at release 8.34, and VT is now + treated as white space. + + PCRE_EXTENDED also causes characters between an unescaped # outside a + character class and the next newline, inclusive, to be ignored. + PCRE_EXTENDED is equivalent to Perl's /x option, and it can be changed + within a pattern by a (?x) option setting. + + Which characters are interpreted as newlines is controlled by the + options passed to pcre_compile() or by a special sequence at the start + of the pattern, as described in the section entitled "Newline conven- + tions" in the pcrepattern documentation. Note that the end of this type + of comment is a literal newline sequence in the pattern; escape + sequences that happen to represent a newline do not count. + + This option makes it possible to include comments inside complicated + patterns. Note, however, that this applies only to data characters. + White space characters may never appear within special character + sequences in a pattern, for example within the sequence (?( that intro- + duces a conditional subpattern. + + PCRE_EXTRA + + This option was invented in order to turn on additional functionality + of PCRE that is incompatible with Perl, but it is currently of very + little use. When set, any backslash in a pattern that is followed by a + letter that has no special meaning causes an error, thus reserving + these combinations for future expansion. By default, as in Perl, a + backslash followed by a letter with no special meaning is treated as a + literal. (Perl can, however, be persuaded to give an error for this, by + running it with the -w option.) There are at present no other features + controlled by this option. It can also be set by a (?X) option setting + within a pattern. + + PCRE_FIRSTLINE + + If this option is set, an unanchored pattern is required to match + before or at the first newline in the subject string, though the + matched text may continue over the newline. + + PCRE_JAVASCRIPT_COMPAT + + If this option is set, PCRE's behaviour is changed in some ways so that + it is compatible with JavaScript rather than Perl. The changes are as + follows: + + (1) A lone closing square bracket in a pattern causes a compile-time + error, because this is illegal in JavaScript (by default it is treated + as a data character). Thus, the pattern AB]CD becomes illegal when this + option is set. + + (2) At run time, a back reference to an unset subpattern group matches + an empty string (by default this causes the current matching alterna- + tive to fail). A pattern such as (\1)(a) succeeds when this option is + set (assuming it can find an "a" in the subject), whereas it fails by + default, for Perl compatibility. + + (3) \U matches an upper case "U" character; by default \U causes a com- + pile time error (Perl uses \U to upper case subsequent characters). + + (4) \u matches a lower case "u" character unless it is followed by four + hexadecimal digits, in which case the hexadecimal number defines the + code point to match. By default, \u causes a compile time error (Perl + uses it to upper case the following character). + + (5) \x matches a lower case "x" character unless it is followed by two + hexadecimal digits, in which case the hexadecimal number defines the + code point to match. By default, as in Perl, a hexadecimal number is + always expected after \x, but it may have zero, one, or two digits (so, + for example, \xz matches a binary zero character followed by z). + + PCRE_MULTILINE + + By default, for the purposes of matching "start of line" and "end of + line", PCRE treats the subject string as consisting of a single line of + characters, even if it actually contains newlines. The "start of line" + metacharacter (^) matches only at the start of the string, and the "end + of line" metacharacter ($) matches only at the end of the string, or + before a terminating newline (except when PCRE_DOLLAR_ENDONLY is set). + Note, however, that unless PCRE_DOTALL is set, the "any character" + metacharacter (.) does not match at a newline. This behaviour (for ^, + $, and dot) is the same as Perl. + + When PCRE_MULTILINE it is set, the "start of line" and "end of line" + constructs match immediately following or immediately before internal + newlines in the subject string, respectively, as well as at the very + start and end. This is equivalent to Perl's /m option, and it can be + changed within a pattern by a (?m) option setting. If there are no new- + lines in a subject string, or no occurrences of ^ or $ in a pattern, + setting PCRE_MULTILINE has no effect. + + PCRE_NEVER_UTF + + This option locks out interpretation of the pattern as UTF-8 (or UTF-16 + or UTF-32 in the 16-bit and 32-bit libraries). In particular, it pre- + vents the creator of the pattern from switching to UTF interpretation + by starting the pattern with (*UTF). This may be useful in applications + that process patterns from external sources. The combination of + PCRE_UTF8 and PCRE_NEVER_UTF also causes an error. + + PCRE_NEWLINE_CR + PCRE_NEWLINE_LF + PCRE_NEWLINE_CRLF + PCRE_NEWLINE_ANYCRLF + PCRE_NEWLINE_ANY + + These options override the default newline definition that was chosen + when PCRE was built. Setting the first or the second specifies that a + newline is indicated by a single character (CR or LF, respectively). + Setting PCRE_NEWLINE_CRLF specifies that a newline is indicated by the + two-character CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies + that any of the three preceding sequences should be recognized. Setting + PCRE_NEWLINE_ANY specifies that any Unicode newline sequence should be + recognized. + + In an ASCII/Unicode environment, the Unicode newline sequences are the + three just mentioned, plus the single characters VT (vertical tab, + U+000B), FF (form feed, U+000C), NEL (next line, U+0085), LS (line sep- + arator, U+2028), and PS (paragraph separator, U+2029). For the 8-bit + library, the last two are recognized only in UTF-8 mode. + + When PCRE is compiled to run in an EBCDIC (mainframe) environment, the + code for CR is 0x0d, the same as ASCII. However, the character code for + LF is normally 0x15, though in some EBCDIC environments 0x25 is used. + Whichever of these is not LF is made to correspond to Unicode's NEL + character. EBCDIC codes are all less than 256. For more details, see + the pcrebuild documentation. + + The newline setting in the options word uses three bits that are + treated as a number, giving eight possibilities. Currently only six are + used (default plus the five values above). This means that if you set + more than one newline option, the combination may or may not be sensi- + ble. For example, PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to + PCRE_NEWLINE_CRLF, but other combinations may yield unused numbers and + cause an error. + + The only time that a line break in a pattern is specially recognized + when compiling is when PCRE_EXTENDED is set. CR and LF are white space + characters, and so are ignored in this mode. Also, an unescaped # out- + side a character class indicates a comment that lasts until after the + next line break sequence. In other circumstances, line break sequences + in patterns are treated as literal data. + + The newline option that is set at compile time becomes the default that + is used for pcre_exec() and pcre_dfa_exec(), but it can be overridden. + + PCRE_NO_AUTO_CAPTURE + + If this option is set, it disables the use of numbered capturing paren- + theses in the pattern. Any opening parenthesis that is not followed by + ? behaves as if it were followed by ?: but named parentheses can still + be used for capturing (and they acquire numbers in the usual way). + There is no equivalent of this option in Perl. + + PCRE_NO_AUTO_POSSESS + + If this option is set, it disables "auto-possessification". This is an + optimization that, for example, turns a+b into a++b in order to avoid + backtracks into a+ that can never be successful. However, if callouts + are in use, auto-possessification means that some of them are never + taken. You can set this option if you want the matching functions to do + a full unoptimized search and run all the callouts, but it is mainly + provided for testing purposes. + + PCRE_NO_START_OPTIMIZE + + This is an option that acts at matching time; that is, it is really an + option for pcre_exec() or pcre_dfa_exec(). If it is set at compile + time, it is remembered with the compiled pattern and assumed at match- + ing time. This is necessary if you want to use JIT execution, because + the JIT compiler needs to know whether or not this option is set. For + details see the discussion of PCRE_NO_START_OPTIMIZE below. + + PCRE_UCP + + This option changes the way PCRE processes \B, \b, \D, \d, \S, \s, \W, + \w, and some of the POSIX character classes. By default, only ASCII + characters are recognized, but if PCRE_UCP is set, Unicode properties + are used instead to classify characters. More details are given in the + section on generic character types in the pcrepattern page. If you set + PCRE_UCP, matching one of the items it affects takes much longer. The + option is available only if PCRE has been compiled with Unicode prop- + erty support. + + PCRE_UNGREEDY + + This option inverts the "greediness" of the quantifiers so that they + are not greedy by default, but become greedy if followed by "?". It is + not compatible with Perl. It can also be set by a (?U) option setting + within the pattern. + + PCRE_UTF8 + + This option causes PCRE to regard both the pattern and the subject as + strings of UTF-8 characters instead of single-byte strings. However, it + is available only when PCRE is built to include UTF support. If not, + the use of this option provokes an error. Details of how this option + changes the behaviour of PCRE are given in the pcreunicode page. + + PCRE_NO_UTF8_CHECK + + When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is + automatically checked. There is a discussion about the validity of + UTF-8 strings in the pcreunicode page. If an invalid UTF-8 sequence is + found, pcre_compile() returns an error. If you already know that your + pattern is valid, and you want to skip this check for performance rea- + sons, you can set the PCRE_NO_UTF8_CHECK option. When it is set, the + effect of passing an invalid UTF-8 string as a pattern is undefined. It + may cause your program to crash or loop. Note that this option can also + be passed to pcre_exec() and pcre_dfa_exec(), to suppress the validity + checking of subject strings only. If the same string is being matched + many times, the option can be safely set for the second and subsequent + matchings to improve performance. + + +COMPILATION ERROR CODES + + The following table lists the error codes than may be returned by + pcre_compile2(), along with the error messages that may be returned by + both compiling functions. Note that error messages are always 8-bit + ASCII strings, even in 16-bit or 32-bit mode. As PCRE has developed, + some error codes have fallen out of use. To avoid confusion, they have + not been re-used. + + 0 no error + 1 \ at end of pattern + 2 \c at end of pattern + 3 unrecognized character follows \ + 4 numbers out of order in {} quantifier + 5 number too big in {} quantifier + 6 missing terminating ] for character class + 7 invalid escape sequence in character class + 8 range out of order in character class + 9 nothing to repeat + 10 [this code is not in use] + 11 internal error: unexpected repeat + 12 unrecognized character after (? or (?- + 13 POSIX named classes are supported only within a class + 14 missing ) + 15 reference to non-existent subpattern + 16 erroffset passed as NULL + 17 unknown option bit(s) set + 18 missing ) after comment + 19 [this code is not in use] + 20 regular expression is too large + 21 failed to get memory + 22 unmatched parentheses + 23 internal error: code overflow + 24 unrecognized character after (?< + 25 lookbehind assertion is not fixed length + 26 malformed number or name after (?( + 27 conditional group contains more than two branches + 28 assertion expected after (?( + 29 (?R or (?[+-]digits must be followed by ) + 30 unknown POSIX class name + 31 POSIX collating elements are not supported + 32 this version of PCRE is compiled without UTF support + 33 [this code is not in use] + 34 character value in \x{} or \o{} is too large + 35 invalid condition (?(0) + 36 \C not allowed in lookbehind assertion + 37 PCRE does not support \L, \l, \N{name}, \U, or \u + 38 number after (?C is > 255 + 39 closing ) for (?C expected + 40 recursive call could loop indefinitely + 41 unrecognized character after (?P + 42 syntax error in subpattern name (missing terminator) + 43 two named subpatterns have the same name + 44 invalid UTF-8 string (specifically UTF-8) + 45 support for \P, \p, and \X has not been compiled + 46 malformed \P or \p sequence + 47 unknown property name after \P or \p + 48 subpattern name is too long (maximum 32 characters) + 49 too many named subpatterns (maximum 10000) + 50 [this code is not in use] + 51 octal value is greater than \377 in 8-bit non-UTF-8 mode + 52 internal error: overran compiling workspace + 53 internal error: previously-checked referenced subpattern + not found + 54 DEFINE group contains more than one branch + 55 repeating a DEFINE group is not allowed + 56 inconsistent NEWLINE options + 57 \g is not followed by a braced, angle-bracketed, or quoted + name/number or by a plain number + 58 a numbered reference must not be zero + 59 an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT) + 60 (*VERB) not recognized or malformed + 61 number is too big + 62 subpattern name expected + 63 digit expected after (?+ + 64 ] is an invalid data character in JavaScript compatibility mode + 65 different names for subpatterns of the same number are + not allowed + 66 (*MARK) must have an argument + 67 this version of PCRE is not compiled with Unicode property + support + 68 \c must be followed by an ASCII character + 69 \k is not followed by a braced, angle-bracketed, or quoted name + 70 internal error: unknown opcode in find_fixedlength() + 71 \N is not supported in a class + 72 too many forward references + 73 disallowed Unicode code point (>= 0xd800 && <= 0xdfff) + 74 invalid UTF-16 string (specifically UTF-16) + 75 name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN) + 76 character value in \u.... sequence is too large + 77 invalid UTF-32 string (specifically UTF-32) + 78 setting UTF is disabled by the application + 79 non-hex character in \x{} (closing brace missing?) + 80 non-octal character in \o{} (closing brace missing?) + 81 missing opening brace after \o + 82 parentheses are too deeply nested + 83 invalid range in character class + 84 group name must start with a non-digit + 85 parentheses are too deeply nested (stack check) + + The numbers 32 and 10000 in errors 48 and 49 are defaults; different + values may be used if the limits were changed when PCRE was built. + + +STUDYING A PATTERN + + pcre_extra *pcre_study(const pcre *code, int options, + const char **errptr); + + If a compiled pattern is going to be used several times, it is worth + spending more time analyzing it in order to speed up the time taken for + matching. The function pcre_study() takes a pointer to a compiled pat- + tern as its first argument. If studying the pattern produces additional + information that will help speed up matching, pcre_study() returns a + pointer to a pcre_extra block, in which the study_data field points to + the results of the study. + + The returned value from pcre_study() can be passed directly to + pcre_exec() or pcre_dfa_exec(). However, a pcre_extra block also con- + tains other fields that can be set by the caller before the block is + passed; these are described below in the section on matching a pattern. + + If studying the pattern does not produce any useful information, + pcre_study() returns NULL by default. In that circumstance, if the + calling program wants to pass any of the other fields to pcre_exec() or + pcre_dfa_exec(), it must set up its own pcre_extra block. However, if + pcre_study() is called with the PCRE_STUDY_EXTRA_NEEDED option, it + returns a pcre_extra block even if studying did not find any additional + information. It may still return NULL, however, if an error occurs in + pcre_study(). + + The second argument of pcre_study() contains option bits. There are + three further options in addition to PCRE_STUDY_EXTRA_NEEDED: + + PCRE_STUDY_JIT_COMPILE + PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE + PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE + + If any of these are set, and the just-in-time compiler is available, + the pattern is further compiled into machine code that executes much + faster than the pcre_exec() interpretive matching function. If the + just-in-time compiler is not available, these options are ignored. All + undefined bits in the options argument must be zero. + + JIT compilation is a heavyweight optimization. It can take some time + for patterns to be analyzed, and for one-off matches and simple pat- + terns the benefit of faster execution might be offset by a much slower + study time. Not all patterns can be optimized by the JIT compiler. For + those that cannot be handled, matching automatically falls back to the + pcre_exec() interpreter. For more details, see the pcrejit documenta- + tion. + + The third argument for pcre_study() is a pointer for an error message. + If studying succeeds (even if no data is returned), the variable it + points to is set to NULL. Otherwise it is set to point to a textual + error message. This is a static string that is part of the library. You + must not try to free it. You should test the error pointer for NULL + after calling pcre_study(), to be sure that it has run successfully. + + When you are finished with a pattern, you can free the memory used for + the study data by calling pcre_free_study(). This function was added to + the API for release 8.20. For earlier versions, the memory could be + freed with pcre_free(), just like the pattern itself. This will still + work in cases where JIT optimization is not used, but it is advisable + to change to the new function when convenient. + + This is a typical way in which pcre_study() is used (except that in a + real application there should be tests for errors): + + int rc; + pcre *re; + pcre_extra *sd; + re = pcre_compile("pattern", 0, &error, &erroroffset, NULL); + sd = pcre_study( + re, /* result of pcre_compile() */ + 0, /* no options */ + &error); /* set to NULL or points to a message */ + rc = pcre_exec( /* see below for details of pcre_exec() options */ + re, sd, "subject", 7, 0, 0, ovector, 30); + ... + pcre_free_study(sd); + pcre_free(re); + + Studying a pattern does two things: first, a lower bound for the length + of subject string that is needed to match the pattern is computed. This + does not mean that there are any strings of that length that match, but + it does guarantee that no shorter strings match. The value is used to + avoid wasting time by trying to match strings that are shorter than the + lower bound. You can find out the value in a calling program via the + pcre_fullinfo() function. + + Studying a pattern is also useful for non-anchored patterns that do not + have a single fixed starting character. A bitmap of possible starting + bytes is created. This speeds up finding a position in the subject at + which to start matching. (In 16-bit mode, the bitmap is used for 16-bit + values less than 256. In 32-bit mode, the bitmap is used for 32-bit + values less than 256.) + + These two optimizations apply to both pcre_exec() and pcre_dfa_exec(), + and the information is also used by the JIT compiler. The optimiza- + tions can be disabled by setting the PCRE_NO_START_OPTIMIZE option. + You might want to do this if your pattern contains callouts or (*MARK) + and you want to make use of these facilities in cases where matching + fails. + + PCRE_NO_START_OPTIMIZE can be specified at either compile time or exe- + cution time. However, if PCRE_NO_START_OPTIMIZE is passed to + pcre_exec(), (that is, after any JIT compilation has happened) JIT exe- + cution is disabled. For JIT execution to work with PCRE_NO_START_OPTI- + MIZE, the option must be set at compile time. + + There is a longer discussion of PCRE_NO_START_OPTIMIZE below. + + +LOCALE SUPPORT + + PCRE handles caseless matching, and determines whether characters are + letters, digits, or whatever, by reference to a set of tables, indexed + by character code point. When running in UTF-8 mode, or in the 16- or + 32-bit libraries, this applies only to characters with code points less + than 256. By default, higher-valued code points never match escapes + such as \w or \d. However, if PCRE is built with Unicode property sup- + port, all characters can be tested with \p and \P, or, alternatively, + the PCRE_UCP option can be set when a pattern is compiled; this causes + \w and friends to use Unicode property support instead of the built-in + tables. + + The use of locales with Unicode is discouraged. If you are handling + characters with code points greater than 128, you should either use + Unicode support, or use locales, but not try to mix the two. + + PCRE contains an internal set of tables that are used when the final + argument of pcre_compile() is NULL. These are sufficient for many + applications. Normally, the internal tables recognize only ASCII char- + acters. However, when PCRE is built, it is possible to cause the inter- + nal tables to be rebuilt in the default "C" locale of the local system, + which may cause them to be different. + + The internal tables can always be overridden by tables supplied by the + application that calls PCRE. These may be created in a different locale + from the default. As more and more applications change to using Uni- + code, the need for this locale support is expected to die away. + + External tables are built by calling the pcre_maketables() function, + which has no arguments, in the relevant locale. The result can then be + passed to pcre_compile() as often as necessary. For example, to build + and use tables that are appropriate for the French locale (where + accented characters with values greater than 128 are treated as let- + ters), the following code could be used: + + setlocale(LC_CTYPE, "fr_FR"); + tables = pcre_maketables(); + re = pcre_compile(..., tables); + + The locale name "fr_FR" is used on Linux and other Unix-like systems; + if you are using Windows, the name for the French locale is "french". + + When pcre_maketables() runs, the tables are built in memory that is + obtained via pcre_malloc. It is the caller's responsibility to ensure + that the memory containing the tables remains available for as long as + it is needed. + + The pointer that is passed to pcre_compile() is saved with the compiled + pattern, and the same tables are used via this pointer by pcre_study() + and also by pcre_exec() and pcre_dfa_exec(). Thus, for any single pat- + tern, compilation, studying and matching all happen in the same locale, + but different patterns can be processed in different locales. + + It is possible to pass a table pointer or NULL (indicating the use of + the internal tables) to pcre_exec() or pcre_dfa_exec() (see the discus- + sion below in the section on matching a pattern). This facility is pro- + vided for use with pre-compiled patterns that have been saved and + reloaded. Character tables are not saved with patterns, so if a non- + standard table was used at compile time, it must be provided again when + the reloaded pattern is matched. Attempting to use this facility to + match a pattern in a different locale from the one in which it was com- + piled is likely to lead to anomalous (usually incorrect) results. + + +INFORMATION ABOUT A PATTERN + + int pcre_fullinfo(const pcre *code, const pcre_extra *extra, + int what, void *where); + + The pcre_fullinfo() function returns information about a compiled pat- + tern. It replaces the pcre_info() function, which was removed from the + library at version 8.30, after more than 10 years of obsolescence. + + The first argument for pcre_fullinfo() is a pointer to the compiled + pattern. The second argument is the result of pcre_study(), or NULL if + the pattern was not studied. The third argument specifies which piece + of information is required, and the fourth argument is a pointer to a + variable to receive the data. The yield of the function is zero for + success, or one of the following negative numbers: + + PCRE_ERROR_NULL the argument code was NULL + the argument where was NULL + PCRE_ERROR_BADMAGIC the "magic number" was not found + PCRE_ERROR_BADENDIANNESS the pattern was compiled with different + endianness + PCRE_ERROR_BADOPTION the value of what was invalid + PCRE_ERROR_UNSET the requested field is not set + + The "magic number" is placed at the start of each compiled pattern as + an simple check against passing an arbitrary memory pointer. The endi- + anness error can occur if a compiled pattern is saved and reloaded on a + different host. Here is a typical call of pcre_fullinfo(), to obtain + the length of the compiled pattern: + + int rc; + size_t length; + rc = pcre_fullinfo( + re, /* result of pcre_compile() */ + sd, /* result of pcre_study(), or NULL */ + PCRE_INFO_SIZE, /* what is required */ + &length); /* where to put the data */ + + The possible values for the third argument are defined in pcre.h, and + are as follows: + + PCRE_INFO_BACKREFMAX + + Return the number of the highest back reference in the pattern. The + fourth argument should point to an int variable. Zero is returned if + there are no back references. + + PCRE_INFO_CAPTURECOUNT + + Return the number of capturing subpatterns in the pattern. The fourth + argument should point to an int variable. + + PCRE_INFO_DEFAULT_TABLES + + Return a pointer to the internal default character tables within PCRE. + The fourth argument should point to an unsigned char * variable. This + information call is provided for internal use by the pcre_study() func- + tion. External callers can cause PCRE to use its internal tables by + passing a NULL table pointer. + + PCRE_INFO_FIRSTBYTE (deprecated) + + Return information about the first data unit of any matched string, for + a non-anchored pattern. The name of this option refers to the 8-bit + library, where data units are bytes. The fourth argument should point + to an int variable. Negative values are used for special cases. How- + ever, this means that when the 32-bit library is in non-UTF-32 mode, + the full 32-bit range of characters cannot be returned. For this rea- + son, this value is deprecated; use PCRE_INFO_FIRSTCHARACTERFLAGS and + PCRE_INFO_FIRSTCHARACTER instead. + + If there is a fixed first value, for example, the letter "c" from a + pattern such as (cat|cow|coyote), its value is returned. In the 8-bit + library, the value is always less than 256. In the 16-bit library the + value can be up to 0xffff. In the 32-bit library the value can be up to + 0x10ffff. + + If there is no fixed first value, and if either + + (a) the pattern was compiled with the PCRE_MULTILINE option, and every + branch starts with "^", or + + (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not + set (if it were set, the pattern would be anchored), + + -1 is returned, indicating that the pattern matches only at the start + of a subject string or after any newline within the string. Otherwise + -2 is returned. For anchored patterns, -2 is returned. + + PCRE_INFO_FIRSTCHARACTER + + Return the value of the first data unit (non-UTF character) of any + matched string in the situation where PCRE_INFO_FIRSTCHARACTERFLAGS + returns 1; otherwise return 0. The fourth argument should point to an + uint_t variable. + + In the 8-bit library, the value is always less than 256. In the 16-bit + library the value can be up to 0xffff. In the 32-bit library in UTF-32 + mode the value can be up to 0x10ffff, and up to 0xffffffff when not + using UTF-32 mode. + + PCRE_INFO_FIRSTCHARACTERFLAGS + + Return information about the first data unit of any matched string, for + a non-anchored pattern. The fourth argument should point to an int + variable. + + If there is a fixed first value, for example, the letter "c" from a + pattern such as (cat|cow|coyote), 1 is returned, and the character + value can be retrieved using PCRE_INFO_FIRSTCHARACTER. If there is no + fixed first value, and if either + + (a) the pattern was compiled with the PCRE_MULTILINE option, and every + branch starts with "^", or + + (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not + set (if it were set, the pattern would be anchored), + + 2 is returned, indicating that the pattern matches only at the start of + a subject string or after any newline within the string. Otherwise 0 is + returned. For anchored patterns, 0 is returned. + + PCRE_INFO_FIRSTTABLE + + If the pattern was studied, and this resulted in the construction of a + 256-bit table indicating a fixed set of values for the first data unit + in any matching string, a pointer to the table is returned. Otherwise + NULL is returned. The fourth argument should point to an unsigned char + * variable. + + PCRE_INFO_HASCRORLF + + Return 1 if the pattern contains any explicit matches for CR or LF + characters, otherwise 0. The fourth argument should point to an int + variable. An explicit match is either a literal CR or LF character, or + \r or \n. + + PCRE_INFO_JCHANGED + + Return 1 if the (?J) or (?-J) option setting is used in the pattern, + otherwise 0. The fourth argument should point to an int variable. (?J) + and (?-J) set and unset the local PCRE_DUPNAMES option, respectively. + + PCRE_INFO_JIT + + Return 1 if the pattern was studied with one of the JIT options, and + just-in-time compiling was successful. The fourth argument should point + to an int variable. A return value of 0 means that JIT support is not + available in this version of PCRE, or that the pattern was not studied + with a JIT option, or that the JIT compiler could not handle this par- + ticular pattern. See the pcrejit documentation for details of what can + and cannot be handled. + + PCRE_INFO_JITSIZE + + If the pattern was successfully studied with a JIT option, return the + size of the JIT compiled code, otherwise return zero. The fourth argu- + ment should point to a size_t variable. + + PCRE_INFO_LASTLITERAL + + Return the value of the rightmost literal data unit that must exist in + any matched string, other than at its start, if such a value has been + recorded. The fourth argument should point to an int variable. If there + is no such value, -1 is returned. For anchored patterns, a last literal + value is recorded only if it follows something of variable length. For + example, for the pattern /^a\d+z\d+/ the returned value is "z", but for + /^a\dz\d/ the returned value is -1. + + Since for the 32-bit library using the non-UTF-32 mode, this function + is unable to return the full 32-bit range of characters, this value is + deprecated; instead the PCRE_INFO_REQUIREDCHARFLAGS and + PCRE_INFO_REQUIREDCHAR values should be used. + + PCRE_INFO_MATCH_EMPTY + + Return 1 if the pattern can match an empty string, otherwise 0. The + fourth argument should point to an int variable. + + PCRE_INFO_MATCHLIMIT + + If the pattern set a match limit by including an item of the form + (*LIMIT_MATCH=nnnn) at the start, the value is returned. The fourth + argument should point to an unsigned 32-bit integer. If no such value + has been set, the call to pcre_fullinfo() returns the error + PCRE_ERROR_UNSET. + + PCRE_INFO_MAXLOOKBEHIND + + Return the number of characters (NB not data units) in the longest + lookbehind assertion in the pattern. This information is useful when + doing multi-segment matching using the partial matching facilities. + Note that the simple assertions \b and \B require a one-character look- + behind. \A also registers a one-character lookbehind, though it does + not actually inspect the previous character. This is to ensure that at + least one character from the old segment is retained when a new segment + is processed. Otherwise, if there are no lookbehinds in the pattern, \A + might match incorrectly at the start of a new segment. + + PCRE_INFO_MINLENGTH + + If the pattern was studied and a minimum length for matching subject + strings was computed, its value is returned. Otherwise the returned + value is -1. The value is a number of characters, which in UTF mode may + be different from the number of data units. The fourth argument should + point to an int variable. A non-negative value is a lower bound to the + length of any matching string. There may not be any strings of that + length that do actually match, but every string that does match is at + least that long. + + PCRE_INFO_NAMECOUNT + PCRE_INFO_NAMEENTRYSIZE + PCRE_INFO_NAMETABLE + + PCRE supports the use of named as well as numbered capturing parenthe- + ses. The names are just an additional way of identifying the parenthe- + ses, which still acquire numbers. Several convenience functions such as + pcre_get_named_substring() are provided for extracting captured sub- + strings by name. It is also possible to extract the data directly, by + first converting the name to a number in order to access the correct + pointers in the output vector (described with pcre_exec() below). To do + the conversion, you need to use the name-to-number map, which is + described by these three values. + + The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT + gives the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size + of each entry; both of these return an int value. The entry size + depends on the length of the longest name. PCRE_INFO_NAMETABLE returns + a pointer to the first entry of the table. This is a pointer to char in + the 8-bit library, where the first two bytes of each entry are the num- + ber of the capturing parenthesis, most significant byte first. In the + 16-bit library, the pointer points to 16-bit data units, the first of + which contains the parenthesis number. In the 32-bit library, the + pointer points to 32-bit data units, the first of which contains the + parenthesis number. The rest of the entry is the corresponding name, + zero terminated. + + The names are in alphabetical order. If (?| is used to create multiple + groups with the same number, as described in the section on duplicate + subpattern numbers in the pcrepattern page, the groups may be given the + same name, but there is only one entry in the table. Different names + for groups of the same number are not permitted. Duplicate names for + subpatterns with different numbers are permitted, but only if PCRE_DUP- + NAMES is set. They appear in the table in the order in which they were + found in the pattern. In the absence of (?| this is the order of + increasing number; when (?| is used this is not necessarily the case + because later subpatterns may have lower numbers. + + As a simple example of the name/number table, consider the following + pattern after compilation by the 8-bit library (assume PCRE_EXTENDED is + set, so white space - including newlines - is ignored): + + (?<date> (?<year>(\d\d)?\d\d) - + (?<month>\d\d) - (?<day>\d\d) ) + + There are four named subpatterns, so the table has four entries, and + each entry in the table is eight bytes long. The table is as follows, + with non-printing bytes shows in hexadecimal, and undefined bytes shown + as ??: + + 00 01 d a t e 00 ?? + 00 05 d a y 00 ?? ?? + 00 04 m o n t h 00 + 00 02 y e a r 00 ?? + + When writing code to extract data from named subpatterns using the + name-to-number map, remember that the length of the entries is likely + to be different for each compiled pattern. + + PCRE_INFO_OKPARTIAL + + Return 1 if the pattern can be used for partial matching with + pcre_exec(), otherwise 0. The fourth argument should point to an int + variable. From release 8.00, this always returns 1, because the + restrictions that previously applied to partial matching have been + lifted. The pcrepartial documentation gives details of partial match- + ing. + + PCRE_INFO_OPTIONS + + Return a copy of the options with which the pattern was compiled. The + fourth argument should point to an unsigned long int variable. These + option bits are those specified in the call to pcre_compile(), modified + by any top-level option settings at the start of the pattern itself. In + other words, they are the options that will be in force when matching + starts. For example, if the pattern /(?im)abc(?-i)d/ is compiled with + the PCRE_EXTENDED option, the result is PCRE_CASELESS, PCRE_MULTILINE, + and PCRE_EXTENDED. + + A pattern is automatically anchored by PCRE if all of its top-level + alternatives begin with one of the following: + + ^ unless PCRE_MULTILINE is set + \A always + \G always + .* if PCRE_DOTALL is set and there are no back + references to the subpattern in which .* appears + + For such patterns, the PCRE_ANCHORED bit is set in the options returned + by pcre_fullinfo(). + + PCRE_INFO_RECURSIONLIMIT + + If the pattern set a recursion limit by including an item of the form + (*LIMIT_RECURSION=nnnn) at the start, the value is returned. The fourth + argument should point to an unsigned 32-bit integer. If no such value + has been set, the call to pcre_fullinfo() returns the error + PCRE_ERROR_UNSET. + + PCRE_INFO_SIZE + + Return the size of the compiled pattern in bytes (for all three + libraries). The fourth argument should point to a size_t variable. This + value does not include the size of the pcre structure that is returned + by pcre_compile(). The value that is passed as the argument to + pcre_malloc() when pcre_compile() is getting memory in which to place + the compiled data is the value returned by this option plus the size of + the pcre structure. Studying a compiled pattern, with or without JIT, + does not alter the value returned by this option. + + PCRE_INFO_STUDYSIZE + + Return the size in bytes (for all three libraries) of the data block + pointed to by the study_data field in a pcre_extra block. If pcre_extra + is NULL, or there is no study data, zero is returned. The fourth argu- + ment should point to a size_t variable. The study_data field is set by + pcre_study() to record information that will speed up matching (see the + section entitled "Studying a pattern" above). The format of the + study_data block is private, but its length is made available via this + option so that it can be saved and restored (see the pcreprecompile + documentation for details). + + PCRE_INFO_REQUIREDCHARFLAGS + + Returns 1 if there is a rightmost literal data unit that must exist in + any matched string, other than at its start. The fourth argument should + point to an int variable. If there is no such value, 0 is returned. If + returning 1, the character value itself can be retrieved using + PCRE_INFO_REQUIREDCHAR. + + For anchored patterns, a last literal value is recorded only if it fol- + lows something of variable length. For example, for the pattern + /^a\d+z\d+/ the returned value 1 (with "z" returned from + PCRE_INFO_REQUIREDCHAR), but for /^a\dz\d/ the returned value is 0. + + PCRE_INFO_REQUIREDCHAR + + Return the value of the rightmost literal data unit that must exist in + any matched string, other than at its start, if such a value has been + recorded. The fourth argument should point to an uint32_t variable. If + there is no such value, 0 is returned. + + +REFERENCE COUNTS + + int pcre_refcount(pcre *code, int adjust); + + The pcre_refcount() function is used to maintain a reference count in + the data block that contains a compiled pattern. It is provided for the + benefit of applications that operate in an object-oriented manner, + where different parts of the application may be using the same compiled + pattern, but you want to free the block when they are all done. + + When a pattern is compiled, the reference count field is initialized to + zero. It is changed only by calling this function, whose action is to + add the adjust value (which may be positive or negative) to it. The + yield of the function is the new value. However, the value of the count + is constrained to lie between 0 and 65535, inclusive. If the new value + is outside these limits, it is forced to the appropriate limit value. + + Except when it is zero, the reference count is not correctly preserved + if a pattern is compiled on one host and then transferred to a host + whose byte-order is different. (This seems a highly unlikely scenario.) + + +MATCHING A PATTERN: THE TRADITIONAL FUNCTION + + int pcre_exec(const pcre *code, const pcre_extra *extra, + const char *subject, int length, int startoffset, + int options, int *ovector, int ovecsize); + + The function pcre_exec() is called to match a subject string against a + compiled pattern, which is passed in the code argument. If the pattern + was studied, the result of the study should be passed in the extra + argument. You can call pcre_exec() with the same code and extra argu- + ments as many times as you like, in order to match different subject + strings with the same pattern. + + This function is the main matching facility of the library, and it + operates in a Perl-like manner. For specialist use there is also an + alternative matching function, which is described below in the section + about the pcre_dfa_exec() function. + + In most applications, the pattern will have been compiled (and option- + ally studied) in the same process that calls pcre_exec(). However, it + is possible to save compiled patterns and study data, and then use them + later in different processes, possibly even on different hosts. For a + discussion about this, see the pcreprecompile documentation. + + Here is an example of a simple call to pcre_exec(): + + int rc; + int ovector[30]; + rc = pcre_exec( + re, /* result of pcre_compile() */ + NULL, /* we didn't study the pattern */ + "some string", /* the subject string */ + 11, /* the length of the subject string */ + 0, /* start at offset 0 in the subject */ + 0, /* default options */ + ovector, /* vector of integers for substring information */ + 30); /* number of elements (NOT size in bytes) */ + + Extra data for pcre_exec() + + If the extra argument is not NULL, it must point to a pcre_extra data + block. The pcre_study() function returns such a block (when it doesn't + return NULL), but you can also create one for yourself, and pass addi- + tional information in it. The pcre_extra block contains the following + fields (not necessarily in this order): + + unsigned long int flags; + void *study_data; + void *executable_jit; + unsigned long int match_limit; + unsigned long int match_limit_recursion; + void *callout_data; + const unsigned char *tables; + unsigned char **mark; + + In the 16-bit version of this structure, the mark field has type + "PCRE_UCHAR16 **". + + In the 32-bit version of this structure, the mark field has type + "PCRE_UCHAR32 **". + + The flags field is used to specify which of the other fields are set. + The flag bits are: + + PCRE_EXTRA_CALLOUT_DATA + PCRE_EXTRA_EXECUTABLE_JIT + PCRE_EXTRA_MARK + PCRE_EXTRA_MATCH_LIMIT + PCRE_EXTRA_MATCH_LIMIT_RECURSION + PCRE_EXTRA_STUDY_DATA + PCRE_EXTRA_TABLES + + Other flag bits should be set to zero. The study_data field and some- + times the executable_jit field are set in the pcre_extra block that is + returned by pcre_study(), together with the appropriate flag bits. You + should not set these yourself, but you may add to the block by setting + other fields and their corresponding flag bits. + + The match_limit field provides a means of preventing PCRE from using up + a vast amount of resources when running patterns that are not going to + match, but which have a very large number of possibilities in their + search trees. The classic example is a pattern that uses nested unlim- + ited repeats. + + Internally, pcre_exec() uses a function called match(), which it calls + repeatedly (sometimes recursively). The limit set by match_limit is + imposed on the number of times this function is called during a match, + which has the effect of limiting the amount of backtracking that can + take place. For patterns that are not anchored, the count restarts from + zero for each position in the subject string. + + When pcre_exec() is called with a pattern that was successfully studied + with a JIT option, the way that the matching is executed is entirely + different. However, there is still the possibility of runaway matching + that goes on for a very long time, and so the match_limit value is also + used in this case (but in a different way) to limit how long the match- + ing can continue. + + The default value for the limit can be set when PCRE is built; the + default default is 10 million, which handles all but the most extreme + cases. You can override the default by suppling pcre_exec() with a + pcre_extra block in which match_limit is set, and + PCRE_EXTRA_MATCH_LIMIT is set in the flags field. If the limit is + exceeded, pcre_exec() returns PCRE_ERROR_MATCHLIMIT. + + A value for the match limit may also be supplied by an item at the + start of a pattern of the form + + (*LIMIT_MATCH=d) + + where d is a decimal number. However, such a setting is ignored unless + d is less than the limit set by the caller of pcre_exec() or, if no + such limit is set, less than the default. + + The match_limit_recursion field is similar to match_limit, but instead + of limiting the total number of times that match() is called, it limits + the depth of recursion. The recursion depth is a smaller number than + the total number of calls, because not all calls to match() are recur- + sive. This limit is of use only if it is set smaller than match_limit. + + Limiting the recursion depth limits the amount of machine stack that + can be used, or, when PCRE has been compiled to use memory on the heap + instead of the stack, the amount of heap memory that can be used. This + limit is not relevant, and is ignored, when matching is done using JIT + compiled code. + + The default value for match_limit_recursion can be set when PCRE is + built; the default default is the same value as the default for + match_limit. You can override the default by suppling pcre_exec() with + a pcre_extra block in which match_limit_recursion is set, and + PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the flags field. If the + limit is exceeded, pcre_exec() returns PCRE_ERROR_RECURSIONLIMIT. + + A value for the recursion limit may also be supplied by an item at the + start of a pattern of the form + + (*LIMIT_RECURSION=d) + + where d is a decimal number. However, such a setting is ignored unless + d is less than the limit set by the caller of pcre_exec() or, if no + such limit is set, less than the default. + + The callout_data field is used in conjunction with the "callout" fea- + ture, and is described in the pcrecallout documentation. + + The tables field is provided for use with patterns that have been pre- + compiled using custom character tables, saved to disc or elsewhere, and + then reloaded, because the tables that were used to compile a pattern + are not saved with it. See the pcreprecompile documentation for a dis- + cussion of saving compiled patterns for later use. If NULL is passed + using this mechanism, it forces PCRE's internal tables to be used. + + Warning: The tables that pcre_exec() uses must be the same as those + that were used when the pattern was compiled. If this is not the case, + the behaviour of pcre_exec() is undefined. Therefore, when a pattern is + compiled and matched in the same process, this field should never be + set. In this (the most common) case, the correct table pointer is auto- + matically passed with the compiled pattern from pcre_compile() to + pcre_exec(). + + If PCRE_EXTRA_MARK is set in the flags field, the mark field must be + set to point to a suitable variable. If the pattern contains any back- + tracking control verbs such as (*MARK:NAME), and the execution ends up + with a name to pass back, a pointer to the name string (zero termi- + nated) is placed in the variable pointed to by the mark field. The + names are within the compiled pattern; if you wish to retain such a + name you must copy it before freeing the memory of a compiled pattern. + If there is no name to pass back, the variable pointed to by the mark + field is set to NULL. For details of the backtracking control verbs, + see the section entitled "Backtracking control" in the pcrepattern doc- + umentation. + + Option bits for pcre_exec() + + The unused bits of the options argument for pcre_exec() must be zero. + The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_xxx, + PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, + PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_HARD, and + PCRE_PARTIAL_SOFT. + + If the pattern was successfully studied with one of the just-in-time + (JIT) compile options, the only supported options for JIT execution are + PCRE_NO_UTF8_CHECK, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, + PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and PCRE_PARTIAL_SOFT. If an + unsupported option is used, JIT execution is disabled and the normal + interpretive code in pcre_exec() is run. + + PCRE_ANCHORED + + The PCRE_ANCHORED option limits pcre_exec() to matching at the first + matching position. If a pattern was compiled with PCRE_ANCHORED, or + turned out to be anchored by virtue of its contents, it cannot be made + unachored at matching time. + + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE + + These options (which are mutually exclusive) control what the \R escape + sequence matches. The choice is either to match only CR, LF, or CRLF, + or to match any Unicode newline sequence. These options override the + choice that was made or defaulted when the pattern was compiled. + + PCRE_NEWLINE_CR + PCRE_NEWLINE_LF + PCRE_NEWLINE_CRLF + PCRE_NEWLINE_ANYCRLF + PCRE_NEWLINE_ANY + + These options override the newline definition that was chosen or + defaulted when the pattern was compiled. For details, see the descrip- + tion of pcre_compile() above. During matching, the newline choice + affects the behaviour of the dot, circumflex, and dollar metacharac- + ters. It may also alter the way the match position is advanced after a + match failure for an unanchored pattern. + + When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is + set, and a match attempt for an unanchored pattern fails when the cur- + rent position is at a CRLF sequence, and the pattern contains no + explicit matches for CR or LF characters, the match position is + advanced by two characters instead of one, in other words, to after the + CRLF. + + The above rule is a compromise that makes the most common cases work as + expected. For example, if the pattern is .+A (and the PCRE_DOTALL + option is not set), it does not match the string "\r\nA" because, after + failing at the start, it skips both the CR and the LF before retrying. + However, the pattern [\r\n]A does match that string, because it con- + tains an explicit CR or LF reference, and so advances only by one char- + acter after the first failure. + + An explicit match for CR of LF is either a literal appearance of one of + those characters, or one of the \r or \n escape sequences. Implicit + matches such as [^X] do not count, nor does \s (which includes CR and + LF in the characters that it matches). + + Notwithstanding the above, anomalous effects may still occur when CRLF + is a valid newline sequence and explicit \r or \n escapes appear in the + pattern. + + PCRE_NOTBOL + + This option specifies that first character of the subject string is not + the beginning of a line, so the circumflex metacharacter should not + match before it. Setting this without PCRE_MULTILINE (at compile time) + causes circumflex never to match. This option affects only the behav- + iour of the circumflex metacharacter. It does not affect \A. + + PCRE_NOTEOL + + This option specifies that the end of the subject string is not the end + of a line, so the dollar metacharacter should not match it nor (except + in multiline mode) a newline immediately before it. Setting this with- + out PCRE_MULTILINE (at compile time) causes dollar never to match. This + option affects only the behaviour of the dollar metacharacter. It does + not affect \Z or \z. + + PCRE_NOTEMPTY + + An empty string is not considered to be a valid match if this option is + set. If there are alternatives in the pattern, they are tried. If all + the alternatives match the empty string, the entire match fails. For + example, if the pattern + + a?b? + + is applied to a string not beginning with "a" or "b", it matches an + empty string at the start of the subject. With PCRE_NOTEMPTY set, this + match is not valid, so PCRE searches further into the string for occur- + rences of "a" or "b". + + PCRE_NOTEMPTY_ATSTART + + This is like PCRE_NOTEMPTY, except that an empty string match that is + not at the start of the subject is permitted. If the pattern is + anchored, such a match can occur only if the pattern contains \K. + + Perl has no direct equivalent of PCRE_NOTEMPTY or + PCRE_NOTEMPTY_ATSTART, but it does make a special case of a pattern + match of the empty string within its split() function, and when using + the /g modifier. It is possible to emulate Perl's behaviour after + matching a null string by first trying the match again at the same off- + set with PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED, and then if that + fails, by advancing the starting offset (see below) and trying an ordi- + nary match again. There is some code that demonstrates how to do this + in the pcredemo sample program. In the most general case, you have to + check to see if the newline convention recognizes CRLF as a newline, + and if so, and the current character is CR followed by LF, advance the + starting offset by two characters instead of one. + + PCRE_NO_START_OPTIMIZE + + There are a number of optimizations that pcre_exec() uses at the start + of a match, in order to speed up the process. For example, if it is + known that an unanchored match must start with a specific character, it + searches the subject for that character, and fails immediately if it + cannot find it, without actually running the main matching function. + This means that a special item such as (*COMMIT) at the start of a pat- + tern is not considered until after a suitable starting point for the + match has been found. Also, when callouts or (*MARK) items are in use, + these "start-up" optimizations can cause them to be skipped if the pat- + tern is never actually used. The start-up optimizations are in effect a + pre-scan of the subject that takes place before the pattern is run. + + The PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, + possibly causing performance to suffer, but ensuring that in cases + where the result is "no match", the callouts do occur, and that items + such as (*COMMIT) and (*MARK) are considered at every possible starting + position in the subject string. If PCRE_NO_START_OPTIMIZE is set at + compile time, it cannot be unset at matching time. The use of + PCRE_NO_START_OPTIMIZE at matching time (that is, passing it to + pcre_exec()) disables JIT execution; in this situation, matching is + always done using interpretively. + + Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching + operation. Consider the pattern + + (*COMMIT)ABC + + When this is compiled, PCRE records the fact that a match must start + with the character "A". Suppose the subject string is "DEFABC". The + start-up optimization scans along the subject, finds "A" and runs the + first match attempt from there. The (*COMMIT) item means that the pat- + tern must match the current starting position, which in this case, it + does. However, if the same match is run with PCRE_NO_START_OPTIMIZE + set, the initial scan along the subject string does not happen. The + first match attempt is run starting from "D" and when this fails, + (*COMMIT) prevents any further matches being tried, so the overall + result is "no match". If the pattern is studied, more start-up opti- + mizations may be used. For example, a minimum length for the subject + may be recorded. Consider the pattern + + (*MARK:A)(X|Y) + + The minimum length for a match is one character. If the subject is + "ABC", there will be attempts to match "ABC", "BC", "C", and then + finally an empty string. If the pattern is studied, the final attempt + does not take place, because PCRE knows that the subject is too short, + and so the (*MARK) is never encountered. In this case, studying the + pattern does not affect the overall match result, which is still "no + match", but it does affect the auxiliary information that is returned. + + PCRE_NO_UTF8_CHECK + + When PCRE_UTF8 is set at compile time, the validity of the subject as a + UTF-8 string is automatically checked when pcre_exec() is subsequently + called. The entire string is checked before any other processing takes + place. The value of startoffset is also checked to ensure that it + points to the start of a UTF-8 character. There is a discussion about + the validity of UTF-8 strings in the pcreunicode page. If an invalid + sequence of bytes is found, pcre_exec() returns the error + PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is a + truncated character at the end of the subject, PCRE_ERROR_SHORTUTF8. In + both cases, information about the precise nature of the error may also + be returned (see the descriptions of these errors in the section enti- + tled Error return values from pcre_exec() below). If startoffset con- + tains a value that does not point to the start of a UTF-8 character (or + to the end of the subject), PCRE_ERROR_BADUTF8_OFFSET is returned. + + If you already know that your subject is valid, and you want to skip + these checks for performance reasons, you can set the + PCRE_NO_UTF8_CHECK option when calling pcre_exec(). You might want to + do this for the second and subsequent calls to pcre_exec() if you are + making repeated calls to find all the matches in a single subject + string. However, you should be sure that the value of startoffset + points to the start of a character (or the end of the subject). When + PCRE_NO_UTF8_CHECK is set, the effect of passing an invalid string as a + subject or an invalid value of startoffset is undefined. Your program + may crash or loop. + + PCRE_PARTIAL_HARD + PCRE_PARTIAL_SOFT + + These options turn on the partial matching feature. For backwards com- + patibility, PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. A partial + match occurs if the end of the subject string is reached successfully, + but there are not enough subject characters to complete the match. If + this happens when PCRE_PARTIAL_SOFT (but not PCRE_PARTIAL_HARD) is set, + matching continues by testing any remaining alternatives. Only if no + complete match can be found is PCRE_ERROR_PARTIAL returned instead of + PCRE_ERROR_NOMATCH. In other words, PCRE_PARTIAL_SOFT says that the + caller is prepared to handle a partial match, but only if no complete + match can be found. + + If PCRE_PARTIAL_HARD is set, it overrides PCRE_PARTIAL_SOFT. In this + case, if a partial match is found, pcre_exec() immediately returns + PCRE_ERROR_PARTIAL, without considering any other alternatives. In + other words, when PCRE_PARTIAL_HARD is set, a partial match is consid- + ered to be more important that an alternative complete match. + + In both cases, the portion of the string that was inspected when the + partial match was found is set as the first matching string. There is a + more detailed discussion of partial and multi-segment matching, with + examples, in the pcrepartial documentation. + + The string to be matched by pcre_exec() + + The subject string is passed to pcre_exec() as a pointer in subject, a + length in length, and a starting offset in startoffset. The units for + length and startoffset are bytes for the 8-bit library, 16-bit data + items for the 16-bit library, and 32-bit data items for the 32-bit + library. + + If startoffset is negative or greater than the length of the subject, + pcre_exec() returns PCRE_ERROR_BADOFFSET. When the starting offset is + zero, the search for a match starts at the beginning of the subject, + and this is by far the most common case. In UTF-8 or UTF-16 mode, the + offset must point to the start of a character, or the end of the sub- + ject (in UTF-32 mode, one data unit equals one character, so all off- + sets are valid). Unlike the pattern string, the subject may contain + binary zeroes. + + A non-zero starting offset is useful when searching for another match + in the same subject by calling pcre_exec() again after a previous suc- + cess. Setting startoffset differs from just passing over a shortened + string and setting PCRE_NOTBOL in the case of a pattern that begins + with any kind of lookbehind. For example, consider the pattern + + \Biss\B + + which finds occurrences of "iss" in the middle of words. (\B matches + only if the current position in the subject is not a word boundary.) + When applied to the string "Mississipi" the first call to pcre_exec() + finds the first occurrence. If pcre_exec() is called again with just + the remainder of the subject, namely "issipi", it does not match, + because \B is always false at the start of the subject, which is deemed + to be a word boundary. However, if pcre_exec() is passed the entire + string again, but with startoffset set to 4, it finds the second occur- + rence of "iss" because it is able to look behind the starting point to + discover that it is preceded by a letter. + + Finding all the matches in a subject is tricky when the pattern can + match an empty string. It is possible to emulate Perl's /g behaviour by + first trying the match again at the same offset, with the + PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED options, and then if that + fails, advancing the starting offset and trying an ordinary match + again. There is some code that demonstrates how to do this in the pcre- + demo sample program. In the most general case, you have to check to see + if the newline convention recognizes CRLF as a newline, and if so, and + the current character is CR followed by LF, advance the starting offset + by two characters instead of one. + + If a non-zero starting offset is passed when the pattern is anchored, + one attempt to match at the given offset is made. This can only succeed + if the pattern does not require the match to be at the start of the + subject. + + How pcre_exec() returns captured substrings + + In general, a pattern matches a certain portion of the subject, and in + addition, further substrings from the subject may be picked out by + parts of the pattern. Following the usage in Jeffrey Friedl's book, + this is called "capturing" in what follows, and the phrase "capturing + subpattern" is used for a fragment of a pattern that picks out a sub- + string. PCRE supports several other kinds of parenthesized subpattern + that do not cause substrings to be captured. + + Captured substrings are returned to the caller via a vector of integers + whose address is passed in ovector. The number of elements in the vec- + tor is passed in ovecsize, which must be a non-negative number. Note: + this argument is NOT the size of ovector in bytes. + + The first two-thirds of the vector is used to pass back captured sub- + strings, each substring using a pair of integers. The remaining third + of the vector is used as workspace by pcre_exec() while matching cap- + turing subpatterns, and is not available for passing back information. + The number passed in ovecsize should always be a multiple of three. If + it is not, it is rounded down. + + When a match is successful, information about captured substrings is + returned in pairs of integers, starting at the beginning of ovector, + and continuing up to two-thirds of its length at the most. The first + element of each pair is set to the offset of the first character in a + substring, and the second is set to the offset of the first character + after the end of a substring. These values are always data unit off- + sets, even in UTF mode. They are byte offsets in the 8-bit library, + 16-bit data item offsets in the 16-bit library, and 32-bit data item + offsets in the 32-bit library. Note: they are not character counts. + + The first pair of integers, ovector[0] and ovector[1], identify the + portion of the subject string matched by the entire pattern. The next + pair is used for the first capturing subpattern, and so on. The value + returned by pcre_exec() is one more than the highest numbered pair that + has been set. For example, if two substrings have been captured, the + returned value is 3. If there are no capturing subpatterns, the return + value from a successful match is 1, indicating that just the first pair + of offsets has been set. + + If a capturing subpattern is matched repeatedly, it is the last portion + of the string that it matched that is returned. + + If the vector is too small to hold all the captured substring offsets, + it is used as far as possible (up to two-thirds of its length), and the + function returns a value of zero. If neither the actual string matched + nor any captured substrings are of interest, pcre_exec() may be called + with ovector passed as NULL and ovecsize as zero. However, if the pat- + tern contains back references and the ovector is not big enough to + remember the related substrings, PCRE has to get additional memory for + use during matching. Thus it is usually advisable to supply an ovector + of reasonable size. + + There are some cases where zero is returned (indicating vector over- + flow) when in fact the vector is exactly the right size for the final + match. For example, consider the pattern + + (a)(?:(b)c|bd) + + If a vector of 6 elements (allowing for only 1 captured substring) is + given with subject string "abd", pcre_exec() will try to set the second + captured string, thereby recording a vector overflow, before failing to + match "c" and backing up to try the second alternative. The zero + return, however, does correctly indicate that the maximum number of + slots (namely 2) have been filled. In similar cases where there is tem- + porary overflow, but the final number of used slots is actually less + than the maximum, a non-zero value is returned. + + The pcre_fullinfo() function can be used to find out how many capturing + subpatterns there are in a compiled pattern. The smallest size for + ovector that will allow for n captured substrings, in addition to the + offsets of the substring matched by the whole pattern, is (n+1)*3. + + It is possible for capturing subpattern number n+1 to match some part + of the subject when subpattern n has not been used at all. For example, + if the string "abc" is matched against the pattern (a|(z))(bc) the + return from the function is 4, and subpatterns 1 and 3 are matched, but + 2 is not. When this happens, both values in the offset pairs corre- + sponding to unused subpatterns are set to -1. + + Offset values that correspond to unused subpatterns at the end of the + expression are also set to -1. For example, if the string "abc" is + matched against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not + matched. The return from the function is 2, because the highest used + capturing subpattern number is 1, and the offsets for for the second + and third capturing subpatterns (assuming the vector is large enough, + of course) are set to -1. + + Note: Elements in the first two-thirds of ovector that do not corre- + spond to capturing parentheses in the pattern are never changed. That + is, if a pattern contains n capturing parentheses, no more than ovec- + tor[0] to ovector[2n+1] are set by pcre_exec(). The other elements (in + the first two-thirds) retain whatever values they previously had. + + Some convenience functions are provided for extracting the captured + substrings as separate strings. These are described below. + + Error return values from pcre_exec() + + If pcre_exec() fails, it returns a negative number. The following are + defined in the header file: + + PCRE_ERROR_NOMATCH (-1) + + The subject string did not match the pattern. + + PCRE_ERROR_NULL (-2) + + Either code or subject was passed as NULL, or ovector was NULL and + ovecsize was not zero. + + PCRE_ERROR_BADOPTION (-3) + + An unrecognized bit was set in the options argument. + + PCRE_ERROR_BADMAGIC (-4) + + PCRE stores a 4-byte "magic number" at the start of the compiled code, + to catch the case when it is passed a junk pointer and to detect when a + pattern that was compiled in an environment of one endianness is run in + an environment with the other endianness. This is the error that PCRE + gives when the magic number is not present. + + PCRE_ERROR_UNKNOWN_OPCODE (-5) + + While running the pattern match, an unknown item was encountered in the + compiled pattern. This error could be caused by a bug in PCRE or by + overwriting of the compiled pattern. + + PCRE_ERROR_NOMEMORY (-6) + + If a pattern contains back references, but the ovector that is passed + to pcre_exec() is not big enough to remember the referenced substrings, + PCRE gets a block of memory at the start of matching to use for this + purpose. If the call via pcre_malloc() fails, this error is given. The + memory is automatically freed at the end of matching. + + This error is also given if pcre_stack_malloc() fails in pcre_exec(). + This can happen only when PCRE has been compiled with --disable-stack- + for-recursion. + + PCRE_ERROR_NOSUBSTRING (-7) + + This error is used by the pcre_copy_substring(), pcre_get_substring(), + and pcre_get_substring_list() functions (see below). It is never + returned by pcre_exec(). + + PCRE_ERROR_MATCHLIMIT (-8) + + The backtracking limit, as specified by the match_limit field in a + pcre_extra structure (or defaulted) was reached. See the description + above. + + PCRE_ERROR_CALLOUT (-9) + + This error is never generated by pcre_exec() itself. It is provided for + use by callout functions that want to yield a distinctive error code. + See the pcrecallout documentation for details. + + PCRE_ERROR_BADUTF8 (-10) + + A string that contains an invalid UTF-8 byte sequence was passed as a + subject, and the PCRE_NO_UTF8_CHECK option was not set. If the size of + the output vector (ovecsize) is at least 2, the byte offset to the + start of the the invalid UTF-8 character is placed in the first ele- + ment, and a reason code is placed in the second element. The reason + codes are listed in the following section. For backward compatibility, + if PCRE_PARTIAL_HARD is set and the problem is a truncated UTF-8 char- + acter at the end of the subject (reason codes 1 to 5), + PCRE_ERROR_SHORTUTF8 is returned instead of PCRE_ERROR_BADUTF8. + + PCRE_ERROR_BADUTF8_OFFSET (-11) + + The UTF-8 byte sequence that was passed as a subject was checked and + found to be valid (the PCRE_NO_UTF8_CHECK option was not set), but the + value of startoffset did not point to the beginning of a UTF-8 charac- + ter or the end of the subject. + + PCRE_ERROR_PARTIAL (-12) + + The subject string did not match, but it did match partially. See the + pcrepartial documentation for details of partial matching. + + PCRE_ERROR_BADPARTIAL (-13) + + This code is no longer in use. It was formerly returned when the + PCRE_PARTIAL option was used with a compiled pattern containing items + that were not supported for partial matching. From release 8.00 + onwards, there are no restrictions on partial matching. + + PCRE_ERROR_INTERNAL (-14) + + An unexpected internal error has occurred. This error could be caused + by a bug in PCRE or by overwriting of the compiled pattern. + + PCRE_ERROR_BADCOUNT (-15) + + This error is given if the value of the ovecsize argument is negative. + + PCRE_ERROR_RECURSIONLIMIT (-21) + + The internal recursion limit, as specified by the match_limit_recursion + field in a pcre_extra structure (or defaulted) was reached. See the + description above. + + PCRE_ERROR_BADNEWLINE (-23) + + An invalid combination of PCRE_NEWLINE_xxx options was given. + + PCRE_ERROR_BADOFFSET (-24) + + The value of startoffset was negative or greater than the length of the + subject, that is, the value in length. + + PCRE_ERROR_SHORTUTF8 (-25) + + This error is returned instead of PCRE_ERROR_BADUTF8 when the subject + string ends with a truncated UTF-8 character and the PCRE_PARTIAL_HARD + option is set. Information about the failure is returned as for + PCRE_ERROR_BADUTF8. It is in fact sufficient to detect this case, but + this special error code for PCRE_PARTIAL_HARD precedes the implementa- + tion of returned information; it is retained for backwards compatibil- + ity. + + PCRE_ERROR_RECURSELOOP (-26) + + This error is returned when pcre_exec() detects a recursion loop within + the pattern. Specifically, it means that either the whole pattern or a + subpattern has been called recursively for the second time at the same + position in the subject string. Some simple patterns that might do this + are detected and faulted at compile time, but more complicated cases, + in particular mutual recursions between two different subpatterns, can- + not be detected until run time. + + PCRE_ERROR_JIT_STACKLIMIT (-27) + + This error is returned when a pattern that was successfully studied + using a JIT compile option is being matched, but the memory available + for the just-in-time processing stack is not large enough. See the + pcrejit documentation for more details. + + PCRE_ERROR_BADMODE (-28) + + This error is given if a pattern that was compiled by the 8-bit library + is passed to a 16-bit or 32-bit library function, or vice versa. + + PCRE_ERROR_BADENDIANNESS (-29) + + This error is given if a pattern that was compiled and saved is + reloaded on a host with different endianness. The utility function + pcre_pattern_to_host_byte_order() can be used to convert such a pattern + so that it runs on the new host. + + PCRE_ERROR_JIT_BADOPTION + + This error is returned when a pattern that was successfully studied + using a JIT compile option is being matched, but the matching mode + (partial or complete match) does not correspond to any JIT compilation + mode. When the JIT fast path function is used, this error may be also + given for invalid options. See the pcrejit documentation for more + details. + + PCRE_ERROR_BADLENGTH (-32) + + This error is given if pcre_exec() is called with a negative value for + the length argument. + + Error numbers -16 to -20, -22, and 30 are not used by pcre_exec(). + + Reason codes for invalid UTF-8 strings + + This section applies only to the 8-bit library. The corresponding + information for the 16-bit and 32-bit libraries is given in the pcre16 + and pcre32 pages. + + When pcre_exec() returns either PCRE_ERROR_BADUTF8 or PCRE_ERROR_SHORT- + UTF8, and the size of the output vector (ovecsize) is at least 2, the + offset of the start of the invalid UTF-8 character is placed in the + first output vector element (ovector[0]) and a reason code is placed in + the second element (ovector[1]). The reason codes are given names in + the pcre.h header file: + + PCRE_UTF8_ERR1 + PCRE_UTF8_ERR2 + PCRE_UTF8_ERR3 + PCRE_UTF8_ERR4 + PCRE_UTF8_ERR5 + + The string ends with a truncated UTF-8 character; the code specifies + how many bytes are missing (1 to 5). Although RFC 3629 restricts UTF-8 + characters to be no longer than 4 bytes, the encoding scheme (origi- + nally defined by RFC 2279) allows for up to 6 bytes, and this is + checked first; hence the possibility of 4 or 5 missing bytes. + + PCRE_UTF8_ERR6 + PCRE_UTF8_ERR7 + PCRE_UTF8_ERR8 + PCRE_UTF8_ERR9 + PCRE_UTF8_ERR10 + + The two most significant bits of the 2nd, 3rd, 4th, 5th, or 6th byte of + the character do not have the binary value 0b10 (that is, either the + most significant bit is 0, or the next bit is 1). + + PCRE_UTF8_ERR11 + PCRE_UTF8_ERR12 + + A character that is valid by the RFC 2279 rules is either 5 or 6 bytes + long; these code points are excluded by RFC 3629. + + PCRE_UTF8_ERR13 + + A 4-byte character has a value greater than 0x10fff; these code points + are excluded by RFC 3629. + + PCRE_UTF8_ERR14 + + A 3-byte character has a value in the range 0xd800 to 0xdfff; this + range of code points are reserved by RFC 3629 for use with UTF-16, and + so are excluded from UTF-8. + + PCRE_UTF8_ERR15 + PCRE_UTF8_ERR16 + PCRE_UTF8_ERR17 + PCRE_UTF8_ERR18 + PCRE_UTF8_ERR19 + + A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes + for a value that can be represented by fewer bytes, which is invalid. + For example, the two bytes 0xc0, 0xae give the value 0x2e, whose cor- + rect coding uses just one byte. + + PCRE_UTF8_ERR20 + + The two most significant bits of the first byte of a character have the + binary value 0b10 (that is, the most significant bit is 1 and the sec- + ond is 0). Such a byte can only validly occur as the second or subse- + quent byte of a multi-byte character. + + PCRE_UTF8_ERR21 + + The first byte of a character has the value 0xfe or 0xff. These values + can never occur in a valid UTF-8 string. + + PCRE_UTF8_ERR22 + + This error code was formerly used when the presence of a so-called + "non-character" caused an error. Unicode corrigendum #9 makes it clear + that such characters should not cause a string to be rejected, and so + this code is no longer in use and is never returned. + + +EXTRACTING CAPTURED SUBSTRINGS BY NUMBER + + int pcre_copy_substring(const char *subject, int *ovector, + int stringcount, int stringnumber, char *buffer, + int buffersize); + + int pcre_get_substring(const char *subject, int *ovector, + int stringcount, int stringnumber, + const char **stringptr); + + int pcre_get_substring_list(const char *subject, + int *ovector, int stringcount, const char ***listptr); + + Captured substrings can be accessed directly by using the offsets + returned by pcre_exec() in ovector. For convenience, the functions + pcre_copy_substring(), pcre_get_substring(), and pcre_get_sub- + string_list() are provided for extracting captured substrings as new, + separate, zero-terminated strings. These functions identify substrings + by number. The next section describes functions for extracting named + substrings. + + A substring that contains a binary zero is correctly extracted and has + a further zero added on the end, but the result is not, of course, a C + string. However, you can process such a string by referring to the + length that is returned by pcre_copy_substring() and pcre_get_sub- + string(). Unfortunately, the interface to pcre_get_substring_list() is + not adequate for handling strings containing binary zeros, because the + end of the final string is not independently indicated. + + The first three arguments are the same for all three of these func- + tions: subject is the subject string that has just been successfully + matched, ovector is a pointer to the vector of integer offsets that was + passed to pcre_exec(), and stringcount is the number of substrings that + were captured by the match, including the substring that matched the + entire regular expression. This is the value returned by pcre_exec() if + it is greater than zero. If pcre_exec() returned zero, indicating that + it ran out of space in ovector, the value passed as stringcount should + be the number of elements in the vector divided by three. + + The functions pcre_copy_substring() and pcre_get_substring() extract a + single substring, whose number is given as stringnumber. A value of + zero extracts the substring that matched the entire pattern, whereas + higher values extract the captured substrings. For pcre_copy_sub- + string(), the string is placed in buffer, whose length is given by + buffersize, while for pcre_get_substring() a new block of memory is + obtained via pcre_malloc, and its address is returned via stringptr. + The yield of the function is the length of the string, not including + the terminating zero, or one of these error codes: + + PCRE_ERROR_NOMEMORY (-6) + + The buffer was too small for pcre_copy_substring(), or the attempt to + get memory failed for pcre_get_substring(). + + PCRE_ERROR_NOSUBSTRING (-7) + + There is no substring whose number is stringnumber. + + The pcre_get_substring_list() function extracts all available sub- + strings and builds a list of pointers to them. All this is done in a + single block of memory that is obtained via pcre_malloc. The address of + the memory block is returned via listptr, which is also the start of + the list of string pointers. The end of the list is marked by a NULL + pointer. The yield of the function is zero if all went well, or the + error code + + PCRE_ERROR_NOMEMORY (-6) + + if the attempt to get the memory block failed. + + When any of these functions encounter a substring that is unset, which + can happen when capturing subpattern number n+1 matches some part of + the subject, but subpattern n has not been used at all, they return an + empty string. This can be distinguished from a genuine zero-length sub- + string by inspecting the appropriate offset in ovector, which is nega- + tive for unset substrings. + + The two convenience functions pcre_free_substring() and pcre_free_sub- + string_list() can be used to free the memory returned by a previous + call of pcre_get_substring() or pcre_get_substring_list(), respec- + tively. They do nothing more than call the function pointed to by + pcre_free, which of course could be called directly from a C program. + However, PCRE is used in some situations where it is linked via a spe- + cial interface to another programming language that cannot use + pcre_free directly; it is for these cases that the functions are pro- + vided. + + +EXTRACTING CAPTURED SUBSTRINGS BY NAME + + int pcre_get_stringnumber(const pcre *code, + const char *name); + + int pcre_copy_named_substring(const pcre *code, + const char *subject, int *ovector, + int stringcount, const char *stringname, + char *buffer, int buffersize); + + int pcre_get_named_substring(const pcre *code, + const char *subject, int *ovector, + int stringcount, const char *stringname, + const char **stringptr); + + To extract a substring by name, you first have to find associated num- + ber. For example, for this pattern + + (a+)b(?<xxx>\d+)... + + the number of the subpattern called "xxx" is 2. If the name is known to + be unique (PCRE_DUPNAMES was not set), you can find the number from the + name by calling pcre_get_stringnumber(). The first argument is the com- + piled pattern, and the second is the name. The yield of the function is + the subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no + subpattern of that name. + + Given the number, you can extract the substring directly, or use one of + the functions described in the previous section. For convenience, there + are also two functions that do the whole job. + + Most of the arguments of pcre_copy_named_substring() and + pcre_get_named_substring() are the same as those for the similarly + named functions that extract by number. As these are described in the + previous section, they are not re-described here. There are just two + differences: + + First, instead of a substring number, a substring name is given. Sec- + ond, there is an extra argument, given at the start, which is a pointer + to the compiled pattern. This is needed in order to gain access to the + name-to-number translation table. + + These functions call pcre_get_stringnumber(), and if it succeeds, they + then call pcre_copy_substring() or pcre_get_substring(), as appropri- + ate. NOTE: If PCRE_DUPNAMES is set and there are duplicate names, the + behaviour may not be what you want (see the next section). + + Warning: If the pattern uses the (?| feature to set up multiple subpat- + terns with the same number, as described in the section on duplicate + subpattern numbers in the pcrepattern page, you cannot use names to + distinguish the different subpatterns, because names are not included + in the compiled code. The matching process uses only numbers. For this + reason, the use of different names for subpatterns of the same number + causes an error at compile time. + + +DUPLICATE SUBPATTERN NAMES + + int pcre_get_stringtable_entries(const pcre *code, + const char *name, char **first, char **last); + + When a pattern is compiled with the PCRE_DUPNAMES option, names for + subpatterns are not required to be unique. (Duplicate names are always + allowed for subpatterns with the same number, created by using the (?| + feature. Indeed, if such subpatterns are named, they are required to + use the same names.) + + Normally, patterns with duplicate names are such that in any one match, + only one of the named subpatterns participates. An example is shown in + the pcrepattern documentation. + + When duplicates are present, pcre_copy_named_substring() and + pcre_get_named_substring() return the first substring corresponding to + the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING + (-7) is returned; no data is returned. The pcre_get_stringnumber() + function returns one of the numbers that are associated with the name, + but it is not defined which it is. + + If you want to get full details of all captured substrings for a given + name, you must use the pcre_get_stringtable_entries() function. The + first argument is the compiled pattern, and the second is the name. The + third and fourth are pointers to variables which are updated by the + function. After it has run, they point to the first and last entries in + the name-to-number table for the given name. The function itself + returns the length of each entry, or PCRE_ERROR_NOSUBSTRING (-7) if + there are none. The format of the table is described above in the sec- + tion entitled Information about a pattern above. Given all the rele- + vant entries for the name, you can extract each of their numbers, and + hence the captured data, if any. + + +FINDING ALL POSSIBLE MATCHES + + The traditional matching function uses a similar algorithm to Perl, + which stops when it finds the first match, starting at a given point in + the subject. If you want to find all possible matches, or the longest + possible match, consider using the alternative matching function (see + below) instead. If you cannot use the alternative function, but still + need to find all possible matches, you can kludge it up by making use + of the callout facility, which is described in the pcrecallout documen- + tation. + + What you have to do is to insert a callout right at the end of the pat- + tern. When your callout function is called, extract and save the cur- + rent matched substring. Then return 1, which forces pcre_exec() to + backtrack and try other alternatives. Ultimately, when it runs out of + matches, pcre_exec() will yield PCRE_ERROR_NOMATCH. + + +OBTAINING AN ESTIMATE OF STACK USAGE + + Matching certain patterns using pcre_exec() can use a lot of process + stack, which in certain environments can be rather limited in size. + Some users find it helpful to have an estimate of the amount of stack + that is used by pcre_exec(), to help them set recursion limits, as + described in the pcrestack documentation. The estimate that is output + by pcretest when called with the -m and -C options is obtained by call- + ing pcre_exec with the values NULL, NULL, NULL, -999, and -999 for its + first five arguments. + + Normally, if its first argument is NULL, pcre_exec() immediately + returns the negative error code PCRE_ERROR_NULL, but with this special + combination of arguments, it returns instead a negative number whose + absolute value is the approximate stack frame size in bytes. (A nega- + tive number is used so that it is clear that no match has happened.) + The value is approximate because in some cases, recursive calls to + pcre_exec() occur when there are one or two additional variables on the + stack. + + If PCRE has been compiled to use the heap instead of the stack for + recursion, the value returned is the size of each block that is + obtained from the heap. + + +MATCHING A PATTERN: THE ALTERNATIVE FUNCTION + + int pcre_dfa_exec(const pcre *code, const pcre_extra *extra, + const char *subject, int length, int startoffset, + int options, int *ovector, int ovecsize, + int *workspace, int wscount); + + The function pcre_dfa_exec() is called to match a subject string + against a compiled pattern, using a matching algorithm that scans the + subject string just once, and does not backtrack. This has different + characteristics to the normal algorithm, and is not compatible with + Perl. Some of the features of PCRE patterns are not supported. Never- + theless, there are times when this kind of matching can be useful. For + a discussion of the two matching algorithms, and a list of features + that pcre_dfa_exec() does not support, see the pcrematching documenta- + tion. + + The arguments for the pcre_dfa_exec() function are the same as for + pcre_exec(), plus two extras. The ovector argument is used in a differ- + ent way, and this is described below. The other common arguments are + used in the same way as for pcre_exec(), so their description is not + repeated here. + + The two additional arguments provide workspace for the function. The + workspace vector should contain at least 20 elements. It is used for + keeping track of multiple paths through the pattern tree. More + workspace will be needed for patterns and subjects where there are a + lot of potential matches. + + Here is an example of a simple call to pcre_dfa_exec(): + + int rc; + int ovector[10]; + int wspace[20]; + rc = pcre_dfa_exec( + re, /* result of pcre_compile() */ + NULL, /* we didn't study the pattern */ + "some string", /* the subject string */ + 11, /* the length of the subject string */ + 0, /* start at offset 0 in the subject */ + 0, /* default options */ + ovector, /* vector of integers for substring information */ + 10, /* number of elements (NOT size in bytes) */ + wspace, /* working space vector */ + 20); /* number of elements (NOT size in bytes) */ + + Option bits for pcre_dfa_exec() + + The unused bits of the options argument for pcre_dfa_exec() must be + zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEW- + LINE_xxx, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, + PCRE_NOTEMPTY_ATSTART, PCRE_NO_UTF8_CHECK, PCRE_BSR_ANYCRLF, + PCRE_BSR_UNICODE, PCRE_NO_START_OPTIMIZE, PCRE_PARTIAL_HARD, PCRE_PAR- + TIAL_SOFT, PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last + four of these are exactly the same as for pcre_exec(), so their + description is not repeated here. + + PCRE_PARTIAL_HARD + PCRE_PARTIAL_SOFT + + These have the same general effect as they do for pcre_exec(), but the + details are slightly different. When PCRE_PARTIAL_HARD is set for + pcre_dfa_exec(), it returns PCRE_ERROR_PARTIAL if the end of the sub- + ject is reached and there is still at least one matching possibility + that requires additional characters. This happens even if some complete + matches have also been found. When PCRE_PARTIAL_SOFT is set, the return + code PCRE_ERROR_NOMATCH is converted into PCRE_ERROR_PARTIAL if the end + of the subject is reached, there have been no complete matches, but + there is still at least one matching possibility. The portion of the + string that was inspected when the longest partial match was found is + set as the first matching string in both cases. There is a more + detailed discussion of partial and multi-segment matching, with exam- + ples, in the pcrepartial documentation. + + PCRE_DFA_SHORTEST + + Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to + stop as soon as it has found one match. Because of the way the alterna- + tive algorithm works, this is necessarily the shortest possible match + at the first possible matching point in the subject string. + + PCRE_DFA_RESTART + + When pcre_dfa_exec() returns a partial match, it is possible to call it + again, with additional subject characters, and have it continue with + the same match. The PCRE_DFA_RESTART option requests this action; when + it is set, the workspace and wscount options must reference the same + vector as before because data about the match so far is left in them + after a partial match. There is more discussion of this facility in the + pcrepartial documentation. + + Successful returns from pcre_dfa_exec() + + When pcre_dfa_exec() succeeds, it may have matched more than one sub- + string in the subject. Note, however, that all the matches from one run + of the function start at the same point in the subject. The shorter + matches are all initial substrings of the longer matches. For example, + if the pattern + + <.*> + + is matched against the string + + This is <something> <something else> <something further> no more + + the three matched strings are + + <something> + <something> <something else> + <something> <something else> <something further> + + On success, the yield of the function is a number greater than zero, + which is the number of matched substrings. The substrings themselves + are returned in ovector. Each string uses two elements; the first is + the offset to the start, and the second is the offset to the end. In + fact, all the strings have the same start offset. (Space could have + been saved by giving this only once, but it was decided to retain some + compatibility with the way pcre_exec() returns data, even though the + meaning of the strings is different.) + + The strings are returned in reverse order of length; that is, the long- + est matching string is given first. If there were too many matches to + fit into ovector, the yield of the function is zero, and the vector is + filled with the longest matches. Unlike pcre_exec(), pcre_dfa_exec() + can use the entire ovector for returning matched strings. + + NOTE: PCRE's "auto-possessification" optimization usually applies to + character repeats at the end of a pattern (as well as internally). For + example, the pattern "a\d+" is compiled as if it were "a\d++" because + there is no point even considering the possibility of backtracking into + the repeated digits. For DFA matching, this means that only one possi- + ble match is found. If you really do want multiple matches in such + cases, either use an ungreedy repeat ("a\d+?") or set the + PCRE_NO_AUTO_POSSESS option when compiling. + + Error returns from pcre_dfa_exec() + + The pcre_dfa_exec() function returns a negative number when it fails. + Many of the errors are the same as for pcre_exec(), and these are + described above. There are in addition the following errors that are + specific to pcre_dfa_exec(): + + PCRE_ERROR_DFA_UITEM (-16) + + This return is given if pcre_dfa_exec() encounters an item in the pat- + tern that it does not support, for instance, the use of \C or a back + reference. + + PCRE_ERROR_DFA_UCOND (-17) + + This return is given if pcre_dfa_exec() encounters a condition item + that uses a back reference for the condition, or a test for recursion + in a specific group. These are not supported. + + PCRE_ERROR_DFA_UMLIMIT (-18) + + This return is given if pcre_dfa_exec() is called with an extra block + that contains a setting of the match_limit or match_limit_recursion + fields. This is not supported (these fields are meaningless for DFA + matching). + + PCRE_ERROR_DFA_WSSIZE (-19) + + This return is given if pcre_dfa_exec() runs out of space in the + workspace vector. + + PCRE_ERROR_DFA_RECURSE (-20) + + When a recursive subpattern is processed, the matching function calls + itself recursively, using private vectors for ovector and workspace. + This error is given if the output vector is not large enough. This + should be extremely rare, as a vector of size 1000 is used. + + PCRE_ERROR_DFA_BADRESTART (-30) + + When pcre_dfa_exec() is called with the PCRE_DFA_RESTART option, some + plausibility checks are made on the contents of the workspace, which + should contain data about the previous partial match. If any of these + checks fail, this error is given. + + +SEE ALSO + + pcre16(3), pcre32(3), pcrebuild(3), pcrecallout(3), pcrecpp(3)(3), + pcrematching(3), pcrepartial(3), pcreposix(3), pcreprecompile(3), pcre- + sample(3), pcrestack(3). + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 09 February 2014 + Copyright (c) 1997-2014 University of Cambridge. +------------------------------------------------------------------------------ + + +PCRECALLOUT(3) Library Functions Manual PCRECALLOUT(3) + + + +NAME + PCRE - Perl-compatible regular expressions + +SYNOPSIS + + #include <pcre.h> + + int (*pcre_callout)(pcre_callout_block *); + + int (*pcre16_callout)(pcre16_callout_block *); + + int (*pcre32_callout)(pcre32_callout_block *); + + +DESCRIPTION + + PCRE provides a feature called "callout", which is a means of temporar- + ily passing control to the caller of PCRE in the middle of pattern + matching. The caller of PCRE provides an external function by putting + its entry point in the global variable pcre_callout (pcre16_callout for + the 16-bit library, pcre32_callout for the 32-bit library). By default, + this variable contains NULL, which disables all calling out. + + Within a regular expression, (?C) indicates the points at which the + external function is to be called. Different callout points can be + identified by putting a number less than 256 after the letter C. The + default value is zero. For example, this pattern has two callout + points: + + (?C1)abc(?C2)def + + If the PCRE_AUTO_CALLOUT option bit is set when a pattern is compiled, + PCRE automatically inserts callouts, all with number 255, before each + item in the pattern. For example, if PCRE_AUTO_CALLOUT is used with the + pattern + + A(\d{2}|--) + + it is processed as if it were + + (?C255)A(?C255)((?C255)\d{2}(?C255)|(?C255)-(?C255)-(?C255))(?C255) + + Notice that there is a callout before and after each parenthesis and + alternation bar. If the pattern contains a conditional group whose con- + dition is an assertion, an automatic callout is inserted immediately + before the condition. Such a callout may also be inserted explicitly, + for example: + + (?(?C9)(?=a)ab|de) + + This applies only to assertion conditions (because they are themselves + independent groups). + + Automatic callouts can be used for tracking the progress of pattern + matching. The pcretest program has a pattern qualifier (/C) that sets + automatic callouts; when it is used, the output indicates how the pat- + tern is being matched. This is useful information when you are trying + to optimize the performance of a particular pattern. + + +MISSING CALLOUTS + + You should be aware that, because of optimizations in the way PCRE com- + piles and matches patterns, callouts sometimes do not happen exactly as + you might expect. + + At compile time, PCRE "auto-possessifies" repeated items when it knows + that what follows cannot be part of the repeat. For example, a+[bc] is + compiled as if it were a++[bc]. The pcretest output when this pattern + is anchored and then applied with automatic callouts to the string + "aaaa" is: + + --->aaaa + +0 ^ ^ + +1 ^ a+ + +3 ^ ^ [bc] + No match + + This indicates that when matching [bc] fails, there is no backtracking + into a+ and therefore the callouts that would be taken for the back- + tracks do not occur. You can disable the auto-possessify feature by + passing PCRE_NO_AUTO_POSSESS to pcre_compile(), or starting the pattern + with (*NO_AUTO_POSSESS). If this is done in pcretest (using the /O + qualifier), the output changes to this: + + --->aaaa + +0 ^ ^ + +1 ^ a+ + +3 ^ ^ [bc] + +3 ^ ^ [bc] + +3 ^ ^ [bc] + +3 ^^ [bc] + No match + + This time, when matching [bc] fails, the matcher backtracks into a+ and + tries again, repeatedly, until a+ itself fails. + + Other optimizations that provide fast "no match" results also affect + callouts. For example, if the pattern is + + ab(?C4)cd + + PCRE knows that any matching string must contain the letter "d". If the + subject string is "abyz", the lack of "d" means that matching doesn't + ever start, and the callout is never reached. However, with "abyd", + though the result is still no match, the callout is obeyed. + + If the pattern is studied, PCRE knows the minimum length of a matching + string, and will immediately give a "no match" return without actually + running a match if the subject is not long enough, or, for unanchored + patterns, if it has been scanned far enough. + + You can disable these optimizations by passing the PCRE_NO_START_OPTI- + MIZE option to the matching function, or by starting the pattern with + (*NO_START_OPT). This slows down the matching process, but does ensure + that callouts such as the example above are obeyed. + + +THE CALLOUT INTERFACE + + During matching, when PCRE reaches a callout point, the external func- + tion defined by pcre_callout or pcre[16|32]_callout is called (if it is + set). This applies to both normal and DFA matching. The only argument + to the callout function is a pointer to a pcre_callout or + pcre[16|32]_callout block. These structures contains the following + fields: + + int version; + int callout_number; + int *offset_vector; + const char *subject; (8-bit version) + PCRE_SPTR16 subject; (16-bit version) + PCRE_SPTR32 subject; (32-bit version) + int subject_length; + int start_match; + int current_position; + int capture_top; + int capture_last; + void *callout_data; + int pattern_position; + int next_item_length; + const unsigned char *mark; (8-bit version) + const PCRE_UCHAR16 *mark; (16-bit version) + const PCRE_UCHAR32 *mark; (32-bit version) + + The version field is an integer containing the version number of the + block format. The initial version was 0; the current version is 2. The + version number will change again in future if additional fields are + added, but the intention is never to remove any of the existing fields. + + The callout_number field contains the number of the callout, as com- + piled into the pattern (that is, the number after ?C for manual call- + outs, and 255 for automatically generated callouts). + + The offset_vector field is a pointer to the vector of offsets that was + passed by the caller to the matching function. When pcre_exec() or + pcre[16|32]_exec() is used, the contents can be inspected, in order to + extract substrings that have been matched so far, in the same way as + for extracting substrings after a match has completed. For the DFA + matching functions, this field is not useful. + + The subject and subject_length fields contain copies of the values that + were passed to the matching function. + + The start_match field normally contains the offset within the subject + at which the current match attempt started. However, if the escape + sequence \K has been encountered, this value is changed to reflect the + modified starting point. If the pattern is not anchored, the callout + function may be called several times from the same point in the pattern + for different starting points in the subject. + + The current_position field contains the offset within the subject of + the current match pointer. + + When the pcre_exec() or pcre[16|32]_exec() is used, the capture_top + field contains one more than the number of the highest numbered cap- + tured substring so far. If no substrings have been captured, the value + of capture_top is one. This is always the case when the DFA functions + are used, because they do not support captured substrings. + + The capture_last field contains the number of the most recently cap- + tured substring. However, when a recursion exits, the value reverts to + what it was outside the recursion, as do the values of all captured + substrings. If no substrings have been captured, the value of cap- + ture_last is -1. This is always the case for the DFA matching func- + tions. + + The callout_data field contains a value that is passed to a matching + function specifically so that it can be passed back in callouts. It is + passed in the callout_data field of a pcre_extra or pcre[16|32]_extra + data structure. If no such data was passed, the value of callout_data + in a callout block is NULL. There is a description of the pcre_extra + structure in the pcreapi documentation. + + The pattern_position field is present from version 1 of the callout + structure. It contains the offset to the next item to be matched in the + pattern string. + + The next_item_length field is present from version 1 of the callout + structure. It contains the length of the next item to be matched in the + pattern string. When the callout immediately precedes an alternation + bar, a closing parenthesis, or the end of the pattern, the length is + zero. When the callout precedes an opening parenthesis, the length is + that of the entire subpattern. + + The pattern_position and next_item_length fields are intended to help + in distinguishing between different automatic callouts, which all have + the same callout number. However, they are set for all callouts. + + The mark field is present from version 2 of the callout structure. In + callouts from pcre_exec() or pcre[16|32]_exec() it contains a pointer + to the zero-terminated name of the most recently passed (*MARK), + (*PRUNE), or (*THEN) item in the match, or NULL if no such items have + been passed. Instances of (*PRUNE) or (*THEN) without a name do not + obliterate a previous (*MARK). In callouts from the DFA matching func- + tions this field always contains NULL. + + +RETURN VALUES + + The external callout function returns an integer to PCRE. If the value + is zero, matching proceeds as normal. If the value is greater than + zero, matching fails at the current point, but the testing of other + matching possibilities goes ahead, just as if a lookahead assertion had + failed. If the value is less than zero, the match is abandoned, the + matching function returns the negative value. + + Negative values should normally be chosen from the set of + PCRE_ERROR_xxx values. In particular, PCRE_ERROR_NOMATCH forces a stan- + dard "no match" failure. The error number PCRE_ERROR_CALLOUT is + reserved for use by callout functions; it will never be used by PCRE + itself. + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 12 November 2013 + Copyright (c) 1997-2013 University of Cambridge. +------------------------------------------------------------------------------ + + +PCRECOMPAT(3) Library Functions Manual PCRECOMPAT(3) + + + +NAME + PCRE - Perl-compatible regular expressions + +DIFFERENCES BETWEEN PCRE AND PERL + + This document describes the differences in the ways that PCRE and Perl + handle regular expressions. The differences described here are with + respect to Perl versions 5.10 and above. + + 1. PCRE has only a subset of Perl's Unicode support. Details of what it + does have are given in the pcreunicode page. + + 2. PCRE allows repeat quantifiers only on parenthesized assertions, but + they do not mean what you might think. For example, (?!a){3} does not + assert that the next three characters are not "a". It just asserts that + the next character is not "a" three times (in principle: PCRE optimizes + this to run the assertion just once). Perl allows repeat quantifiers on + other assertions such as \b, but these do not seem to have any use. + + 3. Capturing subpatterns that occur inside negative lookahead asser- + tions are counted, but their entries in the offsets vector are never + set. Perl sometimes (but not always) sets its numerical variables from + inside negative assertions. + + 4. Though binary zero characters are supported in the subject string, + they are not allowed in a pattern string because it is passed as a nor- + mal C string, terminated by zero. The escape sequence \0 can be used in + the pattern to represent a binary zero. + + 5. The following Perl escape sequences are not supported: \l, \u, \L, + \U, and \N when followed by a character name or Unicode value. (\N on + its own, matching a non-newline character, is supported.) In fact these + are implemented by Perl's general string-handling and are not part of + its pattern matching engine. If any of these are encountered by PCRE, + an error is generated by default. However, if the PCRE_JAVASCRIPT_COM- + PAT option is set, \U and \u are interpreted as JavaScript interprets + them. + + 6. The Perl escape sequences \p, \P, and \X are supported only if PCRE + is built with Unicode character property support. The properties that + can be tested with \p and \P are limited to the general category prop- + erties such as Lu and Nd, script names such as Greek or Han, and the + derived properties Any and L&. PCRE does support the Cs (surrogate) + property, which Perl does not; the Perl documentation says "Because + Perl hides the need for the user to understand the internal representa- + tion of Unicode characters, there is no need to implement the somewhat + messy concept of surrogates." + + 7. PCRE does support the \Q...\E escape for quoting substrings. Charac- + ters in between are treated as literals. This is slightly different + from Perl in that $ and @ are also handled as literals inside the + quotes. In Perl, they cause variable interpolation (but of course PCRE + does not have variables). Note the following examples: + + Pattern PCRE matches Perl matches + + \Qabc$xyz\E abc$xyz abc followed by the + contents of $xyz + \Qabc\$xyz\E abc\$xyz abc\$xyz + \Qabc\E\$\Qxyz\E abc$xyz abc$xyz + + The \Q...\E sequence is recognized both inside and outside character + classes. + + 8. Fairly obviously, PCRE does not support the (?{code}) and (??{code}) + constructions. However, there is support for recursive patterns. This + is not available in Perl 5.8, but it is in Perl 5.10. Also, the PCRE + "callout" feature allows an external function to be called during pat- + tern matching. See the pcrecallout documentation for details. + + 9. Subpatterns that are called as subroutines (whether or not recur- + sively) are always treated as atomic groups in PCRE. This is like + Python, but unlike Perl. Captured values that are set outside a sub- + routine call can be reference from inside in PCRE, but not in Perl. + There is a discussion that explains these differences in more detail in + the section on recursion differences from Perl in the pcrepattern page. + + 10. If any of the backtracking control verbs are used in a subpattern + that is called as a subroutine (whether or not recursively), their + effect is confined to that subpattern; it does not extend to the sur- + rounding pattern. This is not always the case in Perl. In particular, + if (*THEN) is present in a group that is called as a subroutine, its + action is limited to that group, even if the group does not contain any + | characters. Note that such subpatterns are processed as anchored at + the point where they are tested. + + 11. If a pattern contains more than one backtracking control verb, the + first one that is backtracked onto acts. For example, in the pattern + A(*COMMIT)B(*PRUNE)C a failure in B triggers (*COMMIT), but a failure + in C triggers (*PRUNE). Perl's behaviour is more complex; in many cases + it is the same as PCRE, but there are examples where it differs. + + 12. Most backtracking verbs in assertions have their normal actions. + They are not confined to the assertion. + + 13. There are some differences that are concerned with the settings of + captured strings when part of a pattern is repeated. For example, + matching "aba" against the pattern /^(a(b)?)+$/ in Perl leaves $2 + unset, but in PCRE it is set to "b". + + 14. PCRE's handling of duplicate subpattern numbers and duplicate sub- + pattern names is not as general as Perl's. This is a consequence of the + fact the PCRE works internally just with numbers, using an external ta- + ble to translate between numbers and names. In particular, a pattern + such as (?|(?<a>A)|(?<b)B), where the two capturing parentheses have + the same number but different names, is not supported, and causes an + error at compile time. If it were allowed, it would not be possible to + distinguish which parentheses matched, because both names map to cap- + turing subpattern number 1. To avoid this confusing situation, an error + is given at compile time. + + 15. Perl recognizes comments in some places that PCRE does not, for + example, between the ( and ? at the start of a subpattern. If the /x + modifier is set, Perl allows white space between ( and ? (though cur- + rent Perls warn that this is deprecated) but PCRE never does, even if + the PCRE_EXTENDED option is set. + + 16. Perl, when in warning mode, gives warnings for character classes + such as [A-\d] or [a-[:digit:]]. It then treats the hyphens as liter- + als. PCRE has no warning features, so it gives an error in these cases + because they are almost certainly user mistakes. + + 17. In PCRE, the upper/lower case character properties Lu and Ll are + not affected when case-independent matching is specified. For example, + \p{Lu} always matches an upper case letter. I think Perl has changed in + this respect; in the release at the time of writing (5.16), \p{Lu} and + \p{Ll} match all letters, regardless of case, when case independence is + specified. + + 18. PCRE provides some extensions to the Perl regular expression facil- + ities. Perl 5.10 includes new features that are not in earlier ver- + sions of Perl, some of which (such as named parentheses) have been in + PCRE for some time. This list is with respect to Perl 5.10: + + (a) Although lookbehind assertions in PCRE must match fixed length + strings, each alternative branch of a lookbehind assertion can match a + different length of string. Perl requires them all to have the same + length. + + (b) If PCRE_DOLLAR_ENDONLY is set and PCRE_MULTILINE is not set, the $ + meta-character matches only at the very end of the string. + + (c) If PCRE_EXTRA is set, a backslash followed by a letter with no spe- + cial meaning is faulted. Otherwise, like Perl, the backslash is quietly + ignored. (Perl can be made to issue a warning.) + + (d) If PCRE_UNGREEDY is set, the greediness of the repetition quanti- + fiers is inverted, that is, by default they are not greedy, but if fol- + lowed by a question mark they are. + + (e) PCRE_ANCHORED can be used at matching time to force a pattern to be + tried only at the first matching position in the subject string. + + (f) The PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, + and PCRE_NO_AUTO_CAPTURE options for pcre_exec() have no Perl equiva- + lents. + + (g) The \R escape sequence can be restricted to match only CR, LF, or + CRLF by the PCRE_BSR_ANYCRLF option. + + (h) The callout facility is PCRE-specific. + + (i) The partial matching facility is PCRE-specific. + + (j) Patterns compiled by PCRE can be saved and re-used at a later time, + even on different hosts that have the other endianness. However, this + does not apply to optimized data created by the just-in-time compiler. + + (k) The alternative matching functions (pcre_dfa_exec(), + pcre16_dfa_exec() and pcre32_dfa_exec(),) match in a different way and + are not Perl-compatible. + + (l) PCRE recognizes some special sequences such as (*CR) at the start + of a pattern that set overall options that cannot be changed within the + pattern. + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 10 November 2013 + Copyright (c) 1997-2013 University of Cambridge. +------------------------------------------------------------------------------ + + +PCREPATTERN(3) Library Functions Manual PCREPATTERN(3) + + + +NAME + PCRE - Perl-compatible regular expressions + +PCRE REGULAR EXPRESSION DETAILS + + The syntax and semantics of the regular expressions that are supported + by PCRE are described in detail below. There is a quick-reference syn- + tax summary in the pcresyntax page. PCRE tries to match Perl syntax and + semantics as closely as it can. PCRE also supports some alternative + regular expression syntax (which does not conflict with the Perl syn- + tax) in order to provide some compatibility with regular expressions in + Python, .NET, and Oniguruma. + + Perl's regular expressions are described in its own documentation, and + regular expressions in general are covered in a number of books, some + of which have copious examples. Jeffrey Friedl's "Mastering Regular + Expressions", published by O'Reilly, covers regular expressions in + great detail. This description of PCRE's regular expressions is + intended as reference material. + + This document discusses the patterns that are supported by PCRE when + one its main matching functions, pcre_exec() (8-bit) or + pcre[16|32]_exec() (16- or 32-bit), is used. PCRE also has alternative + matching functions, pcre_dfa_exec() and pcre[16|32_dfa_exec(), which + match using a different algorithm that is not Perl-compatible. Some of + the features discussed below are not available when DFA matching is + used. The advantages and disadvantages of the alternative functions, + and how they differ from the normal functions, are discussed in the + pcrematching page. + + +SPECIAL START-OF-PATTERN ITEMS + + A number of options that can be passed to pcre_compile() can also be + set by special items at the start of a pattern. These are not Perl-com- + patible, but are provided to make these options accessible to pattern + writers who are not able to change the program that processes the pat- + tern. Any number of these items may appear, but they must all be + together right at the start of the pattern string, and the letters must + be in upper case. + + UTF support + + The original operation of PCRE was on strings of one-byte characters. + However, there is now also support for UTF-8 strings in the original + library, an extra library that supports 16-bit and UTF-16 character + strings, and a third library that supports 32-bit and UTF-32 character + strings. To use these features, PCRE must be built to include appropri- + ate support. When using UTF strings you must either call the compiling + function with the PCRE_UTF8, PCRE_UTF16, or PCRE_UTF32 option, or the + pattern must start with one of these special sequences: + + (*UTF8) + (*UTF16) + (*UTF32) + (*UTF) + + (*UTF) is a generic sequence that can be used with any of the + libraries. Starting a pattern with such a sequence is equivalent to + setting the relevant option. How setting a UTF mode affects pattern + matching is mentioned in several places below. There is also a summary + of features in the pcreunicode page. + + Some applications that allow their users to supply patterns may wish to + restrict them to non-UTF data for security reasons. If the + PCRE_NEVER_UTF option is set at compile time, (*UTF) etc. are not + allowed, and their appearance causes an error. + + Unicode property support + + Another special sequence that may appear at the start of a pattern is + (*UCP). This has the same effect as setting the PCRE_UCP option: it + causes sequences such as \d and \w to use Unicode properties to deter- + mine character types, instead of recognizing only characters with codes + less than 128 via a lookup table. + + Disabling auto-possessification + + If a pattern starts with (*NO_AUTO_POSSESS), it has the same effect as + setting the PCRE_NO_AUTO_POSSESS option at compile time. This stops + PCRE from making quantifiers possessive when what follows cannot match + the repeated item. For example, by default a+b is treated as a++b. For + more details, see the pcreapi documentation. + + Disabling start-up optimizations + + If a pattern starts with (*NO_START_OPT), it has the same effect as + setting the PCRE_NO_START_OPTIMIZE option either at compile or matching + time. This disables several optimizations for quickly reaching "no + match" results. For more details, see the pcreapi documentation. + + Newline conventions + + PCRE supports five different conventions for indicating line breaks in + strings: a single CR (carriage return) character, a single LF (line- + feed) character, the two-character sequence CRLF, any of the three pre- + ceding, or any Unicode newline sequence. The pcreapi page has further + discussion about newlines, and shows how to set the newline convention + in the options arguments for the compiling and matching functions. + + It is also possible to specify a newline convention by starting a pat- + tern string with one of the following five sequences: + + (*CR) carriage return + (*LF) linefeed + (*CRLF) carriage return, followed by linefeed + (*ANYCRLF) any of the three above + (*ANY) all Unicode newline sequences + + These override the default and the options given to the compiling func- + tion. For example, on a Unix system where LF is the default newline + sequence, the pattern + + (*CR)a.b + + changes the convention to CR. That pattern matches "a\nb" because LF is + no longer a newline. If more than one of these settings is present, the + last one is used. + + The newline convention affects where the circumflex and dollar asser- + tions are true. It also affects the interpretation of the dot metachar- + acter when PCRE_DOTALL is not set, and the behaviour of \N. However, it + does not affect what the \R escape sequence matches. By default, this + is any Unicode newline sequence, for Perl compatibility. However, this + can be changed; see the description of \R in the section entitled "New- + line sequences" below. A change of \R setting can be combined with a + change of newline convention. + + Setting match and recursion limits + + The caller of pcre_exec() can set a limit on the number of times the + internal match() function is called and on the maximum depth of recur- + sive calls. These facilities are provided to catch runaway matches that + are provoked by patterns with huge matching trees (a typical example is + a pattern with nested unlimited repeats) and to avoid running out of + system stack by too much recursion. When one of these limits is + reached, pcre_exec() gives an error return. The limits can also be set + by items at the start of the pattern of the form + + (*LIMIT_MATCH=d) + (*LIMIT_RECURSION=d) + + where d is any number of decimal digits. However, the value of the set- + ting must be less than the value set (or defaulted) by the caller of + pcre_exec() for it to have any effect. In other words, the pattern + writer can lower the limits set by the programmer, but not raise them. + If there is more than one setting of one of these limits, the lower + value is used. + + +EBCDIC CHARACTER CODES + + PCRE can be compiled to run in an environment that uses EBCDIC as its + character code rather than ASCII or Unicode (typically a mainframe sys- + tem). In the sections below, character code values are ASCII or Uni- + code; in an EBCDIC environment these characters may have different code + values, and there are no code points greater than 255. + + +CHARACTERS AND METACHARACTERS + + A regular expression is a pattern that is matched against a subject + string from left to right. Most characters stand for themselves in a + pattern, and match the corresponding characters in the subject. As a + trivial example, the pattern + + The quick brown fox + + matches a portion of a subject string that is identical to itself. When + caseless matching is specified (the PCRE_CASELESS option), letters are + matched independently of case. In a UTF mode, PCRE always understands + the concept of case for characters whose values are less than 128, so + caseless matching is always possible. For characters with higher val- + ues, the concept of case is supported if PCRE is compiled with Unicode + property support, but not otherwise. If you want to use caseless + matching for characters 128 and above, you must ensure that PCRE is + compiled with Unicode property support as well as with UTF support. + + The power of regular expressions comes from the ability to include + alternatives and repetitions in the pattern. These are encoded in the + pattern by the use of metacharacters, which do not stand for themselves + but instead are interpreted in some special way. + + There are two different sets of metacharacters: those that are recog- + nized anywhere in the pattern except within square brackets, and those + that are recognized within square brackets. Outside square brackets, + the metacharacters are as follows: + + \ general escape character with several uses + ^ assert start of string (or line, in multiline mode) + $ assert end of string (or line, in multiline mode) + . match any character except newline (by default) + [ start character class definition + | start of alternative branch + ( start subpattern + ) end subpattern + ? extends the meaning of ( + also 0 or 1 quantifier + also quantifier minimizer + * 0 or more quantifier + + 1 or more quantifier + also "possessive quantifier" + { start min/max quantifier + + Part of a pattern that is in square brackets is called a "character + class". In a character class the only metacharacters are: + + \ general escape character + ^ negate the class, but only if the first character + - indicates character range + [ POSIX character class (only if followed by POSIX + syntax) + ] terminates the character class + + The following sections describe the use of each of the metacharacters. + + +BACKSLASH + + The backslash character has several uses. Firstly, if it is followed by + a character that is not a number or a letter, it takes away any special + meaning that character may have. This use of backslash as an escape + character applies both inside and outside character classes. + + For example, if you want to match a * character, you write \* in the + pattern. This escaping action applies whether or not the following + character would otherwise be interpreted as a metacharacter, so it is + always safe to precede a non-alphanumeric with backslash to specify + that it stands for itself. In particular, if you want to match a back- + slash, you write \\. + + In a UTF mode, only ASCII numbers and letters have any special meaning + after a backslash. All other characters (in particular, those whose + codepoints are greater than 127) are treated as literals. + + If a pattern is compiled with the PCRE_EXTENDED option, most white + space in the pattern (other than in a character class), and characters + between a # outside a character class and the next newline, inclusive, + are ignored. An escaping backslash can be used to include a white space + or # character as part of the pattern. + + If you want to remove the special meaning from a sequence of charac- + ters, you can do so by putting them between \Q and \E. This is differ- + ent from Perl in that $ and @ are handled as literals in \Q...\E + sequences in PCRE, whereas in Perl, $ and @ cause variable interpola- + tion. Note the following examples: + + Pattern PCRE matches Perl matches + + \Qabc$xyz\E abc$xyz abc followed by the + contents of $xyz + \Qabc\$xyz\E abc\$xyz abc\$xyz + \Qabc\E\$\Qxyz\E abc$xyz abc$xyz + + The \Q...\E sequence is recognized both inside and outside character + classes. An isolated \E that is not preceded by \Q is ignored. If \Q + is not followed by \E later in the pattern, the literal interpretation + continues to the end of the pattern (that is, \E is assumed at the + end). If the isolated \Q is inside a character class, this causes an + error, because the character class is not terminated. + + Non-printing characters + + A second use of backslash provides a way of encoding non-printing char- + acters in patterns in a visible manner. There is no restriction on the + appearance of non-printing characters, apart from the binary zero that + terminates a pattern, but when a pattern is being prepared by text + editing, it is often easier to use one of the following escape + sequences than the binary character it represents: + + \a alarm, that is, the BEL character (hex 07) + \cx "control-x", where x is any ASCII character + \e escape (hex 1B) + \f form feed (hex 0C) + \n linefeed (hex 0A) + \r carriage return (hex 0D) + \t tab (hex 09) + \0dd character with octal code 0dd + \ddd character with octal code ddd, or back reference + \o{ddd..} character with octal code ddd.. + \xhh character with hex code hh + \x{hhh..} character with hex code hhh.. (non-JavaScript mode) + \uhhhh character with hex code hhhh (JavaScript mode only) + + The precise effect of \cx on ASCII characters is as follows: if x is a + lower case letter, it is converted to upper case. Then bit 6 of the + character (hex 40) is inverted. Thus \cA to \cZ become hex 01 to hex 1A + (A is 41, Z is 5A), but \c{ becomes hex 3B ({ is 7B), and \c; becomes + hex 7B (; is 3B). If the data item (byte or 16-bit value) following \c + has a value greater than 127, a compile-time error occurs. This locks + out non-ASCII characters in all modes. + + The \c facility was designed for use with ASCII characters, but with + the extension to Unicode it is even less useful than it once was. It + is, however, recognized when PCRE is compiled in EBCDIC mode, where + data items are always bytes. In this mode, all values are valid after + \c. If the next character is a lower case letter, it is converted to + upper case. Then the 0xc0 bits of the byte are inverted. Thus \cA + becomes hex 01, as in ASCII (A is C1), but because the EBCDIC letters + are disjoint, \cZ becomes hex 29 (Z is E9), and other characters also + generate different values. + + After \0 up to two further octal digits are read. If there are fewer + than two digits, just those that are present are used. Thus the + sequence \0\x\07 specifies two binary zeros followed by a BEL character + (code value 7). Make sure you supply two digits after the initial zero + if the pattern character that follows is itself an octal digit. + + The escape \o must be followed by a sequence of octal digits, enclosed + in braces. An error occurs if this is not the case. This escape is a + recent addition to Perl; it provides way of specifying character code + points as octal numbers greater than 0777, and it also allows octal + numbers and back references to be unambiguously specified. + + For greater clarity and unambiguity, it is best to avoid following \ by + a digit greater than zero. Instead, use \o{} or \x{} to specify charac- + ter numbers, and \g{} to specify back references. The following para- + graphs describe the old, ambiguous syntax. + + The handling of a backslash followed by a digit other than 0 is compli- + cated, and Perl has changed in recent releases, causing PCRE also to + change. Outside a character class, PCRE reads the digit and any follow- + ing digits as a decimal number. If the number is less than 8, or if + there have been at least that many previous capturing left parentheses + in the expression, the entire sequence is taken as a back reference. A + description of how this works is given later, following the discussion + of parenthesized subpatterns. + + Inside a character class, or if the decimal number following \ is + greater than 7 and there have not been that many capturing subpatterns, + PCRE handles \8 and \9 as the literal characters "8" and "9", and oth- + erwise re-reads up to three octal digits following the backslash, using + them to generate a data character. Any subsequent digits stand for + themselves. For example: + + \040 is another way of writing an ASCII space + \40 is the same, provided there are fewer than 40 + previous capturing subpatterns + \7 is always a back reference + \11 might be a back reference, or another way of + writing a tab + \011 is always a tab + \0113 is a tab followed by the character "3" + \113 might be a back reference, otherwise the + character with octal code 113 + \377 might be a back reference, otherwise + the value 255 (decimal) + \81 is either a back reference, or the two + characters "8" and "1" + + Note that octal values of 100 or greater that are specified using this + syntax must not be introduced by a leading zero, because no more than + three octal digits are ever read. + + By default, after \x that is not followed by {, from zero to two hexa- + decimal digits are read (letters can be in upper or lower case). Any + number of hexadecimal digits may appear between \x{ and }. If a charac- + ter other than a hexadecimal digit appears between \x{ and }, or if + there is no terminating }, an error occurs. + + If the PCRE_JAVASCRIPT_COMPAT option is set, the interpretation of \x + is as just described only when it is followed by two hexadecimal dig- + its. Otherwise, it matches a literal "x" character. In JavaScript + mode, support for code points greater than 256 is provided by \u, which + must be followed by four hexadecimal digits; otherwise it matches a + literal "u" character. + + Characters whose value is less than 256 can be defined by either of the + two syntaxes for \x (or by \u in JavaScript mode). There is no differ- + ence in the way they are handled. For example, \xdc is exactly the same + as \x{dc} (or \u00dc in JavaScript mode). + + Constraints on character values + + Characters that are specified using octal or hexadecimal numbers are + limited to certain values, as follows: + + 8-bit non-UTF mode less than 0x100 + 8-bit UTF-8 mode less than 0x10ffff and a valid codepoint + 16-bit non-UTF mode less than 0x10000 + 16-bit UTF-16 mode less than 0x10ffff and a valid codepoint + 32-bit non-UTF mode less than 0x100000000 + 32-bit UTF-32 mode less than 0x10ffff and a valid codepoint + + Invalid Unicode codepoints are the range 0xd800 to 0xdfff (the so- + called "surrogate" codepoints), and 0xffef. + + Escape sequences in character classes + + All the sequences that define a single character value can be used both + inside and outside character classes. In addition, inside a character + class, \b is interpreted as the backspace character (hex 08). + + \N is not allowed in a character class. \B, \R, and \X are not special + inside a character class. Like other unrecognized escape sequences, + they are treated as the literal characters "B", "R", and "X" by + default, but cause an error if the PCRE_EXTRA option is set. Outside a + character class, these sequences have different meanings. + + Unsupported escape sequences + + In Perl, the sequences \l, \L, \u, and \U are recognized by its string + handler and used to modify the case of following characters. By + default, PCRE does not support these escape sequences. However, if the + PCRE_JAVASCRIPT_COMPAT option is set, \U matches a "U" character, and + \u can be used to define a character by code point, as described in the + previous section. + + Absolute and relative back references + + The sequence \g followed by an unsigned or a negative number, option- + ally enclosed in braces, is an absolute or relative back reference. A + named back reference can be coded as \g{name}. Back references are dis- + cussed later, following the discussion of parenthesized subpatterns. + + Absolute and relative subroutine calls + + For compatibility with Oniguruma, the non-Perl syntax \g followed by a + name or a number enclosed either in angle brackets or single quotes, is + an alternative syntax for referencing a subpattern as a "subroutine". + Details are discussed later. Note that \g{...} (Perl syntax) and + \g<...> (Oniguruma syntax) are not synonymous. The former is a back + reference; the latter is a subroutine call. + + Generic character types + + Another use of backslash is for specifying generic character types: + + \d any decimal digit + \D any character that is not a decimal digit + \h any horizontal white space character + \H any character that is not a horizontal white space character + \s any white space character + \S any character that is not a white space character + \v any vertical white space character + \V any character that is not a vertical white space character + \w any "word" character + \W any "non-word" character + + There is also the single sequence \N, which matches a non-newline char- + acter. This is the same as the "." metacharacter when PCRE_DOTALL is + not set. Perl also uses \N to match characters by name; PCRE does not + support this. + + Each pair of lower and upper case escape sequences partitions the com- + plete set of characters into two disjoint sets. Any given character + matches one, and only one, of each pair. The sequences can appear both + inside and outside character classes. They each match one character of + the appropriate type. If the current matching point is at the end of + the subject string, all of them fail, because there is no character to + match. + + For compatibility with Perl, \s did not used to match the VT character + (code 11), which made it different from the the POSIX "space" class. + However, Perl added VT at release 5.18, and PCRE followed suit at + release 8.34. The default \s characters are now HT (9), LF (10), VT + (11), FF (12), CR (13), and space (32), which are defined as white + space in the "C" locale. This list may vary if locale-specific matching + is taking place. For example, in some locales the "non-breaking space" + character (\xA0) is recognized as white space, and in others the VT + character is not. + + A "word" character is an underscore or any character that is a letter + or digit. By default, the definition of letters and digits is con- + trolled by PCRE's low-valued character tables, and may vary if locale- + specific matching is taking place (see "Locale support" in the pcreapi + page). For example, in a French locale such as "fr_FR" in Unix-like + systems, or "french" in Windows, some character codes greater than 127 + are used for accented letters, and these are then matched by \w. The + use of locales with Unicode is discouraged. + + By default, characters whose code points are greater than 127 never + match \d, \s, or \w, and always match \D, \S, and \W, although this may + vary for characters in the range 128-255 when locale-specific matching + is happening. These escape sequences retain their original meanings + from before Unicode support was available, mainly for efficiency rea- + sons. If PCRE is compiled with Unicode property support, and the + PCRE_UCP option is set, the behaviour is changed so that Unicode prop- + erties are used to determine character types, as follows: + + \d any character that matches \p{Nd} (decimal digit) + \s any character that matches \p{Z} or \h or \v + \w any character that matches \p{L} or \p{N}, plus underscore + + The upper case escapes match the inverse sets of characters. Note that + \d matches only decimal digits, whereas \w matches any Unicode digit, + as well as any Unicode letter, and underscore. Note also that PCRE_UCP + affects \b, and \B because they are defined in terms of \w and \W. + Matching these sequences is noticeably slower when PCRE_UCP is set. + + The sequences \h, \H, \v, and \V are features that were added to Perl + at release 5.10. In contrast to the other sequences, which match only + ASCII characters by default, these always match certain high-valued + code points, whether or not PCRE_UCP is set. The horizontal space char- + acters are: + + U+0009 Horizontal tab (HT) + U+0020 Space + U+00A0 Non-break space + U+1680 Ogham space mark + U+180E Mongolian vowel separator + U+2000 En quad + U+2001 Em quad + U+2002 En space + U+2003 Em space + U+2004 Three-per-em space + U+2005 Four-per-em space + U+2006 Six-per-em space + U+2007 Figure space + U+2008 Punctuation space + U+2009 Thin space + U+200A Hair space + U+202F Narrow no-break space + U+205F Medium mathematical space + U+3000 Ideographic space + + The vertical space characters are: + + U+000A Linefeed (LF) + U+000B Vertical tab (VT) + U+000C Form feed (FF) + U+000D Carriage return (CR) + U+0085 Next line (NEL) + U+2028 Line separator + U+2029 Paragraph separator + + In 8-bit, non-UTF-8 mode, only the characters with codepoints less than + 256 are relevant. + + Newline sequences + + Outside a character class, by default, the escape sequence \R matches + any Unicode newline sequence. In 8-bit non-UTF-8 mode \R is equivalent + to the following: + + (?>\r\n|\n|\x0b|\f|\r|\x85) + + This is an example of an "atomic group", details of which are given + below. This particular group matches either the two-character sequence + CR followed by LF, or one of the single characters LF (linefeed, + U+000A), VT (vertical tab, U+000B), FF (form feed, U+000C), CR (car- + riage return, U+000D), or NEL (next line, U+0085). The two-character + sequence is treated as a single unit that cannot be split. + + In other modes, two additional characters whose codepoints are greater + than 255 are added: LS (line separator, U+2028) and PS (paragraph sepa- + rator, U+2029). Unicode character property support is not needed for + these characters to be recognized. + + It is possible to restrict \R to match only CR, LF, or CRLF (instead of + the complete set of Unicode line endings) by setting the option + PCRE_BSR_ANYCRLF either at compile time or when the pattern is matched. + (BSR is an abbrevation for "backslash R".) This can be made the default + when PCRE is built; if this is the case, the other behaviour can be + requested via the PCRE_BSR_UNICODE option. It is also possible to + specify these settings by starting a pattern string with one of the + following sequences: + + (*BSR_ANYCRLF) CR, LF, or CRLF only + (*BSR_UNICODE) any Unicode newline sequence + + These override the default and the options given to the compiling func- + tion, but they can themselves be overridden by options given to a + matching function. Note that these special settings, which are not + Perl-compatible, are recognized only at the very start of a pattern, + and that they must be in upper case. If more than one of them is + present, the last one is used. They can be combined with a change of + newline convention; for example, a pattern can start with: + + (*ANY)(*BSR_ANYCRLF) + + They can also be combined with the (*UTF8), (*UTF16), (*UTF32), (*UTF) + or (*UCP) special sequences. Inside a character class, \R is treated as + an unrecognized escape sequence, and so matches the letter "R" by + default, but causes an error if PCRE_EXTRA is set. + + Unicode character properties + + When PCRE is built with Unicode character property support, three addi- + tional escape sequences that match characters with specific properties + are available. When in 8-bit non-UTF-8 mode, these sequences are of + course limited to testing characters whose codepoints are less than + 256, but they do work in this mode. The extra escape sequences are: + + \p{xx} a character with the xx property + \P{xx} a character without the xx property + \X a Unicode extended grapheme cluster + + The property names represented by xx above are limited to the Unicode + script names, the general category properties, "Any", which matches any + character (including newline), and some special PCRE properties + (described in the next section). Other Perl properties such as "InMu- + sicalSymbols" are not currently supported by PCRE. Note that \P{Any} + does not match any characters, so always causes a match failure. + + Sets of Unicode characters are defined as belonging to certain scripts. + A character from one of these sets can be matched using a script name. + For example: + + \p{Greek} + \P{Han} + + Those that are not part of an identified script are lumped together as + "Common". The current list of scripts is: + + Arabic, Armenian, Avestan, Balinese, Bamum, Batak, Bengali, Bopomofo, + Brahmi, Braille, Buginese, Buhid, Canadian_Aboriginal, Carian, Chakma, + Cham, Cherokee, Common, Coptic, Cuneiform, Cypriot, Cyrillic, Deseret, + Devanagari, Egyptian_Hieroglyphs, Ethiopic, Georgian, Glagolitic, + Gothic, Greek, Gujarati, Gurmukhi, Han, Hangul, Hanunoo, Hebrew, Hira- + gana, Imperial_Aramaic, Inherited, Inscriptional_Pahlavi, Inscrip- + tional_Parthian, Javanese, Kaithi, Kannada, Katakana, Kayah_Li, + Kharoshthi, Khmer, Lao, Latin, Lepcha, Limbu, Linear_B, Lisu, Lycian, + Lydian, Malayalam, Mandaic, Meetei_Mayek, Meroitic_Cursive, + Meroitic_Hieroglyphs, Miao, Mongolian, Myanmar, New_Tai_Lue, Nko, + Ogham, Old_Italic, Old_Persian, Old_South_Arabian, Old_Turkic, + Ol_Chiki, Oriya, Osmanya, Phags_Pa, Phoenician, Rejang, Runic, Samari- + tan, Saurashtra, Sharada, Shavian, Sinhala, Sora_Sompeng, Sundanese, + Syloti_Nagri, Syriac, Tagalog, Tagbanwa, Tai_Le, Tai_Tham, Tai_Viet, + Takri, Tamil, Telugu, Thaana, Thai, Tibetan, Tifinagh, Ugaritic, Vai, + Yi. + + Each character has exactly one Unicode general category property, spec- + ified by a two-letter abbreviation. For compatibility with Perl, nega- + tion can be specified by including a circumflex between the opening + brace and the property name. For example, \p{^Lu} is the same as + \P{Lu}. + + If only one letter is specified with \p or \P, it includes all the gen- + eral category properties that start with that letter. In this case, in + the absence of negation, the curly brackets in the escape sequence are + optional; these two examples have the same effect: + + \p{L} + \pL + + The following general category property codes are supported: + + C Other + Cc Control + Cf Format + Cn Unassigned + Co Private use + Cs Surrogate + + L Letter + Ll Lower case letter + Lm Modifier letter + Lo Other letter + Lt Title case letter + Lu Upper case letter + + M Mark + Mc Spacing mark + Me Enclosing mark + Mn Non-spacing mark + + N Number + Nd Decimal number + Nl Letter number + No Other number + + P Punctuation + Pc Connector punctuation + Pd Dash punctuation + Pe Close punctuation + Pf Final punctuation + Pi Initial punctuation + Po Other punctuation + Ps Open punctuation + + S Symbol + Sc Currency symbol + Sk Modifier symbol + Sm Mathematical symbol + So Other symbol + + Z Separator + Zl Line separator + Zp Paragraph separator + Zs Space separator + + The special property L& is also supported: it matches a character that + has the Lu, Ll, or Lt property, in other words, a letter that is not + classified as a modifier or "other". + + The Cs (Surrogate) property applies only to characters in the range + U+D800 to U+DFFF. Such characters are not valid in Unicode strings and + so cannot be tested by PCRE, unless UTF validity checking has been + turned off (see the discussion of PCRE_NO_UTF8_CHECK, + PCRE_NO_UTF16_CHECK and PCRE_NO_UTF32_CHECK in the pcreapi page). Perl + does not support the Cs property. + + The long synonyms for property names that Perl supports (such as + \p{Letter}) are not supported by PCRE, nor is it permitted to prefix + any of these properties with "Is". + + No character that is in the Unicode table has the Cn (unassigned) prop- + erty. Instead, this property is assumed for any code point that is not + in the Unicode table. + + Specifying caseless matching does not affect these escape sequences. + For example, \p{Lu} always matches only upper case letters. This is + different from the behaviour of current versions of Perl. + + Matching characters by Unicode property is not fast, because PCRE has + to do a multistage table lookup in order to find a character's prop- + erty. That is why the traditional escape sequences such as \d and \w do + not use Unicode properties in PCRE by default, though you can make them + do so by setting the PCRE_UCP option or by starting the pattern with + (*UCP). + + Extended grapheme clusters + + The \X escape matches any number of Unicode characters that form an + "extended grapheme cluster", and treats the sequence as an atomic group + (see below). Up to and including release 8.31, PCRE matched an ear- + lier, simpler definition that was equivalent to + + (?>\PM\pM*) + + That is, it matched a character without the "mark" property, followed + by zero or more characters with the "mark" property. Characters with + the "mark" property are typically non-spacing accents that affect the + preceding character. + + This simple definition was extended in Unicode to include more compli- + cated kinds of composite character by giving each character a grapheme + breaking property, and creating rules that use these properties to + define the boundaries of extended grapheme clusters. In releases of + PCRE later than 8.31, \X matches one of these clusters. + + \X always matches at least one character. Then it decides whether to + add additional characters according to the following rules for ending a + cluster: + + 1. End at the end of the subject string. + + 2. Do not end between CR and LF; otherwise end after any control char- + acter. + + 3. Do not break Hangul (a Korean script) syllable sequences. Hangul + characters are of five types: L, V, T, LV, and LVT. An L character may + be followed by an L, V, LV, or LVT character; an LV or V character may + be followed by a V or T character; an LVT or T character may be follwed + only by a T character. + + 4. Do not end before extending characters or spacing marks. Characters + with the "mark" property always have the "extend" grapheme breaking + property. + + 5. Do not end after prepend characters. + + 6. Otherwise, end the cluster. + + PCRE's additional properties + + As well as the standard Unicode properties described above, PCRE sup- + ports four more that make it possible to convert traditional escape + sequences such as \w and \s to use Unicode properties. PCRE uses these + non-standard, non-Perl properties internally when PCRE_UCP is set. How- + ever, they may also be used explicitly. These properties are: + + Xan Any alphanumeric character + Xps Any POSIX space character + Xsp Any Perl space character + Xwd Any Perl "word" character + + Xan matches characters that have either the L (letter) or the N (num- + ber) property. Xps matches the characters tab, linefeed, vertical tab, + form feed, or carriage return, and any other character that has the Z + (separator) property. Xsp is the same as Xps; it used to exclude ver- + tical tab, for Perl compatibility, but Perl changed, and so PCRE fol- + lowed at release 8.34. Xwd matches the same characters as Xan, plus + underscore. + + There is another non-standard property, Xuc, which matches any charac- + ter that can be represented by a Universal Character Name in C++ and + other programming languages. These are the characters $, @, ` (grave + accent), and all characters with Unicode code points greater than or + equal to U+00A0, except for the surrogates U+D800 to U+DFFF. Note that + most base (ASCII) characters are excluded. (Universal Character Names + are of the form \uHHHH or \UHHHHHHHH where H is a hexadecimal digit. + Note that the Xuc property does not match these sequences but the char- + acters that they represent.) + + Resetting the match start + + The escape sequence \K causes any previously matched characters not to + be included in the final matched sequence. For example, the pattern: + + foo\Kbar + + matches "foobar", but reports that it has matched "bar". This feature + is similar to a lookbehind assertion (described below). However, in + this case, the part of the subject before the real match does not have + to be of fixed length, as lookbehind assertions do. The use of \K does + not interfere with the setting of captured substrings. For example, + when the pattern + + (foo)\Kbar + + matches "foobar", the first substring is still set to "foo". + + Perl documents that the use of \K within assertions is "not well + defined". In PCRE, \K is acted upon when it occurs inside positive + assertions, but is ignored in negative assertions. Note that when a + pattern such as (?=ab\K) matches, the reported start of the match can + be greater than the end of the match. + + Simple assertions + + The final use of backslash is for certain simple assertions. An asser- + tion specifies a condition that has to be met at a particular point in + a match, without consuming any characters from the subject string. The + use of subpatterns for more complicated assertions is described below. + The backslashed assertions are: + + \b matches at a word boundary + \B matches when not at a word boundary + \A matches at the start of the subject + \Z matches at the end of the subject + also matches before a newline at the end of the subject + \z matches only at the end of the subject + \G matches at the first matching position in the subject + + Inside a character class, \b has a different meaning; it matches the + backspace character. If any other of these assertions appears in a + character class, by default it matches the corresponding literal char- + acter (for example, \B matches the letter B). However, if the + PCRE_EXTRA option is set, an "invalid escape sequence" error is gener- + ated instead. + + A word boundary is a position in the subject string where the current + character and the previous character do not both match \w or \W (i.e. + one matches \w and the other matches \W), or the start or end of the + string if the first or last character matches \w, respectively. In a + UTF mode, the meanings of \w and \W can be changed by setting the + PCRE_UCP option. When this is done, it also affects \b and \B. Neither + PCRE nor Perl has a separate "start of word" or "end of word" metase- + quence. However, whatever follows \b normally determines which it is. + For example, the fragment \ba matches "a" at the start of a word. + + The \A, \Z, and \z assertions differ from the traditional circumflex + and dollar (described in the next section) in that they only ever match + at the very start and end of the subject string, whatever options are + set. Thus, they are independent of multiline mode. These three asser- + tions are not affected by the PCRE_NOTBOL or PCRE_NOTEOL options, which + affect only the behaviour of the circumflex and dollar metacharacters. + However, if the startoffset argument of pcre_exec() is non-zero, indi- + cating that matching is to start at a point other than the beginning of + the subject, \A can never match. The difference between \Z and \z is + that \Z matches before a newline at the end of the string as well as at + the very end, whereas \z matches only at the end. + + The \G assertion is true only when the current matching position is at + the start point of the match, as specified by the startoffset argument + of pcre_exec(). It differs from \A when the value of startoffset is + non-zero. By calling pcre_exec() multiple times with appropriate argu- + ments, you can mimic Perl's /g option, and it is in this kind of imple- + mentation where \G can be useful. + + Note, however, that PCRE's interpretation of \G, as the start of the + current match, is subtly different from Perl's, which defines it as the + end of the previous match. In Perl, these can be different when the + previously matched string was empty. Because PCRE does just one match + at a time, it cannot reproduce this behaviour. + + If all the alternatives of a pattern begin with \G, the expression is + anchored to the starting match position, and the "anchored" flag is set + in the compiled regular expression. + + +CIRCUMFLEX AND DOLLAR + + The circumflex and dollar metacharacters are zero-width assertions. + That is, they test for a particular condition being true without con- + suming any characters from the subject string. + + Outside a character class, in the default matching mode, the circumflex + character is an assertion that is true only if the current matching + point is at the start of the subject string. If the startoffset argu- + ment of pcre_exec() is non-zero, circumflex can never match if the + PCRE_MULTILINE option is unset. Inside a character class, circumflex + has an entirely different meaning (see below). + + Circumflex need not be the first character of the pattern if a number + of alternatives are involved, but it should be the first thing in each + alternative in which it appears if the pattern is ever to match that + branch. If all possible alternatives start with a circumflex, that is, + if the pattern is constrained to match only at the start of the sub- + ject, it is said to be an "anchored" pattern. (There are also other + constructs that can cause a pattern to be anchored.) + + The dollar character is an assertion that is true only if the current + matching point is at the end of the subject string, or immediately + before a newline at the end of the string (by default). Note, however, + that it does not actually match the newline. Dollar need not be the + last character of the pattern if a number of alternatives are involved, + but it should be the last item in any branch in which it appears. Dol- + lar has no special meaning in a character class. + + The meaning of dollar can be changed so that it matches only at the + very end of the string, by setting the PCRE_DOLLAR_ENDONLY option at + compile time. This does not affect the \Z assertion. + + The meanings of the circumflex and dollar characters are changed if the + PCRE_MULTILINE option is set. When this is the case, a circumflex + matches immediately after internal newlines as well as at the start of + the subject string. It does not match after a newline that ends the + string. A dollar matches before any newlines in the string, as well as + at the very end, when PCRE_MULTILINE is set. When newline is specified + as the two-character sequence CRLF, isolated CR and LF characters do + not indicate newlines. + + For example, the pattern /^abc$/ matches the subject string "def\nabc" + (where \n represents a newline) in multiline mode, but not otherwise. + Consequently, patterns that are anchored in single line mode because + all branches start with ^ are not anchored in multiline mode, and a + match for circumflex is possible when the startoffset argument of + pcre_exec() is non-zero. The PCRE_DOLLAR_ENDONLY option is ignored if + PCRE_MULTILINE is set. + + Note that the sequences \A, \Z, and \z can be used to match the start + and end of the subject in both modes, and if all branches of a pattern + start with \A it is always anchored, whether or not PCRE_MULTILINE is + set. + + +FULL STOP (PERIOD, DOT) AND \N + + Outside a character class, a dot in the pattern matches any one charac- + ter in the subject string except (by default) a character that signi- + fies the end of a line. + + When a line ending is defined as a single character, dot never matches + that character; when the two-character sequence CRLF is used, dot does + not match CR if it is immediately followed by LF, but otherwise it + matches all characters (including isolated CRs and LFs). When any Uni- + code line endings are being recognized, dot does not match CR or LF or + any of the other line ending characters. + + The behaviour of dot with regard to newlines can be changed. If the + PCRE_DOTALL option is set, a dot matches any one character, without + exception. If the two-character sequence CRLF is present in the subject + string, it takes two dots to match it. + + The handling of dot is entirely independent of the handling of circum- + flex and dollar, the only relationship being that they both involve + newlines. Dot has no special meaning in a character class. + + The escape sequence \N behaves like a dot, except that it is not + affected by the PCRE_DOTALL option. In other words, it matches any + character except one that signifies the end of a line. Perl also uses + \N to match characters by name; PCRE does not support this. + + +MATCHING A SINGLE DATA UNIT + + Outside a character class, the escape sequence \C matches any one data + unit, whether or not a UTF mode is set. In the 8-bit library, one data + unit is one byte; in the 16-bit library it is a 16-bit unit; in the + 32-bit library it is a 32-bit unit. Unlike a dot, \C always matches + line-ending characters. The feature is provided in Perl in order to + match individual bytes in UTF-8 mode, but it is unclear how it can use- + fully be used. Because \C breaks up characters into individual data + units, matching one unit with \C in a UTF mode means that the rest of + the string may start with a malformed UTF character. This has undefined + results, because PCRE assumes that it is dealing with valid UTF strings + (and by default it checks this at the start of processing unless the + PCRE_NO_UTF8_CHECK, PCRE_NO_UTF16_CHECK or PCRE_NO_UTF32_CHECK option + is used). + + PCRE does not allow \C to appear in lookbehind assertions (described + below) in a UTF mode, because this would make it impossible to calcu- + late the length of the lookbehind. + + In general, the \C escape sequence is best avoided. However, one way of + using it that avoids the problem of malformed UTF characters is to use + a lookahead to check the length of the next character, as in this pat- + tern, which could be used with a UTF-8 string (ignore white space and + line breaks): + + (?| (?=[\x00-\x7f])(\C) | + (?=[\x80-\x{7ff}])(\C)(\C) | + (?=[\x{800}-\x{ffff}])(\C)(\C)(\C) | + (?=[\x{10000}-\x{1fffff}])(\C)(\C)(\C)(\C)) + + A group that starts with (?| resets the capturing parentheses numbers + in each alternative (see "Duplicate Subpattern Numbers" below). The + assertions at the start of each branch check the next UTF-8 character + for values whose encoding uses 1, 2, 3, or 4 bytes, respectively. The + character's individual bytes are then captured by the appropriate num- + ber of groups. + + +SQUARE BRACKETS AND CHARACTER CLASSES + + An opening square bracket introduces a character class, terminated by a + closing square bracket. A closing square bracket on its own is not spe- + cial by default. However, if the PCRE_JAVASCRIPT_COMPAT option is set, + a lone closing square bracket causes a compile-time error. If a closing + square bracket is required as a member of the class, it should be the + first data character in the class (after an initial circumflex, if + present) or escaped with a backslash. + + A character class matches a single character in the subject. In a UTF + mode, the character may be more than one data unit long. A matched + character must be in the set of characters defined by the class, unless + the first character in the class definition is a circumflex, in which + case the subject character must not be in the set defined by the class. + If a circumflex is actually required as a member of the class, ensure + it is not the first character, or escape it with a backslash. + + For example, the character class [aeiou] matches any lower case vowel, + while [^aeiou] matches any character that is not a lower case vowel. + Note that a circumflex is just a convenient notation for specifying the + characters that are in the class by enumerating those that are not. A + class that starts with a circumflex is not an assertion; it still con- + sumes a character from the subject string, and therefore it fails if + the current pointer is at the end of the string. + + In UTF-8 (UTF-16, UTF-32) mode, characters with values greater than 255 + (0xffff) can be included in a class as a literal string of data units, + or by using the \x{ escaping mechanism. + + When caseless matching is set, any letters in a class represent both + their upper case and lower case versions, so for example, a caseless + [aeiou] matches "A" as well as "a", and a caseless [^aeiou] does not + match "A", whereas a caseful version would. In a UTF mode, PCRE always + understands the concept of case for characters whose values are less + than 128, so caseless matching is always possible. For characters with + higher values, the concept of case is supported if PCRE is compiled + with Unicode property support, but not otherwise. If you want to use + caseless matching in a UTF mode for characters 128 and above, you must + ensure that PCRE is compiled with Unicode property support as well as + with UTF support. + + Characters that might indicate line breaks are never treated in any + special way when matching character classes, whatever line-ending + sequence is in use, and whatever setting of the PCRE_DOTALL and + PCRE_MULTILINE options is used. A class such as [^a] always matches one + of these characters. + + The minus (hyphen) character can be used to specify a range of charac- + ters in a character class. For example, [d-m] matches any letter + between d and m, inclusive. If a minus character is required in a + class, it must be escaped with a backslash or appear in a position + where it cannot be interpreted as indicating a range, typically as the + first or last character in the class, or immediately after a range. For + example, [b-d-z] matches letters in the range b to d, a hyphen charac- + ter, or z. + + It is not possible to have the literal character "]" as the end charac- + ter of a range. A pattern such as [W-]46] is interpreted as a class of + two characters ("W" and "-") followed by a literal string "46]", so it + would match "W46]" or "-46]". However, if the "]" is escaped with a + backslash it is interpreted as the end of range, so [W-\]46] is inter- + preted as a class containing a range followed by two other characters. + The octal or hexadecimal representation of "]" can also be used to end + a range. + + An error is generated if a POSIX character class (see below) or an + escape sequence other than one that defines a single character appears + at a point where a range ending character is expected. For example, + [z-\xff] is valid, but [A-\d] and [A-[:digit:]] are not. + + Ranges operate in the collating sequence of character values. They can + also be used for characters specified numerically, for example + [\000-\037]. Ranges can include any characters that are valid for the + current mode. + + If a range that includes letters is used when caseless matching is set, + it matches the letters in either case. For example, [W-c] is equivalent + to [][\\^_`wxyzabc], matched caselessly, and in a non-UTF mode, if + character tables for a French locale are in use, [\xc8-\xcb] matches + accented E characters in both cases. In UTF modes, PCRE supports the + concept of case for characters with values greater than 128 only when + it is compiled with Unicode property support. + + The character escape sequences \d, \D, \h, \H, \p, \P, \s, \S, \v, \V, + \w, and \W may appear in a character class, and add the characters that + they match to the class. For example, [\dABCDEF] matches any hexadeci- + mal digit. In UTF modes, the PCRE_UCP option affects the meanings of + \d, \s, \w and their upper case partners, just as it does when they + appear outside a character class, as described in the section entitled + "Generic character types" above. The escape sequence \b has a different + meaning inside a character class; it matches the backspace character. + The sequences \B, \N, \R, and \X are not special inside a character + class. Like any other unrecognized escape sequences, they are treated + as the literal characters "B", "N", "R", and "X" by default, but cause + an error if the PCRE_EXTRA option is set. + + A circumflex can conveniently be used with the upper case character + types to specify a more restricted set of characters than the matching + lower case type. For example, the class [^\W_] matches any letter or + digit, but not underscore, whereas [\w] includes underscore. A positive + character class should be read as "something OR something OR ..." and a + negative class as "NOT something AND NOT something AND NOT ...". + + The only metacharacters that are recognized in character classes are + backslash, hyphen (only where it can be interpreted as specifying a + range), circumflex (only at the start), opening square bracket (only + when it can be interpreted as introducing a POSIX class name, or for a + special compatibility feature - see the next two sections), and the + terminating closing square bracket. However, escaping other non- + alphanumeric characters does no harm. + + +POSIX CHARACTER CLASSES + + Perl supports the POSIX notation for character classes. This uses names + enclosed by [: and :] within the enclosing square brackets. PCRE also + supports this notation. For example, + + [01[:alpha:]%] + + matches "0", "1", any alphabetic character, or "%". The supported class + names are: + + alnum letters and digits + alpha letters + ascii character codes 0 - 127 + blank space or tab only + cntrl control characters + digit decimal digits (same as \d) + graph printing characters, excluding space + lower lower case letters + print printing characters, including space + punct printing characters, excluding letters and digits and space + space white space (the same as \s from PCRE 8.34) + upper upper case letters + word "word" characters (same as \w) + xdigit hexadecimal digits + + The default "space" characters are HT (9), LF (10), VT (11), FF (12), + CR (13), and space (32). If locale-specific matching is taking place, + the list of space characters may be different; there may be fewer or + more of them. "Space" used to be different to \s, which did not include + VT, for Perl compatibility. However, Perl changed at release 5.18, and + PCRE followed at release 8.34. "Space" and \s now match the same set + of characters. + + The name "word" is a Perl extension, and "blank" is a GNU extension + from Perl 5.8. Another Perl extension is negation, which is indicated + by a ^ character after the colon. For example, + + [12[:^digit:]] + + matches "1", "2", or any non-digit. PCRE (and Perl) also recognize the + POSIX syntax [.ch.] and [=ch=] where "ch" is a "collating element", but + these are not supported, and an error is given if they are encountered. + + By default, characters with values greater than 128 do not match any of + the POSIX character classes. However, if the PCRE_UCP option is passed + to pcre_compile(), some of the classes are changed so that Unicode + character properties are used. This is achieved by replacing certain + POSIX classes by other sequences, as follows: + + [:alnum:] becomes \p{Xan} + [:alpha:] becomes \p{L} + [:blank:] becomes \h + [:digit:] becomes \p{Nd} + [:lower:] becomes \p{Ll} + [:space:] becomes \p{Xps} + [:upper:] becomes \p{Lu} + [:word:] becomes \p{Xwd} + + Negated versions, such as [:^alpha:] use \P instead of \p. Three other + POSIX classes are handled specially in UCP mode: + + [:graph:] This matches characters that have glyphs that mark the page + when printed. In Unicode property terms, it matches all char- + acters with the L, M, N, P, S, or Cf properties, except for: + + U+061C Arabic Letter Mark + U+180E Mongolian Vowel Separator + U+2066 - U+2069 Various "isolate"s + + + [:print:] This matches the same characters as [:graph:] plus space + characters that are not controls, that is, characters with + the Zs property. + + [:punct:] This matches all characters that have the Unicode P (punctua- + tion) property, plus those characters whose code points are + less than 128 that have the S (Symbol) property. + + The other POSIX classes are unchanged, and match only characters with + code points less than 128. + + +COMPATIBILITY FEATURE FOR WORD BOUNDARIES + + In the POSIX.2 compliant library that was included in 4.4BSD Unix, the + ugly syntax [[:<:]] and [[:>:]] is used for matching "start of word" + and "end of word". PCRE treats these items as follows: + + [[:<:]] is converted to \b(?=\w) + [[:>:]] is converted to \b(?<=\w) + + Only these exact character sequences are recognized. A sequence such as + [a[:<:]b] provokes error for an unrecognized POSIX class name. This + support is not compatible with Perl. It is provided to help migrations + from other environments, and is best not used in any new patterns. Note + that \b matches at the start and the end of a word (see "Simple asser- + tions" above), and in a Perl-style pattern the preceding or following + character normally shows which is wanted, without the need for the + assertions that are used above in order to give exactly the POSIX be- + haviour. + + +VERTICAL BAR + + Vertical bar characters are used to separate alternative patterns. For + example, the pattern + + gilbert|sullivan + + matches either "gilbert" or "sullivan". Any number of alternatives may + appear, and an empty alternative is permitted (matching the empty + string). The matching process tries each alternative in turn, from left + to right, and the first one that succeeds is used. If the alternatives + are within a subpattern (defined below), "succeeds" means matching the + rest of the main pattern as well as the alternative in the subpattern. + + +INTERNAL OPTION SETTING + + The settings of the PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and + PCRE_EXTENDED options (which are Perl-compatible) can be changed from + within the pattern by a sequence of Perl option letters enclosed + between "(?" and ")". The option letters are + + i for PCRE_CASELESS + m for PCRE_MULTILINE + s for PCRE_DOTALL + x for PCRE_EXTENDED + + For example, (?im) sets caseless, multiline matching. It is also possi- + ble to unset these options by preceding the letter with a hyphen, and a + combined setting and unsetting such as (?im-sx), which sets PCRE_CASE- + LESS and PCRE_MULTILINE while unsetting PCRE_DOTALL and PCRE_EXTENDED, + is also permitted. If a letter appears both before and after the + hyphen, the option is unset. + + The PCRE-specific options PCRE_DUPNAMES, PCRE_UNGREEDY, and PCRE_EXTRA + can be changed in the same way as the Perl-compatible options by using + the characters J, U and X respectively. + + When one of these option changes occurs at top level (that is, not + inside subpattern parentheses), the change applies to the remainder of + the pattern that follows. If the change is placed right at the start of + a pattern, PCRE extracts it into the global options (and it will there- + fore show up in data extracted by the pcre_fullinfo() function). + + An option change within a subpattern (see below for a description of + subpatterns) affects only that part of the subpattern that follows it, + so + + (a(?i)b)c + + matches abc and aBc and no other strings (assuming PCRE_CASELESS is not + used). By this means, options can be made to have different settings + in different parts of the pattern. Any changes made in one alternative + do carry on into subsequent branches within the same subpattern. For + example, + + (a(?i)b|c) + + matches "ab", "aB", "c", and "C", even though when matching "C" the + first branch is abandoned before the option setting. This is because + the effects of option settings happen at compile time. There would be + some very weird behaviour otherwise. + + Note: There are other PCRE-specific options that can be set by the + application when the compiling or matching functions are called. In + some cases the pattern can contain special leading sequences such as + (*CRLF) to override what the application has set or what has been + defaulted. Details are given in the section entitled "Newline + sequences" above. There are also the (*UTF8), (*UTF16),(*UTF32), and + (*UCP) leading sequences that can be used to set UTF and Unicode prop- + erty modes; they are equivalent to setting the PCRE_UTF8, PCRE_UTF16, + PCRE_UTF32 and the PCRE_UCP options, respectively. The (*UTF) sequence + is a generic version that can be used with any of the libraries. How- + ever, the application can set the PCRE_NEVER_UTF option, which locks + out the use of the (*UTF) sequences. + + +SUBPATTERNS + + Subpatterns are delimited by parentheses (round brackets), which can be + nested. Turning part of a pattern into a subpattern does two things: + + 1. It localizes a set of alternatives. For example, the pattern + + cat(aract|erpillar|) + + matches "cataract", "caterpillar", or "cat". Without the parentheses, + it would match "cataract", "erpillar" or an empty string. + + 2. It sets up the subpattern as a capturing subpattern. This means + that, when the whole pattern matches, that portion of the subject + string that matched the subpattern is passed back to the caller via the + ovector argument of the matching function. (This applies only to the + traditional matching functions; the DFA matching functions do not sup- + port capturing.) + + Opening parentheses are counted from left to right (starting from 1) to + obtain numbers for the capturing subpatterns. For example, if the + string "the red king" is matched against the pattern + + the ((red|white) (king|queen)) + + the captured substrings are "red king", "red", and "king", and are num- + bered 1, 2, and 3, respectively. + + The fact that plain parentheses fulfil two functions is not always + helpful. There are often times when a grouping subpattern is required + without a capturing requirement. If an opening parenthesis is followed + by a question mark and a colon, the subpattern does not do any captur- + ing, and is not counted when computing the number of any subsequent + capturing subpatterns. For example, if the string "the white queen" is + matched against the pattern + + the ((?:red|white) (king|queen)) + + the captured substrings are "white queen" and "queen", and are numbered + 1 and 2. The maximum number of capturing subpatterns is 65535. + + As a convenient shorthand, if any option settings are required at the + start of a non-capturing subpattern, the option letters may appear + between the "?" and the ":". Thus the two patterns + + (?i:saturday|sunday) + (?:(?i)saturday|sunday) + + match exactly the same set of strings. Because alternative branches are + tried from left to right, and options are not reset until the end of + the subpattern is reached, an option setting in one branch does affect + subsequent branches, so the above patterns match "SUNDAY" as well as + "Saturday". + + +DUPLICATE SUBPATTERN NUMBERS + + Perl 5.10 introduced a feature whereby each alternative in a subpattern + uses the same numbers for its capturing parentheses. Such a subpattern + starts with (?| and is itself a non-capturing subpattern. For example, + consider this pattern: + + (?|(Sat)ur|(Sun))day + + Because the two alternatives are inside a (?| group, both sets of cap- + turing parentheses are numbered one. Thus, when the pattern matches, + you can look at captured substring number one, whichever alternative + matched. This construct is useful when you want to capture part, but + not all, of one of a number of alternatives. Inside a (?| group, paren- + theses are numbered as usual, but the number is reset at the start of + each branch. The numbers of any capturing parentheses that follow the + subpattern start after the highest number used in any branch. The fol- + lowing example is taken from the Perl documentation. The numbers under- + neath show in which buffer the captured content will be stored. + + # before ---------------branch-reset----------- after + / ( a ) (?| x ( y ) z | (p (q) r) | (t) u (v) ) ( z ) /x + # 1 2 2 3 2 3 4 + + A back reference to a numbered subpattern uses the most recent value + that is set for that number by any subpattern. The following pattern + matches "abcabc" or "defdef": + + /(?|(abc)|(def))\1/ + + In contrast, a subroutine call to a numbered subpattern always refers + to the first one in the pattern with the given number. The following + pattern matches "abcabc" or "defabc": + + /(?|(abc)|(def))(?1)/ + + If a condition test for a subpattern's having matched refers to a non- + unique number, the test is true if any of the subpatterns of that num- + ber have matched. + + An alternative approach to using this "branch reset" feature is to use + duplicate named subpatterns, as described in the next section. + + +NAMED SUBPATTERNS + + Identifying capturing parentheses by number is simple, but it can be + very hard to keep track of the numbers in complicated regular expres- + sions. Furthermore, if an expression is modified, the numbers may + change. To help with this difficulty, PCRE supports the naming of sub- + patterns. This feature was not added to Perl until release 5.10. Python + had the feature earlier, and PCRE introduced it at release 4.0, using + the Python syntax. PCRE now supports both the Perl and the Python syn- + tax. Perl allows identically numbered subpatterns to have different + names, but PCRE does not. + + In PCRE, a subpattern can be named in one of three ways: (?<name>...) + or (?'name'...) as in Perl, or (?P<name>...) as in Python. References + to capturing parentheses from other parts of the pattern, such as back + references, recursion, and conditions, can be made by name as well as + by number. + + Names consist of up to 32 alphanumeric characters and underscores, but + must start with a non-digit. Named capturing parentheses are still + allocated numbers as well as names, exactly as if the names were not + present. The PCRE API provides function calls for extracting the name- + to-number translation table from a compiled pattern. There is also a + convenience function for extracting a captured substring by name. + + By default, a name must be unique within a pattern, but it is possible + to relax this constraint by setting the PCRE_DUPNAMES option at compile + time. (Duplicate names are also always permitted for subpatterns with + the same number, set up as described in the previous section.) Dupli- + cate names can be useful for patterns where only one instance of the + named parentheses can match. Suppose you want to match the name of a + weekday, either as a 3-letter abbreviation or as the full name, and in + both cases you want to extract the abbreviation. This pattern (ignoring + the line breaks) does the job: + + (?<DN>Mon|Fri|Sun)(?:day)?| + (?<DN>Tue)(?:sday)?| + (?<DN>Wed)(?:nesday)?| + (?<DN>Thu)(?:rsday)?| + (?<DN>Sat)(?:urday)? + + There are five capturing substrings, but only one is ever set after a + match. (An alternative way of solving this problem is to use a "branch + reset" subpattern, as described in the previous section.) + + The convenience function for extracting the data by name returns the + substring for the first (and in this example, the only) subpattern of + that name that matched. This saves searching to find which numbered + subpattern it was. + + If you make a back reference to a non-unique named subpattern from + elsewhere in the pattern, the subpatterns to which the name refers are + checked in the order in which they appear in the overall pattern. The + first one that is set is used for the reference. For example, this pat- + tern matches both "foofoo" and "barbar" but not "foobar" or "barfoo": + + (?:(?<n>foo)|(?<n>bar))\k<n> + + + If you make a subroutine call to a non-unique named subpattern, the one + that corresponds to the first occurrence of the name is used. In the + absence of duplicate numbers (see the previous section) this is the one + with the lowest number. + + If you use a named reference in a condition test (see the section about + conditions below), either to check whether a subpattern has matched, or + to check for recursion, all subpatterns with the same name are tested. + If the condition is true for any one of them, the overall condition is + true. This is the same behaviour as testing by number. For further + details of the interfaces for handling named subpatterns, see the + pcreapi documentation. + + Warning: You cannot use different names to distinguish between two sub- + patterns with the same number because PCRE uses only the numbers when + matching. For this reason, an error is given at compile time if differ- + ent names are given to subpatterns with the same number. However, you + can always give the same name to subpatterns with the same number, even + when PCRE_DUPNAMES is not set. + + +REPETITION + + Repetition is specified by quantifiers, which can follow any of the + following items: + + a literal data character + the dot metacharacter + the \C escape sequence + the \X escape sequence + the \R escape sequence + an escape such as \d or \pL that matches a single character + a character class + a back reference (see next section) + a parenthesized subpattern (including assertions) + a subroutine call to a subpattern (recursive or otherwise) + + The general repetition quantifier specifies a minimum and maximum num- + ber of permitted matches, by giving the two numbers in curly brackets + (braces), separated by a comma. The numbers must be less than 65536, + and the first must be less than or equal to the second. For example: + + z{2,4} + + matches "zz", "zzz", or "zzzz". A closing brace on its own is not a + special character. If the second number is omitted, but the comma is + present, there is no upper limit; if the second number and the comma + are both omitted, the quantifier specifies an exact number of required + matches. Thus + + [aeiou]{3,} + + matches at least 3 successive vowels, but may match many more, while + + \d{8} + + matches exactly 8 digits. An opening curly bracket that appears in a + position where a quantifier is not allowed, or one that does not match + the syntax of a quantifier, is taken as a literal character. For exam- + ple, {,6} is not a quantifier, but a literal string of four characters. + + In UTF modes, quantifiers apply to characters rather than to individual + data units. Thus, for example, \x{100}{2} matches two characters, each + of which is represented by a two-byte sequence in a UTF-8 string. Simi- + larly, \X{3} matches three Unicode extended grapheme clusters, each of + which may be several data units long (and they may be of different + lengths). + + The quantifier {0} is permitted, causing the expression to behave as if + the previous item and the quantifier were not present. This may be use- + ful for subpatterns that are referenced as subroutines from elsewhere + in the pattern (but see also the section entitled "Defining subpatterns + for use by reference only" below). Items other than subpatterns that + have a {0} quantifier are omitted from the compiled pattern. + + For convenience, the three most common quantifiers have single-charac- + ter abbreviations: + + * is equivalent to {0,} + + is equivalent to {1,} + ? is equivalent to {0,1} + + It is possible to construct infinite loops by following a subpattern + that can match no characters with a quantifier that has no upper limit, + for example: + + (a?)* + + Earlier versions of Perl and PCRE used to give an error at compile time + for such patterns. However, because there are cases where this can be + useful, such patterns are now accepted, but if any repetition of the + subpattern does in fact match no characters, the loop is forcibly bro- + ken. + + By default, the quantifiers are "greedy", that is, they match as much + as possible (up to the maximum number of permitted times), without + causing the rest of the pattern to fail. The classic example of where + this gives problems is in trying to match comments in C programs. These + appear between /* and */ and within the comment, individual * and / + characters may appear. An attempt to match C comments by applying the + pattern + + /\*.*\*/ + + to the string + + /* first comment */ not comment /* second comment */ + + fails, because it matches the entire string owing to the greediness of + the .* item. + + However, if a quantifier is followed by a question mark, it ceases to + be greedy, and instead matches the minimum number of times possible, so + the pattern + + /\*.*?\*/ + + does the right thing with the C comments. The meaning of the various + quantifiers is not otherwise changed, just the preferred number of + matches. Do not confuse this use of question mark with its use as a + quantifier in its own right. Because it has two uses, it can sometimes + appear doubled, as in + + \d??\d + + which matches one digit by preference, but can match two if that is the + only way the rest of the pattern matches. + + If the PCRE_UNGREEDY option is set (an option that is not available in + Perl), the quantifiers are not greedy by default, but individual ones + can be made greedy by following them with a question mark. In other + words, it inverts the default behaviour. + + When a parenthesized subpattern is quantified with a minimum repeat + count that is greater than 1 or with a limited maximum, more memory is + required for the compiled pattern, in proportion to the size of the + minimum or maximum. + + If a pattern starts with .* or .{0,} and the PCRE_DOTALL option (equiv- + alent to Perl's /s) is set, thus allowing the dot to match newlines, + the pattern is implicitly anchored, because whatever follows will be + tried against every character position in the subject string, so there + is no point in retrying the overall match at any position after the + first. PCRE normally treats such a pattern as though it were preceded + by \A. + + In cases where it is known that the subject string contains no new- + lines, it is worth setting PCRE_DOTALL in order to obtain this opti- + mization, or alternatively using ^ to indicate anchoring explicitly. + + However, there are some cases where the optimization cannot be used. + When .* is inside capturing parentheses that are the subject of a back + reference elsewhere in the pattern, a match at the start may fail where + a later one succeeds. Consider, for example: + + (.*)abc\1 + + If the subject is "xyz123abc123" the match point is the fourth charac- + ter. For this reason, such a pattern is not implicitly anchored. + + Another case where implicit anchoring is not applied is when the lead- + ing .* is inside an atomic group. Once again, a match at the start may + fail where a later one succeeds. Consider this pattern: + + (?>.*?a)b + + It matches "ab" in the subject "aab". The use of the backtracking con- + trol verbs (*PRUNE) and (*SKIP) also disable this optimization. + + When a capturing subpattern is repeated, the value captured is the sub- + string that matched the final iteration. For example, after + + (tweedle[dume]{3}\s*)+ + + has matched "tweedledum tweedledee" the value of the captured substring + is "tweedledee". However, if there are nested capturing subpatterns, + the corresponding captured values may have been set in previous itera- + tions. For example, after + + /(a|(b))+/ + + matches "aba" the value of the second captured substring is "b". + + +ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS + + With both maximizing ("greedy") and minimizing ("ungreedy" or "lazy") + repetition, failure of what follows normally causes the repeated item + to be re-evaluated to see if a different number of repeats allows the + rest of the pattern to match. Sometimes it is useful to prevent this, + either to change the nature of the match, or to cause it fail earlier + than it otherwise might, when the author of the pattern knows there is + no point in carrying on. + + Consider, for example, the pattern \d+foo when applied to the subject + line + + 123456bar + + After matching all 6 digits and then failing to match "foo", the normal + action of the matcher is to try again with only 5 digits matching the + \d+ item, and then with 4, and so on, before ultimately failing. + "Atomic grouping" (a term taken from Jeffrey Friedl's book) provides + the means for specifying that once a subpattern has matched, it is not + to be re-evaluated in this way. + + If we use atomic grouping for the previous example, the matcher gives + up immediately on failing to match "foo" the first time. The notation + is a kind of special parenthesis, starting with (?> as in this example: + + (?>\d+)foo + + This kind of parenthesis "locks up" the part of the pattern it con- + tains once it has matched, and a failure further into the pattern is + prevented from backtracking into it. Backtracking past it to previous + items, however, works as normal. + + An alternative description is that a subpattern of this type matches + the string of characters that an identical standalone pattern would + match, if anchored at the current point in the subject string. + + Atomic grouping subpatterns are not capturing subpatterns. Simple cases + such as the above example can be thought of as a maximizing repeat that + must swallow everything it can. So, while both \d+ and \d+? are pre- + pared to adjust the number of digits they match in order to make the + rest of the pattern match, (?>\d+) can only match an entire sequence of + digits. + + Atomic groups in general can of course contain arbitrarily complicated + subpatterns, and can be nested. However, when the subpattern for an + atomic group is just a single repeated item, as in the example above, a + simpler notation, called a "possessive quantifier" can be used. This + consists of an additional + character following a quantifier. Using + this notation, the previous example can be rewritten as + + \d++foo + + Note that a possessive quantifier can be used with an entire group, for + example: + + (abc|xyz){2,3}+ + + Possessive quantifiers are always greedy; the setting of the + PCRE_UNGREEDY option is ignored. They are a convenient notation for the + simpler forms of atomic group. However, there is no difference in the + meaning of a possessive quantifier and the equivalent atomic group, + though there may be a performance difference; possessive quantifiers + should be slightly faster. + + The possessive quantifier syntax is an extension to the Perl 5.8 syn- + tax. Jeffrey Friedl originated the idea (and the name) in the first + edition of his book. Mike McCloskey liked it, so implemented it when he + built Sun's Java package, and PCRE copied it from there. It ultimately + found its way into Perl at release 5.10. + + PCRE has an optimization that automatically "possessifies" certain sim- + ple pattern constructs. For example, the sequence A+B is treated as + A++B because there is no point in backtracking into a sequence of A's + when B must follow. + + When a pattern contains an unlimited repeat inside a subpattern that + can itself be repeated an unlimited number of times, the use of an + atomic group is the only way to avoid some failing matches taking a + very long time indeed. The pattern + + (\D+|<\d+>)*[!?] + + matches an unlimited number of substrings that either consist of non- + digits, or digits enclosed in <>, followed by either ! or ?. When it + matches, it runs quickly. However, if it is applied to + + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + + it takes a long time before reporting failure. This is because the + string can be divided between the internal \D+ repeat and the external + * repeat in a large number of ways, and all have to be tried. (The + example uses [!?] rather than a single character at the end, because + both PCRE and Perl have an optimization that allows for fast failure + when a single character is used. They remember the last single charac- + ter that is required for a match, and fail early if it is not present + in the string.) If the pattern is changed so that it uses an atomic + group, like this: + + ((?>\D+)|<\d+>)*[!?] + + sequences of non-digits cannot be broken, and failure happens quickly. + + +BACK REFERENCES + + Outside a character class, a backslash followed by a digit greater than + 0 (and possibly further digits) is a back reference to a capturing sub- + pattern earlier (that is, to its left) in the pattern, provided there + have been that many previous capturing left parentheses. + + However, if the decimal number following the backslash is less than 10, + it is always taken as a back reference, and causes an error only if + there are not that many capturing left parentheses in the entire pat- + tern. In other words, the parentheses that are referenced need not be + to the left of the reference for numbers less than 10. A "forward back + reference" of this type can make sense when a repetition is involved + and the subpattern to the right has participated in an earlier itera- + tion. + + It is not possible to have a numerical "forward back reference" to a + subpattern whose number is 10 or more using this syntax because a + sequence such as \50 is interpreted as a character defined in octal. + See the subsection entitled "Non-printing characters" above for further + details of the handling of digits following a backslash. There is no + such problem when named parentheses are used. A back reference to any + subpattern is possible using named parentheses (see below). + + Another way of avoiding the ambiguity inherent in the use of digits + following a backslash is to use the \g escape sequence. This escape + must be followed by an unsigned number or a negative number, optionally + enclosed in braces. These examples are all identical: + + (ring), \1 + (ring), \g1 + (ring), \g{1} + + An unsigned number specifies an absolute reference without the ambigu- + ity that is present in the older syntax. It is also useful when literal + digits follow the reference. A negative number is a relative reference. + Consider this example: + + (abc(def)ghi)\g{-1} + + The sequence \g{-1} is a reference to the most recently started captur- + ing subpattern before \g, that is, is it equivalent to \2 in this exam- + ple. Similarly, \g{-2} would be equivalent to \1. The use of relative + references can be helpful in long patterns, and also in patterns that + are created by joining together fragments that contain references + within themselves. + + A back reference matches whatever actually matched the capturing sub- + pattern in the current subject string, rather than anything matching + the subpattern itself (see "Subpatterns as subroutines" below for a way + of doing that). So the pattern + + (sens|respons)e and \1ibility + + matches "sense and sensibility" and "response and responsibility", but + not "sense and responsibility". If caseful matching is in force at the + time of the back reference, the case of letters is relevant. For exam- + ple, + + ((?i)rah)\s+\1 + + matches "rah rah" and "RAH RAH", but not "RAH rah", even though the + original capturing subpattern is matched caselessly. + + There are several different ways of writing back references to named + subpatterns. The .NET syntax \k{name} and the Perl syntax \k<name> or + \k'name' are supported, as is the Python syntax (?P=name). Perl 5.10's + unified back reference syntax, in which \g can be used for both numeric + and named references, is also supported. We could rewrite the above + example in any of the following ways: + + (?<p1>(?i)rah)\s+\k<p1> + (?'p1'(?i)rah)\s+\k{p1} + (?P<p1>(?i)rah)\s+(?P=p1) + (?<p1>(?i)rah)\s+\g{p1} + + A subpattern that is referenced by name may appear in the pattern + before or after the reference. + + There may be more than one back reference to the same subpattern. If a + subpattern has not actually been used in a particular match, any back + references to it always fail by default. For example, the pattern + + (a|(bc))\2 + + always fails if it starts to match "a" rather than "bc". However, if + the PCRE_JAVASCRIPT_COMPAT option is set at compile time, a back refer- + ence to an unset value matches an empty string. + + Because there may be many capturing parentheses in a pattern, all dig- + its following a backslash are taken as part of a potential back refer- + ence number. If the pattern continues with a digit character, some + delimiter must be used to terminate the back reference. If the + PCRE_EXTENDED option is set, this can be white space. Otherwise, the + \g{ syntax or an empty comment (see "Comments" below) can be used. + + Recursive back references + + A back reference that occurs inside the parentheses to which it refers + fails when the subpattern is first used, so, for example, (a\1) never + matches. However, such references can be useful inside repeated sub- + patterns. For example, the pattern + + (a|b\1)+ + + matches any number of "a"s and also "aba", "ababbaa" etc. At each iter- + ation of the subpattern, the back reference matches the character + string corresponding to the previous iteration. In order for this to + work, the pattern must be such that the first iteration does not need + to match the back reference. This can be done using alternation, as in + the example above, or by a quantifier with a minimum of zero. + + Back references of this type cause the group that they reference to be + treated as an atomic group. Once the whole group has been matched, a + subsequent matching failure cannot cause backtracking into the middle + of the group. + + +ASSERTIONS + + An assertion is a test on the characters following or preceding the + current matching point that does not actually consume any characters. + The simple assertions coded as \b, \B, \A, \G, \Z, \z, ^ and $ are + described above. + + More complicated assertions are coded as subpatterns. There are two + kinds: those that look ahead of the current position in the subject + string, and those that look behind it. An assertion subpattern is + matched in the normal way, except that it does not cause the current + matching position to be changed. + + Assertion subpatterns are not capturing subpatterns. If such an asser- + tion contains capturing subpatterns within it, these are counted for + the purposes of numbering the capturing subpatterns in the whole pat- + tern. However, substring capturing is carried out only for positive + assertions. (Perl sometimes, but not always, does do capturing in nega- + tive assertions.) + + For compatibility with Perl, assertion subpatterns may be repeated; + though it makes no sense to assert the same thing several times, the + side effect of capturing parentheses may occasionally be useful. In + practice, there only three cases: + + (1) If the quantifier is {0}, the assertion is never obeyed during + matching. However, it may contain internal capturing parenthesized + groups that are called from elsewhere via the subroutine mechanism. + + (2) If quantifier is {0,n} where n is greater than zero, it is treated + as if it were {0,1}. At run time, the rest of the pattern match is + tried with and without the assertion, the order depending on the greed- + iness of the quantifier. + + (3) If the minimum repetition is greater than zero, the quantifier is + ignored. The assertion is obeyed just once when encountered during + matching. + + Lookahead assertions + + Lookahead assertions start with (?= for positive assertions and (?! for + negative assertions. For example, + + \w+(?=;) + + matches a word followed by a semicolon, but does not include the semi- + colon in the match, and + + foo(?!bar) + + matches any occurrence of "foo" that is not followed by "bar". Note + that the apparently similar pattern + + (?!foo)bar + + does not find an occurrence of "bar" that is preceded by something + other than "foo"; it finds any occurrence of "bar" whatsoever, because + the assertion (?!foo) is always true when the next three characters are + "bar". A lookbehind assertion is needed to achieve the other effect. + + If you want to force a matching failure at some point in a pattern, the + most convenient way to do it is with (?!) because an empty string + always matches, so an assertion that requires there not to be an empty + string must always fail. The backtracking control verb (*FAIL) or (*F) + is a synonym for (?!). + + Lookbehind assertions + + Lookbehind assertions start with (?<= for positive assertions and (?<! + for negative assertions. For example, + + (?<!foo)bar + + does find an occurrence of "bar" that is not preceded by "foo". The + contents of a lookbehind assertion are restricted such that all the + strings it matches must have a fixed length. However, if there are sev- + eral top-level alternatives, they do not all have to have the same + fixed length. Thus + + (?<=bullock|donkey) + + is permitted, but + + (?<!dogs?|cats?) + + causes an error at compile time. Branches that match different length + strings are permitted only at the top level of a lookbehind assertion. + This is an extension compared with Perl, which requires all branches to + match the same length of string. An assertion such as + + (?<=ab(c|de)) + + is not permitted, because its single top-level branch can match two + different lengths, but it is acceptable to PCRE if rewritten to use two + top-level branches: + + (?<=abc|abde) + + In some cases, the escape sequence \K (see above) can be used instead + of a lookbehind assertion to get round the fixed-length restriction. + + The implementation of lookbehind assertions is, for each alternative, + to temporarily move the current position back by the fixed length and + then try to match. If there are insufficient characters before the cur- + rent position, the assertion fails. + + In a UTF mode, PCRE does not allow the \C escape (which matches a sin- + gle data unit even in a UTF mode) to appear in lookbehind assertions, + because it makes it impossible to calculate the length of the lookbe- + hind. The \X and \R escapes, which can match different numbers of data + units, are also not permitted. + + "Subroutine" calls (see below) such as (?2) or (?&X) are permitted in + lookbehinds, as long as the subpattern matches a fixed-length string. + Recursion, however, is not supported. + + Possessive quantifiers can be used in conjunction with lookbehind + assertions to specify efficient matching of fixed-length strings at the + end of subject strings. Consider a simple pattern such as + + abcd$ + + when applied to a long string that does not match. Because matching + proceeds from left to right, PCRE will look for each "a" in the subject + and then see if what follows matches the rest of the pattern. If the + pattern is specified as + + ^.*abcd$ + + the initial .* matches the entire string at first, but when this fails + (because there is no following "a"), it backtracks to match all but the + last character, then all but the last two characters, and so on. Once + again the search for "a" covers the entire string, from right to left, + so we are no better off. However, if the pattern is written as + + ^.*+(?<=abcd) + + there can be no backtracking for the .*+ item; it can match only the + entire string. The subsequent lookbehind assertion does a single test + on the last four characters. If it fails, the match fails immediately. + For long strings, this approach makes a significant difference to the + processing time. + + Using multiple assertions + + Several assertions (of any sort) may occur in succession. For example, + + (?<=\d{3})(?<!999)foo + + matches "foo" preceded by three digits that are not "999". Notice that + each of the assertions is applied independently at the same point in + the subject string. First there is a check that the previous three + characters are all digits, and then there is a check that the same + three characters are not "999". This pattern does not match "foo" pre- + ceded by six characters, the first of which are digits and the last + three of which are not "999". For example, it doesn't match "123abc- + foo". A pattern to do that is + + (?<=\d{3}...)(?<!999)foo + + This time the first assertion looks at the preceding six characters, + checking that the first three are digits, and then the second assertion + checks that the preceding three characters are not "999". + + Assertions can be nested in any combination. For example, + + (?<=(?<!foo)bar)baz + + matches an occurrence of "baz" that is preceded by "bar" which in turn + is not preceded by "foo", while + + (?<=\d{3}(?!999)...)foo + + is another pattern that matches "foo" preceded by three digits and any + three characters that are not "999". + + +CONDITIONAL SUBPATTERNS + + It is possible to cause the matching process to obey a subpattern con- + ditionally or to choose between two alternative subpatterns, depending + on the result of an assertion, or whether a specific capturing subpat- + tern has already been matched. The two possible forms of conditional + subpattern are: + + (?(condition)yes-pattern) + (?(condition)yes-pattern|no-pattern) + + If the condition is satisfied, the yes-pattern is used; otherwise the + no-pattern (if present) is used. If there are more than two alterna- + tives in the subpattern, a compile-time error occurs. Each of the two + alternatives may itself contain nested subpatterns of any form, includ- + ing conditional subpatterns; the restriction to two alternatives + applies only at the level of the condition. This pattern fragment is an + example where the alternatives are complex: + + (?(1) (A|B|C) | (D | (?(2)E|F) | E) ) + + + There are four kinds of condition: references to subpatterns, refer- + ences to recursion, a pseudo-condition called DEFINE, and assertions. + + Checking for a used subpattern by number + + If the text between the parentheses consists of a sequence of digits, + the condition is true if a capturing subpattern of that number has pre- + viously matched. If there is more than one capturing subpattern with + the same number (see the earlier section about duplicate subpattern + numbers), the condition is true if any of them have matched. An alter- + native notation is to precede the digits with a plus or minus sign. In + this case, the subpattern number is relative rather than absolute. The + most recently opened parentheses can be referenced by (?(-1), the next + most recent by (?(-2), and so on. Inside loops it can also make sense + to refer to subsequent groups. The next parentheses to be opened can be + referenced as (?(+1), and so on. (The value zero in any of these forms + is not used; it provokes a compile-time error.) + + Consider the following pattern, which contains non-significant white + space to make it more readable (assume the PCRE_EXTENDED option) and to + divide it into three parts for ease of discussion: + + ( \( )? [^()]+ (?(1) \) ) + + The first part matches an optional opening parenthesis, and if that + character is present, sets it as the first captured substring. The sec- + ond part matches one or more characters that are not parentheses. The + third part is a conditional subpattern that tests whether or not the + first set of parentheses matched. If they did, that is, if subject + started with an opening parenthesis, the condition is true, and so the + yes-pattern is executed and a closing parenthesis is required. Other- + wise, since no-pattern is not present, the subpattern matches nothing. + In other words, this pattern matches a sequence of non-parentheses, + optionally enclosed in parentheses. + + If you were embedding this pattern in a larger one, you could use a + relative reference: + + ...other stuff... ( \( )? [^()]+ (?(-1) \) ) ... + + This makes the fragment independent of the parentheses in the larger + pattern. + + Checking for a used subpattern by name + + Perl uses the syntax (?(<name>)...) or (?('name')...) to test for a + used subpattern by name. For compatibility with earlier versions of + PCRE, which had this facility before Perl, the syntax (?(name)...) is + also recognized. + + Rewriting the above example to use a named subpattern gives this: + + (?<OPEN> \( )? [^()]+ (?(<OPEN>) \) ) + + If the name used in a condition of this kind is a duplicate, the test + is applied to all subpatterns of the same name, and is true if any one + of them has matched. + + Checking for pattern recursion + + If the condition is the string (R), and there is no subpattern with the + name R, the condition is true if a recursive call to the whole pattern + or any subpattern has been made. If digits or a name preceded by amper- + sand follow the letter R, for example: + + (?(R3)...) or (?(R&name)...) + + the condition is true if the most recent recursion is into a subpattern + whose number or name is given. This condition does not check the entire + recursion stack. If the name used in a condition of this kind is a + duplicate, the test is applied to all subpatterns of the same name, and + is true if any one of them is the most recent recursion. + + At "top level", all these recursion test conditions are false. The + syntax for recursive patterns is described below. + + Defining subpatterns for use by reference only + + If the condition is the string (DEFINE), and there is no subpattern + with the name DEFINE, the condition is always false. In this case, + there may be only one alternative in the subpattern. It is always + skipped if control reaches this point in the pattern; the idea of + DEFINE is that it can be used to define subroutines that can be refer- + enced from elsewhere. (The use of subroutines is described below.) For + example, a pattern to match an IPv4 address such as "192.168.23.245" + could be written like this (ignore white space and line breaks): + + (?(DEFINE) (?<byte> 2[0-4]\d | 25[0-5] | 1\d\d | [1-9]?\d) ) + \b (?&byte) (\.(?&byte)){3} \b + + The first part of the pattern is a DEFINE group inside which a another + group named "byte" is defined. This matches an individual component of + an IPv4 address (a number less than 256). When matching takes place, + this part of the pattern is skipped because DEFINE acts like a false + condition. The rest of the pattern uses references to the named group + to match the four dot-separated components of an IPv4 address, insist- + ing on a word boundary at each end. + + Assertion conditions + + If the condition is not in any of the above formats, it must be an + assertion. This may be a positive or negative lookahead or lookbehind + assertion. Consider this pattern, again containing non-significant + white space, and with the two alternatives on the second line: + + (?(?=[^a-z]*[a-z]) + \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) + + The condition is a positive lookahead assertion that matches an + optional sequence of non-letters followed by a letter. In other words, + it tests for the presence of at least one letter in the subject. If a + letter is found, the subject is matched against the first alternative; + otherwise it is matched against the second. This pattern matches + strings in one of the two forms dd-aaa-dd or dd-dd-dd, where aaa are + letters and dd are digits. + + +COMMENTS + + There are two ways of including comments in patterns that are processed + by PCRE. In both cases, the start of the comment must not be in a char- + acter class, nor in the middle of any other sequence of related charac- + ters such as (?: or a subpattern name or number. The characters that + make up a comment play no part in the pattern matching. + + The sequence (?# marks the start of a comment that continues up to the + next closing parenthesis. Nested parentheses are not permitted. If the + PCRE_EXTENDED option is set, an unescaped # character also introduces a + comment, which in this case continues to immediately after the next + newline character or character sequence in the pattern. Which charac- + ters are interpreted as newlines is controlled by the options passed to + a compiling function or by a special sequence at the start of the pat- + tern, as described in the section entitled "Newline conventions" above. + Note that the end of this type of comment is a literal newline sequence + in the pattern; escape sequences that happen to represent a newline do + not count. For example, consider this pattern when PCRE_EXTENDED is + set, and the default newline convention is in force: + + abc #comment \n still comment + + On encountering the # character, pcre_compile() skips along, looking + for a newline in the pattern. The sequence \n is still literal at this + stage, so it does not terminate the comment. Only an actual character + with the code value 0x0a (the default newline) does so. + + +RECURSIVE PATTERNS + + Consider the problem of matching a string in parentheses, allowing for + unlimited nested parentheses. Without the use of recursion, the best + that can be done is to use a pattern that matches up to some fixed + depth of nesting. It is not possible to handle an arbitrary nesting + depth. + + For some time, Perl has provided a facility that allows regular expres- + sions to recurse (amongst other things). It does this by interpolating + Perl code in the expression at run time, and the code can refer to the + expression itself. A Perl pattern using code interpolation to solve the + parentheses problem can be created like this: + + $re = qr{\( (?: (?>[^()]+) | (?p{$re}) )* \)}x; + + The (?p{...}) item interpolates Perl code at run time, and in this case + refers recursively to the pattern in which it appears. + + Obviously, PCRE cannot support the interpolation of Perl code. Instead, + it supports special syntax for recursion of the entire pattern, and + also for individual subpattern recursion. After its introduction in + PCRE and Python, this kind of recursion was subsequently introduced + into Perl at release 5.10. + + A special item that consists of (? followed by a number greater than + zero and a closing parenthesis is a recursive subroutine call of the + subpattern of the given number, provided that it occurs inside that + subpattern. (If not, it is a non-recursive subroutine call, which is + described in the next section.) The special item (?R) or (?0) is a + recursive call of the entire regular expression. + + This PCRE pattern solves the nested parentheses problem (assume the + PCRE_EXTENDED option is set so that white space is ignored): + + \( ( [^()]++ | (?R) )* \) + + First it matches an opening parenthesis. Then it matches any number of + substrings which can either be a sequence of non-parentheses, or a + recursive match of the pattern itself (that is, a correctly parenthe- + sized substring). Finally there is a closing parenthesis. Note the use + of a possessive quantifier to avoid backtracking into sequences of non- + parentheses. + + If this were part of a larger pattern, you would not want to recurse + the entire pattern, so instead you could use this: + + ( \( ( [^()]++ | (?1) )* \) ) + + We have put the pattern into parentheses, and caused the recursion to + refer to them instead of the whole pattern. + + In a larger pattern, keeping track of parenthesis numbers can be + tricky. This is made easier by the use of relative references. Instead + of (?1) in the pattern above you can write (?-2) to refer to the second + most recently opened parentheses preceding the recursion. In other + words, a negative number counts capturing parentheses leftwards from + the point at which it is encountered. + + It is also possible to refer to subsequently opened parentheses, by + writing references such as (?+2). However, these cannot be recursive + because the reference is not inside the parentheses that are refer- + enced. They are always non-recursive subroutine calls, as described in + the next section. + + An alternative approach is to use named parentheses instead. The Perl + syntax for this is (?&name); PCRE's earlier syntax (?P>name) is also + supported. We could rewrite the above example as follows: + + (?<pn> \( ( [^()]++ | (?&pn) )* \) ) + + If there is more than one subpattern with the same name, the earliest + one is used. + + This particular example pattern that we have been looking at contains + nested unlimited repeats, and so the use of a possessive quantifier for + matching strings of non-parentheses is important when applying the pat- + tern to strings that do not match. For example, when this pattern is + applied to + + (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa() + + it yields "no match" quickly. However, if a possessive quantifier is + not used, the match runs for a very long time indeed because there are + so many different ways the + and * repeats can carve up the subject, + and all have to be tested before failure can be reported. + + At the end of a match, the values of capturing parentheses are those + from the outermost level. If you want to obtain intermediate values, a + callout function can be used (see below and the pcrecallout documenta- + tion). If the pattern above is matched against + + (ab(cd)ef) + + the value for the inner capturing parentheses (numbered 2) is "ef", + which is the last value taken on at the top level. If a capturing sub- + pattern is not matched at the top level, its final captured value is + unset, even if it was (temporarily) set at a deeper level during the + matching process. + + If there are more than 15 capturing parentheses in a pattern, PCRE has + to obtain extra memory to store data during a recursion, which it does + by using pcre_malloc, freeing it via pcre_free afterwards. If no memory + can be obtained, the match fails with the PCRE_ERROR_NOMEMORY error. + + Do not confuse the (?R) item with the condition (R), which tests for + recursion. Consider this pattern, which matches text in angle brack- + ets, allowing for arbitrary nesting. Only digits are allowed in nested + brackets (that is, when recursing), whereas any characters are permit- + ted at the outer level. + + < (?: (?(R) \d++ | [^<>]*+) | (?R)) * > + + In this pattern, (?(R) is the start of a conditional subpattern, with + two different alternatives for the recursive and non-recursive cases. + The (?R) item is the actual recursive call. + + Differences in recursion processing between PCRE and Perl + + Recursion processing in PCRE differs from Perl in two important ways. + In PCRE (like Python, but unlike Perl), a recursive subpattern call is + always treated as an atomic group. That is, once it has matched some of + the subject string, it is never re-entered, even if it contains untried + alternatives and there is a subsequent matching failure. This can be + illustrated by the following pattern, which purports to match a palin- + dromic string that contains an odd number of characters (for example, + "a", "aba", "abcba", "abcdcba"): + + ^(.|(.)(?1)\2)$ + + The idea is that it either matches a single character, or two identical + characters surrounding a sub-palindrome. In Perl, this pattern works; + in PCRE it does not if the pattern is longer than three characters. + Consider the subject string "abcba": + + At the top level, the first character is matched, but as it is not at + the end of the string, the first alternative fails; the second alterna- + tive is taken and the recursion kicks in. The recursive call to subpat- + tern 1 successfully matches the next character ("b"). (Note that the + beginning and end of line tests are not part of the recursion). + + Back at the top level, the next character ("c") is compared with what + subpattern 2 matched, which was "a". This fails. Because the recursion + is treated as an atomic group, there are now no backtracking points, + and so the entire match fails. (Perl is able, at this point, to re- + enter the recursion and try the second alternative.) However, if the + pattern is written with the alternatives in the other order, things are + different: + + ^((.)(?1)\2|.)$ + + This time, the recursing alternative is tried first, and continues to + recurse until it runs out of characters, at which point the recursion + fails. But this time we do have another alternative to try at the + higher level. That is the big difference: in the previous case the + remaining alternative is at a deeper recursion level, which PCRE cannot + use. + + To change the pattern so that it matches all palindromic strings, not + just those with an odd number of characters, it is tempting to change + the pattern to this: + + ^((.)(?1)\2|.?)$ + + Again, this works in Perl, but not in PCRE, and for the same reason. + When a deeper recursion has matched a single character, it cannot be + entered again in order to match an empty string. The solution is to + separate the two cases, and write out the odd and even cases as alter- + natives at the higher level: + + ^(?:((.)(?1)\2|)|((.)(?3)\4|.)) + + If you want to match typical palindromic phrases, the pattern has to + ignore all non-word characters, which can be done like this: + + ^\W*+(?:((.)\W*+(?1)\W*+\2|)|((.)\W*+(?3)\W*+\4|\W*+.\W*+))\W*+$ + + If run with the PCRE_CASELESS option, this pattern matches phrases such + as "A man, a plan, a canal: Panama!" and it works well in both PCRE and + Perl. Note the use of the possessive quantifier *+ to avoid backtrack- + ing into sequences of non-word characters. Without this, PCRE takes a + great deal longer (ten times or more) to match typical phrases, and + Perl takes so long that you think it has gone into a loop. + + WARNING: The palindrome-matching patterns above work only if the sub- + ject string does not start with a palindrome that is shorter than the + entire string. For example, although "abcba" is correctly matched, if + the subject is "ababa", PCRE finds the palindrome "aba" at the start, + then fails at top level because the end of the string does not follow. + Once again, it cannot jump back into the recursion to try other alter- + natives, so the entire match fails. + + The second way in which PCRE and Perl differ in their recursion pro- + cessing is in the handling of captured values. In Perl, when a subpat- + tern is called recursively or as a subpattern (see the next section), + it has no access to any values that were captured outside the recur- + sion, whereas in PCRE these values can be referenced. Consider this + pattern: + + ^(.)(\1|a(?2)) + + In PCRE, this pattern matches "bab". The first capturing parentheses + match "b", then in the second group, when the back reference \1 fails + to match "b", the second alternative matches "a" and then recurses. In + the recursion, \1 does now match "b" and so the whole match succeeds. + In Perl, the pattern fails to match because inside the recursive call + \1 cannot access the externally set value. + + +SUBPATTERNS AS SUBROUTINES + + If the syntax for a recursive subpattern call (either by number or by + name) is used outside the parentheses to which it refers, it operates + like a subroutine in a programming language. The called subpattern may + be defined before or after the reference. A numbered reference can be + absolute or relative, as in these examples: + + (...(absolute)...)...(?2)... + (...(relative)...)...(?-1)... + (...(?+1)...(relative)... + + An earlier example pointed out that the pattern + + (sens|respons)e and \1ibility + + matches "sense and sensibility" and "response and responsibility", but + not "sense and responsibility". If instead the pattern + + (sens|respons)e and (?1)ibility + + is used, it does match "sense and responsibility" as well as the other + two strings. Another example is given in the discussion of DEFINE + above. + + All subroutine calls, whether recursive or not, are always treated as + atomic groups. That is, once a subroutine has matched some of the sub- + ject string, it is never re-entered, even if it contains untried alter- + natives and there is a subsequent matching failure. Any capturing + parentheses that are set during the subroutine call revert to their + previous values afterwards. + + Processing options such as case-independence are fixed when a subpat- + tern is defined, so if it is used as a subroutine, such options cannot + be changed for different calls. For example, consider this pattern: + + (abc)(?i:(?-1)) + + It matches "abcabc". It does not match "abcABC" because the change of + processing option does not affect the called subpattern. + + +ONIGURUMA SUBROUTINE SYNTAX + + For compatibility with Oniguruma, the non-Perl syntax \g followed by a + name or a number enclosed either in angle brackets or single quotes, is + an alternative syntax for referencing a subpattern as a subroutine, + possibly recursively. Here are two of the examples used above, rewrit- + ten using this syntax: + + (?<pn> \( ( (?>[^()]+) | \g<pn> )* \) ) + (sens|respons)e and \g'1'ibility + + PCRE supports an extension to Oniguruma: if a number is preceded by a + plus or a minus sign it is taken as a relative reference. For example: + + (abc)(?i:\g<-1>) + + Note that \g{...} (Perl syntax) and \g<...> (Oniguruma syntax) are not + synonymous. The former is a back reference; the latter is a subroutine + call. + + +CALLOUTS + + Perl has a feature whereby using the sequence (?{...}) causes arbitrary + Perl code to be obeyed in the middle of matching a regular expression. + This makes it possible, amongst other things, to extract different sub- + strings that match the same pair of parentheses when there is a repeti- + tion. + + PCRE provides a similar feature, but of course it cannot obey arbitrary + Perl code. The feature is called "callout". The caller of PCRE provides + an external function by putting its entry point in the global variable + pcre_callout (8-bit library) or pcre[16|32]_callout (16-bit or 32-bit + library). By default, this variable contains NULL, which disables all + calling out. + + Within a regular expression, (?C) indicates the points at which the + external function is to be called. If you want to identify different + callout points, you can put a number less than 256 after the letter C. + The default value is zero. For example, this pattern has two callout + points: + + (?C1)abc(?C2)def + + If the PCRE_AUTO_CALLOUT flag is passed to a compiling function, call- + outs are automatically installed before each item in the pattern. They + are all numbered 255. If there is a conditional group in the pattern + whose condition is an assertion, an additional callout is inserted just + before the condition. An explicit callout may also be set at this posi- + tion, as in this example: + + (?(?C9)(?=a)abc|def) + + Note that this applies only to assertion conditions, not to other types + of condition. + + During matching, when PCRE reaches a callout point, the external func- + tion is called. It is provided with the number of the callout, the + position in the pattern, and, optionally, one item of data originally + supplied by the caller of the matching function. The callout function + may cause matching to proceed, to backtrack, or to fail altogether. + + By default, PCRE implements a number of optimizations at compile time + and matching time, and one side-effect is that sometimes callouts are + skipped. If you need all possible callouts to happen, you need to set + options that disable the relevant optimizations. More details, and a + complete description of the interface to the callout function, are + given in the pcrecallout documentation. + + +BACKTRACKING CONTROL + + Perl 5.10 introduced a number of "Special Backtracking Control Verbs", + which are still described in the Perl documentation as "experimental + and subject to change or removal in a future version of Perl". It goes + on to say: "Their usage in production code should be noted to avoid + problems during upgrades." The same remarks apply to the PCRE features + described in this section. + + The new verbs make use of what was previously invalid syntax: an open- + ing parenthesis followed by an asterisk. They are generally of the form + (*VERB) or (*VERB:NAME). Some may take either form, possibly behaving + differently depending on whether or not a name is present. A name is + any sequence of characters that does not include a closing parenthesis. + The maximum length of name is 255 in the 8-bit library and 65535 in the + 16-bit and 32-bit libraries. If the name is empty, that is, if the + closing parenthesis immediately follows the colon, the effect is as if + the colon were not there. Any number of these verbs may occur in a + pattern. + + Since these verbs are specifically related to backtracking, most of + them can be used only when the pattern is to be matched using one of + the traditional matching functions, because these use a backtracking + algorithm. With the exception of (*FAIL), which behaves like a failing + negative assertion, the backtracking control verbs cause an error if + encountered by a DFA matching function. + + The behaviour of these verbs in repeated groups, assertions, and in + subpatterns called as subroutines (whether or not recursively) is docu- + mented below. + + Optimizations that affect backtracking verbs + + PCRE contains some optimizations that are used to speed up matching by + running some checks at the start of each match attempt. For example, it + may know the minimum length of matching subject, or that a particular + character must be present. When one of these optimizations bypasses the + running of a match, any included backtracking verbs will not, of + course, be processed. You can suppress the start-of-match optimizations + by setting the PCRE_NO_START_OPTIMIZE option when calling pcre_com- + pile() or pcre_exec(), or by starting the pattern with (*NO_START_OPT). + There is more discussion of this option in the section entitled "Option + bits for pcre_exec()" in the pcreapi documentation. + + Experiments with Perl suggest that it too has similar optimizations, + sometimes leading to anomalous results. + + Verbs that act immediately + + The following verbs act as soon as they are encountered. They may not + be followed by a name. + + (*ACCEPT) + + This verb causes the match to end successfully, skipping the remainder + of the pattern. However, when it is inside a subpattern that is called + as a subroutine, only that subpattern is ended successfully. Matching + then continues at the outer level. If (*ACCEPT) in triggered in a posi- + tive assertion, the assertion succeeds; in a negative assertion, the + assertion fails. + + If (*ACCEPT) is inside capturing parentheses, the data so far is cap- + tured. For example: + + A((?:A|B(*ACCEPT)|C)D) + + This matches "AB", "AAD", or "ACD"; when it matches "AB", "B" is cap- + tured by the outer parentheses. + + (*FAIL) or (*F) + + This verb causes a matching failure, forcing backtracking to occur. It + is equivalent to (?!) but easier to read. The Perl documentation notes + that it is probably useful only when combined with (?{}) or (??{}). + Those are, of course, Perl features that are not present in PCRE. The + nearest equivalent is the callout feature, as for example in this pat- + tern: + + a+(?C)(*FAIL) + + A match with the string "aaaa" always fails, but the callout is taken + before each backtrack happens (in this example, 10 times). + + Recording which path was taken + + There is one verb whose main purpose is to track how a match was + arrived at, though it also has a secondary use in conjunction with + advancing the match starting point (see (*SKIP) below). + + (*MARK:NAME) or (*:NAME) + + A name is always required with this verb. There may be as many + instances of (*MARK) as you like in a pattern, and their names do not + have to be unique. + + When a match succeeds, the name of the last-encountered (*MARK:NAME), + (*PRUNE:NAME), or (*THEN:NAME) on the matching path is passed back to + the caller as described in the section entitled "Extra data for + pcre_exec()" in the pcreapi documentation. Here is an example of + pcretest output, where the /K modifier requests the retrieval and out- + putting of (*MARK) data: + + re> /X(*MARK:A)Y|X(*MARK:B)Z/K + data> XY + 0: XY + MK: A + XZ + 0: XZ + MK: B + + The (*MARK) name is tagged with "MK:" in this output, and in this exam- + ple it indicates which of the two alternatives matched. This is a more + efficient way of obtaining this information than putting each alterna- + tive in its own capturing parentheses. + + If a verb with a name is encountered in a positive assertion that is + true, the name is recorded and passed back if it is the last-encoun- + tered. This does not happen for negative assertions or failing positive + assertions. + + After a partial match or a failed match, the last encountered name in + the entire match process is returned. For example: + + re> /X(*MARK:A)Y|X(*MARK:B)Z/K + data> XP + No match, mark = B + + Note that in this unanchored example the mark is retained from the + match attempt that started at the letter "X" in the subject. Subsequent + match attempts starting at "P" and then with an empty string do not get + as far as the (*MARK) item, but nevertheless do not reset it. + + If you are interested in (*MARK) values after failed matches, you + should probably set the PCRE_NO_START_OPTIMIZE option (see above) to + ensure that the match is always attempted. + + Verbs that act after backtracking + + The following verbs do nothing when they are encountered. Matching con- + tinues with what follows, but if there is no subsequent match, causing + a backtrack to the verb, a failure is forced. That is, backtracking + cannot pass to the left of the verb. However, when one of these verbs + appears inside an atomic group or an assertion that is true, its effect + is confined to that group, because once the group has been matched, + there is never any backtracking into it. In this situation, backtrack- + ing can "jump back" to the left of the entire atomic group or asser- + tion. (Remember also, as stated above, that this localization also + applies in subroutine calls.) + + These verbs differ in exactly what kind of failure occurs when back- + tracking reaches them. The behaviour described below is what happens + when the verb is not in a subroutine or an assertion. Subsequent sec- + tions cover these special cases. + + (*COMMIT) + + This verb, which may not be followed by a name, causes the whole match + to fail outright if there is a later matching failure that causes back- + tracking to reach it. Even if the pattern is unanchored, no further + attempts to find a match by advancing the starting point take place. If + (*COMMIT) is the only backtracking verb that is encountered, once it + has been passed pcre_exec() is committed to finding a match at the cur- + rent starting point, or not at all. For example: + + a+(*COMMIT)b + + This matches "xxaab" but not "aacaab". It can be thought of as a kind + of dynamic anchor, or "I've started, so I must finish." The name of the + most recently passed (*MARK) in the path is passed back when (*COMMIT) + forces a match failure. + + If there is more than one backtracking verb in a pattern, a different + one that follows (*COMMIT) may be triggered first, so merely passing + (*COMMIT) during a match does not always guarantee that a match must be + at this starting point. + + Note that (*COMMIT) at the start of a pattern is not the same as an + anchor, unless PCRE's start-of-match optimizations are turned off, as + shown in this output from pcretest: + + re> /(*COMMIT)abc/ + data> xyzabc + 0: abc + data> xyzabc\Y + No match + + For this pattern, PCRE knows that any match must start with "a", so the + optimization skips along the subject to "a" before applying the pattern + to the first set of data. The match attempt then succeeds. In the sec- + ond set of data, the escape sequence \Y is interpreted by the pcretest + program. It causes the PCRE_NO_START_OPTIMIZE option to be set when + pcre_exec() is called. This disables the optimization that skips along + to the first character. The pattern is now applied starting at "x", and + so the (*COMMIT) causes the match to fail without trying any other + starting points. + + (*PRUNE) or (*PRUNE:NAME) + + This verb causes the match to fail at the current starting position in + the subject if there is a later matching failure that causes backtrack- + ing to reach it. If the pattern is unanchored, the normal "bumpalong" + advance to the next starting character then happens. Backtracking can + occur as usual to the left of (*PRUNE), before it is reached, or when + matching to the right of (*PRUNE), but if there is no match to the + right, backtracking cannot cross (*PRUNE). In simple cases, the use of + (*PRUNE) is just an alternative to an atomic group or possessive quan- + tifier, but there are some uses of (*PRUNE) that cannot be expressed in + any other way. In an anchored pattern (*PRUNE) has the same effect as + (*COMMIT). + + The behaviour of (*PRUNE:NAME) is the not the same as + (*MARK:NAME)(*PRUNE). It is like (*MARK:NAME) in that the name is + remembered for passing back to the caller. However, (*SKIP:NAME) + searches only for names set with (*MARK). + + (*SKIP) + + This verb, when given without a name, is like (*PRUNE), except that if + the pattern is unanchored, the "bumpalong" advance is not to the next + character, but to the position in the subject where (*SKIP) was encoun- + tered. (*SKIP) signifies that whatever text was matched leading up to + it cannot be part of a successful match. Consider: + + a+(*SKIP)b + + If the subject is "aaaac...", after the first match attempt fails + (starting at the first character in the string), the starting point + skips on to start the next attempt at "c". Note that a possessive quan- + tifer does not have the same effect as this example; although it would + suppress backtracking during the first match attempt, the second + attempt would start at the second character instead of skipping on to + "c". + + (*SKIP:NAME) + + When (*SKIP) has an associated name, its behaviour is modified. When it + is triggered, the previous path through the pattern is searched for the + most recent (*MARK) that has the same name. If one is found, the + "bumpalong" advance is to the subject position that corresponds to that + (*MARK) instead of to where (*SKIP) was encountered. If no (*MARK) with + a matching name is found, the (*SKIP) is ignored. + + Note that (*SKIP:NAME) searches only for names set by (*MARK:NAME). It + ignores names that are set by (*PRUNE:NAME) or (*THEN:NAME). + + (*THEN) or (*THEN:NAME) + + This verb causes a skip to the next innermost alternative when back- + tracking reaches it. That is, it cancels any further backtracking + within the current alternative. Its name comes from the observation + that it can be used for a pattern-based if-then-else block: + + ( COND1 (*THEN) FOO | COND2 (*THEN) BAR | COND3 (*THEN) BAZ ) ... + + If the COND1 pattern matches, FOO is tried (and possibly further items + after the end of the group if FOO succeeds); on failure, the matcher + skips to the second alternative and tries COND2, without backtracking + into COND1. If that succeeds and BAR fails, COND3 is tried. If subse- + quently BAZ fails, there are no more alternatives, so there is a back- + track to whatever came before the entire group. If (*THEN) is not + inside an alternation, it acts like (*PRUNE). + + The behaviour of (*THEN:NAME) is the not the same as + (*MARK:NAME)(*THEN). It is like (*MARK:NAME) in that the name is + remembered for passing back to the caller. However, (*SKIP:NAME) + searches only for names set with (*MARK). + + A subpattern that does not contain a | character is just a part of the + enclosing alternative; it is not a nested alternation with only one + alternative. The effect of (*THEN) extends beyond such a subpattern to + the enclosing alternative. Consider this pattern, where A, B, etc. are + complex pattern fragments that do not contain any | characters at this + level: + + A (B(*THEN)C) | D + + If A and B are matched, but there is a failure in C, matching does not + backtrack into A; instead it moves to the next alternative, that is, D. + However, if the subpattern containing (*THEN) is given an alternative, + it behaves differently: + + A (B(*THEN)C | (*FAIL)) | D + + The effect of (*THEN) is now confined to the inner subpattern. After a + failure in C, matching moves to (*FAIL), which causes the whole subpat- + tern to fail because there are no more alternatives to try. In this + case, matching does now backtrack into A. + + Note that a conditional subpattern is not considered as having two + alternatives, because only one is ever used. In other words, the | + character in a conditional subpattern has a different meaning. Ignoring + white space, consider: + + ^.*? (?(?=a) a | b(*THEN)c ) + + If the subject is "ba", this pattern does not match. Because .*? is + ungreedy, it initially matches zero characters. The condition (?=a) + then fails, the character "b" is matched, but "c" is not. At this + point, matching does not backtrack to .*? as might perhaps be expected + from the presence of the | character. The conditional subpattern is + part of the single alternative that comprises the whole pattern, and so + the match fails. (If there was a backtrack into .*?, allowing it to + match "b", the match would succeed.) + + The verbs just described provide four different "strengths" of control + when subsequent matching fails. (*THEN) is the weakest, carrying on the + match at the next alternative. (*PRUNE) comes next, failing the match + at the current starting position, but allowing an advance to the next + character (for an unanchored pattern). (*SKIP) is similar, except that + the advance may be more than one character. (*COMMIT) is the strongest, + causing the entire match to fail. + + More than one backtracking verb + + If more than one backtracking verb is present in a pattern, the one + that is backtracked onto first acts. For example, consider this pat- + tern, where A, B, etc. are complex pattern fragments: + + (A(*COMMIT)B(*THEN)C|ABD) + + If A matches but B fails, the backtrack to (*COMMIT) causes the entire + match to fail. However, if A and B match, but C fails, the backtrack to + (*THEN) causes the next alternative (ABD) to be tried. This behaviour + is consistent, but is not always the same as Perl's. It means that if + two or more backtracking verbs appear in succession, all the the last + of them has no effect. Consider this example: + + ...(*COMMIT)(*PRUNE)... + + If there is a matching failure to the right, backtracking onto (*PRUNE) + causes it to be triggered, and its action is taken. There can never be + a backtrack onto (*COMMIT). + + Backtracking verbs in repeated groups + + PCRE differs from Perl in its handling of backtracking verbs in + repeated groups. For example, consider: + + /(a(*COMMIT)b)+ac/ + + If the subject is "abac", Perl matches, but PCRE fails because the + (*COMMIT) in the second repeat of the group acts. + + Backtracking verbs in assertions + + (*FAIL) in an assertion has its normal effect: it forces an immediate + backtrack. + + (*ACCEPT) in a positive assertion causes the assertion to succeed with- + out any further processing. In a negative assertion, (*ACCEPT) causes + the assertion to fail without any further processing. + + The other backtracking verbs are not treated specially if they appear + in a positive assertion. In particular, (*THEN) skips to the next + alternative in the innermost enclosing group that has alternations, + whether or not this is within the assertion. + + Negative assertions are, however, different, in order to ensure that + changing a positive assertion into a negative assertion changes its + result. Backtracking into (*COMMIT), (*SKIP), or (*PRUNE) causes a neg- + ative assertion to be true, without considering any further alternative + branches in the assertion. Backtracking into (*THEN) causes it to skip + to the next enclosing alternative within the assertion (the normal be- + haviour), but if the assertion does not have such an alternative, + (*THEN) behaves like (*PRUNE). + + Backtracking verbs in subroutines + + These behaviours occur whether or not the subpattern is called recur- + sively. Perl's treatment of subroutines is different in some cases. + + (*FAIL) in a subpattern called as a subroutine has its normal effect: + it forces an immediate backtrack. + + (*ACCEPT) in a subpattern called as a subroutine causes the subroutine + match to succeed without any further processing. Matching then contin- + ues after the subroutine call. + + (*COMMIT), (*SKIP), and (*PRUNE) in a subpattern called as a subroutine + cause the subroutine match to fail. + + (*THEN) skips to the next alternative in the innermost enclosing group + within the subpattern that has alternatives. If there is no such group + within the subpattern, (*THEN) causes the subroutine match to fail. + + +SEE ALSO + + pcreapi(3), pcrecallout(3), pcrematching(3), pcresyntax(3), pcre(3), + pcre16(3), pcre32(3). + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 08 January 2014 + Copyright (c) 1997-2014 University of Cambridge. +------------------------------------------------------------------------------ + + +PCRESYNTAX(3) Library Functions Manual PCRESYNTAX(3) + + + +NAME + PCRE - Perl-compatible regular expressions + +PCRE REGULAR EXPRESSION SYNTAX SUMMARY + + The full syntax and semantics of the regular expressions that are sup- + ported by PCRE are described in the pcrepattern documentation. This + document contains a quick-reference summary of the syntax. + + +QUOTING + + \x where x is non-alphanumeric is a literal x + \Q...\E treat enclosed characters as literal + + +CHARACTERS + + \a alarm, that is, the BEL character (hex 07) + \cx "control-x", where x is any ASCII character + \e escape (hex 1B) + \f form feed (hex 0C) + \n newline (hex 0A) + \r carriage return (hex 0D) + \t tab (hex 09) + \0dd character with octal code 0dd + \ddd character with octal code ddd, or backreference + \o{ddd..} character with octal code ddd.. + \xhh character with hex code hh + \x{hhh..} character with hex code hhh.. + + Note that \0dd is always an octal code, and that \8 and \9 are the lit- + eral characters "8" and "9". + + +CHARACTER TYPES + + . any character except newline; + in dotall mode, any character whatsoever + \C one data unit, even in UTF mode (best avoided) + \d a decimal digit + \D a character that is not a decimal digit + \h a horizontal white space character + \H a character that is not a horizontal white space character + \N a character that is not a newline + \p{xx} a character with the xx property + \P{xx} a character without the xx property + \R a newline sequence + \s a white space character + \S a character that is not a white space character + \v a vertical white space character + \V a character that is not a vertical white space character + \w a "word" character + \W a "non-word" character + \X a Unicode extended grapheme cluster + + By default, \d, \s, and \w match only ASCII characters, even in UTF-8 + mode or in the 16- bit and 32-bit libraries. However, if locale-spe- + cific matching is happening, \s and \w may also match characters with + code points in the range 128-255. If the PCRE_UCP option is set, the + behaviour of these escape sequences is changed to use Unicode proper- + ties and they match many more characters. + + +GENERAL CATEGORY PROPERTIES FOR \p and \P + + C Other + Cc Control + Cf Format + Cn Unassigned + Co Private use + Cs Surrogate + + L Letter + Ll Lower case letter + Lm Modifier letter + Lo Other letter + Lt Title case letter + Lu Upper case letter + L& Ll, Lu, or Lt + + M Mark + Mc Spacing mark + Me Enclosing mark + Mn Non-spacing mark + + N Number + Nd Decimal number + Nl Letter number + No Other number + + P Punctuation + Pc Connector punctuation + Pd Dash punctuation + Pe Close punctuation + Pf Final punctuation + Pi Initial punctuation + Po Other punctuation + Ps Open punctuation + + S Symbol + Sc Currency symbol + Sk Modifier symbol + Sm Mathematical symbol + So Other symbol + + Z Separator + Zl Line separator + Zp Paragraph separator + Zs Space separator + + +PCRE SPECIAL CATEGORY PROPERTIES FOR \p and \P + + Xan Alphanumeric: union of properties L and N + Xps POSIX space: property Z or tab, NL, VT, FF, CR + Xsp Perl space: property Z or tab, NL, VT, FF, CR + Xuc Univerally-named character: one that can be + represented by a Universal Character Name + Xwd Perl word: property Xan or underscore + + Perl and POSIX space are now the same. Perl added VT to its space char- + acter set at release 5.18 and PCRE changed at release 8.34. + + +SCRIPT NAMES FOR \p AND \P + + Arabic, Armenian, Avestan, Balinese, Bamum, Batak, Bengali, Bopomofo, + Brahmi, Braille, Buginese, Buhid, Canadian_Aboriginal, Carian, Chakma, + Cham, Cherokee, Common, Coptic, Cuneiform, Cypriot, Cyrillic, Deseret, + Devanagari, Egyptian_Hieroglyphs, Ethiopic, Georgian, Glagolitic, + Gothic, Greek, Gujarati, Gurmukhi, Han, Hangul, Hanunoo, Hebrew, Hira- + gana, Imperial_Aramaic, Inherited, Inscriptional_Pahlavi, Inscrip- + tional_Parthian, Javanese, Kaithi, Kannada, Katakana, Kayah_Li, + Kharoshthi, Khmer, Lao, Latin, Lepcha, Limbu, Linear_B, Lisu, Lycian, + Lydian, Malayalam, Mandaic, Meetei_Mayek, Meroitic_Cursive, + Meroitic_Hieroglyphs, Miao, Mongolian, Myanmar, New_Tai_Lue, Nko, + Ogham, Old_Italic, Old_Persian, Old_South_Arabian, Old_Turkic, + Ol_Chiki, Oriya, Osmanya, Phags_Pa, Phoenician, Rejang, Runic, Samari- + tan, Saurashtra, Sharada, Shavian, Sinhala, Sora_Sompeng, Sundanese, + Syloti_Nagri, Syriac, Tagalog, Tagbanwa, Tai_Le, Tai_Tham, Tai_Viet, + Takri, Tamil, Telugu, Thaana, Thai, Tibetan, Tifinagh, Ugaritic, Vai, + Yi. + + +CHARACTER CLASSES + + [...] positive character class + [^...] negative character class + [x-y] range (can be used for hex characters) + [[:xxx:]] positive POSIX named set + [[:^xxx:]] negative POSIX named set + + alnum alphanumeric + alpha alphabetic + ascii 0-127 + blank space or tab + cntrl control character + digit decimal digit + graph printing, excluding space + lower lower case letter + print printing, including space + punct printing, excluding alphanumeric + space white space + upper upper case letter + word same as \w + xdigit hexadecimal digit + + In PCRE, POSIX character set names recognize only ASCII characters by + default, but some of them use Unicode properties if PCRE_UCP is set. + You can use \Q...\E inside a character class. + + +QUANTIFIERS + + ? 0 or 1, greedy + ?+ 0 or 1, possessive + ?? 0 or 1, lazy + * 0 or more, greedy + *+ 0 or more, possessive + *? 0 or more, lazy + + 1 or more, greedy + ++ 1 or more, possessive + +? 1 or more, lazy + {n} exactly n + {n,m} at least n, no more than m, greedy + {n,m}+ at least n, no more than m, possessive + {n,m}? at least n, no more than m, lazy + {n,} n or more, greedy + {n,}+ n or more, possessive + {n,}? n or more, lazy + + +ANCHORS AND SIMPLE ASSERTIONS + + \b word boundary + \B not a word boundary + ^ start of subject + also after internal newline in multiline mode + \A start of subject + $ end of subject + also before newline at end of subject + also before internal newline in multiline mode + \Z end of subject + also before newline at end of subject + \z end of subject + \G first matching position in subject + + +MATCH POINT RESET + + \K reset start of match + + \K is honoured in positive assertions, but ignored in negative ones. + + +ALTERNATION + + expr|expr|expr... + + +CAPTURING + + (...) capturing group + (?<name>...) named capturing group (Perl) + (?'name'...) named capturing group (Perl) + (?P<name>...) named capturing group (Python) + (?:...) non-capturing group + (?|...) non-capturing group; reset group numbers for + capturing groups in each alternative + + +ATOMIC GROUPS + + (?>...) atomic, non-capturing group + + +COMMENT + + (?#....) comment (not nestable) + + +OPTION SETTING + + (?i) caseless + (?J) allow duplicate names + (?m) multiline + (?s) single line (dotall) + (?U) default ungreedy (lazy) + (?x) extended (ignore white space) + (?-...) unset option(s) + + The following are recognized only at the very start of a pattern or + after one of the newline or \R options with similar syntax. More than + one of them may appear. + + (*LIMIT_MATCH=d) set the match limit to d (decimal number) + (*LIMIT_RECURSION=d) set the recursion limit to d (decimal number) + (*NO_AUTO_POSSESS) no auto-possessification (PCRE_NO_AUTO_POSSESS) + (*NO_START_OPT) no start-match optimization (PCRE_NO_START_OPTIMIZE) + (*UTF8) set UTF-8 mode: 8-bit library (PCRE_UTF8) + (*UTF16) set UTF-16 mode: 16-bit library (PCRE_UTF16) + (*UTF32) set UTF-32 mode: 32-bit library (PCRE_UTF32) + (*UTF) set appropriate UTF mode for the library in use + (*UCP) set PCRE_UCP (use Unicode properties for \d etc) + + Note that LIMIT_MATCH and LIMIT_RECURSION can only reduce the value of + the limits set by the caller of pcre_exec(), not increase them. + + +NEWLINE CONVENTION + + These are recognized only at the very start of the pattern or after + option settings with a similar syntax. + + (*CR) carriage return only + (*LF) linefeed only + (*CRLF) carriage return followed by linefeed + (*ANYCRLF) all three of the above + (*ANY) any Unicode newline sequence + + +WHAT \R MATCHES + + These are recognized only at the very start of the pattern or after + option setting with a similar syntax. + + (*BSR_ANYCRLF) CR, LF, or CRLF + (*BSR_UNICODE) any Unicode newline sequence + + +LOOKAHEAD AND LOOKBEHIND ASSERTIONS + + (?=...) positive look ahead + (?!...) negative look ahead + (?<=...) positive look behind + (?<!...) negative look behind + + Each top-level branch of a look behind must be of a fixed length. + + +BACKREFERENCES + + \n reference by number (can be ambiguous) + \gn reference by number + \g{n} reference by number + \g{-n} relative reference by number + \k<name> reference by name (Perl) + \k'name' reference by name (Perl) + \g{name} reference by name (Perl) + \k{name} reference by name (.NET) + (?P=name) reference by name (Python) + + +SUBROUTINE REFERENCES (POSSIBLY RECURSIVE) + + (?R) recurse whole pattern + (?n) call subpattern by absolute number + (?+n) call subpattern by relative number + (?-n) call subpattern by relative number + (?&name) call subpattern by name (Perl) + (?P>name) call subpattern by name (Python) + \g<name> call subpattern by name (Oniguruma) + \g'name' call subpattern by name (Oniguruma) + \g<n> call subpattern by absolute number (Oniguruma) + \g'n' call subpattern by absolute number (Oniguruma) + \g<+n> call subpattern by relative number (PCRE extension) + \g'+n' call subpattern by relative number (PCRE extension) + \g<-n> call subpattern by relative number (PCRE extension) + \g'-n' call subpattern by relative number (PCRE extension) + + +CONDITIONAL PATTERNS + + (?(condition)yes-pattern) + (?(condition)yes-pattern|no-pattern) + + (?(n)... absolute reference condition + (?(+n)... relative reference condition + (?(-n)... relative reference condition + (?(<name>)... named reference condition (Perl) + (?('name')... named reference condition (Perl) + (?(name)... named reference condition (PCRE) + (?(R)... overall recursion condition + (?(Rn)... specific group recursion condition + (?(R&name)... specific recursion condition + (?(DEFINE)... define subpattern for reference + (?(assert)... assertion condition + + +BACKTRACKING CONTROL + + The following act immediately they are reached: + + (*ACCEPT) force successful match + (*FAIL) force backtrack; synonym (*F) + (*MARK:NAME) set name to be passed back; synonym (*:NAME) + + The following act only when a subsequent match failure causes a back- + track to reach them. They all force a match failure, but they differ in + what happens afterwards. Those that advance the start-of-match point do + so only if the pattern is not anchored. + + (*COMMIT) overall failure, no advance of starting point + (*PRUNE) advance to next starting character + (*PRUNE:NAME) equivalent to (*MARK:NAME)(*PRUNE) + (*SKIP) advance to current matching position + (*SKIP:NAME) advance to position corresponding to an earlier + (*MARK:NAME); if not found, the (*SKIP) is ignored + (*THEN) local failure, backtrack to next alternation + (*THEN:NAME) equivalent to (*MARK:NAME)(*THEN) + + +CALLOUTS + + (?C) callout + (?Cn) callout with data n + + +SEE ALSO + + pcrepattern(3), pcreapi(3), pcrecallout(3), pcrematching(3), pcre(3). + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 08 January 2014 + Copyright (c) 1997-2014 University of Cambridge. +------------------------------------------------------------------------------ + + +PCREUNICODE(3) Library Functions Manual PCREUNICODE(3) + + + +NAME + PCRE - Perl-compatible regular expressions + +UTF-8, UTF-16, UTF-32, AND UNICODE PROPERTY SUPPORT + + As well as UTF-8 support, PCRE also supports UTF-16 (from release 8.30) + and UTF-32 (from release 8.32), by means of two additional libraries. + They can be built as well as, or instead of, the 8-bit library. + + +UTF-8 SUPPORT + + In order process UTF-8 strings, you must build PCRE's 8-bit library + with UTF support, and, in addition, you must call pcre_compile() with + the PCRE_UTF8 option flag, or the pattern must start with the sequence + (*UTF8) or (*UTF). When either of these is the case, both the pattern + and any subject strings that are matched against it are treated as + UTF-8 strings instead of strings of individual 1-byte characters. + + +UTF-16 AND UTF-32 SUPPORT + + In order process UTF-16 or UTF-32 strings, you must build PCRE's 16-bit + or 32-bit library with UTF support, and, in addition, you must call + pcre16_compile() or pcre32_compile() with the PCRE_UTF16 or PCRE_UTF32 + option flag, as appropriate. Alternatively, the pattern must start with + the sequence (*UTF16), (*UTF32), as appropriate, or (*UTF), which can + be used with either library. When UTF mode is set, both the pattern and + any subject strings that are matched against it are treated as UTF-16 + or UTF-32 strings instead of strings of individual 16-bit or 32-bit + characters. + + +UTF SUPPORT OVERHEAD + + If you compile PCRE with UTF support, but do not use it at run time, + the library will be a bit bigger, but the additional run time overhead + is limited to testing the PCRE_UTF[8|16|32] flag occasionally, so + should not be very big. + + +UNICODE PROPERTY SUPPORT + + If PCRE is built with Unicode character property support (which implies + UTF support), the escape sequences \p{..}, \P{..}, and \X can be used. + The available properties that can be tested are limited to the general + category properties such as Lu for an upper case letter or Nd for a + decimal number, the Unicode script names such as Arabic or Han, and the + derived properties Any and L&. Full lists is given in the pcrepattern + and pcresyntax documentation. Only the short names for properties are + supported. For example, \p{L} matches a letter. Its Perl synonym, + \p{Letter}, is not supported. Furthermore, in Perl, many properties + may optionally be prefixed by "Is", for compatibility with Perl 5.6. + PCRE does not support this. + + Validity of UTF-8 strings + + When you set the PCRE_UTF8 flag, the byte strings passed as patterns + and subjects are (by default) checked for validity on entry to the rel- + evant functions. The entire string is checked before any other process- + ing takes place. From release 7.3 of PCRE, the check is according the + rules of RFC 3629, which are themselves derived from the Unicode speci- + fication. Earlier releases of PCRE followed the rules of RFC 2279, + which allows the full range of 31-bit values (0 to 0x7FFFFFFF). The + current check allows only values in the range U+0 to U+10FFFF, exclud- + ing the surrogate area. (From release 8.33 the so-called "non-charac- + ter" code points are no longer excluded because Unicode corrigendum #9 + makes it clear that they should not be.) + + Characters in the "Surrogate Area" of Unicode are reserved for use by + UTF-16, where they are used in pairs to encode codepoints with values + greater than 0xFFFF. The code points that are encoded by UTF-16 pairs + are available independently in the UTF-8 and UTF-32 encodings. (In + other words, the whole surrogate thing is a fudge for UTF-16 which + unfortunately messes up UTF-8 and UTF-32.) + + If an invalid UTF-8 string is passed to PCRE, an error return is given. + At compile time, the only additional information is the offset to the + first byte of the failing character. The run-time functions pcre_exec() + and pcre_dfa_exec() also pass back this information, as well as a more + detailed reason code if the caller has provided memory in which to do + this. + + In some situations, you may already know that your strings are valid, + and therefore want to skip these checks in order to improve perfor- + mance, for example in the case of a long subject string that is being + scanned repeatedly. If you set the PCRE_NO_UTF8_CHECK flag at compile + time or at run time, PCRE assumes that the pattern or subject it is + given (respectively) contains only valid UTF-8 codes. In this case, it + does not diagnose an invalid UTF-8 string. + + Note that passing PCRE_NO_UTF8_CHECK to pcre_compile() just disables + the check for the pattern; it does not also apply to subject strings. + If you want to disable the check for a subject string you must pass + this option to pcre_exec() or pcre_dfa_exec(). + + If you pass an invalid UTF-8 string when PCRE_NO_UTF8_CHECK is set, the + result is undefined and your program may crash. + + Validity of UTF-16 strings + + When you set the PCRE_UTF16 flag, the strings of 16-bit data units that + are passed as patterns and subjects are (by default) checked for valid- + ity on entry to the relevant functions. Values other than those in the + surrogate range U+D800 to U+DFFF are independent code points. Values in + the surrogate range must be used in pairs in the correct manner. + + If an invalid UTF-16 string is passed to PCRE, an error return is + given. At compile time, the only additional information is the offset + to the first data unit of the failing character. The run-time functions + pcre16_exec() and pcre16_dfa_exec() also pass back this information, as + well as a more detailed reason code if the caller has provided memory + in which to do this. + + In some situations, you may already know that your strings are valid, + and therefore want to skip these checks in order to improve perfor- + mance. If you set the PCRE_NO_UTF16_CHECK flag at compile time or at + run time, PCRE assumes that the pattern or subject it is given (respec- + tively) contains only valid UTF-16 sequences. In this case, it does not + diagnose an invalid UTF-16 string. However, if an invalid string is + passed, the result is undefined. + + Validity of UTF-32 strings + + When you set the PCRE_UTF32 flag, the strings of 32-bit data units that + are passed as patterns and subjects are (by default) checked for valid- + ity on entry to the relevant functions. This check allows only values + in the range U+0 to U+10FFFF, excluding the surrogate area U+D800 to + U+DFFF. + + If an invalid UTF-32 string is passed to PCRE, an error return is + given. At compile time, the only additional information is the offset + to the first data unit of the failing character. The run-time functions + pcre32_exec() and pcre32_dfa_exec() also pass back this information, as + well as a more detailed reason code if the caller has provided memory + in which to do this. + + In some situations, you may already know that your strings are valid, + and therefore want to skip these checks in order to improve perfor- + mance. If you set the PCRE_NO_UTF32_CHECK flag at compile time or at + run time, PCRE assumes that the pattern or subject it is given (respec- + tively) contains only valid UTF-32 sequences. In this case, it does not + diagnose an invalid UTF-32 string. However, if an invalid string is + passed, the result is undefined. + + General comments about UTF modes + + 1. Codepoints less than 256 can be specified in patterns by either + braced or unbraced hexadecimal escape sequences (for example, \x{b3} or + \xb3). Larger values have to use braced sequences. + + 2. Octal numbers up to \777 are recognized, and in UTF-8 mode they + match two-byte characters for values greater than \177. + + 3. Repeat quantifiers apply to complete UTF characters, not to individ- + ual data units, for example: \x{100}{3}. + + 4. The dot metacharacter matches one UTF character instead of a single + data unit. + + 5. The escape sequence \C can be used to match a single byte in UTF-8 + mode, or a single 16-bit data unit in UTF-16 mode, or a single 32-bit + data unit in UTF-32 mode, but its use can lead to some strange effects + because it breaks up multi-unit characters (see the description of \C + in the pcrepattern documentation). The use of \C is not supported in + the alternative matching function pcre[16|32]_dfa_exec(), nor is it + supported in UTF mode by the JIT optimization of pcre[16|32]_exec(). If + JIT optimization is requested for a UTF pattern that contains \C, it + will not succeed, and so the matching will be carried out by the normal + interpretive function. + + 6. The character escapes \b, \B, \d, \D, \s, \S, \w, and \W correctly + test characters of any code value, but, by default, the characters that + PCRE recognizes as digits, spaces, or word characters remain the same + set as in non-UTF mode, all with values less than 256. This remains + true even when PCRE is built to include Unicode property support, + because to do otherwise would slow down PCRE in many common cases. Note + in particular that this applies to \b and \B, because they are defined + in terms of \w and \W. If you really want to test for a wider sense of, + say, "digit", you can use explicit Unicode property tests such as + \p{Nd}. Alternatively, if you set the PCRE_UCP option, the way that the + character escapes work is changed so that Unicode properties are used + to determine which characters match. There are more details in the sec- + tion on generic character types in the pcrepattern documentation. + + 7. Similarly, characters that match the POSIX named character classes + are all low-valued characters, unless the PCRE_UCP option is set. + + 8. However, the horizontal and vertical white space matching escapes + (\h, \H, \v, and \V) do match all the appropriate Unicode characters, + whether or not PCRE_UCP is set. + + 9. Case-insensitive matching applies only to characters whose values + are less than 128, unless PCRE is built with Unicode property support. + A few Unicode characters such as Greek sigma have more than two code- + points that are case-equivalent. Up to and including PCRE release 8.31, + only one-to-one case mappings were supported, but later releases (with + Unicode property support) do treat as case-equivalent all versions of + characters such as Greek sigma. + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 27 February 2013 + Copyright (c) 1997-2013 University of Cambridge. +------------------------------------------------------------------------------ + + +PCREJIT(3) Library Functions Manual PCREJIT(3) + + + +NAME + PCRE - Perl-compatible regular expressions + +PCRE JUST-IN-TIME COMPILER SUPPORT + + Just-in-time compiling is a heavyweight optimization that can greatly + speed up pattern matching. However, it comes at the cost of extra pro- + cessing before the match is performed. Therefore, it is of most benefit + when the same pattern is going to be matched many times. This does not + necessarily mean many calls of a matching function; if the pattern is + not anchored, matching attempts may take place many times at various + positions in the subject, even for a single call. Therefore, if the + subject string is very long, it may still pay to use JIT for one-off + matches. + + JIT support applies only to the traditional Perl-compatible matching + function. It does not apply when the DFA matching function is being + used. The code for this support was written by Zoltan Herczeg. + + +8-BIT, 16-BIT AND 32-BIT SUPPORT + + JIT support is available for all of the 8-bit, 16-bit and 32-bit PCRE + libraries. To keep this documentation simple, only the 8-bit interface + is described in what follows. If you are using the 16-bit library, sub- + stitute the 16-bit functions and 16-bit structures (for example, + pcre16_jit_stack instead of pcre_jit_stack). If you are using the + 32-bit library, substitute the 32-bit functions and 32-bit structures + (for example, pcre32_jit_stack instead of pcre_jit_stack). + + +AVAILABILITY OF JIT SUPPORT + + JIT support is an optional feature of PCRE. The "configure" option + --enable-jit (or equivalent CMake option) must be set when PCRE is + built if you want to use JIT. The support is limited to the following + hardware platforms: + + ARM v5, v7, and Thumb2 + Intel x86 32-bit and 64-bit + MIPS 32-bit + Power PC 32-bit and 64-bit + SPARC 32-bit (experimental) + + If --enable-jit is set on an unsupported platform, compilation fails. + + A program that is linked with PCRE 8.20 or later can tell if JIT sup- + port is available by calling pcre_config() with the PCRE_CONFIG_JIT + option. The result is 1 when JIT is available, and 0 otherwise. How- + ever, a simple program does not need to check this in order to use JIT. + The normal API is implemented in a way that falls back to the interpre- + tive code if JIT is not available. For programs that need the best pos- + sible performance, there is also a "fast path" API that is JIT-spe- + cific. + + If your program may sometimes be linked with versions of PCRE that are + older than 8.20, but you want to use JIT when it is available, you can + test the values of PCRE_MAJOR and PCRE_MINOR, or the existence of a JIT + macro such as PCRE_CONFIG_JIT, for compile-time control of your code. + + +SIMPLE USE OF JIT + + You have to do two things to make use of the JIT support in the sim- + plest way: + + (1) Call pcre_study() with the PCRE_STUDY_JIT_COMPILE option for + each compiled pattern, and pass the resulting pcre_extra block to + pcre_exec(). + + (2) Use pcre_free_study() to free the pcre_extra block when it is + no longer needed, instead of just freeing it yourself. This + ensures that + any JIT data is also freed. + + For a program that may be linked with pre-8.20 versions of PCRE, you + can insert + + #ifndef PCRE_STUDY_JIT_COMPILE + #define PCRE_STUDY_JIT_COMPILE 0 + #endif + + so that no option is passed to pcre_study(), and then use something + like this to free the study data: + + #ifdef PCRE_CONFIG_JIT + pcre_free_study(study_ptr); + #else + pcre_free(study_ptr); + #endif + + PCRE_STUDY_JIT_COMPILE requests the JIT compiler to generate code for + complete matches. If you want to run partial matches using the + PCRE_PARTIAL_HARD or PCRE_PARTIAL_SOFT options of pcre_exec(), you + should set one or both of the following options in addition to, or + instead of, PCRE_STUDY_JIT_COMPILE when you call pcre_study(): + + PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE + PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE + + The JIT compiler generates different optimized code for each of the + three modes (normal, soft partial, hard partial). When pcre_exec() is + called, the appropriate code is run if it is available. Otherwise, the + pattern is matched using interpretive code. + + In some circumstances you may need to call additional functions. These + are described in the section entitled "Controlling the JIT stack" + below. + + If JIT support is not available, PCRE_STUDY_JIT_COMPILE etc. are + ignored, and no JIT data is created. Otherwise, the compiled pattern is + passed to the JIT compiler, which turns it into machine code that exe- + cutes much faster than the normal interpretive code. When pcre_exec() + is passed a pcre_extra block containing a pointer to JIT code of the + appropriate mode (normal or hard/soft partial), it obeys that code + instead of running the interpreter. The result is identical, but the + compiled JIT code runs much faster. + + There are some pcre_exec() options that are not supported for JIT exe- + cution. There are also some pattern items that JIT cannot handle. + Details are given below. In both cases, execution automatically falls + back to the interpretive code. If you want to know whether JIT was + actually used for a particular match, you should arrange for a JIT + callback function to be set up as described in the section entitled + "Controlling the JIT stack" below, even if you do not need to supply a + non-default JIT stack. Such a callback function is called whenever JIT + code is about to be obeyed. If the execution options are not right for + JIT execution, the callback function is not obeyed. + + If the JIT compiler finds an unsupported item, no JIT data is gener- + ated. You can find out if JIT execution is available after studying a + pattern by calling pcre_fullinfo() with the PCRE_INFO_JIT option. A + result of 1 means that JIT compilation was successful. A result of 0 + means that JIT support is not available, or the pattern was not studied + with PCRE_STUDY_JIT_COMPILE etc., or the JIT compiler was not able to + handle the pattern. + + Once a pattern has been studied, with or without JIT, it can be used as + many times as you like for matching different subject strings. + + +UNSUPPORTED OPTIONS AND PATTERN ITEMS + + The only pcre_exec() options that are supported for JIT execution are + PCRE_NO_UTF8_CHECK, PCRE_NO_UTF16_CHECK, PCRE_NO_UTF32_CHECK, PCRE_NOT- + BOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, PCRE_PAR- + TIAL_HARD, and PCRE_PARTIAL_SOFT. + + The only unsupported pattern items are \C (match a single data unit) + when running in a UTF mode, and a callout immediately before an asser- + tion condition in a conditional group. + + +RETURN VALUES FROM JIT EXECUTION + + When a pattern is matched using JIT execution, the return values are + the same as those given by the interpretive pcre_exec() code, with the + addition of one new error code: PCRE_ERROR_JIT_STACKLIMIT. This means + that the memory used for the JIT stack was insufficient. See "Control- + ling the JIT stack" below for a discussion of JIT stack usage. For com- + patibility with the interpretive pcre_exec() code, no more than two- + thirds of the ovector argument is used for passing back captured sub- + strings. + + The error code PCRE_ERROR_MATCHLIMIT is returned by the JIT code if + searching a very large pattern tree goes on for too long, as it is in + the same circumstance when JIT is not used, but the details of exactly + what is counted are not the same. The PCRE_ERROR_RECURSIONLIMIT error + code is never returned by JIT execution. + + +SAVING AND RESTORING COMPILED PATTERNS + + The code that is generated by the JIT compiler is architecture-spe- + cific, and is also position dependent. For those reasons it cannot be + saved (in a file or database) and restored later like the bytecode and + other data of a compiled pattern. Saving and restoring compiled pat- + terns is not something many people do. More detail about this facility + is given in the pcreprecompile documentation. It should be possible to + run pcre_study() on a saved and restored pattern, and thereby recreate + the JIT data, but because JIT compilation uses significant resources, + it is probably not worth doing this; you might as well recompile the + original pattern. + + +CONTROLLING THE JIT STACK + + When the compiled JIT code runs, it needs a block of memory to use as a + stack. By default, it uses 32K on the machine stack. However, some + large or complicated patterns need more than this. The error + PCRE_ERROR_JIT_STACKLIMIT is given when there is not enough stack. + Three functions are provided for managing blocks of memory for use as + JIT stacks. There is further discussion about the use of JIT stacks in + the section entitled "JIT stack FAQ" below. + + The pcre_jit_stack_alloc() function creates a JIT stack. Its arguments + are a starting size and a maximum size, and it returns a pointer to an + opaque structure of type pcre_jit_stack, or NULL if there is an error. + The pcre_jit_stack_free() function can be used to free a stack that is + no longer needed. (For the technically minded: the address space is + allocated by mmap or VirtualAlloc.) + + JIT uses far less memory for recursion than the interpretive code, and + a maximum stack size of 512K to 1M should be more than enough for any + pattern. + + The pcre_assign_jit_stack() function specifies which stack JIT code + should use. Its arguments are as follows: + + pcre_extra *extra + pcre_jit_callback callback + void *data + + The extra argument must be the result of studying a pattern with + PCRE_STUDY_JIT_COMPILE etc. There are three cases for the values of the + other two options: + + (1) If callback is NULL and data is NULL, an internal 32K block + on the machine stack is used. + + (2) If callback is NULL and data is not NULL, data must be + a valid JIT stack, the result of calling pcre_jit_stack_alloc(). + + (3) If callback is not NULL, it must point to a function that is + called with data as an argument at the start of matching, in + order to set up a JIT stack. If the return from the callback + function is NULL, the internal 32K stack is used; otherwise the + return value must be a valid JIT stack, the result of calling + pcre_jit_stack_alloc(). + + A callback function is obeyed whenever JIT code is about to be run; it + is not obeyed when pcre_exec() is called with options that are incom- + patible for JIT execution. A callback function can therefore be used to + determine whether a match operation was executed by JIT or by the + interpreter. + + You may safely use the same JIT stack for more than one pattern (either + by assigning directly or by callback), as long as the patterns are all + matched sequentially in the same thread. In a multithread application, + if you do not specify a JIT stack, or if you assign or pass back NULL + from a callback, that is thread-safe, because each thread has its own + machine stack. However, if you assign or pass back a non-NULL JIT + stack, this must be a different stack for each thread so that the + application is thread-safe. + + Strictly speaking, even more is allowed. You can assign the same non- + NULL stack to any number of patterns as long as they are not used for + matching by multiple threads at the same time. For example, you can + assign the same stack to all compiled patterns, and use a global mutex + in the callback to wait until the stack is available for use. However, + this is an inefficient solution, and not recommended. + + This is a suggestion for how a multithreaded program that needs to set + up non-default JIT stacks might operate: + + During thread initalization + thread_local_var = pcre_jit_stack_alloc(...) + + During thread exit + pcre_jit_stack_free(thread_local_var) + + Use a one-line callback function + return thread_local_var + + All the functions described in this section do nothing if JIT is not + available, and pcre_assign_jit_stack() does nothing unless the extra + argument is non-NULL and points to a pcre_extra block that is the + result of a successful study with PCRE_STUDY_JIT_COMPILE etc. + + +JIT STACK FAQ + + (1) Why do we need JIT stacks? + + PCRE (and JIT) is a recursive, depth-first engine, so it needs a stack + where the local data of the current node is pushed before checking its + child nodes. Allocating real machine stack on some platforms is diffi- + cult. For example, the stack chain needs to be updated every time if we + extend the stack on PowerPC. Although it is possible, its updating + time overhead decreases performance. So we do the recursion in memory. + + (2) Why don't we simply allocate blocks of memory with malloc()? + + Modern operating systems have a nice feature: they can reserve an + address space instead of allocating memory. We can safely allocate mem- + ory pages inside this address space, so the stack could grow without + moving memory data (this is important because of pointers). Thus we can + allocate 1M address space, and use only a single memory page (usually + 4K) if that is enough. However, we can still grow up to 1M anytime if + needed. + + (3) Who "owns" a JIT stack? + + The owner of the stack is the user program, not the JIT studied pattern + or anything else. The user program must ensure that if a stack is used + by pcre_exec(), (that is, it is assigned to the pattern currently run- + ning), that stack must not be used by any other threads (to avoid over- + writing the same memory area). The best practice for multithreaded pro- + grams is to allocate a stack for each thread, and return this stack + through the JIT callback function. + + (4) When should a JIT stack be freed? + + You can free a JIT stack at any time, as long as it will not be used by + pcre_exec() again. When you assign the stack to a pattern, only a + pointer is set. There is no reference counting or any other magic. You + can free the patterns and stacks in any order, anytime. Just do not + call pcre_exec() with a pattern pointing to an already freed stack, as + that will cause SEGFAULT. (Also, do not free a stack currently used by + pcre_exec() in another thread). You can also replace the stack for a + pattern at any time. You can even free the previous stack before + assigning a replacement. + + (5) Should I allocate/free a stack every time before/after calling + pcre_exec()? + + No, because this is too costly in terms of resources. However, you + could implement some clever idea which release the stack if it is not + used in let's say two minutes. The JIT callback can help to achieve + this without keeping a list of the currently JIT studied patterns. + + (6) OK, the stack is for long term memory allocation. But what happens + if a pattern causes stack overflow with a stack of 1M? Is that 1M kept + until the stack is freed? + + Especially on embedded sytems, it might be a good idea to release mem- + ory sometimes without freeing the stack. There is no API for this at + the moment. Probably a function call which returns with the currently + allocated memory for any stack and another which allows releasing mem- + ory (shrinking the stack) would be a good idea if someone needs this. + + (7) This is too much of a headache. Isn't there any better solution for + JIT stack handling? + + No, thanks to Windows. If POSIX threads were used everywhere, we could + throw out this complicated API. + + +EXAMPLE CODE + + This is a single-threaded example that specifies a JIT stack without + using a callback. + + int rc; + int ovector[30]; + pcre *re; + pcre_extra *extra; + pcre_jit_stack *jit_stack; + + re = pcre_compile(pattern, 0, &error, &erroffset, NULL); + /* Check for errors */ + extra = pcre_study(re, PCRE_STUDY_JIT_COMPILE, &error); + jit_stack = pcre_jit_stack_alloc(32*1024, 512*1024); + /* Check for error (NULL) */ + pcre_assign_jit_stack(extra, NULL, jit_stack); + rc = pcre_exec(re, extra, subject, length, 0, 0, ovector, 30); + /* Check results */ + pcre_free(re); + pcre_free_study(extra); + pcre_jit_stack_free(jit_stack); + + +JIT FAST PATH API + + Because the API described above falls back to interpreted execution + when JIT is not available, it is convenient for programs that are writ- + ten for general use in many environments. However, calling JIT via + pcre_exec() does have a performance impact. Programs that are written + for use where JIT is known to be available, and which need the best + possible performance, can instead use a "fast path" API to call JIT + execution directly instead of calling pcre_exec() (obviously only for + patterns that have been successfully studied by JIT). + + The fast path function is called pcre_jit_exec(), and it takes exactly + the same arguments as pcre_exec(), plus one additional argument that + must point to a JIT stack. The JIT stack arrangements described above + do not apply. The return values are the same as for pcre_exec(). + + When you call pcre_exec(), as well as testing for invalid options, a + number of other sanity checks are performed on the arguments. For exam- + ple, if the subject pointer is NULL, or its length is negative, an + immediate error is given. Also, unless PCRE_NO_UTF[8|16|32] is set, a + UTF subject string is tested for validity. In the interests of speed, + these checks do not happen on the JIT fast path, and if invalid data is + passed, the result is undefined. + + Bypassing the sanity checks and the pcre_exec() wrapping can give + speedups of more than 10%. + + +SEE ALSO + + pcreapi(3) + + +AUTHOR + + Philip Hazel (FAQ by Zoltan Herczeg) + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 17 March 2013 + Copyright (c) 1997-2013 University of Cambridge. +------------------------------------------------------------------------------ + + +PCREPARTIAL(3) Library Functions Manual PCREPARTIAL(3) + + + +NAME + PCRE - Perl-compatible regular expressions + +PARTIAL MATCHING IN PCRE + + In normal use of PCRE, if the subject string that is passed to a match- + ing function matches as far as it goes, but is too short to match the + entire pattern, PCRE_ERROR_NOMATCH is returned. There are circumstances + where it might be helpful to distinguish this case from other cases in + which there is no match. + + Consider, for example, an application where a human is required to type + in data for a field with specific formatting requirements. An example + might be a date in the form ddmmmyy, defined by this pattern: + + ^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$ + + If the application sees the user's keystrokes one by one, and can check + that what has been typed so far is potentially valid, it is able to + raise an error as soon as a mistake is made, by beeping and not + reflecting the character that has been typed, for example. This immedi- + ate feedback is likely to be a better user interface than a check that + is delayed until the entire string has been entered. Partial matching + can also be useful when the subject string is very long and is not all + available at once. + + PCRE supports partial matching by means of the PCRE_PARTIAL_SOFT and + PCRE_PARTIAL_HARD options, which can be set when calling any of the + matching functions. For backwards compatibility, PCRE_PARTIAL is a syn- + onym for PCRE_PARTIAL_SOFT. The essential difference between the two + options is whether or not a partial match is preferred to an alterna- + tive complete match, though the details differ between the two types of + matching function. If both options are set, PCRE_PARTIAL_HARD takes + precedence. + + If you want to use partial matching with just-in-time optimized code, + you must call pcre_study(), pcre16_study() or pcre32_study() with one + or both of these options: + + PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE + PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE + + PCRE_STUDY_JIT_COMPILE should also be set if you are going to run non- + partial matches on the same pattern. If the appropriate JIT study mode + has not been set for a match, the interpretive matching code is used. + + Setting a partial matching option disables two of PCRE's standard opti- + mizations. PCRE remembers the last literal data unit in a pattern, and + abandons matching immediately if it is not present in the subject + string. This optimization cannot be used for a subject string that + might match only partially. If the pattern was studied, PCRE knows the + minimum length of a matching string, and does not bother to run the + matching function on shorter strings. This optimization is also dis- + abled for partial matching. + + +PARTIAL MATCHING USING pcre_exec() OR pcre[16|32]_exec() + + A partial match occurs during a call to pcre_exec() or + pcre[16|32]_exec() when the end of the subject string is reached suc- + cessfully, but matching cannot continue because more characters are + needed. However, at least one character in the subject must have been + inspected. This character need not form part of the final matched + string; lookbehind assertions and the \K escape sequence provide ways + of inspecting characters before the start of a matched substring. The + requirement for inspecting at least one character exists because an + empty string can always be matched; without such a restriction there + would always be a partial match of an empty string at the end of the + subject. + + If there are at least two slots in the offsets vector when a partial + match is returned, the first slot is set to the offset of the earliest + character that was inspected. For convenience, the second offset points + to the end of the subject so that a substring can easily be identified. + If there are at least three slots in the offsets vector, the third slot + is set to the offset of the character where matching started. + + For the majority of patterns, the contents of the first and third slots + will be the same. However, for patterns that contain lookbehind asser- + tions, or begin with \b or \B, characters before the one where matching + started may have been inspected while carrying out the match. For exam- + ple, consider this pattern: + + /(?<=abc)123/ + + This pattern matches "123", but only if it is preceded by "abc". If the + subject string is "xyzabc12", the first two offsets after a partial + match are for the substring "abc12", because all these characters were + inspected. However, the third offset is set to 6, because that is the + offset where matching began. + + What happens when a partial match is identified depends on which of the + two partial matching options are set. + + PCRE_PARTIAL_SOFT WITH pcre_exec() OR pcre[16|32]_exec() + + If PCRE_PARTIAL_SOFT is set when pcre_exec() or pcre[16|32]_exec() + identifies a partial match, the partial match is remembered, but match- + ing continues as normal, and other alternatives in the pattern are + tried. If no complete match can be found, PCRE_ERROR_PARTIAL is + returned instead of PCRE_ERROR_NOMATCH. + + This option is "soft" because it prefers a complete match over a par- + tial match. All the various matching items in a pattern behave as if + the subject string is potentially complete. For example, \z, \Z, and $ + match at the end of the subject, as normal, and for \b and \B the end + of the subject is treated as a non-alphanumeric. + + If there is more than one partial match, the first one that was found + provides the data that is returned. Consider this pattern: + + /123\w+X|dogY/ + + If this is matched against the subject string "abc123dog", both alter- + natives fail to match, but the end of the subject is reached during + matching, so PCRE_ERROR_PARTIAL is returned. The offsets are set to 3 + and 9, identifying "123dog" as the first partial match that was found. + (In this example, there are two partial matches, because "dog" on its + own partially matches the second alternative.) + + PCRE_PARTIAL_HARD WITH pcre_exec() OR pcre[16|32]_exec() + + If PCRE_PARTIAL_HARD is set for pcre_exec() or pcre[16|32]_exec(), + PCRE_ERROR_PARTIAL is returned as soon as a partial match is found, + without continuing to search for possible complete matches. This option + is "hard" because it prefers an earlier partial match over a later com- + plete match. For this reason, the assumption is made that the end of + the supplied subject string may not be the true end of the available + data, and so, if \z, \Z, \b, \B, or $ are encountered at the end of the + subject, the result is PCRE_ERROR_PARTIAL, provided that at least one + character in the subject has been inspected. + + Setting PCRE_PARTIAL_HARD also affects the way UTF-8 and UTF-16 subject + strings are checked for validity. Normally, an invalid sequence causes + the error PCRE_ERROR_BADUTF8 or PCRE_ERROR_BADUTF16. However, in the + special case of a truncated character at the end of the subject, + PCRE_ERROR_SHORTUTF8 or PCRE_ERROR_SHORTUTF16 is returned when + PCRE_PARTIAL_HARD is set. + + Comparing hard and soft partial matching + + The difference between the two partial matching options can be illus- + trated by a pattern such as: + + /dog(sbody)?/ + + This matches either "dog" or "dogsbody", greedily (that is, it prefers + the longer string if possible). If it is matched against the string + "dog" with PCRE_PARTIAL_SOFT, it yields a complete match for "dog". + However, if PCRE_PARTIAL_HARD is set, the result is PCRE_ERROR_PARTIAL. + On the other hand, if the pattern is made ungreedy the result is dif- + ferent: + + /dog(sbody)??/ + + In this case the result is always a complete match because that is + found first, and matching never continues after finding a complete + match. It might be easier to follow this explanation by thinking of the + two patterns like this: + + /dog(sbody)?/ is the same as /dogsbody|dog/ + /dog(sbody)??/ is the same as /dog|dogsbody/ + + The second pattern will never match "dogsbody", because it will always + find the shorter match first. + + +PARTIAL MATCHING USING pcre_dfa_exec() OR pcre[16|32]_dfa_exec() + + The DFA functions move along the subject string character by character, + without backtracking, searching for all possible matches simultane- + ously. If the end of the subject is reached before the end of the pat- + tern, there is the possibility of a partial match, again provided that + at least one character has been inspected. + + When PCRE_PARTIAL_SOFT is set, PCRE_ERROR_PARTIAL is returned only if + there have been no complete matches. Otherwise, the complete matches + are returned. However, if PCRE_PARTIAL_HARD is set, a partial match + takes precedence over any complete matches. The portion of the string + that was inspected when the longest partial match was found is set as + the first matching string, provided there are at least two slots in the + offsets vector. + + Because the DFA functions always search for all possible matches, and + there is no difference between greedy and ungreedy repetition, their + behaviour is different from the standard functions when PCRE_PAR- + TIAL_HARD is set. Consider the string "dog" matched against the + ungreedy pattern shown above: + + /dog(sbody)??/ + + Whereas the standard functions stop as soon as they find the complete + match for "dog", the DFA functions also find the partial match for + "dogsbody", and so return that when PCRE_PARTIAL_HARD is set. + + +PARTIAL MATCHING AND WORD BOUNDARIES + + If a pattern ends with one of sequences \b or \B, which test for word + boundaries, partial matching with PCRE_PARTIAL_SOFT can give counter- + intuitive results. Consider this pattern: + + /\bcat\b/ + + This matches "cat", provided there is a word boundary at either end. If + the subject string is "the cat", the comparison of the final "t" with a + following character cannot take place, so a partial match is found. + However, normal matching carries on, and \b matches at the end of the + subject when the last character is a letter, so a complete match is + found. The result, therefore, is not PCRE_ERROR_PARTIAL. Using + PCRE_PARTIAL_HARD in this case does yield PCRE_ERROR_PARTIAL, because + then the partial match takes precedence. + + +FORMERLY RESTRICTED PATTERNS + + For releases of PCRE prior to 8.00, because of the way certain internal + optimizations were implemented in the pcre_exec() function, the + PCRE_PARTIAL option (predecessor of PCRE_PARTIAL_SOFT) could not be + used with all patterns. From release 8.00 onwards, the restrictions no + longer apply, and partial matching with can be requested for any pat- + tern. + + Items that were formerly restricted were repeated single characters and + repeated metasequences. If PCRE_PARTIAL was set for a pattern that did + not conform to the restrictions, pcre_exec() returned the error code + PCRE_ERROR_BADPARTIAL (-13). This error code is no longer in use. The + PCRE_INFO_OKPARTIAL call to pcre_fullinfo() to find out if a compiled + pattern can be used for partial matching now always returns 1. + + +EXAMPLE OF PARTIAL MATCHING USING PCRETEST + + If the escape sequence \P is present in a pcretest data line, the + PCRE_PARTIAL_SOFT option is used for the match. Here is a run of + pcretest that uses the date example quoted above: + + re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ + data> 25jun04\P + 0: 25jun04 + 1: jun + data> 25dec3\P + Partial match: 23dec3 + data> 3ju\P + Partial match: 3ju + data> 3juj\P + No match + data> j\P + No match + + The first data string is matched completely, so pcretest shows the + matched substrings. The remaining four strings do not match the com- + plete pattern, but the first two are partial matches. Similar output is + obtained if DFA matching is used. + + If the escape sequence \P is present more than once in a pcretest data + line, the PCRE_PARTIAL_HARD option is set for the match. + + +MULTI-SEGMENT MATCHING WITH pcre_dfa_exec() OR pcre[16|32]_dfa_exec() + + When a partial match has been found using a DFA matching function, it + is possible to continue the match by providing additional subject data + and calling the function again with the same compiled regular expres- + sion, this time setting the PCRE_DFA_RESTART option. You must pass the + same working space as before, because this is where details of the pre- + vious partial match are stored. Here is an example using pcretest, + using the \R escape sequence to set the PCRE_DFA_RESTART option (\D + specifies the use of the DFA matching function): + + re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ + data> 23ja\P\D + Partial match: 23ja + data> n05\R\D + 0: n05 + + The first call has "23ja" as the subject, and requests partial match- + ing; the second call has "n05" as the subject for the continued + (restarted) match. Notice that when the match is complete, only the + last part is shown; PCRE does not retain the previously partially- + matched string. It is up to the calling program to do that if it needs + to. + + That means that, for an unanchored pattern, if a continued match fails, + it is not possible to try again at a new starting point. All this + facility is capable of doing is continuing with the previous match + attempt. In the previous example, if the second set of data is "ug23" + the result is no match, even though there would be a match for "aug23" + if the entire string were given at once. Depending on the application, + this may or may not be what you want. The only way to allow for start- + ing again at the next character is to retain the matched part of the + subject and try a new complete match. + + You can set the PCRE_PARTIAL_SOFT or PCRE_PARTIAL_HARD options with + PCRE_DFA_RESTART to continue partial matching over multiple segments. + This facility can be used to pass very long subject strings to the DFA + matching functions. + + +MULTI-SEGMENT MATCHING WITH pcre_exec() OR pcre[16|32]_exec() + + From release 8.00, the standard matching functions can also be used to + do multi-segment matching. Unlike the DFA functions, it is not possible + to restart the previous match with a new segment of data. Instead, new + data must be added to the previous subject string, and the entire match + re-run, starting from the point where the partial match occurred. Ear- + lier data can be discarded. + + It is best to use PCRE_PARTIAL_HARD in this situation, because it does + not treat the end of a segment as the end of the subject when matching + \z, \Z, \b, \B, and $. Consider an unanchored pattern that matches + dates: + + re> /\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d/ + data> The date is 23ja\P\P + Partial match: 23ja + + At this stage, an application could discard the text preceding "23ja", + add on text from the next segment, and call the matching function + again. Unlike the DFA matching functions, the entire matching string + must always be available, and the complete matching process occurs for + each call, so more memory and more processing time is needed. + + Note: If the pattern contains lookbehind assertions, or \K, or starts + with \b or \B, the string that is returned for a partial match includes + characters that precede the start of what would be returned for a com- + plete match, because it contains all the characters that were inspected + during the partial match. + + +ISSUES WITH MULTI-SEGMENT MATCHING + + Certain types of pattern may give problems with multi-segment matching, + whichever matching function is used. + + 1. If the pattern contains a test for the beginning of a line, you need + to pass the PCRE_NOTBOL option when the subject string for any call + does start at the beginning of a line. There is also a PCRE_NOTEOL + option, but in practice when doing multi-segment matching you should be + using PCRE_PARTIAL_HARD, which includes the effect of PCRE_NOTEOL. + + 2. Lookbehind assertions that have already been obeyed are catered for + in the offsets that are returned for a partial match. However a lookbe- + hind assertion later in the pattern could require even earlier charac- + ters to be inspected. You can handle this case by using the + PCRE_INFO_MAXLOOKBEHIND option of the pcre_fullinfo() or + pcre[16|32]_fullinfo() functions to obtain the length of the longest + lookbehind in the pattern. This length is given in characters, not + bytes. If you always retain at least that many characters before the + partially matched string, all should be well. (Of course, near the + start of the subject, fewer characters may be present; in that case all + characters should be retained.) + + From release 8.33, there is a more accurate way of deciding which char- + acters to retain. Instead of subtracting the length of the longest + lookbehind from the earliest inspected character (offsets[0]), the + match start position (offsets[2]) should be used, and the next match + attempt started at the offsets[2] character by setting the startoffset + argument of pcre_exec() or pcre_dfa_exec(). + + For example, if the pattern "(?<=123)abc" is partially matched against + the string "xx123a", the three offset values returned are 2, 6, and 5. + This indicates that the matching process that gave a partial match + started at offset 5, but the characters "123a" were all inspected. The + maximum lookbehind for that pattern is 3, so taking that away from 5 + shows that we need only keep "123a", and the next match attempt can be + started at offset 3 (that is, at "a") when further characters have been + added. When the match start is not the earliest inspected character, + pcretest shows it explicitly: + + re> "(?<=123)abc" + data> xx123a\P\P + Partial match at offset 5: 123a + + 3. Because a partial match must always contain at least one character, + what might be considered a partial match of an empty string actually + gives a "no match" result. For example: + + re> /c(?<=abc)x/ + data> ab\P + No match + + If the next segment begins "cx", a match should be found, but this will + only happen if characters from the previous segment are retained. For + this reason, a "no match" result should be interpreted as "partial + match of an empty string" when the pattern contains lookbehinds. + + 4. Matching a subject string that is split into multiple segments may + not always produce exactly the same result as matching over one single + long string, especially when PCRE_PARTIAL_SOFT is used. The section + "Partial Matching and Word Boundaries" above describes an issue that + arises if the pattern ends with \b or \B. Another kind of difference + may occur when there are multiple matching possibilities, because (for + PCRE_PARTIAL_SOFT) a partial match result is given only when there are + no completed matches. This means that as soon as the shortest match has + been found, continuation to a new subject segment is no longer possi- + ble. Consider again this pcretest example: + + re> /dog(sbody)?/ + data> dogsb\P + 0: dog + data> do\P\D + Partial match: do + data> gsb\R\P\D + 0: g + data> dogsbody\D + 0: dogsbody + 1: dog + + The first data line passes the string "dogsb" to a standard matching + function, setting the PCRE_PARTIAL_SOFT option. Although the string is + a partial match for "dogsbody", the result is not PCRE_ERROR_PARTIAL, + because the shorter string "dog" is a complete match. Similarly, when + the subject is presented to a DFA matching function in several parts + ("do" and "gsb" being the first two) the match stops when "dog" has + been found, and it is not possible to continue. On the other hand, if + "dogsbody" is presented as a single string, a DFA matching function + finds both matches. + + Because of these problems, it is best to use PCRE_PARTIAL_HARD when + matching multi-segment data. The example above then behaves differ- + ently: + + re> /dog(sbody)?/ + data> dogsb\P\P + Partial match: dogsb + data> do\P\D + Partial match: do + data> gsb\R\P\P\D + Partial match: gsb + + 5. Patterns that contain alternatives at the top level which do not all + start with the same pattern item may not work as expected when + PCRE_DFA_RESTART is used. For example, consider this pattern: + + 1234|3789 + + If the first part of the subject is "ABC123", a partial match of the + first alternative is found at offset 3. There is no partial match for + the second alternative, because such a match does not start at the same + point in the subject string. Attempting to continue with the string + "7890" does not yield a match because only those alternatives that + match at one point in the subject are remembered. The problem arises + because the start of the second alternative matches within the first + alternative. There is no problem with anchored patterns or patterns + such as: + + 1234|ABCD + + where no string can be a partial match for both alternatives. This is + not a problem if a standard matching function is used, because the + entire match has to be rerun each time: + + re> /1234|3789/ + data> ABC123\P\P + Partial match: 123 + data> 1237890 + 0: 3789 + + Of course, instead of using PCRE_DFA_RESTART, the same technique of re- + running the entire match can also be used with the DFA matching func- + tions. Another possibility is to work with two buffers. If a partial + match at offset n in the first buffer is followed by "no match" when + PCRE_DFA_RESTART is used on the second buffer, you can then try a new + match starting at offset n+1 in the first buffer. + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 02 July 2013 + Copyright (c) 1997-2013 University of Cambridge. +------------------------------------------------------------------------------ + + +PCREPRECOMPILE(3) Library Functions Manual PCREPRECOMPILE(3) + + + +NAME + PCRE - Perl-compatible regular expressions + +SAVING AND RE-USING PRECOMPILED PCRE PATTERNS + + If you are running an application that uses a large number of regular + expression patterns, it may be useful to store them in a precompiled + form instead of having to compile them every time the application is + run. If you are not using any private character tables (see the + pcre_maketables() documentation), this is relatively straightforward. + If you are using private tables, it is a little bit more complicated. + However, if you are using the just-in-time optimization feature, it is + not possible to save and reload the JIT data. + + If you save compiled patterns to a file, you can copy them to a differ- + ent host and run them there. If the two hosts have different endianness + (byte order), you should run the pcre[16|32]_pat- + tern_to_host_byte_order() function on the new host before trying to + match the pattern. The matching functions return PCRE_ERROR_BADENDIAN- + NESS if they detect a pattern with the wrong endianness. + + Compiling regular expressions with one version of PCRE for use with a + different version is not guaranteed to work and may cause crashes, and + saving and restoring a compiled pattern loses any JIT optimization + data. + + +SAVING A COMPILED PATTERN + + The value returned by pcre[16|32]_compile() points to a single block of + memory that holds the compiled pattern and associated data. You can + find the length of this block in bytes by calling + pcre[16|32]_fullinfo() with an argument of PCRE_INFO_SIZE. You can then + save the data in any appropriate manner. Here is sample code for the + 8-bit library that compiles a pattern and writes it to a file. It + assumes that the variable fd refers to a file that is open for output: + + int erroroffset, rc, size; + char *error; + pcre *re; + + re = pcre_compile("my pattern", 0, &error, &erroroffset, NULL); + if (re == NULL) { ... handle errors ... } + rc = pcre_fullinfo(re, NULL, PCRE_INFO_SIZE, &size); + if (rc < 0) { ... handle errors ... } + rc = fwrite(re, 1, size, fd); + if (rc != size) { ... handle errors ... } + + In this example, the bytes that comprise the compiled pattern are + copied exactly. Note that this is binary data that may contain any of + the 256 possible byte values. On systems that make a distinction + between binary and non-binary data, be sure that the file is opened for + binary output. + + If you want to write more than one pattern to a file, you will have to + devise a way of separating them. For binary data, preceding each pat- + tern with its length is probably the most straightforward approach. + Another possibility is to write out the data in hexadecimal instead of + binary, one pattern to a line. + + Saving compiled patterns in a file is only one possible way of storing + them for later use. They could equally well be saved in a database, or + in the memory of some daemon process that passes them via sockets to + the processes that want them. + + If the pattern has been studied, it is also possible to save the normal + study data in a similar way to the compiled pattern itself. However, if + the PCRE_STUDY_JIT_COMPILE was used, the just-in-time data that is cre- + ated cannot be saved because it is too dependent on the current envi- + ronment. When studying generates additional information, + pcre[16|32]_study() returns a pointer to a pcre[16|32]_extra data + block. Its format is defined in the section on matching a pattern in + the pcreapi documentation. The study_data field points to the binary + study data, and this is what you must save (not the pcre[16|32]_extra + block itself). The length of the study data can be obtained by calling + pcre[16|32]_fullinfo() with an argument of PCRE_INFO_STUDYSIZE. Remem- + ber to check that pcre[16|32]_study() did return a non-NULL value + before trying to save the study data. + + +RE-USING A PRECOMPILED PATTERN + + Re-using a precompiled pattern is straightforward. Having reloaded it + into main memory, called pcre[16|32]_pattern_to_host_byte_order() if + necessary, you pass its pointer to pcre[16|32]_exec() or + pcre[16|32]_dfa_exec() in the usual way. + + However, if you passed a pointer to custom character tables when the + pattern was compiled (the tableptr argument of pcre[16|32]_compile()), + you must now pass a similar pointer to pcre[16|32]_exec() or + pcre[16|32]_dfa_exec(), because the value saved with the compiled pat- + tern will obviously be nonsense. A field in a pcre[16|32]_extra() block + is used to pass this data, as described in the section on matching a + pattern in the pcreapi documentation. + + Warning: The tables that pcre_exec() and pcre_dfa_exec() use must be + the same as those that were used when the pattern was compiled. If this + is not the case, the behaviour is undefined. + + If you did not provide custom character tables when the pattern was + compiled, the pointer in the compiled pattern is NULL, which causes the + matching functions to use PCRE's internal tables. Thus, you do not need + to take any special action at run time in this case. + + If you saved study data with the compiled pattern, you need to create + your own pcre[16|32]_extra data block and set the study_data field to + point to the reloaded study data. You must also set the + PCRE_EXTRA_STUDY_DATA bit in the flags field to indicate that study + data is present. Then pass the pcre[16|32]_extra block to the matching + function in the usual way. If the pattern was studied for just-in-time + optimization, that data cannot be saved, and so is lost by a + save/restore cycle. + + +COMPATIBILITY WITH DIFFERENT PCRE RELEASES + + In general, it is safest to recompile all saved patterns when you + update to a new PCRE release, though not all updates actually require + this. + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 12 November 2013 + Copyright (c) 1997-2013 University of Cambridge. +------------------------------------------------------------------------------ + + +PCREPERFORM(3) Library Functions Manual PCREPERFORM(3) + + + +NAME + PCRE - Perl-compatible regular expressions + +PCRE PERFORMANCE + + Two aspects of performance are discussed below: memory usage and pro- + cessing time. The way you express your pattern as a regular expression + can affect both of them. + + +COMPILED PATTERN MEMORY USAGE + + Patterns are compiled by PCRE into a reasonably efficient interpretive + code, so that most simple patterns do not use much memory. However, + there is one case where the memory usage of a compiled pattern can be + unexpectedly large. If a parenthesized subpattern has a quantifier with + a minimum greater than 1 and/or a limited maximum, the whole subpattern + is repeated in the compiled code. For example, the pattern + + (abc|def){2,4} + + is compiled as if it were + + (abc|def)(abc|def)((abc|def)(abc|def)?)? + + (Technical aside: It is done this way so that backtrack points within + each of the repetitions can be independently maintained.) + + For regular expressions whose quantifiers use only small numbers, this + is not usually a problem. However, if the numbers are large, and par- + ticularly if such repetitions are nested, the memory usage can become + an embarrassment. For example, the very simple pattern + + ((ab){1,1000}c){1,3} + + uses 51K bytes when compiled using the 8-bit library. When PCRE is com- + piled with its default internal pointer size of two bytes, the size + limit on a compiled pattern is 64K data units, and this is reached with + the above pattern if the outer repetition is increased from 3 to 4. + PCRE can be compiled to use larger internal pointers and thus handle + larger compiled patterns, but it is better to try to rewrite your pat- + tern to use less memory if you can. + + One way of reducing the memory usage for such patterns is to make use + of PCRE's "subroutine" facility. Re-writing the above pattern as + + ((ab)(?2){0,999}c)(?1){0,2} + + reduces the memory requirements to 18K, and indeed it remains under 20K + even with the outer repetition increased to 100. However, this pattern + is not exactly equivalent, because the "subroutine" calls are treated + as atomic groups into which there can be no backtracking if there is a + subsequent matching failure. Therefore, PCRE cannot do this kind of + rewriting automatically. Furthermore, there is a noticeable loss of + speed when executing the modified pattern. Nevertheless, if the atomic + grouping is not a problem and the loss of speed is acceptable, this + kind of rewriting will allow you to process patterns that PCRE cannot + otherwise handle. + + +STACK USAGE AT RUN TIME + + When pcre_exec() or pcre[16|32]_exec() is used for matching, certain + kinds of pattern can cause it to use large amounts of the process + stack. In some environments the default process stack is quite small, + and if it runs out the result is often SIGSEGV. This issue is probably + the most frequently raised problem with PCRE. Rewriting your pattern + can often help. The pcrestack documentation discusses this issue in + detail. + + +PROCESSING TIME + + Certain items in regular expression patterns are processed more effi- + ciently than others. It is more efficient to use a character class like + [aeiou] than a set of single-character alternatives such as + (a|e|i|o|u). In general, the simplest construction that provides the + required behaviour is usually the most efficient. Jeffrey Friedl's book + contains a lot of useful general discussion about optimizing regular + expressions for efficient performance. This document contains a few + observations about PCRE. + + Using Unicode character properties (the \p, \P, and \X escapes) is + slow, because PCRE has to use a multi-stage table lookup whenever it + needs a character's property. If you can find an alternative pattern + that does not use character properties, it will probably be faster. + + By default, the escape sequences \b, \d, \s, and \w, and the POSIX + character classes such as [:alpha:] do not use Unicode properties, + partly for backwards compatibility, and partly for performance reasons. + However, you can set PCRE_UCP if you want Unicode character properties + to be used. This can double the matching time for items such as \d, + when matched with a traditional matching function; the performance loss + is less with a DFA matching function, and in both cases there is not + much difference for \b. + + When a pattern begins with .* not in parentheses, or in parentheses + that are not the subject of a backreference, and the PCRE_DOTALL option + is set, the pattern is implicitly anchored by PCRE, since it can match + only at the start of a subject string. However, if PCRE_DOTALL is not + set, PCRE cannot make this optimization, because the . metacharacter + does not then match a newline, and if the subject string contains new- + lines, the pattern may match from the character immediately following + one of them instead of from the very start. For example, the pattern + + .*second + + matches the subject "first\nand second" (where \n stands for a newline + character), with the match starting at the seventh character. In order + to do this, PCRE has to retry the match starting after every newline in + the subject. + + If you are using such a pattern with subject strings that do not con- + tain newlines, the best performance is obtained by setting PCRE_DOTALL, + or starting the pattern with ^.* or ^.*? to indicate explicit anchor- + ing. That saves PCRE from having to scan along the subject looking for + a newline to restart at. + + Beware of patterns that contain nested indefinite repeats. These can + take a long time to run when applied to a string that does not match. + Consider the pattern fragment + + ^(a+)* + + This can match "aaaa" in 16 different ways, and this number increases + very rapidly as the string gets longer. (The * repeat can match 0, 1, + 2, 3, or 4 times, and for each of those cases other than 0 or 4, the + + repeats can match different numbers of times.) When the remainder of + the pattern is such that the entire match is going to fail, PCRE has in + principle to try every possible variation, and this can take an + extremely long time, even for relatively short strings. + + An optimization catches some of the more simple cases such as + + (a+)*b + + where a literal character follows. Before embarking on the standard + matching procedure, PCRE checks that there is a "b" later in the sub- + ject string, and if there is not, it fails the match immediately. How- + ever, when there is no following literal this optimization cannot be + used. You can see the difference by comparing the behaviour of + + (a+)*\d + + with the pattern above. The former gives a failure almost instantly + when applied to a whole line of "a" characters, whereas the latter + takes an appreciable time with strings longer than about 20 characters. + + In many cases, the solution to this kind of performance issue is to use + an atomic group or a possessive quantifier. + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 25 August 2012 + Copyright (c) 1997-2012 University of Cambridge. +------------------------------------------------------------------------------ + + +PCREPOSIX(3) Library Functions Manual PCREPOSIX(3) + + + +NAME + PCRE - Perl-compatible regular expressions. + +SYNOPSIS + + #include <pcreposix.h> + + int regcomp(regex_t *preg, const char *pattern, + int cflags); + + int regexec(regex_t *preg, const char *string, + size_t nmatch, regmatch_t pmatch[], int eflags); + size_t regerror(int errcode, const regex_t *preg, + char *errbuf, size_t errbuf_size); + + void regfree(regex_t *preg); + + +DESCRIPTION + + This set of functions provides a POSIX-style API for the PCRE regular + expression 8-bit library. See the pcreapi documentation for a descrip- + tion of PCRE's native API, which contains much additional functional- + ity. There is no POSIX-style wrapper for PCRE's 16-bit and 32-bit + library. + + The functions described here are just wrapper functions that ultimately + call the PCRE native API. Their prototypes are defined in the + pcreposix.h header file, and on Unix systems the library itself is + called pcreposix.a, so can be accessed by adding -lpcreposix to the + command for linking an application that uses them. Because the POSIX + functions call the native ones, it is also necessary to add -lpcre. + + I have implemented only those POSIX option bits that can be reasonably + mapped to PCRE native options. In addition, the option REG_EXTENDED is + defined with the value zero. This has no effect, but since programs + that are written to the POSIX interface often use it, this makes it + easier to slot in PCRE as a replacement library. Other POSIX options + are not even defined. + + There are also some other options that are not defined by POSIX. These + have been added at the request of users who want to make use of certain + PCRE-specific features via the POSIX calling interface. + + When PCRE is called via these functions, it is only the API that is + POSIX-like in style. The syntax and semantics of the regular expres- + sions themselves are still those of Perl, subject to the setting of + various PCRE options, as described below. "POSIX-like in style" means + that the API approximates to the POSIX definition; it is not fully + POSIX-compatible, and in multi-byte encoding domains it is probably + even less compatible. + + The header for these functions is supplied as pcreposix.h to avoid any + potential clash with other POSIX libraries. It can, of course, be + renamed or aliased as regex.h, which is the "correct" name. It provides + two structure types, regex_t for compiled internal forms, and reg- + match_t for returning captured substrings. It also defines some con- + stants whose names start with "REG_"; these are used for setting + options and identifying error codes. + + +COMPILING A PATTERN + + The function regcomp() is called to compile a pattern into an internal + form. The pattern is a C string terminated by a binary zero, and is + passed in the argument pattern. The preg argument is a pointer to a + regex_t structure that is used as a base for storing information about + the compiled regular expression. + + The argument cflags is either zero, or contains one or more of the bits + defined by the following macros: + + REG_DOTALL + + The PCRE_DOTALL option is set when the regular expression is passed for + compilation to the native function. Note that REG_DOTALL is not part of + the POSIX standard. + + REG_ICASE + + The PCRE_CASELESS option is set when the regular expression is passed + for compilation to the native function. + + REG_NEWLINE + + The PCRE_MULTILINE option is set when the regular expression is passed + for compilation to the native function. Note that this does not mimic + the defined POSIX behaviour for REG_NEWLINE (see the following sec- + tion). + + REG_NOSUB + + The PCRE_NO_AUTO_CAPTURE option is set when the regular expression is + passed for compilation to the native function. In addition, when a pat- + tern that is compiled with this flag is passed to regexec() for match- + ing, the nmatch and pmatch arguments are ignored, and no captured + strings are returned. + + REG_UCP + + The PCRE_UCP option is set when the regular expression is passed for + compilation to the native function. This causes PCRE to use Unicode + properties when matchine \d, \w, etc., instead of just recognizing + ASCII values. Note that REG_UTF8 is not part of the POSIX standard. + + REG_UNGREEDY + + The PCRE_UNGREEDY option is set when the regular expression is passed + for compilation to the native function. Note that REG_UNGREEDY is not + part of the POSIX standard. + + REG_UTF8 + + The PCRE_UTF8 option is set when the regular expression is passed for + compilation to the native function. This causes the pattern itself and + all data strings used for matching it to be treated as UTF-8 strings. + Note that REG_UTF8 is not part of the POSIX standard. + + In the absence of these flags, no options are passed to the native + function. This means the the regex is compiled with PCRE default + semantics. In particular, the way it handles newline characters in the + subject string is the Perl way, not the POSIX way. Note that setting + PCRE_MULTILINE has only some of the effects specified for REG_NEWLINE. + It does not affect the way newlines are matched by . (they are not) or + by a negative class such as [^a] (they are). + + The yield of regcomp() is zero on success, and non-zero otherwise. The + preg structure is filled in on success, and one member of the structure + is public: re_nsub contains the number of capturing subpatterns in the + regular expression. Various error codes are defined in the header file. + + NOTE: If the yield of regcomp() is non-zero, you must not attempt to + use the contents of the preg structure. If, for example, you pass it to + regexec(), the result is undefined and your program is likely to crash. + + +MATCHING NEWLINE CHARACTERS + + This area is not simple, because POSIX and Perl take different views of + things. It is not possible to get PCRE to obey POSIX semantics, but + then PCRE was never intended to be a POSIX engine. The following table + lists the different possibilities for matching newline characters in + PCRE: + + Default Change with + + . matches newline no PCRE_DOTALL + newline matches [^a] yes not changeable + $ matches \n at end yes PCRE_DOLLARENDONLY + $ matches \n in middle no PCRE_MULTILINE + ^ matches \n in middle no PCRE_MULTILINE + + This is the equivalent table for POSIX: + + Default Change with + + . matches newline yes REG_NEWLINE + newline matches [^a] yes REG_NEWLINE + $ matches \n at end no REG_NEWLINE + $ matches \n in middle no REG_NEWLINE + ^ matches \n in middle no REG_NEWLINE + + PCRE's behaviour is the same as Perl's, except that there is no equiva- + lent for PCRE_DOLLAR_ENDONLY in Perl. In both PCRE and Perl, there is + no way to stop newline from matching [^a]. + + The default POSIX newline handling can be obtained by setting + PCRE_DOTALL and PCRE_DOLLAR_ENDONLY, but there is no way to make PCRE + behave exactly as for the REG_NEWLINE action. + + +MATCHING A PATTERN + + The function regexec() is called to match a compiled pattern preg + against a given string, which is by default terminated by a zero byte + (but see REG_STARTEND below), subject to the options in eflags. These + can be: + + REG_NOTBOL + + The PCRE_NOTBOL option is set when calling the underlying PCRE matching + function. + + REG_NOTEMPTY + + The PCRE_NOTEMPTY option is set when calling the underlying PCRE match- + ing function. Note that REG_NOTEMPTY is not part of the POSIX standard. + However, setting this option can give more POSIX-like behaviour in some + situations. + + REG_NOTEOL + + The PCRE_NOTEOL option is set when calling the underlying PCRE matching + function. + + REG_STARTEND + + The string is considered to start at string + pmatch[0].rm_so and to + have a terminating NUL located at string + pmatch[0].rm_eo (there need + not actually be a NUL at that location), regardless of the value of + nmatch. This is a BSD extension, compatible with but not specified by + IEEE Standard 1003.2 (POSIX.2), and should be used with caution in + software intended to be portable to other systems. Note that a non-zero + rm_so does not imply REG_NOTBOL; REG_STARTEND affects only the location + of the string, not how it is matched. + + If the pattern was compiled with the REG_NOSUB flag, no data about any + matched strings is returned. The nmatch and pmatch arguments of + regexec() are ignored. + + If the value of nmatch is zero, or if the value pmatch is NULL, no data + about any matched strings is returned. + + Otherwise,the portion of the string that was matched, and also any cap- + tured substrings, are returned via the pmatch argument, which points to + an array of nmatch structures of type regmatch_t, containing the mem- + bers rm_so and rm_eo. These contain the offset to the first character + of each substring and the offset to the first character after the end + of each substring, respectively. The 0th element of the vector relates + to the entire portion of string that was matched; subsequent elements + relate to the capturing subpatterns of the regular expression. Unused + entries in the array have both structure members set to -1. + + A successful match yields a zero return; various error codes are + defined in the header file, of which REG_NOMATCH is the "expected" + failure code. + + +ERROR MESSAGES + + The regerror() function maps a non-zero errorcode from either regcomp() + or regexec() to a printable message. If preg is not NULL, the error + should have arisen from the use of that structure. A message terminated + by a binary zero is placed in errbuf. The length of the message, + including the zero, is limited to errbuf_size. The yield of the func- + tion is the size of buffer needed to hold the whole message. + + +MEMORY USAGE + + Compiling a regular expression causes memory to be allocated and asso- + ciated with the preg structure. The function regfree() frees all such + memory, after which preg may no longer be used as a compiled expres- + sion. + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 09 January 2012 + Copyright (c) 1997-2012 University of Cambridge. +------------------------------------------------------------------------------ + + +PCRECPP(3) Library Functions Manual PCRECPP(3) + + + +NAME + PCRE - Perl-compatible regular expressions. + +SYNOPSIS OF C++ WRAPPER + + #include <pcrecpp.h> + + +DESCRIPTION + + The C++ wrapper for PCRE was provided by Google Inc. Some additional + functionality was added by Giuseppe Maxia. This brief man page was con- + structed from the notes in the pcrecpp.h file, which should be con- + sulted for further details. Note that the C++ wrapper supports only the + original 8-bit PCRE library. There is no 16-bit or 32-bit support at + present. + + +MATCHING INTERFACE + + The "FullMatch" operation checks that supplied text matches a supplied + pattern exactly. If pointer arguments are supplied, it copies matched + sub-strings that match sub-patterns into them. + + Example: successful match + pcrecpp::RE re("h.*o"); + re.FullMatch("hello"); + + Example: unsuccessful match (requires full match): + pcrecpp::RE re("e"); + !re.FullMatch("hello"); + + Example: creating a temporary RE object: + pcrecpp::RE("h.*o").FullMatch("hello"); + + You can pass in a "const char*" or a "string" for "text". The examples + below tend to use a const char*. You can, as in the different examples + above, store the RE object explicitly in a variable or use a temporary + RE object. The examples below use one mode or the other arbitrarily. + Either could correctly be used for any of these examples. + + You must supply extra pointer arguments to extract matched subpieces. + + Example: extracts "ruby" into "s" and 1234 into "i" + int i; + string s; + pcrecpp::RE re("(\\w+):(\\d+)"); + re.FullMatch("ruby:1234", &s, &i); + + Example: does not try to extract any extra sub-patterns + re.FullMatch("ruby:1234", &s); + + Example: does not try to extract into NULL + re.FullMatch("ruby:1234", NULL, &i); + + Example: integer overflow causes failure + !re.FullMatch("ruby:1234567891234", NULL, &i); + + Example: fails because there aren't enough sub-patterns: + !pcrecpp::RE("\\w+:\\d+").FullMatch("ruby:1234", &s); + + Example: fails because string cannot be stored in integer + !pcrecpp::RE("(.*)").FullMatch("ruby", &i); + + The provided pointer arguments can be pointers to any scalar numeric + type, or one of: + + string (matched piece is copied to string) + StringPiece (StringPiece is mutated to point to matched piece) + T (where "bool T::ParseFrom(const char*, int)" exists) + NULL (the corresponding matched sub-pattern is not copied) + + The function returns true iff all of the following conditions are sat- + isfied: + + a. "text" matches "pattern" exactly; + + b. The number of matched sub-patterns is >= number of supplied + pointers; + + c. The "i"th argument has a suitable type for holding the + string captured as the "i"th sub-pattern. If you pass in + void * NULL for the "i"th argument, or a non-void * NULL + of the correct type, or pass fewer arguments than the + number of sub-patterns, "i"th captured sub-pattern is + ignored. + + CAVEAT: An optional sub-pattern that does not exist in the matched + string is assigned the empty string. Therefore, the following will + return false (because the empty string is not a valid number): + + int number; + pcrecpp::RE::FullMatch("abc", "[a-z]+(\\d+)?", &number); + + The matching interface supports at most 16 arguments per call. If you + need more, consider using the more general interface + pcrecpp::RE::DoMatch. See pcrecpp.h for the signature for DoMatch. + + NOTE: Do not use no_arg, which is used internally to mark the end of a + list of optional arguments, as a placeholder for missing arguments, as + this can lead to segfaults. + + +QUOTING METACHARACTERS + + You can use the "QuoteMeta" operation to insert backslashes before all + potentially meaningful characters in a string. The returned string, + used as a regular expression, will exactly match the original string. + + Example: + string quoted = RE::QuoteMeta(unquoted); + + Note that it's legal to escape a character even if it has no special + meaning in a regular expression -- so this function does that. (This + also makes it identical to the perl function of the same name; see + "perldoc -f quotemeta".) For example, "1.5-2.0?" becomes + "1\.5\-2\.0\?". + + +PARTIAL MATCHES + + You can use the "PartialMatch" operation when you want the pattern to + match any substring of the text. + + Example: simple search for a string: + pcrecpp::RE("ell").PartialMatch("hello"); + + Example: find first number in a string: + int number; + pcrecpp::RE re("(\\d+)"); + re.PartialMatch("x*100 + 20", &number); + assert(number == 100); + + +UTF-8 AND THE MATCHING INTERFACE + + By default, pattern and text are plain text, one byte per character. + The UTF8 flag, passed to the constructor, causes both pattern and + string to be treated as UTF-8 text, still a byte stream but potentially + multiple bytes per character. In practice, the text is likelier to be + UTF-8 than the pattern, but the match returned may depend on the UTF8 + flag, so always use it when matching UTF8 text. For example, "." will + match one byte normally but with UTF8 set may match up to three bytes + of a multi-byte character. + + Example: + pcrecpp::RE_Options options; + options.set_utf8(); + pcrecpp::RE re(utf8_pattern, options); + re.FullMatch(utf8_string); + + Example: using the convenience function UTF8(): + pcrecpp::RE re(utf8_pattern, pcrecpp::UTF8()); + re.FullMatch(utf8_string); + + NOTE: The UTF8 flag is ignored if pcre was not configured with the + --enable-utf8 flag. + + +PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE + + PCRE defines some modifiers to change the behavior of the regular + expression engine. The C++ wrapper defines an auxiliary class, + RE_Options, as a vehicle to pass such modifiers to a RE class. Cur- + rently, the following modifiers are supported: + + modifier description Perl corresponding + + PCRE_CASELESS case insensitive match /i + PCRE_MULTILINE multiple lines match /m + PCRE_DOTALL dot matches newlines /s + PCRE_DOLLAR_ENDONLY $ matches only at end N/A + PCRE_EXTRA strict escape parsing N/A + PCRE_EXTENDED ignore white spaces /x + PCRE_UTF8 handles UTF8 chars built-in + PCRE_UNGREEDY reverses * and *? N/A + PCRE_NO_AUTO_CAPTURE disables capturing parens N/A (*) + + (*) Both Perl and PCRE allow non capturing parentheses by means of the + "?:" modifier within the pattern itself. e.g. (?:ab|cd) does not cap- + ture, while (ab|cd) does. + + For a full account on how each modifier works, please check the PCRE + API reference page. + + For each modifier, there are two member functions whose name is made + out of the modifier in lowercase, without the "PCRE_" prefix. For + instance, PCRE_CASELESS is handled by + + bool caseless() + + which returns true if the modifier is set, and + + RE_Options & set_caseless(bool) + + which sets or unsets the modifier. Moreover, PCRE_EXTRA_MATCH_LIMIT can + be accessed through the set_match_limit() and match_limit() member + functions. Setting match_limit to a non-zero value will limit the exe- + cution of pcre to keep it from doing bad things like blowing the stack + or taking an eternity to return a result. A value of 5000 is good + enough to stop stack blowup in a 2MB thread stack. Setting match_limit + to zero disables match limiting. Alternatively, you can call + match_limit_recursion() which uses PCRE_EXTRA_MATCH_LIMIT_RECURSION to + limit how much PCRE recurses. match_limit() limits the number of + matches PCRE does; match_limit_recursion() limits the depth of internal + recursion, and therefore the amount of stack that is used. + + Normally, to pass one or more modifiers to a RE class, you declare a + RE_Options object, set the appropriate options, and pass this object to + a RE constructor. Example: + + RE_Options opt; + opt.set_caseless(true); + if (RE("HELLO", opt).PartialMatch("hello world")) ... + + RE_options has two constructors. The default constructor takes no argu- + ments and creates a set of flags that are off by default. The optional + parameter option_flags is to facilitate transfer of legacy code from C + programs. This lets you do + + RE(pattern, + RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str); + + However, new code is better off doing + + RE(pattern, + RE_Options().set_caseless(true).set_multiline(true)) + .PartialMatch(str); + + If you are going to pass one of the most used modifiers, there are some + convenience functions that return a RE_Options class with the appropri- + ate modifier already set: CASELESS(), UTF8(), MULTILINE(), DOTALL(), + and EXTENDED(). + + If you need to set several options at once, and you don't want to go + through the pains of declaring a RE_Options object and setting several + options, there is a parallel method that give you such ability on the + fly. You can concatenate several set_xxxxx() member functions, since + each of them returns a reference to its class object. For example, to + pass PCRE_CASELESS, PCRE_EXTENDED, and PCRE_MULTILINE to a RE with one + statement, you may write: + + RE(" ^ xyz \\s+ .* blah$", + RE_Options() + .set_caseless(true) + .set_extended(true) + .set_multiline(true)).PartialMatch(sometext); + + +SCANNING TEXT INCREMENTALLY + + The "Consume" operation may be useful if you want to repeatedly match + regular expressions at the front of a string and skip over them as they + match. This requires use of the "StringPiece" type, which represents a + sub-range of a real string. Like RE, StringPiece is defined in the + pcrecpp namespace. + + Example: read lines of the form "var = value" from a string. + string contents = ...; // Fill string somehow + pcrecpp::StringPiece input(contents); // Wrap in a StringPiece + + string var; + int value; + pcrecpp::RE re("(\\w+) = (\\d+)\n"); + while (re.Consume(&input, &var, &value)) { + ...; + } + + Each successful call to "Consume" will set "var/value", and also + advance "input" so it points past the matched text. + + The "FindAndConsume" operation is similar to "Consume" but does not + anchor your match at the beginning of the string. For example, you + could extract all words from a string by repeatedly calling + + pcrecpp::RE("(\\w+)").FindAndConsume(&input, &word) + + +PARSING HEX/OCTAL/C-RADIX NUMBERS + + By default, if you pass a pointer to a numeric value, the corresponding + text is interpreted as a base-10 number. You can instead wrap the + pointer with a call to one of the operators Hex(), Octal(), or CRadix() + to interpret the text in another base. The CRadix operator interprets + C-style "0" (base-8) and "0x" (base-16) prefixes, but defaults to + base-10. + + Example: + int a, b, c, d; + pcrecpp::RE re("(.*) (.*) (.*) (.*)"); + re.FullMatch("100 40 0100 0x40", + pcrecpp::Octal(&a), pcrecpp::Hex(&b), + pcrecpp::CRadix(&c), pcrecpp::CRadix(&d)); + + will leave 64 in a, b, c, and d. + + +REPLACING PARTS OF STRINGS + + You can replace the first match of "pattern" in "str" with "rewrite". + Within "rewrite", backslash-escaped digits (\1 to \9) can be used to + insert text matching corresponding parenthesized group from the pat- + tern. \0 in "rewrite" refers to the entire matching text. For example: + + string s = "yabba dabba doo"; + pcrecpp::RE("b+").Replace("d", &s); + + will leave "s" containing "yada dabba doo". The result is true if the + pattern matches and a replacement occurs, false otherwise. + + GlobalReplace is like Replace except that it replaces all occurrences + of the pattern in the string with the rewrite. Replacements are not + subject to re-matching. For example: + + string s = "yabba dabba doo"; + pcrecpp::RE("b+").GlobalReplace("d", &s); + + will leave "s" containing "yada dada doo". It returns the number of + replacements made. + + Extract is like Replace, except that if the pattern matches, "rewrite" + is copied into "out" (an additional argument) with substitutions. The + non-matching portions of "text" are ignored. Returns true iff a match + occurred and the extraction happened successfully; if no match occurs, + the string is left unaffected. + + +AUTHOR + + The C++ wrapper was contributed by Google Inc. + Copyright (c) 2007 Google Inc. + + +REVISION + + Last updated: 08 January 2012 +------------------------------------------------------------------------------ + + +PCRESAMPLE(3) Library Functions Manual PCRESAMPLE(3) + + + +NAME + PCRE - Perl-compatible regular expressions + +PCRE SAMPLE PROGRAM + + A simple, complete demonstration program, to get you started with using + PCRE, is supplied in the file pcredemo.c in the PCRE distribution. A + listing of this program is given in the pcredemo documentation. If you + do not have a copy of the PCRE distribution, you can save this listing + to re-create pcredemo.c. + + The demonstration program, which uses the original PCRE 8-bit library, + compiles the regular expression that is its first argument, and matches + it against the subject string in its second argument. No PCRE options + are set, and default character tables are used. If matching succeeds, + the program outputs the portion of the subject that matched, together + with the contents of any captured substrings. + + If the -g option is given on the command line, the program then goes on + to check for further matches of the same regular expression in the same + subject string. The logic is a little bit tricky because of the possi- + bility of matching an empty string. Comments in the code explain what + is going on. + + If PCRE is installed in the standard include and library directories + for your operating system, you should be able to compile the demonstra- + tion program using this command: + + gcc -o pcredemo pcredemo.c -lpcre + + If PCRE is installed elsewhere, you may need to add additional options + to the command line. For example, on a Unix-like system that has PCRE + installed in /usr/local, you can compile the demonstration program + using a command like this: + + gcc -o pcredemo -I/usr/local/include pcredemo.c \ + -L/usr/local/lib -lpcre + + In a Windows environment, if you want to statically link the program + against a non-dll pcre.a file, you must uncomment the line that defines + PCRE_STATIC before including pcre.h, because otherwise the pcre_mal- + loc() and pcre_free() exported functions will be declared + __declspec(dllimport), with unwanted results. + + Once you have compiled and linked the demonstration program, you can + run simple tests like this: + + ./pcredemo 'cat|dog' 'the cat sat on the mat' + ./pcredemo -g 'cat|dog' 'the dog sat on the cat' + + Note that there is a much more comprehensive test program, called + pcretest, which supports many more facilities for testing regular + expressions and both PCRE libraries. The pcredemo program is provided + as a simple coding example. + + If you try to run pcredemo when PCRE is not installed in the standard + library directory, you may get an error like this on some operating + systems (e.g. Solaris): + + ld.so.1: a.out: fatal: libpcre.so.0: open failed: No such file or + directory + + This is caused by the way shared library support works on those sys- + tems. You need to add + + -R/usr/local/lib + + (for example) to the compile command to get round this problem. + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 10 January 2012 + Copyright (c) 1997-2012 University of Cambridge. +------------------------------------------------------------------------------ +PCRELIMITS(3) Library Functions Manual PCRELIMITS(3) + + + +NAME + PCRE - Perl-compatible regular expressions + +SIZE AND OTHER LIMITATIONS + + There are some size limitations in PCRE but it is hoped that they will + never in practice be relevant. + + The maximum length of a compiled pattern is approximately 64K data + units (bytes for the 8-bit library, 16-bit units for the 16-bit + library, and 32-bit units for the 32-bit library) if PCRE is compiled + with the default internal linkage size, which is 2 bytes for the 8-bit + and 16-bit libraries, and 4 bytes for the 32-bit library. If you want + to process regular expressions that are truly enormous, you can compile + PCRE with an internal linkage size of 3 or 4 (when building the 16-bit + or 32-bit library, 3 is rounded up to 4). See the README file in the + source distribution and the pcrebuild documentation for details. In + these cases the limit is substantially larger. However, the speed of + execution is slower. + + All values in repeating quantifiers must be less than 65536. + + There is no limit to the number of parenthesized subpatterns, but there + can be no more than 65535 capturing subpatterns. There is, however, a + limit to the depth of nesting of parenthesized subpatterns of all + kinds. This is imposed in order to limit the amount of system stack + used at compile time. The limit can be specified when PCRE is built; + the default is 250. + + There is a limit to the number of forward references to subsequent sub- + patterns of around 200,000. Repeated forward references with fixed + upper limits, for example, (?2){0,100} when subpattern number 2 is to + the right, are included in the count. There is no limit to the number + of backward references. + + The maximum length of name for a named subpattern is 32 characters, and + the maximum number of named subpatterns is 10000. + + The maximum length of a name in a (*MARK), (*PRUNE), (*SKIP), or + (*THEN) verb is 255 for the 8-bit library and 65535 for the 16-bit and + 32-bit libraries. + + The maximum length of a subject string is the largest positive number + that an integer variable can hold. However, when using the traditional + matching function, PCRE uses recursion to handle subpatterns and indef- + inite repetition. This means that the available stack space may limit + the size of a subject string that can be processed by certain patterns. + For a discussion of stack issues, see the pcrestack documentation. + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 05 November 2013 + Copyright (c) 1997-2013 University of Cambridge. +------------------------------------------------------------------------------ + + +PCRESTACK(3) Library Functions Manual PCRESTACK(3) + + + +NAME + PCRE - Perl-compatible regular expressions + +PCRE DISCUSSION OF STACK USAGE + + When you call pcre[16|32]_exec(), it makes use of an internal function + called match(). This calls itself recursively at branch points in the + pattern, in order to remember the state of the match so that it can + back up and try a different alternative if the first one fails. As + matching proceeds deeper and deeper into the tree of possibilities, the + recursion depth increases. The match() function is also called in other + circumstances, for example, whenever a parenthesized sub-pattern is + entered, and in certain cases of repetition. + + Not all calls of match() increase the recursion depth; for an item such + as a* it may be called several times at the same level, after matching + different numbers of a's. Furthermore, in a number of cases where the + result of the recursive call would immediately be passed back as the + result of the current call (a "tail recursion"), the function is just + restarted instead. + + The above comments apply when pcre[16|32]_exec() is run in its normal + interpretive manner. If the pattern was studied with the + PCRE_STUDY_JIT_COMPILE option, and just-in-time compiling was success- + ful, and the options passed to pcre[16|32]_exec() were not incompati- + ble, the matching process uses the JIT-compiled code instead of the + match() function. In this case, the memory requirements are handled + entirely differently. See the pcrejit documentation for details. + + The pcre[16|32]_dfa_exec() function operates in an entirely different + way, and uses recursion only when there is a regular expression recur- + sion or subroutine call in the pattern. This includes the processing of + assertion and "once-only" subpatterns, which are handled like subrou- + tine calls. Normally, these are never very deep, and the limit on the + complexity of pcre[16|32]_dfa_exec() is controlled by the amount of + workspace it is given. However, it is possible to write patterns with + runaway infinite recursions; such patterns will cause + pcre[16|32]_dfa_exec() to run out of stack. At present, there is no + protection against this. + + The comments that follow do NOT apply to pcre[16|32]_dfa_exec(); they + are relevant only for pcre[16|32]_exec() without the JIT optimization. + + Reducing pcre[16|32]_exec()'s stack usage + + Each time that match() is actually called recursively, it uses memory + from the process stack. For certain kinds of pattern and data, very + large amounts of stack may be needed, despite the recognition of "tail + recursion". You can often reduce the amount of recursion, and there- + fore the amount of stack used, by modifying the pattern that is being + matched. Consider, for example, this pattern: + + ([^<]|<(?!inet))+ + + It matches from wherever it starts until it encounters "<inet" or the + end of the data, and is the kind of pattern that might be used when + processing an XML file. Each iteration of the outer parentheses matches + either one character that is not "<" or a "<" that is not followed by + "inet". However, each time a parenthesis is processed, a recursion + occurs, so this formulation uses a stack frame for each matched charac- + ter. For a long string, a lot of stack is required. Consider now this + rewritten pattern, which matches exactly the same strings: + + ([^<]++|<(?!inet))+ + + This uses very much less stack, because runs of characters that do not + contain "<" are "swallowed" in one item inside the parentheses. Recur- + sion happens only when a "<" character that is not followed by "inet" + is encountered (and we assume this is relatively rare). A possessive + quantifier is used to stop any backtracking into the runs of non-"<" + characters, but that is not related to stack usage. + + This example shows that one way of avoiding stack problems when match- + ing long subject strings is to write repeated parenthesized subpatterns + to match more than one character whenever possible. + + Compiling PCRE to use heap instead of stack for pcre[16|32]_exec() + + In environments where stack memory is constrained, you might want to + compile PCRE to use heap memory instead of stack for remembering back- + up points when pcre[16|32]_exec() is running. This makes it run a lot + more slowly, however. Details of how to do this are given in the pcre- + build documentation. When built in this way, instead of using the + stack, PCRE obtains and frees memory by calling the functions that are + pointed to by the pcre[16|32]_stack_malloc and pcre[16|32]_stack_free + variables. By default, these point to malloc() and free(), but you can + replace the pointers to cause PCRE to use your own functions. Since the + block sizes are always the same, and are always freed in reverse order, + it may be possible to implement customized memory handlers that are + more efficient than the standard functions. + + Limiting pcre[16|32]_exec()'s stack usage + + You can set limits on the number of times that match() is called, both + in total and recursively. If a limit is exceeded, pcre[16|32]_exec() + returns an error code. Setting suitable limits should prevent it from + running out of stack. The default values of the limits are very large, + and unlikely ever to operate. They can be changed when PCRE is built, + and they can also be set when pcre[16|32]_exec() is called. For details + of these interfaces, see the pcrebuild documentation and the section on + extra data for pcre[16|32]_exec() in the pcreapi documentation. + + As a very rough rule of thumb, you should reckon on about 500 bytes per + recursion. Thus, if you want to limit your stack usage to 8Mb, you + should set the limit at 16000 recursions. A 64Mb stack, on the other + hand, can support around 128000 recursions. + + In Unix-like environments, the pcretest test program has a command line + option (-S) that can be used to increase the size of its stack. As long + as the stack is large enough, another option (-M) can be used to find + the smallest limits that allow a particular pattern to match a given + subject string. This is done by calling pcre[16|32]_exec() repeatedly + with different limits. + + Obtaining an estimate of stack usage + + The actual amount of stack used per recursion can vary quite a lot, + depending on the compiler that was used to build PCRE and the optimiza- + tion or debugging options that were set for it. The rule of thumb value + of 500 bytes mentioned above may be larger or smaller than what is + actually needed. A better approximation can be obtained by running this + command: + + pcretest -m -C + + The -C option causes pcretest to output information about the options + with which PCRE was compiled. When -m is also given (before -C), infor- + mation about stack use is given in a line like this: + + Match recursion uses stack: approximate frame size = 640 bytes + + The value is approximate because some recursions need a bit more (up to + perhaps 16 more bytes). + + If the above command is given when PCRE is compiled to use the heap + instead of the stack for recursion, the value that is output is the + size of each block that is obtained from the heap. + + Changing stack size in Unix-like systems + + In Unix-like environments, there is not often a problem with the stack + unless very long strings are involved, though the default limit on + stack size varies from system to system. Values from 8Mb to 64Mb are + common. You can find your default limit by running the command: + + ulimit -s + + Unfortunately, the effect of running out of stack is often SIGSEGV, + though sometimes a more explicit error message is given. You can nor- + mally increase the limit on stack size by code such as this: + + struct rlimit rlim; + getrlimit(RLIMIT_STACK, &rlim); + rlim.rlim_cur = 100*1024*1024; + setrlimit(RLIMIT_STACK, &rlim); + + This reads the current limits (soft and hard) using getrlimit(), then + attempts to increase the soft limit to 100Mb using setrlimit(). You + must do this before calling pcre[16|32]_exec(). + + Changing stack size in Mac OS X + + Using setrlimit(), as described above, should also work on Mac OS X. It + is also possible to set a stack size when linking a program. There is a + discussion about stack sizes in Mac OS X at this web site: + http://developer.apple.com/qa/qa2005/qa1419.html. + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 24 June 2012 + Copyright (c) 1997-2012 University of Cambridge. +------------------------------------------------------------------------------ + + diff --git a/plugins/Pcre16/docs/doc/pcre16.3 b/plugins/Pcre16/docs/doc/pcre16.3 new file mode 100644 index 0000000000..85126a6792 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre16.3 @@ -0,0 +1,371 @@ +.TH PCRE 3 "12 May 2013" "PCRE 8.33" +.SH NAME +PCRE - Perl-compatible regular expressions +.sp +.B #include <pcre.h> +. +. +.SH "PCRE 16-BIT API BASIC FUNCTIONS" +.rs +.sp +.nf +.B pcre16 *pcre16_compile(PCRE_SPTR16 \fIpattern\fP, int \fIoptions\fP, +.B " const char **\fIerrptr\fP, int *\fIerroffset\fP," +.B " const unsigned char *\fItableptr\fP);" +.sp +.B pcre16 *pcre16_compile2(PCRE_SPTR16 \fIpattern\fP, int \fIoptions\fP, +.B " int *\fIerrorcodeptr\fP," +.B " const char **\fIerrptr\fP, int *\fIerroffset\fP," +.B " const unsigned char *\fItableptr\fP);" +.sp +.B pcre16_extra *pcre16_study(const pcre16 *\fIcode\fP, int \fIoptions\fP, +.B " const char **\fIerrptr\fP);" +.sp +.B void pcre16_free_study(pcre16_extra *\fIextra\fP); +.sp +.B int pcre16_exec(const pcre16 *\fIcode\fP, "const pcre16_extra *\fIextra\fP," +.B " PCRE_SPTR16 \fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP," +.B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);" +.sp +.B int pcre16_dfa_exec(const pcre16 *\fIcode\fP, "const pcre16_extra *\fIextra\fP," +.B " PCRE_SPTR16 \fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP," +.B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP," +.B " int *\fIworkspace\fP, int \fIwscount\fP);" +.fi +. +. +.SH "PCRE 16-BIT API STRING EXTRACTION FUNCTIONS" +.rs +.sp +.nf +.B int pcre16_copy_named_substring(const pcre16 *\fIcode\fP, +.B " PCRE_SPTR16 \fIsubject\fP, int *\fIovector\fP," +.B " int \fIstringcount\fP, PCRE_SPTR16 \fIstringname\fP," +.B " PCRE_UCHAR16 *\fIbuffer\fP, int \fIbuffersize\fP);" +.sp +.B int pcre16_copy_substring(PCRE_SPTR16 \fIsubject\fP, int *\fIovector\fP, +.B " int \fIstringcount\fP, int \fIstringnumber\fP, PCRE_UCHAR16 *\fIbuffer\fP," +.B " int \fIbuffersize\fP);" +.sp +.B int pcre16_get_named_substring(const pcre16 *\fIcode\fP, +.B " PCRE_SPTR16 \fIsubject\fP, int *\fIovector\fP," +.B " int \fIstringcount\fP, PCRE_SPTR16 \fIstringname\fP," +.B " PCRE_SPTR16 *\fIstringptr\fP);" +.sp +.B int pcre16_get_stringnumber(const pcre16 *\fIcode\fP, +.B " PCRE_SPTR16 \fIname\fP); +.sp +.B int pcre16_get_stringtable_entries(const pcre16 *\fIcode\fP, +.B " PCRE_SPTR16 \fIname\fP, PCRE_UCHAR16 **\fIfirst\fP, PCRE_UCHAR16 **\fIlast\fP);" +.sp +.B int pcre16_get_substring(PCRE_SPTR16 \fIsubject\fP, int *\fIovector\fP, +.B " int \fIstringcount\fP, int \fIstringnumber\fP," +.B " PCRE_SPTR16 *\fIstringptr\fP);" +.sp +.B int pcre16_get_substring_list(PCRE_SPTR16 \fIsubject\fP, +.B " int *\fIovector\fP, int \fIstringcount\fP, PCRE_SPTR16 **\fIlistptr\fP);" +.sp +.B void pcre16_free_substring(PCRE_SPTR16 \fIstringptr\fP); +.sp +.B void pcre16_free_substring_list(PCRE_SPTR16 *\fIstringptr\fP); +.fi +. +. +.SH "PCRE 16-BIT API AUXILIARY FUNCTIONS" +.rs +.sp +.nf +.B pcre16_jit_stack *pcre16_jit_stack_alloc(int \fIstartsize\fP, int \fImaxsize\fP); +.sp +.B void pcre16_jit_stack_free(pcre16_jit_stack *\fIstack\fP); +.sp +.B void pcre16_assign_jit_stack(pcre16_extra *\fIextra\fP, +.B " pcre16_jit_callback \fIcallback\fP, void *\fIdata\fP);" +.sp +.B const unsigned char *pcre16_maketables(void); +.sp +.B int pcre16_fullinfo(const pcre16 *\fIcode\fP, "const pcre16_extra *\fIextra\fP," +.B " int \fIwhat\fP, void *\fIwhere\fP);" +.sp +.B int pcre16_refcount(pcre16 *\fIcode\fP, int \fIadjust\fP); +.sp +.B int pcre16_config(int \fIwhat\fP, void *\fIwhere\fP); +.sp +.B const char *pcre16_version(void); +.sp +.B int pcre16_pattern_to_host_byte_order(pcre16 *\fIcode\fP, +.B " pcre16_extra *\fIextra\fP, const unsigned char *\fItables\fP);" +.fi +. +. +.SH "PCRE 16-BIT API INDIRECTED FUNCTIONS" +.rs +.sp +.nf +.B void *(*pcre16_malloc)(size_t); +.sp +.B void (*pcre16_free)(void *); +.sp +.B void *(*pcre16_stack_malloc)(size_t); +.sp +.B void (*pcre16_stack_free)(void *); +.sp +.B int (*pcre16_callout)(pcre16_callout_block *); +.fi +. +. +.SH "PCRE 16-BIT API 16-BIT-ONLY FUNCTION" +.rs +.sp +.nf +.B int pcre16_utf16_to_host_byte_order(PCRE_UCHAR16 *\fIoutput\fP, +.B " PCRE_SPTR16 \fIinput\fP, int \fIlength\fP, int *\fIbyte_order\fP," +.B " int \fIkeep_boms\fP);" +.fi +. +. +.SH "THE PCRE 16-BIT LIBRARY" +.rs +.sp +Starting with release 8.30, it is possible to compile a PCRE library that +supports 16-bit character strings, including UTF-16 strings, as well as or +instead of the original 8-bit library. The majority of the work to make this +possible was done by Zoltan Herczeg. The two libraries contain identical sets +of functions, used in exactly the same way. Only the names of the functions and +the data types of their arguments and results are different. To avoid +over-complication and reduce the documentation maintenance load, most of the +PCRE documentation describes the 8-bit library, with only occasional references +to the 16-bit library. This page describes what is different when you use the +16-bit library. +.P +WARNING: A single application can be linked with both libraries, but you must +take care when processing any particular pattern to use functions from just one +library. For example, if you want to study a pattern that was compiled with +\fBpcre16_compile()\fP, you must do so with \fBpcre16_study()\fP, not +\fBpcre_study()\fP, and you must free the study data with +\fBpcre16_free_study()\fP. +. +. +.SH "THE HEADER FILE" +.rs +.sp +There is only one header file, \fBpcre.h\fP. It contains prototypes for all the +functions in all libraries, as well as definitions of flags, structures, error +codes, etc. +. +. +.SH "THE LIBRARY NAME" +.rs +.sp +In Unix-like systems, the 16-bit library is called \fBlibpcre16\fP, and can +normally be accesss by adding \fB-lpcre16\fP to the command for linking an +application that uses PCRE. +. +. +.SH "STRING TYPES" +.rs +.sp +In the 8-bit library, strings are passed to PCRE library functions as vectors +of bytes with the C type "char *". In the 16-bit library, strings are passed as +vectors of unsigned 16-bit quantities. The macro PCRE_UCHAR16 specifies an +appropriate data type, and PCRE_SPTR16 is defined as "const PCRE_UCHAR16 *". In +very many environments, "short int" is a 16-bit data type. When PCRE is built, +it defines PCRE_UCHAR16 as "unsigned short int", but checks that it really is a +16-bit data type. If it is not, the build fails with an error message telling +the maintainer to modify the definition appropriately. +. +. +.SH "STRUCTURE TYPES" +.rs +.sp +The types of the opaque structures that are used for compiled 16-bit patterns +and JIT stacks are \fBpcre16\fP and \fBpcre16_jit_stack\fP respectively. The +type of the user-accessible structure that is returned by \fBpcre16_study()\fP +is \fBpcre16_extra\fP, and the type of the structure that is used for passing +data to a callout function is \fBpcre16_callout_block\fP. These structures +contain the same fields, with the same names, as their 8-bit counterparts. The +only difference is that pointers to character strings are 16-bit instead of +8-bit types. +. +. +.SH "16-BIT FUNCTIONS" +.rs +.sp +For every function in the 8-bit library there is a corresponding function in +the 16-bit library with a name that starts with \fBpcre16_\fP instead of +\fBpcre_\fP. The prototypes are listed above. In addition, there is one extra +function, \fBpcre16_utf16_to_host_byte_order()\fP. This is a utility function +that converts a UTF-16 character string to host byte order if necessary. The +other 16-bit functions expect the strings they are passed to be in host byte +order. +.P +The \fIinput\fP and \fIoutput\fP arguments of +\fBpcre16_utf16_to_host_byte_order()\fP may point to the same address, that is, +conversion in place is supported. The output buffer must be at least as long as +the input. +.P +The \fIlength\fP argument specifies the number of 16-bit data units in the +input string; a negative value specifies a zero-terminated string. +.P +If \fIbyte_order\fP is NULL, it is assumed that the string starts off in host +byte order. This may be changed by byte-order marks (BOMs) anywhere in the +string (commonly as the first character). +.P +If \fIbyte_order\fP is not NULL, a non-zero value of the integer to which it +points means that the input starts off in host byte order, otherwise the +opposite order is assumed. Again, BOMs in the string can change this. The final +byte order is passed back at the end of processing. +.P +If \fIkeep_boms\fP is not zero, byte-order mark characters (0xfeff) are copied +into the output string. Otherwise they are discarded. +.P +The result of the function is the number of 16-bit units placed into the output +buffer, including the zero terminator if the string was zero-terminated. +. +. +.SH "SUBJECT STRING OFFSETS" +.rs +.sp +The lengths and starting offsets of subject strings must be specified in 16-bit +data units, and the offsets within subject strings that are returned by the +matching functions are in also 16-bit units rather than bytes. +. +. +.SH "NAMED SUBPATTERNS" +.rs +.sp +The name-to-number translation table that is maintained for named subpatterns +uses 16-bit characters. The \fBpcre16_get_stringtable_entries()\fP function +returns the length of each entry in the table as the number of 16-bit data +units. +. +. +.SH "OPTION NAMES" +.rs +.sp +There are two new general option names, PCRE_UTF16 and PCRE_NO_UTF16_CHECK, +which correspond to PCRE_UTF8 and PCRE_NO_UTF8_CHECK in the 8-bit library. In +fact, these new options define the same bits in the options word. There is a +discussion about the +.\" HTML <a href="pcreunicode.html#utf16strings"> +.\" </a> +validity of UTF-16 strings +.\" +in the +.\" HREF +\fBpcreunicode\fP +.\" +page. +.P +For the \fBpcre16_config()\fP function there is an option PCRE_CONFIG_UTF16 +that returns 1 if UTF-16 support is configured, otherwise 0. If this option is +given to \fBpcre_config()\fP or \fBpcre32_config()\fP, or if the +PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF32 option is given to \fBpcre16_config()\fP, +the result is the PCRE_ERROR_BADOPTION error. +. +. +.SH "CHARACTER CODES" +.rs +.sp +In 16-bit mode, when PCRE_UTF16 is not set, character values are treated in the +same way as in 8-bit, non UTF-8 mode, except, of course, that they can range +from 0 to 0xffff instead of 0 to 0xff. Character types for characters less than +0xff can therefore be influenced by the locale in the same way as before. +Characters greater than 0xff have only one case, and no "type" (such as letter +or digit). +.P +In UTF-16 mode, the character code is Unicode, in the range 0 to 0x10ffff, with +the exception of values in the range 0xd800 to 0xdfff because those are +"surrogate" values that are used in pairs to encode values greater than 0xffff. +.P +A UTF-16 string can indicate its endianness by special code knows as a +byte-order mark (BOM). The PCRE functions do not handle this, expecting strings +to be in host byte order. A utility function called +\fBpcre16_utf16_to_host_byte_order()\fP is provided to help with this (see +above). +. +. +.SH "ERROR NAMES" +.rs +.sp +The errors PCRE_ERROR_BADUTF16_OFFSET and PCRE_ERROR_SHORTUTF16 correspond to +their 8-bit counterparts. The error PCRE_ERROR_BADMODE is given when a compiled +pattern is passed to a function that processes patterns in the other +mode, for example, if a pattern compiled with \fBpcre_compile()\fP is passed to +\fBpcre16_exec()\fP. +.P +There are new error codes whose names begin with PCRE_UTF16_ERR for invalid +UTF-16 strings, corresponding to the PCRE_UTF8_ERR codes for UTF-8 strings that +are described in the section entitled +.\" HTML <a href="pcreapi.html#badutf8reasons"> +.\" </a> +"Reason codes for invalid UTF-8 strings" +.\" +in the main +.\" HREF +\fBpcreapi\fP +.\" +page. The UTF-16 errors are: +.sp + PCRE_UTF16_ERR1 Missing low surrogate at end of string + PCRE_UTF16_ERR2 Invalid low surrogate follows high surrogate + PCRE_UTF16_ERR3 Isolated low surrogate + PCRE_UTF16_ERR4 Non-character +. +. +.SH "ERROR TEXTS" +.rs +.sp +If there is an error while compiling a pattern, the error text that is passed +back by \fBpcre16_compile()\fP or \fBpcre16_compile2()\fP is still an 8-bit +character string, zero-terminated. +. +. +.SH "CALLOUTS" +.rs +.sp +The \fIsubject\fP and \fImark\fP fields in the callout block that is passed to +a callout function point to 16-bit vectors. +. +. +.SH "TESTING" +.rs +.sp +The \fBpcretest\fP program continues to operate with 8-bit input and output +files, but it can be used for testing the 16-bit library. If it is run with the +command line option \fB-16\fP, patterns and subject strings are converted from +8-bit to 16-bit before being passed to PCRE, and the 16-bit library functions +are used instead of the 8-bit ones. Returned 16-bit strings are converted to +8-bit for output. If both the 8-bit and the 32-bit libraries were not compiled, +\fBpcretest\fP defaults to 16-bit and the \fB-16\fP option is ignored. +.P +When PCRE is being built, the \fBRunTest\fP script that is called by "make +check" uses the \fBpcretest\fP \fB-C\fP option to discover which of the 8-bit, +16-bit and 32-bit libraries has been built, and runs the tests appropriately. +. +. +.SH "NOT SUPPORTED IN 16-BIT MODE" +.rs +.sp +Not all the features of the 8-bit library are available with the 16-bit +library. The C++ and POSIX wrapper functions support only the 8-bit library, +and the \fBpcregrep\fP program is at present 8-bit only. +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 12 May 2013 +Copyright (c) 1997-2013 University of Cambridge. +.fi diff --git a/plugins/Pcre16/docs/doc/pcre32.3 b/plugins/Pcre16/docs/doc/pcre32.3 new file mode 100644 index 0000000000..7cde8c0877 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre32.3 @@ -0,0 +1,369 @@ +.TH PCRE 3 "12 May 2013" "PCRE 8.33" +.SH NAME +PCRE - Perl-compatible regular expressions +.sp +.B #include <pcre.h> +. +. +.SH "PCRE 32-BIT API BASIC FUNCTIONS" +.rs +.sp +.nf +.B pcre32 *pcre32_compile(PCRE_SPTR32 \fIpattern\fP, int \fIoptions\fP, +.B " const char **\fIerrptr\fP, int *\fIerroffset\fP," +.B " const unsigned char *\fItableptr\fP);" +.sp +.B pcre32 *pcre32_compile2(PCRE_SPTR32 \fIpattern\fP, int \fIoptions\fP, +.B " int *\fIerrorcodeptr\fP," +.B " const unsigned char *\fItableptr\fP);" +.sp +.B pcre32_extra *pcre32_study(const pcre32 *\fIcode\fP, int \fIoptions\fP, +.B " const char **\fIerrptr\fP);" +.sp +.B void pcre32_free_study(pcre32_extra *\fIextra\fP); +.sp +.B int pcre32_exec(const pcre32 *\fIcode\fP, "const pcre32_extra *\fIextra\fP," +.B " PCRE_SPTR32 \fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP," +.B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);" +.sp +.B int pcre32_dfa_exec(const pcre32 *\fIcode\fP, "const pcre32_extra *\fIextra\fP," +.B " PCRE_SPTR32 \fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP," +.B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP," +.B " int *\fIworkspace\fP, int \fIwscount\fP);" +.fi +. +. +.SH "PCRE 32-BIT API STRING EXTRACTION FUNCTIONS" +.rs +.sp +.nf +.B int pcre32_copy_named_substring(const pcre32 *\fIcode\fP, +.B " PCRE_SPTR32 \fIsubject\fP, int *\fIovector\fP," +.B " int \fIstringcount\fP, PCRE_SPTR32 \fIstringname\fP," +.B " PCRE_UCHAR32 *\fIbuffer\fP, int \fIbuffersize\fP);" +.sp +.B int pcre32_copy_substring(PCRE_SPTR32 \fIsubject\fP, int *\fIovector\fP, +.B " int \fIstringcount\fP, int \fIstringnumber\fP, PCRE_UCHAR32 *\fIbuffer\fP," +.B " int \fIbuffersize\fP);" +.sp +.B int pcre32_get_named_substring(const pcre32 *\fIcode\fP, +.B " PCRE_SPTR32 \fIsubject\fP, int *\fIovector\fP," +.B " int \fIstringcount\fP, PCRE_SPTR32 \fIstringname\fP," +.B " PCRE_SPTR32 *\fIstringptr\fP);" +.sp +.B int pcre32_get_stringnumber(const pcre32 *\fIcode\fP, +.B " PCRE_SPTR32 \fIname\fP);" +.sp +.B int pcre32_get_stringtable_entries(const pcre32 *\fIcode\fP, +.B " PCRE_SPTR32 \fIname\fP, PCRE_UCHAR32 **\fIfirst\fP, PCRE_UCHAR32 **\fIlast\fP);" +.sp +.B int pcre32_get_substring(PCRE_SPTR32 \fIsubject\fP, int *\fIovector\fP, +.B " int \fIstringcount\fP, int \fIstringnumber\fP," +.B " PCRE_SPTR32 *\fIstringptr\fP);" +.sp +.B int pcre32_get_substring_list(PCRE_SPTR32 \fIsubject\fP, +.B " int *\fIovector\fP, int \fIstringcount\fP, PCRE_SPTR32 **\fIlistptr\fP);" +.sp +.B void pcre32_free_substring(PCRE_SPTR32 \fIstringptr\fP); +.sp +.B void pcre32_free_substring_list(PCRE_SPTR32 *\fIstringptr\fP); +.fi +. +. +.SH "PCRE 32-BIT API AUXILIARY FUNCTIONS" +.rs +.sp +.nf +.B pcre32_jit_stack *pcre32_jit_stack_alloc(int \fIstartsize\fP, int \fImaxsize\fP); +.sp +.B void pcre32_jit_stack_free(pcre32_jit_stack *\fIstack\fP); +.sp +.B void pcre32_assign_jit_stack(pcre32_extra *\fIextra\fP, +.B " pcre32_jit_callback \fIcallback\fP, void *\fIdata\fP);" +.sp +.B const unsigned char *pcre32_maketables(void); +.sp +.B int pcre32_fullinfo(const pcre32 *\fIcode\fP, "const pcre32_extra *\fIextra\fP," +.B " int \fIwhat\fP, void *\fIwhere\fP);" +.sp +.B int pcre32_refcount(pcre32 *\fIcode\fP, int \fIadjust\fP); +.sp +.B int pcre32_config(int \fIwhat\fP, void *\fIwhere\fP); +.sp +.B const char *pcre32_version(void); +.sp +.B int pcre32_pattern_to_host_byte_order(pcre32 *\fIcode\fP, +.B " pcre32_extra *\fIextra\fP, const unsigned char *\fItables\fP);" +.fi +. +. +.SH "PCRE 32-BIT API INDIRECTED FUNCTIONS" +.rs +.sp +.nf +.B void *(*pcre32_malloc)(size_t); +.sp +.B void (*pcre32_free)(void *); +.sp +.B void *(*pcre32_stack_malloc)(size_t); +.sp +.B void (*pcre32_stack_free)(void *); +.sp +.B int (*pcre32_callout)(pcre32_callout_block *); +.fi +. +. +.SH "PCRE 32-BIT API 32-BIT-ONLY FUNCTION" +.rs +.sp +.nf +.B int pcre32_utf32_to_host_byte_order(PCRE_UCHAR32 *\fIoutput\fP, +.B " PCRE_SPTR32 \fIinput\fP, int \fIlength\fP, int *\fIbyte_order\fP," +.B " int \fIkeep_boms\fP);" +.fi +. +. +.SH "THE PCRE 32-BIT LIBRARY" +.rs +.sp +Starting with release 8.32, it is possible to compile a PCRE library that +supports 32-bit character strings, including UTF-32 strings, as well as or +instead of the original 8-bit library. This work was done by Christian Persch, +based on the work done by Zoltan Herczeg for the 16-bit library. All three +libraries contain identical sets of functions, used in exactly the same way. +Only the names of the functions and the data types of their arguments and +results are different. To avoid over-complication and reduce the documentation +maintenance load, most of the PCRE documentation describes the 8-bit library, +with only occasional references to the 16-bit and 32-bit libraries. This page +describes what is different when you use the 32-bit library. +.P +WARNING: A single application can be linked with all or any of the three +libraries, but you must take care when processing any particular pattern +to use functions from just one library. For example, if you want to study +a pattern that was compiled with \fBpcre32_compile()\fP, you must do so +with \fBpcre32_study()\fP, not \fBpcre_study()\fP, and you must free the +study data with \fBpcre32_free_study()\fP. +. +. +.SH "THE HEADER FILE" +.rs +.sp +There is only one header file, \fBpcre.h\fP. It contains prototypes for all the +functions in all libraries, as well as definitions of flags, structures, error +codes, etc. +. +. +.SH "THE LIBRARY NAME" +.rs +.sp +In Unix-like systems, the 32-bit library is called \fBlibpcre32\fP, and can +normally be accesss by adding \fB-lpcre32\fP to the command for linking an +application that uses PCRE. +. +. +.SH "STRING TYPES" +.rs +.sp +In the 8-bit library, strings are passed to PCRE library functions as vectors +of bytes with the C type "char *". In the 32-bit library, strings are passed as +vectors of unsigned 32-bit quantities. The macro PCRE_UCHAR32 specifies an +appropriate data type, and PCRE_SPTR32 is defined as "const PCRE_UCHAR32 *". In +very many environments, "unsigned int" is a 32-bit data type. When PCRE is +built, it defines PCRE_UCHAR32 as "unsigned int", but checks that it really is +a 32-bit data type. If it is not, the build fails with an error message telling +the maintainer to modify the definition appropriately. +. +. +.SH "STRUCTURE TYPES" +.rs +.sp +The types of the opaque structures that are used for compiled 32-bit patterns +and JIT stacks are \fBpcre32\fP and \fBpcre32_jit_stack\fP respectively. The +type of the user-accessible structure that is returned by \fBpcre32_study()\fP +is \fBpcre32_extra\fP, and the type of the structure that is used for passing +data to a callout function is \fBpcre32_callout_block\fP. These structures +contain the same fields, with the same names, as their 8-bit counterparts. The +only difference is that pointers to character strings are 32-bit instead of +8-bit types. +. +. +.SH "32-BIT FUNCTIONS" +.rs +.sp +For every function in the 8-bit library there is a corresponding function in +the 32-bit library with a name that starts with \fBpcre32_\fP instead of +\fBpcre_\fP. The prototypes are listed above. In addition, there is one extra +function, \fBpcre32_utf32_to_host_byte_order()\fP. This is a utility function +that converts a UTF-32 character string to host byte order if necessary. The +other 32-bit functions expect the strings they are passed to be in host byte +order. +.P +The \fIinput\fP and \fIoutput\fP arguments of +\fBpcre32_utf32_to_host_byte_order()\fP may point to the same address, that is, +conversion in place is supported. The output buffer must be at least as long as +the input. +.P +The \fIlength\fP argument specifies the number of 32-bit data units in the +input string; a negative value specifies a zero-terminated string. +.P +If \fIbyte_order\fP is NULL, it is assumed that the string starts off in host +byte order. This may be changed by byte-order marks (BOMs) anywhere in the +string (commonly as the first character). +.P +If \fIbyte_order\fP is not NULL, a non-zero value of the integer to which it +points means that the input starts off in host byte order, otherwise the +opposite order is assumed. Again, BOMs in the string can change this. The final +byte order is passed back at the end of processing. +.P +If \fIkeep_boms\fP is not zero, byte-order mark characters (0xfeff) are copied +into the output string. Otherwise they are discarded. +.P +The result of the function is the number of 32-bit units placed into the output +buffer, including the zero terminator if the string was zero-terminated. +. +. +.SH "SUBJECT STRING OFFSETS" +.rs +.sp +The lengths and starting offsets of subject strings must be specified in 32-bit +data units, and the offsets within subject strings that are returned by the +matching functions are in also 32-bit units rather than bytes. +. +. +.SH "NAMED SUBPATTERNS" +.rs +.sp +The name-to-number translation table that is maintained for named subpatterns +uses 32-bit characters. The \fBpcre32_get_stringtable_entries()\fP function +returns the length of each entry in the table as the number of 32-bit data +units. +. +. +.SH "OPTION NAMES" +.rs +.sp +There are two new general option names, PCRE_UTF32 and PCRE_NO_UTF32_CHECK, +which correspond to PCRE_UTF8 and PCRE_NO_UTF8_CHECK in the 8-bit library. In +fact, these new options define the same bits in the options word. There is a +discussion about the +.\" HTML <a href="pcreunicode.html#utf32strings"> +.\" </a> +validity of UTF-32 strings +.\" +in the +.\" HREF +\fBpcreunicode\fP +.\" +page. +.P +For the \fBpcre32_config()\fP function there is an option PCRE_CONFIG_UTF32 +that returns 1 if UTF-32 support is configured, otherwise 0. If this option is +given to \fBpcre_config()\fP or \fBpcre16_config()\fP, or if the +PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF16 option is given to \fBpcre32_config()\fP, +the result is the PCRE_ERROR_BADOPTION error. +. +. +.SH "CHARACTER CODES" +.rs +.sp +In 32-bit mode, when PCRE_UTF32 is not set, character values are treated in the +same way as in 8-bit, non UTF-8 mode, except, of course, that they can range +from 0 to 0x7fffffff instead of 0 to 0xff. Character types for characters less +than 0xff can therefore be influenced by the locale in the same way as before. +Characters greater than 0xff have only one case, and no "type" (such as letter +or digit). +.P +In UTF-32 mode, the character code is Unicode, in the range 0 to 0x10ffff, with +the exception of values in the range 0xd800 to 0xdfff because those are +"surrogate" values that are ill-formed in UTF-32. +.P +A UTF-32 string can indicate its endianness by special code knows as a +byte-order mark (BOM). The PCRE functions do not handle this, expecting strings +to be in host byte order. A utility function called +\fBpcre32_utf32_to_host_byte_order()\fP is provided to help with this (see +above). +. +. +.SH "ERROR NAMES" +.rs +.sp +The error PCRE_ERROR_BADUTF32 corresponds to its 8-bit counterpart. +The error PCRE_ERROR_BADMODE is given when a compiled +pattern is passed to a function that processes patterns in the other +mode, for example, if a pattern compiled with \fBpcre_compile()\fP is passed to +\fBpcre32_exec()\fP. +.P +There are new error codes whose names begin with PCRE_UTF32_ERR for invalid +UTF-32 strings, corresponding to the PCRE_UTF8_ERR codes for UTF-8 strings that +are described in the section entitled +.\" HTML <a href="pcreapi.html#badutf8reasons"> +.\" </a> +"Reason codes for invalid UTF-8 strings" +.\" +in the main +.\" HREF +\fBpcreapi\fP +.\" +page. The UTF-32 errors are: +.sp + PCRE_UTF32_ERR1 Surrogate character (range from 0xd800 to 0xdfff) + PCRE_UTF32_ERR2 Non-character + PCRE_UTF32_ERR3 Character > 0x10ffff +. +. +.SH "ERROR TEXTS" +.rs +.sp +If there is an error while compiling a pattern, the error text that is passed +back by \fBpcre32_compile()\fP or \fBpcre32_compile2()\fP is still an 8-bit +character string, zero-terminated. +. +. +.SH "CALLOUTS" +.rs +.sp +The \fIsubject\fP and \fImark\fP fields in the callout block that is passed to +a callout function point to 32-bit vectors. +. +. +.SH "TESTING" +.rs +.sp +The \fBpcretest\fP program continues to operate with 8-bit input and output +files, but it can be used for testing the 32-bit library. If it is run with the +command line option \fB-32\fP, patterns and subject strings are converted from +8-bit to 32-bit before being passed to PCRE, and the 32-bit library functions +are used instead of the 8-bit ones. Returned 32-bit strings are converted to +8-bit for output. If both the 8-bit and the 16-bit libraries were not compiled, +\fBpcretest\fP defaults to 32-bit and the \fB-32\fP option is ignored. +.P +When PCRE is being built, the \fBRunTest\fP script that is called by "make +check" uses the \fBpcretest\fP \fB-C\fP option to discover which of the 8-bit, +16-bit and 32-bit libraries has been built, and runs the tests appropriately. +. +. +.SH "NOT SUPPORTED IN 32-BIT MODE" +.rs +.sp +Not all the features of the 8-bit library are available with the 32-bit +library. The C++ and POSIX wrapper functions support only the 8-bit library, +and the \fBpcregrep\fP program is at present 8-bit only. +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 12 May 2013 +Copyright (c) 1997-2013 University of Cambridge. +.fi diff --git a/plugins/Pcre16/docs/doc/pcre_assign_jit_stack.3 b/plugins/Pcre16/docs/doc/pcre_assign_jit_stack.3 new file mode 100644 index 0000000000..0ecf6f2c60 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_assign_jit_stack.3 @@ -0,0 +1,59 @@ +.TH PCRE_ASSIGN_JIT_STACK 3 "24 June 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.nf +.B void pcre_assign_jit_stack(pcre_extra *\fIextra\fP, +.B " pcre_jit_callback \fIcallback\fP, void *\fIdata\fP);" +.sp +.B void pcre16_assign_jit_stack(pcre16_extra *\fIextra\fP, +.B " pcre16_jit_callback \fIcallback\fP, void *\fIdata\fP);" +.sp +.B void pcre32_assign_jit_stack(pcre32_extra *\fIextra\fP, +.B " pcre32_jit_callback \fIcallback\fP, void *\fIdata\fP);" +.fi +. +.SH DESCRIPTION +.rs +.sp +This function provides control over the memory used as a stack at run-time by a +call to \fBpcre[16|32]_exec()\fP with a pattern that has been successfully +compiled with JIT optimization. The arguments are: +.sp + extra the data pointer returned by \fBpcre[16|32]_study()\fP + callback a callback function + data a JIT stack or a value to be passed to the callback + function +.P +If \fIcallback\fP is NULL and \fIdata\fP is NULL, an internal 32K block on +the machine stack is used. +.P +If \fIcallback\fP is NULL and \fIdata\fP is not NULL, \fIdata\fP must +be a valid JIT stack, the result of calling \fBpcre[16|32]_jit_stack_alloc()\fP. +.P +If \fIcallback\fP not NULL, it is called with \fIdata\fP as an argument at +the start of matching, in order to set up a JIT stack. If the result is NULL, +the internal 32K stack is used; otherwise the return value must be a valid JIT +stack, the result of calling \fBpcre[16|32]_jit_stack_alloc()\fP. +.P +You may safely assign the same JIT stack to multiple patterns, as long as they +are all matched in the same thread. In a multithread application, each thread +must use its own JIT stack. For more details, see the +.\" HREF +\fBpcrejit\fP +.\" +page. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_compile.3 b/plugins/Pcre16/docs/doc/pcre_compile.3 new file mode 100644 index 0000000000..5c16ebe26d --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_compile.3 @@ -0,0 +1,96 @@ +.TH PCRE_COMPILE 3 "01 October 2013" "PCRE 8.34" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.nf +.B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP, +.B " const char **\fIerrptr\fP, int *\fIerroffset\fP," +.B " const unsigned char *\fItableptr\fP);" +.sp +.B pcre16 *pcre16_compile(PCRE_SPTR16 \fIpattern\fP, int \fIoptions\fP, +.B " const char **\fIerrptr\fP, int *\fIerroffset\fP," +.B " const unsigned char *\fItableptr\fP);" +.sp +.B pcre32 *pcre32_compile(PCRE_SPTR32 \fIpattern\fP, int \fIoptions\fP, +.B " const char **\fIerrptr\fP, int *\fIerroffset\fP," +.B " const unsigned char *\fItableptr\fP);" +.fi +. +.SH DESCRIPTION +.rs +.sp +This function compiles a regular expression into an internal form. It is the +same as \fBpcre[16|32]_compile2()\fP, except for the absence of the +\fIerrorcodeptr\fP argument. Its arguments are: +.sp + \fIpattern\fP A zero-terminated string containing the + regular expression to be compiled + \fIoptions\fP Zero or more option bits + \fIerrptr\fP Where to put an error message + \fIerroffset\fP Offset in pattern where error was found + \fItableptr\fP Pointer to character tables, or NULL to + use the built-in default +.sp +The option bits are: +.sp + PCRE_ANCHORED Force pattern anchoring + PCRE_AUTO_CALLOUT Compile automatic callouts + PCRE_BSR_ANYCRLF \eR matches only CR, LF, or CRLF + PCRE_BSR_UNICODE \eR matches all Unicode line endings + PCRE_CASELESS Do caseless matching + PCRE_DOLLAR_ENDONLY $ not to match newline at end + PCRE_DOTALL . matches anything including NL + PCRE_DUPNAMES Allow duplicate names for subpatterns + PCRE_EXTENDED Ignore white space and # comments + PCRE_EXTRA PCRE extra features + (not much use currently) + PCRE_FIRSTLINE Force matching to be before newline + PCRE_JAVASCRIPT_COMPAT JavaScript compatibility + PCRE_MULTILINE ^ and $ match newlines within data + PCRE_NEVER_UTF Lock out UTF, e.g. via (*UTF) + PCRE_NEWLINE_ANY Recognize any Unicode newline sequence + PCRE_NEWLINE_ANYCRLF Recognize CR, LF, and CRLF as newline + sequences + PCRE_NEWLINE_CR Set CR as the newline sequence + PCRE_NEWLINE_CRLF Set CRLF as the newline sequence + PCRE_NEWLINE_LF Set LF as the newline sequence + PCRE_NO_AUTO_CAPTURE Disable numbered capturing paren- + theses (named ones available) + PCRE_NO_AUTO_POSSESS Disable auto-possessification + PCRE_NO_START_OPTIMIZE Disable match-time start optimizations + PCRE_NO_UTF16_CHECK Do not check the pattern for UTF-16 + validity (only relevant if + PCRE_UTF16 is set) + PCRE_NO_UTF32_CHECK Do not check the pattern for UTF-32 + validity (only relevant if + PCRE_UTF32 is set) + PCRE_NO_UTF8_CHECK Do not check the pattern for UTF-8 + validity (only relevant if + PCRE_UTF8 is set) + PCRE_UCP Use Unicode properties for \ed, \ew, etc. + PCRE_UNGREEDY Invert greediness of quantifiers + PCRE_UTF16 Run in \fBpcre16_compile()\fP UTF-16 mode + PCRE_UTF32 Run in \fBpcre32_compile()\fP UTF-32 mode + PCRE_UTF8 Run in \fBpcre_compile()\fP UTF-8 mode +.sp +PCRE must be built with UTF support in order to use PCRE_UTF8/16/32 and +PCRE_NO_UTF8/16/32_CHECK, and with UCP support if PCRE_UCP is used. +.P +The yield of the function is a pointer to a private data structure that +contains the compiled pattern, or NULL if an error was detected. Note that +compiling regular expressions with one version of PCRE for use with a different +version is not guaranteed to work and may cause crashes. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_compile2.3 b/plugins/Pcre16/docs/doc/pcre_compile2.3 new file mode 100644 index 0000000000..377420180e --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_compile2.3 @@ -0,0 +1,101 @@ +.TH PCRE_COMPILE2 3 "01 October 2013" "PCRE 8.34" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.nf +.B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP, +.B " int *\fIerrorcodeptr\fP," +.B " const char **\fIerrptr\fP, int *\fIerroffset\fP," +.B " const unsigned char *\fItableptr\fP);" +.sp +.B pcre16 *pcre16_compile2(PCRE_SPTR16 \fIpattern\fP, int \fIoptions\fP, +.B " int *\fIerrorcodeptr\fP," +.B " const char **\fIerrptr\fP, int *\fIerroffset\fP," +.B " const unsigned char *\fItableptr\fP);" +.sp +.B pcre32 *pcre32_compile2(PCRE_SPTR32 \fIpattern\fP, int \fIoptions\fP, +.B " int *\fIerrorcodeptr\fP,£ +.B " const char **\fIerrptr\fP, int *\fIerroffset\fP," +.B " const unsigned char *\fItableptr\fP);" +.fi +. +.SH DESCRIPTION +.rs +.sp +This function compiles a regular expression into an internal form. It is the +same as \fBpcre[16|32]_compile()\fP, except for the addition of the +\fIerrorcodeptr\fP argument. The arguments are: +. +.sp + \fIpattern\fP A zero-terminated string containing the + regular expression to be compiled + \fIoptions\fP Zero or more option bits + \fIerrorcodeptr\fP Where to put an error code + \fIerrptr\fP Where to put an error message + \fIerroffset\fP Offset in pattern where error was found + \fItableptr\fP Pointer to character tables, or NULL to + use the built-in default +.sp +The option bits are: +.sp + PCRE_ANCHORED Force pattern anchoring + PCRE_AUTO_CALLOUT Compile automatic callouts + PCRE_BSR_ANYCRLF \eR matches only CR, LF, or CRLF + PCRE_BSR_UNICODE \eR matches all Unicode line endings + PCRE_CASELESS Do caseless matching + PCRE_DOLLAR_ENDONLY $ not to match newline at end + PCRE_DOTALL . matches anything including NL + PCRE_DUPNAMES Allow duplicate names for subpatterns + PCRE_EXTENDED Ignore white space and # comments + PCRE_EXTRA PCRE extra features + (not much use currently) + PCRE_FIRSTLINE Force matching to be before newline + PCRE_JAVASCRIPT_COMPAT JavaScript compatibility + PCRE_MULTILINE ^ and $ match newlines within data + PCRE_NEVER_UTF Lock out UTF, e.g. via (*UTF) + PCRE_NEWLINE_ANY Recognize any Unicode newline sequence + PCRE_NEWLINE_ANYCRLF Recognize CR, LF, and CRLF as newline + sequences + PCRE_NEWLINE_CR Set CR as the newline sequence + PCRE_NEWLINE_CRLF Set CRLF as the newline sequence + PCRE_NEWLINE_LF Set LF as the newline sequence + PCRE_NO_AUTO_CAPTURE Disable numbered capturing paren- + theses (named ones available) + PCRE_NO_AUTO_POSSESS Disable auto-possessification + PCRE_NO_START_OPTIMIZE Disable match-time start optimizations + PCRE_NO_UTF16_CHECK Do not check the pattern for UTF-16 + validity (only relevant if + PCRE_UTF16 is set) + PCRE_NO_UTF32_CHECK Do not check the pattern for UTF-32 + validity (only relevant if + PCRE_UTF32 is set) + PCRE_NO_UTF8_CHECK Do not check the pattern for UTF-8 + validity (only relevant if + PCRE_UTF8 is set) + PCRE_UCP Use Unicode properties for \ed, \ew, etc. + PCRE_UNGREEDY Invert greediness of quantifiers + PCRE_UTF16 Run \fBpcre16_compile()\fP in UTF-16 mode + PCRE_UTF32 Run \fBpcre32_compile()\fP in UTF-32 mode + PCRE_UTF8 Run \fBpcre_compile()\fP in UTF-8 mode +.sp +PCRE must be built with UTF support in order to use PCRE_UTF8/16/32 and +PCRE_NO_UTF8/16/32_CHECK, and with UCP support if PCRE_UCP is used. +.P +The yield of the function is a pointer to a private data structure that +contains the compiled pattern, or NULL if an error was detected. Note that +compiling regular expressions with one version of PCRE for use with a different +version is not guaranteed to work and may cause crashes. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_config.3 b/plugins/Pcre16/docs/doc/pcre_config.3 new file mode 100644 index 0000000000..d3de14bb73 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_config.3 @@ -0,0 +1,77 @@ +.TH PCRE_CONFIG 3 "05 November 2013" "PCRE 8.34" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.SM +.B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP); +.PP +.B int pcre16_config(int \fIwhat\fP, void *\fIwhere\fP); +.PP +.B int pcre32_config(int \fIwhat\fP, void *\fIwhere\fP); +. +.SH DESCRIPTION +.rs +.sp +This function makes it possible for a client program to find out which optional +features are available in the version of the PCRE library it is using. The +arguments are as follows: +.sp + \fIwhat\fP A code specifying what information is required + \fIwhere\fP Points to where to put the data +.sp +The \fIwhere\fP argument must point to an integer variable, except for +PCRE_CONFIG_MATCH_LIMIT and PCRE_CONFIG_MATCH_LIMIT_RECURSION, when it must +point to an unsigned long integer. The available codes are: +.sp + PCRE_CONFIG_JIT Availability of just-in-time compiler + support (1=yes 0=no) + PCRE_CONFIG_JITTARGET String containing information about the + target architecture for the JIT compiler, + or NULL if there is no JIT support + PCRE_CONFIG_LINK_SIZE Internal link size: 2, 3, or 4 + PCRE_CONFIG_PARENS_LIMIT Parentheses nesting limit + PCRE_CONFIG_MATCH_LIMIT Internal resource limit + PCRE_CONFIG_MATCH_LIMIT_RECURSION + Internal recursion depth limit + PCRE_CONFIG_NEWLINE Value of the default newline sequence: + 13 (0x000d) for CR + 10 (0x000a) for LF + 3338 (0x0d0a) for CRLF + -2 for ANYCRLF + -1 for ANY + PCRE_CONFIG_BSR Indicates what \eR matches by default: + 0 all Unicode line endings + 1 CR, LF, or CRLF only + PCRE_CONFIG_POSIX_MALLOC_THRESHOLD + Threshold of return slots, above which + \fBmalloc()\fP is used by the POSIX API + PCRE_CONFIG_STACKRECURSE Recursion implementation (1=stack 0=heap) + PCRE_CONFIG_UTF16 Availability of UTF-16 support (1=yes + 0=no); option for \fBpcre16_config()\fP + PCRE_CONFIG_UTF32 Availability of UTF-32 support (1=yes + 0=no); option for \fBpcre32_config()\fP + PCRE_CONFIG_UTF8 Availability of UTF-8 support (1=yes 0=no); + option for \fBpcre_config()\fP + PCRE_CONFIG_UNICODE_PROPERTIES + Availability of Unicode property support + (1=yes 0=no) +.sp +The function yields 0 on success or PCRE_ERROR_BADOPTION otherwise. That error +is also given if PCRE_CONFIG_UTF16 or PCRE_CONFIG_UTF32 is passed to +\fBpcre_config()\fP, if PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF32 is passed to +\fBpcre16_config()\fP, or if PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF16 is passed to +\fBpcre32_config()\fP. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_copy_named_substring.3 b/plugins/Pcre16/docs/doc/pcre_copy_named_substring.3 new file mode 100644 index 0000000000..52582aecb2 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_copy_named_substring.3 @@ -0,0 +1,51 @@ +.TH PCRE_COPY_NAMED_SUBSTRING 3 "24 June 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.nf +.B int pcre_copy_named_substring(const pcre *\fIcode\fP, +.B " const char *\fIsubject\fP, int *\fIovector\fP," +.B " int \fIstringcount\fP, const char *\fIstringname\fP," +.B " char *\fIbuffer\fP, int \fIbuffersize\fP);" +.sp +.B int pcre16_copy_named_substring(const pcre16 *\fIcode\fP, +.B " PCRE_SPTR16 \fIsubject\fP, int *\fIovector\fP," +.B " int \fIstringcount\fP, PCRE_SPTR16 \fIstringname\fP," +.B " PCRE_UCHAR16 *\fIbuffer\fP, int \fIbuffersize\fP);" +.sp +.B int pcre32_copy_named_substring(const pcre32 *\fIcode\fP, +.B " PCRE_SPTR32 \fIsubject\fP, int *\fIovector\fP," +.B " int \fIstringcount\fP, PCRE_SPTR32 \fIstringname\fP," +.B " PCRE_UCHAR32 *\fIbuffer\fP, int \fIbuffersize\fP);" +.fi +. +.SH DESCRIPTION +.rs +.sp +This is a convenience function for extracting a captured substring, identified +by name, into a given buffer. The arguments are: +.sp + \fIcode\fP Pattern that was successfully matched + \fIsubject\fP Subject that has been successfully matched + \fIovector\fP Offset vector that \fBpcre[16|32]_exec()\fP used + \fIstringcount\fP Value returned by \fBpcre[16|32]_exec()\fP + \fIstringname\fP Name of the required substring + \fIbuffer\fP Buffer to receive the string + \fIbuffersize\fP Size of buffer +.sp +The yield is the length of the substring, PCRE_ERROR_NOMEMORY if the buffer was +too small, or PCRE_ERROR_NOSUBSTRING if the string name is invalid. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_copy_substring.3 b/plugins/Pcre16/docs/doc/pcre_copy_substring.3 new file mode 100644 index 0000000000..83af6e800a --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_copy_substring.3 @@ -0,0 +1,47 @@ +.TH PCRE_COPY_SUBSTRING 3 "24 June 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.nf +.B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP, +.B " int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP," +.B " int \fIbuffersize\fP);" +.sp +.B int pcre16_copy_substring(PCRE_SPTR16 \fIsubject\fP, int *\fIovector\fP, +.B " int \fIstringcount\fP, int \fIstringnumber\fP, PCRE_UCHAR16 *\fIbuffer\fP," +.B " int \fIbuffersize\fP);" +.sp +.B int pcre32_copy_substring(PCRE_SPTR32 \fIsubject\fP, int *\fIovector\fP, +.B " int \fIstringcount\fP, int \fIstringnumber\fP, PCRE_UCHAR32 *\fIbuffer\fP," +.B " int \fIbuffersize\fP);" +.fi +. +.SH DESCRIPTION +.rs +.sp +This is a convenience function for extracting a captured substring into a given +buffer. The arguments are: +.sp + \fIsubject\fP Subject that has been successfully matched + \fIovector\fP Offset vector that \fBpcre[16|32]_exec()\fP used + \fIstringcount\fP Value returned by \fBpcre[16|32]_exec()\fP + \fIstringnumber\fP Number of the required substring + \fIbuffer\fP Buffer to receive the string + \fIbuffersize\fP Size of buffer +.sp +The yield is the length of the string, PCRE_ERROR_NOMEMORY if the buffer was +too small, or PCRE_ERROR_NOSUBSTRING if the string number is invalid. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_dfa_exec.3 b/plugins/Pcre16/docs/doc/pcre_dfa_exec.3 new file mode 100644 index 0000000000..39c2e836da --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_dfa_exec.3 @@ -0,0 +1,118 @@ +.TH PCRE_DFA_EXEC 3 "12 May 2013" "PCRE 8.33" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.nf +.B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," +.B " const char *\fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP," +.B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP," +.B " int *\fIworkspace\fP, int \fIwscount\fP);" +.sp +.B int pcre16_dfa_exec(const pcre16 *\fIcode\fP, "const pcre16_extra *\fIextra\fP," +.B " PCRE_SPTR16 \fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP," +.B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP," +.B " int *\fIworkspace\fP, int \fIwscount\fP);" +.sp +.B int pcre32_dfa_exec(const pcre32 *\fIcode\fP, "const pcre32_extra *\fIextra\fP," +.B " PCRE_SPTR32 \fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP," +.B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP," +.B " int *\fIworkspace\fP, int \fIwscount\fP);" +.fi +. +.SH DESCRIPTION +.rs +.sp +This function matches a compiled regular expression against a given subject +string, using an alternative matching algorithm that scans the subject string +just once (\fInot\fP Perl-compatible). Note that the main, Perl-compatible, +matching function is \fBpcre[16|32]_exec()\fP. The arguments for this function +are: +.sp + \fIcode\fP Points to the compiled pattern + \fIextra\fP Points to an associated \fBpcre[16|32]_extra\fP structure, + or is NULL + \fIsubject\fP Points to the subject string + \fIlength\fP Length of the subject string + \fIstartoffset\fP Offset in the subject at which to start matching + \fIoptions\fP Option bits + \fIovector\fP Points to a vector of ints for result offsets + \fIovecsize\fP Number of elements in the vector + \fIworkspace\fP Points to a vector of ints used as working space + \fIwscount\fP Number of elements in the vector +.sp +The units for \fIlength\fP and \fIstartoffset\fP are bytes for +\fBpcre_exec()\fP, 16-bit data items for \fBpcre16_exec()\fP, and 32-bit items +for \fBpcre32_exec()\fP. The options are: +.sp + PCRE_ANCHORED Match only at the first position + PCRE_BSR_ANYCRLF \eR matches only CR, LF, or CRLF + PCRE_BSR_UNICODE \eR matches all Unicode line endings + PCRE_NEWLINE_ANY Recognize any Unicode newline sequence + PCRE_NEWLINE_ANYCRLF Recognize CR, LF, & CRLF as newline sequences + PCRE_NEWLINE_CR Recognize CR as the only newline sequence + PCRE_NEWLINE_CRLF Recognize CRLF as the only newline sequence + PCRE_NEWLINE_LF Recognize LF as the only newline sequence + PCRE_NOTBOL Subject is not the beginning of a line + PCRE_NOTEOL Subject is not the end of a line + PCRE_NOTEMPTY An empty string is not a valid match + PCRE_NOTEMPTY_ATSTART An empty string at the start of the subject + is not a valid match + PCRE_NO_START_OPTIMIZE Do not do "start-match" optimizations + PCRE_NO_UTF16_CHECK Do not check the subject for UTF-16 + validity (only relevant if PCRE_UTF16 + was set at compile time) + PCRE_NO_UTF32_CHECK Do not check the subject for UTF-32 + validity (only relevant if PCRE_UTF32 + was set at compile time) + PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8 + validity (only relevant if PCRE_UTF8 + was set at compile time) + PCRE_PARTIAL ) Return PCRE_ERROR_PARTIAL for a partial + PCRE_PARTIAL_SOFT ) match if no full matches are found + PCRE_PARTIAL_HARD Return PCRE_ERROR_PARTIAL for a partial match + even if there is a full match as well + PCRE_DFA_SHORTEST Return only the shortest match + PCRE_DFA_RESTART Restart after a partial match +.sp +There are restrictions on what may appear in a pattern when using this matching +function. Details are given in the +.\" HREF +\fBpcrematching\fP +.\" +documentation. For details of partial matching, see the +.\" HREF +\fBpcrepartial\fP +.\" +page. +.P +A \fBpcre[16|32]_extra\fP structure contains the following fields: +.sp + \fIflags\fP Bits indicating which fields are set + \fIstudy_data\fP Opaque data from \fBpcre[16|32]_study()\fP + \fImatch_limit\fP Limit on internal resource use + \fImatch_limit_recursion\fP Limit on internal recursion depth + \fIcallout_data\fP Opaque data passed back to callouts + \fItables\fP Points to character tables or is NULL + \fImark\fP For passing back a *MARK pointer + \fIexecutable_jit\fP Opaque data from JIT compilation +.sp +The flag bits are PCRE_EXTRA_STUDY_DATA, PCRE_EXTRA_MATCH_LIMIT, +PCRE_EXTRA_MATCH_LIMIT_RECURSION, PCRE_EXTRA_CALLOUT_DATA, +PCRE_EXTRA_TABLES, PCRE_EXTRA_MARK and PCRE_EXTRA_EXECUTABLE_JIT. For this +matching function, the \fImatch_limit\fP and \fImatch_limit_recursion\fP fields +are not used, and must not be set. The PCRE_EXTRA_EXECUTABLE_JIT flag and +the corresponding variable are ignored. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_exec.3 b/plugins/Pcre16/docs/doc/pcre_exec.3 new file mode 100644 index 0000000000..4686bd6de0 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_exec.3 @@ -0,0 +1,99 @@ +.TH PCRE_EXEC 3 "12 May 2013" "PCRE 8.33" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.nf +.B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," +.B " const char *\fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP," +.B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);" +.sp +.B int pcre16_exec(const pcre16 *\fIcode\fP, "const pcre16_extra *\fIextra\fP," +.B " PCRE_SPTR16 \fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP," +.B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);" +.sp +.B int pcre32_exec(const pcre32 *\fIcode\fP, "const pcre32_extra *\fIextra\fP," +.B " PCRE_SPTR32 \fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP," +.B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);" +.fi +. +.SH DESCRIPTION +.rs +.sp +This function matches a compiled regular expression against a given subject +string, using a matching algorithm that is similar to Perl's. It returns +offsets to captured substrings. Its arguments are: +.sp + \fIcode\fP Points to the compiled pattern + \fIextra\fP Points to an associated \fBpcre[16|32]_extra\fP structure, + or is NULL + \fIsubject\fP Points to the subject string + \fIlength\fP Length of the subject string + \fIstartoffset\fP Offset in the subject at which to start matching + \fIoptions\fP Option bits + \fIovector\fP Points to a vector of ints for result offsets + \fIovecsize\fP Number of elements in the vector (a multiple of 3) +.sp +The units for \fIlength\fP and \fIstartoffset\fP are bytes for +\fBpcre_exec()\fP, 16-bit data items for \fBpcre16_exec()\fP, and 32-bit items +for \fBpcre32_exec()\fP. The options are: +.sp + PCRE_ANCHORED Match only at the first position + PCRE_BSR_ANYCRLF \eR matches only CR, LF, or CRLF + PCRE_BSR_UNICODE \eR matches all Unicode line endings + PCRE_NEWLINE_ANY Recognize any Unicode newline sequence + PCRE_NEWLINE_ANYCRLF Recognize CR, LF, & CRLF as newline sequences + PCRE_NEWLINE_CR Recognize CR as the only newline sequence + PCRE_NEWLINE_CRLF Recognize CRLF as the only newline sequence + PCRE_NEWLINE_LF Recognize LF as the only newline sequence + PCRE_NOTBOL Subject string is not the beginning of a line + PCRE_NOTEOL Subject string is not the end of a line + PCRE_NOTEMPTY An empty string is not a valid match + PCRE_NOTEMPTY_ATSTART An empty string at the start of the subject + is not a valid match + PCRE_NO_START_OPTIMIZE Do not do "start-match" optimizations + PCRE_NO_UTF16_CHECK Do not check the subject for UTF-16 + validity (only relevant if PCRE_UTF16 + was set at compile time) + PCRE_NO_UTF32_CHECK Do not check the subject for UTF-32 + validity (only relevant if PCRE_UTF32 + was set at compile time) + PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8 + validity (only relevant if PCRE_UTF8 + was set at compile time) + PCRE_PARTIAL ) Return PCRE_ERROR_PARTIAL for a partial + PCRE_PARTIAL_SOFT ) match if no full matches are found + PCRE_PARTIAL_HARD Return PCRE_ERROR_PARTIAL for a partial match + if that is found before a full match +.sp +For details of partial matching, see the +.\" HREF +\fBpcrepartial\fP +.\" +page. A \fBpcre_extra\fP structure contains the following fields: +.sp + \fIflags\fP Bits indicating which fields are set + \fIstudy_data\fP Opaque data from \fBpcre[16|32]_study()\fP + \fImatch_limit\fP Limit on internal resource use + \fImatch_limit_recursion\fP Limit on internal recursion depth + \fIcallout_data\fP Opaque data passed back to callouts + \fItables\fP Points to character tables or is NULL + \fImark\fP For passing back a *MARK pointer + \fIexecutable_jit\fP Opaque data from JIT compilation +.sp +The flag bits are PCRE_EXTRA_STUDY_DATA, PCRE_EXTRA_MATCH_LIMIT, +PCRE_EXTRA_MATCH_LIMIT_RECURSION, PCRE_EXTRA_CALLOUT_DATA, +PCRE_EXTRA_TABLES, PCRE_EXTRA_MARK and PCRE_EXTRA_EXECUTABLE_JIT. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_free_study.3 b/plugins/Pcre16/docs/doc/pcre_free_study.3 new file mode 100644 index 0000000000..8826b73597 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_free_study.3 @@ -0,0 +1,31 @@ +.TH PCRE_FREE_STUDY 3 "24 June 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.SM +.B void pcre_free_study(pcre_extra *\fIextra\fP); +.PP +.B void pcre16_free_study(pcre16_extra *\fIextra\fP); +.PP +.B void pcre32_free_study(pcre32_extra *\fIextra\fP); +. +.SH DESCRIPTION +.rs +.sp +This function is used to free the memory used for the data generated by a call +to \fBpcre[16|32]_study()\fP when it is no longer needed. The argument must be the +result of such a call. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_free_substring.3 b/plugins/Pcre16/docs/doc/pcre_free_substring.3 new file mode 100644 index 0000000000..88c04019f4 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_free_substring.3 @@ -0,0 +1,31 @@ +.TH PCRE_FREE_SUBSTRING 3 "24 June 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.SM +.B void pcre_free_substring(const char *\fIstringptr\fP); +.PP +.B void pcre16_free_substring(PCRE_SPTR16 \fIstringptr\fP); +.PP +.B void pcre32_free_substring(PCRE_SPTR32 \fIstringptr\fP); +. +.SH DESCRIPTION +.rs +.sp +This is a convenience function for freeing the store obtained by a previous +call to \fBpcre[16|32]_get_substring()\fP or \fBpcre[16|32]_get_named_substring()\fP. +Its only argument is a pointer to the string. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_free_substring_list.3 b/plugins/Pcre16/docs/doc/pcre_free_substring_list.3 new file mode 100644 index 0000000000..248b4bd01b --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_free_substring_list.3 @@ -0,0 +1,31 @@ +.TH PCRE_FREE_SUBSTRING_LIST 3 "24 June 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.SM +.B void pcre_free_substring_list(const char **\fIstringptr\fP); +.PP +.B void pcre16_free_substring_list(PCRE_SPTR16 *\fIstringptr\fP); +.PP +.B void pcre32_free_substring_list(PCRE_SPTR32 *\fIstringptr\fP); +. +.SH DESCRIPTION +.rs +.sp +This is a convenience function for freeing the store obtained by a previous +call to \fBpcre[16|32]_get_substring_list()\fP. Its only argument is a pointer to +the list of string pointers. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_fullinfo.3 b/plugins/Pcre16/docs/doc/pcre_fullinfo.3 new file mode 100644 index 0000000000..01e2e92874 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_fullinfo.3 @@ -0,0 +1,93 @@ +.TH PCRE_FULLINFO 3 "24 June 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.nf +.B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," +.B " int \fIwhat\fP, void *\fIwhere\fP);" +.sp +.B int pcre16_fullinfo(const pcre16 *\fIcode\fP, "const pcre16_extra *\fIextra\fP," +.B " int \fIwhat\fP, void *\fIwhere\fP);" +.sp +.B int pcre32_fullinfo(const pcre32 *\fIcode\fP, "const pcre32_extra *\fIextra\fP," +.B " int \fIwhat\fP, void *\fIwhere\fP);" +.fi +. +.SH DESCRIPTION +.rs +.sp +This function returns information about a compiled pattern. Its arguments are: +.sp + \fIcode\fP Compiled regular expression + \fIextra\fP Result of \fBpcre[16|32]_study()\fP or NULL + \fIwhat\fP What information is required + \fIwhere\fP Where to put the information +.sp +The following information is available: +.sp + PCRE_INFO_BACKREFMAX Number of highest back reference + PCRE_INFO_CAPTURECOUNT Number of capturing subpatterns + PCRE_INFO_DEFAULT_TABLES Pointer to default tables + PCRE_INFO_FIRSTBYTE Fixed first data unit for a match, or + -1 for start of string + or after newline, or + -2 otherwise + PCRE_INFO_FIRSTTABLE Table of first data units (after studying) + PCRE_INFO_HASCRORLF Return 1 if explicit CR or LF matches exist + PCRE_INFO_JCHANGED Return 1 if (?J) or (?-J) was used + PCRE_INFO_JIT Return 1 after successful JIT compilation + PCRE_INFO_JITSIZE Size of JIT compiled code + PCRE_INFO_LASTLITERAL Literal last data unit required + PCRE_INFO_MINLENGTH Lower bound length of matching strings + PCRE_INFO_NAMECOUNT Number of named subpatterns + PCRE_INFO_NAMEENTRYSIZE Size of name table entry + PCRE_INFO_NAMETABLE Pointer to name table + PCRE_INFO_OKPARTIAL Return 1 if partial matching can be tried + (always returns 1 after release 8.00) + PCRE_INFO_OPTIONS Option bits used for compilation + PCRE_INFO_SIZE Size of compiled pattern + PCRE_INFO_STUDYSIZE Size of study data + PCRE_INFO_FIRSTCHARACTER Fixed first data unit for a match + PCRE_INFO_FIRSTCHARACTERFLAGS Returns + 1 if there is a first data character set, which can + then be retrieved using PCRE_INFO_FIRSTCHARACTER, + 2 if the first character is at the start of the data + string or after a newline, and + 0 otherwise + PCRE_INFO_REQUIREDCHAR Literal last data unit required + PCRE_INFO_REQUIREDCHARFLAGS Returns 1 if the last data character is set (which can then + be retrieved using PCRE_INFO_REQUIREDCHAR); 0 otherwise +.sp +The \fIwhere\fP argument must point to an integer variable, except for the +following \fIwhat\fP values: +.sp + PCRE_INFO_DEFAULT_TABLES const unsigned char * + PCRE_INFO_FIRSTTABLE const unsigned char * + PCRE_INFO_NAMETABLE PCRE_SPTR16 (16-bit library) + PCRE_INFO_NAMETABLE PCRE_SPTR32 (32-bit library) + PCRE_INFO_NAMETABLE const unsigned char * (8-bit library) + PCRE_INFO_OPTIONS unsigned long int + PCRE_INFO_SIZE size_t + PCRE_INFO_FIRSTCHARACTER uint32_t + PCRE_INFO_REQUIREDCHAR uint32_t +.sp +The yield of the function is zero on success or: +.sp + PCRE_ERROR_NULL the argument \fIcode\fP was NULL + the argument \fIwhere\fP was NULL + PCRE_ERROR_BADMAGIC the "magic number" was not found + PCRE_ERROR_BADOPTION the value of \fIwhat\fP was invalid +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_get_named_substring.3 b/plugins/Pcre16/docs/doc/pcre_get_named_substring.3 new file mode 100644 index 0000000000..84d4ee7dbb --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_get_named_substring.3 @@ -0,0 +1,54 @@ +.TH PCRE_GET_NAMED_SUBSTRING 3 "24 June 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.nf +.B int pcre_get_named_substring(const pcre *\fIcode\fP, +.B " const char *\fIsubject\fP, int *\fIovector\fP," +.B " int \fIstringcount\fP, const char *\fIstringname\fP," +.B " const char **\fIstringptr\fP);" +.sp +.B int pcre16_get_named_substring(const pcre16 *\fIcode\fP, +.B " PCRE_SPTR16 \fIsubject\fP, int *\fIovector\fP," +.B " int \fIstringcount\fP, PCRE_SPTR16 \fIstringname\fP," +.B " PCRE_SPTR16 *\fIstringptr\fP);" +.sp +.B int pcre32_get_named_substring(const pcre32 *\fIcode\fP, +.B " PCRE_SPTR32 \fIsubject\fP, int *\fIovector\fP," +.B " int \fIstringcount\fP, PCRE_SPTR32 \fIstringname\fP," +.B " PCRE_SPTR32 *\fIstringptr\fP);" +.fi +. +.SH DESCRIPTION +.rs +.sp +This is a convenience function for extracting a captured substring by name. The +arguments are: +.sp + \fIcode\fP Compiled pattern + \fIsubject\fP Subject that has been successfully matched + \fIovector\fP Offset vector that \fBpcre[16|32]_exec()\fP used + \fIstringcount\fP Value returned by \fBpcre[16|32]_exec()\fP + \fIstringname\fP Name of the required substring + \fIstringptr\fP Where to put the string pointer +.sp +The memory in which the substring is placed is obtained by calling +\fBpcre[16|32]_malloc()\fP. The convenience function +\fBpcre[16|32]_free_substring()\fP can be used to free it when it is no longer +needed. The yield of the function is the length of the extracted substring, +PCRE_ERROR_NOMEMORY if sufficient memory could not be obtained, or +PCRE_ERROR_NOSUBSTRING if the string name is invalid. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_get_stringnumber.3 b/plugins/Pcre16/docs/doc/pcre_get_stringnumber.3 new file mode 100644 index 0000000000..9fc5291dc8 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_get_stringnumber.3 @@ -0,0 +1,43 @@ +.TH PCRE_GET_STRINGNUMBER 3 "24 June 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.nf +.B int pcre_get_stringnumber(const pcre *\fIcode\fP, +.B " const char *\fIname\fP);" +.sp +.B int pcre16_get_stringnumber(const pcre16 *\fIcode\fP, +.B " PCRE_SPTR16 \fIname\fP);" +.sp +.B int pcre32_get_stringnumber(const pcre32 *\fIcode\fP, +.B " PCRE_SPTR32 \fIname\fP);" +.fi +. +.SH DESCRIPTION +.rs +.sp +This convenience function finds the number of a named substring capturing +parenthesis in a compiled pattern. Its arguments are: +.sp + \fIcode\fP Compiled regular expression + \fIname\fP Name whose number is required +.sp +The yield of the function is the number of the parenthesis if the name is +found, or PCRE_ERROR_NOSUBSTRING otherwise. When duplicate names are allowed +(PCRE_DUPNAMES is set), it is not defined which of the numbers is returned by +\fBpcre[16|32]_get_stringnumber()\fP. You can obtain the complete list by calling +\fBpcre[16|32]_get_stringtable_entries()\fP. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_get_stringtable_entries.3 b/plugins/Pcre16/docs/doc/pcre_get_stringtable_entries.3 new file mode 100644 index 0000000000..5c58c90c0e --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_get_stringtable_entries.3 @@ -0,0 +1,46 @@ +.TH PCRE_GET_STRINGTABLE_ENTRIES 3 "24 June 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.nf +.B int pcre_get_stringtable_entries(const pcre *\fIcode\fP, +.B " const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);" +.sp +.B int pcre16_get_stringtable_entries(const pcre16 *\fIcode\fP, +.B " PCRE_SPTR16 \fIname\fP, PCRE_UCHAR16 **\fIfirst\fP, PCRE_UCHAR16 **\fIlast\fP);" +.sp +.B int pcre32_get_stringtable_entries(const pcre32 *\fIcode\fP, +.B " PCRE_SPTR32 \fIname\fP, PCRE_UCHAR32 **\fIfirst\fP, PCRE_UCHAR32 **\fIlast\fP);" +.fi +. +.SH DESCRIPTION +.rs +.sp +This convenience function finds, for a compiled pattern, the first and last +entries for a given name in the table that translates capturing parenthesis +names into numbers. When names are required to be unique (PCRE_DUPNAMES is +\fInot\fP set), it is usually easier to use \fBpcre[16|32]_get_stringnumber()\fP +instead. +.sp + \fIcode\fP Compiled regular expression + \fIname\fP Name whose entries required + \fIfirst\fP Where to return a pointer to the first entry + \fIlast\fP Where to return a pointer to the last entry +.sp +The yield of the function is the length of each entry, or +PCRE_ERROR_NOSUBSTRING if none are found. +.P +There is a complete description of the PCRE native API, including the format of +the table entries, in the +.\" HREF +\fBpcreapi\fP +.\" +page, and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_get_substring.3 b/plugins/Pcre16/docs/doc/pcre_get_substring.3 new file mode 100644 index 0000000000..1e62b2c0c6 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_get_substring.3 @@ -0,0 +1,50 @@ +.TH PCRE_GET_SUBSTRING 3 "24 June 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.nf +.B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP, +.B " int \fIstringcount\fP, int \fIstringnumber\fP," +.B " const char **\fIstringptr\fP);" +.sp +.B int pcre16_get_substring(PCRE_SPTR16 \fIsubject\fP, int *\fIovector\fP, +.B " int \fIstringcount\fP, int \fIstringnumber\fP," +.B " PCRE_SPTR16 *\fIstringptr\fP);" +.sp +.B int pcre32_get_substring(PCRE_SPTR32 \fIsubject\fP, int *\fIovector\fP, +.B " int \fIstringcount\fP, int \fIstringnumber\fP," +.B " PCRE_SPTR32 *\fIstringptr\fP);" +.fi +. +.SH DESCRIPTION +.rs +.sp +This is a convenience function for extracting a captured substring. The +arguments are: +.sp + \fIsubject\fP Subject that has been successfully matched + \fIovector\fP Offset vector that \fBpcre[16|32]_exec()\fP used + \fIstringcount\fP Value returned by \fBpcre[16|32]_exec()\fP + \fIstringnumber\fP Number of the required substring + \fIstringptr\fP Where to put the string pointer +.sp +The memory in which the substring is placed is obtained by calling +\fBpcre[16|32]_malloc()\fP. The convenience function +\fBpcre[16|32]_free_substring()\fP can be used to free it when it is no longer +needed. The yield of the function is the length of the substring, +PCRE_ERROR_NOMEMORY if sufficient memory could not be obtained, or +PCRE_ERROR_NOSUBSTRING if the string number is invalid. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_get_substring_list.3 b/plugins/Pcre16/docs/doc/pcre_get_substring_list.3 new file mode 100644 index 0000000000..511a4a39d6 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_get_substring_list.3 @@ -0,0 +1,47 @@ +.TH PCRE_GET_SUBSTRING_LIST 3 "24 June 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.nf +.B int pcre_get_substring_list(const char *\fIsubject\fP, +.B " int *\fIovector\fP, int \fIstringcount\fP, const char ***\fIlistptr\fP);" +.sp +.B int pcre16_get_substring_list(PCRE_SPTR16 \fIsubject\fP, +.B " int *\fIovector\fP, int \fIstringcount\fP, PCRE_SPTR16 **\fIlistptr\fP);" +.sp +.B int pcre32_get_substring_list(PCRE_SPTR32 \fIsubject\fP, +.B " int *\fIovector\fP, int \fIstringcount\fP, PCRE_SPTR32 **\fIlistptr\fP);" +.fi +. +.SH DESCRIPTION +.rs +.sp +This is a convenience function for extracting a list of all the captured +substrings. The arguments are: +.sp + \fIsubject\fP Subject that has been successfully matched + \fIovector\fP Offset vector that \fBpcre[16|32]_exec\fP used + \fIstringcount\fP Value returned by \fBpcre[16|32]_exec\fP + \fIlistptr\fP Where to put a pointer to the list +.sp +The memory in which the substrings and the list are placed is obtained by +calling \fBpcre[16|32]_malloc()\fP. The convenience function +\fBpcre[16|32]_free_substring_list()\fP can be used to free it when it is no +longer needed. A pointer to a list of pointers is put in the variable whose +address is in \fIlistptr\fP. The list is terminated by a NULL pointer. The +yield of the function is zero on success or PCRE_ERROR_NOMEMORY if sufficient +memory could not be obtained. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_jit_exec.3 b/plugins/Pcre16/docs/doc/pcre_jit_exec.3 new file mode 100644 index 0000000000..ba85168178 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_jit_exec.3 @@ -0,0 +1,96 @@ +.TH PCRE_EXEC 3 "31 October 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.nf +.B int pcre_jit_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," +.B " const char *\fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP," +.B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP," +.B " pcre_jit_stack *\fIjstack\fP);" +.sp +.B int pcre16_jit_exec(const pcre16 *\fIcode\fP, "const pcre16_extra *\fIextra\fP," +.B " PCRE_SPTR16 \fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP," +.B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP," +.B " pcre_jit_stack *\fIjstack\fP);" +.sp +.B int pcre32_jit_exec(const pcre32 *\fIcode\fP, "const pcre32_extra *\fIextra\fP," +.B " PCRE_SPTR32 \fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP," +.B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP," +.B " pcre_jit_stack *\fIjstack\fP);" +.fi +. +.SH DESCRIPTION +.rs +.sp +This function matches a compiled regular expression that has been successfully +studied with one of the JIT options against a given subject string, using a +matching algorithm that is similar to Perl's. It is a "fast path" interface to +JIT, and it bypasses some of the sanity checks that \fBpcre_exec()\fP applies. +It returns offsets to captured substrings. Its arguments are: +.sp + \fIcode\fP Points to the compiled pattern + \fIextra\fP Points to an associated \fBpcre[16|32]_extra\fP structure, + or is NULL + \fIsubject\fP Points to the subject string + \fIlength\fP Length of the subject string, in bytes + \fIstartoffset\fP Offset in bytes in the subject at which to + start matching + \fIoptions\fP Option bits + \fIovector\fP Points to a vector of ints for result offsets + \fIovecsize\fP Number of elements in the vector (a multiple of 3) + \fIjstack\fP Pointer to a JIT stack +.sp +The allowed options are: +.sp + PCRE_NOTBOL Subject string is not the beginning of a line + PCRE_NOTEOL Subject string is not the end of a line + PCRE_NOTEMPTY An empty string is not a valid match + PCRE_NOTEMPTY_ATSTART An empty string at the start of the subject + is not a valid match + PCRE_NO_UTF16_CHECK Do not check the subject for UTF-16 + validity (only relevant if PCRE_UTF16 + was set at compile time) + PCRE_NO_UTF32_CHECK Do not check the subject for UTF-32 + validity (only relevant if PCRE_UTF32 + was set at compile time) + PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8 + validity (only relevant if PCRE_UTF8 + was set at compile time) + PCRE_PARTIAL ) Return PCRE_ERROR_PARTIAL for a partial + PCRE_PARTIAL_SOFT ) match if no full matches are found + PCRE_PARTIAL_HARD Return PCRE_ERROR_PARTIAL for a partial match + if that is found before a full match +.sp +However, the PCRE_NO_UTF[8|16|32]_CHECK options have no effect, as this check +is never applied. For details of partial matching, see the +.\" HREF +\fBpcrepartial\fP +.\" +page. A \fBpcre_extra\fP structure contains the following fields: +.sp + \fIflags\fP Bits indicating which fields are set + \fIstudy_data\fP Opaque data from \fBpcre[16|32]_study()\fP + \fImatch_limit\fP Limit on internal resource use + \fImatch_limit_recursion\fP Limit on internal recursion depth + \fIcallout_data\fP Opaque data passed back to callouts + \fItables\fP Points to character tables or is NULL + \fImark\fP For passing back a *MARK pointer + \fIexecutable_jit\fP Opaque data from JIT compilation +.sp +The flag bits are PCRE_EXTRA_STUDY_DATA, PCRE_EXTRA_MATCH_LIMIT, +PCRE_EXTRA_MATCH_LIMIT_RECURSION, PCRE_EXTRA_CALLOUT_DATA, +PCRE_EXTRA_TABLES, PCRE_EXTRA_MARK and PCRE_EXTRA_EXECUTABLE_JIT. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the JIT API in the +.\" HREF +\fBpcrejit\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_jit_stack_alloc.3 b/plugins/Pcre16/docs/doc/pcre_jit_stack_alloc.3 new file mode 100644 index 0000000000..11c97a0fc8 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_jit_stack_alloc.3 @@ -0,0 +1,43 @@ +.TH PCRE_JIT_STACK_ALLOC 3 "24 June 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.nf +.B pcre_jit_stack *pcre_jit_stack_alloc(int \fIstartsize\fP, +.B " int \fImaxsize\fP);" +.sp +.B pcre16_jit_stack *pcre16_jit_stack_alloc(int \fIstartsize\fP, +.B " int \fImaxsize\fP);" +.sp +.B pcre32_jit_stack *pcre32_jit_stack_alloc(int \fIstartsize\fP, +.B " int \fImaxsize\fP);" +.fi +. +.SH DESCRIPTION +.rs +.sp +This function is used to create a stack for use by the code compiled by the JIT +optimization of \fBpcre[16|32]_study()\fP. The arguments are a starting size for +the stack, and a maximum size to which it is allowed to grow. The result can be +passed to the JIT run-time code by \fBpcre[16|32]_assign_jit_stack()\fP, or that +function can set up a callback for obtaining a stack. A maximum stack size of +512K to 1M should be more than enough for any pattern. For more details, see +the +.\" HREF +\fBpcrejit\fP +.\" +page. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_jit_stack_free.3 b/plugins/Pcre16/docs/doc/pcre_jit_stack_free.3 new file mode 100644 index 0000000000..494724e844 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_jit_stack_free.3 @@ -0,0 +1,35 @@ +.TH PCRE_JIT_STACK_FREE 3 "24 June 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.SM +.B void pcre_jit_stack_free(pcre_jit_stack *\fIstack\fP); +.PP +.B void pcre16_jit_stack_free(pcre16_jit_stack *\fIstack\fP); +.PP +.B void pcre32_jit_stack_free(pcre32_jit_stack *\fIstack\fP); +. +.SH DESCRIPTION +.rs +.sp +This function is used to free a JIT stack that was created by +\fBpcre[16|32]_jit_stack_alloc()\fP when it is no longer needed. For more details, +see the +.\" HREF +\fBpcrejit\fP +.\" +page. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_maketables.3 b/plugins/Pcre16/docs/doc/pcre_maketables.3 new file mode 100644 index 0000000000..b2c3d23aa6 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_maketables.3 @@ -0,0 +1,33 @@ +.TH PCRE_MAKETABLES 3 "24 June 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.SM +.B const unsigned char *pcre_maketables(void); +.PP +.B const unsigned char *pcre16_maketables(void); +.PP +.B const unsigned char *pcre32_maketables(void); +. +.SH DESCRIPTION +.rs +.sp +This function builds a set of character tables for character values less than +256. These can be passed to \fBpcre[16|32]_compile()\fP to override PCRE's +internal, built-in tables (which were made by \fBpcre[16|32]_maketables()\fP when +PCRE was compiled). You might want to do this if you are using a non-standard +locale. The function yields a pointer to the tables. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_pattern_to_host_byte_order.3 b/plugins/Pcre16/docs/doc/pcre_pattern_to_host_byte_order.3 new file mode 100644 index 0000000000..b0c41c38e8 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_pattern_to_host_byte_order.3 @@ -0,0 +1,44 @@ +.TH PCRE_PATTERN_TO_HOST_BYTE_ORDER 3 "24 June 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.nf +.B int pcre_pattern_to_host_byte_order(pcre *\fIcode\fP, +.B " pcre_extra *\fIextra\fP, const unsigned char *\fItables\fP);" +.sp +.B int pcre16_pattern_to_host_byte_order(pcre16 *\fIcode\fP, +.B " pcre16_extra *\fIextra\fP, const unsigned char *\fItables\fP);" +.sp +.B int pcre32_pattern_to_host_byte_order(pcre32 *\fIcode\fP, +.B " pcre32_extra *\fIextra\fP, const unsigned char *\fItables\fP);" +.fi +. +.SH DESCRIPTION +.rs +.sp +This function ensures that the bytes in 2-byte and 4-byte values in a compiled +pattern are in the correct order for the current host. It is useful when a +pattern that has been compiled on one host is transferred to another that might +have different endianness. The arguments are: +.sp + \fIcode\fP A compiled regular expression + \fIextra\fP Points to an associated \fBpcre[16|32]_extra\fP structure, + or is NULL + \fItables\fP Pointer to character tables, or NULL to + set the built-in default +.sp +The result is 0 for success, a negative PCRE_ERROR_xxx value otherwise. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_refcount.3 b/plugins/Pcre16/docs/doc/pcre_refcount.3 new file mode 100644 index 0000000000..45a41fef6a --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_refcount.3 @@ -0,0 +1,36 @@ +.TH PCRE_REFCOUNT 3 "24 June 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.SM +.B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP); +.PP +.B int pcre16_refcount(pcre16 *\fIcode\fP, int \fIadjust\fP); +.PP +.B int pcre32_refcount(pcre32 *\fIcode\fP, int \fIadjust\fP); +. +.SH DESCRIPTION +.rs +.sp +This function is used to maintain a reference count inside a data block that +contains a compiled pattern. Its arguments are: +.sp + \fIcode\fP Compiled regular expression + \fIadjust\fP Adjustment to reference value +.sp +The yield of the function is the adjusted reference value, which is constrained +to lie between 0 and 65535. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_study.3 b/plugins/Pcre16/docs/doc/pcre_study.3 new file mode 100644 index 0000000000..1200e0a668 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_study.3 @@ -0,0 +1,54 @@ +.TH PCRE_STUDY 3 " 24 June 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.nf +.B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP, +.B " const char **\fIerrptr\fP);" +.sp +.B pcre16_extra *pcre16_study(const pcre16 *\fIcode\fP, int \fIoptions\fP, +.B " const char **\fIerrptr\fP);" +.sp +.B pcre32_extra *pcre32_study(const pcre32 *\fIcode\fP, int \fIoptions\fP, +.B " const char **\fIerrptr\fP);" +.fi +. +.SH DESCRIPTION +.rs +.sp +This function studies a compiled pattern, to see if additional information can +be extracted that might speed up matching. Its arguments are: +.sp + \fIcode\fP A compiled regular expression + \fIoptions\fP Options for \fBpcre[16|32]_study()\fP + \fIerrptr\fP Where to put an error message +.sp +If the function succeeds, it returns a value that can be passed to +\fBpcre[16|32]_exec()\fP or \fBpcre[16|32]_dfa_exec()\fP via their \fIextra\fP +arguments. +.P +If the function returns NULL, either it could not find any additional +information, or there was an error. You can tell the difference by looking at +the error value. It is NULL in first case. +.P +The only option is PCRE_STUDY_JIT_COMPILE. It requests just-in-time compilation +if possible. If PCRE has been compiled without JIT support, this option is +ignored. See the +.\" HREF +\fBpcrejit\fP +.\" +page for further details. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_utf16_to_host_byte_order.3 b/plugins/Pcre16/docs/doc/pcre_utf16_to_host_byte_order.3 new file mode 100644 index 0000000000..1851b619da --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_utf16_to_host_byte_order.3 @@ -0,0 +1,45 @@ +.TH PCRE_UTF16_TO_HOST_BYTE_ORDER 3 "21 January 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.nf +.B int pcre16_utf16_to_host_byte_order(PCRE_UCHAR16 *\fIoutput\fP, +.B " PCRE_SPTR16 \fIinput\fP, int \fIlength\fP, int *\fIhost_byte_order\fP," +.B " int \fIkeep_boms\fP);" +.fi +. +. +.SH DESCRIPTION +.rs +.sp +This function, which exists only in the 16-bit library, converts a UTF-16 +string to the correct order for the current host, taking account of any byte +order marks (BOMs) within the string. Its arguments are: +.sp + \fIoutput\fP pointer to output buffer, may be the same as \fIinput\fP + \fIinput\fP pointer to input buffer + \fIlength\fP number of 16-bit units in the input, or negative for + a zero-terminated string + \fIhost_byte_order\fP a NULL value or a non-zero value pointed to means + start in host byte order + \fIkeep_boms\fP if non-zero, BOMs are copied to the output string +.sp +The result of the function is the number of 16-bit units placed into the output +buffer, including the zero terminator if the string was zero-terminated. +.P +If \fIhost_byte_order\fP is not NULL, it is set to indicate the byte order that +is current at the end of the string. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_utf32_to_host_byte_order.3 b/plugins/Pcre16/docs/doc/pcre_utf32_to_host_byte_order.3 new file mode 100644 index 0000000000..a415dcf5fa --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_utf32_to_host_byte_order.3 @@ -0,0 +1,45 @@ +.TH PCRE_UTF32_TO_HOST_BYTE_ORDER 3 "24 June 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.nf +.B int pcre32_utf32_to_host_byte_order(PCRE_UCHAR32 *\fIoutput\fP, +.B " PCRE_SPTR32 \fIinput\fP, int \fIlength\fP, int *\fIhost_byte_order\fP," +.B " int \fIkeep_boms\fP);" +.fi +. +. +.SH DESCRIPTION +.rs +.sp +This function, which exists only in the 32-bit library, converts a UTF-32 +string to the correct order for the current host, taking account of any byte +order marks (BOMs) within the string. Its arguments are: +.sp + \fIoutput\fP pointer to output buffer, may be the same as \fIinput\fP + \fIinput\fP pointer to input buffer + \fIlength\fP number of 32-bit units in the input, or negative for + a zero-terminated string + \fIhost_byte_order\fP a NULL value or a non-zero value pointed to means + start in host byte order + \fIkeep_boms\fP if non-zero, BOMs are copied to the output string +.sp +The result of the function is the number of 32-bit units placed into the output +buffer, including the zero terminator if the string was zero-terminated. +.P +If \fIhost_byte_order\fP is not NULL, it is set to indicate the byte order that +is current at the end of the string. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcre_version.3 b/plugins/Pcre16/docs/doc/pcre_version.3 new file mode 100644 index 0000000000..0f4973f9c7 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcre_version.3 @@ -0,0 +1,31 @@ +.TH PCRE_VERSION 3 "24 June 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.SM +.B const char *pcre_version(void); +.PP +.B const char *pcre16_version(void); +.PP +.B const char *pcre32_version(void); +. +.SH DESCRIPTION +.rs +.sp +This function (even in the 16-bit and 32-bit libraries) returns a +zero-terminated, 8-bit character string that gives the version number of the +PCRE library and the date of its release. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/plugins/Pcre16/docs/doc/pcreapi.3 b/plugins/Pcre16/docs/doc/pcreapi.3 new file mode 100644 index 0000000000..ab3eaa0b52 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcreapi.3 @@ -0,0 +1,2919 @@ +.TH PCREAPI 3 "09 February 2014" "PCRE 8.35" +.SH NAME +PCRE - Perl-compatible regular expressions +.sp +.B #include <pcre.h> +. +. +.SH "PCRE NATIVE API BASIC FUNCTIONS" +.rs +.sp +.nf +.B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP, +.B " const char **\fIerrptr\fP, int *\fIerroffset\fP," +.B " const unsigned char *\fItableptr\fP);" +.sp +.B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP, +.B " int *\fIerrorcodeptr\fP," +.B " const char **\fIerrptr\fP, int *\fIerroffset\fP," +.B " const unsigned char *\fItableptr\fP);" +.sp +.B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP, +.B " const char **\fIerrptr\fP);" +.sp +.B void pcre_free_study(pcre_extra *\fIextra\fP); +.sp +.B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," +.B " const char *\fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP," +.B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);" +.sp +.B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," +.B " const char *\fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP," +.B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP," +.B " int *\fIworkspace\fP, int \fIwscount\fP);" +.fi +. +. +.SH "PCRE NATIVE API STRING EXTRACTION FUNCTIONS" +.rs +.sp +.nf +.B int pcre_copy_named_substring(const pcre *\fIcode\fP, +.B " const char *\fIsubject\fP, int *\fIovector\fP," +.B " int \fIstringcount\fP, const char *\fIstringname\fP," +.B " char *\fIbuffer\fP, int \fIbuffersize\fP);" +.sp +.B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP, +.B " int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP," +.B " int \fIbuffersize\fP);" +.sp +.B int pcre_get_named_substring(const pcre *\fIcode\fP, +.B " const char *\fIsubject\fP, int *\fIovector\fP," +.B " int \fIstringcount\fP, const char *\fIstringname\fP," +.B " const char **\fIstringptr\fP);" +.sp +.B int pcre_get_stringnumber(const pcre *\fIcode\fP, +.B " const char *\fIname\fP);" +.sp +.B int pcre_get_stringtable_entries(const pcre *\fIcode\fP, +.B " const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);" +.sp +.B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP, +.B " int \fIstringcount\fP, int \fIstringnumber\fP," +.B " const char **\fIstringptr\fP);" +.sp +.B int pcre_get_substring_list(const char *\fIsubject\fP, +.B " int *\fIovector\fP, int \fIstringcount\fP, const char ***\fIlistptr\fP);" +.sp +.B void pcre_free_substring(const char *\fIstringptr\fP); +.sp +.B void pcre_free_substring_list(const char **\fIstringptr\fP); +.fi +. +. +.SH "PCRE NATIVE API AUXILIARY FUNCTIONS" +.rs +.sp +.nf +.B int pcre_jit_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," +.B " const char *\fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP," +.B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP," +.B " pcre_jit_stack *\fIjstack\fP);" +.sp +.B pcre_jit_stack *pcre_jit_stack_alloc(int \fIstartsize\fP, int \fImaxsize\fP); +.sp +.B void pcre_jit_stack_free(pcre_jit_stack *\fIstack\fP); +.sp +.B void pcre_assign_jit_stack(pcre_extra *\fIextra\fP, +.B " pcre_jit_callback \fIcallback\fP, void *\fIdata\fP);" +.sp +.B const unsigned char *pcre_maketables(void); +.sp +.B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," +.B " int \fIwhat\fP, void *\fIwhere\fP);" +.sp +.B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP); +.sp +.B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP); +.sp +.B const char *pcre_version(void); +.sp +.B int pcre_pattern_to_host_byte_order(pcre *\fIcode\fP, +.B " pcre_extra *\fIextra\fP, const unsigned char *\fItables\fP);" +.fi +. +. +.SH "PCRE NATIVE API INDIRECTED FUNCTIONS" +.rs +.sp +.nf +.B void *(*pcre_malloc)(size_t); +.sp +.B void (*pcre_free)(void *); +.sp +.B void *(*pcre_stack_malloc)(size_t); +.sp +.B void (*pcre_stack_free)(void *); +.sp +.B int (*pcre_callout)(pcre_callout_block *); +.sp +.B int (*pcre_stack_guard)(void); +.fi +. +. +.SH "PCRE 8-BIT, 16-BIT, AND 32-BIT LIBRARIES" +.rs +.sp +As well as support for 8-bit character strings, PCRE also supports 16-bit +strings (from release 8.30) and 32-bit strings (from release 8.32), by means of +two additional libraries. They can be built as well as, or instead of, the +8-bit library. To avoid too much complication, this document describes the +8-bit versions of the functions, with only occasional references to the 16-bit +and 32-bit libraries. +.P +The 16-bit and 32-bit functions operate in the same way as their 8-bit +counterparts; they just use different data types for their arguments and +results, and their names start with \fBpcre16_\fP or \fBpcre32_\fP instead of +\fBpcre_\fP. For every option that has UTF8 in its name (for example, +PCRE_UTF8), there are corresponding 16-bit and 32-bit names with UTF8 replaced +by UTF16 or UTF32, respectively. This facility is in fact just cosmetic; the +16-bit and 32-bit option names define the same bit values. +.P +References to bytes and UTF-8 in this document should be read as references to +16-bit data units and UTF-16 when using the 16-bit library, or 32-bit data +units and UTF-32 when using the 32-bit library, unless specified otherwise. +More details of the specific differences for the 16-bit and 32-bit libraries +are given in the +.\" HREF +\fBpcre16\fP +.\" +and +.\" HREF +\fBpcre32\fP +.\" +pages. +. +. +.SH "PCRE API OVERVIEW" +.rs +.sp +PCRE has its own native API, which is described in this document. There are +also some wrapper functions (for the 8-bit library only) that correspond to the +POSIX regular expression API, but they do not give access to all the +functionality. They are described in the +.\" HREF +\fBpcreposix\fP +.\" +documentation. Both of these APIs define a set of C function calls. A C++ +wrapper (again for the 8-bit library only) is also distributed with PCRE. It is +documented in the +.\" HREF +\fBpcrecpp\fP +.\" +page. +.P +The native API C function prototypes are defined in the header file +\fBpcre.h\fP, and on Unix-like systems the (8-bit) library itself is called +\fBlibpcre\fP. It can normally be accessed by adding \fB-lpcre\fP to the +command for linking an application that uses PCRE. The header file defines the +macros PCRE_MAJOR and PCRE_MINOR to contain the major and minor release numbers +for the library. Applications can use these to include support for different +releases of PCRE. +.P +In a Windows environment, if you want to statically link an application program +against a non-dll \fBpcre.a\fP file, you must define PCRE_STATIC before +including \fBpcre.h\fP or \fBpcrecpp.h\fP, because otherwise the +\fBpcre_malloc()\fP and \fBpcre_free()\fP exported functions will be declared +\fB__declspec(dllimport)\fP, with unwanted results. +.P +The functions \fBpcre_compile()\fP, \fBpcre_compile2()\fP, \fBpcre_study()\fP, +and \fBpcre_exec()\fP are used for compiling and matching regular expressions +in a Perl-compatible manner. A sample program that demonstrates the simplest +way of using them is provided in the file called \fIpcredemo.c\fP in the PCRE +source distribution. A listing of this program is given in the +.\" HREF +\fBpcredemo\fP +.\" +documentation, and the +.\" HREF +\fBpcresample\fP +.\" +documentation describes how to compile and run it. +.P +Just-in-time compiler support is an optional feature of PCRE that can be built +in appropriate hardware environments. It greatly speeds up the matching +performance of many patterns. Simple programs can easily request that it be +used if available, by setting an option that is ignored when it is not +relevant. More complicated programs might need to make use of the functions +\fBpcre_jit_stack_alloc()\fP, \fBpcre_jit_stack_free()\fP, and +\fBpcre_assign_jit_stack()\fP in order to control the JIT code's memory usage. +.P +From release 8.32 there is also a direct interface for JIT execution, which +gives improved performance. The JIT-specific functions are discussed in the +.\" HREF +\fBpcrejit\fP +.\" +documentation. +.P +A second matching function, \fBpcre_dfa_exec()\fP, which is not +Perl-compatible, is also provided. This uses a different algorithm for the +matching. The alternative algorithm finds all possible matches (at a given +point in the subject), and scans the subject just once (unless there are +lookbehind assertions). However, this algorithm does not return captured +substrings. A description of the two matching algorithms and their advantages +and disadvantages is given in the +.\" HREF +\fBpcrematching\fP +.\" +documentation. +.P +In addition to the main compiling and matching functions, there are convenience +functions for extracting captured substrings from a subject string that is +matched by \fBpcre_exec()\fP. They are: +.sp + \fBpcre_copy_substring()\fP + \fBpcre_copy_named_substring()\fP + \fBpcre_get_substring()\fP + \fBpcre_get_named_substring()\fP + \fBpcre_get_substring_list()\fP + \fBpcre_get_stringnumber()\fP + \fBpcre_get_stringtable_entries()\fP +.sp +\fBpcre_free_substring()\fP and \fBpcre_free_substring_list()\fP are also +provided, to free the memory used for extracted strings. +.P +The function \fBpcre_maketables()\fP is used to build a set of character tables +in the current locale for passing to \fBpcre_compile()\fP, \fBpcre_exec()\fP, +or \fBpcre_dfa_exec()\fP. This is an optional facility that is provided for +specialist use. Most commonly, no special tables are passed, in which case +internal tables that are generated when PCRE is built are used. +.P +The function \fBpcre_fullinfo()\fP is used to find out information about a +compiled pattern. The function \fBpcre_version()\fP returns a pointer to a +string containing the version of PCRE and its date of release. +.P +The function \fBpcre_refcount()\fP maintains a reference count in a data block +containing a compiled pattern. This is provided for the benefit of +object-oriented applications. +.P +The global variables \fBpcre_malloc\fP and \fBpcre_free\fP initially contain +the entry points of the standard \fBmalloc()\fP and \fBfree()\fP functions, +respectively. PCRE calls the memory management functions via these variables, +so a calling program can replace them if it wishes to intercept the calls. This +should be done before calling any PCRE functions. +.P +The global variables \fBpcre_stack_malloc\fP and \fBpcre_stack_free\fP are also +indirections to memory management functions. These special functions are used +only when PCRE is compiled to use the heap for remembering data, instead of +recursive function calls, when running the \fBpcre_exec()\fP function. See the +.\" HREF +\fBpcrebuild\fP +.\" +documentation for details of how to do this. It is a non-standard way of +building PCRE, for use in environments that have limited stacks. Because of the +greater use of memory management, it runs more slowly. Separate functions are +provided so that special-purpose external code can be used for this case. When +used, these functions are always called in a stack-like manner (last obtained, +first freed), and always for memory blocks of the same size. There is a +discussion about PCRE's stack usage in the +.\" HREF +\fBpcrestack\fP +.\" +documentation. +.P +The global variable \fBpcre_callout\fP initially contains NULL. It can be set +by the caller to a "callout" function, which PCRE will then call at specified +points during a matching operation. Details are given in the +.\" HREF +\fBpcrecallout\fP +.\" +documentation. +.P +The global variable \fBpcre_stack_guard\fP initially contains NULL. It can be +set by the caller to a function that is called by PCRE whenever it starts +to compile a parenthesized part of a pattern. When parentheses are nested, PCRE +uses recursive function calls, which use up the system stack. This function is +provided so that applications with restricted stacks can force a compilation +error if the stack runs out. The function should return zero if all is well, or +non-zero to force an error. +. +. +.\" HTML <a name="newlines"></a> +.SH NEWLINES +.rs +.sp +PCRE supports five different conventions for indicating line breaks in +strings: a single CR (carriage return) character, a single LF (linefeed) +character, the two-character sequence CRLF, any of the three preceding, or any +Unicode newline sequence. The Unicode newline sequences are the three just +mentioned, plus the single characters VT (vertical tab, U+000B), FF (form feed, +U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS +(paragraph separator, U+2029). +.P +Each of the first three conventions is used by at least one operating system as +its standard newline sequence. When PCRE is built, a default can be specified. +The default default is LF, which is the Unix standard. When PCRE is run, the +default can be overridden, either when a pattern is compiled, or when it is +matched. +.P +At compile time, the newline convention can be specified by the \fIoptions\fP +argument of \fBpcre_compile()\fP, or it can be specified by special text at the +start of the pattern itself; this overrides any other settings. See the +.\" HREF +\fBpcrepattern\fP +.\" +page for details of the special character sequences. +.P +In the PCRE documentation the word "newline" is used to mean "the character or +pair of characters that indicate a line break". The choice of newline +convention affects the handling of the dot, circumflex, and dollar +metacharacters, the handling of #-comments in /x mode, and, when CRLF is a +recognized line ending sequence, the match position advancement for a +non-anchored pattern. There is more detail about this in the +.\" HTML <a href="#execoptions"> +.\" </a> +section on \fBpcre_exec()\fP options +.\" +below. +.P +The choice of newline convention does not affect the interpretation of +the \en or \er escape sequences, nor does it affect what \eR matches, which is +controlled in a similar way, but by separate options. +. +. +.SH MULTITHREADING +.rs +.sp +The PCRE functions can be used in multi-threading applications, with the +proviso that the memory management functions pointed to by \fBpcre_malloc\fP, +\fBpcre_free\fP, \fBpcre_stack_malloc\fP, and \fBpcre_stack_free\fP, and the +callout and stack-checking functions pointed to by \fBpcre_callout\fP and +\fBpcre_stack_guard\fP, are shared by all threads. +.P +The compiled form of a regular expression is not altered during matching, so +the same compiled pattern can safely be used by several threads at once. +.P +If the just-in-time optimization feature is being used, it needs separate +memory stack areas for each thread. See the +.\" HREF +\fBpcrejit\fP +.\" +documentation for more details. +. +. +.SH "SAVING PRECOMPILED PATTERNS FOR LATER USE" +.rs +.sp +The compiled form of a regular expression can be saved and re-used at a later +time, possibly by a different program, and even on a host other than the one on +which it was compiled. Details are given in the +.\" HREF +\fBpcreprecompile\fP +.\" +documentation, which includes a description of the +\fBpcre_pattern_to_host_byte_order()\fP function. However, compiling a regular +expression with one version of PCRE for use with a different version is not +guaranteed to work and may cause crashes. +. +. +.SH "CHECKING BUILD-TIME OPTIONS" +.rs +.sp +.B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP); +.PP +The function \fBpcre_config()\fP makes it possible for a PCRE client to +discover which optional features have been compiled into the PCRE library. The +.\" HREF +\fBpcrebuild\fP +.\" +documentation has more details about these optional features. +.P +The first argument for \fBpcre_config()\fP is an integer, specifying which +information is required; the second argument is a pointer to a variable into +which the information is placed. The returned value is zero on success, or the +negative error code PCRE_ERROR_BADOPTION if the value in the first argument is +not recognized. The following information is available: +.sp + PCRE_CONFIG_UTF8 +.sp +The output is an integer that is set to one if UTF-8 support is available; +otherwise it is set to zero. This value should normally be given to the 8-bit +version of this function, \fBpcre_config()\fP. If it is given to the 16-bit +or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION. +.sp + PCRE_CONFIG_UTF16 +.sp +The output is an integer that is set to one if UTF-16 support is available; +otherwise it is set to zero. This value should normally be given to the 16-bit +version of this function, \fBpcre16_config()\fP. If it is given to the 8-bit +or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION. +.sp + PCRE_CONFIG_UTF32 +.sp +The output is an integer that is set to one if UTF-32 support is available; +otherwise it is set to zero. This value should normally be given to the 32-bit +version of this function, \fBpcre32_config()\fP. If it is given to the 8-bit +or 16-bit version of this function, the result is PCRE_ERROR_BADOPTION. +.sp + PCRE_CONFIG_UNICODE_PROPERTIES +.sp +The output is an integer that is set to one if support for Unicode character +properties is available; otherwise it is set to zero. +.sp + PCRE_CONFIG_JIT +.sp +The output is an integer that is set to one if support for just-in-time +compiling is available; otherwise it is set to zero. +.sp + PCRE_CONFIG_JITTARGET +.sp +The output is a pointer to a zero-terminated "const char *" string. If JIT +support is available, the string contains the name of the architecture for +which the JIT compiler is configured, for example "x86 32bit (little endian + +unaligned)". If JIT support is not available, the result is NULL. +.sp + PCRE_CONFIG_NEWLINE +.sp +The output is an integer whose value specifies the default character sequence +that is recognized as meaning "newline". The values that are supported in +ASCII/Unicode environments are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for +ANYCRLF, and -1 for ANY. In EBCDIC environments, CR, ANYCRLF, and ANY yield the +same values. However, the value for LF is normally 21, though some EBCDIC +environments use 37. The corresponding values for CRLF are 3349 and 3365. The +default should normally correspond to the standard sequence for your operating +system. +.sp + PCRE_CONFIG_BSR +.sp +The output is an integer whose value indicates what character sequences the \eR +escape sequence matches by default. A value of 0 means that \eR matches any +Unicode line ending sequence; a value of 1 means that \eR matches only CR, LF, +or CRLF. The default can be overridden when a pattern is compiled or matched. +.sp + PCRE_CONFIG_LINK_SIZE +.sp +The output is an integer that contains the number of bytes used for internal +linkage in compiled regular expressions. For the 8-bit library, the value can +be 2, 3, or 4. For the 16-bit library, the value is either 2 or 4 and is still +a number of bytes. For the 32-bit library, the value is either 2 or 4 and is +still a number of bytes. The default value of 2 is sufficient for all but the +most massive patterns, since it allows the compiled pattern to be up to 64K in +size. Larger values allow larger regular expressions to be compiled, at the +expense of slower matching. +.sp + PCRE_CONFIG_POSIX_MALLOC_THRESHOLD +.sp +The output is an integer that contains the threshold above which the POSIX +interface uses \fBmalloc()\fP for output vectors. Further details are given in +the +.\" HREF +\fBpcreposix\fP +.\" +documentation. +.sp + PCRE_CONFIG_PARENS_LIMIT +.sp +The output is a long integer that gives the maximum depth of nesting of +parentheses (of any kind) in a pattern. This limit is imposed to cap the amount +of system stack used when a pattern is compiled. It is specified when PCRE is +built; the default is 250. This limit does not take into account the stack that +may already be used by the calling application. For finer control over +compilation stack usage, you can set a pointer to an external checking function +in \fBpcre_stack_guard\fP. +.sp + PCRE_CONFIG_MATCH_LIMIT +.sp +The output is a long integer that gives the default limit for the number of +internal matching function calls in a \fBpcre_exec()\fP execution. Further +details are given with \fBpcre_exec()\fP below. +.sp + PCRE_CONFIG_MATCH_LIMIT_RECURSION +.sp +The output is a long integer that gives the default limit for the depth of +recursion when calling the internal matching function in a \fBpcre_exec()\fP +execution. Further details are given with \fBpcre_exec()\fP below. +.sp + PCRE_CONFIG_STACKRECURSE +.sp +The output is an integer that is set to one if internal recursion when running +\fBpcre_exec()\fP is implemented by recursive function calls that use the stack +to remember their state. This is the usual way that PCRE is compiled. The +output is zero if PCRE was compiled to use blocks of data on the heap instead +of recursive function calls. In this case, \fBpcre_stack_malloc\fP and +\fBpcre_stack_free\fP are called to manage memory blocks on the heap, thus +avoiding the use of the stack. +. +. +.SH "COMPILING A PATTERN" +.rs +.sp +.nf +.B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP, +.B " const char **\fIerrptr\fP, int *\fIerroffset\fP," +.B " const unsigned char *\fItableptr\fP);" +.sp +.B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP, +.B " int *\fIerrorcodeptr\fP," +.B " const char **\fIerrptr\fP, int *\fIerroffset\fP," +.B " const unsigned char *\fItableptr\fP);" +.fi +.P +Either of the functions \fBpcre_compile()\fP or \fBpcre_compile2()\fP can be +called to compile a pattern into an internal form. The only difference between +the two interfaces is that \fBpcre_compile2()\fP has an additional argument, +\fIerrorcodeptr\fP, via which a numerical error code can be returned. To avoid +too much repetition, we refer just to \fBpcre_compile()\fP below, but the +information applies equally to \fBpcre_compile2()\fP. +.P +The pattern is a C string terminated by a binary zero, and is passed in the +\fIpattern\fP argument. A pointer to a single block of memory that is obtained +via \fBpcre_malloc\fP is returned. This contains the compiled code and related +data. The \fBpcre\fP type is defined for the returned block; this is a typedef +for a structure whose contents are not externally defined. It is up to the +caller to free the memory (via \fBpcre_free\fP) when it is no longer required. +.P +Although the compiled code of a PCRE regex is relocatable, that is, it does not +depend on memory location, the complete \fBpcre\fP data block is not +fully relocatable, because it may contain a copy of the \fItableptr\fP +argument, which is an address (see below). +.P +The \fIoptions\fP argument contains various bit settings that affect the +compilation. It should be zero if no options are required. The available +options are described below. Some of them (in particular, those that are +compatible with Perl, but some others as well) can also be set and unset from +within the pattern (see the detailed description in the +.\" HREF +\fBpcrepattern\fP +.\" +documentation). For those options that can be different in different parts of +the pattern, the contents of the \fIoptions\fP argument specifies their +settings at the start of compilation and execution. The PCRE_ANCHORED, +PCRE_BSR_\fIxxx\fP, PCRE_NEWLINE_\fIxxx\fP, PCRE_NO_UTF8_CHECK, and +PCRE_NO_START_OPTIMIZE options can be set at the time of matching as well as at +compile time. +.P +If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately. +Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns +NULL, and sets the variable pointed to by \fIerrptr\fP to point to a textual +error message. This is a static string that is part of the library. You must +not try to free it. Normally, the offset from the start of the pattern to the +data unit that was being processed when the error was discovered is placed in +the variable pointed to by \fIerroffset\fP, which must not be NULL (if it is, +an immediate error is given). However, for an invalid UTF-8 or UTF-16 string, +the offset is that of the first data unit of the failing character. +.P +Some errors are not detected until the whole pattern has been scanned; in these +cases, the offset passed back is the length of the pattern. Note that the +offset is in data units, not characters, even in a UTF mode. It may sometimes +point into the middle of a UTF-8 or UTF-16 character. +.P +If \fBpcre_compile2()\fP is used instead of \fBpcre_compile()\fP, and the +\fIerrorcodeptr\fP argument is not NULL, a non-zero error code number is +returned via this argument in the event of an error. This is in addition to the +textual error message. Error codes and messages are listed below. +.P +If the final argument, \fItableptr\fP, is NULL, PCRE uses a default set of +character tables that are built when PCRE is compiled, using the default C +locale. Otherwise, \fItableptr\fP must be an address that is the result of a +call to \fBpcre_maketables()\fP. This value is stored with the compiled +pattern, and used again by \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP when the +pattern is matched. For more discussion, see the section on locale support +below. +.P +This code fragment shows a typical straightforward call to \fBpcre_compile()\fP: +.sp + pcre *re; + const char *error; + int erroffset; + re = pcre_compile( + "^A.*Z", /* the pattern */ + 0, /* default options */ + &error, /* for error message */ + &erroffset, /* for error offset */ + NULL); /* use default character tables */ +.sp +The following names for option bits are defined in the \fBpcre.h\fP header +file: +.sp + PCRE_ANCHORED +.sp +If this bit is set, the pattern is forced to be "anchored", that is, it is +constrained to match only at the first matching point in the string that is +being searched (the "subject string"). This effect can also be achieved by +appropriate constructs in the pattern itself, which is the only way to do it in +Perl. +.sp + PCRE_AUTO_CALLOUT +.sp +If this bit is set, \fBpcre_compile()\fP automatically inserts callout items, +all with number 255, before each pattern item. For discussion of the callout +facility, see the +.\" HREF +\fBpcrecallout\fP +.\" +documentation. +.sp + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE +.sp +These options (which are mutually exclusive) control what the \eR escape +sequence matches. The choice is either to match only CR, LF, or CRLF, or to +match any Unicode newline sequence. The default is specified when PCRE is +built. It can be overridden from within the pattern, or by setting an option +when a compiled pattern is matched. +.sp + PCRE_CASELESS +.sp +If this bit is set, letters in the pattern match both upper and lower case +letters. It is equivalent to Perl's /i option, and it can be changed within a +pattern by a (?i) option setting. In UTF-8 mode, PCRE always understands the +concept of case for characters whose values are less than 128, so caseless +matching is always possible. For characters with higher values, the concept of +case is supported if PCRE is compiled with Unicode property support, but not +otherwise. If you want to use caseless matching for characters 128 and above, +you must ensure that PCRE is compiled with Unicode property support as well as +with UTF-8 support. +.sp + PCRE_DOLLAR_ENDONLY +.sp +If this bit is set, a dollar metacharacter in the pattern matches only at the +end of the subject string. Without this option, a dollar also matches +immediately before a newline at the end of the string (but not before any other +newlines). The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set. +There is no equivalent to this option in Perl, and no way to set it within a +pattern. +.sp + PCRE_DOTALL +.sp +If this bit is set, a dot metacharacter in the pattern matches a character of +any value, including one that indicates a newline. However, it only ever +matches one character, even if newlines are coded as CRLF. Without this option, +a dot does not match when the current position is at a newline. This option is +equivalent to Perl's /s option, and it can be changed within a pattern by a +(?s) option setting. A negative class such as [^a] always matches newline +characters, independent of the setting of this option. +.sp + PCRE_DUPNAMES +.sp +If this bit is set, names used to identify capturing subpatterns need not be +unique. This can be helpful for certain types of pattern when it is known that +only one instance of the named subpattern can ever be matched. There are more +details of named subpatterns below; see also the +.\" HREF +\fBpcrepattern\fP +.\" +documentation. +.sp + PCRE_EXTENDED +.sp +If this bit is set, most white space characters in the pattern are totally +ignored except when escaped or inside a character class. However, white space +is not allowed within sequences such as (?> that introduce various +parenthesized subpatterns, nor within a numerical quantifier such as {1,3}. +However, ignorable white space is permitted between an item and a following +quantifier and between a quantifier and a following + that indicates +possessiveness. +.P +White space did not used to include the VT character (code 11), because Perl +did not treat this character as white space. However, Perl changed at release +5.18, so PCRE followed at release 8.34, and VT is now treated as white space. +.P +PCRE_EXTENDED also causes characters between an unescaped # outside a character +class and the next newline, inclusive, to be ignored. PCRE_EXTENDED is +equivalent to Perl's /x option, and it can be changed within a pattern by a +(?x) option setting. +.P +Which characters are interpreted as newlines is controlled by the options +passed to \fBpcre_compile()\fP or by a special sequence at the start of the +pattern, as described in the section entitled +.\" HTML <a href="pcrepattern.html#newlines"> +.\" </a> +"Newline conventions" +.\" +in the \fBpcrepattern\fP documentation. Note that the end of this type of +comment is a literal newline sequence in the pattern; escape sequences that +happen to represent a newline do not count. +.P +This option makes it possible to include comments inside complicated patterns. +Note, however, that this applies only to data characters. White space characters +may never appear within special character sequences in a pattern, for example +within the sequence (?( that introduces a conditional subpattern. +.sp + PCRE_EXTRA +.sp +This option was invented in order to turn on additional functionality of PCRE +that is incompatible with Perl, but it is currently of very little use. When +set, any backslash in a pattern that is followed by a letter that has no +special meaning causes an error, thus reserving these combinations for future +expansion. By default, as in Perl, a backslash followed by a letter with no +special meaning is treated as a literal. (Perl can, however, be persuaded to +give an error for this, by running it with the -w option.) There are at present +no other features controlled by this option. It can also be set by a (?X) +option setting within a pattern. +.sp + PCRE_FIRSTLINE +.sp +If this option is set, an unanchored pattern is required to match before or at +the first newline in the subject string, though the matched text may continue +over the newline. +.sp + PCRE_JAVASCRIPT_COMPAT +.sp +If this option is set, PCRE's behaviour is changed in some ways so that it is +compatible with JavaScript rather than Perl. The changes are as follows: +.P +(1) A lone closing square bracket in a pattern causes a compile-time error, +because this is illegal in JavaScript (by default it is treated as a data +character). Thus, the pattern AB]CD becomes illegal when this option is set. +.P +(2) At run time, a back reference to an unset subpattern group matches an empty +string (by default this causes the current matching alternative to fail). A +pattern such as (\e1)(a) succeeds when this option is set (assuming it can find +an "a" in the subject), whereas it fails by default, for Perl compatibility. +.P +(3) \eU matches an upper case "U" character; by default \eU causes a compile +time error (Perl uses \eU to upper case subsequent characters). +.P +(4) \eu matches a lower case "u" character unless it is followed by four +hexadecimal digits, in which case the hexadecimal number defines the code point +to match. By default, \eu causes a compile time error (Perl uses it to upper +case the following character). +.P +(5) \ex matches a lower case "x" character unless it is followed by two +hexadecimal digits, in which case the hexadecimal number defines the code point +to match. By default, as in Perl, a hexadecimal number is always expected after +\ex, but it may have zero, one, or two digits (so, for example, \exz matches a +binary zero character followed by z). +.sp + PCRE_MULTILINE +.sp +By default, for the purposes of matching "start of line" and "end of line", +PCRE treats the subject string as consisting of a single line of characters, +even if it actually contains newlines. The "start of line" metacharacter (^) +matches only at the start of the string, and the "end of line" metacharacter +($) matches only at the end of the string, or before a terminating newline +(except when PCRE_DOLLAR_ENDONLY is set). Note, however, that unless +PCRE_DOTALL is set, the "any character" metacharacter (.) does not match at a +newline. This behaviour (for ^, $, and dot) is the same as Perl. +.P +When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs +match immediately following or immediately before internal newlines in the +subject string, respectively, as well as at the very start and end. This is +equivalent to Perl's /m option, and it can be changed within a pattern by a +(?m) option setting. If there are no newlines in a subject string, or no +occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect. +.sp + PCRE_NEVER_UTF +.sp +This option locks out interpretation of the pattern as UTF-8 (or UTF-16 or +UTF-32 in the 16-bit and 32-bit libraries). In particular, it prevents the +creator of the pattern from switching to UTF interpretation by starting the +pattern with (*UTF). This may be useful in applications that process patterns +from external sources. The combination of PCRE_UTF8 and PCRE_NEVER_UTF also +causes an error. +.sp + PCRE_NEWLINE_CR + PCRE_NEWLINE_LF + PCRE_NEWLINE_CRLF + PCRE_NEWLINE_ANYCRLF + PCRE_NEWLINE_ANY +.sp +These options override the default newline definition that was chosen when PCRE +was built. Setting the first or the second specifies that a newline is +indicated by a single character (CR or LF, respectively). Setting +PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character +CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three +preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies +that any Unicode newline sequence should be recognized. +.P +In an ASCII/Unicode environment, the Unicode newline sequences are the three +just mentioned, plus the single characters VT (vertical tab, U+000B), FF (form +feed, U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS +(paragraph separator, U+2029). For the 8-bit library, the last two are +recognized only in UTF-8 mode. +.P +When PCRE is compiled to run in an EBCDIC (mainframe) environment, the code for +CR is 0x0d, the same as ASCII. However, the character code for LF is normally +0x15, though in some EBCDIC environments 0x25 is used. Whichever of these is +not LF is made to correspond to Unicode's NEL character. EBCDIC codes are all +less than 256. For more details, see the +.\" HREF +\fBpcrebuild\fP +.\" +documentation. +.P +The newline setting in the options word uses three bits that are treated +as a number, giving eight possibilities. Currently only six are used (default +plus the five values above). This means that if you set more than one newline +option, the combination may or may not be sensible. For example, +PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but +other combinations may yield unused numbers and cause an error. +.P +The only time that a line break in a pattern is specially recognized when +compiling is when PCRE_EXTENDED is set. CR and LF are white space characters, +and so are ignored in this mode. Also, an unescaped # outside a character class +indicates a comment that lasts until after the next line break sequence. In +other circumstances, line break sequences in patterns are treated as literal +data. +.P +The newline option that is set at compile time becomes the default that is used +for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden. +.sp + PCRE_NO_AUTO_CAPTURE +.sp +If this option is set, it disables the use of numbered capturing parentheses in +the pattern. Any opening parenthesis that is not followed by ? behaves as if it +were followed by ?: but named parentheses can still be used for capturing (and +they acquire numbers in the usual way). There is no equivalent of this option +in Perl. +.sp + PCRE_NO_AUTO_POSSESS +.sp +If this option is set, it disables "auto-possessification". This is an +optimization that, for example, turns a+b into a++b in order to avoid +backtracks into a+ that can never be successful. However, if callouts are in +use, auto-possessification means that some of them are never taken. You can set +this option if you want the matching functions to do a full unoptimized search +and run all the callouts, but it is mainly provided for testing purposes. +.sp + PCRE_NO_START_OPTIMIZE +.sp +This is an option that acts at matching time; that is, it is really an option +for \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP. If it is set at compile time, +it is remembered with the compiled pattern and assumed at matching time. This +is necessary if you want to use JIT execution, because the JIT compiler needs +to know whether or not this option is set. For details see the discussion of +PCRE_NO_START_OPTIMIZE +.\" HTML <a href="#execoptions"> +.\" </a> +below. +.\" +.sp + PCRE_UCP +.sp +This option changes the way PCRE processes \eB, \eb, \eD, \ed, \eS, \es, \eW, +\ew, and some of the POSIX character classes. By default, only ASCII characters +are recognized, but if PCRE_UCP is set, Unicode properties are used instead to +classify characters. More details are given in the section on +.\" HTML <a href="pcre.html#genericchartypes"> +.\" </a> +generic character types +.\" +in the +.\" HREF +\fBpcrepattern\fP +.\" +page. If you set PCRE_UCP, matching one of the items it affects takes much +longer. The option is available only if PCRE has been compiled with Unicode +property support. +.sp + PCRE_UNGREEDY +.sp +This option inverts the "greediness" of the quantifiers so that they are not +greedy by default, but become greedy if followed by "?". It is not compatible +with Perl. It can also be set by a (?U) option setting within the pattern. +.sp + PCRE_UTF8 +.sp +This option causes PCRE to regard both the pattern and the subject as strings +of UTF-8 characters instead of single-byte strings. However, it is available +only when PCRE is built to include UTF support. If not, the use of this option +provokes an error. Details of how this option changes the behaviour of PCRE are +given in the +.\" HREF +\fBpcreunicode\fP +.\" +page. +.sp + PCRE_NO_UTF8_CHECK +.sp +When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is +automatically checked. There is a discussion about the +.\" HTML <a href="pcreunicode.html#utf8strings"> +.\" </a> +validity of UTF-8 strings +.\" +in the +.\" HREF +\fBpcreunicode\fP +.\" +page. If an invalid UTF-8 sequence is found, \fBpcre_compile()\fP returns an +error. If you already know that your pattern is valid, and you want to skip +this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK option. +When it is set, the effect of passing an invalid UTF-8 string as a pattern is +undefined. It may cause your program to crash or loop. Note that this option +can also be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress +the validity checking of subject strings only. If the same string is being +matched many times, the option can be safely set for the second and subsequent +matchings to improve performance. +. +. +.SH "COMPILATION ERROR CODES" +.rs +.sp +The following table lists the error codes than may be returned by +\fBpcre_compile2()\fP, along with the error messages that may be returned by +both compiling functions. Note that error messages are always 8-bit ASCII +strings, even in 16-bit or 32-bit mode. As PCRE has developed, some error codes +have fallen out of use. To avoid confusion, they have not been re-used. +.sp + 0 no error + 1 \e at end of pattern + 2 \ec at end of pattern + 3 unrecognized character follows \e + 4 numbers out of order in {} quantifier + 5 number too big in {} quantifier + 6 missing terminating ] for character class + 7 invalid escape sequence in character class + 8 range out of order in character class + 9 nothing to repeat + 10 [this code is not in use] + 11 internal error: unexpected repeat + 12 unrecognized character after (? or (?- + 13 POSIX named classes are supported only within a class + 14 missing ) + 15 reference to non-existent subpattern + 16 erroffset passed as NULL + 17 unknown option bit(s) set + 18 missing ) after comment + 19 [this code is not in use] + 20 regular expression is too large + 21 failed to get memory + 22 unmatched parentheses + 23 internal error: code overflow + 24 unrecognized character after (?< + 25 lookbehind assertion is not fixed length + 26 malformed number or name after (?( + 27 conditional group contains more than two branches + 28 assertion expected after (?( + 29 (?R or (?[+-]digits must be followed by ) + 30 unknown POSIX class name + 31 POSIX collating elements are not supported + 32 this version of PCRE is compiled without UTF support + 33 [this code is not in use] + 34 character value in \ex{} or \eo{} is too large + 35 invalid condition (?(0) + 36 \eC not allowed in lookbehind assertion + 37 PCRE does not support \eL, \el, \eN{name}, \eU, or \eu + 38 number after (?C is > 255 + 39 closing ) for (?C expected + 40 recursive call could loop indefinitely + 41 unrecognized character after (?P + 42 syntax error in subpattern name (missing terminator) + 43 two named subpatterns have the same name + 44 invalid UTF-8 string (specifically UTF-8) + 45 support for \eP, \ep, and \eX has not been compiled + 46 malformed \eP or \ep sequence + 47 unknown property name after \eP or \ep + 48 subpattern name is too long (maximum 32 characters) + 49 too many named subpatterns (maximum 10000) + 50 [this code is not in use] + 51 octal value is greater than \e377 in 8-bit non-UTF-8 mode + 52 internal error: overran compiling workspace + 53 internal error: previously-checked referenced subpattern + not found + 54 DEFINE group contains more than one branch + 55 repeating a DEFINE group is not allowed + 56 inconsistent NEWLINE options + 57 \eg is not followed by a braced, angle-bracketed, or quoted + name/number or by a plain number + 58 a numbered reference must not be zero + 59 an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT) + 60 (*VERB) not recognized or malformed + 61 number is too big + 62 subpattern name expected + 63 digit expected after (?+ + 64 ] is an invalid data character in JavaScript compatibility mode + 65 different names for subpatterns of the same number are + not allowed + 66 (*MARK) must have an argument + 67 this version of PCRE is not compiled with Unicode property + support + 68 \ec must be followed by an ASCII character + 69 \ek is not followed by a braced, angle-bracketed, or quoted name + 70 internal error: unknown opcode in find_fixedlength() + 71 \eN is not supported in a class + 72 too many forward references + 73 disallowed Unicode code point (>= 0xd800 && <= 0xdfff) + 74 invalid UTF-16 string (specifically UTF-16) + 75 name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN) + 76 character value in \eu.... sequence is too large + 77 invalid UTF-32 string (specifically UTF-32) + 78 setting UTF is disabled by the application + 79 non-hex character in \ex{} (closing brace missing?) + 80 non-octal character in \eo{} (closing brace missing?) + 81 missing opening brace after \eo + 82 parentheses are too deeply nested + 83 invalid range in character class + 84 group name must start with a non-digit + 85 parentheses are too deeply nested (stack check) +.sp +The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may +be used if the limits were changed when PCRE was built. +. +. +.\" HTML <a name="studyingapattern"></a> +.SH "STUDYING A PATTERN" +.rs +.sp +.nf +.B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP, +.B " const char **\fIerrptr\fP);" +.fi +.PP +If a compiled pattern is going to be used several times, it is worth spending +more time analyzing it in order to speed up the time taken for matching. The +function \fBpcre_study()\fP takes a pointer to a compiled pattern as its first +argument. If studying the pattern produces additional information that will +help speed up matching, \fBpcre_study()\fP returns a pointer to a +\fBpcre_extra\fP block, in which the \fIstudy_data\fP field points to the +results of the study. +.P +The returned value from \fBpcre_study()\fP can be passed directly to +\fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP. However, a \fBpcre_extra\fP block +also contains other fields that can be set by the caller before the block is +passed; these are described +.\" HTML <a href="#extradata"> +.\" </a> +below +.\" +in the section on matching a pattern. +.P +If studying the pattern does not produce any useful information, +\fBpcre_study()\fP returns NULL by default. In that circumstance, if the +calling program wants to pass any of the other fields to \fBpcre_exec()\fP or +\fBpcre_dfa_exec()\fP, it must set up its own \fBpcre_extra\fP block. However, +if \fBpcre_study()\fP is called with the PCRE_STUDY_EXTRA_NEEDED option, it +returns a \fBpcre_extra\fP block even if studying did not find any additional +information. It may still return NULL, however, if an error occurs in +\fBpcre_study()\fP. +.P +The second argument of \fBpcre_study()\fP contains option bits. There are three +further options in addition to PCRE_STUDY_EXTRA_NEEDED: +.sp + PCRE_STUDY_JIT_COMPILE + PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE + PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE +.sp +If any of these are set, and the just-in-time compiler is available, the +pattern is further compiled into machine code that executes much faster than +the \fBpcre_exec()\fP interpretive matching function. If the just-in-time +compiler is not available, these options are ignored. All undefined bits in the +\fIoptions\fP argument must be zero. +.P +JIT compilation is a heavyweight optimization. It can take some time for +patterns to be analyzed, and for one-off matches and simple patterns the +benefit of faster execution might be offset by a much slower study time. +Not all patterns can be optimized by the JIT compiler. For those that cannot be +handled, matching automatically falls back to the \fBpcre_exec()\fP +interpreter. For more details, see the +.\" HREF +\fBpcrejit\fP +.\" +documentation. +.P +The third argument for \fBpcre_study()\fP is a pointer for an error message. If +studying succeeds (even if no data is returned), the variable it points to is +set to NULL. Otherwise it is set to point to a textual error message. This is a +static string that is part of the library. You must not try to free it. You +should test the error pointer for NULL after calling \fBpcre_study()\fP, to be +sure that it has run successfully. +.P +When you are finished with a pattern, you can free the memory used for the +study data by calling \fBpcre_free_study()\fP. This function was added to the +API for release 8.20. For earlier versions, the memory could be freed with +\fBpcre_free()\fP, just like the pattern itself. This will still work in cases +where JIT optimization is not used, but it is advisable to change to the new +function when convenient. +.P +This is a typical way in which \fBpcre_study\fP() is used (except that in a +real application there should be tests for errors): +.sp + int rc; + pcre *re; + pcre_extra *sd; + re = pcre_compile("pattern", 0, &error, &erroroffset, NULL); + sd = pcre_study( + re, /* result of pcre_compile() */ + 0, /* no options */ + &error); /* set to NULL or points to a message */ + rc = pcre_exec( /* see below for details of pcre_exec() options */ + re, sd, "subject", 7, 0, 0, ovector, 30); + ... + pcre_free_study(sd); + pcre_free(re); +.sp +Studying a pattern does two things: first, a lower bound for the length of +subject string that is needed to match the pattern is computed. This does not +mean that there are any strings of that length that match, but it does +guarantee that no shorter strings match. The value is used to avoid wasting +time by trying to match strings that are shorter than the lower bound. You can +find out the value in a calling program via the \fBpcre_fullinfo()\fP function. +.P +Studying a pattern is also useful for non-anchored patterns that do not have a +single fixed starting character. A bitmap of possible starting bytes is +created. This speeds up finding a position in the subject at which to start +matching. (In 16-bit mode, the bitmap is used for 16-bit values less than 256. +In 32-bit mode, the bitmap is used for 32-bit values less than 256.) +.P +These two optimizations apply to both \fBpcre_exec()\fP and +\fBpcre_dfa_exec()\fP, and the information is also used by the JIT compiler. +The optimizations can be disabled by setting the PCRE_NO_START_OPTIMIZE option. +You might want to do this if your pattern contains callouts or (*MARK) and you +want to make use of these facilities in cases where matching fails. +.P +PCRE_NO_START_OPTIMIZE can be specified at either compile time or execution +time. However, if PCRE_NO_START_OPTIMIZE is passed to \fBpcre_exec()\fP, (that +is, after any JIT compilation has happened) JIT execution is disabled. For JIT +execution to work with PCRE_NO_START_OPTIMIZE, the option must be set at +compile time. +.P +There is a longer discussion of PCRE_NO_START_OPTIMIZE +.\" HTML <a href="#execoptions"> +.\" </a> +below. +.\" +. +. +.\" HTML <a name="localesupport"></a> +.SH "LOCALE SUPPORT" +.rs +.sp +PCRE handles caseless matching, and determines whether characters are letters, +digits, or whatever, by reference to a set of tables, indexed by character +code point. When running in UTF-8 mode, or in the 16- or 32-bit libraries, this +applies only to characters with code points less than 256. By default, +higher-valued code points never match escapes such as \ew or \ed. However, if +PCRE is built with Unicode property support, all characters can be tested with +\ep and \eP, or, alternatively, the PCRE_UCP option can be set when a pattern +is compiled; this causes \ew and friends to use Unicode property support +instead of the built-in tables. +.P +The use of locales with Unicode is discouraged. If you are handling characters +with code points greater than 128, you should either use Unicode support, or +use locales, but not try to mix the two. +.P +PCRE contains an internal set of tables that are used when the final argument +of \fBpcre_compile()\fP is NULL. These are sufficient for many applications. +Normally, the internal tables recognize only ASCII characters. However, when +PCRE is built, it is possible to cause the internal tables to be rebuilt in the +default "C" locale of the local system, which may cause them to be different. +.P +The internal tables can always be overridden by tables supplied by the +application that calls PCRE. These may be created in a different locale from +the default. As more and more applications change to using Unicode, the need +for this locale support is expected to die away. +.P +External tables are built by calling the \fBpcre_maketables()\fP function, +which has no arguments, in the relevant locale. The result can then be passed +to \fBpcre_compile()\fP as often as necessary. For example, to build and use +tables that are appropriate for the French locale (where accented characters +with values greater than 128 are treated as letters), the following code could +be used: +.sp + setlocale(LC_CTYPE, "fr_FR"); + tables = pcre_maketables(); + re = pcre_compile(..., tables); +.sp +The locale name "fr_FR" is used on Linux and other Unix-like systems; if you +are using Windows, the name for the French locale is "french". +.P +When \fBpcre_maketables()\fP runs, the tables are built in memory that is +obtained via \fBpcre_malloc\fP. It is the caller's responsibility to ensure +that the memory containing the tables remains available for as long as it is +needed. +.P +The pointer that is passed to \fBpcre_compile()\fP is saved with the compiled +pattern, and the same tables are used via this pointer by \fBpcre_study()\fP +and also by \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP. Thus, for any single +pattern, compilation, studying and matching all happen in the same locale, but +different patterns can be processed in different locales. +.P +It is possible to pass a table pointer or NULL (indicating the use of the +internal tables) to \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP (see the +discussion below in the section on matching a pattern). This facility is +provided for use with pre-compiled patterns that have been saved and reloaded. +Character tables are not saved with patterns, so if a non-standard table was +used at compile time, it must be provided again when the reloaded pattern is +matched. Attempting to use this facility to match a pattern in a different +locale from the one in which it was compiled is likely to lead to anomalous +(usually incorrect) results. +. +. +.\" HTML <a name="infoaboutpattern"></a> +.SH "INFORMATION ABOUT A PATTERN" +.rs +.sp +.nf +.B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," +.B " int \fIwhat\fP, void *\fIwhere\fP);" +.fi +.PP +The \fBpcre_fullinfo()\fP function returns information about a compiled +pattern. It replaces the \fBpcre_info()\fP function, which was removed from the +library at version 8.30, after more than 10 years of obsolescence. +.P +The first argument for \fBpcre_fullinfo()\fP is a pointer to the compiled +pattern. The second argument is the result of \fBpcre_study()\fP, or NULL if +the pattern was not studied. The third argument specifies which piece of +information is required, and the fourth argument is a pointer to a variable +to receive the data. The yield of the function is zero for success, or one of +the following negative numbers: +.sp + PCRE_ERROR_NULL the argument \fIcode\fP was NULL + the argument \fIwhere\fP was NULL + PCRE_ERROR_BADMAGIC the "magic number" was not found + PCRE_ERROR_BADENDIANNESS the pattern was compiled with different + endianness + PCRE_ERROR_BADOPTION the value of \fIwhat\fP was invalid + PCRE_ERROR_UNSET the requested field is not set +.sp +The "magic number" is placed at the start of each compiled pattern as an simple +check against passing an arbitrary memory pointer. The endianness error can +occur if a compiled pattern is saved and reloaded on a different host. Here is +a typical call of \fBpcre_fullinfo()\fP, to obtain the length of the compiled +pattern: +.sp + int rc; + size_t length; + rc = pcre_fullinfo( + re, /* result of pcre_compile() */ + sd, /* result of pcre_study(), or NULL */ + PCRE_INFO_SIZE, /* what is required */ + &length); /* where to put the data */ +.sp +The possible values for the third argument are defined in \fBpcre.h\fP, and are +as follows: +.sp + PCRE_INFO_BACKREFMAX +.sp +Return the number of the highest back reference in the pattern. The fourth +argument should point to an \fBint\fP variable. Zero is returned if there are +no back references. +.sp + PCRE_INFO_CAPTURECOUNT +.sp +Return the number of capturing subpatterns in the pattern. The fourth argument +should point to an \fBint\fP variable. +.sp + PCRE_INFO_DEFAULT_TABLES +.sp +Return a pointer to the internal default character tables within PCRE. The +fourth argument should point to an \fBunsigned char *\fP variable. This +information call is provided for internal use by the \fBpcre_study()\fP +function. External callers can cause PCRE to use its internal tables by passing +a NULL table pointer. +.sp + PCRE_INFO_FIRSTBYTE (deprecated) +.sp +Return information about the first data unit of any matched string, for a +non-anchored pattern. The name of this option refers to the 8-bit library, +where data units are bytes. The fourth argument should point to an \fBint\fP +variable. Negative values are used for special cases. However, this means that +when the 32-bit library is in non-UTF-32 mode, the full 32-bit range of +characters cannot be returned. For this reason, this value is deprecated; use +PCRE_INFO_FIRSTCHARACTERFLAGS and PCRE_INFO_FIRSTCHARACTER instead. +.P +If there is a fixed first value, for example, the letter "c" from a pattern +such as (cat|cow|coyote), its value is returned. In the 8-bit library, the +value is always less than 256. In the 16-bit library the value can be up to +0xffff. In the 32-bit library the value can be up to 0x10ffff. +.P +If there is no fixed first value, and if either +.sp +(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch +starts with "^", or +.sp +(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set +(if it were set, the pattern would be anchored), +.sp +-1 is returned, indicating that the pattern matches only at the start of a +subject string or after any newline within the string. Otherwise -2 is +returned. For anchored patterns, -2 is returned. +.sp + PCRE_INFO_FIRSTCHARACTER +.sp +Return the value of the first data unit (non-UTF character) of any matched +string in the situation where PCRE_INFO_FIRSTCHARACTERFLAGS returns 1; +otherwise return 0. The fourth argument should point to an \fBuint_t\fP +variable. +.P +In the 8-bit library, the value is always less than 256. In the 16-bit library +the value can be up to 0xffff. In the 32-bit library in UTF-32 mode the value +can be up to 0x10ffff, and up to 0xffffffff when not using UTF-32 mode. +.sp + PCRE_INFO_FIRSTCHARACTERFLAGS +.sp +Return information about the first data unit of any matched string, for a +non-anchored pattern. The fourth argument should point to an \fBint\fP +variable. +.P +If there is a fixed first value, for example, the letter "c" from a pattern +such as (cat|cow|coyote), 1 is returned, and the character value can be +retrieved using PCRE_INFO_FIRSTCHARACTER. If there is no fixed first value, and +if either +.sp +(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch +starts with "^", or +.sp +(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set +(if it were set, the pattern would be anchored), +.sp +2 is returned, indicating that the pattern matches only at the start of a +subject string or after any newline within the string. Otherwise 0 is +returned. For anchored patterns, 0 is returned. +.sp + PCRE_INFO_FIRSTTABLE +.sp +If the pattern was studied, and this resulted in the construction of a 256-bit +table indicating a fixed set of values for the first data unit in any matching +string, a pointer to the table is returned. Otherwise NULL is returned. The +fourth argument should point to an \fBunsigned char *\fP variable. +.sp + PCRE_INFO_HASCRORLF +.sp +Return 1 if the pattern contains any explicit matches for CR or LF characters, +otherwise 0. The fourth argument should point to an \fBint\fP variable. An +explicit match is either a literal CR or LF character, or \er or \en. +.sp + PCRE_INFO_JCHANGED +.sp +Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise +0. The fourth argument should point to an \fBint\fP variable. (?J) and +(?-J) set and unset the local PCRE_DUPNAMES option, respectively. +.sp + PCRE_INFO_JIT +.sp +Return 1 if the pattern was studied with one of the JIT options, and +just-in-time compiling was successful. The fourth argument should point to an +\fBint\fP variable. A return value of 0 means that JIT support is not available +in this version of PCRE, or that the pattern was not studied with a JIT option, +or that the JIT compiler could not handle this particular pattern. See the +.\" HREF +\fBpcrejit\fP +.\" +documentation for details of what can and cannot be handled. +.sp + PCRE_INFO_JITSIZE +.sp +If the pattern was successfully studied with a JIT option, return the size of +the JIT compiled code, otherwise return zero. The fourth argument should point +to a \fBsize_t\fP variable. +.sp + PCRE_INFO_LASTLITERAL +.sp +Return the value of the rightmost literal data unit that must exist in any +matched string, other than at its start, if such a value has been recorded. The +fourth argument should point to an \fBint\fP variable. If there is no such +value, -1 is returned. For anchored patterns, a last literal value is recorded +only if it follows something of variable length. For example, for the pattern +/^a\ed+z\ed+/ the returned value is "z", but for /^a\edz\ed/ the returned value +is -1. +.P +Since for the 32-bit library using the non-UTF-32 mode, this function is unable +to return the full 32-bit range of characters, this value is deprecated; +instead the PCRE_INFO_REQUIREDCHARFLAGS and PCRE_INFO_REQUIREDCHAR values should +be used. +.sp + PCRE_INFO_MATCH_EMPTY +.sp +Return 1 if the pattern can match an empty string, otherwise 0. The fourth +argument should point to an \fBint\fP variable. +.sp + PCRE_INFO_MATCHLIMIT +.sp +If the pattern set a match limit by including an item of the form +(*LIMIT_MATCH=nnnn) at the start, the value is returned. The fourth argument +should point to an unsigned 32-bit integer. If no such value has been set, the +call to \fBpcre_fullinfo()\fP returns the error PCRE_ERROR_UNSET. +.sp + PCRE_INFO_MAXLOOKBEHIND +.sp +Return the number of characters (NB not data units) in the longest lookbehind +assertion in the pattern. This information is useful when doing multi-segment +matching using the partial matching facilities. Note that the simple assertions +\eb and \eB require a one-character lookbehind. \eA also registers a +one-character lookbehind, though it does not actually inspect the previous +character. This is to ensure that at least one character from the old segment +is retained when a new segment is processed. Otherwise, if there are no +lookbehinds in the pattern, \eA might match incorrectly at the start of a new +segment. +.sp + PCRE_INFO_MINLENGTH +.sp +If the pattern was studied and a minimum length for matching subject strings +was computed, its value is returned. Otherwise the returned value is -1. The +value is a number of characters, which in UTF mode may be different from the +number of data units. The fourth argument should point to an \fBint\fP +variable. A non-negative value is a lower bound to the length of any matching +string. There may not be any strings of that length that do actually match, but +every string that does match is at least that long. +.sp + PCRE_INFO_NAMECOUNT + PCRE_INFO_NAMEENTRYSIZE + PCRE_INFO_NAMETABLE +.sp +PCRE supports the use of named as well as numbered capturing parentheses. The +names are just an additional way of identifying the parentheses, which still +acquire numbers. Several convenience functions such as +\fBpcre_get_named_substring()\fP are provided for extracting captured +substrings by name. It is also possible to extract the data directly, by first +converting the name to a number in order to access the correct pointers in the +output vector (described with \fBpcre_exec()\fP below). To do the conversion, +you need to use the name-to-number map, which is described by these three +values. +.P +The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT gives +the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each +entry; both of these return an \fBint\fP value. The entry size depends on the +length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first +entry of the table. This is a pointer to \fBchar\fP in the 8-bit library, where +the first two bytes of each entry are the number of the capturing parenthesis, +most significant byte first. In the 16-bit library, the pointer points to +16-bit data units, the first of which contains the parenthesis number. In the +32-bit library, the pointer points to 32-bit data units, the first of which +contains the parenthesis number. The rest of the entry is the corresponding +name, zero terminated. +.P +The names are in alphabetical order. If (?| is used to create multiple groups +with the same number, as described in the +.\" HTML <a href="pcrepattern.html#dupsubpatternnumber"> +.\" </a> +section on duplicate subpattern numbers +.\" +in the +.\" HREF +\fBpcrepattern\fP +.\" +page, the groups may be given the same name, but there is only one entry in the +table. Different names for groups of the same number are not permitted. +Duplicate names for subpatterns with different numbers are permitted, +but only if PCRE_DUPNAMES is set. They appear in the table in the order in +which they were found in the pattern. In the absence of (?| this is the order +of increasing number; when (?| is used this is not necessarily the case because +later subpatterns may have lower numbers. +.P +As a simple example of the name/number table, consider the following pattern +after compilation by the 8-bit library (assume PCRE_EXTENDED is set, so white +space - including newlines - is ignored): +.sp +.\" JOIN + (?<date> (?<year>(\ed\ed)?\ed\ed) - + (?<month>\ed\ed) - (?<day>\ed\ed) ) +.sp +There are four named subpatterns, so the table has four entries, and each entry +in the table is eight bytes long. The table is as follows, with non-printing +bytes shows in hexadecimal, and undefined bytes shown as ??: +.sp + 00 01 d a t e 00 ?? + 00 05 d a y 00 ?? ?? + 00 04 m o n t h 00 + 00 02 y e a r 00 ?? +.sp +When writing code to extract data from named subpatterns using the +name-to-number map, remember that the length of the entries is likely to be +different for each compiled pattern. +.sp + PCRE_INFO_OKPARTIAL +.sp +Return 1 if the pattern can be used for partial matching with +\fBpcre_exec()\fP, otherwise 0. The fourth argument should point to an +\fBint\fP variable. From release 8.00, this always returns 1, because the +restrictions that previously applied to partial matching have been lifted. The +.\" HREF +\fBpcrepartial\fP +.\" +documentation gives details of partial matching. +.sp + PCRE_INFO_OPTIONS +.sp +Return a copy of the options with which the pattern was compiled. The fourth +argument should point to an \fBunsigned long int\fP variable. These option bits +are those specified in the call to \fBpcre_compile()\fP, modified by any +top-level option settings at the start of the pattern itself. In other words, +they are the options that will be in force when matching starts. For example, +if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the +result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED. +.P +A pattern is automatically anchored by PCRE if all of its top-level +alternatives begin with one of the following: +.sp + ^ unless PCRE_MULTILINE is set + \eA always + \eG always +.\" JOIN + .* if PCRE_DOTALL is set and there are no back + references to the subpattern in which .* appears +.sp +For such patterns, the PCRE_ANCHORED bit is set in the options returned by +\fBpcre_fullinfo()\fP. +.sp + PCRE_INFO_RECURSIONLIMIT +.sp +If the pattern set a recursion limit by including an item of the form +(*LIMIT_RECURSION=nnnn) at the start, the value is returned. The fourth +argument should point to an unsigned 32-bit integer. If no such value has been +set, the call to \fBpcre_fullinfo()\fP returns the error PCRE_ERROR_UNSET. +.sp + PCRE_INFO_SIZE +.sp +Return the size of the compiled pattern in bytes (for all three libraries). The +fourth argument should point to a \fBsize_t\fP variable. This value does not +include the size of the \fBpcre\fP structure that is returned by +\fBpcre_compile()\fP. The value that is passed as the argument to +\fBpcre_malloc()\fP when \fBpcre_compile()\fP is getting memory in which to +place the compiled data is the value returned by this option plus the size of +the \fBpcre\fP structure. Studying a compiled pattern, with or without JIT, +does not alter the value returned by this option. +.sp + PCRE_INFO_STUDYSIZE +.sp +Return the size in bytes (for all three libraries) of the data block pointed to +by the \fIstudy_data\fP field in a \fBpcre_extra\fP block. If \fBpcre_extra\fP +is NULL, or there is no study data, zero is returned. The fourth argument +should point to a \fBsize_t\fP variable. The \fIstudy_data\fP field is set by +\fBpcre_study()\fP to record information that will speed up matching (see the +section entitled +.\" HTML <a href="#studyingapattern"> +.\" </a> +"Studying a pattern" +.\" +above). The format of the \fIstudy_data\fP block is private, but its length +is made available via this option so that it can be saved and restored (see the +.\" HREF +\fBpcreprecompile\fP +.\" +documentation for details). +.sp + PCRE_INFO_REQUIREDCHARFLAGS +.sp +Returns 1 if there is a rightmost literal data unit that must exist in any +matched string, other than at its start. The fourth argument should point to +an \fBint\fP variable. If there is no such value, 0 is returned. If returning +1, the character value itself can be retrieved using PCRE_INFO_REQUIREDCHAR. +.P +For anchored patterns, a last literal value is recorded only if it follows +something of variable length. For example, for the pattern /^a\ed+z\ed+/ the +returned value 1 (with "z" returned from PCRE_INFO_REQUIREDCHAR), but for +/^a\edz\ed/ the returned value is 0. +.sp + PCRE_INFO_REQUIREDCHAR +.sp +Return the value of the rightmost literal data unit that must exist in any +matched string, other than at its start, if such a value has been recorded. The +fourth argument should point to an \fBuint32_t\fP variable. If there is no such +value, 0 is returned. +. +. +.SH "REFERENCE COUNTS" +.rs +.sp +.B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP); +.PP +The \fBpcre_refcount()\fP function is used to maintain a reference count in the +data block that contains a compiled pattern. It is provided for the benefit of +applications that operate in an object-oriented manner, where different parts +of the application may be using the same compiled pattern, but you want to free +the block when they are all done. +.P +When a pattern is compiled, the reference count field is initialized to zero. +It is changed only by calling this function, whose action is to add the +\fIadjust\fP value (which may be positive or negative) to it. The yield of the +function is the new value. However, the value of the count is constrained to +lie between 0 and 65535, inclusive. If the new value is outside these limits, +it is forced to the appropriate limit value. +.P +Except when it is zero, the reference count is not correctly preserved if a +pattern is compiled on one host and then transferred to a host whose byte-order +is different. (This seems a highly unlikely scenario.) +. +. +.SH "MATCHING A PATTERN: THE TRADITIONAL FUNCTION" +.rs +.sp +.nf +.B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," +.B " const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP, +.B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);" +.fi +.P +The function \fBpcre_exec()\fP is called to match a subject string against a +compiled pattern, which is passed in the \fIcode\fP argument. If the +pattern was studied, the result of the study should be passed in the +\fIextra\fP argument. You can call \fBpcre_exec()\fP with the same \fIcode\fP +and \fIextra\fP arguments as many times as you like, in order to match +different subject strings with the same pattern. +.P +This function is the main matching facility of the library, and it operates in +a Perl-like manner. For specialist use there is also an alternative matching +function, which is described +.\" HTML <a href="#dfamatch"> +.\" </a> +below +.\" +in the section about the \fBpcre_dfa_exec()\fP function. +.P +In most applications, the pattern will have been compiled (and optionally +studied) in the same process that calls \fBpcre_exec()\fP. However, it is +possible to save compiled patterns and study data, and then use them later +in different processes, possibly even on different hosts. For a discussion +about this, see the +.\" HREF +\fBpcreprecompile\fP +.\" +documentation. +.P +Here is an example of a simple call to \fBpcre_exec()\fP: +.sp + int rc; + int ovector[30]; + rc = pcre_exec( + re, /* result of pcre_compile() */ + NULL, /* we didn't study the pattern */ + "some string", /* the subject string */ + 11, /* the length of the subject string */ + 0, /* start at offset 0 in the subject */ + 0, /* default options */ + ovector, /* vector of integers for substring information */ + 30); /* number of elements (NOT size in bytes) */ +. +. +.\" HTML <a name="extradata"></a> +.SS "Extra data for \fBpcre_exec()\fR" +.rs +.sp +If the \fIextra\fP argument is not NULL, it must point to a \fBpcre_extra\fP +data block. The \fBpcre_study()\fP function returns such a block (when it +doesn't return NULL), but you can also create one for yourself, and pass +additional information in it. The \fBpcre_extra\fP block contains the following +fields (not necessarily in this order): +.sp + unsigned long int \fIflags\fP; + void *\fIstudy_data\fP; + void *\fIexecutable_jit\fP; + unsigned long int \fImatch_limit\fP; + unsigned long int \fImatch_limit_recursion\fP; + void *\fIcallout_data\fP; + const unsigned char *\fItables\fP; + unsigned char **\fImark\fP; +.sp +In the 16-bit version of this structure, the \fImark\fP field has type +"PCRE_UCHAR16 **". +.sp +In the 32-bit version of this structure, the \fImark\fP field has type +"PCRE_UCHAR32 **". +.P +The \fIflags\fP field is used to specify which of the other fields are set. The +flag bits are: +.sp + PCRE_EXTRA_CALLOUT_DATA + PCRE_EXTRA_EXECUTABLE_JIT + PCRE_EXTRA_MARK + PCRE_EXTRA_MATCH_LIMIT + PCRE_EXTRA_MATCH_LIMIT_RECURSION + PCRE_EXTRA_STUDY_DATA + PCRE_EXTRA_TABLES +.sp +Other flag bits should be set to zero. The \fIstudy_data\fP field and sometimes +the \fIexecutable_jit\fP field are set in the \fBpcre_extra\fP block that is +returned by \fBpcre_study()\fP, together with the appropriate flag bits. You +should not set these yourself, but you may add to the block by setting other +fields and their corresponding flag bits. +.P +The \fImatch_limit\fP field provides a means of preventing PCRE from using up a +vast amount of resources when running patterns that are not going to match, +but which have a very large number of possibilities in their search trees. The +classic example is a pattern that uses nested unlimited repeats. +.P +Internally, \fBpcre_exec()\fP uses a function called \fBmatch()\fP, which it +calls repeatedly (sometimes recursively). The limit set by \fImatch_limit\fP is +imposed on the number of times this function is called during a match, which +has the effect of limiting the amount of backtracking that can take place. For +patterns that are not anchored, the count restarts from zero for each position +in the subject string. +.P +When \fBpcre_exec()\fP is called with a pattern that was successfully studied +with a JIT option, the way that the matching is executed is entirely different. +However, there is still the possibility of runaway matching that goes on for a +very long time, and so the \fImatch_limit\fP value is also used in this case +(but in a different way) to limit how long the matching can continue. +.P +The default value for the limit can be set when PCRE is built; the default +default is 10 million, which handles all but the most extreme cases. You can +override the default by suppling \fBpcre_exec()\fP with a \fBpcre_extra\fP +block in which \fImatch_limit\fP is set, and PCRE_EXTRA_MATCH_LIMIT is set in +the \fIflags\fP field. If the limit is exceeded, \fBpcre_exec()\fP returns +PCRE_ERROR_MATCHLIMIT. +.P +A value for the match limit may also be supplied by an item at the start of a +pattern of the form +.sp + (*LIMIT_MATCH=d) +.sp +where d is a decimal number. However, such a setting is ignored unless d is +less than the limit set by the caller of \fBpcre_exec()\fP or, if no such limit +is set, less than the default. +.P +The \fImatch_limit_recursion\fP field is similar to \fImatch_limit\fP, but +instead of limiting the total number of times that \fBmatch()\fP is called, it +limits the depth of recursion. The recursion depth is a smaller number than the +total number of calls, because not all calls to \fBmatch()\fP are recursive. +This limit is of use only if it is set smaller than \fImatch_limit\fP. +.P +Limiting the recursion depth limits the amount of machine stack that can be +used, or, when PCRE has been compiled to use memory on the heap instead of the +stack, the amount of heap memory that can be used. This limit is not relevant, +and is ignored, when matching is done using JIT compiled code. +.P +The default value for \fImatch_limit_recursion\fP can be set when PCRE is +built; the default default is the same value as the default for +\fImatch_limit\fP. You can override the default by suppling \fBpcre_exec()\fP +with a \fBpcre_extra\fP block in which \fImatch_limit_recursion\fP is set, and +PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the \fIflags\fP field. If the limit +is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT. +.P +A value for the recursion limit may also be supplied by an item at the start of +a pattern of the form +.sp + (*LIMIT_RECURSION=d) +.sp +where d is a decimal number. However, such a setting is ignored unless d is +less than the limit set by the caller of \fBpcre_exec()\fP or, if no such limit +is set, less than the default. +.P +The \fIcallout_data\fP field is used in conjunction with the "callout" feature, +and is described in the +.\" HREF +\fBpcrecallout\fP +.\" +documentation. +.P +The \fItables\fP field is provided for use with patterns that have been +pre-compiled using custom character tables, saved to disc or elsewhere, and +then reloaded, because the tables that were used to compile a pattern are not +saved with it. See the +.\" HREF +\fBpcreprecompile\fP +.\" +documentation for a discussion of saving compiled patterns for later use. If +NULL is passed using this mechanism, it forces PCRE's internal tables to be +used. +.P +\fBWarning:\fP The tables that \fBpcre_exec()\fP uses must be the same as those +that were used when the pattern was compiled. If this is not the case, the +behaviour of \fBpcre_exec()\fP is undefined. Therefore, when a pattern is +compiled and matched in the same process, this field should never be set. In +this (the most common) case, the correct table pointer is automatically passed +with the compiled pattern from \fBpcre_compile()\fP to \fBpcre_exec()\fP. +.P +If PCRE_EXTRA_MARK is set in the \fIflags\fP field, the \fImark\fP field must +be set to point to a suitable variable. If the pattern contains any +backtracking control verbs such as (*MARK:NAME), and the execution ends up with +a name to pass back, a pointer to the name string (zero terminated) is placed +in the variable pointed to by the \fImark\fP field. The names are within the +compiled pattern; if you wish to retain such a name you must copy it before +freeing the memory of a compiled pattern. If there is no name to pass back, the +variable pointed to by the \fImark\fP field is set to NULL. For details of the +backtracking control verbs, see the section entitled +.\" HTML <a href="pcrepattern#backtrackcontrol"> +.\" </a> +"Backtracking control" +.\" +in the +.\" HREF +\fBpcrepattern\fP +.\" +documentation. +. +. +.\" HTML <a name="execoptions"></a> +.SS "Option bits for \fBpcre_exec()\fP" +.rs +.sp +The unused bits of the \fIoptions\fP argument for \fBpcre_exec()\fP must be +zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP, +PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, +PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_HARD, and +PCRE_PARTIAL_SOFT. +.P +If the pattern was successfully studied with one of the just-in-time (JIT) +compile options, the only supported options for JIT execution are +PCRE_NO_UTF8_CHECK, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, +PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and PCRE_PARTIAL_SOFT. If an +unsupported option is used, JIT execution is disabled and the normal +interpretive code in \fBpcre_exec()\fP is run. +.sp + PCRE_ANCHORED +.sp +The PCRE_ANCHORED option limits \fBpcre_exec()\fP to matching at the first +matching position. If a pattern was compiled with PCRE_ANCHORED, or turned out +to be anchored by virtue of its contents, it cannot be made unachored at +matching time. +.sp + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE +.sp +These options (which are mutually exclusive) control what the \eR escape +sequence matches. The choice is either to match only CR, LF, or CRLF, or to +match any Unicode newline sequence. These options override the choice that was +made or defaulted when the pattern was compiled. +.sp + PCRE_NEWLINE_CR + PCRE_NEWLINE_LF + PCRE_NEWLINE_CRLF + PCRE_NEWLINE_ANYCRLF + PCRE_NEWLINE_ANY +.sp +These options override the newline definition that was chosen or defaulted when +the pattern was compiled. For details, see the description of +\fBpcre_compile()\fP above. During matching, the newline choice affects the +behaviour of the dot, circumflex, and dollar metacharacters. It may also alter +the way the match position is advanced after a match failure for an unanchored +pattern. +.P +When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is set, and a +match attempt for an unanchored pattern fails when the current position is at a +CRLF sequence, and the pattern contains no explicit matches for CR or LF +characters, the match position is advanced by two characters instead of one, in +other words, to after the CRLF. +.P +The above rule is a compromise that makes the most common cases work as +expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not +set), it does not match the string "\er\enA" because, after failing at the +start, it skips both the CR and the LF before retrying. However, the pattern +[\er\en]A does match that string, because it contains an explicit CR or LF +reference, and so advances only by one character after the first failure. +.P +An explicit match for CR of LF is either a literal appearance of one of those +characters, or one of the \er or \en escape sequences. Implicit matches such as +[^X] do not count, nor does \es (which includes CR and LF in the characters +that it matches). +.P +Notwithstanding the above, anomalous effects may still occur when CRLF is a +valid newline sequence and explicit \er or \en escapes appear in the pattern. +.sp + PCRE_NOTBOL +.sp +This option specifies that first character of the subject string is not the +beginning of a line, so the circumflex metacharacter should not match before +it. Setting this without PCRE_MULTILINE (at compile time) causes circumflex +never to match. This option affects only the behaviour of the circumflex +metacharacter. It does not affect \eA. +.sp + PCRE_NOTEOL +.sp +This option specifies that the end of the subject string is not the end of a +line, so the dollar metacharacter should not match it nor (except in multiline +mode) a newline immediately before it. Setting this without PCRE_MULTILINE (at +compile time) causes dollar never to match. This option affects only the +behaviour of the dollar metacharacter. It does not affect \eZ or \ez. +.sp + PCRE_NOTEMPTY +.sp +An empty string is not considered to be a valid match if this option is set. If +there are alternatives in the pattern, they are tried. If all the alternatives +match the empty string, the entire match fails. For example, if the pattern +.sp + a?b? +.sp +is applied to a string not beginning with "a" or "b", it matches an empty +string at the start of the subject. With PCRE_NOTEMPTY set, this match is not +valid, so PCRE searches further into the string for occurrences of "a" or "b". +.sp + PCRE_NOTEMPTY_ATSTART +.sp +This is like PCRE_NOTEMPTY, except that an empty string match that is not at +the start of the subject is permitted. If the pattern is anchored, such a match +can occur only if the pattern contains \eK. +.P +Perl has no direct equivalent of PCRE_NOTEMPTY or PCRE_NOTEMPTY_ATSTART, but it +does make a special case of a pattern match of the empty string within its +\fBsplit()\fP function, and when using the /g modifier. It is possible to +emulate Perl's behaviour after matching a null string by first trying the match +again at the same offset with PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED, and then +if that fails, by advancing the starting offset (see below) and trying an +ordinary match again. There is some code that demonstrates how to do this in +the +.\" HREF +\fBpcredemo\fP +.\" +sample program. In the most general case, you have to check to see if the +newline convention recognizes CRLF as a newline, and if so, and the current +character is CR followed by LF, advance the starting offset by two characters +instead of one. +.sp + PCRE_NO_START_OPTIMIZE +.sp +There are a number of optimizations that \fBpcre_exec()\fP uses at the start of +a match, in order to speed up the process. For example, if it is known that an +unanchored match must start with a specific character, it searches the subject +for that character, and fails immediately if it cannot find it, without +actually running the main matching function. This means that a special item +such as (*COMMIT) at the start of a pattern is not considered until after a +suitable starting point for the match has been found. Also, when callouts or +(*MARK) items are in use, these "start-up" optimizations can cause them to be +skipped if the pattern is never actually used. The start-up optimizations are +in effect a pre-scan of the subject that takes place before the pattern is run. +.P +The PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, possibly +causing performance to suffer, but ensuring that in cases where the result is +"no match", the callouts do occur, and that items such as (*COMMIT) and (*MARK) +are considered at every possible starting position in the subject string. If +PCRE_NO_START_OPTIMIZE is set at compile time, it cannot be unset at matching +time. The use of PCRE_NO_START_OPTIMIZE at matching time (that is, passing it +to \fBpcre_exec()\fP) disables JIT execution; in this situation, matching is +always done using interpretively. +.P +Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching operation. +Consider the pattern +.sp + (*COMMIT)ABC +.sp +When this is compiled, PCRE records the fact that a match must start with the +character "A". Suppose the subject string is "DEFABC". The start-up +optimization scans along the subject, finds "A" and runs the first match +attempt from there. The (*COMMIT) item means that the pattern must match the +current starting position, which in this case, it does. However, if the same +match is run with PCRE_NO_START_OPTIMIZE set, the initial scan along the +subject string does not happen. The first match attempt is run starting from +"D" and when this fails, (*COMMIT) prevents any further matches being tried, so +the overall result is "no match". If the pattern is studied, more start-up +optimizations may be used. For example, a minimum length for the subject may be +recorded. Consider the pattern +.sp + (*MARK:A)(X|Y) +.sp +The minimum length for a match is one character. If the subject is "ABC", there +will be attempts to match "ABC", "BC", "C", and then finally an empty string. +If the pattern is studied, the final attempt does not take place, because PCRE +knows that the subject is too short, and so the (*MARK) is never encountered. +In this case, studying the pattern does not affect the overall match result, +which is still "no match", but it does affect the auxiliary information that is +returned. +.sp + PCRE_NO_UTF8_CHECK +.sp +When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8 +string is automatically checked when \fBpcre_exec()\fP is subsequently called. +The entire string is checked before any other processing takes place. The value +of \fIstartoffset\fP is also checked to ensure that it points to the start of a +UTF-8 character. There is a discussion about the +.\" HTML <a href="pcreunicode.html#utf8strings"> +.\" </a> +validity of UTF-8 strings +.\" +in the +.\" HREF +\fBpcreunicode\fP +.\" +page. If an invalid sequence of bytes is found, \fBpcre_exec()\fP returns the +error PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is a +truncated character at the end of the subject, PCRE_ERROR_SHORTUTF8. In both +cases, information about the precise nature of the error may also be returned +(see the descriptions of these errors in the section entitled \fIError return +values from\fP \fBpcre_exec()\fP +.\" HTML <a href="#errorlist"> +.\" </a> +below). +.\" +If \fIstartoffset\fP contains a value that does not point to the start of a +UTF-8 character (or to the end of the subject), PCRE_ERROR_BADUTF8_OFFSET is +returned. +.P +If you already know that your subject is valid, and you want to skip these +checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when +calling \fBpcre_exec()\fP. You might want to do this for the second and +subsequent calls to \fBpcre_exec()\fP if you are making repeated calls to find +all the matches in a single subject string. However, you should be sure that +the value of \fIstartoffset\fP points to the start of a character (or the end +of the subject). When PCRE_NO_UTF8_CHECK is set, the effect of passing an +invalid string as a subject or an invalid value of \fIstartoffset\fP is +undefined. Your program may crash or loop. +.sp + PCRE_PARTIAL_HARD + PCRE_PARTIAL_SOFT +.sp +These options turn on the partial matching feature. For backwards +compatibility, PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. A partial match +occurs if the end of the subject string is reached successfully, but there are +not enough subject characters to complete the match. If this happens when +PCRE_PARTIAL_SOFT (but not PCRE_PARTIAL_HARD) is set, matching continues by +testing any remaining alternatives. Only if no complete match can be found is +PCRE_ERROR_PARTIAL returned instead of PCRE_ERROR_NOMATCH. In other words, +PCRE_PARTIAL_SOFT says that the caller is prepared to handle a partial match, +but only if no complete match can be found. +.P +If PCRE_PARTIAL_HARD is set, it overrides PCRE_PARTIAL_SOFT. In this case, if a +partial match is found, \fBpcre_exec()\fP immediately returns +PCRE_ERROR_PARTIAL, without considering any other alternatives. In other words, +when PCRE_PARTIAL_HARD is set, a partial match is considered to be more +important that an alternative complete match. +.P +In both cases, the portion of the string that was inspected when the partial +match was found is set as the first matching string. There is a more detailed +discussion of partial and multi-segment matching, with examples, in the +.\" HREF +\fBpcrepartial\fP +.\" +documentation. +. +. +.SS "The string to be matched by \fBpcre_exec()\fP" +.rs +.sp +The subject string is passed to \fBpcre_exec()\fP as a pointer in +\fIsubject\fP, a length in \fIlength\fP, and a starting offset in +\fIstartoffset\fP. The units for \fIlength\fP and \fIstartoffset\fP are bytes +for the 8-bit library, 16-bit data items for the 16-bit library, and 32-bit +data items for the 32-bit library. +.P +If \fIstartoffset\fP is negative or greater than the length of the subject, +\fBpcre_exec()\fP returns PCRE_ERROR_BADOFFSET. When the starting offset is +zero, the search for a match starts at the beginning of the subject, and this +is by far the most common case. In UTF-8 or UTF-16 mode, the offset must point +to the start of a character, or the end of the subject (in UTF-32 mode, one +data unit equals one character, so all offsets are valid). Unlike the pattern +string, the subject may contain binary zeroes. +.P +A non-zero starting offset is useful when searching for another match in the +same subject by calling \fBpcre_exec()\fP again after a previous success. +Setting \fIstartoffset\fP differs from just passing over a shortened string and +setting PCRE_NOTBOL in the case of a pattern that begins with any kind of +lookbehind. For example, consider the pattern +.sp + \eBiss\eB +.sp +which finds occurrences of "iss" in the middle of words. (\eB matches only if +the current position in the subject is not a word boundary.) When applied to +the string "Mississipi" the first call to \fBpcre_exec()\fP finds the first +occurrence. If \fBpcre_exec()\fP is called again with just the remainder of the +subject, namely "issipi", it does not match, because \eB is always false at the +start of the subject, which is deemed to be a word boundary. However, if +\fBpcre_exec()\fP is passed the entire string again, but with \fIstartoffset\fP +set to 4, it finds the second occurrence of "iss" because it is able to look +behind the starting point to discover that it is preceded by a letter. +.P +Finding all the matches in a subject is tricky when the pattern can match an +empty string. It is possible to emulate Perl's /g behaviour by first trying the +match again at the same offset, with the PCRE_NOTEMPTY_ATSTART and +PCRE_ANCHORED options, and then if that fails, advancing the starting offset +and trying an ordinary match again. There is some code that demonstrates how to +do this in the +.\" HREF +\fBpcredemo\fP +.\" +sample program. In the most general case, you have to check to see if the +newline convention recognizes CRLF as a newline, and if so, and the current +character is CR followed by LF, advance the starting offset by two characters +instead of one. +.P +If a non-zero starting offset is passed when the pattern is anchored, one +attempt to match at the given offset is made. This can only succeed if the +pattern does not require the match to be at the start of the subject. +. +. +.SS "How \fBpcre_exec()\fP returns captured substrings" +.rs +.sp +In general, a pattern matches a certain portion of the subject, and in +addition, further substrings from the subject may be picked out by parts of the +pattern. Following the usage in Jeffrey Friedl's book, this is called +"capturing" in what follows, and the phrase "capturing subpattern" is used for +a fragment of a pattern that picks out a substring. PCRE supports several other +kinds of parenthesized subpattern that do not cause substrings to be captured. +.P +Captured substrings are returned to the caller via a vector of integers whose +address is passed in \fIovector\fP. The number of elements in the vector is +passed in \fIovecsize\fP, which must be a non-negative number. \fBNote\fP: this +argument is NOT the size of \fIovector\fP in bytes. +.P +The first two-thirds of the vector is used to pass back captured substrings, +each substring using a pair of integers. The remaining third of the vector is +used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns, +and is not available for passing back information. The number passed in +\fIovecsize\fP should always be a multiple of three. If it is not, it is +rounded down. +.P +When a match is successful, information about captured substrings is returned +in pairs of integers, starting at the beginning of \fIovector\fP, and +continuing up to two-thirds of its length at the most. The first element of +each pair is set to the offset of the first character in a substring, and the +second is set to the offset of the first character after the end of a +substring. These values are always data unit offsets, even in UTF mode. They +are byte offsets in the 8-bit library, 16-bit data item offsets in the 16-bit +library, and 32-bit data item offsets in the 32-bit library. \fBNote\fP: they +are not character counts. +.P +The first pair of integers, \fIovector[0]\fP and \fIovector[1]\fP, identify the +portion of the subject string matched by the entire pattern. The next pair is +used for the first capturing subpattern, and so on. The value returned by +\fBpcre_exec()\fP is one more than the highest numbered pair that has been set. +For example, if two substrings have been captured, the returned value is 3. If +there are no capturing subpatterns, the return value from a successful match is +1, indicating that just the first pair of offsets has been set. +.P +If a capturing subpattern is matched repeatedly, it is the last portion of the +string that it matched that is returned. +.P +If the vector is too small to hold all the captured substring offsets, it is +used as far as possible (up to two-thirds of its length), and the function +returns a value of zero. If neither the actual string matched nor any captured +substrings are of interest, \fBpcre_exec()\fP may be called with \fIovector\fP +passed as NULL and \fIovecsize\fP as zero. However, if the pattern contains +back references and the \fIovector\fP is not big enough to remember the related +substrings, PCRE has to get additional memory for use during matching. Thus it +is usually advisable to supply an \fIovector\fP of reasonable size. +.P +There are some cases where zero is returned (indicating vector overflow) when +in fact the vector is exactly the right size for the final match. For example, +consider the pattern +.sp + (a)(?:(b)c|bd) +.sp +If a vector of 6 elements (allowing for only 1 captured substring) is given +with subject string "abd", \fBpcre_exec()\fP will try to set the second +captured string, thereby recording a vector overflow, before failing to match +"c" and backing up to try the second alternative. The zero return, however, +does correctly indicate that the maximum number of slots (namely 2) have been +filled. In similar cases where there is temporary overflow, but the final +number of used slots is actually less than the maximum, a non-zero value is +returned. +.P +The \fBpcre_fullinfo()\fP function can be used to find out how many capturing +subpatterns there are in a compiled pattern. The smallest size for +\fIovector\fP that will allow for \fIn\fP captured substrings, in addition to +the offsets of the substring matched by the whole pattern, is (\fIn\fP+1)*3. +.P +It is possible for capturing subpattern number \fIn+1\fP to match some part of +the subject when subpattern \fIn\fP has not been used at all. For example, if +the string "abc" is matched against the pattern (a|(z))(bc) the return from the +function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this +happens, both values in the offset pairs corresponding to unused subpatterns +are set to -1. +.P +Offset values that correspond to unused subpatterns at the end of the +expression are also set to -1. For example, if the string "abc" is matched +against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The +return from the function is 2, because the highest used capturing subpattern +number is 1, and the offsets for for the second and third capturing subpatterns +(assuming the vector is large enough, of course) are set to -1. +.P +\fBNote\fP: Elements in the first two-thirds of \fIovector\fP that do not +correspond to capturing parentheses in the pattern are never changed. That is, +if a pattern contains \fIn\fP capturing parentheses, no more than +\fIovector[0]\fP to \fIovector[2n+1]\fP are set by \fBpcre_exec()\fP. The other +elements (in the first two-thirds) retain whatever values they previously had. +.P +Some convenience functions are provided for extracting the captured substrings +as separate strings. These are described below. +. +. +.\" HTML <a name="errorlist"></a> +.SS "Error return values from \fBpcre_exec()\fP" +.rs +.sp +If \fBpcre_exec()\fP fails, it returns a negative number. The following are +defined in the header file: +.sp + PCRE_ERROR_NOMATCH (-1) +.sp +The subject string did not match the pattern. +.sp + PCRE_ERROR_NULL (-2) +.sp +Either \fIcode\fP or \fIsubject\fP was passed as NULL, or \fIovector\fP was +NULL and \fIovecsize\fP was not zero. +.sp + PCRE_ERROR_BADOPTION (-3) +.sp +An unrecognized bit was set in the \fIoptions\fP argument. +.sp + PCRE_ERROR_BADMAGIC (-4) +.sp +PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch +the case when it is passed a junk pointer and to detect when a pattern that was +compiled in an environment of one endianness is run in an environment with the +other endianness. This is the error that PCRE gives when the magic number is +not present. +.sp + PCRE_ERROR_UNKNOWN_OPCODE (-5) +.sp +While running the pattern match, an unknown item was encountered in the +compiled pattern. This error could be caused by a bug in PCRE or by overwriting +of the compiled pattern. +.sp + PCRE_ERROR_NOMEMORY (-6) +.sp +If a pattern contains back references, but the \fIovector\fP that is passed to +\fBpcre_exec()\fP is not big enough to remember the referenced substrings, PCRE +gets a block of memory at the start of matching to use for this purpose. If the +call via \fBpcre_malloc()\fP fails, this error is given. The memory is +automatically freed at the end of matching. +.P +This error is also given if \fBpcre_stack_malloc()\fP fails in +\fBpcre_exec()\fP. This can happen only when PCRE has been compiled with +\fB--disable-stack-for-recursion\fP. +.sp + PCRE_ERROR_NOSUBSTRING (-7) +.sp +This error is used by the \fBpcre_copy_substring()\fP, +\fBpcre_get_substring()\fP, and \fBpcre_get_substring_list()\fP functions (see +below). It is never returned by \fBpcre_exec()\fP. +.sp + PCRE_ERROR_MATCHLIMIT (-8) +.sp +The backtracking limit, as specified by the \fImatch_limit\fP field in a +\fBpcre_extra\fP structure (or defaulted) was reached. See the description +above. +.sp + PCRE_ERROR_CALLOUT (-9) +.sp +This error is never generated by \fBpcre_exec()\fP itself. It is provided for +use by callout functions that want to yield a distinctive error code. See the +.\" HREF +\fBpcrecallout\fP +.\" +documentation for details. +.sp + PCRE_ERROR_BADUTF8 (-10) +.sp +A string that contains an invalid UTF-8 byte sequence was passed as a subject, +and the PCRE_NO_UTF8_CHECK option was not set. If the size of the output vector +(\fIovecsize\fP) is at least 2, the byte offset to the start of the the invalid +UTF-8 character is placed in the first element, and a reason code is placed in +the second element. The reason codes are listed in the +.\" HTML <a href="#badutf8reasons"> +.\" </a> +following section. +.\" +For backward compatibility, if PCRE_PARTIAL_HARD is set and the problem is a +truncated UTF-8 character at the end of the subject (reason codes 1 to 5), +PCRE_ERROR_SHORTUTF8 is returned instead of PCRE_ERROR_BADUTF8. +.sp + PCRE_ERROR_BADUTF8_OFFSET (-11) +.sp +The UTF-8 byte sequence that was passed as a subject was checked and found to +be valid (the PCRE_NO_UTF8_CHECK option was not set), but the value of +\fIstartoffset\fP did not point to the beginning of a UTF-8 character or the +end of the subject. +.sp + PCRE_ERROR_PARTIAL (-12) +.sp +The subject string did not match, but it did match partially. See the +.\" HREF +\fBpcrepartial\fP +.\" +documentation for details of partial matching. +.sp + PCRE_ERROR_BADPARTIAL (-13) +.sp +This code is no longer in use. It was formerly returned when the PCRE_PARTIAL +option was used with a compiled pattern containing items that were not +supported for partial matching. From release 8.00 onwards, there are no +restrictions on partial matching. +.sp + PCRE_ERROR_INTERNAL (-14) +.sp +An unexpected internal error has occurred. This error could be caused by a bug +in PCRE or by overwriting of the compiled pattern. +.sp + PCRE_ERROR_BADCOUNT (-15) +.sp +This error is given if the value of the \fIovecsize\fP argument is negative. +.sp + PCRE_ERROR_RECURSIONLIMIT (-21) +.sp +The internal recursion limit, as specified by the \fImatch_limit_recursion\fP +field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the +description above. +.sp + PCRE_ERROR_BADNEWLINE (-23) +.sp +An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given. +.sp + PCRE_ERROR_BADOFFSET (-24) +.sp +The value of \fIstartoffset\fP was negative or greater than the length of the +subject, that is, the value in \fIlength\fP. +.sp + PCRE_ERROR_SHORTUTF8 (-25) +.sp +This error is returned instead of PCRE_ERROR_BADUTF8 when the subject string +ends with a truncated UTF-8 character and the PCRE_PARTIAL_HARD option is set. +Information about the failure is returned as for PCRE_ERROR_BADUTF8. It is in +fact sufficient to detect this case, but this special error code for +PCRE_PARTIAL_HARD precedes the implementation of returned information; it is +retained for backwards compatibility. +.sp + PCRE_ERROR_RECURSELOOP (-26) +.sp +This error is returned when \fBpcre_exec()\fP detects a recursion loop within +the pattern. Specifically, it means that either the whole pattern or a +subpattern has been called recursively for the second time at the same position +in the subject string. Some simple patterns that might do this are detected and +faulted at compile time, but more complicated cases, in particular mutual +recursions between two different subpatterns, cannot be detected until run +time. +.sp + PCRE_ERROR_JIT_STACKLIMIT (-27) +.sp +This error is returned when a pattern that was successfully studied using a +JIT compile option is being matched, but the memory available for the +just-in-time processing stack is not large enough. See the +.\" HREF +\fBpcrejit\fP +.\" +documentation for more details. +.sp + PCRE_ERROR_BADMODE (-28) +.sp +This error is given if a pattern that was compiled by the 8-bit library is +passed to a 16-bit or 32-bit library function, or vice versa. +.sp + PCRE_ERROR_BADENDIANNESS (-29) +.sp +This error is given if a pattern that was compiled and saved is reloaded on a +host with different endianness. The utility function +\fBpcre_pattern_to_host_byte_order()\fP can be used to convert such a pattern +so that it runs on the new host. +.sp + PCRE_ERROR_JIT_BADOPTION +.sp +This error is returned when a pattern that was successfully studied using a JIT +compile option is being matched, but the matching mode (partial or complete +match) does not correspond to any JIT compilation mode. When the JIT fast path +function is used, this error may be also given for invalid options. See the +.\" HREF +\fBpcrejit\fP +.\" +documentation for more details. +.sp + PCRE_ERROR_BADLENGTH (-32) +.sp +This error is given if \fBpcre_exec()\fP is called with a negative value for +the \fIlength\fP argument. +.P +Error numbers -16 to -20, -22, and 30 are not used by \fBpcre_exec()\fP. +. +. +.\" HTML <a name="badutf8reasons"></a> +.SS "Reason codes for invalid UTF-8 strings" +.rs +.sp +This section applies only to the 8-bit library. The corresponding information +for the 16-bit and 32-bit libraries is given in the +.\" HREF +\fBpcre16\fP +.\" +and +.\" HREF +\fBpcre32\fP +.\" +pages. +.P +When \fBpcre_exec()\fP returns either PCRE_ERROR_BADUTF8 or +PCRE_ERROR_SHORTUTF8, and the size of the output vector (\fIovecsize\fP) is at +least 2, the offset of the start of the invalid UTF-8 character is placed in +the first output vector element (\fIovector[0]\fP) and a reason code is placed +in the second element (\fIovector[1]\fP). The reason codes are given names in +the \fBpcre.h\fP header file: +.sp + PCRE_UTF8_ERR1 + PCRE_UTF8_ERR2 + PCRE_UTF8_ERR3 + PCRE_UTF8_ERR4 + PCRE_UTF8_ERR5 +.sp +The string ends with a truncated UTF-8 character; the code specifies how many +bytes are missing (1 to 5). Although RFC 3629 restricts UTF-8 characters to be +no longer than 4 bytes, the encoding scheme (originally defined by RFC 2279) +allows for up to 6 bytes, and this is checked first; hence the possibility of +4 or 5 missing bytes. +.sp + PCRE_UTF8_ERR6 + PCRE_UTF8_ERR7 + PCRE_UTF8_ERR8 + PCRE_UTF8_ERR9 + PCRE_UTF8_ERR10 +.sp +The two most significant bits of the 2nd, 3rd, 4th, 5th, or 6th byte of the +character do not have the binary value 0b10 (that is, either the most +significant bit is 0, or the next bit is 1). +.sp + PCRE_UTF8_ERR11 + PCRE_UTF8_ERR12 +.sp +A character that is valid by the RFC 2279 rules is either 5 or 6 bytes long; +these code points are excluded by RFC 3629. +.sp + PCRE_UTF8_ERR13 +.sp +A 4-byte character has a value greater than 0x10fff; these code points are +excluded by RFC 3629. +.sp + PCRE_UTF8_ERR14 +.sp +A 3-byte character has a value in the range 0xd800 to 0xdfff; this range of +code points are reserved by RFC 3629 for use with UTF-16, and so are excluded +from UTF-8. +.sp + PCRE_UTF8_ERR15 + PCRE_UTF8_ERR16 + PCRE_UTF8_ERR17 + PCRE_UTF8_ERR18 + PCRE_UTF8_ERR19 +.sp +A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes for a +value that can be represented by fewer bytes, which is invalid. For example, +the two bytes 0xc0, 0xae give the value 0x2e, whose correct coding uses just +one byte. +.sp + PCRE_UTF8_ERR20 +.sp +The two most significant bits of the first byte of a character have the binary +value 0b10 (that is, the most significant bit is 1 and the second is 0). Such a +byte can only validly occur as the second or subsequent byte of a multi-byte +character. +.sp + PCRE_UTF8_ERR21 +.sp +The first byte of a character has the value 0xfe or 0xff. These values can +never occur in a valid UTF-8 string. +.sp + PCRE_UTF8_ERR22 +.sp +This error code was formerly used when the presence of a so-called +"non-character" caused an error. Unicode corrigendum #9 makes it clear that +such characters should not cause a string to be rejected, and so this code is +no longer in use and is never returned. +. +. +.SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER" +.rs +.sp +.nf +.B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP, +.B " int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP," +.B " int \fIbuffersize\fP);" +.sp +.B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP, +.B " int \fIstringcount\fP, int \fIstringnumber\fP," +.B " const char **\fIstringptr\fP);" +.sp +.B int pcre_get_substring_list(const char *\fIsubject\fP, +.B " int *\fIovector\fP, int \fIstringcount\fP, const char ***\fIlistptr\fP);" +.fi +.PP +Captured substrings can be accessed directly by using the offsets returned by +\fBpcre_exec()\fP in \fIovector\fP. For convenience, the functions +\fBpcre_copy_substring()\fP, \fBpcre_get_substring()\fP, and +\fBpcre_get_substring_list()\fP are provided for extracting captured substrings +as new, separate, zero-terminated strings. These functions identify substrings +by number. The next section describes functions for extracting named +substrings. +.P +A substring that contains a binary zero is correctly extracted and has a +further zero added on the end, but the result is not, of course, a C string. +However, you can process such a string by referring to the length that is +returned by \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP. +Unfortunately, the interface to \fBpcre_get_substring_list()\fP is not adequate +for handling strings containing binary zeros, because the end of the final +string is not independently indicated. +.P +The first three arguments are the same for all three of these functions: +\fIsubject\fP is the subject string that has just been successfully matched, +\fIovector\fP is a pointer to the vector of integer offsets that was passed to +\fBpcre_exec()\fP, and \fIstringcount\fP is the number of substrings that were +captured by the match, including the substring that matched the entire regular +expression. This is the value returned by \fBpcre_exec()\fP if it is greater +than zero. If \fBpcre_exec()\fP returned zero, indicating that it ran out of +space in \fIovector\fP, the value passed as \fIstringcount\fP should be the +number of elements in the vector divided by three. +.P +The functions \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP +extract a single substring, whose number is given as \fIstringnumber\fP. A +value of zero extracts the substring that matched the entire pattern, whereas +higher values extract the captured substrings. For \fBpcre_copy_substring()\fP, +the string is placed in \fIbuffer\fP, whose length is given by +\fIbuffersize\fP, while for \fBpcre_get_substring()\fP a new block of memory is +obtained via \fBpcre_malloc\fP, and its address is returned via +\fIstringptr\fP. The yield of the function is the length of the string, not +including the terminating zero, or one of these error codes: +.sp + PCRE_ERROR_NOMEMORY (-6) +.sp +The buffer was too small for \fBpcre_copy_substring()\fP, or the attempt to get +memory failed for \fBpcre_get_substring()\fP. +.sp + PCRE_ERROR_NOSUBSTRING (-7) +.sp +There is no substring whose number is \fIstringnumber\fP. +.P +The \fBpcre_get_substring_list()\fP function extracts all available substrings +and builds a list of pointers to them. All this is done in a single block of +memory that is obtained via \fBpcre_malloc\fP. The address of the memory block +is returned via \fIlistptr\fP, which is also the start of the list of string +pointers. The end of the list is marked by a NULL pointer. The yield of the +function is zero if all went well, or the error code +.sp + PCRE_ERROR_NOMEMORY (-6) +.sp +if the attempt to get the memory block failed. +.P +When any of these functions encounter a substring that is unset, which can +happen when capturing subpattern number \fIn+1\fP matches some part of the +subject, but subpattern \fIn\fP has not been used at all, they return an empty +string. This can be distinguished from a genuine zero-length substring by +inspecting the appropriate offset in \fIovector\fP, which is negative for unset +substrings. +.P +The two convenience functions \fBpcre_free_substring()\fP and +\fBpcre_free_substring_list()\fP can be used to free the memory returned by +a previous call of \fBpcre_get_substring()\fP or +\fBpcre_get_substring_list()\fP, respectively. They do nothing more than call +the function pointed to by \fBpcre_free\fP, which of course could be called +directly from a C program. However, PCRE is used in some situations where it is +linked via a special interface to another programming language that cannot use +\fBpcre_free\fP directly; it is for these cases that the functions are +provided. +. +. +.SH "EXTRACTING CAPTURED SUBSTRINGS BY NAME" +.rs +.sp +.nf +.B int pcre_get_stringnumber(const pcre *\fIcode\fP, +.B " const char *\fIname\fP);" +.sp +.B int pcre_copy_named_substring(const pcre *\fIcode\fP, +.B " const char *\fIsubject\fP, int *\fIovector\fP," +.B " int \fIstringcount\fP, const char *\fIstringname\fP," +.B " char *\fIbuffer\fP, int \fIbuffersize\fP);" +.sp +.B int pcre_get_named_substring(const pcre *\fIcode\fP, +.B " const char *\fIsubject\fP, int *\fIovector\fP," +.B " int \fIstringcount\fP, const char *\fIstringname\fP," +.B " const char **\fIstringptr\fP);" +.fi +.PP +To extract a substring by name, you first have to find associated number. +For example, for this pattern +.sp + (a+)b(?<xxx>\ed+)... +.sp +the number of the subpattern called "xxx" is 2. If the name is known to be +unique (PCRE_DUPNAMES was not set), you can find the number from the name by +calling \fBpcre_get_stringnumber()\fP. The first argument is the compiled +pattern, and the second is the name. The yield of the function is the +subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no subpattern of +that name. +.P +Given the number, you can extract the substring directly, or use one of the +functions described in the previous section. For convenience, there are also +two functions that do the whole job. +.P +Most of the arguments of \fBpcre_copy_named_substring()\fP and +\fBpcre_get_named_substring()\fP are the same as those for the similarly named +functions that extract by number. As these are described in the previous +section, they are not re-described here. There are just two differences: +.P +First, instead of a substring number, a substring name is given. Second, there +is an extra argument, given at the start, which is a pointer to the compiled +pattern. This is needed in order to gain access to the name-to-number +translation table. +.P +These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they +then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as +appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names, +the behaviour may not be what you want (see the next section). +.P +\fBWarning:\fP If the pattern uses the (?| feature to set up multiple +subpatterns with the same number, as described in the +.\" HTML <a href="pcrepattern.html#dupsubpatternnumber"> +.\" </a> +section on duplicate subpattern numbers +.\" +in the +.\" HREF +\fBpcrepattern\fP +.\" +page, you cannot use names to distinguish the different subpatterns, because +names are not included in the compiled code. The matching process uses only +numbers. For this reason, the use of different names for subpatterns of the +same number causes an error at compile time. +. +. +.SH "DUPLICATE SUBPATTERN NAMES" +.rs +.sp +.nf +.B int pcre_get_stringtable_entries(const pcre *\fIcode\fP, +.B " const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);" +.fi +.PP +When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns +are not required to be unique. (Duplicate names are always allowed for +subpatterns with the same number, created by using the (?| feature. Indeed, if +such subpatterns are named, they are required to use the same names.) +.P +Normally, patterns with duplicate names are such that in any one match, only +one of the named subpatterns participates. An example is shown in the +.\" HREF +\fBpcrepattern\fP +.\" +documentation. +.P +When duplicates are present, \fBpcre_copy_named_substring()\fP and +\fBpcre_get_named_substring()\fP return the first substring corresponding to +the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING (-7) is +returned; no data is returned. The \fBpcre_get_stringnumber()\fP function +returns one of the numbers that are associated with the name, but it is not +defined which it is. +.P +If you want to get full details of all captured substrings for a given name, +you must use the \fBpcre_get_stringtable_entries()\fP function. The first +argument is the compiled pattern, and the second is the name. The third and +fourth are pointers to variables which are updated by the function. After it +has run, they point to the first and last entries in the name-to-number table +for the given name. The function itself returns the length of each entry, or +PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is +described above in the section entitled \fIInformation about a pattern\fP +.\" HTML <a href="#infoaboutpattern"> +.\" </a> +above. +.\" +Given all the relevant entries for the name, you can extract each of their +numbers, and hence the captured data, if any. +. +. +.SH "FINDING ALL POSSIBLE MATCHES" +.rs +.sp +The traditional matching function uses a similar algorithm to Perl, which stops +when it finds the first match, starting at a given point in the subject. If you +want to find all possible matches, or the longest possible match, consider +using the alternative matching function (see below) instead. If you cannot use +the alternative function, but still need to find all possible matches, you +can kludge it up by making use of the callout facility, which is described in +the +.\" HREF +\fBpcrecallout\fP +.\" +documentation. +.P +What you have to do is to insert a callout right at the end of the pattern. +When your callout function is called, extract and save the current matched +substring. Then return 1, which forces \fBpcre_exec()\fP to backtrack and try +other alternatives. Ultimately, when it runs out of matches, \fBpcre_exec()\fP +will yield PCRE_ERROR_NOMATCH. +. +. +.SH "OBTAINING AN ESTIMATE OF STACK USAGE" +.rs +.sp +Matching certain patterns using \fBpcre_exec()\fP can use a lot of process +stack, which in certain environments can be rather limited in size. Some users +find it helpful to have an estimate of the amount of stack that is used by +\fBpcre_exec()\fP, to help them set recursion limits, as described in the +.\" HREF +\fBpcrestack\fP +.\" +documentation. The estimate that is output by \fBpcretest\fP when called with +the \fB-m\fP and \fB-C\fP options is obtained by calling \fBpcre_exec\fP with +the values NULL, NULL, NULL, -999, and -999 for its first five arguments. +.P +Normally, if its first argument is NULL, \fBpcre_exec()\fP immediately returns +the negative error code PCRE_ERROR_NULL, but with this special combination of +arguments, it returns instead a negative number whose absolute value is the +approximate stack frame size in bytes. (A negative number is used so that it is +clear that no match has happened.) The value is approximate because in some +cases, recursive calls to \fBpcre_exec()\fP occur when there are one or two +additional variables on the stack. +.P +If PCRE has been compiled to use the heap instead of the stack for recursion, +the value returned is the size of each block that is obtained from the heap. +. +. +.\" HTML <a name="dfamatch"></a> +.SH "MATCHING A PATTERN: THE ALTERNATIVE FUNCTION" +.rs +.sp +.nf +.B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," +.B " const char *\fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP," +.B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP," +.B " int *\fIworkspace\fP, int \fIwscount\fP);" +.fi +.P +The function \fBpcre_dfa_exec()\fP is called to match a subject string against +a compiled pattern, using a matching algorithm that scans the subject string +just once, and does not backtrack. This has different characteristics to the +normal algorithm, and is not compatible with Perl. Some of the features of PCRE +patterns are not supported. Nevertheless, there are times when this kind of +matching can be useful. For a discussion of the two matching algorithms, and a +list of features that \fBpcre_dfa_exec()\fP does not support, see the +.\" HREF +\fBpcrematching\fP +.\" +documentation. +.P +The arguments for the \fBpcre_dfa_exec()\fP function are the same as for +\fBpcre_exec()\fP, plus two extras. The \fIovector\fP argument is used in a +different way, and this is described below. The other common arguments are used +in the same way as for \fBpcre_exec()\fP, so their description is not repeated +here. +.P +The two additional arguments provide workspace for the function. The workspace +vector should contain at least 20 elements. It is used for keeping track of +multiple paths through the pattern tree. More workspace will be needed for +patterns and subjects where there are a lot of potential matches. +.P +Here is an example of a simple call to \fBpcre_dfa_exec()\fP: +.sp + int rc; + int ovector[10]; + int wspace[20]; + rc = pcre_dfa_exec( + re, /* result of pcre_compile() */ + NULL, /* we didn't study the pattern */ + "some string", /* the subject string */ + 11, /* the length of the subject string */ + 0, /* start at offset 0 in the subject */ + 0, /* default options */ + ovector, /* vector of integers for substring information */ + 10, /* number of elements (NOT size in bytes) */ + wspace, /* working space vector */ + 20); /* number of elements (NOT size in bytes) */ +. +.SS "Option bits for \fBpcre_dfa_exec()\fP" +.rs +.sp +The unused bits of the \fIoptions\fP argument for \fBpcre_dfa_exec()\fP must be +zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP, +PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, +PCRE_NO_UTF8_CHECK, PCRE_BSR_ANYCRLF, PCRE_BSR_UNICODE, PCRE_NO_START_OPTIMIZE, +PCRE_PARTIAL_HARD, PCRE_PARTIAL_SOFT, PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. +All but the last four of these are exactly the same as for \fBpcre_exec()\fP, +so their description is not repeated here. +.sp + PCRE_PARTIAL_HARD + PCRE_PARTIAL_SOFT +.sp +These have the same general effect as they do for \fBpcre_exec()\fP, but the +details are slightly different. When PCRE_PARTIAL_HARD is set for +\fBpcre_dfa_exec()\fP, it returns PCRE_ERROR_PARTIAL if the end of the subject +is reached and there is still at least one matching possibility that requires +additional characters. This happens even if some complete matches have also +been found. When PCRE_PARTIAL_SOFT is set, the return code PCRE_ERROR_NOMATCH +is converted into PCRE_ERROR_PARTIAL if the end of the subject is reached, +there have been no complete matches, but there is still at least one matching +possibility. The portion of the string that was inspected when the longest +partial match was found is set as the first matching string in both cases. +There is a more detailed discussion of partial and multi-segment matching, with +examples, in the +.\" HREF +\fBpcrepartial\fP +.\" +documentation. +.sp + PCRE_DFA_SHORTEST +.sp +Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as +soon as it has found one match. Because of the way the alternative algorithm +works, this is necessarily the shortest possible match at the first possible +matching point in the subject string. +.sp + PCRE_DFA_RESTART +.sp +When \fBpcre_dfa_exec()\fP returns a partial match, it is possible to call it +again, with additional subject characters, and have it continue with the same +match. The PCRE_DFA_RESTART option requests this action; when it is set, the +\fIworkspace\fP and \fIwscount\fP options must reference the same vector as +before because data about the match so far is left in them after a partial +match. There is more discussion of this facility in the +.\" HREF +\fBpcrepartial\fP +.\" +documentation. +. +. +.SS "Successful returns from \fBpcre_dfa_exec()\fP" +.rs +.sp +When \fBpcre_dfa_exec()\fP succeeds, it may have matched more than one +substring in the subject. Note, however, that all the matches from one run of +the function start at the same point in the subject. The shorter matches are +all initial substrings of the longer matches. For example, if the pattern +.sp + <.*> +.sp +is matched against the string +.sp + This is <something> <something else> <something further> no more +.sp +the three matched strings are +.sp + <something> + <something> <something else> + <something> <something else> <something further> +.sp +On success, the yield of the function is a number greater than zero, which is +the number of matched substrings. The substrings themselves are returned in +\fIovector\fP. Each string uses two elements; the first is the offset to the +start, and the second is the offset to the end. In fact, all the strings have +the same start offset. (Space could have been saved by giving this only once, +but it was decided to retain some compatibility with the way \fBpcre_exec()\fP +returns data, even though the meaning of the strings is different.) +.P +The strings are returned in reverse order of length; that is, the longest +matching string is given first. If there were too many matches to fit into +\fIovector\fP, the yield of the function is zero, and the vector is filled with +the longest matches. Unlike \fBpcre_exec()\fP, \fBpcre_dfa_exec()\fP can use +the entire \fIovector\fP for returning matched strings. +.P +NOTE: PCRE's "auto-possessification" optimization usually applies to character +repeats at the end of a pattern (as well as internally). For example, the +pattern "a\ed+" is compiled as if it were "a\ed++" because there is no point +even considering the possibility of backtracking into the repeated digits. For +DFA matching, this means that only one possible match is found. If you really +do want multiple matches in such cases, either use an ungreedy repeat +("a\ed+?") or set the PCRE_NO_AUTO_POSSESS option when compiling. +. +. +.SS "Error returns from \fBpcre_dfa_exec()\fP" +.rs +.sp +The \fBpcre_dfa_exec()\fP function returns a negative number when it fails. +Many of the errors are the same as for \fBpcre_exec()\fP, and these are +described +.\" HTML <a href="#errorlist"> +.\" </a> +above. +.\" +There are in addition the following errors that are specific to +\fBpcre_dfa_exec()\fP: +.sp + PCRE_ERROR_DFA_UITEM (-16) +.sp +This return is given if \fBpcre_dfa_exec()\fP encounters an item in the pattern +that it does not support, for instance, the use of \eC or a back reference. +.sp + PCRE_ERROR_DFA_UCOND (-17) +.sp +This return is given if \fBpcre_dfa_exec()\fP encounters a condition item that +uses a back reference for the condition, or a test for recursion in a specific +group. These are not supported. +.sp + PCRE_ERROR_DFA_UMLIMIT (-18) +.sp +This return is given if \fBpcre_dfa_exec()\fP is called with an \fIextra\fP +block that contains a setting of the \fImatch_limit\fP or +\fImatch_limit_recursion\fP fields. This is not supported (these fields are +meaningless for DFA matching). +.sp + PCRE_ERROR_DFA_WSSIZE (-19) +.sp +This return is given if \fBpcre_dfa_exec()\fP runs out of space in the +\fIworkspace\fP vector. +.sp + PCRE_ERROR_DFA_RECURSE (-20) +.sp +When a recursive subpattern is processed, the matching function calls itself +recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This +error is given if the output vector is not large enough. This should be +extremely rare, as a vector of size 1000 is used. +.sp + PCRE_ERROR_DFA_BADRESTART (-30) +.sp +When \fBpcre_dfa_exec()\fP is called with the \fBPCRE_DFA_RESTART\fP option, +some plausibility checks are made on the contents of the workspace, which +should contain data about the previous partial match. If any of these checks +fail, this error is given. +. +. +.SH "SEE ALSO" +.rs +.sp +\fBpcre16\fP(3), \fBpcre32\fP(3), \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), +\fBpcrecpp(3)\fP(3), \fBpcrematching\fP(3), \fBpcrepartial\fP(3), +\fBpcreposix\fP(3), \fBpcreprecompile\fP(3), \fBpcresample\fP(3), +\fBpcrestack\fP(3). +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 09 February 2014 +Copyright (c) 1997-2014 University of Cambridge. +.fi diff --git a/plugins/Pcre16/docs/doc/pcrebuild.3 b/plugins/Pcre16/docs/doc/pcrebuild.3 new file mode 100644 index 0000000000..403f2ae32f --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcrebuild.3 @@ -0,0 +1,550 @@ +.TH PCREBUILD 3 "12 May 2013" "PCRE 8.33" +.SH NAME +PCRE - Perl-compatible regular expressions +. +. +.SH "BUILDING PCRE" +.rs +.sp +PCRE is distributed with a \fBconfigure\fP script that can be used to build the +library in Unix-like environments using the applications known as Autotools. +Also in the distribution are files to support building using \fBCMake\fP +instead of \fBconfigure\fP. The text file +.\" HTML <a href="README.txt"> +.\" </a> +\fBREADME\fP +.\" +contains general information about building with Autotools (some of which is +repeated below), and also has some comments about building on various operating +systems. There is a lot more information about building PCRE without using +Autotools (including information about using \fBCMake\fP and building "by +hand") in the text file called +.\" HTML <a href="NON-AUTOTOOLS-BUILD.txt"> +.\" </a> +\fBNON-AUTOTOOLS-BUILD\fP. +.\" +You should consult this file as well as the +.\" HTML <a href="README.txt"> +.\" </a> +\fBREADME\fP +.\" +file if you are building in a non-Unix-like environment. +. +. +.SH "PCRE BUILD-TIME OPTIONS" +.rs +.sp +The rest of this document describes the optional features of PCRE that can be +selected when the library is compiled. It assumes use of the \fBconfigure\fP +script, where the optional features are selected or deselected by providing +options to \fBconfigure\fP before running the \fBmake\fP command. However, the +same options can be selected in both Unix-like and non-Unix-like environments +using the GUI facility of \fBcmake-gui\fP if you are using \fBCMake\fP instead +of \fBconfigure\fP to build PCRE. +.P +If you are not using Autotools or \fBCMake\fP, option selection can be done by +editing the \fBconfig.h\fP file, or by passing parameter settings to the +compiler, as described in +.\" HTML <a href="NON-AUTOTOOLS-BUILD.txt"> +.\" </a> +\fBNON-AUTOTOOLS-BUILD\fP. +.\" +.P +The complete list of options for \fBconfigure\fP (which includes the standard +ones such as the selection of the installation directory) can be obtained by +running +.sp + ./configure --help +.sp +The following sections include descriptions of options whose names begin with +--enable or --disable. These settings specify changes to the defaults for the +\fBconfigure\fP command. Because of the way that \fBconfigure\fP works, +--enable and --disable always come in pairs, so the complementary option always +exists as well, but as it specifies the default, it is not described. +. +. +.SH "BUILDING 8-BIT, 16-BIT AND 32-BIT LIBRARIES" +.rs +.sp +By default, a library called \fBlibpcre\fP is built, containing functions that +take string arguments contained in vectors of bytes, either as single-byte +characters, or interpreted as UTF-8 strings. You can also build a separate +library, called \fBlibpcre16\fP, in which strings are contained in vectors of +16-bit data units and interpreted either as single-unit characters or UTF-16 +strings, by adding +.sp + --enable-pcre16 +.sp +to the \fBconfigure\fP command. You can also build yet another separate +library, called \fBlibpcre32\fP, in which strings are contained in vectors of +32-bit data units and interpreted either as single-unit characters or UTF-32 +strings, by adding +.sp + --enable-pcre32 +.sp +to the \fBconfigure\fP command. If you do not want the 8-bit library, add +.sp + --disable-pcre8 +.sp +as well. At least one of the three libraries must be built. Note that the C++ +and POSIX wrappers are for the 8-bit library only, and that \fBpcregrep\fP is +an 8-bit program. None of these are built if you select only the 16-bit or +32-bit libraries. +. +. +.SH "BUILDING SHARED AND STATIC LIBRARIES" +.rs +.sp +The Autotools PCRE building process uses \fBlibtool\fP to build both shared and +static libraries by default. You can suppress one of these by adding one of +.sp + --disable-shared + --disable-static +.sp +to the \fBconfigure\fP command, as required. +. +. +.SH "C++ SUPPORT" +.rs +.sp +By default, if the 8-bit library is being built, the \fBconfigure\fP script +will search for a C++ compiler and C++ header files. If it finds them, it +automatically builds the C++ wrapper library (which supports only 8-bit +strings). You can disable this by adding +.sp + --disable-cpp +.sp +to the \fBconfigure\fP command. +. +. +.SH "UTF-8, UTF-16 AND UTF-32 SUPPORT" +.rs +.sp +To build PCRE with support for UTF Unicode character strings, add +.sp + --enable-utf +.sp +to the \fBconfigure\fP command. This setting applies to all three libraries, +adding support for UTF-8 to the 8-bit library, support for UTF-16 to the 16-bit +library, and support for UTF-32 to the to the 32-bit library. There are no +separate options for enabling UTF-8, UTF-16 and UTF-32 independently because +that would allow ridiculous settings such as requesting UTF-16 support while +building only the 8-bit library. It is not possible to build one library with +UTF support and another without in the same configuration. (For backwards +compatibility, --enable-utf8 is a synonym of --enable-utf.) +.P +Of itself, this setting does not make PCRE treat strings as UTF-8, UTF-16 or +UTF-32. As well as compiling PCRE with this option, you also have have to set +the PCRE_UTF8, PCRE_UTF16 or PCRE_UTF32 option (as appropriate) when you call +one of the pattern compiling functions. +.P +If you set --enable-utf when compiling in an EBCDIC environment, PCRE expects +its input to be either ASCII or UTF-8 (depending on the run-time option). It is +not possible to support both EBCDIC and UTF-8 codes in the same version of the +library. Consequently, --enable-utf and --enable-ebcdic are mutually +exclusive. +. +. +.SH "UNICODE CHARACTER PROPERTY SUPPORT" +.rs +.sp +UTF support allows the libraries to process character codepoints up to 0x10ffff +in the strings that they handle. On its own, however, it does not provide any +facilities for accessing the properties of such characters. If you want to be +able to use the pattern escapes \eP, \ep, and \eX, which refer to Unicode +character properties, you must add +.sp + --enable-unicode-properties +.sp +to the \fBconfigure\fP command. This implies UTF support, even if you have +not explicitly requested it. +.P +Including Unicode property support adds around 30K of tables to the PCRE +library. Only the general category properties such as \fILu\fP and \fINd\fP are +supported. Details are given in the +.\" HREF +\fBpcrepattern\fP +.\" +documentation. +. +. +.SH "JUST-IN-TIME COMPILER SUPPORT" +.rs +.sp +Just-in-time compiler support is included in the build by specifying +.sp + --enable-jit +.sp +This support is available only for certain hardware architectures. If this +option is set for an unsupported architecture, a compile time error occurs. +See the +.\" HREF +\fBpcrejit\fP +.\" +documentation for a discussion of JIT usage. When JIT support is enabled, +pcregrep automatically makes use of it, unless you add +.sp + --disable-pcregrep-jit +.sp +to the "configure" command. +. +. +.SH "CODE VALUE OF NEWLINE" +.rs +.sp +By default, PCRE interprets the linefeed (LF) character as indicating the end +of a line. This is the normal newline character on Unix-like systems. You can +compile PCRE to use carriage return (CR) instead, by adding +.sp + --enable-newline-is-cr +.sp +to the \fBconfigure\fP command. There is also a --enable-newline-is-lf option, +which explicitly specifies linefeed as the newline character. +.sp +Alternatively, you can specify that line endings are to be indicated by the two +character sequence CRLF. If you want this, add +.sp + --enable-newline-is-crlf +.sp +to the \fBconfigure\fP command. There is a fourth option, specified by +.sp + --enable-newline-is-anycrlf +.sp +which causes PCRE to recognize any of the three sequences CR, LF, or CRLF as +indicating a line ending. Finally, a fifth option, specified by +.sp + --enable-newline-is-any +.sp +causes PCRE to recognize any Unicode newline sequence. +.P +Whatever line ending convention is selected when PCRE is built can be +overridden when the library functions are called. At build time it is +conventional to use the standard for your operating system. +. +. +.SH "WHAT \eR MATCHES" +.rs +.sp +By default, the sequence \eR in a pattern matches any Unicode newline sequence, +whatever has been selected as the line ending sequence. If you specify +.sp + --enable-bsr-anycrlf +.sp +the default is changed so that \eR matches only CR, LF, or CRLF. Whatever is +selected when PCRE is built can be overridden when the library functions are +called. +. +. +.SH "POSIX MALLOC USAGE" +.rs +.sp +When the 8-bit library is called through the POSIX interface (see the +.\" HREF +\fBpcreposix\fP +.\" +documentation), additional working storage is required for holding the pointers +to capturing substrings, because PCRE requires three integers per substring, +whereas the POSIX interface provides only two. If the number of expected +substrings is small, the wrapper function uses space on the stack, because this +is faster than using \fBmalloc()\fP for each call. The default threshold above +which the stack is no longer used is 10; it can be changed by adding a setting +such as +.sp + --with-posix-malloc-threshold=20 +.sp +to the \fBconfigure\fP command. +. +. +.SH "HANDLING VERY LARGE PATTERNS" +.rs +.sp +Within a compiled pattern, offset values are used to point from one part to +another (for example, from an opening parenthesis to an alternation +metacharacter). By default, in the 8-bit and 16-bit libraries, two-byte values +are used for these offsets, leading to a maximum size for a compiled pattern of +around 64K. This is sufficient to handle all but the most gigantic patterns. +Nevertheless, some people do want to process truly enormous patterns, so it is +possible to compile PCRE to use three-byte or four-byte offsets by adding a +setting such as +.sp + --with-link-size=3 +.sp +to the \fBconfigure\fP command. The value given must be 2, 3, or 4. For the +16-bit library, a value of 3 is rounded up to 4. In these libraries, using +longer offsets slows down the operation of PCRE because it has to load +additional data when handling them. For the 32-bit library the value is always +4 and cannot be overridden; the value of --with-link-size is ignored. +. +. +.SH "AVOIDING EXCESSIVE STACK USAGE" +.rs +.sp +When matching with the \fBpcre_exec()\fP function, PCRE implements backtracking +by making recursive calls to an internal function called \fBmatch()\fP. In +environments where the size of the stack is limited, this can severely limit +PCRE's operation. (The Unix environment does not usually suffer from this +problem, but it may sometimes be necessary to increase the maximum stack size. +There is a discussion in the +.\" HREF +\fBpcrestack\fP +.\" +documentation.) An alternative approach to recursion that uses memory from the +heap to remember data, instead of using recursive function calls, has been +implemented to work round the problem of limited stack size. If you want to +build a version of PCRE that works this way, add +.sp + --disable-stack-for-recursion +.sp +to the \fBconfigure\fP command. With this configuration, PCRE will use the +\fBpcre_stack_malloc\fP and \fBpcre_stack_free\fP variables to call memory +management functions. By default these point to \fBmalloc()\fP and +\fBfree()\fP, but you can replace the pointers so that your own functions are +used instead. +.P +Separate functions are provided rather than using \fBpcre_malloc\fP and +\fBpcre_free\fP because the usage is very predictable: the block sizes +requested are always the same, and the blocks are always freed in reverse +order. A calling program might be able to implement optimized functions that +perform better than \fBmalloc()\fP and \fBfree()\fP. PCRE runs noticeably more +slowly when built in this way. This option affects only the \fBpcre_exec()\fP +function; it is not relevant for \fBpcre_dfa_exec()\fP. +. +. +.SH "LIMITING PCRE RESOURCE USAGE" +.rs +.sp +Internally, PCRE has a function called \fBmatch()\fP, which it calls repeatedly +(sometimes recursively) when matching a pattern with the \fBpcre_exec()\fP +function. By controlling the maximum number of times this function may be +called during a single matching operation, a limit can be placed on the +resources used by a single call to \fBpcre_exec()\fP. The limit can be changed +at run time, as described in the +.\" HREF +\fBpcreapi\fP +.\" +documentation. The default is 10 million, but this can be changed by adding a +setting such as +.sp + --with-match-limit=500000 +.sp +to the \fBconfigure\fP command. This setting has no effect on the +\fBpcre_dfa_exec()\fP matching function. +.P +In some environments it is desirable to limit the depth of recursive calls of +\fBmatch()\fP more strictly than the total number of calls, in order to +restrict the maximum amount of stack (or heap, if --disable-stack-for-recursion +is specified) that is used. A second limit controls this; it defaults to the +value that is set for --with-match-limit, which imposes no additional +constraints. However, you can set a lower limit by adding, for example, +.sp + --with-match-limit-recursion=10000 +.sp +to the \fBconfigure\fP command. This value can also be overridden at run time. +. +. +.SH "CREATING CHARACTER TABLES AT BUILD TIME" +.rs +.sp +PCRE uses fixed tables for processing characters whose code values are less +than 256. By default, PCRE is built with a set of tables that are distributed +in the file \fIpcre_chartables.c.dist\fP. These tables are for ASCII codes +only. If you add +.sp + --enable-rebuild-chartables +.sp +to the \fBconfigure\fP command, the distributed tables are no longer used. +Instead, a program called \fBdftables\fP is compiled and run. This outputs the +source for new set of tables, created in the default locale of your C run-time +system. (This method of replacing the tables does not work if you are cross +compiling, because \fBdftables\fP is run on the local host. If you need to +create alternative tables when cross compiling, you will have to do so "by +hand".) +. +. +.SH "USING EBCDIC CODE" +.rs +.sp +PCRE assumes by default that it will run in an environment where the character +code is ASCII (or Unicode, which is a superset of ASCII). This is the case for +most computer operating systems. PCRE can, however, be compiled to run in an +EBCDIC environment by adding +.sp + --enable-ebcdic +.sp +to the \fBconfigure\fP command. This setting implies +--enable-rebuild-chartables. You should only use it if you know that you are in +an EBCDIC environment (for example, an IBM mainframe operating system). The +--enable-ebcdic option is incompatible with --enable-utf. +.P +The EBCDIC character that corresponds to an ASCII LF is assumed to have the +value 0x15 by default. However, in some EBCDIC environments, 0x25 is used. In +such an environment you should use +.sp + --enable-ebcdic-nl25 +.sp +as well as, or instead of, --enable-ebcdic. The EBCDIC character for CR has the +same value as in ASCII, namely, 0x0d. Whichever of 0x15 and 0x25 is \fInot\fP +chosen as LF is made to correspond to the Unicode NEL character (which, in +Unicode, is 0x85). +.P +The options that select newline behaviour, such as --enable-newline-is-cr, +and equivalent run-time options, refer to these character values in an EBCDIC +environment. +. +. +.SH "PCREGREP OPTIONS FOR COMPRESSED FILE SUPPORT" +.rs +.sp +By default, \fBpcregrep\fP reads all files as plain text. You can build it so +that it recognizes files whose names end in \fB.gz\fP or \fB.bz2\fP, and reads +them with \fBlibz\fP or \fBlibbz2\fP, respectively, by adding one or both of +.sp + --enable-pcregrep-libz + --enable-pcregrep-libbz2 +.sp +to the \fBconfigure\fP command. These options naturally require that the +relevant libraries are installed on your system. Configuration will fail if +they are not. +. +. +.SH "PCREGREP BUFFER SIZE" +.rs +.sp +\fBpcregrep\fP uses an internal buffer to hold a "window" on the file it is +scanning, in order to be able to output "before" and "after" lines when it +finds a match. The size of the buffer is controlled by a parameter whose +default value is 20K. The buffer itself is three times this size, but because +of the way it is used for holding "before" lines, the longest line that is +guaranteed to be processable is the parameter size. You can change the default +parameter value by adding, for example, +.sp + --with-pcregrep-bufsize=50K +.sp +to the \fBconfigure\fP command. The caller of \fPpcregrep\fP can, however, +override this value by specifying a run-time option. +. +. +.SH "PCRETEST OPTION FOR LIBREADLINE SUPPORT" +.rs +.sp +If you add +.sp + --enable-pcretest-libreadline +.sp +to the \fBconfigure\fP command, \fBpcretest\fP is linked with the +\fBlibreadline\fP library, and when its input is from a terminal, it reads it +using the \fBreadline()\fP function. This provides line-editing and history +facilities. Note that \fBlibreadline\fP is GPL-licensed, so if you distribute a +binary of \fBpcretest\fP linked in this way, there may be licensing issues. +.P +Setting this option causes the \fB-lreadline\fP option to be added to the +\fBpcretest\fP build. In many operating environments with a sytem-installed +\fBlibreadline\fP this is sufficient. However, in some environments (e.g. +if an unmodified distribution version of readline is in use), some extra +configuration may be necessary. The INSTALL file for \fBlibreadline\fP says +this: +.sp + "Readline uses the termcap functions, but does not link with the + termcap or curses library itself, allowing applications which link + with readline the to choose an appropriate library." +.sp +If your environment has not been set up so that an appropriate library is +automatically included, you may need to add something like +.sp + LIBS="-ncurses" +.sp +immediately before the \fBconfigure\fP command. +. +. +.SH "DEBUGGING WITH VALGRIND SUPPORT" +.rs +.sp +By adding the +.sp + --enable-valgrind +.sp +option to to the \fBconfigure\fP command, PCRE will use valgrind annotations +to mark certain memory regions as unaddressable. This allows it to detect +invalid memory accesses, and is mostly useful for debugging PCRE itself. +. +. +.SH "CODE COVERAGE REPORTING" +.rs +.sp +If your C compiler is gcc, you can build a version of PCRE that can generate a +code coverage report for its test suite. To enable this, you must install +\fBlcov\fP version 1.6 or above. Then specify +.sp + --enable-coverage +.sp +to the \fBconfigure\fP command and build PCRE in the usual way. +.P +Note that using \fBccache\fP (a caching C compiler) is incompatible with code +coverage reporting. If you have configured \fBccache\fP to run automatically +on your system, you must set the environment variable +.sp + CCACHE_DISABLE=1 +.sp +before running \fBmake\fP to build PCRE, so that \fBccache\fP is not used. +.P +When --enable-coverage is used, the following addition targets are added to the +\fIMakefile\fP: +.sp + make coverage +.sp +This creates a fresh coverage report for the PCRE test suite. It is equivalent +to running "make coverage-reset", "make coverage-baseline", "make check", and +then "make coverage-report". +.sp + make coverage-reset +.sp +This zeroes the coverage counters, but does nothing else. +.sp + make coverage-baseline +.sp +This captures baseline coverage information. +.sp + make coverage-report +.sp +This creates the coverage report. +.sp + make coverage-clean-report +.sp +This removes the generated coverage report without cleaning the coverage data +itself. +.sp + make coverage-clean-data +.sp +This removes the captured coverage data without removing the coverage files +created at compile time (*.gcno). +.sp + make coverage-clean +.sp +This cleans all coverage data including the generated coverage report. For more +information about code coverage, see the \fBgcov\fP and \fBlcov\fP +documentation. +. +. +.SH "SEE ALSO" +.rs +.sp +\fBpcreapi\fP(3), \fBpcre16\fP, \fBpcre32\fP, \fBpcre_config\fP(3). +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 12 May 2013 +Copyright (c) 1997-2013 University of Cambridge. +.fi diff --git a/plugins/Pcre16/docs/doc/pcrecallout.3 b/plugins/Pcre16/docs/doc/pcrecallout.3 new file mode 100644 index 0000000000..8ebc995952 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcrecallout.3 @@ -0,0 +1,255 @@ +.TH PCRECALLOUT 3 "12 November 2013" "PCRE 8.34" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.SM +.B int (*pcre_callout)(pcre_callout_block *); +.PP +.B int (*pcre16_callout)(pcre16_callout_block *); +.PP +.B int (*pcre32_callout)(pcre32_callout_block *); +. +.SH DESCRIPTION +.rs +.sp +PCRE provides a feature called "callout", which is a means of temporarily +passing control to the caller of PCRE in the middle of pattern matching. The +caller of PCRE provides an external function by putting its entry point in the +global variable \fIpcre_callout\fP (\fIpcre16_callout\fP for the 16-bit +library, \fIpcre32_callout\fP for the 32-bit library). By default, this +variable contains NULL, which disables all calling out. +.P +Within a regular expression, (?C) indicates the points at which the external +function is to be called. Different callout points can be identified by putting +a number less than 256 after the letter C. The default value is zero. +For example, this pattern has two callout points: +.sp + (?C1)abc(?C2)def +.sp +If the PCRE_AUTO_CALLOUT option bit is set when a pattern is compiled, PCRE +automatically inserts callouts, all with number 255, before each item in the +pattern. For example, if PCRE_AUTO_CALLOUT is used with the pattern +.sp + A(\ed{2}|--) +.sp +it is processed as if it were +.sp +(?C255)A(?C255)((?C255)\ed{2}(?C255)|(?C255)-(?C255)-(?C255))(?C255) +.sp +Notice that there is a callout before and after each parenthesis and +alternation bar. If the pattern contains a conditional group whose condition is +an assertion, an automatic callout is inserted immediately before the +condition. Such a callout may also be inserted explicitly, for example: +.sp + (?(?C9)(?=a)ab|de) +.sp +This applies only to assertion conditions (because they are themselves +independent groups). +.P +Automatic callouts can be used for tracking the progress of pattern matching. +The +.\" HREF +\fBpcretest\fP +.\" +program has a pattern qualifier (/C) that sets automatic callouts; when it is +used, the output indicates how the pattern is being matched. This is useful +information when you are trying to optimize the performance of a particular +pattern. +. +. +.SH "MISSING CALLOUTS" +.rs +.sp +You should be aware that, because of optimizations in the way PCRE compiles and +matches patterns, callouts sometimes do not happen exactly as you might expect. +.P +At compile time, PCRE "auto-possessifies" repeated items when it knows that +what follows cannot be part of the repeat. For example, a+[bc] is compiled as +if it were a++[bc]. The \fBpcretest\fP output when this pattern is anchored and +then applied with automatic callouts to the string "aaaa" is: +.sp + --->aaaa + +0 ^ ^ + +1 ^ a+ + +3 ^ ^ [bc] + No match +.sp +This indicates that when matching [bc] fails, there is no backtracking into a+ +and therefore the callouts that would be taken for the backtracks do not occur. +You can disable the auto-possessify feature by passing PCRE_NO_AUTO_POSSESS +to \fBpcre_compile()\fP, or starting the pattern with (*NO_AUTO_POSSESS). If +this is done in \fBpcretest\fP (using the /O qualifier), the output changes to +this: +.sp + --->aaaa + +0 ^ ^ + +1 ^ a+ + +3 ^ ^ [bc] + +3 ^ ^ [bc] + +3 ^ ^ [bc] + +3 ^^ [bc] + No match +.sp +This time, when matching [bc] fails, the matcher backtracks into a+ and tries +again, repeatedly, until a+ itself fails. +.P +Other optimizations that provide fast "no match" results also affect callouts. +For example, if the pattern is +.sp + ab(?C4)cd +.sp +PCRE knows that any matching string must contain the letter "d". If the subject +string is "abyz", the lack of "d" means that matching doesn't ever start, and +the callout is never reached. However, with "abyd", though the result is still +no match, the callout is obeyed. +.P +If the pattern is studied, PCRE knows the minimum length of a matching string, +and will immediately give a "no match" return without actually running a match +if the subject is not long enough, or, for unanchored patterns, if it has +been scanned far enough. +.P +You can disable these optimizations by passing the PCRE_NO_START_OPTIMIZE +option to the matching function, or by starting the pattern with +(*NO_START_OPT). This slows down the matching process, but does ensure that +callouts such as the example above are obeyed. +. +. +.SH "THE CALLOUT INTERFACE" +.rs +.sp +During matching, when PCRE reaches a callout point, the external function +defined by \fIpcre_callout\fP or \fIpcre[16|32]_callout\fP is called (if it is +set). This applies to both normal and DFA matching. The only argument to the +callout function is a pointer to a \fBpcre_callout\fP or +\fBpcre[16|32]_callout\fP block. These structures contains the following +fields: +.sp + int \fIversion\fP; + int \fIcallout_number\fP; + int *\fIoffset_vector\fP; + const char *\fIsubject\fP; (8-bit version) + PCRE_SPTR16 \fIsubject\fP; (16-bit version) + PCRE_SPTR32 \fIsubject\fP; (32-bit version) + int \fIsubject_length\fP; + int \fIstart_match\fP; + int \fIcurrent_position\fP; + int \fIcapture_top\fP; + int \fIcapture_last\fP; + void *\fIcallout_data\fP; + int \fIpattern_position\fP; + int \fInext_item_length\fP; + const unsigned char *\fImark\fP; (8-bit version) + const PCRE_UCHAR16 *\fImark\fP; (16-bit version) + const PCRE_UCHAR32 *\fImark\fP; (32-bit version) +.sp +The \fIversion\fP field is an integer containing the version number of the +block format. The initial version was 0; the current version is 2. The version +number will change again in future if additional fields are added, but the +intention is never to remove any of the existing fields. +.P +The \fIcallout_number\fP field contains the number of the callout, as compiled +into the pattern (that is, the number after ?C for manual callouts, and 255 for +automatically generated callouts). +.P +The \fIoffset_vector\fP field is a pointer to the vector of offsets that was +passed by the caller to the matching function. When \fBpcre_exec()\fP or +\fBpcre[16|32]_exec()\fP is used, the contents can be inspected, in order to +extract substrings that have been matched so far, in the same way as for +extracting substrings after a match has completed. For the DFA matching +functions, this field is not useful. +.P +The \fIsubject\fP and \fIsubject_length\fP fields contain copies of the values +that were passed to the matching function. +.P +The \fIstart_match\fP field normally contains the offset within the subject at +which the current match attempt started. However, if the escape sequence \eK +has been encountered, this value is changed to reflect the modified starting +point. If the pattern is not anchored, the callout function may be called +several times from the same point in the pattern for different starting points +in the subject. +.P +The \fIcurrent_position\fP field contains the offset within the subject of the +current match pointer. +.P +When the \fBpcre_exec()\fP or \fBpcre[16|32]_exec()\fP is used, the +\fIcapture_top\fP field contains one more than the number of the highest +numbered captured substring so far. If no substrings have been captured, the +value of \fIcapture_top\fP is one. This is always the case when the DFA +functions are used, because they do not support captured substrings. +.P +The \fIcapture_last\fP field contains the number of the most recently captured +substring. However, when a recursion exits, the value reverts to what it was +outside the recursion, as do the values of all captured substrings. If no +substrings have been captured, the value of \fIcapture_last\fP is -1. This is +always the case for the DFA matching functions. +.P +The \fIcallout_data\fP field contains a value that is passed to a matching +function specifically so that it can be passed back in callouts. It is passed +in the \fIcallout_data\fP field of a \fBpcre_extra\fP or \fBpcre[16|32]_extra\fP +data structure. If no such data was passed, the value of \fIcallout_data\fP in +a callout block is NULL. There is a description of the \fBpcre_extra\fP +structure in the +.\" HREF +\fBpcreapi\fP +.\" +documentation. +.P +The \fIpattern_position\fP field is present from version 1 of the callout +structure. It contains the offset to the next item to be matched in the pattern +string. +.P +The \fInext_item_length\fP field is present from version 1 of the callout +structure. It contains the length of the next item to be matched in the pattern +string. When the callout immediately precedes an alternation bar, a closing +parenthesis, or the end of the pattern, the length is zero. When the callout +precedes an opening parenthesis, the length is that of the entire subpattern. +.P +The \fIpattern_position\fP and \fInext_item_length\fP fields are intended to +help in distinguishing between different automatic callouts, which all have the +same callout number. However, they are set for all callouts. +.P +The \fImark\fP field is present from version 2 of the callout structure. In +callouts from \fBpcre_exec()\fP or \fBpcre[16|32]_exec()\fP it contains a +pointer to the zero-terminated name of the most recently passed (*MARK), +(*PRUNE), or (*THEN) item in the match, or NULL if no such items have been +passed. Instances of (*PRUNE) or (*THEN) without a name do not obliterate a +previous (*MARK). In callouts from the DFA matching functions this field always +contains NULL. +. +. +.SH "RETURN VALUES" +.rs +.sp +The external callout function returns an integer to PCRE. If the value is zero, +matching proceeds as normal. If the value is greater than zero, matching fails +at the current point, but the testing of other matching possibilities goes +ahead, just as if a lookahead assertion had failed. If the value is less than +zero, the match is abandoned, the matching function returns the negative value. +.P +Negative values should normally be chosen from the set of PCRE_ERROR_xxx +values. In particular, PCRE_ERROR_NOMATCH forces a standard "no match" failure. +The error number PCRE_ERROR_CALLOUT is reserved for use by callout functions; +it will never be used by PCRE itself. +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 12 November 2013 +Copyright (c) 1997-2013 University of Cambridge. +.fi diff --git a/plugins/Pcre16/docs/doc/pcrecompat.3 b/plugins/Pcre16/docs/doc/pcrecompat.3 new file mode 100644 index 0000000000..0cc4019823 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcrecompat.3 @@ -0,0 +1,200 @@ +.TH PCRECOMPAT 3 "10 November 2013" "PCRE 8.34" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH "DIFFERENCES BETWEEN PCRE AND PERL" +.rs +.sp +This document describes the differences in the ways that PCRE and Perl handle +regular expressions. The differences described here are with respect to Perl +versions 5.10 and above. +.P +1. PCRE has only a subset of Perl's Unicode support. Details of what it does +have are given in the +.\" HREF +\fBpcreunicode\fP +.\" +page. +.P +2. PCRE allows repeat quantifiers only on parenthesized assertions, but they do +not mean what you might think. For example, (?!a){3} does not assert that the +next three characters are not "a". It just asserts that the next character is +not "a" three times (in principle: PCRE optimizes this to run the assertion +just once). Perl allows repeat quantifiers on other assertions such as \eb, but +these do not seem to have any use. +.P +3. Capturing subpatterns that occur inside negative lookahead assertions are +counted, but their entries in the offsets vector are never set. Perl sometimes +(but not always) sets its numerical variables from inside negative assertions. +.P +4. Though binary zero characters are supported in the subject string, they are +not allowed in a pattern string because it is passed as a normal C string, +terminated by zero. The escape sequence \e0 can be used in the pattern to +represent a binary zero. +.P +5. The following Perl escape sequences are not supported: \el, \eu, \eL, +\eU, and \eN when followed by a character name or Unicode value. (\eN on its +own, matching a non-newline character, is supported.) In fact these are +implemented by Perl's general string-handling and are not part of its pattern +matching engine. If any of these are encountered by PCRE, an error is +generated by default. However, if the PCRE_JAVASCRIPT_COMPAT option is set, +\eU and \eu are interpreted as JavaScript interprets them. +.P +6. The Perl escape sequences \ep, \eP, and \eX are supported only if PCRE is +built with Unicode character property support. The properties that can be +tested with \ep and \eP are limited to the general category properties such as +Lu and Nd, script names such as Greek or Han, and the derived properties Any +and L&. PCRE does support the Cs (surrogate) property, which Perl does not; the +Perl documentation says "Because Perl hides the need for the user to understand +the internal representation of Unicode characters, there is no need to +implement the somewhat messy concept of surrogates." +.P +7. PCRE does support the \eQ...\eE escape for quoting substrings. Characters in +between are treated as literals. This is slightly different from Perl in that $ +and @ are also handled as literals inside the quotes. In Perl, they cause +variable interpolation (but of course PCRE does not have variables). Note the +following examples: +.sp + Pattern PCRE matches Perl matches +.sp +.\" JOIN + \eQabc$xyz\eE abc$xyz abc followed by the + contents of $xyz + \eQabc\e$xyz\eE abc\e$xyz abc\e$xyz + \eQabc\eE\e$\eQxyz\eE abc$xyz abc$xyz +.sp +The \eQ...\eE sequence is recognized both inside and outside character classes. +.P +8. Fairly obviously, PCRE does not support the (?{code}) and (??{code}) +constructions. However, there is support for recursive patterns. This is not +available in Perl 5.8, but it is in Perl 5.10. Also, the PCRE "callout" +feature allows an external function to be called during pattern matching. See +the +.\" HREF +\fBpcrecallout\fP +.\" +documentation for details. +.P +9. Subpatterns that are called as subroutines (whether or not recursively) are +always treated as atomic groups in PCRE. This is like Python, but unlike Perl. +Captured values that are set outside a subroutine call can be reference from +inside in PCRE, but not in Perl. There is a discussion that explains these +differences in more detail in the +.\" HTML <a href="pcrepattern.html#recursiondifference"> +.\" </a> +section on recursion differences from Perl +.\" +in the +.\" HREF +\fBpcrepattern\fP +.\" +page. +.P +10. If any of the backtracking control verbs are used in a subpattern that is +called as a subroutine (whether or not recursively), their effect is confined +to that subpattern; it does not extend to the surrounding pattern. This is not +always the case in Perl. In particular, if (*THEN) is present in a group that +is called as a subroutine, its action is limited to that group, even if the +group does not contain any | characters. Note that such subpatterns are +processed as anchored at the point where they are tested. +.P +11. If a pattern contains more than one backtracking control verb, the first +one that is backtracked onto acts. For example, in the pattern +A(*COMMIT)B(*PRUNE)C a failure in B triggers (*COMMIT), but a failure in C +triggers (*PRUNE). Perl's behaviour is more complex; in many cases it is the +same as PCRE, but there are examples where it differs. +.P +12. Most backtracking verbs in assertions have their normal actions. They are +not confined to the assertion. +.P +13. There are some differences that are concerned with the settings of captured +strings when part of a pattern is repeated. For example, matching "aba" against +the pattern /^(a(b)?)+$/ in Perl leaves $2 unset, but in PCRE it is set to "b". +.P +14. PCRE's handling of duplicate subpattern numbers and duplicate subpattern +names is not as general as Perl's. This is a consequence of the fact the PCRE +works internally just with numbers, using an external table to translate +between numbers and names. In particular, a pattern such as (?|(?<a>A)|(?<b)B), +where the two capturing parentheses have the same number but different names, +is not supported, and causes an error at compile time. If it were allowed, it +would not be possible to distinguish which parentheses matched, because both +names map to capturing subpattern number 1. To avoid this confusing situation, +an error is given at compile time. +.P +15. Perl recognizes comments in some places that PCRE does not, for example, +between the ( and ? at the start of a subpattern. If the /x modifier is set, +Perl allows white space between ( and ? (though current Perls warn that this is +deprecated) but PCRE never does, even if the PCRE_EXTENDED option is set. +.P +16. Perl, when in warning mode, gives warnings for character classes such as +[A-\ed] or [a-[:digit:]]. It then treats the hyphens as literals. PCRE has no +warning features, so it gives an error in these cases because they are almost +certainly user mistakes. +.P +17. In PCRE, the upper/lower case character properties Lu and Ll are not +affected when case-independent matching is specified. For example, \ep{Lu} +always matches an upper case letter. I think Perl has changed in this respect; +in the release at the time of writing (5.16), \ep{Lu} and \ep{Ll} match all +letters, regardless of case, when case independence is specified. +.P +18. PCRE provides some extensions to the Perl regular expression facilities. +Perl 5.10 includes new features that are not in earlier versions of Perl, some +of which (such as named parentheses) have been in PCRE for some time. This list +is with respect to Perl 5.10: +.sp +(a) Although lookbehind assertions in PCRE must match fixed length strings, +each alternative branch of a lookbehind assertion can match a different length +of string. Perl requires them all to have the same length. +.sp +(b) If PCRE_DOLLAR_ENDONLY is set and PCRE_MULTILINE is not set, the $ +meta-character matches only at the very end of the string. +.sp +(c) If PCRE_EXTRA is set, a backslash followed by a letter with no special +meaning is faulted. Otherwise, like Perl, the backslash is quietly ignored. +(Perl can be made to issue a warning.) +.sp +(d) If PCRE_UNGREEDY is set, the greediness of the repetition quantifiers is +inverted, that is, by default they are not greedy, but if followed by a +question mark they are. +.sp +(e) PCRE_ANCHORED can be used at matching time to force a pattern to be tried +only at the first matching position in the subject string. +.sp +(f) The PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, and +PCRE_NO_AUTO_CAPTURE options for \fBpcre_exec()\fP have no Perl equivalents. +.sp +(g) The \eR escape sequence can be restricted to match only CR, LF, or CRLF +by the PCRE_BSR_ANYCRLF option. +.sp +(h) The callout facility is PCRE-specific. +.sp +(i) The partial matching facility is PCRE-specific. +.sp +(j) Patterns compiled by PCRE can be saved and re-used at a later time, even on +different hosts that have the other endianness. However, this does not apply to +optimized data created by the just-in-time compiler. +.sp +(k) The alternative matching functions (\fBpcre_dfa_exec()\fP, +\fBpcre16_dfa_exec()\fP and \fBpcre32_dfa_exec()\fP,) match in a different way +and are not Perl-compatible. +.sp +(l) PCRE recognizes some special sequences such as (*CR) at the start of +a pattern that set overall options that cannot be changed within the pattern. +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 10 November 2013 +Copyright (c) 1997-2013 University of Cambridge. +.fi diff --git a/plugins/Pcre16/docs/doc/pcrecpp.3 b/plugins/Pcre16/docs/doc/pcrecpp.3 new file mode 100644 index 0000000000..fbddd86ab3 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcrecpp.3 @@ -0,0 +1,348 @@ +.TH PCRECPP 3 "08 January 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions. +.SH "SYNOPSIS OF C++ WRAPPER" +.rs +.sp +.B #include <pcrecpp.h> +. +.SH DESCRIPTION +.rs +.sp +The C++ wrapper for PCRE was provided by Google Inc. Some additional +functionality was added by Giuseppe Maxia. This brief man page was constructed +from the notes in the \fIpcrecpp.h\fP file, which should be consulted for +further details. Note that the C++ wrapper supports only the original 8-bit +PCRE library. There is no 16-bit or 32-bit support at present. +. +. +.SH "MATCHING INTERFACE" +.rs +.sp +The "FullMatch" operation checks that supplied text matches a supplied pattern +exactly. If pointer arguments are supplied, it copies matched sub-strings that +match sub-patterns into them. +.sp + Example: successful match + pcrecpp::RE re("h.*o"); + re.FullMatch("hello"); +.sp + Example: unsuccessful match (requires full match): + pcrecpp::RE re("e"); + !re.FullMatch("hello"); +.sp + Example: creating a temporary RE object: + pcrecpp::RE("h.*o").FullMatch("hello"); +.sp +You can pass in a "const char*" or a "string" for "text". The examples below +tend to use a const char*. You can, as in the different examples above, store +the RE object explicitly in a variable or use a temporary RE object. The +examples below use one mode or the other arbitrarily. Either could correctly be +used for any of these examples. +.P +You must supply extra pointer arguments to extract matched subpieces. +.sp + Example: extracts "ruby" into "s" and 1234 into "i" + int i; + string s; + pcrecpp::RE re("(\e\ew+):(\e\ed+)"); + re.FullMatch("ruby:1234", &s, &i); +.sp + Example: does not try to extract any extra sub-patterns + re.FullMatch("ruby:1234", &s); +.sp + Example: does not try to extract into NULL + re.FullMatch("ruby:1234", NULL, &i); +.sp + Example: integer overflow causes failure + !re.FullMatch("ruby:1234567891234", NULL, &i); +.sp + Example: fails because there aren't enough sub-patterns: + !pcrecpp::RE("\e\ew+:\e\ed+").FullMatch("ruby:1234", &s); +.sp + Example: fails because string cannot be stored in integer + !pcrecpp::RE("(.*)").FullMatch("ruby", &i); +.sp +The provided pointer arguments can be pointers to any scalar numeric +type, or one of: +.sp + string (matched piece is copied to string) + StringPiece (StringPiece is mutated to point to matched piece) + T (where "bool T::ParseFrom(const char*, int)" exists) + NULL (the corresponding matched sub-pattern is not copied) +.sp +The function returns true iff all of the following conditions are satisfied: +.sp + a. "text" matches "pattern" exactly; +.sp + b. The number of matched sub-patterns is >= number of supplied + pointers; +.sp + c. The "i"th argument has a suitable type for holding the + string captured as the "i"th sub-pattern. If you pass in + void * NULL for the "i"th argument, or a non-void * NULL + of the correct type, or pass fewer arguments than the + number of sub-patterns, "i"th captured sub-pattern is + ignored. +.sp +CAVEAT: An optional sub-pattern that does not exist in the matched +string is assigned the empty string. Therefore, the following will +return false (because the empty string is not a valid number): +.sp + int number; + pcrecpp::RE::FullMatch("abc", "[a-z]+(\e\ed+)?", &number); +.sp +The matching interface supports at most 16 arguments per call. +If you need more, consider using the more general interface +\fBpcrecpp::RE::DoMatch\fP. See \fBpcrecpp.h\fP for the signature for +\fBDoMatch\fP. +.P +NOTE: Do not use \fBno_arg\fP, which is used internally to mark the end of a +list of optional arguments, as a placeholder for missing arguments, as this can +lead to segfaults. +. +. +.SH "QUOTING METACHARACTERS" +.rs +.sp +You can use the "QuoteMeta" operation to insert backslashes before all +potentially meaningful characters in a string. The returned string, used as a +regular expression, will exactly match the original string. +.sp + Example: + string quoted = RE::QuoteMeta(unquoted); +.sp +Note that it's legal to escape a character even if it has no special meaning in +a regular expression -- so this function does that. (This also makes it +identical to the perl function of the same name; see "perldoc -f quotemeta".) +For example, "1.5-2.0?" becomes "1\e.5\e-2\e.0\e?". +. +.SH "PARTIAL MATCHES" +.rs +.sp +You can use the "PartialMatch" operation when you want the pattern +to match any substring of the text. +.sp + Example: simple search for a string: + pcrecpp::RE("ell").PartialMatch("hello"); +.sp + Example: find first number in a string: + int number; + pcrecpp::RE re("(\e\ed+)"); + re.PartialMatch("x*100 + 20", &number); + assert(number == 100); +. +. +.SH "UTF-8 AND THE MATCHING INTERFACE" +.rs +.sp +By default, pattern and text are plain text, one byte per character. The UTF8 +flag, passed to the constructor, causes both pattern and string to be treated +as UTF-8 text, still a byte stream but potentially multiple bytes per +character. In practice, the text is likelier to be UTF-8 than the pattern, but +the match returned may depend on the UTF8 flag, so always use it when matching +UTF8 text. For example, "." will match one byte normally but with UTF8 set may +match up to three bytes of a multi-byte character. +.sp + Example: + pcrecpp::RE_Options options; + options.set_utf8(); + pcrecpp::RE re(utf8_pattern, options); + re.FullMatch(utf8_string); +.sp + Example: using the convenience function UTF8(): + pcrecpp::RE re(utf8_pattern, pcrecpp::UTF8()); + re.FullMatch(utf8_string); +.sp +NOTE: The UTF8 flag is ignored if pcre was not configured with the + --enable-utf8 flag. +. +. +.SH "PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE" +.rs +.sp +PCRE defines some modifiers to change the behavior of the regular expression +engine. The C++ wrapper defines an auxiliary class, RE_Options, as a vehicle to +pass such modifiers to a RE class. Currently, the following modifiers are +supported: +.sp + modifier description Perl corresponding +.sp + PCRE_CASELESS case insensitive match /i + PCRE_MULTILINE multiple lines match /m + PCRE_DOTALL dot matches newlines /s + PCRE_DOLLAR_ENDONLY $ matches only at end N/A + PCRE_EXTRA strict escape parsing N/A + PCRE_EXTENDED ignore white spaces /x + PCRE_UTF8 handles UTF8 chars built-in + PCRE_UNGREEDY reverses * and *? N/A + PCRE_NO_AUTO_CAPTURE disables capturing parens N/A (*) +.sp +(*) Both Perl and PCRE allow non capturing parentheses by means of the +"?:" modifier within the pattern itself. e.g. (?:ab|cd) does not +capture, while (ab|cd) does. +.P +For a full account on how each modifier works, please check the +PCRE API reference page. +.P +For each modifier, there are two member functions whose name is made +out of the modifier in lowercase, without the "PCRE_" prefix. For +instance, PCRE_CASELESS is handled by +.sp + bool caseless() +.sp +which returns true if the modifier is set, and +.sp + RE_Options & set_caseless(bool) +.sp +which sets or unsets the modifier. Moreover, PCRE_EXTRA_MATCH_LIMIT can be +accessed through the \fBset_match_limit()\fP and \fBmatch_limit()\fP member +functions. Setting \fImatch_limit\fP to a non-zero value will limit the +execution of pcre to keep it from doing bad things like blowing the stack or +taking an eternity to return a result. A value of 5000 is good enough to stop +stack blowup in a 2MB thread stack. Setting \fImatch_limit\fP to zero disables +match limiting. Alternatively, you can call \fBmatch_limit_recursion()\fP +which uses PCRE_EXTRA_MATCH_LIMIT_RECURSION to limit how much PCRE +recurses. \fBmatch_limit()\fP limits the number of matches PCRE does; +\fBmatch_limit_recursion()\fP limits the depth of internal recursion, and +therefore the amount of stack that is used. +.P +Normally, to pass one or more modifiers to a RE class, you declare +a \fIRE_Options\fP object, set the appropriate options, and pass this +object to a RE constructor. Example: +.sp + RE_Options opt; + opt.set_caseless(true); + if (RE("HELLO", opt).PartialMatch("hello world")) ... +.sp +RE_options has two constructors. The default constructor takes no arguments and +creates a set of flags that are off by default. The optional parameter +\fIoption_flags\fP is to facilitate transfer of legacy code from C programs. +This lets you do +.sp + RE(pattern, + RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str); +.sp +However, new code is better off doing +.sp + RE(pattern, + RE_Options().set_caseless(true).set_multiline(true)) + .PartialMatch(str); +.sp +If you are going to pass one of the most used modifiers, there are some +convenience functions that return a RE_Options class with the +appropriate modifier already set: \fBCASELESS()\fP, \fBUTF8()\fP, +\fBMULTILINE()\fP, \fBDOTALL\fP(), and \fBEXTENDED()\fP. +.P +If you need to set several options at once, and you don't want to go through +the pains of declaring a RE_Options object and setting several options, there +is a parallel method that give you such ability on the fly. You can concatenate +several \fBset_xxxxx()\fP member functions, since each of them returns a +reference to its class object. For example, to pass PCRE_CASELESS, +PCRE_EXTENDED, and PCRE_MULTILINE to a RE with one statement, you may write: +.sp + RE(" ^ xyz \e\es+ .* blah$", + RE_Options() + .set_caseless(true) + .set_extended(true) + .set_multiline(true)).PartialMatch(sometext); +.sp +. +. +.SH "SCANNING TEXT INCREMENTALLY" +.rs +.sp +The "Consume" operation may be useful if you want to repeatedly +match regular expressions at the front of a string and skip over +them as they match. This requires use of the "StringPiece" type, +which represents a sub-range of a real string. Like RE, StringPiece +is defined in the pcrecpp namespace. +.sp + Example: read lines of the form "var = value" from a string. + string contents = ...; // Fill string somehow + pcrecpp::StringPiece input(contents); // Wrap in a StringPiece +.sp + string var; + int value; + pcrecpp::RE re("(\e\ew+) = (\e\ed+)\en"); + while (re.Consume(&input, &var, &value)) { + ...; + } +.sp +Each successful call to "Consume" will set "var/value", and also +advance "input" so it points past the matched text. +.P +The "FindAndConsume" operation is similar to "Consume" but does not +anchor your match at the beginning of the string. For example, you +could extract all words from a string by repeatedly calling +.sp + pcrecpp::RE("(\e\ew+)").FindAndConsume(&input, &word) +. +. +.SH "PARSING HEX/OCTAL/C-RADIX NUMBERS" +.rs +.sp +By default, if you pass a pointer to a numeric value, the +corresponding text is interpreted as a base-10 number. You can +instead wrap the pointer with a call to one of the operators Hex(), +Octal(), or CRadix() to interpret the text in another base. The +CRadix operator interprets C-style "0" (base-8) and "0x" (base-16) +prefixes, but defaults to base-10. +.sp + Example: + int a, b, c, d; + pcrecpp::RE re("(.*) (.*) (.*) (.*)"); + re.FullMatch("100 40 0100 0x40", + pcrecpp::Octal(&a), pcrecpp::Hex(&b), + pcrecpp::CRadix(&c), pcrecpp::CRadix(&d)); +.sp +will leave 64 in a, b, c, and d. +. +. +.SH "REPLACING PARTS OF STRINGS" +.rs +.sp +You can replace the first match of "pattern" in "str" with "rewrite". +Within "rewrite", backslash-escaped digits (\e1 to \e9) can be +used to insert text matching corresponding parenthesized group +from the pattern. \e0 in "rewrite" refers to the entire matching +text. For example: +.sp + string s = "yabba dabba doo"; + pcrecpp::RE("b+").Replace("d", &s); +.sp +will leave "s" containing "yada dabba doo". The result is true if the pattern +matches and a replacement occurs, false otherwise. +.P +\fBGlobalReplace\fP is like \fBReplace\fP except that it replaces all +occurrences of the pattern in the string with the rewrite. Replacements are +not subject to re-matching. For example: +.sp + string s = "yabba dabba doo"; + pcrecpp::RE("b+").GlobalReplace("d", &s); +.sp +will leave "s" containing "yada dada doo". It returns the number of +replacements made. +.P +\fBExtract\fP is like \fBReplace\fP, except that if the pattern matches, +"rewrite" is copied into "out" (an additional argument) with substitutions. +The non-matching portions of "text" are ignored. Returns true iff a match +occurred and the extraction happened successfully; if no match occurs, the +string is left unaffected. +. +. +.SH AUTHOR +.rs +.sp +.nf +The C++ wrapper was contributed by Google Inc. +Copyright (c) 2007 Google Inc. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 08 January 2012 +.fi diff --git a/plugins/Pcre16/docs/doc/pcredemo.3 b/plugins/Pcre16/docs/doc/pcredemo.3 new file mode 100644 index 0000000000..194629b1fa --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcredemo.3 @@ -0,0 +1,424 @@ +.\" Start example. +.de EX +. nr mE \\n(.f +. nf +. nh +. ft CW +.. +. +. +.\" End example. +.de EE +. ft \\n(mE +. fi +. hy \\n(HY +.. +. +.EX +/************************************************* +* PCRE DEMONSTRATION PROGRAM * +*************************************************/ + +/* This is a demonstration program to illustrate the most straightforward ways +of calling the PCRE regular expression library from a C program. See the +pcresample documentation for a short discussion ("man pcresample" if you have +the PCRE man pages installed). + +In Unix-like environments, if PCRE is installed in your standard system +libraries, you should be able to compile this program using this command: + +gcc -Wall pcredemo.c -lpcre -o pcredemo + +If PCRE is not installed in a standard place, it is likely to be installed with +support for the pkg-config mechanism. If you have pkg-config, you can compile +this program using this command: + +gcc -Wall pcredemo.c `pkg-config --cflags --libs libpcre` -o pcredemo + +If you do not have pkg-config, you may have to use this: + +gcc -Wall pcredemo.c -I/usr/local/include -L/usr/local/lib \e + -R/usr/local/lib -lpcre -o pcredemo + +Replace "/usr/local/include" and "/usr/local/lib" with wherever the include and +library files for PCRE are installed on your system. Only some operating +systems (e.g. Solaris) use the -R option. + +Building under Windows: + +If you want to statically link this program against a non-dll .a file, you must +define PCRE_STATIC before including pcre.h, otherwise the pcre_malloc() and +pcre_free() exported functions will be declared __declspec(dllimport), with +unwanted results. So in this environment, uncomment the following line. */ + +/* #define PCRE_STATIC */ + +#include <stdio.h> +#include <string.h> +#include <pcre.h> + +#define OVECCOUNT 30 /* should be a multiple of 3 */ + + +int main(int argc, char **argv) +{ +pcre *re; +const char *error; +char *pattern; +char *subject; +unsigned char *name_table; +unsigned int option_bits; +int erroffset; +int find_all; +int crlf_is_newline; +int namecount; +int name_entry_size; +int ovector[OVECCOUNT]; +int subject_length; +int rc, i; +int utf8; + + +/************************************************************************** +* First, sort out the command line. There is only one possible option at * +* the moment, "-g" to request repeated matching to find all occurrences, * +* like Perl's /g option. We set the variable find_all to a non-zero value * +* if the -g option is present. Apart from that, there must be exactly two * +* arguments. * +**************************************************************************/ + +find_all = 0; +for (i = 1; i < argc; i++) + { + if (strcmp(argv[i], "-g") == 0) find_all = 1; + else break; + } + +/* After the options, we require exactly two arguments, which are the pattern, +and the subject string. */ + +if (argc - i != 2) + { + printf("Two arguments required: a regex and a subject string\en"); + return 1; + } + +pattern = argv[i]; +subject = argv[i+1]; +subject_length = (int)strlen(subject); + + +/************************************************************************* +* Now we are going to compile the regular expression pattern, and handle * +* and errors that are detected. * +*************************************************************************/ + +re = pcre_compile( + pattern, /* the pattern */ + 0, /* default options */ + &error, /* for error message */ + &erroffset, /* for error offset */ + NULL); /* use default character tables */ + +/* Compilation failed: print the error message and exit */ + +if (re == NULL) + { + printf("PCRE compilation failed at offset %d: %s\en", erroffset, error); + return 1; + } + + +/************************************************************************* +* If the compilation succeeded, we call PCRE again, in order to do a * +* pattern match against the subject string. This does just ONE match. If * +* further matching is needed, it will be done below. * +*************************************************************************/ + +rc = pcre_exec( + re, /* the compiled pattern */ + NULL, /* no extra data - we didn't study the pattern */ + subject, /* the subject string */ + subject_length, /* the length of the subject */ + 0, /* start at offset 0 in the subject */ + 0, /* default options */ + ovector, /* output vector for substring information */ + OVECCOUNT); /* number of elements in the output vector */ + +/* Matching failed: handle error cases */ + +if (rc < 0) + { + switch(rc) + { + case PCRE_ERROR_NOMATCH: printf("No match\en"); break; + /* + Handle other special cases if you like + */ + default: printf("Matching error %d\en", rc); break; + } + pcre_free(re); /* Release memory used for the compiled pattern */ + return 1; + } + +/* Match succeded */ + +printf("\enMatch succeeded at offset %d\en", ovector[0]); + + +/************************************************************************* +* We have found the first match within the subject string. If the output * +* vector wasn't big enough, say so. Then output any substrings that were * +* captured. * +*************************************************************************/ + +/* The output vector wasn't big enough */ + +if (rc == 0) + { + rc = OVECCOUNT/3; + printf("ovector only has room for %d captured substrings\en", rc - 1); + } + +/* Show substrings stored in the output vector by number. Obviously, in a real +application you might want to do things other than print them. */ + +for (i = 0; i < rc; i++) + { + char *substring_start = subject + ovector[2*i]; + int substring_length = ovector[2*i+1] - ovector[2*i]; + printf("%2d: %.*s\en", i, substring_length, substring_start); + } + + +/************************************************************************** +* That concludes the basic part of this demonstration program. We have * +* compiled a pattern, and performed a single match. The code that follows * +* shows first how to access named substrings, and then how to code for * +* repeated matches on the same subject. * +**************************************************************************/ + +/* See if there are any named substrings, and if so, show them by name. First +we have to extract the count of named parentheses from the pattern. */ + +(void)pcre_fullinfo( + re, /* the compiled pattern */ + NULL, /* no extra data - we didn't study the pattern */ + PCRE_INFO_NAMECOUNT, /* number of named substrings */ + &namecount); /* where to put the answer */ + +if (namecount <= 0) printf("No named substrings\en"); else + { + unsigned char *tabptr; + printf("Named substrings\en"); + + /* Before we can access the substrings, we must extract the table for + translating names to numbers, and the size of each entry in the table. */ + + (void)pcre_fullinfo( + re, /* the compiled pattern */ + NULL, /* no extra data - we didn't study the pattern */ + PCRE_INFO_NAMETABLE, /* address of the table */ + &name_table); /* where to put the answer */ + + (void)pcre_fullinfo( + re, /* the compiled pattern */ + NULL, /* no extra data - we didn't study the pattern */ + PCRE_INFO_NAMEENTRYSIZE, /* size of each entry in the table */ + &name_entry_size); /* where to put the answer */ + + /* Now we can scan the table and, for each entry, print the number, the name, + and the substring itself. */ + + tabptr = name_table; + for (i = 0; i < namecount; i++) + { + int n = (tabptr[0] << 8) | tabptr[1]; + printf("(%d) %*s: %.*s\en", n, name_entry_size - 3, tabptr + 2, + ovector[2*n+1] - ovector[2*n], subject + ovector[2*n]); + tabptr += name_entry_size; + } + } + + +/************************************************************************* +* If the "-g" option was given on the command line, we want to continue * +* to search for additional matches in the subject string, in a similar * +* way to the /g option in Perl. This turns out to be trickier than you * +* might think because of the possibility of matching an empty string. * +* What happens is as follows: * +* * +* If the previous match was NOT for an empty string, we can just start * +* the next match at the end of the previous one. * +* * +* If the previous match WAS for an empty string, we can't do that, as it * +* would lead to an infinite loop. Instead, a special call of pcre_exec() * +* is made with the PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED flags set. * +* The first of these tells PCRE that an empty string at the start of the * +* subject is not a valid match; other possibilities must be tried. The * +* second flag restricts PCRE to one match attempt at the initial string * +* position. If this match succeeds, an alternative to the empty string * +* match has been found, and we can print it and proceed round the loop, * +* advancing by the length of whatever was found. If this match does not * +* succeed, we still stay in the loop, advancing by just one character. * +* In UTF-8 mode, which can be set by (*UTF8) in the pattern, this may be * +* more than one byte. * +* * +* However, there is a complication concerned with newlines. When the * +* newline convention is such that CRLF is a valid newline, we must * +* advance by two characters rather than one. The newline convention can * +* be set in the regex by (*CR), etc.; if not, we must find the default. * +*************************************************************************/ + +if (!find_all) /* Check for -g */ + { + pcre_free(re); /* Release the memory used for the compiled pattern */ + return 0; /* Finish unless -g was given */ + } + +/* Before running the loop, check for UTF-8 and whether CRLF is a valid newline +sequence. First, find the options with which the regex was compiled; extract +the UTF-8 state, and mask off all but the newline options. */ + +(void)pcre_fullinfo(re, NULL, PCRE_INFO_OPTIONS, &option_bits); +utf8 = option_bits & PCRE_UTF8; +option_bits &= PCRE_NEWLINE_CR|PCRE_NEWLINE_LF|PCRE_NEWLINE_CRLF| + PCRE_NEWLINE_ANY|PCRE_NEWLINE_ANYCRLF; + +/* If no newline options were set, find the default newline convention from the +build configuration. */ + +if (option_bits == 0) + { + int d; + (void)pcre_config(PCRE_CONFIG_NEWLINE, &d); + /* Note that these values are always the ASCII ones, even in + EBCDIC environments. CR = 13, NL = 10. */ + option_bits = (d == 13)? PCRE_NEWLINE_CR : + (d == 10)? PCRE_NEWLINE_LF : + (d == (13<<8 | 10))? PCRE_NEWLINE_CRLF : + (d == -2)? PCRE_NEWLINE_ANYCRLF : + (d == -1)? PCRE_NEWLINE_ANY : 0; + } + +/* See if CRLF is a valid newline sequence. */ + +crlf_is_newline = + option_bits == PCRE_NEWLINE_ANY || + option_bits == PCRE_NEWLINE_CRLF || + option_bits == PCRE_NEWLINE_ANYCRLF; + +/* Loop for second and subsequent matches */ + +for (;;) + { + int options = 0; /* Normally no options */ + int start_offset = ovector[1]; /* Start at end of previous match */ + + /* If the previous match was for an empty string, we are finished if we are + at the end of the subject. Otherwise, arrange to run another match at the + same point to see if a non-empty match can be found. */ + + if (ovector[0] == ovector[1]) + { + if (ovector[0] == subject_length) break; + options = PCRE_NOTEMPTY_ATSTART | PCRE_ANCHORED; + } + + /* Run the next matching operation */ + + rc = pcre_exec( + re, /* the compiled pattern */ + NULL, /* no extra data - we didn't study the pattern */ + subject, /* the subject string */ + subject_length, /* the length of the subject */ + start_offset, /* starting offset in the subject */ + options, /* options */ + ovector, /* output vector for substring information */ + OVECCOUNT); /* number of elements in the output vector */ + + /* This time, a result of NOMATCH isn't an error. If the value in "options" + is zero, it just means we have found all possible matches, so the loop ends. + Otherwise, it means we have failed to find a non-empty-string match at a + point where there was a previous empty-string match. In this case, we do what + Perl does: advance the matching position by one character, and continue. We + do this by setting the "end of previous match" offset, because that is picked + up at the top of the loop as the point at which to start again. + + There are two complications: (a) When CRLF is a valid newline sequence, and + the current position is just before it, advance by an extra byte. (b) + Otherwise we must ensure that we skip an entire UTF-8 character if we are in + UTF-8 mode. */ + + if (rc == PCRE_ERROR_NOMATCH) + { + if (options == 0) break; /* All matches found */ + ovector[1] = start_offset + 1; /* Advance one byte */ + if (crlf_is_newline && /* If CRLF is newline & */ + start_offset < subject_length - 1 && /* we are at CRLF, */ + subject[start_offset] == '\er' && + subject[start_offset + 1] == '\en') + ovector[1] += 1; /* Advance by one more. */ + else if (utf8) /* Otherwise, ensure we */ + { /* advance a whole UTF-8 */ + while (ovector[1] < subject_length) /* character. */ + { + if ((subject[ovector[1]] & 0xc0) != 0x80) break; + ovector[1] += 1; + } + } + continue; /* Go round the loop again */ + } + + /* Other matching errors are not recoverable. */ + + if (rc < 0) + { + printf("Matching error %d\en", rc); + pcre_free(re); /* Release memory used for the compiled pattern */ + return 1; + } + + /* Match succeded */ + + printf("\enMatch succeeded again at offset %d\en", ovector[0]); + + /* The match succeeded, but the output vector wasn't big enough. */ + + if (rc == 0) + { + rc = OVECCOUNT/3; + printf("ovector only has room for %d captured substrings\en", rc - 1); + } + + /* As before, show substrings stored in the output vector by number, and then + also any named substrings. */ + + for (i = 0; i < rc; i++) + { + char *substring_start = subject + ovector[2*i]; + int substring_length = ovector[2*i+1] - ovector[2*i]; + printf("%2d: %.*s\en", i, substring_length, substring_start); + } + + if (namecount <= 0) printf("No named substrings\en"); else + { + unsigned char *tabptr = name_table; + printf("Named substrings\en"); + for (i = 0; i < namecount; i++) + { + int n = (tabptr[0] << 8) | tabptr[1]; + printf("(%d) %*s: %.*s\en", n, name_entry_size - 3, tabptr + 2, + ovector[2*n+1] - ovector[2*n], subject + ovector[2*n]); + tabptr += name_entry_size; + } + } + } /* End of loop to find second and subsequent matches */ + +printf("\en"); +pcre_free(re); /* Release memory used for the compiled pattern */ +return 0; +} + +/* End of pcredemo.c */ +.EE diff --git a/plugins/Pcre16/docs/doc/pcregrep.1 b/plugins/Pcre16/docs/doc/pcregrep.1 new file mode 100644 index 0000000000..988667542f --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcregrep.1 @@ -0,0 +1,683 @@ +.TH PCREGREP 1 "03 April 2014" "PCRE 8.35" +.SH NAME +pcregrep - a grep with Perl-compatible regular expressions. +.SH SYNOPSIS +.B pcregrep [options] [long options] [pattern] [path1 path2 ...] +. +.SH DESCRIPTION +.rs +.sp +\fBpcregrep\fP searches files for character patterns, in the same way as other +grep commands do, but it uses the PCRE regular expression library to support +patterns that are compatible with the regular expressions of Perl 5. See +.\" HREF +\fBpcresyntax\fP(3) +.\" +for a quick-reference summary of pattern syntax, or +.\" HREF +\fBpcrepattern\fP(3) +.\" +for a full description of the syntax and semantics of the regular expressions +that PCRE supports. +.P +Patterns, whether supplied on the command line or in a separate file, are given +without delimiters. For example: +.sp + pcregrep Thursday /etc/motd +.sp +If you attempt to use delimiters (for example, by surrounding a pattern with +slashes, as is common in Perl scripts), they are interpreted as part of the +pattern. Quotes can of course be used to delimit patterns on the command line +because they are interpreted by the shell, and indeed quotes are required if a +pattern contains white space or shell metacharacters. +.P +The first argument that follows any option settings is treated as the single +pattern to be matched when neither \fB-e\fP nor \fB-f\fP is present. +Conversely, when one or both of these options are used to specify patterns, all +arguments are treated as path names. At least one of \fB-e\fP, \fB-f\fP, or an +argument pattern must be provided. +.P +If no files are specified, \fBpcregrep\fP reads the standard input. The +standard input can also be referenced by a name consisting of a single hyphen. +For example: +.sp + pcregrep some-pattern /file1 - /file3 +.sp +By default, each line that matches a pattern is copied to the standard +output, and if there is more than one file, the file name is output at the +start of each line, followed by a colon. However, there are options that can +change how \fBpcregrep\fP behaves. In particular, the \fB-M\fP option makes it +possible to search for patterns that span line boundaries. What defines a line +boundary is controlled by the \fB-N\fP (\fB--newline\fP) option. +.P +The amount of memory used for buffering files that are being scanned is +controlled by a parameter that can be set by the \fB--buffer-size\fP option. +The default value for this parameter is specified when \fBpcregrep\fP is built, +with the default default being 20K. A block of memory three times this size is +used (to allow for buffering "before" and "after" lines). An error occurs if a +line overflows the buffer. +.P +Patterns can be no longer than 8K or BUFSIZ bytes, whichever is the greater. +BUFSIZ is defined in \fB<stdio.h>\fP. When there is more than one pattern +(specified by the use of \fB-e\fP and/or \fB-f\fP), each pattern is applied to +each line in the order in which they are defined, except that all the \fB-e\fP +patterns are tried before the \fB-f\fP patterns. +.P +By default, as soon as one pattern matches a line, no further patterns are +considered. However, if \fB--colour\fP (or \fB--color\fP) is used to colour the +matching substrings, or if \fB--only-matching\fP, \fB--file-offsets\fP, or +\fB--line-offsets\fP is used to output only the part of the line that matched +(either shown literally, or as an offset), scanning resumes immediately +following the match, so that further matches on the same line can be found. If +there are multiple patterns, they are all tried on the remainder of the line, +but patterns that follow the one that matched are not tried on the earlier part +of the line. +.P +This behaviour means that the order in which multiple patterns are specified +can affect the output when one of the above options is used. This is no longer +the same behaviour as GNU grep, which now manages to display earlier matches +for later patterns (as long as there is no overlap). +.P +Patterns that can match an empty string are accepted, but empty string +matches are never recognized. An example is the pattern "(super)?(man)?", in +which all components are optional. This pattern finds all occurrences of both +"super" and "man"; the output differs from matching with "super|man" when only +the matching substrings are being shown. +.P +If the \fBLC_ALL\fP or \fBLC_CTYPE\fP environment variable is set, +\fBpcregrep\fP uses the value to set a locale when calling the PCRE library. +The \fB--locale\fP option can be used to override this. +. +. +.SH "SUPPORT FOR COMPRESSED FILES" +.rs +.sp +It is possible to compile \fBpcregrep\fP so that it uses \fBlibz\fP or +\fBlibbz2\fP to read files whose names end in \fB.gz\fP or \fB.bz2\fP, +respectively. You can find out whether your binary has support for one or both +of these file types by running it with the \fB--help\fP option. If the +appropriate support is not present, files are treated as plain text. The +standard input is always so treated. +. +. +.SH "BINARY FILES" +.rs +.sp +By default, a file that contains a binary zero byte within the first 1024 bytes +is identified as a binary file, and is processed specially. (GNU grep also +identifies binary files in this manner.) See the \fB--binary-files\fP option +for a means of changing the way binary files are handled. +. +. +.SH OPTIONS +.rs +.sp +The order in which some of the options appear can affect the output. For +example, both the \fB-h\fP and \fB-l\fP options affect the printing of file +names. Whichever comes later in the command line will be the one that takes +effect. Similarly, except where noted below, if an option is given twice, the +later setting is used. Numerical values for options may be followed by K or M, +to signify multiplication by 1024 or 1024*1024 respectively. +.TP 10 +\fB--\fP +This terminates the list of options. It is useful if the next item on the +command line starts with a hyphen but is not an option. This allows for the +processing of patterns and filenames that start with hyphens. +.TP +\fB-A\fP \fInumber\fP, \fB--after-context=\fP\fInumber\fP +Output \fInumber\fP lines of context after each matching line. If filenames +and/or line numbers are being output, a hyphen separator is used instead of a +colon for the context lines. A line containing "--" is output between each +group of lines, unless they are in fact contiguous in the input file. The value +of \fInumber\fP is expected to be relatively small. However, \fBpcregrep\fP +guarantees to have up to 8K of following text available for context output. +.TP +\fB-a\fP, \fB--text\fP +Treat binary files as text. This is equivalent to +\fB--binary-files\fP=\fItext\fP. +.TP +\fB-B\fP \fInumber\fP, \fB--before-context=\fP\fInumber\fP +Output \fInumber\fP lines of context before each matching line. If filenames +and/or line numbers are being output, a hyphen separator is used instead of a +colon for the context lines. A line containing "--" is output between each +group of lines, unless they are in fact contiguous in the input file. The value +of \fInumber\fP is expected to be relatively small. However, \fBpcregrep\fP +guarantees to have up to 8K of preceding text available for context output. +.TP +\fB--binary-files=\fP\fIword\fP +Specify how binary files are to be processed. If the word is "binary" (the +default), pattern matching is performed on binary files, but the only output is +"Binary file <name> matches" when a match succeeds. If the word is "text", +which is equivalent to the \fB-a\fP or \fB--text\fP option, binary files are +processed in the same way as any other file. In this case, when a match +succeeds, the output may be binary garbage, which can have nasty effects if +sent to a terminal. If the word is "without-match", which is equivalent to the +\fB-I\fP option, binary files are not processed at all; they are assumed not to +be of interest. +.TP +\fB--buffer-size=\fP\fInumber\fP +Set the parameter that controls how much memory is used for buffering files +that are being scanned. +.TP +\fB-C\fP \fInumber\fP, \fB--context=\fP\fInumber\fP +Output \fInumber\fP lines of context both before and after each matching line. +This is equivalent to setting both \fB-A\fP and \fB-B\fP to the same value. +.TP +\fB-c\fP, \fB--count\fP +Do not output individual lines from the files that are being scanned; instead +output the number of lines that would otherwise have been shown. If no lines +are selected, the number zero is output. If several files are are being +scanned, a count is output for each of them. However, if the +\fB--files-with-matches\fP option is also used, only those files whose counts +are greater than zero are listed. When \fB-c\fP is used, the \fB-A\fP, +\fB-B\fP, and \fB-C\fP options are ignored. +.TP +\fB--colour\fP, \fB--color\fP +If this option is given without any data, it is equivalent to "--colour=auto". +If data is required, it must be given in the same shell item, separated by an +equals sign. +.TP +\fB--colour=\fP\fIvalue\fP, \fB--color=\fP\fIvalue\fP +This option specifies under what circumstances the parts of a line that matched +a pattern should be coloured in the output. By default, the output is not +coloured. The value (which is optional, see above) may be "never", "always", or +"auto". In the latter case, colouring happens only if the standard output is +connected to a terminal. More resources are used when colouring is enabled, +because \fBpcregrep\fP has to search for all possible matches in a line, not +just one, in order to colour them all. +.sp +The colour that is used can be specified by setting the environment variable +PCREGREP_COLOUR or PCREGREP_COLOR. The value of this variable should be a +string of two numbers, separated by a semicolon. They are copied directly into +the control string for setting colour on a terminal, so it is your +responsibility to ensure that they make sense. If neither of the environment +variables is set, the default is "1;31", which gives red. +.TP +\fB-D\fP \fIaction\fP, \fB--devices=\fP\fIaction\fP +If an input path is not a regular file or a directory, "action" specifies how +it is to be processed. Valid values are "read" (the default) or "skip" +(silently skip the path). +.TP +\fB-d\fP \fIaction\fP, \fB--directories=\fP\fIaction\fP +If an input path is a directory, "action" specifies how it is to be processed. +Valid values are "read" (the default in non-Windows environments, for +compatibility with GNU grep), "recurse" (equivalent to the \fB-r\fP option), or +"skip" (silently skip the path, the default in Windows environments). In the +"read" case, directories are read as if they were ordinary files. In some +operating systems the effect of reading a directory like this is an immediate +end-of-file; in others it may provoke an error. +.TP +\fB-e\fP \fIpattern\fP, \fB--regex=\fP\fIpattern\fP, \fB--regexp=\fP\fIpattern\fP +Specify a pattern to be matched. This option can be used multiple times in +order to specify several patterns. It can also be used as a way of specifying a +single pattern that starts with a hyphen. When \fB-e\fP is used, no argument +pattern is taken from the command line; all arguments are treated as file +names. There is no limit to the number of patterns. They are applied to each +line in the order in which they are defined until one matches. +.sp +If \fB-f\fP is used with \fB-e\fP, the command line patterns are matched first, +followed by the patterns from the file(s), independent of the order in which +these options are specified. Note that multiple use of \fB-e\fP is not the same +as a single pattern with alternatives. For example, X|Y finds the first +character in a line that is X or Y, whereas if the two patterns are given +separately, with X first, \fBpcregrep\fP finds X if it is present, even if it +follows Y in the line. It finds Y only if there is no X in the line. This +matters only if you are using \fB-o\fP or \fB--colo(u)r\fP to show the part(s) +of the line that matched. +.TP +\fB--exclude\fP=\fIpattern\fP +Files (but not directories) whose names match the pattern are skipped without +being processed. This applies to all files, whether listed on the command line, +obtained from \fB--file-list\fP, or by scanning a directory. The pattern is a +PCRE regular expression, and is matched against the final component of the file +name, not the entire path. The \fB-F\fP, \fB-w\fP, and \fB-x\fP options do not +apply to this pattern. The option may be given any number of times in order to +specify multiple patterns. If a file name matches both an \fB--include\fP +and an \fB--exclude\fP pattern, it is excluded. There is no short form for this +option. +.TP +\fB--exclude-from=\fP\fIfilename\fP +Treat each non-empty line of the file as the data for an \fB--exclude\fP +option. What constitutes a newline when reading the file is the operating +system's default. The \fB--newline\fP option has no effect on this option. This +option may be given more than once in order to specify a number of files to +read. +.TP +\fB--exclude-dir\fP=\fIpattern\fP +Directories whose names match the pattern are skipped without being processed, +whatever the setting of the \fB--recursive\fP option. This applies to all +directories, whether listed on the command line, obtained from +\fB--file-list\fP, or by scanning a parent directory. The pattern is a PCRE +regular expression, and is matched against the final component of the directory +name, not the entire path. The \fB-F\fP, \fB-w\fP, and \fB-x\fP options do not +apply to this pattern. The option may be given any number of times in order to +specify more than one pattern. If a directory matches both \fB--include-dir\fP +and \fB--exclude-dir\fP, it is excluded. There is no short form for this +option. +.TP +\fB-F\fP, \fB--fixed-strings\fP +Interpret each data-matching pattern as a list of fixed strings, separated by +newlines, instead of as a regular expression. What constitutes a newline for +this purpose is controlled by the \fB--newline\fP option. The \fB-w\fP (match +as a word) and \fB-x\fP (match whole line) options can be used with \fB-F\fP. +They apply to each of the fixed strings. A line is selected if any of the fixed +strings are found in it (subject to \fB-w\fP or \fB-x\fP, if present). This +option applies only to the patterns that are matched against the contents of +files; it does not apply to patterns specified by any of the \fB--include\fP or +\fB--exclude\fP options. +.TP +\fB-f\fP \fIfilename\fP, \fB--file=\fP\fIfilename\fP +Read patterns from the file, one per line, and match them against +each line of input. What constitutes a newline when reading the file is the +operating system's default. The \fB--newline\fP option has no effect on this +option. Trailing white space is removed from each line, and blank lines are +ignored. An empty file contains no patterns and therefore matches nothing. See +also the comments about multiple patterns versus a single pattern with +alternatives in the description of \fB-e\fP above. +.sp +If this option is given more than once, all the specified files are +read. A data line is output if any of the patterns match it. A filename can +be given as "-" to refer to the standard input. When \fB-f\fP is used, patterns +specified on the command line using \fB-e\fP may also be present; they are +tested before the file's patterns. However, no other pattern is taken from the +command line; all arguments are treated as the names of paths to be searched. +.TP +\fB--file-list\fP=\fIfilename\fP +Read a list of files and/or directories that are to be scanned from the given +file, one per line. Trailing white space is removed from each line, and blank +lines are ignored. These paths are processed before any that are listed on the +command line. The filename can be given as "-" to refer to the standard input. +If \fB--file\fP and \fB--file-list\fP are both specified as "-", patterns are +read first. This is useful only when the standard input is a terminal, from +which further lines (the list of files) can be read after an end-of-file +indication. If this option is given more than once, all the specified files are +read. +.TP +\fB--file-offsets\fP +Instead of showing lines or parts of lines that match, show each match as an +offset from the start of the file and a length, separated by a comma. In this +mode, no context is shown. That is, the \fB-A\fP, \fB-B\fP, and \fB-C\fP +options are ignored. If there is more than one match in a line, each of them is +shown separately. This option is mutually exclusive with \fB--line-offsets\fP +and \fB--only-matching\fP. +.TP +\fB-H\fP, \fB--with-filename\fP +Force the inclusion of the filename at the start of output lines when searching +a single file. By default, the filename is not shown in this case. For matching +lines, the filename is followed by a colon; for context lines, a hyphen +separator is used. If a line number is also being output, it follows the file +name. +.TP +\fB-h\fP, \fB--no-filename\fP +Suppress the output filenames when searching multiple files. By default, +filenames are shown when multiple files are searched. For matching lines, the +filename is followed by a colon; for context lines, a hyphen separator is used. +If a line number is also being output, it follows the file name. +.TP +\fB--help\fP +Output a help message, giving brief details of the command options and file +type support, and then exit. Anything else on the command line is +ignored. +.TP +\fB-I\fP +Treat binary files as never matching. This is equivalent to +\fB--binary-files\fP=\fIwithout-match\fP. +.TP +\fB-i\fP, \fB--ignore-case\fP +Ignore upper/lower case distinctions during comparisons. +.TP +\fB--include\fP=\fIpattern\fP +If any \fB--include\fP patterns are specified, the only files that are +processed are those that match one of the patterns (and do not match an +\fB--exclude\fP pattern). This option does not affect directories, but it +applies to all files, whether listed on the command line, obtained from +\fB--file-list\fP, or by scanning a directory. The pattern is a PCRE regular +expression, and is matched against the final component of the file name, not +the entire path. The \fB-F\fP, \fB-w\fP, and \fB-x\fP options do not apply to +this pattern. The option may be given any number of times. If a file name +matches both an \fB--include\fP and an \fB--exclude\fP pattern, it is excluded. +There is no short form for this option. +.TP +\fB--include-from=\fP\fIfilename\fP +Treat each non-empty line of the file as the data for an \fB--include\fP +option. What constitutes a newline for this purpose is the operating system's +default. The \fB--newline\fP option has no effect on this option. This option +may be given any number of times; all the files are read. +.TP +\fB--include-dir\fP=\fIpattern\fP +If any \fB--include-dir\fP patterns are specified, the only directories that +are processed are those that match one of the patterns (and do not match an +\fB--exclude-dir\fP pattern). This applies to all directories, whether listed +on the command line, obtained from \fB--file-list\fP, or by scanning a parent +directory. The pattern is a PCRE regular expression, and is matched against the +final component of the directory name, not the entire path. The \fB-F\fP, +\fB-w\fP, and \fB-x\fP options do not apply to this pattern. The option may be +given any number of times. If a directory matches both \fB--include-dir\fP and +\fB--exclude-dir\fP, it is excluded. There is no short form for this option. +.TP +\fB-L\fP, \fB--files-without-match\fP +Instead of outputting lines from the files, just output the names of the files +that do not contain any lines that would have been output. Each file name is +output once, on a separate line. +.TP +\fB-l\fP, \fB--files-with-matches\fP +Instead of outputting lines from the files, just output the names of the files +containing lines that would have been output. Each file name is output +once, on a separate line. Searching normally stops as soon as a matching line +is found in a file. However, if the \fB-c\fP (count) option is also used, +matching continues in order to obtain the correct count, and those files that +have at least one match are listed along with their counts. Using this option +with \fB-c\fP is a way of suppressing the listing of files with no matches. +.TP +\fB--label\fP=\fIname\fP +This option supplies a name to be used for the standard input when file names +are being output. If not supplied, "(standard input)" is used. There is no +short form for this option. +.TP +\fB--line-buffered\fP +When this option is given, input is read and processed line by line, and the +output is flushed after each write. By default, input is read in large chunks, +unless \fBpcregrep\fP can determine that it is reading from a terminal (which +is currently possible only in Unix-like environments). Output to terminal is +normally automatically flushed by the operating system. This option can be +useful when the input or output is attached to a pipe and you do not want +\fBpcregrep\fP to buffer up large amounts of data. However, its use will affect +performance, and the \fB-M\fP (multiline) option ceases to work. +.TP +\fB--line-offsets\fP +Instead of showing lines or parts of lines that match, show each match as a +line number, the offset from the start of the line, and a length. The line +number is terminated by a colon (as usual; see the \fB-n\fP option), and the +offset and length are separated by a comma. In this mode, no context is shown. +That is, the \fB-A\fP, \fB-B\fP, and \fB-C\fP options are ignored. If there is +more than one match in a line, each of them is shown separately. This option is +mutually exclusive with \fB--file-offsets\fP and \fB--only-matching\fP. +.TP +\fB--locale\fP=\fIlocale-name\fP +This option specifies a locale to be used for pattern matching. It overrides +the value in the \fBLC_ALL\fP or \fBLC_CTYPE\fP environment variables. If no +locale is specified, the PCRE library's default (usually the "C" locale) is +used. There is no short form for this option. +.TP +\fB--match-limit\fP=\fInumber\fP +Processing some regular expression patterns can require a very large amount of +memory, leading in some cases to a program crash if not enough is available. +Other patterns may take a very long time to search for all possible matching +strings. The \fBpcre_exec()\fP function that is called by \fBpcregrep\fP to do +the matching has two parameters that can limit the resources that it uses. +.sp +The \fB--match-limit\fP option provides a means of limiting resource usage +when processing patterns that are not going to match, but which have a very +large number of possibilities in their search trees. The classic example is a +pattern that uses nested unlimited repeats. Internally, PCRE uses a function +called \fBmatch()\fP which it calls repeatedly (sometimes recursively). The +limit set by \fB--match-limit\fP is imposed on the number of times this +function is called during a match, which has the effect of limiting the amount +of backtracking that can take place. +.sp +The \fB--recursion-limit\fP option is similar to \fB--match-limit\fP, but +instead of limiting the total number of times that \fBmatch()\fP is called, it +limits the depth of recursive calls, which in turn limits the amount of memory +that can be used. The recursion depth is a smaller number than the total number +of calls, because not all calls to \fBmatch()\fP are recursive. This limit is +of use only if it is set smaller than \fB--match-limit\fP. +.sp +There are no short forms for these options. The default settings are specified +when the PCRE library is compiled, with the default default being 10 million. +.TP +\fB-M\fP, \fB--multiline\fP +Allow patterns to match more than one line. When this option is given, patterns +may usefully contain literal newline characters and internal occurrences of ^ +and $ characters. The output for a successful match may consist of more than +one line, the last of which is the one in which the match ended. If the matched +string ends with a newline sequence the output ends at the end of that line. +.sp +When this option is set, the PCRE library is called in "multiline" mode. +There is a limit to the number of lines that can be matched, imposed by the way +that \fBpcregrep\fP buffers the input file as it scans it. However, +\fBpcregrep\fP ensures that at least 8K characters or the rest of the document +(whichever is the shorter) are available for forward matching, and similarly +the previous 8K characters (or all the previous characters, if fewer than 8K) +are guaranteed to be available for lookbehind assertions. This option does not +work when input is read line by line (see \fP--line-buffered\fP.) +.TP +\fB-N\fP \fInewline-type\fP, \fB--newline\fP=\fInewline-type\fP +The PCRE library supports five different conventions for indicating +the ends of lines. They are the single-character sequences CR (carriage return) +and LF (linefeed), the two-character sequence CRLF, an "anycrlf" convention, +which recognizes any of the preceding three types, and an "any" convention, in +which any Unicode line ending sequence is assumed to end a line. The Unicode +sequences are the three just mentioned, plus VT (vertical tab, U+000B), FF +(form feed, U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and +PS (paragraph separator, U+2029). +.sp +When the PCRE library is built, a default line-ending sequence is specified. +This is normally the standard sequence for the operating system. Unless +otherwise specified by this option, \fBpcregrep\fP uses the library's default. +The possible values for this option are CR, LF, CRLF, ANYCRLF, or ANY. This +makes it possible to use \fBpcregrep\fP to scan files that have come from other +environments without having to modify their line endings. If the data that is +being scanned does not agree with the convention set by this option, +\fBpcregrep\fP may behave in strange ways. Note that this option does not +apply to files specified by the \fB-f\fP, \fB--exclude-from\fP, or +\fB--include-from\fP options, which are expected to use the operating system's +standard newline sequence. +.TP +\fB-n\fP, \fB--line-number\fP +Precede each output line by its line number in the file, followed by a colon +for matching lines or a hyphen for context lines. If the filename is also being +output, it precedes the line number. This option is forced if +\fB--line-offsets\fP is used. +.TP +\fB--no-jit\fP +If the PCRE library is built with support for just-in-time compiling (which +speeds up matching), \fBpcregrep\fP automatically makes use of this, unless it +was explicitly disabled at build time. This option can be used to disable the +use of JIT at run time. It is provided for testing and working round problems. +It should never be needed in normal use. +.TP +\fB-o\fP, \fB--only-matching\fP +Show only the part of the line that matched a pattern instead of the whole +line. In this mode, no context is shown. That is, the \fB-A\fP, \fB-B\fP, and +\fB-C\fP options are ignored. If there is more than one match in a line, each +of them is shown separately. If \fB-o\fP is combined with \fB-v\fP (invert the +sense of the match to find non-matching lines), no output is generated, but the +return code is set appropriately. If the matched portion of the line is empty, +nothing is output unless the file name or line number are being printed, in +which case they are shown on an otherwise empty line. This option is mutually +exclusive with \fB--file-offsets\fP and \fB--line-offsets\fP. +.TP +\fB-o\fP\fInumber\fP, \fB--only-matching\fP=\fInumber\fP +Show only the part of the line that matched the capturing parentheses of the +given number. Up to 32 capturing parentheses are supported, and -o0 is +equivalent to \fB-o\fP without a number. Because these options can be given +without an argument (see above), if an argument is present, it must be given in +the same shell item, for example, -o3 or --only-matching=2. The comments given +for the non-argument case above also apply to this case. If the specified +capturing parentheses do not exist in the pattern, or were not set in the +match, nothing is output unless the file name or line number are being printed. +.sp +If this option is given multiple times, multiple substrings are output, in the +order the options are given. For example, -o3 -o1 -o3 causes the substrings +matched by capturing parentheses 3 and 1 and then 3 again to be output. By +default, there is no separator (but see the next option). +.TP +\fB--om-separator\fP=\fItext\fP +Specify a separating string for multiple occurrences of \fB-o\fP. The default +is an empty string. Separating strings are never coloured. +.TP +\fB-q\fP, \fB--quiet\fP +Work quietly, that is, display nothing except error messages. The exit +status indicates whether or not any matches were found. +.TP +\fB-r\fP, \fB--recursive\fP +If any given path is a directory, recursively scan the files it contains, +taking note of any \fB--include\fP and \fB--exclude\fP settings. By default, a +directory is read as a normal file; in some operating systems this gives an +immediate end-of-file. This option is a shorthand for setting the \fB-d\fP +option to "recurse". +.TP +\fB--recursion-limit\fP=\fInumber\fP +See \fB--match-limit\fP above. +.TP +\fB-s\fP, \fB--no-messages\fP +Suppress error messages about non-existent or unreadable files. Such files are +quietly skipped. However, the return code is still 2, even if matches were +found in other files. +.TP +\fB-u\fP, \fB--utf-8\fP +Operate in UTF-8 mode. This option is available only if PCRE has been compiled +with UTF-8 support. All patterns (including those for any \fB--exclude\fP and +\fB--include\fP options) and all subject lines that are scanned must be valid +strings of UTF-8 characters. +.TP +\fB-V\fP, \fB--version\fP +Write the version numbers of \fBpcregrep\fP and the PCRE library to the +standard output and then exit. Anything else on the command line is +ignored. +.TP +\fB-v\fP, \fB--invert-match\fP +Invert the sense of the match, so that lines which do \fInot\fP match any of +the patterns are the ones that are found. +.TP +\fB-w\fP, \fB--word-regex\fP, \fB--word-regexp\fP +Force the patterns to match only whole words. This is equivalent to having \eb +at the start and end of the pattern. This option applies only to the patterns +that are matched against the contents of files; it does not apply to patterns +specified by any of the \fB--include\fP or \fB--exclude\fP options. +.TP +\fB-x\fP, \fB--line-regex\fP, \fB--line-regexp\fP +Force the patterns to be anchored (each must start matching at the beginning of +a line) and in addition, require them to match entire lines. This is equivalent +to having ^ and $ characters at the start and end of each alternative branch in +every pattern. This option applies only to the patterns that are matched +against the contents of files; it does not apply to patterns specified by any +of the \fB--include\fP or \fB--exclude\fP options. +. +. +.SH "ENVIRONMENT VARIABLES" +.rs +.sp +The environment variables \fBLC_ALL\fP and \fBLC_CTYPE\fP are examined, in that +order, for a locale. The first one that is set is used. This can be overridden +by the \fB--locale\fP option. If no locale is set, the PCRE library's default +(usually the "C" locale) is used. +. +. +.SH "NEWLINES" +.rs +.sp +The \fB-N\fP (\fB--newline\fP) option allows \fBpcregrep\fP to scan files with +different newline conventions from the default. Any parts of the input files +that are written to the standard output are copied identically, with whatever +newline sequences they have in the input. However, the setting of this option +does not affect the interpretation of files specified by the \fB-f\fP, +\fB--exclude-from\fP, or \fB--include-from\fP options, which are assumed to use +the operating system's standard newline sequence, nor does it affect the way in +which \fBpcregrep\fP writes informational messages to the standard error and +output streams. For these it uses the string "\en" to indicate newlines, +relying on the C I/O library to convert this to an appropriate sequence. +. +. +.SH "OPTIONS COMPATIBILITY" +.rs +.sp +Many of the short and long forms of \fBpcregrep\fP's options are the same +as in the GNU \fBgrep\fP program. Any long option of the form +\fB--xxx-regexp\fP (GNU terminology) is also available as \fB--xxx-regex\fP +(PCRE terminology). However, the \fB--file-list\fP, \fB--file-offsets\fP, +\fB--include-dir\fP, \fB--line-offsets\fP, \fB--locale\fP, \fB--match-limit\fP, +\fB-M\fP, \fB--multiline\fP, \fB-N\fP, \fB--newline\fP, \fB--om-separator\fP, +\fB--recursion-limit\fP, \fB-u\fP, and \fB--utf-8\fP options are specific to +\fBpcregrep\fP, as is the use of the \fB--only-matching\fP option with a +capturing parentheses number. +.P +Although most of the common options work the same way, a few are different in +\fBpcregrep\fP. For example, the \fB--include\fP option's argument is a glob +for GNU \fBgrep\fP, but a regular expression for \fBpcregrep\fP. If both the +\fB-c\fP and \fB-l\fP options are given, GNU grep lists only file names, +without counts, but \fBpcregrep\fP gives the counts. +. +. +.SH "OPTIONS WITH DATA" +.rs +.sp +There are four different ways in which an option with data can be specified. +If a short form option is used, the data may follow immediately, or (with one +exception) in the next command line item. For example: +.sp + -f/some/file + -f /some/file +.sp +The exception is the \fB-o\fP option, which may appear with or without data. +Because of this, if data is present, it must follow immediately in the same +item, for example -o3. +.P +If a long form option is used, the data may appear in the same command line +item, separated by an equals character, or (with two exceptions) it may appear +in the next command line item. For example: +.sp + --file=/some/file + --file /some/file +.sp +Note, however, that if you want to supply a file name beginning with ~ as data +in a shell command, and have the shell expand ~ to a home directory, you must +separate the file name from the option, because the shell does not treat ~ +specially unless it is at the start of an item. +.P +The exceptions to the above are the \fB--colour\fP (or \fB--color\fP) and +\fB--only-matching\fP options, for which the data is optional. If one of these +options does have data, it must be given in the first form, using an equals +character. Otherwise \fBpcregrep\fP will assume that it has no data. +. +. +.SH "MATCHING ERRORS" +.rs +.sp +It is possible to supply a regular expression that takes a very long time to +fail to match certain lines. Such patterns normally involve nested indefinite +repeats, for example: (a+)*\ed when matched against a line of a's with no final +digit. The PCRE matching function has a resource limit that causes it to abort +in these circumstances. If this happens, \fBpcregrep\fP outputs an error +message and the line that caused the problem to the standard error stream. If +there are more than 20 such errors, \fBpcregrep\fP gives up. +.P +The \fB--match-limit\fP option of \fBpcregrep\fP can be used to set the overall +resource limit; there is a second option called \fB--recursion-limit\fP that +sets a limit on the amount of memory (usually stack) that is used (see the +discussion of these options above). +. +. +.SH DIAGNOSTICS +.rs +.sp +Exit status is 0 if any matches were found, 1 if no matches were found, and 2 +for syntax errors, overlong lines, non-existent or inaccessible files (even if +matches were found in other files) or too many matching errors. Using the +\fB-s\fP option to suppress error messages about inaccessible files does not +affect the return code. +. +. +.SH "SEE ALSO" +.rs +.sp +\fBpcrepattern\fP(3), \fBpcresyntax\fP(3), \fBpcretest\fP(1). +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 03 April 2014 +Copyright (c) 1997-2014 University of Cambridge. +.fi diff --git a/plugins/Pcre16/docs/doc/pcregrep.txt b/plugins/Pcre16/docs/doc/pcregrep.txt new file mode 100644 index 0000000000..97d9a7bd37 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcregrep.txt @@ -0,0 +1,741 @@ +PCREGREP(1) General Commands Manual PCREGREP(1) + + + +NAME + pcregrep - a grep with Perl-compatible regular expressions. + +SYNOPSIS + pcregrep [options] [long options] [pattern] [path1 path2 ...] + + +DESCRIPTION + + pcregrep searches files for character patterns, in the same way as + other grep commands do, but it uses the PCRE regular expression library + to support patterns that are compatible with the regular expressions of + Perl 5. See pcresyntax(3) for a quick-reference summary of pattern syn- + tax, or pcrepattern(3) for a full description of the syntax and seman- + tics of the regular expressions that PCRE supports. + + Patterns, whether supplied on the command line or in a separate file, + are given without delimiters. For example: + + pcregrep Thursday /etc/motd + + If you attempt to use delimiters (for example, by surrounding a pattern + with slashes, as is common in Perl scripts), they are interpreted as + part of the pattern. Quotes can of course be used to delimit patterns + on the command line because they are interpreted by the shell, and + indeed quotes are required if a pattern contains white space or shell + metacharacters. + + The first argument that follows any option settings is treated as the + single pattern to be matched when neither -e nor -f is present. Con- + versely, when one or both of these options are used to specify pat- + terns, all arguments are treated as path names. At least one of -e, -f, + or an argument pattern must be provided. + + If no files are specified, pcregrep reads the standard input. The stan- + dard input can also be referenced by a name consisting of a single + hyphen. For example: + + pcregrep some-pattern /file1 - /file3 + + By default, each line that matches a pattern is copied to the standard + output, and if there is more than one file, the file name is output at + the start of each line, followed by a colon. However, there are options + that can change how pcregrep behaves. In particular, the -M option + makes it possible to search for patterns that span line boundaries. + What defines a line boundary is controlled by the -N (--newline) + option. + + The amount of memory used for buffering files that are being scanned is + controlled by a parameter that can be set by the --buffer-size option. + The default value for this parameter is specified when pcregrep is + built, with the default default being 20K. A block of memory three + times this size is used (to allow for buffering "before" and "after" + lines). An error occurs if a line overflows the buffer. + + Patterns can be no longer than 8K or BUFSIZ bytes, whichever is the + greater. BUFSIZ is defined in <stdio.h>. When there is more than one + pattern (specified by the use of -e and/or -f), each pattern is applied + to each line in the order in which they are defined, except that all + the -e patterns are tried before the -f patterns. + + By default, as soon as one pattern matches a line, no further patterns + are considered. However, if --colour (or --color) is used to colour the + matching substrings, or if --only-matching, --file-offsets, or --line- + offsets is used to output only the part of the line that matched + (either shown literally, or as an offset), scanning resumes immediately + following the match, so that further matches on the same line can be + found. If there are multiple patterns, they are all tried on the + remainder of the line, but patterns that follow the one that matched + are not tried on the earlier part of the line. + + This behaviour means that the order in which multiple patterns are + specified can affect the output when one of the above options is used. + This is no longer the same behaviour as GNU grep, which now manages to + display earlier matches for later patterns (as long as there is no + overlap). + + Patterns that can match an empty string are accepted, but empty string + matches are never recognized. An example is the pattern + "(super)?(man)?", in which all components are optional. This pattern + finds all occurrences of both "super" and "man"; the output differs + from matching with "super|man" when only the matching substrings are + being shown. + + If the LC_ALL or LC_CTYPE environment variable is set, pcregrep uses + the value to set a locale when calling the PCRE library. The --locale + option can be used to override this. + + +SUPPORT FOR COMPRESSED FILES + + It is possible to compile pcregrep so that it uses libz or libbz2 to + read files whose names end in .gz or .bz2, respectively. You can find + out whether your binary has support for one or both of these file types + by running it with the --help option. If the appropriate support is not + present, files are treated as plain text. The standard input is always + so treated. + + +BINARY FILES + + By default, a file that contains a binary zero byte within the first + 1024 bytes is identified as a binary file, and is processed specially. + (GNU grep also identifies binary files in this manner.) See the + --binary-files option for a means of changing the way binary files are + handled. + + +OPTIONS + + The order in which some of the options appear can affect the output. + For example, both the -h and -l options affect the printing of file + names. Whichever comes later in the command line will be the one that + takes effect. Similarly, except where noted below, if an option is + given twice, the later setting is used. Numerical values for options + may be followed by K or M, to signify multiplication by 1024 or + 1024*1024 respectively. + + -- This terminates the list of options. It is useful if the next + item on the command line starts with a hyphen but is not an + option. This allows for the processing of patterns and file- + names that start with hyphens. + + -A number, --after-context=number + Output number lines of context after each matching line. If + filenames and/or line numbers are being output, a hyphen sep- + arator is used instead of a colon for the context lines. A + line containing "--" is output between each group of lines, + unless they are in fact contiguous in the input file. The + value of number is expected to be relatively small. However, + pcregrep guarantees to have up to 8K of following text avail- + able for context output. + + -a, --text + Treat binary files as text. This is equivalent to --binary- + files=text. + + -B number, --before-context=number + Output number lines of context before each matching line. If + filenames and/or line numbers are being output, a hyphen sep- + arator is used instead of a colon for the context lines. A + line containing "--" is output between each group of lines, + unless they are in fact contiguous in the input file. The + value of number is expected to be relatively small. However, + pcregrep guarantees to have up to 8K of preceding text avail- + able for context output. + + --binary-files=word + Specify how binary files are to be processed. If the word is + "binary" (the default), pattern matching is performed on + binary files, but the only output is "Binary file <name> + matches" when a match succeeds. If the word is "text", which + is equivalent to the -a or --text option, binary files are + processed in the same way as any other file. In this case, + when a match succeeds, the output may be binary garbage, + which can have nasty effects if sent to a terminal. If the + word is "without-match", which is equivalent to the -I + option, binary files are not processed at all; they are + assumed not to be of interest. + + --buffer-size=number + Set the parameter that controls how much memory is used for + buffering files that are being scanned. + + -C number, --context=number + Output number lines of context both before and after each + matching line. This is equivalent to setting both -A and -B + to the same value. + + -c, --count + Do not output individual lines from the files that are being + scanned; instead output the number of lines that would other- + wise have been shown. If no lines are selected, the number + zero is output. If several files are are being scanned, a + count is output for each of them. However, if the --files- + with-matches option is also used, only those files whose + counts are greater than zero are listed. When -c is used, the + -A, -B, and -C options are ignored. + + --colour, --color + If this option is given without any data, it is equivalent to + "--colour=auto". If data is required, it must be given in + the same shell item, separated by an equals sign. + + --colour=value, --color=value + This option specifies under what circumstances the parts of a + line that matched a pattern should be coloured in the output. + By default, the output is not coloured. The value (which is + optional, see above) may be "never", "always", or "auto". In + the latter case, colouring happens only if the standard out- + put is connected to a terminal. More resources are used when + colouring is enabled, because pcregrep has to search for all + possible matches in a line, not just one, in order to colour + them all. + + The colour that is used can be specified by setting the envi- + ronment variable PCREGREP_COLOUR or PCREGREP_COLOR. The value + of this variable should be a string of two numbers, separated + by a semicolon. They are copied directly into the control + string for setting colour on a terminal, so it is your + responsibility to ensure that they make sense. If neither of + the environment variables is set, the default is "1;31", + which gives red. + + -D action, --devices=action + If an input path is not a regular file or a directory, + "action" specifies how it is to be processed. Valid values + are "read" (the default) or "skip" (silently skip the path). + + -d action, --directories=action + If an input path is a directory, "action" specifies how it is + to be processed. Valid values are "read" (the default in + non-Windows environments, for compatibility with GNU grep), + "recurse" (equivalent to the -r option), or "skip" (silently + skip the path, the default in Windows environments). In the + "read" case, directories are read as if they were ordinary + files. In some operating systems the effect of reading a + directory like this is an immediate end-of-file; in others it + may provoke an error. + + -e pattern, --regex=pattern, --regexp=pattern + Specify a pattern to be matched. This option can be used mul- + tiple times in order to specify several patterns. It can also + be used as a way of specifying a single pattern that starts + with a hyphen. When -e is used, no argument pattern is taken + from the command line; all arguments are treated as file + names. There is no limit to the number of patterns. They are + applied to each line in the order in which they are defined + until one matches. + + If -f is used with -e, the command line patterns are matched + first, followed by the patterns from the file(s), independent + of the order in which these options are specified. Note that + multiple use of -e is not the same as a single pattern with + alternatives. For example, X|Y finds the first character in a + line that is X or Y, whereas if the two patterns are given + separately, with X first, pcregrep finds X if it is present, + even if it follows Y in the line. It finds Y only if there is + no X in the line. This matters only if you are using -o or + --colo(u)r to show the part(s) of the line that matched. + + --exclude=pattern + Files (but not directories) whose names match the pattern are + skipped without being processed. This applies to all files, + whether listed on the command line, obtained from --file- + list, or by scanning a directory. The pattern is a PCRE regu- + lar expression, and is matched against the final component of + the file name, not the entire path. The -F, -w, and -x + options do not apply to this pattern. The option may be given + any number of times in order to specify multiple patterns. If + a file name matches both an --include and an --exclude pat- + tern, it is excluded. There is no short form for this option. + + --exclude-from=filename + Treat each non-empty line of the file as the data for an + --exclude option. What constitutes a newline when reading the + file is the operating system's default. The --newline option + has no effect on this option. This option may be given more + than once in order to specify a number of files to read. + + --exclude-dir=pattern + Directories whose names match the pattern are skipped without + being processed, whatever the setting of the --recursive + option. This applies to all directories, whether listed on + the command line, obtained from --file-list, or by scanning a + parent directory. The pattern is a PCRE regular expression, + and is matched against the final component of the directory + name, not the entire path. The -F, -w, and -x options do not + apply to this pattern. The option may be given any number of + times in order to specify more than one pattern. If a direc- + tory matches both --include-dir and --exclude-dir, it is + excluded. There is no short form for this option. + + -F, --fixed-strings + Interpret each data-matching pattern as a list of fixed + strings, separated by newlines, instead of as a regular + expression. What constitutes a newline for this purpose is + controlled by the --newline option. The -w (match as a word) + and -x (match whole line) options can be used with -F. They + apply to each of the fixed strings. A line is selected if any + of the fixed strings are found in it (subject to -w or -x, if + present). This option applies only to the patterns that are + matched against the contents of files; it does not apply to + patterns specified by any of the --include or --exclude + options. + + -f filename, --file=filename + Read patterns from the file, one per line, and match them + against each line of input. What constitutes a newline when + reading the file is the operating system's default. The + --newline option has no effect on this option. Trailing white + space is removed from each line, and blank lines are ignored. + An empty file contains no patterns and therefore matches + nothing. See also the comments about multiple patterns versus + a single pattern with alternatives in the description of -e + above. + + If this option is given more than once, all the specified + files are read. A data line is output if any of the patterns + match it. A filename can be given as "-" to refer to the + standard input. When -f is used, patterns specified on the + command line using -e may also be present; they are tested + before the file's patterns. However, no other pattern is + taken from the command line; all arguments are treated as the + names of paths to be searched. + + --file-list=filename + Read a list of files and/or directories that are to be + scanned from the given file, one per line. Trailing white + space is removed from each line, and blank lines are ignored. + These paths are processed before any that are listed on the + command line. The filename can be given as "-" to refer to + the standard input. If --file and --file-list are both spec- + ified as "-", patterns are read first. This is useful only + when the standard input is a terminal, from which further + lines (the list of files) can be read after an end-of-file + indication. If this option is given more than once, all the + specified files are read. + + --file-offsets + Instead of showing lines or parts of lines that match, show + each match as an offset from the start of the file and a + length, separated by a comma. In this mode, no context is + shown. That is, the -A, -B, and -C options are ignored. If + there is more than one match in a line, each of them is shown + separately. This option is mutually exclusive with --line- + offsets and --only-matching. + + -H, --with-filename + Force the inclusion of the filename at the start of output + lines when searching a single file. By default, the filename + is not shown in this case. For matching lines, the filename + is followed by a colon; for context lines, a hyphen separator + is used. If a line number is also being output, it follows + the file name. + + -h, --no-filename + Suppress the output filenames when searching multiple files. + By default, filenames are shown when multiple files are + searched. For matching lines, the filename is followed by a + colon; for context lines, a hyphen separator is used. If a + line number is also being output, it follows the file name. + + --help Output a help message, giving brief details of the command + options and file type support, and then exit. Anything else + on the command line is ignored. + + -I Treat binary files as never matching. This is equivalent to + --binary-files=without-match. + + -i, --ignore-case + Ignore upper/lower case distinctions during comparisons. + + --include=pattern + If any --include patterns are specified, the only files that + are processed are those that match one of the patterns (and + do not match an --exclude pattern). This option does not + affect directories, but it applies to all files, whether + listed on the command line, obtained from --file-list, or by + scanning a directory. The pattern is a PCRE regular expres- + sion, and is matched against the final component of the file + name, not the entire path. The -F, -w, and -x options do not + apply to this pattern. The option may be given any number of + times. If a file name matches both an --include and an + --exclude pattern, it is excluded. There is no short form + for this option. + + --include-from=filename + Treat each non-empty line of the file as the data for an + --include option. What constitutes a newline for this purpose + is the operating system's default. The --newline option has + no effect on this option. This option may be given any number + of times; all the files are read. + + --include-dir=pattern + If any --include-dir patterns are specified, the only direc- + tories that are processed are those that match one of the + patterns (and do not match an --exclude-dir pattern). This + applies to all directories, whether listed on the command + line, obtained from --file-list, or by scanning a parent + directory. The pattern is a PCRE regular expression, and is + matched against the final component of the directory name, + not the entire path. The -F, -w, and -x options do not apply + to this pattern. The option may be given any number of times. + If a directory matches both --include-dir and --exclude-dir, + it is excluded. There is no short form for this option. + + -L, --files-without-match + Instead of outputting lines from the files, just output the + names of the files that do not contain any lines that would + have been output. Each file name is output once, on a sepa- + rate line. + + -l, --files-with-matches + Instead of outputting lines from the files, just output the + names of the files containing lines that would have been out- + put. Each file name is output once, on a separate line. + Searching normally stops as soon as a matching line is found + in a file. However, if the -c (count) option is also used, + matching continues in order to obtain the correct count, and + those files that have at least one match are listed along + with their counts. Using this option with -c is a way of sup- + pressing the listing of files with no matches. + + --label=name + This option supplies a name to be used for the standard input + when file names are being output. If not supplied, "(standard + input)" is used. There is no short form for this option. + + --line-buffered + When this option is given, input is read and processed line + by line, and the output is flushed after each write. By + default, input is read in large chunks, unless pcregrep can + determine that it is reading from a terminal (which is cur- + rently possible only in Unix-like environments). Output to + terminal is normally automatically flushed by the operating + system. This option can be useful when the input or output is + attached to a pipe and you do not want pcregrep to buffer up + large amounts of data. However, its use will affect perfor- + mance, and the -M (multiline) option ceases to work. + + --line-offsets + Instead of showing lines or parts of lines that match, show + each match as a line number, the offset from the start of the + line, and a length. The line number is terminated by a colon + (as usual; see the -n option), and the offset and length are + separated by a comma. In this mode, no context is shown. + That is, the -A, -B, and -C options are ignored. If there is + more than one match in a line, each of them is shown sepa- + rately. This option is mutually exclusive with --file-offsets + and --only-matching. + + --locale=locale-name + This option specifies a locale to be used for pattern match- + ing. It overrides the value in the LC_ALL or LC_CTYPE envi- + ronment variables. If no locale is specified, the PCRE + library's default (usually the "C" locale) is used. There is + no short form for this option. + + --match-limit=number + Processing some regular expression patterns can require a + very large amount of memory, leading in some cases to a pro- + gram crash if not enough is available. Other patterns may + take a very long time to search for all possible matching + strings. The pcre_exec() function that is called by pcregrep + to do the matching has two parameters that can limit the + resources that it uses. + + The --match-limit option provides a means of limiting + resource usage when processing patterns that are not going to + match, but which have a very large number of possibilities in + their search trees. The classic example is a pattern that + uses nested unlimited repeats. Internally, PCRE uses a func- + tion called match() which it calls repeatedly (sometimes + recursively). The limit set by --match-limit is imposed on + the number of times this function is called during a match, + which has the effect of limiting the amount of backtracking + that can take place. + + The --recursion-limit option is similar to --match-limit, but + instead of limiting the total number of times that match() is + called, it limits the depth of recursive calls, which in turn + limits the amount of memory that can be used. The recursion + depth is a smaller number than the total number of calls, + because not all calls to match() are recursive. This limit is + of use only if it is set smaller than --match-limit. + + There are no short forms for these options. The default set- + tings are specified when the PCRE library is compiled, with + the default default being 10 million. + + -M, --multiline + Allow patterns to match more than one line. When this option + is given, patterns may usefully contain literal newline char- + acters and internal occurrences of ^ and $ characters. The + output for a successful match may consist of more than one + line, the last of which is the one in which the match ended. + If the matched string ends with a newline sequence the output + ends at the end of that line. + + When this option is set, the PCRE library is called in "mul- + tiline" mode. There is a limit to the number of lines that + can be matched, imposed by the way that pcregrep buffers the + input file as it scans it. However, pcregrep ensures that at + least 8K characters or the rest of the document (whichever is + the shorter) are available for forward matching, and simi- + larly the previous 8K characters (or all the previous charac- + ters, if fewer than 8K) are guaranteed to be available for + lookbehind assertions. This option does not work when input + is read line by line (see --line-buffered.) + + -N newline-type, --newline=newline-type + The PCRE library supports five different conventions for + indicating the ends of lines. They are the single-character + sequences CR (carriage return) and LF (linefeed), the two- + character sequence CRLF, an "anycrlf" convention, which rec- + ognizes any of the preceding three types, and an "any" con- + vention, in which any Unicode line ending sequence is assumed + to end a line. The Unicode sequences are the three just men- + tioned, plus VT (vertical tab, U+000B), FF (form feed, + U+000C), NEL (next line, U+0085), LS (line separator, + U+2028), and PS (paragraph separator, U+2029). + + When the PCRE library is built, a default line-ending + sequence is specified. This is normally the standard + sequence for the operating system. Unless otherwise specified + by this option, pcregrep uses the library's default. The + possible values for this option are CR, LF, CRLF, ANYCRLF, or + ANY. This makes it possible to use pcregrep to scan files + that have come from other environments without having to mod- + ify their line endings. If the data that is being scanned + does not agree with the convention set by this option, pcre- + grep may behave in strange ways. Note that this option does + not apply to files specified by the -f, --exclude-from, or + --include-from options, which are expected to use the operat- + ing system's standard newline sequence. + + -n, --line-number + Precede each output line by its line number in the file, fol- + lowed by a colon for matching lines or a hyphen for context + lines. If the filename is also being output, it precedes the + line number. This option is forced if --line-offsets is used. + + --no-jit If the PCRE library is built with support for just-in-time + compiling (which speeds up matching), pcregrep automatically + makes use of this, unless it was explicitly disabled at build + time. This option can be used to disable the use of JIT at + run time. It is provided for testing and working round prob- + lems. It should never be needed in normal use. + + -o, --only-matching + Show only the part of the line that matched a pattern instead + of the whole line. In this mode, no context is shown. That + is, the -A, -B, and -C options are ignored. If there is more + than one match in a line, each of them is shown separately. + If -o is combined with -v (invert the sense of the match to + find non-matching lines), no output is generated, but the + return code is set appropriately. If the matched portion of + the line is empty, nothing is output unless the file name or + line number are being printed, in which case they are shown + on an otherwise empty line. This option is mutually exclusive + with --file-offsets and --line-offsets. + + -onumber, --only-matching=number + Show only the part of the line that matched the capturing + parentheses of the given number. Up to 32 capturing parenthe- + ses are supported, and -o0 is equivalent to -o without a num- + ber. Because these options can be given without an argument + (see above), if an argument is present, it must be given in + the same shell item, for example, -o3 or --only-matching=2. + The comments given for the non-argument case above also apply + to this case. If the specified capturing parentheses do not + exist in the pattern, or were not set in the match, nothing + is output unless the file name or line number are being + printed. + + If this option is given multiple times, multiple substrings + are output, in the order the options are given. For example, + -o3 -o1 -o3 causes the substrings matched by capturing paren- + theses 3 and 1 and then 3 again to be output. By default, + there is no separator (but see the next option). + + --om-separator=text + Specify a separating string for multiple occurrences of -o. + The default is an empty string. Separating strings are never + coloured. + + -q, --quiet + Work quietly, that is, display nothing except error messages. + The exit status indicates whether or not any matches were + found. + + -r, --recursive + If any given path is a directory, recursively scan the files + it contains, taking note of any --include and --exclude set- + tings. By default, a directory is read as a normal file; in + some operating systems this gives an immediate end-of-file. + This option is a shorthand for setting the -d option to + "recurse". + + --recursion-limit=number + See --match-limit above. + + -s, --no-messages + Suppress error messages about non-existent or unreadable + files. Such files are quietly skipped. However, the return + code is still 2, even if matches were found in other files. + + -u, --utf-8 + Operate in UTF-8 mode. This option is available only if PCRE + has been compiled with UTF-8 support. All patterns (including + those for any --exclude and --include options) and all sub- + ject lines that are scanned must be valid strings of UTF-8 + characters. + + -V, --version + Write the version numbers of pcregrep and the PCRE library to + the standard output and then exit. Anything else on the com- + mand line is ignored. + + -v, --invert-match + Invert the sense of the match, so that lines which do not + match any of the patterns are the ones that are found. + + -w, --word-regex, --word-regexp + Force the patterns to match only whole words. This is equiva- + lent to having \b at the start and end of the pattern. This + option applies only to the patterns that are matched against + the contents of files; it does not apply to patterns speci- + fied by any of the --include or --exclude options. + + -x, --line-regex, --line-regexp + Force the patterns to be anchored (each must start matching + at the beginning of a line) and in addition, require them to + match entire lines. This is equivalent to having ^ and $ + characters at the start and end of each alternative branch in + every pattern. This option applies only to the patterns that + are matched against the contents of files; it does not apply + to patterns specified by any of the --include or --exclude + options. + + +ENVIRONMENT VARIABLES + + The environment variables LC_ALL and LC_CTYPE are examined, in that + order, for a locale. The first one that is set is used. This can be + overridden by the --locale option. If no locale is set, the PCRE + library's default (usually the "C" locale) is used. + + +NEWLINES + + The -N (--newline) option allows pcregrep to scan files with different + newline conventions from the default. Any parts of the input files that + are written to the standard output are copied identically, with what- + ever newline sequences they have in the input. However, the setting of + this option does not affect the interpretation of files specified by + the -f, --exclude-from, or --include-from options, which are assumed to + use the operating system's standard newline sequence, nor does it + affect the way in which pcregrep writes informational messages to the + standard error and output streams. For these it uses the string "\n" to + indicate newlines, relying on the C I/O library to convert this to an + appropriate sequence. + + +OPTIONS COMPATIBILITY + + Many of the short and long forms of pcregrep's options are the same as + in the GNU grep program. Any long option of the form --xxx-regexp (GNU + terminology) is also available as --xxx-regex (PCRE terminology). How- + ever, the --file-list, --file-offsets, --include-dir, --line-offsets, + --locale, --match-limit, -M, --multiline, -N, --newline, --om-separa- + tor, --recursion-limit, -u, and --utf-8 options are specific to pcre- + grep, as is the use of the --only-matching option with a capturing + parentheses number. + + Although most of the common options work the same way, a few are dif- + ferent in pcregrep. For example, the --include option's argument is a + glob for GNU grep, but a regular expression for pcregrep. If both the + -c and -l options are given, GNU grep lists only file names, without + counts, but pcregrep gives the counts. + + +OPTIONS WITH DATA + + There are four different ways in which an option with data can be spec- + ified. If a short form option is used, the data may follow immedi- + ately, or (with one exception) in the next command line item. For exam- + ple: + + -f/some/file + -f /some/file + + The exception is the -o option, which may appear with or without data. + Because of this, if data is present, it must follow immediately in the + same item, for example -o3. + + If a long form option is used, the data may appear in the same command + line item, separated by an equals character, or (with two exceptions) + it may appear in the next command line item. For example: + + --file=/some/file + --file /some/file + + Note, however, that if you want to supply a file name beginning with ~ + as data in a shell command, and have the shell expand ~ to a home + directory, you must separate the file name from the option, because the + shell does not treat ~ specially unless it is at the start of an item. + + The exceptions to the above are the --colour (or --color) and --only- + matching options, for which the data is optional. If one of these + options does have data, it must be given in the first form, using an + equals character. Otherwise pcregrep will assume that it has no data. + + +MATCHING ERRORS + + It is possible to supply a regular expression that takes a very long + time to fail to match certain lines. Such patterns normally involve + nested indefinite repeats, for example: (a+)*\d when matched against a + line of a's with no final digit. The PCRE matching function has a + resource limit that causes it to abort in these circumstances. If this + happens, pcregrep outputs an error message and the line that caused the + problem to the standard error stream. If there are more than 20 such + errors, pcregrep gives up. + + The --match-limit option of pcregrep can be used to set the overall + resource limit; there is a second option called --recursion-limit that + sets a limit on the amount of memory (usually stack) that is used (see + the discussion of these options above). + + +DIAGNOSTICS + + Exit status is 0 if any matches were found, 1 if no matches were found, + and 2 for syntax errors, overlong lines, non-existent or inaccessible + files (even if matches were found in other files) or too many matching + errors. Using the -s option to suppress error messages about inaccessi- + ble files does not affect the return code. + + +SEE ALSO + + pcrepattern(3), pcresyntax(3), pcretest(1). + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 03 April 2014 + Copyright (c) 1997-2014 University of Cambridge. diff --git a/plugins/Pcre16/docs/doc/pcrejit.3 b/plugins/Pcre16/docs/doc/pcrejit.3 new file mode 100644 index 0000000000..341403f7c8 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcrejit.3 @@ -0,0 +1,431 @@ +.TH PCREJIT 3 "17 March 2013" "PCRE 8.33" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH "PCRE JUST-IN-TIME COMPILER SUPPORT" +.rs +.sp +Just-in-time compiling is a heavyweight optimization that can greatly speed up +pattern matching. However, it comes at the cost of extra processing before the +match is performed. Therefore, it is of most benefit when the same pattern is +going to be matched many times. This does not necessarily mean many calls of a +matching function; if the pattern is not anchored, matching attempts may take +place many times at various positions in the subject, even for a single call. +Therefore, if the subject string is very long, it may still pay to use JIT for +one-off matches. +.P +JIT support applies only to the traditional Perl-compatible matching function. +It does not apply when the DFA matching function is being used. The code for +this support was written by Zoltan Herczeg. +. +. +.SH "8-BIT, 16-BIT AND 32-BIT SUPPORT" +.rs +.sp +JIT support is available for all of the 8-bit, 16-bit and 32-bit PCRE +libraries. To keep this documentation simple, only the 8-bit interface is +described in what follows. If you are using the 16-bit library, substitute the +16-bit functions and 16-bit structures (for example, \fIpcre16_jit_stack\fP +instead of \fIpcre_jit_stack\fP). If you are using the 32-bit library, +substitute the 32-bit functions and 32-bit structures (for example, +\fIpcre32_jit_stack\fP instead of \fIpcre_jit_stack\fP). +. +. +.SH "AVAILABILITY OF JIT SUPPORT" +.rs +.sp +JIT support is an optional feature of PCRE. The "configure" option --enable-jit +(or equivalent CMake option) must be set when PCRE is built if you want to use +JIT. The support is limited to the following hardware platforms: +.sp + ARM v5, v7, and Thumb2 + Intel x86 32-bit and 64-bit + MIPS 32-bit + Power PC 32-bit and 64-bit + SPARC 32-bit (experimental) +.sp +If --enable-jit is set on an unsupported platform, compilation fails. +.P +A program that is linked with PCRE 8.20 or later can tell if JIT support is +available by calling \fBpcre_config()\fP with the PCRE_CONFIG_JIT option. The +result is 1 when JIT is available, and 0 otherwise. However, a simple program +does not need to check this in order to use JIT. The normal API is implemented +in a way that falls back to the interpretive code if JIT is not available. For +programs that need the best possible performance, there is also a "fast path" +API that is JIT-specific. +.P +If your program may sometimes be linked with versions of PCRE that are older +than 8.20, but you want to use JIT when it is available, you can test +the values of PCRE_MAJOR and PCRE_MINOR, or the existence of a JIT macro such +as PCRE_CONFIG_JIT, for compile-time control of your code. +. +. +.SH "SIMPLE USE OF JIT" +.rs +.sp +You have to do two things to make use of the JIT support in the simplest way: +.sp + (1) Call \fBpcre_study()\fP with the PCRE_STUDY_JIT_COMPILE option for + each compiled pattern, and pass the resulting \fBpcre_extra\fP block to + \fBpcre_exec()\fP. +.sp + (2) Use \fBpcre_free_study()\fP to free the \fBpcre_extra\fP block when it is + no longer needed, instead of just freeing it yourself. This ensures that + any JIT data is also freed. +.sp +For a program that may be linked with pre-8.20 versions of PCRE, you can insert +.sp + #ifndef PCRE_STUDY_JIT_COMPILE + #define PCRE_STUDY_JIT_COMPILE 0 + #endif +.sp +so that no option is passed to \fBpcre_study()\fP, and then use something like +this to free the study data: +.sp + #ifdef PCRE_CONFIG_JIT + pcre_free_study(study_ptr); + #else + pcre_free(study_ptr); + #endif +.sp +PCRE_STUDY_JIT_COMPILE requests the JIT compiler to generate code for complete +matches. If you want to run partial matches using the PCRE_PARTIAL_HARD or +PCRE_PARTIAL_SOFT options of \fBpcre_exec()\fP, you should set one or both of +the following options in addition to, or instead of, PCRE_STUDY_JIT_COMPILE +when you call \fBpcre_study()\fP: +.sp + PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE + PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE +.sp +The JIT compiler generates different optimized code for each of the three +modes (normal, soft partial, hard partial). When \fBpcre_exec()\fP is called, +the appropriate code is run if it is available. Otherwise, the pattern is +matched using interpretive code. +.P +In some circumstances you may need to call additional functions. These are +described in the section entitled +.\" HTML <a href="#stackcontrol"> +.\" </a> +"Controlling the JIT stack" +.\" +below. +.P +If JIT support is not available, PCRE_STUDY_JIT_COMPILE etc. are ignored, and +no JIT data is created. Otherwise, the compiled pattern is passed to the JIT +compiler, which turns it into machine code that executes much faster than the +normal interpretive code. When \fBpcre_exec()\fP is passed a \fBpcre_extra\fP +block containing a pointer to JIT code of the appropriate mode (normal or +hard/soft partial), it obeys that code instead of running the interpreter. The +result is identical, but the compiled JIT code runs much faster. +.P +There are some \fBpcre_exec()\fP options that are not supported for JIT +execution. There are also some pattern items that JIT cannot handle. Details +are given below. In both cases, execution automatically falls back to the +interpretive code. If you want to know whether JIT was actually used for a +particular match, you should arrange for a JIT callback function to be set up +as described in the section entitled +.\" HTML <a href="#stackcontrol"> +.\" </a> +"Controlling the JIT stack" +.\" +below, even if you do not need to supply a non-default JIT stack. Such a +callback function is called whenever JIT code is about to be obeyed. If the +execution options are not right for JIT execution, the callback function is not +obeyed. +.P +If the JIT compiler finds an unsupported item, no JIT data is generated. You +can find out if JIT execution is available after studying a pattern by calling +\fBpcre_fullinfo()\fP with the PCRE_INFO_JIT option. A result of 1 means that +JIT compilation was successful. A result of 0 means that JIT support is not +available, or the pattern was not studied with PCRE_STUDY_JIT_COMPILE etc., or +the JIT compiler was not able to handle the pattern. +.P +Once a pattern has been studied, with or without JIT, it can be used as many +times as you like for matching different subject strings. +. +. +.SH "UNSUPPORTED OPTIONS AND PATTERN ITEMS" +.rs +.sp +The only \fBpcre_exec()\fP options that are supported for JIT execution are +PCRE_NO_UTF8_CHECK, PCRE_NO_UTF16_CHECK, PCRE_NO_UTF32_CHECK, PCRE_NOTBOL, +PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and +PCRE_PARTIAL_SOFT. +.P +The only unsupported pattern items are \eC (match a single data unit) when +running in a UTF mode, and a callout immediately before an assertion condition +in a conditional group. +. +. +.SH "RETURN VALUES FROM JIT EXECUTION" +.rs +.sp +When a pattern is matched using JIT execution, the return values are the same +as those given by the interpretive \fBpcre_exec()\fP code, with the addition of +one new error code: PCRE_ERROR_JIT_STACKLIMIT. This means that the memory used +for the JIT stack was insufficient. See +.\" HTML <a href="#stackcontrol"> +.\" </a> +"Controlling the JIT stack" +.\" +below for a discussion of JIT stack usage. For compatibility with the +interpretive \fBpcre_exec()\fP code, no more than two-thirds of the +\fIovector\fP argument is used for passing back captured substrings. +.P +The error code PCRE_ERROR_MATCHLIMIT is returned by the JIT code if searching a +very large pattern tree goes on for too long, as it is in the same circumstance +when JIT is not used, but the details of exactly what is counted are not the +same. The PCRE_ERROR_RECURSIONLIMIT error code is never returned by JIT +execution. +. +. +.SH "SAVING AND RESTORING COMPILED PATTERNS" +.rs +.sp +The code that is generated by the JIT compiler is architecture-specific, and is +also position dependent. For those reasons it cannot be saved (in a file or +database) and restored later like the bytecode and other data of a compiled +pattern. Saving and restoring compiled patterns is not something many people +do. More detail about this facility is given in the +.\" HREF +\fBpcreprecompile\fP +.\" +documentation. It should be possible to run \fBpcre_study()\fP on a saved and +restored pattern, and thereby recreate the JIT data, but because JIT +compilation uses significant resources, it is probably not worth doing this; +you might as well recompile the original pattern. +. +. +.\" HTML <a name="stackcontrol"></a> +.SH "CONTROLLING THE JIT STACK" +.rs +.sp +When the compiled JIT code runs, it needs a block of memory to use as a stack. +By default, it uses 32K on the machine stack. However, some large or +complicated patterns need more than this. The error PCRE_ERROR_JIT_STACKLIMIT +is given when there is not enough stack. Three functions are provided for +managing blocks of memory for use as JIT stacks. There is further discussion +about the use of JIT stacks in the section entitled +.\" HTML <a href="#stackcontrol"> +.\" </a> +"JIT stack FAQ" +.\" +below. +.P +The \fBpcre_jit_stack_alloc()\fP function creates a JIT stack. Its arguments +are a starting size and a maximum size, and it returns a pointer to an opaque +structure of type \fBpcre_jit_stack\fP, or NULL if there is an error. The +\fBpcre_jit_stack_free()\fP function can be used to free a stack that is no +longer needed. (For the technically minded: the address space is allocated by +mmap or VirtualAlloc.) +.P +JIT uses far less memory for recursion than the interpretive code, +and a maximum stack size of 512K to 1M should be more than enough for any +pattern. +.P +The \fBpcre_assign_jit_stack()\fP function specifies which stack JIT code +should use. Its arguments are as follows: +.sp + pcre_extra *extra + pcre_jit_callback callback + void *data +.sp +The \fIextra\fP argument must be the result of studying a pattern with +PCRE_STUDY_JIT_COMPILE etc. There are three cases for the values of the other +two options: +.sp + (1) If \fIcallback\fP is NULL and \fIdata\fP is NULL, an internal 32K block + on the machine stack is used. +.sp + (2) If \fIcallback\fP is NULL and \fIdata\fP is not NULL, \fIdata\fP must be + a valid JIT stack, the result of calling \fBpcre_jit_stack_alloc()\fP. +.sp + (3) If \fIcallback\fP is not NULL, it must point to a function that is + called with \fIdata\fP as an argument at the start of matching, in + order to set up a JIT stack. If the return from the callback + function is NULL, the internal 32K stack is used; otherwise the + return value must be a valid JIT stack, the result of calling + \fBpcre_jit_stack_alloc()\fP. +.sp +A callback function is obeyed whenever JIT code is about to be run; it is not +obeyed when \fBpcre_exec()\fP is called with options that are incompatible for +JIT execution. A callback function can therefore be used to determine whether a +match operation was executed by JIT or by the interpreter. +.P +You may safely use the same JIT stack for more than one pattern (either by +assigning directly or by callback), as long as the patterns are all matched +sequentially in the same thread. In a multithread application, if you do not +specify a JIT stack, or if you assign or pass back NULL from a callback, that +is thread-safe, because each thread has its own machine stack. However, if you +assign or pass back a non-NULL JIT stack, this must be a different stack for +each thread so that the application is thread-safe. +.P +Strictly speaking, even more is allowed. You can assign the same non-NULL stack +to any number of patterns as long as they are not used for matching by multiple +threads at the same time. For example, you can assign the same stack to all +compiled patterns, and use a global mutex in the callback to wait until the +stack is available for use. However, this is an inefficient solution, and not +recommended. +.P +This is a suggestion for how a multithreaded program that needs to set up +non-default JIT stacks might operate: +.sp + During thread initalization + thread_local_var = pcre_jit_stack_alloc(...) +.sp + During thread exit + pcre_jit_stack_free(thread_local_var) +.sp + Use a one-line callback function + return thread_local_var +.sp +All the functions described in this section do nothing if JIT is not available, +and \fBpcre_assign_jit_stack()\fP does nothing unless the \fBextra\fP argument +is non-NULL and points to a \fBpcre_extra\fP block that is the result of a +successful study with PCRE_STUDY_JIT_COMPILE etc. +. +. +.\" HTML <a name="stackfaq"></a> +.SH "JIT STACK FAQ" +.rs +.sp +(1) Why do we need JIT stacks? +.sp +PCRE (and JIT) is a recursive, depth-first engine, so it needs a stack where +the local data of the current node is pushed before checking its child nodes. +Allocating real machine stack on some platforms is difficult. For example, the +stack chain needs to be updated every time if we extend the stack on PowerPC. +Although it is possible, its updating time overhead decreases performance. So +we do the recursion in memory. +.P +(2) Why don't we simply allocate blocks of memory with \fBmalloc()\fP? +.sp +Modern operating systems have a nice feature: they can reserve an address space +instead of allocating memory. We can safely allocate memory pages inside this +address space, so the stack could grow without moving memory data (this is +important because of pointers). Thus we can allocate 1M address space, and use +only a single memory page (usually 4K) if that is enough. However, we can still +grow up to 1M anytime if needed. +.P +(3) Who "owns" a JIT stack? +.sp +The owner of the stack is the user program, not the JIT studied pattern or +anything else. The user program must ensure that if a stack is used by +\fBpcre_exec()\fP, (that is, it is assigned to the pattern currently running), +that stack must not be used by any other threads (to avoid overwriting the same +memory area). The best practice for multithreaded programs is to allocate a +stack for each thread, and return this stack through the JIT callback function. +.P +(4) When should a JIT stack be freed? +.sp +You can free a JIT stack at any time, as long as it will not be used by +\fBpcre_exec()\fP again. When you assign the stack to a pattern, only a pointer +is set. There is no reference counting or any other magic. You can free the +patterns and stacks in any order, anytime. Just \fIdo not\fP call +\fBpcre_exec()\fP with a pattern pointing to an already freed stack, as that +will cause SEGFAULT. (Also, do not free a stack currently used by +\fBpcre_exec()\fP in another thread). You can also replace the stack for a +pattern at any time. You can even free the previous stack before assigning a +replacement. +.P +(5) Should I allocate/free a stack every time before/after calling +\fBpcre_exec()\fP? +.sp +No, because this is too costly in terms of resources. However, you could +implement some clever idea which release the stack if it is not used in let's +say two minutes. The JIT callback can help to achieve this without keeping a +list of the currently JIT studied patterns. +.P +(6) OK, the stack is for long term memory allocation. But what happens if a +pattern causes stack overflow with a stack of 1M? Is that 1M kept until the +stack is freed? +.sp +Especially on embedded sytems, it might be a good idea to release memory +sometimes without freeing the stack. There is no API for this at the moment. +Probably a function call which returns with the currently allocated memory for +any stack and another which allows releasing memory (shrinking the stack) would +be a good idea if someone needs this. +.P +(7) This is too much of a headache. Isn't there any better solution for JIT +stack handling? +.sp +No, thanks to Windows. If POSIX threads were used everywhere, we could throw +out this complicated API. +. +. +.SH "EXAMPLE CODE" +.rs +.sp +This is a single-threaded example that specifies a JIT stack without using a +callback. +.sp + int rc; + int ovector[30]; + pcre *re; + pcre_extra *extra; + pcre_jit_stack *jit_stack; +.sp + re = pcre_compile(pattern, 0, &error, &erroffset, NULL); + /* Check for errors */ + extra = pcre_study(re, PCRE_STUDY_JIT_COMPILE, &error); + jit_stack = pcre_jit_stack_alloc(32*1024, 512*1024); + /* Check for error (NULL) */ + pcre_assign_jit_stack(extra, NULL, jit_stack); + rc = pcre_exec(re, extra, subject, length, 0, 0, ovector, 30); + /* Check results */ + pcre_free(re); + pcre_free_study(extra); + pcre_jit_stack_free(jit_stack); +.sp +. +. +.SH "JIT FAST PATH API" +.rs +.sp +Because the API described above falls back to interpreted execution when JIT is +not available, it is convenient for programs that are written for general use +in many environments. However, calling JIT via \fBpcre_exec()\fP does have a +performance impact. Programs that are written for use where JIT is known to be +available, and which need the best possible performance, can instead use a +"fast path" API to call JIT execution directly instead of calling +\fBpcre_exec()\fP (obviously only for patterns that have been successfully +studied by JIT). +.P +The fast path function is called \fBpcre_jit_exec()\fP, and it takes exactly +the same arguments as \fBpcre_exec()\fP, plus one additional argument that +must point to a JIT stack. The JIT stack arrangements described above do not +apply. The return values are the same as for \fBpcre_exec()\fP. +.P +When you call \fBpcre_exec()\fP, as well as testing for invalid options, a +number of other sanity checks are performed on the arguments. For example, if +the subject pointer is NULL, or its length is negative, an immediate error is +given. Also, unless PCRE_NO_UTF[8|16|32] is set, a UTF subject string is tested +for validity. In the interests of speed, these checks do not happen on the JIT +fast path, and if invalid data is passed, the result is undefined. +.P +Bypassing the sanity checks and the \fBpcre_exec()\fP wrapping can give +speedups of more than 10%. +. +. +.SH "SEE ALSO" +.rs +.sp +\fBpcreapi\fP(3) +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel (FAQ by Zoltan Herczeg) +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 17 March 2013 +Copyright (c) 1997-2013 University of Cambridge. +.fi diff --git a/plugins/Pcre16/docs/doc/pcrelimits.3 b/plugins/Pcre16/docs/doc/pcrelimits.3 new file mode 100644 index 0000000000..423d6a2768 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcrelimits.3 @@ -0,0 +1,71 @@ +.TH PCRELIMITS 3 "05 November 2013" "PCRE 8.34" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH "SIZE AND OTHER LIMITATIONS" +.rs +.sp +There are some size limitations in PCRE but it is hoped that they will never in +practice be relevant. +.P +The maximum length of a compiled pattern is approximately 64K data units (bytes +for the 8-bit library, 16-bit units for the 16-bit library, and 32-bit units for +the 32-bit library) if PCRE is compiled with the default internal linkage size, +which is 2 bytes for the 8-bit and 16-bit libraries, and 4 bytes for the 32-bit +library. If you want to process regular expressions that are truly enormous, +you can compile PCRE with an internal linkage size of 3 or 4 (when building the +16-bit or 32-bit library, 3 is rounded up to 4). See the \fBREADME\fP file in +the source distribution and the +.\" HREF +\fBpcrebuild\fP +.\" +documentation for details. In these cases the limit is substantially larger. +However, the speed of execution is slower. +.P +All values in repeating quantifiers must be less than 65536. +.P +There is no limit to the number of parenthesized subpatterns, but there can be +no more than 65535 capturing subpatterns. There is, however, a limit to the +depth of nesting of parenthesized subpatterns of all kinds. This is imposed in +order to limit the amount of system stack used at compile time. The limit can +be specified when PCRE is built; the default is 250. +.P +There is a limit to the number of forward references to subsequent subpatterns +of around 200,000. Repeated forward references with fixed upper limits, for +example, (?2){0,100} when subpattern number 2 is to the right, are included in +the count. There is no limit to the number of backward references. +.P +The maximum length of name for a named subpattern is 32 characters, and the +maximum number of named subpatterns is 10000. +.P +The maximum length of a name in a (*MARK), (*PRUNE), (*SKIP), or (*THEN) verb +is 255 for the 8-bit library and 65535 for the 16-bit and 32-bit libraries. +.P +The maximum length of a subject string is the largest positive number that an +integer variable can hold. However, when using the traditional matching +function, PCRE uses recursion to handle subpatterns and indefinite repetition. +This means that the available stack space may limit the size of a subject +string that can be processed by certain patterns. For a discussion of stack +issues, see the +.\" HREF +\fBpcrestack\fP +.\" +documentation. +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 05 November 2013 +Copyright (c) 1997-2013 University of Cambridge. +.fi diff --git a/plugins/Pcre16/docs/doc/pcrematching.3 b/plugins/Pcre16/docs/doc/pcrematching.3 new file mode 100644 index 0000000000..268baf9b8c --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcrematching.3 @@ -0,0 +1,214 @@ +.TH PCREMATCHING 3 "12 November 2013" "PCRE 8.34" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH "PCRE MATCHING ALGORITHMS" +.rs +.sp +This document describes the two different algorithms that are available in PCRE +for matching a compiled regular expression against a given subject string. The +"standard" algorithm is the one provided by the \fBpcre_exec()\fP, +\fBpcre16_exec()\fP and \fBpcre32_exec()\fP functions. These work in the same +as as Perl's matching function, and provide a Perl-compatible matching operation. +The just-in-time (JIT) optimization that is described in the +.\" HREF +\fBpcrejit\fP +.\" +documentation is compatible with these functions. +.P +An alternative algorithm is provided by the \fBpcre_dfa_exec()\fP, +\fBpcre16_dfa_exec()\fP and \fBpcre32_dfa_exec()\fP functions; they operate in +a different way, and are not Perl-compatible. This alternative has advantages +and disadvantages compared with the standard algorithm, and these are described +below. +.P +When there is only one possible way in which a given subject string can match a +pattern, the two algorithms give the same answer. A difference arises, however, +when there are multiple possibilities. For example, if the pattern +.sp + ^<.*> +.sp +is matched against the string +.sp + <something> <something else> <something further> +.sp +there are three possible answers. The standard algorithm finds only one of +them, whereas the alternative algorithm finds all three. +. +. +.SH "REGULAR EXPRESSIONS AS TREES" +.rs +.sp +The set of strings that are matched by a regular expression can be represented +as a tree structure. An unlimited repetition in the pattern makes the tree of +infinite size, but it is still a tree. Matching the pattern to a given subject +string (from a given starting point) can be thought of as a search of the tree. +There are two ways to search a tree: depth-first and breadth-first, and these +correspond to the two matching algorithms provided by PCRE. +. +. +.SH "THE STANDARD MATCHING ALGORITHM" +.rs +.sp +In the terminology of Jeffrey Friedl's book "Mastering Regular +Expressions", the standard algorithm is an "NFA algorithm". It conducts a +depth-first search of the pattern tree. That is, it proceeds along a single +path through the tree, checking that the subject matches what is required. When +there is a mismatch, the algorithm tries any alternatives at the current point, +and if they all fail, it backs up to the previous branch point in the tree, and +tries the next alternative branch at that level. This often involves backing up +(moving to the left) in the subject string as well. The order in which +repetition branches are tried is controlled by the greedy or ungreedy nature of +the quantifier. +.P +If a leaf node is reached, a matching string has been found, and at that point +the algorithm stops. Thus, if there is more than one possible match, this +algorithm returns the first one that it finds. Whether this is the shortest, +the longest, or some intermediate length depends on the way the greedy and +ungreedy repetition quantifiers are specified in the pattern. +.P +Because it ends up with a single path through the tree, it is relatively +straightforward for this algorithm to keep track of the substrings that are +matched by portions of the pattern in parentheses. This provides support for +capturing parentheses and back references. +. +. +.SH "THE ALTERNATIVE MATCHING ALGORITHM" +.rs +.sp +This algorithm conducts a breadth-first search of the tree. Starting from the +first matching point in the subject, it scans the subject string from left to +right, once, character by character, and as it does this, it remembers all the +paths through the tree that represent valid matches. In Friedl's terminology, +this is a kind of "DFA algorithm", though it is not implemented as a +traditional finite state machine (it keeps multiple states active +simultaneously). +.P +Although the general principle of this matching algorithm is that it scans the +subject string only once, without backtracking, there is one exception: when a +lookaround assertion is encountered, the characters following or preceding the +current point have to be independently inspected. +.P +The scan continues until either the end of the subject is reached, or there are +no more unterminated paths. At this point, terminated paths represent the +different matching possibilities (if there are none, the match has failed). +Thus, if there is more than one possible match, this algorithm finds all of +them, and in particular, it finds the longest. The matches are returned in +decreasing order of length. There is an option to stop the algorithm after the +first match (which is necessarily the shortest) is found. +.P +Note that all the matches that are found start at the same point in the +subject. If the pattern +.sp + cat(er(pillar)?)? +.sp +is matched against the string "the caterpillar catchment", the result will be +the three strings "caterpillar", "cater", and "cat" that start at the fifth +character of the subject. The algorithm does not automatically move on to find +matches that start at later positions. +.P +PCRE's "auto-possessification" optimization usually applies to character +repeats at the end of a pattern (as well as internally). For example, the +pattern "a\ed+" is compiled as if it were "a\ed++" because there is no point +even considering the possibility of backtracking into the repeated digits. For +DFA matching, this means that only one possible match is found. If you really +do want multiple matches in such cases, either use an ungreedy repeat +("a\ed+?") or set the PCRE_NO_AUTO_POSSESS option when compiling. +.P +There are a number of features of PCRE regular expressions that are not +supported by the alternative matching algorithm. They are as follows: +.P +1. Because the algorithm finds all possible matches, the greedy or ungreedy +nature of repetition quantifiers is not relevant. Greedy and ungreedy +quantifiers are treated in exactly the same way. However, possessive +quantifiers can make a difference when what follows could also match what is +quantified, for example in a pattern like this: +.sp + ^a++\ew! +.sp +This pattern matches "aaab!" but not "aaa!", which would be matched by a +non-possessive quantifier. Similarly, if an atomic group is present, it is +matched as if it were a standalone pattern at the current point, and the +longest match is then "locked in" for the rest of the overall pattern. +.P +2. When dealing with multiple paths through the tree simultaneously, it is not +straightforward to keep track of captured substrings for the different matching +possibilities, and PCRE's implementation of this algorithm does not attempt to +do this. This means that no captured substrings are available. +.P +3. Because no substrings are captured, back references within the pattern are +not supported, and cause errors if encountered. +.P +4. For the same reason, conditional expressions that use a backreference as the +condition or test for a specific group recursion are not supported. +.P +5. Because many paths through the tree may be active, the \eK escape sequence, +which resets the start of the match when encountered (but may be on some paths +and not on others), is not supported. It causes an error if encountered. +.P +6. Callouts are supported, but the value of the \fIcapture_top\fP field is +always 1, and the value of the \fIcapture_last\fP field is always -1. +.P +7. The \eC escape sequence, which (in the standard algorithm) always matches a +single data unit, even in UTF-8, UTF-16 or UTF-32 modes, is not supported in +these modes, because the alternative algorithm moves through the subject string +one character (not data unit) at a time, for all active paths through the tree. +.P +8. Except for (*FAIL), the backtracking control verbs such as (*PRUNE) are not +supported. (*FAIL) is supported, and behaves like a failing negative assertion. +. +. +.SH "ADVANTAGES OF THE ALTERNATIVE ALGORITHM" +.rs +.sp +Using the alternative matching algorithm provides the following advantages: +.P +1. All possible matches (at a single point in the subject) are automatically +found, and in particular, the longest match is found. To find more than one +match using the standard algorithm, you have to do kludgy things with +callouts. +.P +2. Because the alternative algorithm scans the subject string just once, and +never needs to backtrack (except for lookbehinds), it is possible to pass very +long subject strings to the matching function in several pieces, checking for +partial matching each time. Although it is possible to do multi-segment +matching using the standard algorithm by retaining partially matched +substrings, it is more complicated. The +.\" HREF +\fBpcrepartial\fP +.\" +documentation gives details of partial matching and discusses multi-segment +matching. +. +. +.SH "DISADVANTAGES OF THE ALTERNATIVE ALGORITHM" +.rs +.sp +The alternative algorithm suffers from a number of disadvantages: +.P +1. It is substantially slower than the standard algorithm. This is partly +because it has to search for all possible matches, but is also because it is +less susceptible to optimization. +.P +2. Capturing parentheses and back references are not supported. +.P +3. Although atomic groups are supported, their use does not provide the +performance advantage that it does for the standard algorithm. +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 12 November 2013 +Copyright (c) 1997-2012 University of Cambridge. +.fi diff --git a/plugins/Pcre16/docs/doc/pcrepartial.3 b/plugins/Pcre16/docs/doc/pcrepartial.3 new file mode 100644 index 0000000000..14d0124f1c --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcrepartial.3 @@ -0,0 +1,476 @@ +.TH PCREPARTIAL 3 "02 July 2013" "PCRE 8.34" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH "PARTIAL MATCHING IN PCRE" +.rs +.sp +In normal use of PCRE, if the subject string that is passed to a matching +function matches as far as it goes, but is too short to match the entire +pattern, PCRE_ERROR_NOMATCH is returned. There are circumstances where it might +be helpful to distinguish this case from other cases in which there is no +match. +.P +Consider, for example, an application where a human is required to type in data +for a field with specific formatting requirements. An example might be a date +in the form \fIddmmmyy\fP, defined by this pattern: +.sp + ^\ed?\ed(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\ed\ed$ +.sp +If the application sees the user's keystrokes one by one, and can check that +what has been typed so far is potentially valid, it is able to raise an error +as soon as a mistake is made, by beeping and not reflecting the character that +has been typed, for example. This immediate feedback is likely to be a better +user interface than a check that is delayed until the entire string has been +entered. Partial matching can also be useful when the subject string is very +long and is not all available at once. +.P +PCRE supports partial matching by means of the PCRE_PARTIAL_SOFT and +PCRE_PARTIAL_HARD options, which can be set when calling any of the matching +functions. For backwards compatibility, PCRE_PARTIAL is a synonym for +PCRE_PARTIAL_SOFT. The essential difference between the two options is whether +or not a partial match is preferred to an alternative complete match, though +the details differ between the two types of matching function. If both options +are set, PCRE_PARTIAL_HARD takes precedence. +.P +If you want to use partial matching with just-in-time optimized code, you must +call \fBpcre_study()\fP, \fBpcre16_study()\fP or \fBpcre32_study()\fP with one +or both of these options: +.sp + PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE + PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE +.sp +PCRE_STUDY_JIT_COMPILE should also be set if you are going to run non-partial +matches on the same pattern. If the appropriate JIT study mode has not been set +for a match, the interpretive matching code is used. +.P +Setting a partial matching option disables two of PCRE's standard +optimizations. PCRE remembers the last literal data unit in a pattern, and +abandons matching immediately if it is not present in the subject string. This +optimization cannot be used for a subject string that might match only +partially. If the pattern was studied, PCRE knows the minimum length of a +matching string, and does not bother to run the matching function on shorter +strings. This optimization is also disabled for partial matching. +. +. +.SH "PARTIAL MATCHING USING pcre_exec() OR pcre[16|32]_exec()" +.rs +.sp +A partial match occurs during a call to \fBpcre_exec()\fP or +\fBpcre[16|32]_exec()\fP when the end of the subject string is reached +successfully, but matching cannot continue because more characters are needed. +However, at least one character in the subject must have been inspected. This +character need not form part of the final matched string; lookbehind assertions +and the \eK escape sequence provide ways of inspecting characters before the +start of a matched substring. The requirement for inspecting at least one +character exists because an empty string can always be matched; without such a +restriction there would always be a partial match of an empty string at the end +of the subject. +.P +If there are at least two slots in the offsets vector when a partial match is +returned, the first slot is set to the offset of the earliest character that +was inspected. For convenience, the second offset points to the end of the +subject so that a substring can easily be identified. If there are at least +three slots in the offsets vector, the third slot is set to the offset of the +character where matching started. +.P +For the majority of patterns, the contents of the first and third slots will be +the same. However, for patterns that contain lookbehind assertions, or begin +with \eb or \eB, characters before the one where matching started may have been +inspected while carrying out the match. For example, consider this pattern: +.sp + /(?<=abc)123/ +.sp +This pattern matches "123", but only if it is preceded by "abc". If the subject +string is "xyzabc12", the first two offsets after a partial match are for the +substring "abc12", because all these characters were inspected. However, the +third offset is set to 6, because that is the offset where matching began. +.P +What happens when a partial match is identified depends on which of the two +partial matching options are set. +. +. +.SS "PCRE_PARTIAL_SOFT WITH pcre_exec() OR pcre[16|32]_exec()" +.rs +.sp +If PCRE_PARTIAL_SOFT is set when \fBpcre_exec()\fP or \fBpcre[16|32]_exec()\fP +identifies a partial match, the partial match is remembered, but matching +continues as normal, and other alternatives in the pattern are tried. If no +complete match can be found, PCRE_ERROR_PARTIAL is returned instead of +PCRE_ERROR_NOMATCH. +.P +This option is "soft" because it prefers a complete match over a partial match. +All the various matching items in a pattern behave as if the subject string is +potentially complete. For example, \ez, \eZ, and $ match at the end of the +subject, as normal, and for \eb and \eB the end of the subject is treated as a +non-alphanumeric. +.P +If there is more than one partial match, the first one that was found provides +the data that is returned. Consider this pattern: +.sp + /123\ew+X|dogY/ +.sp +If this is matched against the subject string "abc123dog", both +alternatives fail to match, but the end of the subject is reached during +matching, so PCRE_ERROR_PARTIAL is returned. The offsets are set to 3 and 9, +identifying "123dog" as the first partial match that was found. (In this +example, there are two partial matches, because "dog" on its own partially +matches the second alternative.) +. +. +.SS "PCRE_PARTIAL_HARD WITH pcre_exec() OR pcre[16|32]_exec()" +.rs +.sp +If PCRE_PARTIAL_HARD is set for \fBpcre_exec()\fP or \fBpcre[16|32]_exec()\fP, +PCRE_ERROR_PARTIAL is returned as soon as a partial match is found, without +continuing to search for possible complete matches. This option is "hard" +because it prefers an earlier partial match over a later complete match. For +this reason, the assumption is made that the end of the supplied subject string +may not be the true end of the available data, and so, if \ez, \eZ, \eb, \eB, +or $ are encountered at the end of the subject, the result is +PCRE_ERROR_PARTIAL, provided that at least one character in the subject has +been inspected. +.P +Setting PCRE_PARTIAL_HARD also affects the way UTF-8 and UTF-16 +subject strings are checked for validity. Normally, an invalid sequence +causes the error PCRE_ERROR_BADUTF8 or PCRE_ERROR_BADUTF16. However, in the +special case of a truncated character at the end of the subject, +PCRE_ERROR_SHORTUTF8 or PCRE_ERROR_SHORTUTF16 is returned when +PCRE_PARTIAL_HARD is set. +. +. +.SS "Comparing hard and soft partial matching" +.rs +.sp +The difference between the two partial matching options can be illustrated by a +pattern such as: +.sp + /dog(sbody)?/ +.sp +This matches either "dog" or "dogsbody", greedily (that is, it prefers the +longer string if possible). If it is matched against the string "dog" with +PCRE_PARTIAL_SOFT, it yields a complete match for "dog". However, if +PCRE_PARTIAL_HARD is set, the result is PCRE_ERROR_PARTIAL. On the other hand, +if the pattern is made ungreedy the result is different: +.sp + /dog(sbody)??/ +.sp +In this case the result is always a complete match because that is found first, +and matching never continues after finding a complete match. It might be easier +to follow this explanation by thinking of the two patterns like this: +.sp + /dog(sbody)?/ is the same as /dogsbody|dog/ + /dog(sbody)??/ is the same as /dog|dogsbody/ +.sp +The second pattern will never match "dogsbody", because it will always find the +shorter match first. +. +. +.SH "PARTIAL MATCHING USING pcre_dfa_exec() OR pcre[16|32]_dfa_exec()" +.rs +.sp +The DFA functions move along the subject string character by character, without +backtracking, searching for all possible matches simultaneously. If the end of +the subject is reached before the end of the pattern, there is the possibility +of a partial match, again provided that at least one character has been +inspected. +.P +When PCRE_PARTIAL_SOFT is set, PCRE_ERROR_PARTIAL is returned only if there +have been no complete matches. Otherwise, the complete matches are returned. +However, if PCRE_PARTIAL_HARD is set, a partial match takes precedence over any +complete matches. The portion of the string that was inspected when the longest +partial match was found is set as the first matching string, provided there are +at least two slots in the offsets vector. +.P +Because the DFA functions always search for all possible matches, and there is +no difference between greedy and ungreedy repetition, their behaviour is +different from the standard functions when PCRE_PARTIAL_HARD is set. Consider +the string "dog" matched against the ungreedy pattern shown above: +.sp + /dog(sbody)??/ +.sp +Whereas the standard functions stop as soon as they find the complete match for +"dog", the DFA functions also find the partial match for "dogsbody", and so +return that when PCRE_PARTIAL_HARD is set. +. +. +.SH "PARTIAL MATCHING AND WORD BOUNDARIES" +.rs +.sp +If a pattern ends with one of sequences \eb or \eB, which test for word +boundaries, partial matching with PCRE_PARTIAL_SOFT can give counter-intuitive +results. Consider this pattern: +.sp + /\ebcat\eb/ +.sp +This matches "cat", provided there is a word boundary at either end. If the +subject string is "the cat", the comparison of the final "t" with a following +character cannot take place, so a partial match is found. However, normal +matching carries on, and \eb matches at the end of the subject when the last +character is a letter, so a complete match is found. The result, therefore, is +\fInot\fP PCRE_ERROR_PARTIAL. Using PCRE_PARTIAL_HARD in this case does yield +PCRE_ERROR_PARTIAL, because then the partial match takes precedence. +. +. +.SH "FORMERLY RESTRICTED PATTERNS" +.rs +.sp +For releases of PCRE prior to 8.00, because of the way certain internal +optimizations were implemented in the \fBpcre_exec()\fP function, the +PCRE_PARTIAL option (predecessor of PCRE_PARTIAL_SOFT) could not be used with +all patterns. From release 8.00 onwards, the restrictions no longer apply, and +partial matching with can be requested for any pattern. +.P +Items that were formerly restricted were repeated single characters and +repeated metasequences. If PCRE_PARTIAL was set for a pattern that did not +conform to the restrictions, \fBpcre_exec()\fP returned the error code +PCRE_ERROR_BADPARTIAL (-13). This error code is no longer in use. The +PCRE_INFO_OKPARTIAL call to \fBpcre_fullinfo()\fP to find out if a compiled +pattern can be used for partial matching now always returns 1. +. +. +.SH "EXAMPLE OF PARTIAL MATCHING USING PCRETEST" +.rs +.sp +If the escape sequence \eP is present in a \fBpcretest\fP data line, the +PCRE_PARTIAL_SOFT option is used for the match. Here is a run of \fBpcretest\fP +that uses the date example quoted above: +.sp + re> /^\ed?\ed(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\ed\ed$/ + data> 25jun04\eP + 0: 25jun04 + 1: jun + data> 25dec3\eP + Partial match: 23dec3 + data> 3ju\eP + Partial match: 3ju + data> 3juj\eP + No match + data> j\eP + No match +.sp +The first data string is matched completely, so \fBpcretest\fP shows the +matched substrings. The remaining four strings do not match the complete +pattern, but the first two are partial matches. Similar output is obtained +if DFA matching is used. +.P +If the escape sequence \eP is present more than once in a \fBpcretest\fP data +line, the PCRE_PARTIAL_HARD option is set for the match. +. +. +.SH "MULTI-SEGMENT MATCHING WITH pcre_dfa_exec() OR pcre[16|32]_dfa_exec()" +.rs +.sp +When a partial match has been found using a DFA matching function, it is +possible to continue the match by providing additional subject data and calling +the function again with the same compiled regular expression, this time setting +the PCRE_DFA_RESTART option. You must pass the same working space as before, +because this is where details of the previous partial match are stored. Here is +an example using \fBpcretest\fP, using the \eR escape sequence to set the +PCRE_DFA_RESTART option (\eD specifies the use of the DFA matching function): +.sp + re> /^\ed?\ed(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\ed\ed$/ + data> 23ja\eP\eD + Partial match: 23ja + data> n05\eR\eD + 0: n05 +.sp +The first call has "23ja" as the subject, and requests partial matching; the +second call has "n05" as the subject for the continued (restarted) match. +Notice that when the match is complete, only the last part is shown; PCRE does +not retain the previously partially-matched string. It is up to the calling +program to do that if it needs to. +.P +That means that, for an unanchored pattern, if a continued match fails, it is +not possible to try again at a new starting point. All this facility is capable +of doing is continuing with the previous match attempt. In the previous +example, if the second set of data is "ug23" the result is no match, even +though there would be a match for "aug23" if the entire string were given at +once. Depending on the application, this may or may not be what you want. +The only way to allow for starting again at the next character is to retain the +matched part of the subject and try a new complete match. +.P +You can set the PCRE_PARTIAL_SOFT or PCRE_PARTIAL_HARD options with +PCRE_DFA_RESTART to continue partial matching over multiple segments. This +facility can be used to pass very long subject strings to the DFA matching +functions. +. +. +.SH "MULTI-SEGMENT MATCHING WITH pcre_exec() OR pcre[16|32]_exec()" +.rs +.sp +From release 8.00, the standard matching functions can also be used to do +multi-segment matching. Unlike the DFA functions, it is not possible to +restart the previous match with a new segment of data. Instead, new data must +be added to the previous subject string, and the entire match re-run, starting +from the point where the partial match occurred. Earlier data can be discarded. +.P +It is best to use PCRE_PARTIAL_HARD in this situation, because it does not +treat the end of a segment as the end of the subject when matching \ez, \eZ, +\eb, \eB, and $. Consider an unanchored pattern that matches dates: +.sp + re> /\ed?\ed(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\ed\ed/ + data> The date is 23ja\eP\eP + Partial match: 23ja +.sp +At this stage, an application could discard the text preceding "23ja", add on +text from the next segment, and call the matching function again. Unlike the +DFA matching functions, the entire matching string must always be available, +and the complete matching process occurs for each call, so more memory and more +processing time is needed. +.P +\fBNote:\fP If the pattern contains lookbehind assertions, or \eK, or starts +with \eb or \eB, the string that is returned for a partial match includes +characters that precede the start of what would be returned for a complete +match, because it contains all the characters that were inspected during the +partial match. +. +. +.SH "ISSUES WITH MULTI-SEGMENT MATCHING" +.rs +.sp +Certain types of pattern may give problems with multi-segment matching, +whichever matching function is used. +.P +1. If the pattern contains a test for the beginning of a line, you need to pass +the PCRE_NOTBOL option when the subject string for any call does start at the +beginning of a line. There is also a PCRE_NOTEOL option, but in practice when +doing multi-segment matching you should be using PCRE_PARTIAL_HARD, which +includes the effect of PCRE_NOTEOL. +.P +2. Lookbehind assertions that have already been obeyed are catered for in the +offsets that are returned for a partial match. However a lookbehind assertion +later in the pattern could require even earlier characters to be inspected. You +can handle this case by using the PCRE_INFO_MAXLOOKBEHIND option of the +\fBpcre_fullinfo()\fP or \fBpcre[16|32]_fullinfo()\fP functions to obtain the +length of the longest lookbehind in the pattern. This length is given in +characters, not bytes. If you always retain at least that many characters +before the partially matched string, all should be well. (Of course, near the +start of the subject, fewer characters may be present; in that case all +characters should be retained.) +.P +From release 8.33, there is a more accurate way of deciding which characters to +retain. Instead of subtracting the length of the longest lookbehind from the +earliest inspected character (\fIoffsets[0]\fP), the match start position +(\fIoffsets[2]\fP) should be used, and the next match attempt started at the +\fIoffsets[2]\fP character by setting the \fIstartoffset\fP argument of +\fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP. +.P +For example, if the pattern "(?<=123)abc" is partially +matched against the string "xx123a", the three offset values returned are 2, 6, +and 5. This indicates that the matching process that gave a partial match +started at offset 5, but the characters "123a" were all inspected. The maximum +lookbehind for that pattern is 3, so taking that away from 5 shows that we need +only keep "123a", and the next match attempt can be started at offset 3 (that +is, at "a") when further characters have been added. When the match start is +not the earliest inspected character, \fBpcretest\fP shows it explicitly: +.sp + re> "(?<=123)abc" + data> xx123a\eP\eP + Partial match at offset 5: 123a +.P +3. Because a partial match must always contain at least one character, what +might be considered a partial match of an empty string actually gives a "no +match" result. For example: +.sp + re> /c(?<=abc)x/ + data> ab\eP + No match +.sp +If the next segment begins "cx", a match should be found, but this will only +happen if characters from the previous segment are retained. For this reason, a +"no match" result should be interpreted as "partial match of an empty string" +when the pattern contains lookbehinds. +.P +4. Matching a subject string that is split into multiple segments may not +always produce exactly the same result as matching over one single long string, +especially when PCRE_PARTIAL_SOFT is used. The section "Partial Matching and +Word Boundaries" above describes an issue that arises if the pattern ends with +\eb or \eB. Another kind of difference may occur when there are multiple +matching possibilities, because (for PCRE_PARTIAL_SOFT) a partial match result +is given only when there are no completed matches. This means that as soon as +the shortest match has been found, continuation to a new subject segment is no +longer possible. Consider again this \fBpcretest\fP example: +.sp + re> /dog(sbody)?/ + data> dogsb\eP + 0: dog + data> do\eP\eD + Partial match: do + data> gsb\eR\eP\eD + 0: g + data> dogsbody\eD + 0: dogsbody + 1: dog +.sp +The first data line passes the string "dogsb" to a standard matching function, +setting the PCRE_PARTIAL_SOFT option. Although the string is a partial match +for "dogsbody", the result is not PCRE_ERROR_PARTIAL, because the shorter +string "dog" is a complete match. Similarly, when the subject is presented to +a DFA matching function in several parts ("do" and "gsb" being the first two) +the match stops when "dog" has been found, and it is not possible to continue. +On the other hand, if "dogsbody" is presented as a single string, a DFA +matching function finds both matches. +.P +Because of these problems, it is best to use PCRE_PARTIAL_HARD when matching +multi-segment data. The example above then behaves differently: +.sp + re> /dog(sbody)?/ + data> dogsb\eP\eP + Partial match: dogsb + data> do\eP\eD + Partial match: do + data> gsb\eR\eP\eP\eD + Partial match: gsb +.sp +5. Patterns that contain alternatives at the top level which do not all start +with the same pattern item may not work as expected when PCRE_DFA_RESTART is +used. For example, consider this pattern: +.sp + 1234|3789 +.sp +If the first part of the subject is "ABC123", a partial match of the first +alternative is found at offset 3. There is no partial match for the second +alternative, because such a match does not start at the same point in the +subject string. Attempting to continue with the string "7890" does not yield a +match because only those alternatives that match at one point in the subject +are remembered. The problem arises because the start of the second alternative +matches within the first alternative. There is no problem with anchored +patterns or patterns such as: +.sp + 1234|ABCD +.sp +where no string can be a partial match for both alternatives. This is not a +problem if a standard matching function is used, because the entire match has +to be rerun each time: +.sp + re> /1234|3789/ + data> ABC123\eP\eP + Partial match: 123 + data> 1237890 + 0: 3789 +.sp +Of course, instead of using PCRE_DFA_RESTART, the same technique of re-running +the entire match can also be used with the DFA matching functions. Another +possibility is to work with two buffers. If a partial match at offset \fIn\fP +in the first buffer is followed by "no match" when PCRE_DFA_RESTART is used on +the second buffer, you can then try a new match starting at offset \fIn+1\fP in +the first buffer. +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 02 July 2013 +Copyright (c) 1997-2013 University of Cambridge. +.fi diff --git a/plugins/Pcre16/docs/doc/pcrepattern.3 b/plugins/Pcre16/docs/doc/pcrepattern.3 new file mode 100644 index 0000000000..f1c45cda5d --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcrepattern.3 @@ -0,0 +1,3265 @@ +.TH PCREPATTERN 3 "08 January 2014" "PCRE 8.35" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH "PCRE REGULAR EXPRESSION DETAILS" +.rs +.sp +The syntax and semantics of the regular expressions that are supported by PCRE +are described in detail below. There is a quick-reference syntax summary in the +.\" HREF +\fBpcresyntax\fP +.\" +page. PCRE tries to match Perl syntax and semantics as closely as it can. PCRE +also supports some alternative regular expression syntax (which does not +conflict with the Perl syntax) in order to provide some compatibility with +regular expressions in Python, .NET, and Oniguruma. +.P +Perl's regular expressions are described in its own documentation, and +regular expressions in general are covered in a number of books, some of which +have copious examples. Jeffrey Friedl's "Mastering Regular Expressions", +published by O'Reilly, covers regular expressions in great detail. This +description of PCRE's regular expressions is intended as reference material. +.P +This document discusses the patterns that are supported by PCRE when one its +main matching functions, \fBpcre_exec()\fP (8-bit) or \fBpcre[16|32]_exec()\fP +(16- or 32-bit), is used. PCRE also has alternative matching functions, +\fBpcre_dfa_exec()\fP and \fBpcre[16|32_dfa_exec()\fP, which match using a +different algorithm that is not Perl-compatible. Some of the features discussed +below are not available when DFA matching is used. The advantages and +disadvantages of the alternative functions, and how they differ from the normal +functions, are discussed in the +.\" HREF +\fBpcrematching\fP +.\" +page. +. +. +.SH "SPECIAL START-OF-PATTERN ITEMS" +.rs +.sp +A number of options that can be passed to \fBpcre_compile()\fP can also be set +by special items at the start of a pattern. These are not Perl-compatible, but +are provided to make these options accessible to pattern writers who are not +able to change the program that processes the pattern. Any number of these +items may appear, but they must all be together right at the start of the +pattern string, and the letters must be in upper case. +. +. +.SS "UTF support" +.rs +.sp +The original operation of PCRE was on strings of one-byte characters. However, +there is now also support for UTF-8 strings in the original library, an +extra library that supports 16-bit and UTF-16 character strings, and a +third library that supports 32-bit and UTF-32 character strings. To use these +features, PCRE must be built to include appropriate support. When using UTF +strings you must either call the compiling function with the PCRE_UTF8, +PCRE_UTF16, or PCRE_UTF32 option, or the pattern must start with one of +these special sequences: +.sp + (*UTF8) + (*UTF16) + (*UTF32) + (*UTF) +.sp +(*UTF) is a generic sequence that can be used with any of the libraries. +Starting a pattern with such a sequence is equivalent to setting the relevant +option. How setting a UTF mode affects pattern matching is mentioned in several +places below. There is also a summary of features in the +.\" HREF +\fBpcreunicode\fP +.\" +page. +.P +Some applications that allow their users to supply patterns may wish to +restrict them to non-UTF data for security reasons. If the PCRE_NEVER_UTF +option is set at compile time, (*UTF) etc. are not allowed, and their +appearance causes an error. +. +. +.SS "Unicode property support" +.rs +.sp +Another special sequence that may appear at the start of a pattern is (*UCP). +This has the same effect as setting the PCRE_UCP option: it causes sequences +such as \ed and \ew to use Unicode properties to determine character types, +instead of recognizing only characters with codes less than 128 via a lookup +table. +. +. +.SS "Disabling auto-possessification" +.rs +.sp +If a pattern starts with (*NO_AUTO_POSSESS), it has the same effect as setting +the PCRE_NO_AUTO_POSSESS option at compile time. This stops PCRE from making +quantifiers possessive when what follows cannot match the repeated item. For +example, by default a+b is treated as a++b. For more details, see the +.\" HREF +\fBpcreapi\fP +.\" +documentation. +. +. +.SS "Disabling start-up optimizations" +.rs +.sp +If a pattern starts with (*NO_START_OPT), it has the same effect as setting the +PCRE_NO_START_OPTIMIZE option either at compile or matching time. This disables +several optimizations for quickly reaching "no match" results. For more +details, see the +.\" HREF +\fBpcreapi\fP +.\" +documentation. +. +. +.\" HTML <a name="newlines"></a> +.SS "Newline conventions" +.rs +.sp +PCRE supports five different conventions for indicating line breaks in +strings: a single CR (carriage return) character, a single LF (linefeed) +character, the two-character sequence CRLF, any of the three preceding, or any +Unicode newline sequence. The +.\" HREF +\fBpcreapi\fP +.\" +page has +.\" HTML <a href="pcreapi.html#newlines"> +.\" </a> +further discussion +.\" +about newlines, and shows how to set the newline convention in the +\fIoptions\fP arguments for the compiling and matching functions. +.P +It is also possible to specify a newline convention by starting a pattern +string with one of the following five sequences: +.sp + (*CR) carriage return + (*LF) linefeed + (*CRLF) carriage return, followed by linefeed + (*ANYCRLF) any of the three above + (*ANY) all Unicode newline sequences +.sp +These override the default and the options given to the compiling function. For +example, on a Unix system where LF is the default newline sequence, the pattern +.sp + (*CR)a.b +.sp +changes the convention to CR. That pattern matches "a\enb" because LF is no +longer a newline. If more than one of these settings is present, the last one +is used. +.P +The newline convention affects where the circumflex and dollar assertions are +true. It also affects the interpretation of the dot metacharacter when +PCRE_DOTALL is not set, and the behaviour of \eN. However, it does not affect +what the \eR escape sequence matches. By default, this is any Unicode newline +sequence, for Perl compatibility. However, this can be changed; see the +description of \eR in the section entitled +.\" HTML <a href="#newlineseq"> +.\" </a> +"Newline sequences" +.\" +below. A change of \eR setting can be combined with a change of newline +convention. +. +. +.SS "Setting match and recursion limits" +.rs +.sp +The caller of \fBpcre_exec()\fP can set a limit on the number of times the +internal \fBmatch()\fP function is called and on the maximum depth of +recursive calls. These facilities are provided to catch runaway matches that +are provoked by patterns with huge matching trees (a typical example is a +pattern with nested unlimited repeats) and to avoid running out of system stack +by too much recursion. When one of these limits is reached, \fBpcre_exec()\fP +gives an error return. The limits can also be set by items at the start of the +pattern of the form +.sp + (*LIMIT_MATCH=d) + (*LIMIT_RECURSION=d) +.sp +where d is any number of decimal digits. However, the value of the setting must +be less than the value set (or defaulted) by the caller of \fBpcre_exec()\fP +for it to have any effect. In other words, the pattern writer can lower the +limits set by the programmer, but not raise them. If there is more than one +setting of one of these limits, the lower value is used. +. +. +.SH "EBCDIC CHARACTER CODES" +.rs +.sp +PCRE can be compiled to run in an environment that uses EBCDIC as its character +code rather than ASCII or Unicode (typically a mainframe system). In the +sections below, character code values are ASCII or Unicode; in an EBCDIC +environment these characters may have different code values, and there are no +code points greater than 255. +. +. +.SH "CHARACTERS AND METACHARACTERS" +.rs +.sp +A regular expression is a pattern that is matched against a subject string from +left to right. Most characters stand for themselves in a pattern, and match the +corresponding characters in the subject. As a trivial example, the pattern +.sp + The quick brown fox +.sp +matches a portion of a subject string that is identical to itself. When +caseless matching is specified (the PCRE_CASELESS option), letters are matched +independently of case. In a UTF mode, PCRE always understands the concept of +case for characters whose values are less than 128, so caseless matching is +always possible. For characters with higher values, the concept of case is +supported if PCRE is compiled with Unicode property support, but not otherwise. +If you want to use caseless matching for characters 128 and above, you must +ensure that PCRE is compiled with Unicode property support as well as with +UTF support. +.P +The power of regular expressions comes from the ability to include alternatives +and repetitions in the pattern. These are encoded in the pattern by the use of +\fImetacharacters\fP, which do not stand for themselves but instead are +interpreted in some special way. +.P +There are two different sets of metacharacters: those that are recognized +anywhere in the pattern except within square brackets, and those that are +recognized within square brackets. Outside square brackets, the metacharacters +are as follows: +.sp + \e general escape character with several uses + ^ assert start of string (or line, in multiline mode) + $ assert end of string (or line, in multiline mode) + . match any character except newline (by default) + [ start character class definition + | start of alternative branch + ( start subpattern + ) end subpattern + ? extends the meaning of ( + also 0 or 1 quantifier + also quantifier minimizer + * 0 or more quantifier + + 1 or more quantifier + also "possessive quantifier" + { start min/max quantifier +.sp +Part of a pattern that is in square brackets is called a "character class". In +a character class the only metacharacters are: +.sp + \e general escape character + ^ negate the class, but only if the first character + - indicates character range +.\" JOIN + [ POSIX character class (only if followed by POSIX + syntax) + ] terminates the character class +.sp +The following sections describe the use of each of the metacharacters. +. +. +.SH BACKSLASH +.rs +.sp +The backslash character has several uses. Firstly, if it is followed by a +character that is not a number or a letter, it takes away any special meaning +that character may have. This use of backslash as an escape character applies +both inside and outside character classes. +.P +For example, if you want to match a * character, you write \e* in the pattern. +This escaping action applies whether or not the following character would +otherwise be interpreted as a metacharacter, so it is always safe to precede a +non-alphanumeric with backslash to specify that it stands for itself. In +particular, if you want to match a backslash, you write \e\e. +.P +In a UTF mode, only ASCII numbers and letters have any special meaning after a +backslash. All other characters (in particular, those whose codepoints are +greater than 127) are treated as literals. +.P +If a pattern is compiled with the PCRE_EXTENDED option, most white space in the +pattern (other than in a character class), and characters between a # outside a +character class and the next newline, inclusive, are ignored. An escaping +backslash can be used to include a white space or # character as part of the +pattern. +.P +If you want to remove the special meaning from a sequence of characters, you +can do so by putting them between \eQ and \eE. This is different from Perl in +that $ and @ are handled as literals in \eQ...\eE sequences in PCRE, whereas in +Perl, $ and @ cause variable interpolation. Note the following examples: +.sp + Pattern PCRE matches Perl matches +.sp +.\" JOIN + \eQabc$xyz\eE abc$xyz abc followed by the + contents of $xyz + \eQabc\e$xyz\eE abc\e$xyz abc\e$xyz + \eQabc\eE\e$\eQxyz\eE abc$xyz abc$xyz +.sp +The \eQ...\eE sequence is recognized both inside and outside character classes. +An isolated \eE that is not preceded by \eQ is ignored. If \eQ is not followed +by \eE later in the pattern, the literal interpretation continues to the end of +the pattern (that is, \eE is assumed at the end). If the isolated \eQ is inside +a character class, this causes an error, because the character class is not +terminated. +. +. +.\" HTML <a name="digitsafterbackslash"></a> +.SS "Non-printing characters" +.rs +.sp +A second use of backslash provides a way of encoding non-printing characters +in patterns in a visible manner. There is no restriction on the appearance of +non-printing characters, apart from the binary zero that terminates a pattern, +but when a pattern is being prepared by text editing, it is often easier to use +one of the following escape sequences than the binary character it represents: +.sp + \ea alarm, that is, the BEL character (hex 07) + \ecx "control-x", where x is any ASCII character + \ee escape (hex 1B) + \ef form feed (hex 0C) + \en linefeed (hex 0A) + \er carriage return (hex 0D) + \et tab (hex 09) + \e0dd character with octal code 0dd + \eddd character with octal code ddd, or back reference + \eo{ddd..} character with octal code ddd.. + \exhh character with hex code hh + \ex{hhh..} character with hex code hhh.. (non-JavaScript mode) + \euhhhh character with hex code hhhh (JavaScript mode only) +.sp +The precise effect of \ecx on ASCII characters is as follows: if x is a lower +case letter, it is converted to upper case. Then bit 6 of the character (hex +40) is inverted. Thus \ecA to \ecZ become hex 01 to hex 1A (A is 41, Z is 5A), +but \ec{ becomes hex 3B ({ is 7B), and \ec; becomes hex 7B (; is 3B). If the +data item (byte or 16-bit value) following \ec has a value greater than 127, a +compile-time error occurs. This locks out non-ASCII characters in all modes. +.P +The \ec facility was designed for use with ASCII characters, but with the +extension to Unicode it is even less useful than it once was. It is, however, +recognized when PCRE is compiled in EBCDIC mode, where data items are always +bytes. In this mode, all values are valid after \ec. If the next character is a +lower case letter, it is converted to upper case. Then the 0xc0 bits of the +byte are inverted. Thus \ecA becomes hex 01, as in ASCII (A is C1), but because +the EBCDIC letters are disjoint, \ecZ becomes hex 29 (Z is E9), and other +characters also generate different values. +.P +After \e0 up to two further octal digits are read. If there are fewer than two +digits, just those that are present are used. Thus the sequence \e0\ex\e07 +specifies two binary zeros followed by a BEL character (code value 7). Make +sure you supply two digits after the initial zero if the pattern character that +follows is itself an octal digit. +.P +The escape \eo must be followed by a sequence of octal digits, enclosed in +braces. An error occurs if this is not the case. This escape is a recent +addition to Perl; it provides way of specifying character code points as octal +numbers greater than 0777, and it also allows octal numbers and back references +to be unambiguously specified. +.P +For greater clarity and unambiguity, it is best to avoid following \e by a +digit greater than zero. Instead, use \eo{} or \ex{} to specify character +numbers, and \eg{} to specify back references. The following paragraphs +describe the old, ambiguous syntax. +.P +The handling of a backslash followed by a digit other than 0 is complicated, +and Perl has changed in recent releases, causing PCRE also to change. Outside a +character class, PCRE reads the digit and any following digits as a decimal +number. If the number is less than 8, or if there have been at least that many +previous capturing left parentheses in the expression, the entire sequence is +taken as a \fIback reference\fP. A description of how this works is given +.\" HTML <a href="#backreferences"> +.\" </a> +later, +.\" +following the discussion of +.\" HTML <a href="#subpattern"> +.\" </a> +parenthesized subpatterns. +.\" +.P +Inside a character class, or if the decimal number following \e is greater than +7 and there have not been that many capturing subpatterns, PCRE handles \e8 and +\e9 as the literal characters "8" and "9", and otherwise re-reads up to three +octal digits following the backslash, using them to generate a data character. +Any subsequent digits stand for themselves. For example: +.sp + \e040 is another way of writing an ASCII space +.\" JOIN + \e40 is the same, provided there are fewer than 40 + previous capturing subpatterns + \e7 is always a back reference +.\" JOIN + \e11 might be a back reference, or another way of + writing a tab + \e011 is always a tab + \e0113 is a tab followed by the character "3" +.\" JOIN + \e113 might be a back reference, otherwise the + character with octal code 113 +.\" JOIN + \e377 might be a back reference, otherwise + the value 255 (decimal) +.\" JOIN + \e81 is either a back reference, or the two + characters "8" and "1" +.sp +Note that octal values of 100 or greater that are specified using this syntax +must not be introduced by a leading zero, because no more than three octal +digits are ever read. +.P +By default, after \ex that is not followed by {, from zero to two hexadecimal +digits are read (letters can be in upper or lower case). Any number of +hexadecimal digits may appear between \ex{ and }. If a character other than +a hexadecimal digit appears between \ex{ and }, or if there is no terminating +}, an error occurs. +.P +If the PCRE_JAVASCRIPT_COMPAT option is set, the interpretation of \ex is +as just described only when it is followed by two hexadecimal digits. +Otherwise, it matches a literal "x" character. In JavaScript mode, support for +code points greater than 256 is provided by \eu, which must be followed by +four hexadecimal digits; otherwise it matches a literal "u" character. +.P +Characters whose value is less than 256 can be defined by either of the two +syntaxes for \ex (or by \eu in JavaScript mode). There is no difference in the +way they are handled. For example, \exdc is exactly the same as \ex{dc} (or +\eu00dc in JavaScript mode). +. +. +.SS "Constraints on character values" +.rs +.sp +Characters that are specified using octal or hexadecimal numbers are +limited to certain values, as follows: +.sp + 8-bit non-UTF mode less than 0x100 + 8-bit UTF-8 mode less than 0x10ffff and a valid codepoint + 16-bit non-UTF mode less than 0x10000 + 16-bit UTF-16 mode less than 0x10ffff and a valid codepoint + 32-bit non-UTF mode less than 0x100000000 + 32-bit UTF-32 mode less than 0x10ffff and a valid codepoint +.sp +Invalid Unicode codepoints are the range 0xd800 to 0xdfff (the so-called +"surrogate" codepoints), and 0xffef. +. +. +.SS "Escape sequences in character classes" +.rs +.sp +All the sequences that define a single character value can be used both inside +and outside character classes. In addition, inside a character class, \eb is +interpreted as the backspace character (hex 08). +.P +\eN is not allowed in a character class. \eB, \eR, and \eX are not special +inside a character class. Like other unrecognized escape sequences, they are +treated as the literal characters "B", "R", and "X" by default, but cause an +error if the PCRE_EXTRA option is set. Outside a character class, these +sequences have different meanings. +. +. +.SS "Unsupported escape sequences" +.rs +.sp +In Perl, the sequences \el, \eL, \eu, and \eU are recognized by its string +handler and used to modify the case of following characters. By default, PCRE +does not support these escape sequences. However, if the PCRE_JAVASCRIPT_COMPAT +option is set, \eU matches a "U" character, and \eu can be used to define a +character by code point, as described in the previous section. +. +. +.SS "Absolute and relative back references" +.rs +.sp +The sequence \eg followed by an unsigned or a negative number, optionally +enclosed in braces, is an absolute or relative back reference. A named back +reference can be coded as \eg{name}. Back references are discussed +.\" HTML <a href="#backreferences"> +.\" </a> +later, +.\" +following the discussion of +.\" HTML <a href="#subpattern"> +.\" </a> +parenthesized subpatterns. +.\" +. +. +.SS "Absolute and relative subroutine calls" +.rs +.sp +For compatibility with Oniguruma, the non-Perl syntax \eg followed by a name or +a number enclosed either in angle brackets or single quotes, is an alternative +syntax for referencing a subpattern as a "subroutine". Details are discussed +.\" HTML <a href="#onigurumasubroutines"> +.\" </a> +later. +.\" +Note that \eg{...} (Perl syntax) and \eg<...> (Oniguruma syntax) are \fInot\fP +synonymous. The former is a back reference; the latter is a +.\" HTML <a href="#subpatternsassubroutines"> +.\" </a> +subroutine +.\" +call. +. +. +.\" HTML <a name="genericchartypes"></a> +.SS "Generic character types" +.rs +.sp +Another use of backslash is for specifying generic character types: +.sp + \ed any decimal digit + \eD any character that is not a decimal digit + \eh any horizontal white space character + \eH any character that is not a horizontal white space character + \es any white space character + \eS any character that is not a white space character + \ev any vertical white space character + \eV any character that is not a vertical white space character + \ew any "word" character + \eW any "non-word" character +.sp +There is also the single sequence \eN, which matches a non-newline character. +This is the same as +.\" HTML <a href="#fullstopdot"> +.\" </a> +the "." metacharacter +.\" +when PCRE_DOTALL is not set. Perl also uses \eN to match characters by name; +PCRE does not support this. +.P +Each pair of lower and upper case escape sequences partitions the complete set +of characters into two disjoint sets. Any given character matches one, and only +one, of each pair. The sequences can appear both inside and outside character +classes. They each match one character of the appropriate type. If the current +matching point is at the end of the subject string, all of them fail, because +there is no character to match. +.P +For compatibility with Perl, \es did not used to match the VT character (code +11), which made it different from the the POSIX "space" class. However, Perl +added VT at release 5.18, and PCRE followed suit at release 8.34. The default +\es characters are now HT (9), LF (10), VT (11), FF (12), CR (13), and space +(32), which are defined as white space in the "C" locale. This list may vary if +locale-specific matching is taking place. For example, in some locales the +"non-breaking space" character (\exA0) is recognized as white space, and in +others the VT character is not. +.P +A "word" character is an underscore or any character that is a letter or digit. +By default, the definition of letters and digits is controlled by PCRE's +low-valued character tables, and may vary if locale-specific matching is taking +place (see +.\" HTML <a href="pcreapi.html#localesupport"> +.\" </a> +"Locale support" +.\" +in the +.\" HREF +\fBpcreapi\fP +.\" +page). For example, in a French locale such as "fr_FR" in Unix-like systems, +or "french" in Windows, some character codes greater than 127 are used for +accented letters, and these are then matched by \ew. The use of locales with +Unicode is discouraged. +.P +By default, characters whose code points are greater than 127 never match \ed, +\es, or \ew, and always match \eD, \eS, and \eW, although this may vary for +characters in the range 128-255 when locale-specific matching is happening. +These escape sequences retain their original meanings from before Unicode +support was available, mainly for efficiency reasons. If PCRE is compiled with +Unicode property support, and the PCRE_UCP option is set, the behaviour is +changed so that Unicode properties are used to determine character types, as +follows: +.sp + \ed any character that matches \ep{Nd} (decimal digit) + \es any character that matches \ep{Z} or \eh or \ev + \ew any character that matches \ep{L} or \ep{N}, plus underscore +.sp +The upper case escapes match the inverse sets of characters. Note that \ed +matches only decimal digits, whereas \ew matches any Unicode digit, as well as +any Unicode letter, and underscore. Note also that PCRE_UCP affects \eb, and +\eB because they are defined in terms of \ew and \eW. Matching these sequences +is noticeably slower when PCRE_UCP is set. +.P +The sequences \eh, \eH, \ev, and \eV are features that were added to Perl at +release 5.10. In contrast to the other sequences, which match only ASCII +characters by default, these always match certain high-valued code points, +whether or not PCRE_UCP is set. The horizontal space characters are: +.sp + U+0009 Horizontal tab (HT) + U+0020 Space + U+00A0 Non-break space + U+1680 Ogham space mark + U+180E Mongolian vowel separator + U+2000 En quad + U+2001 Em quad + U+2002 En space + U+2003 Em space + U+2004 Three-per-em space + U+2005 Four-per-em space + U+2006 Six-per-em space + U+2007 Figure space + U+2008 Punctuation space + U+2009 Thin space + U+200A Hair space + U+202F Narrow no-break space + U+205F Medium mathematical space + U+3000 Ideographic space +.sp +The vertical space characters are: +.sp + U+000A Linefeed (LF) + U+000B Vertical tab (VT) + U+000C Form feed (FF) + U+000D Carriage return (CR) + U+0085 Next line (NEL) + U+2028 Line separator + U+2029 Paragraph separator +.sp +In 8-bit, non-UTF-8 mode, only the characters with codepoints less than 256 are +relevant. +. +. +.\" HTML <a name="newlineseq"></a> +.SS "Newline sequences" +.rs +.sp +Outside a character class, by default, the escape sequence \eR matches any +Unicode newline sequence. In 8-bit non-UTF-8 mode \eR is equivalent to the +following: +.sp + (?>\er\en|\en|\ex0b|\ef|\er|\ex85) +.sp +This is an example of an "atomic group", details of which are given +.\" HTML <a href="#atomicgroup"> +.\" </a> +below. +.\" +This particular group matches either the two-character sequence CR followed by +LF, or one of the single characters LF (linefeed, U+000A), VT (vertical tab, +U+000B), FF (form feed, U+000C), CR (carriage return, U+000D), or NEL (next +line, U+0085). The two-character sequence is treated as a single unit that +cannot be split. +.P +In other modes, two additional characters whose codepoints are greater than 255 +are added: LS (line separator, U+2028) and PS (paragraph separator, U+2029). +Unicode character property support is not needed for these characters to be +recognized. +.P +It is possible to restrict \eR to match only CR, LF, or CRLF (instead of the +complete set of Unicode line endings) by setting the option PCRE_BSR_ANYCRLF +either at compile time or when the pattern is matched. (BSR is an abbrevation +for "backslash R".) This can be made the default when PCRE is built; if this is +the case, the other behaviour can be requested via the PCRE_BSR_UNICODE option. +It is also possible to specify these settings by starting a pattern string with +one of the following sequences: +.sp + (*BSR_ANYCRLF) CR, LF, or CRLF only + (*BSR_UNICODE) any Unicode newline sequence +.sp +These override the default and the options given to the compiling function, but +they can themselves be overridden by options given to a matching function. Note +that these special settings, which are not Perl-compatible, are recognized only +at the very start of a pattern, and that they must be in upper case. If more +than one of them is present, the last one is used. They can be combined with a +change of newline convention; for example, a pattern can start with: +.sp + (*ANY)(*BSR_ANYCRLF) +.sp +They can also be combined with the (*UTF8), (*UTF16), (*UTF32), (*UTF) or +(*UCP) special sequences. Inside a character class, \eR is treated as an +unrecognized escape sequence, and so matches the letter "R" by default, but +causes an error if PCRE_EXTRA is set. +. +. +.\" HTML <a name="uniextseq"></a> +.SS Unicode character properties +.rs +.sp +When PCRE is built with Unicode character property support, three additional +escape sequences that match characters with specific properties are available. +When in 8-bit non-UTF-8 mode, these sequences are of course limited to testing +characters whose codepoints are less than 256, but they do work in this mode. +The extra escape sequences are: +.sp + \ep{\fIxx\fP} a character with the \fIxx\fP property + \eP{\fIxx\fP} a character without the \fIxx\fP property + \eX a Unicode extended grapheme cluster +.sp +The property names represented by \fIxx\fP above are limited to the Unicode +script names, the general category properties, "Any", which matches any +character (including newline), and some special PCRE properties (described +in the +.\" HTML <a href="#extraprops"> +.\" </a> +next section). +.\" +Other Perl properties such as "InMusicalSymbols" are not currently supported by +PCRE. Note that \eP{Any} does not match any characters, so always causes a +match failure. +.P +Sets of Unicode characters are defined as belonging to certain scripts. A +character from one of these sets can be matched using a script name. For +example: +.sp + \ep{Greek} + \eP{Han} +.sp +Those that are not part of an identified script are lumped together as +"Common". The current list of scripts is: +.P +Arabic, +Armenian, +Avestan, +Balinese, +Bamum, +Batak, +Bengali, +Bopomofo, +Brahmi, +Braille, +Buginese, +Buhid, +Canadian_Aboriginal, +Carian, +Chakma, +Cham, +Cherokee, +Common, +Coptic, +Cuneiform, +Cypriot, +Cyrillic, +Deseret, +Devanagari, +Egyptian_Hieroglyphs, +Ethiopic, +Georgian, +Glagolitic, +Gothic, +Greek, +Gujarati, +Gurmukhi, +Han, +Hangul, +Hanunoo, +Hebrew, +Hiragana, +Imperial_Aramaic, +Inherited, +Inscriptional_Pahlavi, +Inscriptional_Parthian, +Javanese, +Kaithi, +Kannada, +Katakana, +Kayah_Li, +Kharoshthi, +Khmer, +Lao, +Latin, +Lepcha, +Limbu, +Linear_B, +Lisu, +Lycian, +Lydian, +Malayalam, +Mandaic, +Meetei_Mayek, +Meroitic_Cursive, +Meroitic_Hieroglyphs, +Miao, +Mongolian, +Myanmar, +New_Tai_Lue, +Nko, +Ogham, +Old_Italic, +Old_Persian, +Old_South_Arabian, +Old_Turkic, +Ol_Chiki, +Oriya, +Osmanya, +Phags_Pa, +Phoenician, +Rejang, +Runic, +Samaritan, +Saurashtra, +Sharada, +Shavian, +Sinhala, +Sora_Sompeng, +Sundanese, +Syloti_Nagri, +Syriac, +Tagalog, +Tagbanwa, +Tai_Le, +Tai_Tham, +Tai_Viet, +Takri, +Tamil, +Telugu, +Thaana, +Thai, +Tibetan, +Tifinagh, +Ugaritic, +Vai, +Yi. +.P +Each character has exactly one Unicode general category property, specified by +a two-letter abbreviation. For compatibility with Perl, negation can be +specified by including a circumflex between the opening brace and the property +name. For example, \ep{^Lu} is the same as \eP{Lu}. +.P +If only one letter is specified with \ep or \eP, it includes all the general +category properties that start with that letter. In this case, in the absence +of negation, the curly brackets in the escape sequence are optional; these two +examples have the same effect: +.sp + \ep{L} + \epL +.sp +The following general category property codes are supported: +.sp + C Other + Cc Control + Cf Format + Cn Unassigned + Co Private use + Cs Surrogate +.sp + L Letter + Ll Lower case letter + Lm Modifier letter + Lo Other letter + Lt Title case letter + Lu Upper case letter +.sp + M Mark + Mc Spacing mark + Me Enclosing mark + Mn Non-spacing mark +.sp + N Number + Nd Decimal number + Nl Letter number + No Other number +.sp + P Punctuation + Pc Connector punctuation + Pd Dash punctuation + Pe Close punctuation + Pf Final punctuation + Pi Initial punctuation + Po Other punctuation + Ps Open punctuation +.sp + S Symbol + Sc Currency symbol + Sk Modifier symbol + Sm Mathematical symbol + So Other symbol +.sp + Z Separator + Zl Line separator + Zp Paragraph separator + Zs Space separator +.sp +The special property L& is also supported: it matches a character that has +the Lu, Ll, or Lt property, in other words, a letter that is not classified as +a modifier or "other". +.P +The Cs (Surrogate) property applies only to characters in the range U+D800 to +U+DFFF. Such characters are not valid in Unicode strings and so +cannot be tested by PCRE, unless UTF validity checking has been turned off +(see the discussion of PCRE_NO_UTF8_CHECK, PCRE_NO_UTF16_CHECK and +PCRE_NO_UTF32_CHECK in the +.\" HREF +\fBpcreapi\fP +.\" +page). Perl does not support the Cs property. +.P +The long synonyms for property names that Perl supports (such as \ep{Letter}) +are not supported by PCRE, nor is it permitted to prefix any of these +properties with "Is". +.P +No character that is in the Unicode table has the Cn (unassigned) property. +Instead, this property is assumed for any code point that is not in the +Unicode table. +.P +Specifying caseless matching does not affect these escape sequences. For +example, \ep{Lu} always matches only upper case letters. This is different from +the behaviour of current versions of Perl. +.P +Matching characters by Unicode property is not fast, because PCRE has to do a +multistage table lookup in order to find a character's property. That is why +the traditional escape sequences such as \ed and \ew do not use Unicode +properties in PCRE by default, though you can make them do so by setting the +PCRE_UCP option or by starting the pattern with (*UCP). +. +. +.SS Extended grapheme clusters +.rs +.sp +The \eX escape matches any number of Unicode characters that form an "extended +grapheme cluster", and treats the sequence as an atomic group +.\" HTML <a href="#atomicgroup"> +.\" </a> +(see below). +.\" +Up to and including release 8.31, PCRE matched an earlier, simpler definition +that was equivalent to +.sp + (?>\ePM\epM*) +.sp +That is, it matched a character without the "mark" property, followed by zero +or more characters with the "mark" property. Characters with the "mark" +property are typically non-spacing accents that affect the preceding character. +.P +This simple definition was extended in Unicode to include more complicated +kinds of composite character by giving each character a grapheme breaking +property, and creating rules that use these properties to define the boundaries +of extended grapheme clusters. In releases of PCRE later than 8.31, \eX matches +one of these clusters. +.P +\eX always matches at least one character. Then it decides whether to add +additional characters according to the following rules for ending a cluster: +.P +1. End at the end of the subject string. +.P +2. Do not end between CR and LF; otherwise end after any control character. +.P +3. Do not break Hangul (a Korean script) syllable sequences. Hangul characters +are of five types: L, V, T, LV, and LVT. An L character may be followed by an +L, V, LV, or LVT character; an LV or V character may be followed by a V or T +character; an LVT or T character may be follwed only by a T character. +.P +4. Do not end before extending characters or spacing marks. Characters with +the "mark" property always have the "extend" grapheme breaking property. +.P +5. Do not end after prepend characters. +.P +6. Otherwise, end the cluster. +. +. +.\" HTML <a name="extraprops"></a> +.SS PCRE's additional properties +.rs +.sp +As well as the standard Unicode properties described above, PCRE supports four +more that make it possible to convert traditional escape sequences such as \ew +and \es to use Unicode properties. PCRE uses these non-standard, non-Perl +properties internally when PCRE_UCP is set. However, they may also be used +explicitly. These properties are: +.sp + Xan Any alphanumeric character + Xps Any POSIX space character + Xsp Any Perl space character + Xwd Any Perl "word" character +.sp +Xan matches characters that have either the L (letter) or the N (number) +property. Xps matches the characters tab, linefeed, vertical tab, form feed, or +carriage return, and any other character that has the Z (separator) property. +Xsp is the same as Xps; it used to exclude vertical tab, for Perl +compatibility, but Perl changed, and so PCRE followed at release 8.34. Xwd +matches the same characters as Xan, plus underscore. +.P +There is another non-standard property, Xuc, which matches any character that +can be represented by a Universal Character Name in C++ and other programming +languages. These are the characters $, @, ` (grave accent), and all characters +with Unicode code points greater than or equal to U+00A0, except for the +surrogates U+D800 to U+DFFF. Note that most base (ASCII) characters are +excluded. (Universal Character Names are of the form \euHHHH or \eUHHHHHHHH +where H is a hexadecimal digit. Note that the Xuc property does not match these +sequences but the characters that they represent.) +. +. +.\" HTML <a name="resetmatchstart"></a> +.SS "Resetting the match start" +.rs +.sp +The escape sequence \eK causes any previously matched characters not to be +included in the final matched sequence. For example, the pattern: +.sp + foo\eKbar +.sp +matches "foobar", but reports that it has matched "bar". This feature is +similar to a lookbehind assertion +.\" HTML <a href="#lookbehind"> +.\" </a> +(described below). +.\" +However, in this case, the part of the subject before the real match does not +have to be of fixed length, as lookbehind assertions do. The use of \eK does +not interfere with the setting of +.\" HTML <a href="#subpattern"> +.\" </a> +captured substrings. +.\" +For example, when the pattern +.sp + (foo)\eKbar +.sp +matches "foobar", the first substring is still set to "foo". +.P +Perl documents that the use of \eK within assertions is "not well defined". In +PCRE, \eK is acted upon when it occurs inside positive assertions, but is +ignored in negative assertions. Note that when a pattern such as (?=ab\eK) +matches, the reported start of the match can be greater than the end of the +match. +. +. +.\" HTML <a name="smallassertions"></a> +.SS "Simple assertions" +.rs +.sp +The final use of backslash is for certain simple assertions. An assertion +specifies a condition that has to be met at a particular point in a match, +without consuming any characters from the subject string. The use of +subpatterns for more complicated assertions is described +.\" HTML <a href="#bigassertions"> +.\" </a> +below. +.\" +The backslashed assertions are: +.sp + \eb matches at a word boundary + \eB matches when not at a word boundary + \eA matches at the start of the subject + \eZ matches at the end of the subject + also matches before a newline at the end of the subject + \ez matches only at the end of the subject + \eG matches at the first matching position in the subject +.sp +Inside a character class, \eb has a different meaning; it matches the backspace +character. If any other of these assertions appears in a character class, by +default it matches the corresponding literal character (for example, \eB +matches the letter B). However, if the PCRE_EXTRA option is set, an "invalid +escape sequence" error is generated instead. +.P +A word boundary is a position in the subject string where the current character +and the previous character do not both match \ew or \eW (i.e. one matches +\ew and the other matches \eW), or the start or end of the string if the +first or last character matches \ew, respectively. In a UTF mode, the meanings +of \ew and \eW can be changed by setting the PCRE_UCP option. When this is +done, it also affects \eb and \eB. Neither PCRE nor Perl has a separate "start +of word" or "end of word" metasequence. However, whatever follows \eb normally +determines which it is. For example, the fragment \eba matches "a" at the start +of a word. +.P +The \eA, \eZ, and \ez assertions differ from the traditional circumflex and +dollar (described in the next section) in that they only ever match at the very +start and end of the subject string, whatever options are set. Thus, they are +independent of multiline mode. These three assertions are not affected by the +PCRE_NOTBOL or PCRE_NOTEOL options, which affect only the behaviour of the +circumflex and dollar metacharacters. However, if the \fIstartoffset\fP +argument of \fBpcre_exec()\fP is non-zero, indicating that matching is to start +at a point other than the beginning of the subject, \eA can never match. The +difference between \eZ and \ez is that \eZ matches before a newline at the end +of the string as well as at the very end, whereas \ez matches only at the end. +.P +The \eG assertion is true only when the current matching position is at the +start point of the match, as specified by the \fIstartoffset\fP argument of +\fBpcre_exec()\fP. It differs from \eA when the value of \fIstartoffset\fP is +non-zero. By calling \fBpcre_exec()\fP multiple times with appropriate +arguments, you can mimic Perl's /g option, and it is in this kind of +implementation where \eG can be useful. +.P +Note, however, that PCRE's interpretation of \eG, as the start of the current +match, is subtly different from Perl's, which defines it as the end of the +previous match. In Perl, these can be different when the previously matched +string was empty. Because PCRE does just one match at a time, it cannot +reproduce this behaviour. +.P +If all the alternatives of a pattern begin with \eG, the expression is anchored +to the starting match position, and the "anchored" flag is set in the compiled +regular expression. +. +. +.SH "CIRCUMFLEX AND DOLLAR" +.rs +.sp +The circumflex and dollar metacharacters are zero-width assertions. That is, +they test for a particular condition being true without consuming any +characters from the subject string. +.P +Outside a character class, in the default matching mode, the circumflex +character is an assertion that is true only if the current matching point is at +the start of the subject string. If the \fIstartoffset\fP argument of +\fBpcre_exec()\fP is non-zero, circumflex can never match if the PCRE_MULTILINE +option is unset. Inside a character class, circumflex has an entirely different +meaning +.\" HTML <a href="#characterclass"> +.\" </a> +(see below). +.\" +.P +Circumflex need not be the first character of the pattern if a number of +alternatives are involved, but it should be the first thing in each alternative +in which it appears if the pattern is ever to match that branch. If all +possible alternatives start with a circumflex, that is, if the pattern is +constrained to match only at the start of the subject, it is said to be an +"anchored" pattern. (There are also other constructs that can cause a pattern +to be anchored.) +.P +The dollar character is an assertion that is true only if the current matching +point is at the end of the subject string, or immediately before a newline at +the end of the string (by default). Note, however, that it does not actually +match the newline. Dollar need not be the last character of the pattern if a +number of alternatives are involved, but it should be the last item in any +branch in which it appears. Dollar has no special meaning in a character class. +.P +The meaning of dollar can be changed so that it matches only at the very end of +the string, by setting the PCRE_DOLLAR_ENDONLY option at compile time. This +does not affect the \eZ assertion. +.P +The meanings of the circumflex and dollar characters are changed if the +PCRE_MULTILINE option is set. When this is the case, a circumflex matches +immediately after internal newlines as well as at the start of the subject +string. It does not match after a newline that ends the string. A dollar +matches before any newlines in the string, as well as at the very end, when +PCRE_MULTILINE is set. When newline is specified as the two-character +sequence CRLF, isolated CR and LF characters do not indicate newlines. +.P +For example, the pattern /^abc$/ matches the subject string "def\enabc" (where +\en represents a newline) in multiline mode, but not otherwise. Consequently, +patterns that are anchored in single line mode because all branches start with +^ are not anchored in multiline mode, and a match for circumflex is possible +when the \fIstartoffset\fP argument of \fBpcre_exec()\fP is non-zero. The +PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set. +.P +Note that the sequences \eA, \eZ, and \ez can be used to match the start and +end of the subject in both modes, and if all branches of a pattern start with +\eA it is always anchored, whether or not PCRE_MULTILINE is set. +. +. +.\" HTML <a name="fullstopdot"></a> +.SH "FULL STOP (PERIOD, DOT) AND \eN" +.rs +.sp +Outside a character class, a dot in the pattern matches any one character in +the subject string except (by default) a character that signifies the end of a +line. +.P +When a line ending is defined as a single character, dot never matches that +character; when the two-character sequence CRLF is used, dot does not match CR +if it is immediately followed by LF, but otherwise it matches all characters +(including isolated CRs and LFs). When any Unicode line endings are being +recognized, dot does not match CR or LF or any of the other line ending +characters. +.P +The behaviour of dot with regard to newlines can be changed. If the PCRE_DOTALL +option is set, a dot matches any one character, without exception. If the +two-character sequence CRLF is present in the subject string, it takes two dots +to match it. +.P +The handling of dot is entirely independent of the handling of circumflex and +dollar, the only relationship being that they both involve newlines. Dot has no +special meaning in a character class. +.P +The escape sequence \eN behaves like a dot, except that it is not affected by +the PCRE_DOTALL option. In other words, it matches any character except one +that signifies the end of a line. Perl also uses \eN to match characters by +name; PCRE does not support this. +. +. +.SH "MATCHING A SINGLE DATA UNIT" +.rs +.sp +Outside a character class, the escape sequence \eC matches any one data unit, +whether or not a UTF mode is set. In the 8-bit library, one data unit is one +byte; in the 16-bit library it is a 16-bit unit; in the 32-bit library it is +a 32-bit unit. Unlike a dot, \eC always +matches line-ending characters. The feature is provided in Perl in order to +match individual bytes in UTF-8 mode, but it is unclear how it can usefully be +used. Because \eC breaks up characters into individual data units, matching one +unit with \eC in a UTF mode means that the rest of the string may start with a +malformed UTF character. This has undefined results, because PCRE assumes that +it is dealing with valid UTF strings (and by default it checks this at the +start of processing unless the PCRE_NO_UTF8_CHECK, PCRE_NO_UTF16_CHECK or +PCRE_NO_UTF32_CHECK option is used). +.P +PCRE does not allow \eC to appear in lookbehind assertions +.\" HTML <a href="#lookbehind"> +.\" </a> +(described below) +.\" +in a UTF mode, because this would make it impossible to calculate the length of +the lookbehind. +.P +In general, the \eC escape sequence is best avoided. However, one +way of using it that avoids the problem of malformed UTF characters is to use a +lookahead to check the length of the next character, as in this pattern, which +could be used with a UTF-8 string (ignore white space and line breaks): +.sp + (?| (?=[\ex00-\ex7f])(\eC) | + (?=[\ex80-\ex{7ff}])(\eC)(\eC) | + (?=[\ex{800}-\ex{ffff}])(\eC)(\eC)(\eC) | + (?=[\ex{10000}-\ex{1fffff}])(\eC)(\eC)(\eC)(\eC)) +.sp +A group that starts with (?| resets the capturing parentheses numbers in each +alternative (see +.\" HTML <a href="#dupsubpatternnumber"> +.\" </a> +"Duplicate Subpattern Numbers" +.\" +below). The assertions at the start of each branch check the next UTF-8 +character for values whose encoding uses 1, 2, 3, or 4 bytes, respectively. The +character's individual bytes are then captured by the appropriate number of +groups. +. +. +.\" HTML <a name="characterclass"></a> +.SH "SQUARE BRACKETS AND CHARACTER CLASSES" +.rs +.sp +An opening square bracket introduces a character class, terminated by a closing +square bracket. A closing square bracket on its own is not special by default. +However, if the PCRE_JAVASCRIPT_COMPAT option is set, a lone closing square +bracket causes a compile-time error. If a closing square bracket is required as +a member of the class, it should be the first data character in the class +(after an initial circumflex, if present) or escaped with a backslash. +.P +A character class matches a single character in the subject. In a UTF mode, the +character may be more than one data unit long. A matched character must be in +the set of characters defined by the class, unless the first character in the +class definition is a circumflex, in which case the subject character must not +be in the set defined by the class. If a circumflex is actually required as a +member of the class, ensure it is not the first character, or escape it with a +backslash. +.P +For example, the character class [aeiou] matches any lower case vowel, while +[^aeiou] matches any character that is not a lower case vowel. Note that a +circumflex is just a convenient notation for specifying the characters that +are in the class by enumerating those that are not. A class that starts with a +circumflex is not an assertion; it still consumes a character from the subject +string, and therefore it fails if the current pointer is at the end of the +string. +.P +In UTF-8 (UTF-16, UTF-32) mode, characters with values greater than 255 (0xffff) +can be included in a class as a literal string of data units, or by using the +\ex{ escaping mechanism. +.P +When caseless matching is set, any letters in a class represent both their +upper case and lower case versions, so for example, a caseless [aeiou] matches +"A" as well as "a", and a caseless [^aeiou] does not match "A", whereas a +caseful version would. In a UTF mode, PCRE always understands the concept of +case for characters whose values are less than 128, so caseless matching is +always possible. For characters with higher values, the concept of case is +supported if PCRE is compiled with Unicode property support, but not otherwise. +If you want to use caseless matching in a UTF mode for characters 128 and +above, you must ensure that PCRE is compiled with Unicode property support as +well as with UTF support. +.P +Characters that might indicate line breaks are never treated in any special way +when matching character classes, whatever line-ending sequence is in use, and +whatever setting of the PCRE_DOTALL and PCRE_MULTILINE options is used. A class +such as [^a] always matches one of these characters. +.P +The minus (hyphen) character can be used to specify a range of characters in a +character class. For example, [d-m] matches any letter between d and m, +inclusive. If a minus character is required in a class, it must be escaped with +a backslash or appear in a position where it cannot be interpreted as +indicating a range, typically as the first or last character in the class, or +immediately after a range. For example, [b-d-z] matches letters in the range b +to d, a hyphen character, or z. +.P +It is not possible to have the literal character "]" as the end character of a +range. A pattern such as [W-]46] is interpreted as a class of two characters +("W" and "-") followed by a literal string "46]", so it would match "W46]" or +"-46]". However, if the "]" is escaped with a backslash it is interpreted as +the end of range, so [W-\e]46] is interpreted as a class containing a range +followed by two other characters. The octal or hexadecimal representation of +"]" can also be used to end a range. +.P +An error is generated if a POSIX character class (see below) or an escape +sequence other than one that defines a single character appears at a point +where a range ending character is expected. For example, [z-\exff] is valid, +but [A-\ed] and [A-[:digit:]] are not. +.P +Ranges operate in the collating sequence of character values. They can also be +used for characters specified numerically, for example [\e000-\e037]. Ranges +can include any characters that are valid for the current mode. +.P +If a range that includes letters is used when caseless matching is set, it +matches the letters in either case. For example, [W-c] is equivalent to +[][\e\e^_`wxyzabc], matched caselessly, and in a non-UTF mode, if character +tables for a French locale are in use, [\exc8-\excb] matches accented E +characters in both cases. In UTF modes, PCRE supports the concept of case for +characters with values greater than 128 only when it is compiled with Unicode +property support. +.P +The character escape sequences \ed, \eD, \eh, \eH, \ep, \eP, \es, \eS, \ev, +\eV, \ew, and \eW may appear in a character class, and add the characters that +they match to the class. For example, [\edABCDEF] matches any hexadecimal +digit. In UTF modes, the PCRE_UCP option affects the meanings of \ed, \es, \ew +and their upper case partners, just as it does when they appear outside a +character class, as described in the section entitled +.\" HTML <a href="#genericchartypes"> +.\" </a> +"Generic character types" +.\" +above. The escape sequence \eb has a different meaning inside a character +class; it matches the backspace character. The sequences \eB, \eN, \eR, and \eX +are not special inside a character class. Like any other unrecognized escape +sequences, they are treated as the literal characters "B", "N", "R", and "X" by +default, but cause an error if the PCRE_EXTRA option is set. +.P +A circumflex can conveniently be used with the upper case character types to +specify a more restricted set of characters than the matching lower case type. +For example, the class [^\eW_] matches any letter or digit, but not underscore, +whereas [\ew] includes underscore. A positive character class should be read as +"something OR something OR ..." and a negative class as "NOT something AND NOT +something AND NOT ...". +.P +The only metacharacters that are recognized in character classes are backslash, +hyphen (only where it can be interpreted as specifying a range), circumflex +(only at the start), opening square bracket (only when it can be interpreted as +introducing a POSIX class name, or for a special compatibility feature - see +the next two sections), and the terminating closing square bracket. However, +escaping other non-alphanumeric characters does no harm. +. +. +.SH "POSIX CHARACTER CLASSES" +.rs +.sp +Perl supports the POSIX notation for character classes. This uses names +enclosed by [: and :] within the enclosing square brackets. PCRE also supports +this notation. For example, +.sp + [01[:alpha:]%] +.sp +matches "0", "1", any alphabetic character, or "%". The supported class names +are: +.sp + alnum letters and digits + alpha letters + ascii character codes 0 - 127 + blank space or tab only + cntrl control characters + digit decimal digits (same as \ed) + graph printing characters, excluding space + lower lower case letters + print printing characters, including space + punct printing characters, excluding letters and digits and space + space white space (the same as \es from PCRE 8.34) + upper upper case letters + word "word" characters (same as \ew) + xdigit hexadecimal digits +.sp +The default "space" characters are HT (9), LF (10), VT (11), FF (12), CR (13), +and space (32). If locale-specific matching is taking place, the list of space +characters may be different; there may be fewer or more of them. "Space" used +to be different to \es, which did not include VT, for Perl compatibility. +However, Perl changed at release 5.18, and PCRE followed at release 8.34. +"Space" and \es now match the same set of characters. +.P +The name "word" is a Perl extension, and "blank" is a GNU extension from Perl +5.8. Another Perl extension is negation, which is indicated by a ^ character +after the colon. For example, +.sp + [12[:^digit:]] +.sp +matches "1", "2", or any non-digit. PCRE (and Perl) also recognize the POSIX +syntax [.ch.] and [=ch=] where "ch" is a "collating element", but these are not +supported, and an error is given if they are encountered. +.P +By default, characters with values greater than 128 do not match any of the +POSIX character classes. However, if the PCRE_UCP option is passed to +\fBpcre_compile()\fP, some of the classes are changed so that Unicode character +properties are used. This is achieved by replacing certain POSIX classes by +other sequences, as follows: +.sp + [:alnum:] becomes \ep{Xan} + [:alpha:] becomes \ep{L} + [:blank:] becomes \eh + [:digit:] becomes \ep{Nd} + [:lower:] becomes \ep{Ll} + [:space:] becomes \ep{Xps} + [:upper:] becomes \ep{Lu} + [:word:] becomes \ep{Xwd} +.sp +Negated versions, such as [:^alpha:] use \eP instead of \ep. Three other POSIX +classes are handled specially in UCP mode: +.TP 10 +[:graph:] +This matches characters that have glyphs that mark the page when printed. In +Unicode property terms, it matches all characters with the L, M, N, P, S, or Cf +properties, except for: +.sp + U+061C Arabic Letter Mark + U+180E Mongolian Vowel Separator + U+2066 - U+2069 Various "isolate"s +.sp +.TP 10 +[:print:] +This matches the same characters as [:graph:] plus space characters that are +not controls, that is, characters with the Zs property. +.TP 10 +[:punct:] +This matches all characters that have the Unicode P (punctuation) property, +plus those characters whose code points are less than 128 that have the S +(Symbol) property. +.P +The other POSIX classes are unchanged, and match only characters with code +points less than 128. +. +. +.SH "COMPATIBILITY FEATURE FOR WORD BOUNDARIES" +.rs +.sp +In the POSIX.2 compliant library that was included in 4.4BSD Unix, the ugly +syntax [[:<:]] and [[:>:]] is used for matching "start of word" and "end of +word". PCRE treats these items as follows: +.sp + [[:<:]] is converted to \eb(?=\ew) + [[:>:]] is converted to \eb(?<=\ew) +.sp +Only these exact character sequences are recognized. A sequence such as +[a[:<:]b] provokes error for an unrecognized POSIX class name. This support is +not compatible with Perl. It is provided to help migrations from other +environments, and is best not used in any new patterns. Note that \eb matches +at the start and the end of a word (see +.\" HTML <a href="#smallassertions"> +.\" </a> +"Simple assertions" +.\" +above), and in a Perl-style pattern the preceding or following character +normally shows which is wanted, without the need for the assertions that are +used above in order to give exactly the POSIX behaviour. +. +. +.SH "VERTICAL BAR" +.rs +.sp +Vertical bar characters are used to separate alternative patterns. For example, +the pattern +.sp + gilbert|sullivan +.sp +matches either "gilbert" or "sullivan". Any number of alternatives may appear, +and an empty alternative is permitted (matching the empty string). The matching +process tries each alternative in turn, from left to right, and the first one +that succeeds is used. If the alternatives are within a subpattern +.\" HTML <a href="#subpattern"> +.\" </a> +(defined below), +.\" +"succeeds" means matching the rest of the main pattern as well as the +alternative in the subpattern. +. +. +.SH "INTERNAL OPTION SETTING" +.rs +.sp +The settings of the PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and +PCRE_EXTENDED options (which are Perl-compatible) can be changed from within +the pattern by a sequence of Perl option letters enclosed between "(?" and ")". +The option letters are +.sp + i for PCRE_CASELESS + m for PCRE_MULTILINE + s for PCRE_DOTALL + x for PCRE_EXTENDED +.sp +For example, (?im) sets caseless, multiline matching. It is also possible to +unset these options by preceding the letter with a hyphen, and a combined +setting and unsetting such as (?im-sx), which sets PCRE_CASELESS and +PCRE_MULTILINE while unsetting PCRE_DOTALL and PCRE_EXTENDED, is also +permitted. If a letter appears both before and after the hyphen, the option is +unset. +.P +The PCRE-specific options PCRE_DUPNAMES, PCRE_UNGREEDY, and PCRE_EXTRA can be +changed in the same way as the Perl-compatible options by using the characters +J, U and X respectively. +.P +When one of these option changes occurs at top level (that is, not inside +subpattern parentheses), the change applies to the remainder of the pattern +that follows. If the change is placed right at the start of a pattern, PCRE +extracts it into the global options (and it will therefore show up in data +extracted by the \fBpcre_fullinfo()\fP function). +.P +An option change within a subpattern (see below for a description of +subpatterns) affects only that part of the subpattern that follows it, so +.sp + (a(?i)b)c +.sp +matches abc and aBc and no other strings (assuming PCRE_CASELESS is not used). +By this means, options can be made to have different settings in different +parts of the pattern. Any changes made in one alternative do carry on +into subsequent branches within the same subpattern. For example, +.sp + (a(?i)b|c) +.sp +matches "ab", "aB", "c", and "C", even though when matching "C" the first +branch is abandoned before the option setting. This is because the effects of +option settings happen at compile time. There would be some very weird +behaviour otherwise. +.P +\fBNote:\fP There are other PCRE-specific options that can be set by the +application when the compiling or matching functions are called. In some cases +the pattern can contain special leading sequences such as (*CRLF) to override +what the application has set or what has been defaulted. Details are given in +the section entitled +.\" HTML <a href="#newlineseq"> +.\" </a> +"Newline sequences" +.\" +above. There are also the (*UTF8), (*UTF16),(*UTF32), and (*UCP) leading +sequences that can be used to set UTF and Unicode property modes; they are +equivalent to setting the PCRE_UTF8, PCRE_UTF16, PCRE_UTF32 and the PCRE_UCP +options, respectively. The (*UTF) sequence is a generic version that can be +used with any of the libraries. However, the application can set the +PCRE_NEVER_UTF option, which locks out the use of the (*UTF) sequences. +. +. +.\" HTML <a name="subpattern"></a> +.SH SUBPATTERNS +.rs +.sp +Subpatterns are delimited by parentheses (round brackets), which can be nested. +Turning part of a pattern into a subpattern does two things: +.sp +1. It localizes a set of alternatives. For example, the pattern +.sp + cat(aract|erpillar|) +.sp +matches "cataract", "caterpillar", or "cat". Without the parentheses, it would +match "cataract", "erpillar" or an empty string. +.sp +2. It sets up the subpattern as a capturing subpattern. This means that, when +the whole pattern matches, that portion of the subject string that matched the +subpattern is passed back to the caller via the \fIovector\fP argument of the +matching function. (This applies only to the traditional matching functions; +the DFA matching functions do not support capturing.) +.P +Opening parentheses are counted from left to right (starting from 1) to obtain +numbers for the capturing subpatterns. For example, if the string "the red +king" is matched against the pattern +.sp + the ((red|white) (king|queen)) +.sp +the captured substrings are "red king", "red", and "king", and are numbered 1, +2, and 3, respectively. +.P +The fact that plain parentheses fulfil two functions is not always helpful. +There are often times when a grouping subpattern is required without a +capturing requirement. If an opening parenthesis is followed by a question mark +and a colon, the subpattern does not do any capturing, and is not counted when +computing the number of any subsequent capturing subpatterns. For example, if +the string "the white queen" is matched against the pattern +.sp + the ((?:red|white) (king|queen)) +.sp +the captured substrings are "white queen" and "queen", and are numbered 1 and +2. The maximum number of capturing subpatterns is 65535. +.P +As a convenient shorthand, if any option settings are required at the start of +a non-capturing subpattern, the option letters may appear between the "?" and +the ":". Thus the two patterns +.sp + (?i:saturday|sunday) + (?:(?i)saturday|sunday) +.sp +match exactly the same set of strings. Because alternative branches are tried +from left to right, and options are not reset until the end of the subpattern +is reached, an option setting in one branch does affect subsequent branches, so +the above patterns match "SUNDAY" as well as "Saturday". +. +. +.\" HTML <a name="dupsubpatternnumber"></a> +.SH "DUPLICATE SUBPATTERN NUMBERS" +.rs +.sp +Perl 5.10 introduced a feature whereby each alternative in a subpattern uses +the same numbers for its capturing parentheses. Such a subpattern starts with +(?| and is itself a non-capturing subpattern. For example, consider this +pattern: +.sp + (?|(Sat)ur|(Sun))day +.sp +Because the two alternatives are inside a (?| group, both sets of capturing +parentheses are numbered one. Thus, when the pattern matches, you can look +at captured substring number one, whichever alternative matched. This construct +is useful when you want to capture part, but not all, of one of a number of +alternatives. Inside a (?| group, parentheses are numbered as usual, but the +number is reset at the start of each branch. The numbers of any capturing +parentheses that follow the subpattern start after the highest number used in +any branch. The following example is taken from the Perl documentation. The +numbers underneath show in which buffer the captured content will be stored. +.sp + # before ---------------branch-reset----------- after + / ( a ) (?| x ( y ) z | (p (q) r) | (t) u (v) ) ( z ) /x + # 1 2 2 3 2 3 4 +.sp +A back reference to a numbered subpattern uses the most recent value that is +set for that number by any subpattern. The following pattern matches "abcabc" +or "defdef": +.sp + /(?|(abc)|(def))\e1/ +.sp +In contrast, a subroutine call to a numbered subpattern always refers to the +first one in the pattern with the given number. The following pattern matches +"abcabc" or "defabc": +.sp + /(?|(abc)|(def))(?1)/ +.sp +If a +.\" HTML <a href="#conditions"> +.\" </a> +condition test +.\" +for a subpattern's having matched refers to a non-unique number, the test is +true if any of the subpatterns of that number have matched. +.P +An alternative approach to using this "branch reset" feature is to use +duplicate named subpatterns, as described in the next section. +. +. +.SH "NAMED SUBPATTERNS" +.rs +.sp +Identifying capturing parentheses by number is simple, but it can be very hard +to keep track of the numbers in complicated regular expressions. Furthermore, +if an expression is modified, the numbers may change. To help with this +difficulty, PCRE supports the naming of subpatterns. This feature was not +added to Perl until release 5.10. Python had the feature earlier, and PCRE +introduced it at release 4.0, using the Python syntax. PCRE now supports both +the Perl and the Python syntax. Perl allows identically numbered subpatterns to +have different names, but PCRE does not. +.P +In PCRE, a subpattern can be named in one of three ways: (?<name>...) or +(?'name'...) as in Perl, or (?P<name>...) as in Python. References to capturing +parentheses from other parts of the pattern, such as +.\" HTML <a href="#backreferences"> +.\" </a> +back references, +.\" +.\" HTML <a href="#recursion"> +.\" </a> +recursion, +.\" +and +.\" HTML <a href="#conditions"> +.\" </a> +conditions, +.\" +can be made by name as well as by number. +.P +Names consist of up to 32 alphanumeric characters and underscores, but must +start with a non-digit. Named capturing parentheses are still allocated numbers +as well as names, exactly as if the names were not present. The PCRE API +provides function calls for extracting the name-to-number translation table +from a compiled pattern. There is also a convenience function for extracting a +captured substring by name. +.P +By default, a name must be unique within a pattern, but it is possible to relax +this constraint by setting the PCRE_DUPNAMES option at compile time. (Duplicate +names are also always permitted for subpatterns with the same number, set up as +described in the previous section.) Duplicate names can be useful for patterns +where only one instance of the named parentheses can match. Suppose you want to +match the name of a weekday, either as a 3-letter abbreviation or as the full +name, and in both cases you want to extract the abbreviation. This pattern +(ignoring the line breaks) does the job: +.sp + (?<DN>Mon|Fri|Sun)(?:day)?| + (?<DN>Tue)(?:sday)?| + (?<DN>Wed)(?:nesday)?| + (?<DN>Thu)(?:rsday)?| + (?<DN>Sat)(?:urday)? +.sp +There are five capturing substrings, but only one is ever set after a match. +(An alternative way of solving this problem is to use a "branch reset" +subpattern, as described in the previous section.) +.P +The convenience function for extracting the data by name returns the substring +for the first (and in this example, the only) subpattern of that name that +matched. This saves searching to find which numbered subpattern it was. +.P +If you make a back reference to a non-unique named subpattern from elsewhere in +the pattern, the subpatterns to which the name refers are checked in the order +in which they appear in the overall pattern. The first one that is set is used +for the reference. For example, this pattern matches both "foofoo" and +"barbar" but not "foobar" or "barfoo": +.sp + (?:(?<n>foo)|(?<n>bar))\ek<n> +.sp +.P +If you make a subroutine call to a non-unique named subpattern, the one that +corresponds to the first occurrence of the name is used. In the absence of +duplicate numbers (see the previous section) this is the one with the lowest +number. +.P +If you use a named reference in a condition +test (see the +.\" +.\" HTML <a href="#conditions"> +.\" </a> +section about conditions +.\" +below), either to check whether a subpattern has matched, or to check for +recursion, all subpatterns with the same name are tested. If the condition is +true for any one of them, the overall condition is true. This is the same +behaviour as testing by number. For further details of the interfaces for +handling named subpatterns, see the +.\" HREF +\fBpcreapi\fP +.\" +documentation. +.P +\fBWarning:\fP You cannot use different names to distinguish between two +subpatterns with the same number because PCRE uses only the numbers when +matching. For this reason, an error is given at compile time if different names +are given to subpatterns with the same number. However, you can always give the +same name to subpatterns with the same number, even when PCRE_DUPNAMES is not +set. +. +. +.SH REPETITION +.rs +.sp +Repetition is specified by quantifiers, which can follow any of the following +items: +.sp + a literal data character + the dot metacharacter + the \eC escape sequence + the \eX escape sequence + the \eR escape sequence + an escape such as \ed or \epL that matches a single character + a character class + a back reference (see next section) + a parenthesized subpattern (including assertions) + a subroutine call to a subpattern (recursive or otherwise) +.sp +The general repetition quantifier specifies a minimum and maximum number of +permitted matches, by giving the two numbers in curly brackets (braces), +separated by a comma. The numbers must be less than 65536, and the first must +be less than or equal to the second. For example: +.sp + z{2,4} +.sp +matches "zz", "zzz", or "zzzz". A closing brace on its own is not a special +character. If the second number is omitted, but the comma is present, there is +no upper limit; if the second number and the comma are both omitted, the +quantifier specifies an exact number of required matches. Thus +.sp + [aeiou]{3,} +.sp +matches at least 3 successive vowels, but may match many more, while +.sp + \ed{8} +.sp +matches exactly 8 digits. An opening curly bracket that appears in a position +where a quantifier is not allowed, or one that does not match the syntax of a +quantifier, is taken as a literal character. For example, {,6} is not a +quantifier, but a literal string of four characters. +.P +In UTF modes, quantifiers apply to characters rather than to individual data +units. Thus, for example, \ex{100}{2} matches two characters, each of +which is represented by a two-byte sequence in a UTF-8 string. Similarly, +\eX{3} matches three Unicode extended grapheme clusters, each of which may be +several data units long (and they may be of different lengths). +.P +The quantifier {0} is permitted, causing the expression to behave as if the +previous item and the quantifier were not present. This may be useful for +subpatterns that are referenced as +.\" HTML <a href="#subpatternsassubroutines"> +.\" </a> +subroutines +.\" +from elsewhere in the pattern (but see also the section entitled +.\" HTML <a href="#subdefine"> +.\" </a> +"Defining subpatterns for use by reference only" +.\" +below). Items other than subpatterns that have a {0} quantifier are omitted +from the compiled pattern. +.P +For convenience, the three most common quantifiers have single-character +abbreviations: +.sp + * is equivalent to {0,} + + is equivalent to {1,} + ? is equivalent to {0,1} +.sp +It is possible to construct infinite loops by following a subpattern that can +match no characters with a quantifier that has no upper limit, for example: +.sp + (a?)* +.sp +Earlier versions of Perl and PCRE used to give an error at compile time for +such patterns. However, because there are cases where this can be useful, such +patterns are now accepted, but if any repetition of the subpattern does in fact +match no characters, the loop is forcibly broken. +.P +By default, the quantifiers are "greedy", that is, they match as much as +possible (up to the maximum number of permitted times), without causing the +rest of the pattern to fail. The classic example of where this gives problems +is in trying to match comments in C programs. These appear between /* and */ +and within the comment, individual * and / characters may appear. An attempt to +match C comments by applying the pattern +.sp + /\e*.*\e*/ +.sp +to the string +.sp + /* first comment */ not comment /* second comment */ +.sp +fails, because it matches the entire string owing to the greediness of the .* +item. +.P +However, if a quantifier is followed by a question mark, it ceases to be +greedy, and instead matches the minimum number of times possible, so the +pattern +.sp + /\e*.*?\e*/ +.sp +does the right thing with the C comments. The meaning of the various +quantifiers is not otherwise changed, just the preferred number of matches. +Do not confuse this use of question mark with its use as a quantifier in its +own right. Because it has two uses, it can sometimes appear doubled, as in +.sp + \ed??\ed +.sp +which matches one digit by preference, but can match two if that is the only +way the rest of the pattern matches. +.P +If the PCRE_UNGREEDY option is set (an option that is not available in Perl), +the quantifiers are not greedy by default, but individual ones can be made +greedy by following them with a question mark. In other words, it inverts the +default behaviour. +.P +When a parenthesized subpattern is quantified with a minimum repeat count that +is greater than 1 or with a limited maximum, more memory is required for the +compiled pattern, in proportion to the size of the minimum or maximum. +.P +If a pattern starts with .* or .{0,} and the PCRE_DOTALL option (equivalent +to Perl's /s) is set, thus allowing the dot to match newlines, the pattern is +implicitly anchored, because whatever follows will be tried against every +character position in the subject string, so there is no point in retrying the +overall match at any position after the first. PCRE normally treats such a +pattern as though it were preceded by \eA. +.P +In cases where it is known that the subject string contains no newlines, it is +worth setting PCRE_DOTALL in order to obtain this optimization, or +alternatively using ^ to indicate anchoring explicitly. +.P +However, there are some cases where the optimization cannot be used. When .* +is inside capturing parentheses that are the subject of a back reference +elsewhere in the pattern, a match at the start may fail where a later one +succeeds. Consider, for example: +.sp + (.*)abc\e1 +.sp +If the subject is "xyz123abc123" the match point is the fourth character. For +this reason, such a pattern is not implicitly anchored. +.P +Another case where implicit anchoring is not applied is when the leading .* is +inside an atomic group. Once again, a match at the start may fail where a later +one succeeds. Consider this pattern: +.sp + (?>.*?a)b +.sp +It matches "ab" in the subject "aab". The use of the backtracking control verbs +(*PRUNE) and (*SKIP) also disable this optimization. +.P +When a capturing subpattern is repeated, the value captured is the substring +that matched the final iteration. For example, after +.sp + (tweedle[dume]{3}\es*)+ +.sp +has matched "tweedledum tweedledee" the value of the captured substring is +"tweedledee". However, if there are nested capturing subpatterns, the +corresponding captured values may have been set in previous iterations. For +example, after +.sp + /(a|(b))+/ +.sp +matches "aba" the value of the second captured substring is "b". +. +. +.\" HTML <a name="atomicgroup"></a> +.SH "ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS" +.rs +.sp +With both maximizing ("greedy") and minimizing ("ungreedy" or "lazy") +repetition, failure of what follows normally causes the repeated item to be +re-evaluated to see if a different number of repeats allows the rest of the +pattern to match. Sometimes it is useful to prevent this, either to change the +nature of the match, or to cause it fail earlier than it otherwise might, when +the author of the pattern knows there is no point in carrying on. +.P +Consider, for example, the pattern \ed+foo when applied to the subject line +.sp + 123456bar +.sp +After matching all 6 digits and then failing to match "foo", the normal +action of the matcher is to try again with only 5 digits matching the \ed+ +item, and then with 4, and so on, before ultimately failing. "Atomic grouping" +(a term taken from Jeffrey Friedl's book) provides the means for specifying +that once a subpattern has matched, it is not to be re-evaluated in this way. +.P +If we use atomic grouping for the previous example, the matcher gives up +immediately on failing to match "foo" the first time. The notation is a kind of +special parenthesis, starting with (?> as in this example: +.sp + (?>\ed+)foo +.sp +This kind of parenthesis "locks up" the part of the pattern it contains once +it has matched, and a failure further into the pattern is prevented from +backtracking into it. Backtracking past it to previous items, however, works as +normal. +.P +An alternative description is that a subpattern of this type matches the string +of characters that an identical standalone pattern would match, if anchored at +the current point in the subject string. +.P +Atomic grouping subpatterns are not capturing subpatterns. Simple cases such as +the above example can be thought of as a maximizing repeat that must swallow +everything it can. So, while both \ed+ and \ed+? are prepared to adjust the +number of digits they match in order to make the rest of the pattern match, +(?>\ed+) can only match an entire sequence of digits. +.P +Atomic groups in general can of course contain arbitrarily complicated +subpatterns, and can be nested. However, when the subpattern for an atomic +group is just a single repeated item, as in the example above, a simpler +notation, called a "possessive quantifier" can be used. This consists of an +additional + character following a quantifier. Using this notation, the +previous example can be rewritten as +.sp + \ed++foo +.sp +Note that a possessive quantifier can be used with an entire group, for +example: +.sp + (abc|xyz){2,3}+ +.sp +Possessive quantifiers are always greedy; the setting of the PCRE_UNGREEDY +option is ignored. They are a convenient notation for the simpler forms of +atomic group. However, there is no difference in the meaning of a possessive +quantifier and the equivalent atomic group, though there may be a performance +difference; possessive quantifiers should be slightly faster. +.P +The possessive quantifier syntax is an extension to the Perl 5.8 syntax. +Jeffrey Friedl originated the idea (and the name) in the first edition of his +book. Mike McCloskey liked it, so implemented it when he built Sun's Java +package, and PCRE copied it from there. It ultimately found its way into Perl +at release 5.10. +.P +PCRE has an optimization that automatically "possessifies" certain simple +pattern constructs. For example, the sequence A+B is treated as A++B because +there is no point in backtracking into a sequence of A's when B must follow. +.P +When a pattern contains an unlimited repeat inside a subpattern that can itself +be repeated an unlimited number of times, the use of an atomic group is the +only way to avoid some failing matches taking a very long time indeed. The +pattern +.sp + (\eD+|<\ed+>)*[!?] +.sp +matches an unlimited number of substrings that either consist of non-digits, or +digits enclosed in <>, followed by either ! or ?. When it matches, it runs +quickly. However, if it is applied to +.sp + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +.sp +it takes a long time before reporting failure. This is because the string can +be divided between the internal \eD+ repeat and the external * repeat in a +large number of ways, and all have to be tried. (The example uses [!?] rather +than a single character at the end, because both PCRE and Perl have an +optimization that allows for fast failure when a single character is used. They +remember the last single character that is required for a match, and fail early +if it is not present in the string.) If the pattern is changed so that it uses +an atomic group, like this: +.sp + ((?>\eD+)|<\ed+>)*[!?] +.sp +sequences of non-digits cannot be broken, and failure happens quickly. +. +. +.\" HTML <a name="backreferences"></a> +.SH "BACK REFERENCES" +.rs +.sp +Outside a character class, a backslash followed by a digit greater than 0 (and +possibly further digits) is a back reference to a capturing subpattern earlier +(that is, to its left) in the pattern, provided there have been that many +previous capturing left parentheses. +.P +However, if the decimal number following the backslash is less than 10, it is +always taken as a back reference, and causes an error only if there are not +that many capturing left parentheses in the entire pattern. In other words, the +parentheses that are referenced need not be to the left of the reference for +numbers less than 10. A "forward back reference" of this type can make sense +when a repetition is involved and the subpattern to the right has participated +in an earlier iteration. +.P +It is not possible to have a numerical "forward back reference" to a subpattern +whose number is 10 or more using this syntax because a sequence such as \e50 is +interpreted as a character defined in octal. See the subsection entitled +"Non-printing characters" +.\" HTML <a href="#digitsafterbackslash"> +.\" </a> +above +.\" +for further details of the handling of digits following a backslash. There is +no such problem when named parentheses are used. A back reference to any +subpattern is possible using named parentheses (see below). +.P +Another way of avoiding the ambiguity inherent in the use of digits following a +backslash is to use the \eg escape sequence. This escape must be followed by an +unsigned number or a negative number, optionally enclosed in braces. These +examples are all identical: +.sp + (ring), \e1 + (ring), \eg1 + (ring), \eg{1} +.sp +An unsigned number specifies an absolute reference without the ambiguity that +is present in the older syntax. It is also useful when literal digits follow +the reference. A negative number is a relative reference. Consider this +example: +.sp + (abc(def)ghi)\eg{-1} +.sp +The sequence \eg{-1} is a reference to the most recently started capturing +subpattern before \eg, that is, is it equivalent to \e2 in this example. +Similarly, \eg{-2} would be equivalent to \e1. The use of relative references +can be helpful in long patterns, and also in patterns that are created by +joining together fragments that contain references within themselves. +.P +A back reference matches whatever actually matched the capturing subpattern in +the current subject string, rather than anything matching the subpattern +itself (see +.\" HTML <a href="#subpatternsassubroutines"> +.\" </a> +"Subpatterns as subroutines" +.\" +below for a way of doing that). So the pattern +.sp + (sens|respons)e and \e1ibility +.sp +matches "sense and sensibility" and "response and responsibility", but not +"sense and responsibility". If caseful matching is in force at the time of the +back reference, the case of letters is relevant. For example, +.sp + ((?i)rah)\es+\e1 +.sp +matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original +capturing subpattern is matched caselessly. +.P +There are several different ways of writing back references to named +subpatterns. The .NET syntax \ek{name} and the Perl syntax \ek<name> or +\ek'name' are supported, as is the Python syntax (?P=name). Perl 5.10's unified +back reference syntax, in which \eg can be used for both numeric and named +references, is also supported. We could rewrite the above example in any of +the following ways: +.sp + (?<p1>(?i)rah)\es+\ek<p1> + (?'p1'(?i)rah)\es+\ek{p1} + (?P<p1>(?i)rah)\es+(?P=p1) + (?<p1>(?i)rah)\es+\eg{p1} +.sp +A subpattern that is referenced by name may appear in the pattern before or +after the reference. +.P +There may be more than one back reference to the same subpattern. If a +subpattern has not actually been used in a particular match, any back +references to it always fail by default. For example, the pattern +.sp + (a|(bc))\e2 +.sp +always fails if it starts to match "a" rather than "bc". However, if the +PCRE_JAVASCRIPT_COMPAT option is set at compile time, a back reference to an +unset value matches an empty string. +.P +Because there may be many capturing parentheses in a pattern, all digits +following a backslash are taken as part of a potential back reference number. +If the pattern continues with a digit character, some delimiter must be used to +terminate the back reference. If the PCRE_EXTENDED option is set, this can be +white space. Otherwise, the \eg{ syntax or an empty comment (see +.\" HTML <a href="#comments"> +.\" </a> +"Comments" +.\" +below) can be used. +. +.SS "Recursive back references" +.rs +.sp +A back reference that occurs inside the parentheses to which it refers fails +when the subpattern is first used, so, for example, (a\e1) never matches. +However, such references can be useful inside repeated subpatterns. For +example, the pattern +.sp + (a|b\e1)+ +.sp +matches any number of "a"s and also "aba", "ababbaa" etc. At each iteration of +the subpattern, the back reference matches the character string corresponding +to the previous iteration. In order for this to work, the pattern must be such +that the first iteration does not need to match the back reference. This can be +done using alternation, as in the example above, or by a quantifier with a +minimum of zero. +.P +Back references of this type cause the group that they reference to be treated +as an +.\" HTML <a href="#atomicgroup"> +.\" </a> +atomic group. +.\" +Once the whole group has been matched, a subsequent matching failure cannot +cause backtracking into the middle of the group. +. +. +.\" HTML <a name="bigassertions"></a> +.SH ASSERTIONS +.rs +.sp +An assertion is a test on the characters following or preceding the current +matching point that does not actually consume any characters. The simple +assertions coded as \eb, \eB, \eA, \eG, \eZ, \ez, ^ and $ are described +.\" HTML <a href="#smallassertions"> +.\" </a> +above. +.\" +.P +More complicated assertions are coded as subpatterns. There are two kinds: +those that look ahead of the current position in the subject string, and those +that look behind it. An assertion subpattern is matched in the normal way, +except that it does not cause the current matching position to be changed. +.P +Assertion subpatterns are not capturing subpatterns. If such an assertion +contains capturing subpatterns within it, these are counted for the purposes of +numbering the capturing subpatterns in the whole pattern. However, substring +capturing is carried out only for positive assertions. (Perl sometimes, but not +always, does do capturing in negative assertions.) +.P +For compatibility with Perl, assertion subpatterns may be repeated; though +it makes no sense to assert the same thing several times, the side effect of +capturing parentheses may occasionally be useful. In practice, there only three +cases: +.sp +(1) If the quantifier is {0}, the assertion is never obeyed during matching. +However, it may contain internal capturing parenthesized groups that are called +from elsewhere via the +.\" HTML <a href="#subpatternsassubroutines"> +.\" </a> +subroutine mechanism. +.\" +.sp +(2) If quantifier is {0,n} where n is greater than zero, it is treated as if it +were {0,1}. At run time, the rest of the pattern match is tried with and +without the assertion, the order depending on the greediness of the quantifier. +.sp +(3) If the minimum repetition is greater than zero, the quantifier is ignored. +The assertion is obeyed just once when encountered during matching. +. +. +.SS "Lookahead assertions" +.rs +.sp +Lookahead assertions start with (?= for positive assertions and (?! for +negative assertions. For example, +.sp + \ew+(?=;) +.sp +matches a word followed by a semicolon, but does not include the semicolon in +the match, and +.sp + foo(?!bar) +.sp +matches any occurrence of "foo" that is not followed by "bar". Note that the +apparently similar pattern +.sp + (?!foo)bar +.sp +does not find an occurrence of "bar" that is preceded by something other than +"foo"; it finds any occurrence of "bar" whatsoever, because the assertion +(?!foo) is always true when the next three characters are "bar". A +lookbehind assertion is needed to achieve the other effect. +.P +If you want to force a matching failure at some point in a pattern, the most +convenient way to do it is with (?!) because an empty string always matches, so +an assertion that requires there not to be an empty string must always fail. +The backtracking control verb (*FAIL) or (*F) is a synonym for (?!). +. +. +.\" HTML <a name="lookbehind"></a> +.SS "Lookbehind assertions" +.rs +.sp +Lookbehind assertions start with (?<= for positive assertions and (?<! for +negative assertions. For example, +.sp + (?<!foo)bar +.sp +does find an occurrence of "bar" that is not preceded by "foo". The contents of +a lookbehind assertion are restricted such that all the strings it matches must +have a fixed length. However, if there are several top-level alternatives, they +do not all have to have the same fixed length. Thus +.sp + (?<=bullock|donkey) +.sp +is permitted, but +.sp + (?<!dogs?|cats?) +.sp +causes an error at compile time. Branches that match different length strings +are permitted only at the top level of a lookbehind assertion. This is an +extension compared with Perl, which requires all branches to match the same +length of string. An assertion such as +.sp + (?<=ab(c|de)) +.sp +is not permitted, because its single top-level branch can match two different +lengths, but it is acceptable to PCRE if rewritten to use two top-level +branches: +.sp + (?<=abc|abde) +.sp +In some cases, the escape sequence \eK +.\" HTML <a href="#resetmatchstart"> +.\" </a> +(see above) +.\" +can be used instead of a lookbehind assertion to get round the fixed-length +restriction. +.P +The implementation of lookbehind assertions is, for each alternative, to +temporarily move the current position back by the fixed length and then try to +match. If there are insufficient characters before the current position, the +assertion fails. +.P +In a UTF mode, PCRE does not allow the \eC escape (which matches a single data +unit even in a UTF mode) to appear in lookbehind assertions, because it makes +it impossible to calculate the length of the lookbehind. The \eX and \eR +escapes, which can match different numbers of data units, are also not +permitted. +.P +.\" HTML <a href="#subpatternsassubroutines"> +.\" </a> +"Subroutine" +.\" +calls (see below) such as (?2) or (?&X) are permitted in lookbehinds, as long +as the subpattern matches a fixed-length string. +.\" HTML <a href="#recursion"> +.\" </a> +Recursion, +.\" +however, is not supported. +.P +Possessive quantifiers can be used in conjunction with lookbehind assertions to +specify efficient matching of fixed-length strings at the end of subject +strings. Consider a simple pattern such as +.sp + abcd$ +.sp +when applied to a long string that does not match. Because matching proceeds +from left to right, PCRE will look for each "a" in the subject and then see if +what follows matches the rest of the pattern. If the pattern is specified as +.sp + ^.*abcd$ +.sp +the initial .* matches the entire string at first, but when this fails (because +there is no following "a"), it backtracks to match all but the last character, +then all but the last two characters, and so on. Once again the search for "a" +covers the entire string, from right to left, so we are no better off. However, +if the pattern is written as +.sp + ^.*+(?<=abcd) +.sp +there can be no backtracking for the .*+ item; it can match only the entire +string. The subsequent lookbehind assertion does a single test on the last four +characters. If it fails, the match fails immediately. For long strings, this +approach makes a significant difference to the processing time. +. +. +.SS "Using multiple assertions" +.rs +.sp +Several assertions (of any sort) may occur in succession. For example, +.sp + (?<=\ed{3})(?<!999)foo +.sp +matches "foo" preceded by three digits that are not "999". Notice that each of +the assertions is applied independently at the same point in the subject +string. First there is a check that the previous three characters are all +digits, and then there is a check that the same three characters are not "999". +This pattern does \fInot\fP match "foo" preceded by six characters, the first +of which are digits and the last three of which are not "999". For example, it +doesn't match "123abcfoo". A pattern to do that is +.sp + (?<=\ed{3}...)(?<!999)foo +.sp +This time the first assertion looks at the preceding six characters, checking +that the first three are digits, and then the second assertion checks that the +preceding three characters are not "999". +.P +Assertions can be nested in any combination. For example, +.sp + (?<=(?<!foo)bar)baz +.sp +matches an occurrence of "baz" that is preceded by "bar" which in turn is not +preceded by "foo", while +.sp + (?<=\ed{3}(?!999)...)foo +.sp +is another pattern that matches "foo" preceded by three digits and any three +characters that are not "999". +. +. +.\" HTML <a name="conditions"></a> +.SH "CONDITIONAL SUBPATTERNS" +.rs +.sp +It is possible to cause the matching process to obey a subpattern +conditionally or to choose between two alternative subpatterns, depending on +the result of an assertion, or whether a specific capturing subpattern has +already been matched. The two possible forms of conditional subpattern are: +.sp + (?(condition)yes-pattern) + (?(condition)yes-pattern|no-pattern) +.sp +If the condition is satisfied, the yes-pattern is used; otherwise the +no-pattern (if present) is used. If there are more than two alternatives in the +subpattern, a compile-time error occurs. Each of the two alternatives may +itself contain nested subpatterns of any form, including conditional +subpatterns; the restriction to two alternatives applies only at the level of +the condition. This pattern fragment is an example where the alternatives are +complex: +.sp + (?(1) (A|B|C) | (D | (?(2)E|F) | E) ) +.sp +.P +There are four kinds of condition: references to subpatterns, references to +recursion, a pseudo-condition called DEFINE, and assertions. +. +.SS "Checking for a used subpattern by number" +.rs +.sp +If the text between the parentheses consists of a sequence of digits, the +condition is true if a capturing subpattern of that number has previously +matched. If there is more than one capturing subpattern with the same number +(see the earlier +.\" +.\" HTML <a href="#recursion"> +.\" </a> +section about duplicate subpattern numbers), +.\" +the condition is true if any of them have matched. An alternative notation is +to precede the digits with a plus or minus sign. In this case, the subpattern +number is relative rather than absolute. The most recently opened parentheses +can be referenced by (?(-1), the next most recent by (?(-2), and so on. Inside +loops it can also make sense to refer to subsequent groups. The next +parentheses to be opened can be referenced as (?(+1), and so on. (The value +zero in any of these forms is not used; it provokes a compile-time error.) +.P +Consider the following pattern, which contains non-significant white space to +make it more readable (assume the PCRE_EXTENDED option) and to divide it into +three parts for ease of discussion: +.sp + ( \e( )? [^()]+ (?(1) \e) ) +.sp +The first part matches an optional opening parenthesis, and if that +character is present, sets it as the first captured substring. The second part +matches one or more characters that are not parentheses. The third part is a +conditional subpattern that tests whether or not the first set of parentheses +matched. If they did, that is, if subject started with an opening parenthesis, +the condition is true, and so the yes-pattern is executed and a closing +parenthesis is required. Otherwise, since no-pattern is not present, the +subpattern matches nothing. In other words, this pattern matches a sequence of +non-parentheses, optionally enclosed in parentheses. +.P +If you were embedding this pattern in a larger one, you could use a relative +reference: +.sp + ...other stuff... ( \e( )? [^()]+ (?(-1) \e) ) ... +.sp +This makes the fragment independent of the parentheses in the larger pattern. +. +.SS "Checking for a used subpattern by name" +.rs +.sp +Perl uses the syntax (?(<name>)...) or (?('name')...) to test for a used +subpattern by name. For compatibility with earlier versions of PCRE, which had +this facility before Perl, the syntax (?(name)...) is also recognized. +.P +Rewriting the above example to use a named subpattern gives this: +.sp + (?<OPEN> \e( )? [^()]+ (?(<OPEN>) \e) ) +.sp +If the name used in a condition of this kind is a duplicate, the test is +applied to all subpatterns of the same name, and is true if any one of them has +matched. +. +.SS "Checking for pattern recursion" +.rs +.sp +If the condition is the string (R), and there is no subpattern with the name R, +the condition is true if a recursive call to the whole pattern or any +subpattern has been made. If digits or a name preceded by ampersand follow the +letter R, for example: +.sp + (?(R3)...) or (?(R&name)...) +.sp +the condition is true if the most recent recursion is into a subpattern whose +number or name is given. This condition does not check the entire recursion +stack. If the name used in a condition of this kind is a duplicate, the test is +applied to all subpatterns of the same name, and is true if any one of them is +the most recent recursion. +.P +At "top level", all these recursion test conditions are false. +.\" HTML <a href="#recursion"> +.\" </a> +The syntax for recursive patterns +.\" +is described below. +. +.\" HTML <a name="subdefine"></a> +.SS "Defining subpatterns for use by reference only" +.rs +.sp +If the condition is the string (DEFINE), and there is no subpattern with the +name DEFINE, the condition is always false. In this case, there may be only one +alternative in the subpattern. It is always skipped if control reaches this +point in the pattern; the idea of DEFINE is that it can be used to define +subroutines that can be referenced from elsewhere. (The use of +.\" HTML <a href="#subpatternsassubroutines"> +.\" </a> +subroutines +.\" +is described below.) For example, a pattern to match an IPv4 address such as +"192.168.23.245" could be written like this (ignore white space and line +breaks): +.sp + (?(DEFINE) (?<byte> 2[0-4]\ed | 25[0-5] | 1\ed\ed | [1-9]?\ed) ) + \eb (?&byte) (\e.(?&byte)){3} \eb +.sp +The first part of the pattern is a DEFINE group inside which a another group +named "byte" is defined. This matches an individual component of an IPv4 +address (a number less than 256). When matching takes place, this part of the +pattern is skipped because DEFINE acts like a false condition. The rest of the +pattern uses references to the named group to match the four dot-separated +components of an IPv4 address, insisting on a word boundary at each end. +. +.SS "Assertion conditions" +.rs +.sp +If the condition is not in any of the above formats, it must be an assertion. +This may be a positive or negative lookahead or lookbehind assertion. Consider +this pattern, again containing non-significant white space, and with the two +alternatives on the second line: +.sp + (?(?=[^a-z]*[a-z]) + \ed{2}-[a-z]{3}-\ed{2} | \ed{2}-\ed{2}-\ed{2} ) +.sp +The condition is a positive lookahead assertion that matches an optional +sequence of non-letters followed by a letter. In other words, it tests for the +presence of at least one letter in the subject. If a letter is found, the +subject is matched against the first alternative; otherwise it is matched +against the second. This pattern matches strings in one of the two forms +dd-aaa-dd or dd-dd-dd, where aaa are letters and dd are digits. +. +. +.\" HTML <a name="comments"></a> +.SH COMMENTS +.rs +.sp +There are two ways of including comments in patterns that are processed by +PCRE. In both cases, the start of the comment must not be in a character class, +nor in the middle of any other sequence of related characters such as (?: or a +subpattern name or number. The characters that make up a comment play no part +in the pattern matching. +.P +The sequence (?# marks the start of a comment that continues up to the next +closing parenthesis. Nested parentheses are not permitted. If the PCRE_EXTENDED +option is set, an unescaped # character also introduces a comment, which in +this case continues to immediately after the next newline character or +character sequence in the pattern. Which characters are interpreted as newlines +is controlled by the options passed to a compiling function or by a special +sequence at the start of the pattern, as described in the section entitled +.\" HTML <a href="#newlines"> +.\" </a> +"Newline conventions" +.\" +above. Note that the end of this type of comment is a literal newline sequence +in the pattern; escape sequences that happen to represent a newline do not +count. For example, consider this pattern when PCRE_EXTENDED is set, and the +default newline convention is in force: +.sp + abc #comment \en still comment +.sp +On encountering the # character, \fBpcre_compile()\fP skips along, looking for +a newline in the pattern. The sequence \en is still literal at this stage, so +it does not terminate the comment. Only an actual character with the code value +0x0a (the default newline) does so. +. +. +.\" HTML <a name="recursion"></a> +.SH "RECURSIVE PATTERNS" +.rs +.sp +Consider the problem of matching a string in parentheses, allowing for +unlimited nested parentheses. Without the use of recursion, the best that can +be done is to use a pattern that matches up to some fixed depth of nesting. It +is not possible to handle an arbitrary nesting depth. +.P +For some time, Perl has provided a facility that allows regular expressions to +recurse (amongst other things). It does this by interpolating Perl code in the +expression at run time, and the code can refer to the expression itself. A Perl +pattern using code interpolation to solve the parentheses problem can be +created like this: +.sp + $re = qr{\e( (?: (?>[^()]+) | (?p{$re}) )* \e)}x; +.sp +The (?p{...}) item interpolates Perl code at run time, and in this case refers +recursively to the pattern in which it appears. +.P +Obviously, PCRE cannot support the interpolation of Perl code. Instead, it +supports special syntax for recursion of the entire pattern, and also for +individual subpattern recursion. After its introduction in PCRE and Python, +this kind of recursion was subsequently introduced into Perl at release 5.10. +.P +A special item that consists of (? followed by a number greater than zero and a +closing parenthesis is a recursive subroutine call of the subpattern of the +given number, provided that it occurs inside that subpattern. (If not, it is a +.\" HTML <a href="#subpatternsassubroutines"> +.\" </a> +non-recursive subroutine +.\" +call, which is described in the next section.) The special item (?R) or (?0) is +a recursive call of the entire regular expression. +.P +This PCRE pattern solves the nested parentheses problem (assume the +PCRE_EXTENDED option is set so that white space is ignored): +.sp + \e( ( [^()]++ | (?R) )* \e) +.sp +First it matches an opening parenthesis. Then it matches any number of +substrings which can either be a sequence of non-parentheses, or a recursive +match of the pattern itself (that is, a correctly parenthesized substring). +Finally there is a closing parenthesis. Note the use of a possessive quantifier +to avoid backtracking into sequences of non-parentheses. +.P +If this were part of a larger pattern, you would not want to recurse the entire +pattern, so instead you could use this: +.sp + ( \e( ( [^()]++ | (?1) )* \e) ) +.sp +We have put the pattern into parentheses, and caused the recursion to refer to +them instead of the whole pattern. +.P +In a larger pattern, keeping track of parenthesis numbers can be tricky. This +is made easier by the use of relative references. Instead of (?1) in the +pattern above you can write (?-2) to refer to the second most recently opened +parentheses preceding the recursion. In other words, a negative number counts +capturing parentheses leftwards from the point at which it is encountered. +.P +It is also possible to refer to subsequently opened parentheses, by writing +references such as (?+2). However, these cannot be recursive because the +reference is not inside the parentheses that are referenced. They are always +.\" HTML <a href="#subpatternsassubroutines"> +.\" </a> +non-recursive subroutine +.\" +calls, as described in the next section. +.P +An alternative approach is to use named parentheses instead. The Perl syntax +for this is (?&name); PCRE's earlier syntax (?P>name) is also supported. We +could rewrite the above example as follows: +.sp + (?<pn> \e( ( [^()]++ | (?&pn) )* \e) ) +.sp +If there is more than one subpattern with the same name, the earliest one is +used. +.P +This particular example pattern that we have been looking at contains nested +unlimited repeats, and so the use of a possessive quantifier for matching +strings of non-parentheses is important when applying the pattern to strings +that do not match. For example, when this pattern is applied to +.sp + (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa() +.sp +it yields "no match" quickly. However, if a possessive quantifier is not used, +the match runs for a very long time indeed because there are so many different +ways the + and * repeats can carve up the subject, and all have to be tested +before failure can be reported. +.P +At the end of a match, the values of capturing parentheses are those from +the outermost level. If you want to obtain intermediate values, a callout +function can be used (see below and the +.\" HREF +\fBpcrecallout\fP +.\" +documentation). If the pattern above is matched against +.sp + (ab(cd)ef) +.sp +the value for the inner capturing parentheses (numbered 2) is "ef", which is +the last value taken on at the top level. If a capturing subpattern is not +matched at the top level, its final captured value is unset, even if it was +(temporarily) set at a deeper level during the matching process. +.P +If there are more than 15 capturing parentheses in a pattern, PCRE has to +obtain extra memory to store data during a recursion, which it does by using +\fBpcre_malloc\fP, freeing it via \fBpcre_free\fP afterwards. If no memory can +be obtained, the match fails with the PCRE_ERROR_NOMEMORY error. +.P +Do not confuse the (?R) item with the condition (R), which tests for recursion. +Consider this pattern, which matches text in angle brackets, allowing for +arbitrary nesting. Only digits are allowed in nested brackets (that is, when +recursing), whereas any characters are permitted at the outer level. +.sp + < (?: (?(R) \ed++ | [^<>]*+) | (?R)) * > +.sp +In this pattern, (?(R) is the start of a conditional subpattern, with two +different alternatives for the recursive and non-recursive cases. The (?R) item +is the actual recursive call. +. +. +.\" HTML <a name="recursiondifference"></a> +.SS "Differences in recursion processing between PCRE and Perl" +.rs +.sp +Recursion processing in PCRE differs from Perl in two important ways. In PCRE +(like Python, but unlike Perl), a recursive subpattern call is always treated +as an atomic group. That is, once it has matched some of the subject string, it +is never re-entered, even if it contains untried alternatives and there is a +subsequent matching failure. This can be illustrated by the following pattern, +which purports to match a palindromic string that contains an odd number of +characters (for example, "a", "aba", "abcba", "abcdcba"): +.sp + ^(.|(.)(?1)\e2)$ +.sp +The idea is that it either matches a single character, or two identical +characters surrounding a sub-palindrome. In Perl, this pattern works; in PCRE +it does not if the pattern is longer than three characters. Consider the +subject string "abcba": +.P +At the top level, the first character is matched, but as it is not at the end +of the string, the first alternative fails; the second alternative is taken +and the recursion kicks in. The recursive call to subpattern 1 successfully +matches the next character ("b"). (Note that the beginning and end of line +tests are not part of the recursion). +.P +Back at the top level, the next character ("c") is compared with what +subpattern 2 matched, which was "a". This fails. Because the recursion is +treated as an atomic group, there are now no backtracking points, and so the +entire match fails. (Perl is able, at this point, to re-enter the recursion and +try the second alternative.) However, if the pattern is written with the +alternatives in the other order, things are different: +.sp + ^((.)(?1)\e2|.)$ +.sp +This time, the recursing alternative is tried first, and continues to recurse +until it runs out of characters, at which point the recursion fails. But this +time we do have another alternative to try at the higher level. That is the big +difference: in the previous case the remaining alternative is at a deeper +recursion level, which PCRE cannot use. +.P +To change the pattern so that it matches all palindromic strings, not just +those with an odd number of characters, it is tempting to change the pattern to +this: +.sp + ^((.)(?1)\e2|.?)$ +.sp +Again, this works in Perl, but not in PCRE, and for the same reason. When a +deeper recursion has matched a single character, it cannot be entered again in +order to match an empty string. The solution is to separate the two cases, and +write out the odd and even cases as alternatives at the higher level: +.sp + ^(?:((.)(?1)\e2|)|((.)(?3)\e4|.)) +.sp +If you want to match typical palindromic phrases, the pattern has to ignore all +non-word characters, which can be done like this: +.sp + ^\eW*+(?:((.)\eW*+(?1)\eW*+\e2|)|((.)\eW*+(?3)\eW*+\e4|\eW*+.\eW*+))\eW*+$ +.sp +If run with the PCRE_CASELESS option, this pattern matches phrases such as "A +man, a plan, a canal: Panama!" and it works well in both PCRE and Perl. Note +the use of the possessive quantifier *+ to avoid backtracking into sequences of +non-word characters. Without this, PCRE takes a great deal longer (ten times or +more) to match typical phrases, and Perl takes so long that you think it has +gone into a loop. +.P +\fBWARNING\fP: The palindrome-matching patterns above work only if the subject +string does not start with a palindrome that is shorter than the entire string. +For example, although "abcba" is correctly matched, if the subject is "ababa", +PCRE finds the palindrome "aba" at the start, then fails at top level because +the end of the string does not follow. Once again, it cannot jump back into the +recursion to try other alternatives, so the entire match fails. +.P +The second way in which PCRE and Perl differ in their recursion processing is +in the handling of captured values. In Perl, when a subpattern is called +recursively or as a subpattern (see the next section), it has no access to any +values that were captured outside the recursion, whereas in PCRE these values +can be referenced. Consider this pattern: +.sp + ^(.)(\e1|a(?2)) +.sp +In PCRE, this pattern matches "bab". The first capturing parentheses match "b", +then in the second group, when the back reference \e1 fails to match "b", the +second alternative matches "a" and then recurses. In the recursion, \e1 does +now match "b" and so the whole match succeeds. In Perl, the pattern fails to +match because inside the recursive call \e1 cannot access the externally set +value. +. +. +.\" HTML <a name="subpatternsassubroutines"></a> +.SH "SUBPATTERNS AS SUBROUTINES" +.rs +.sp +If the syntax for a recursive subpattern call (either by number or by +name) is used outside the parentheses to which it refers, it operates like a +subroutine in a programming language. The called subpattern may be defined +before or after the reference. A numbered reference can be absolute or +relative, as in these examples: +.sp + (...(absolute)...)...(?2)... + (...(relative)...)...(?-1)... + (...(?+1)...(relative)... +.sp +An earlier example pointed out that the pattern +.sp + (sens|respons)e and \e1ibility +.sp +matches "sense and sensibility" and "response and responsibility", but not +"sense and responsibility". If instead the pattern +.sp + (sens|respons)e and (?1)ibility +.sp +is used, it does match "sense and responsibility" as well as the other two +strings. Another example is given in the discussion of DEFINE above. +.P +All subroutine calls, whether recursive or not, are always treated as atomic +groups. That is, once a subroutine has matched some of the subject string, it +is never re-entered, even if it contains untried alternatives and there is a +subsequent matching failure. Any capturing parentheses that are set during the +subroutine call revert to their previous values afterwards. +.P +Processing options such as case-independence are fixed when a subpattern is +defined, so if it is used as a subroutine, such options cannot be changed for +different calls. For example, consider this pattern: +.sp + (abc)(?i:(?-1)) +.sp +It matches "abcabc". It does not match "abcABC" because the change of +processing option does not affect the called subpattern. +. +. +.\" HTML <a name="onigurumasubroutines"></a> +.SH "ONIGURUMA SUBROUTINE SYNTAX" +.rs +.sp +For compatibility with Oniguruma, the non-Perl syntax \eg followed by a name or +a number enclosed either in angle brackets or single quotes, is an alternative +syntax for referencing a subpattern as a subroutine, possibly recursively. Here +are two of the examples used above, rewritten using this syntax: +.sp + (?<pn> \e( ( (?>[^()]+) | \eg<pn> )* \e) ) + (sens|respons)e and \eg'1'ibility +.sp +PCRE supports an extension to Oniguruma: if a number is preceded by a +plus or a minus sign it is taken as a relative reference. For example: +.sp + (abc)(?i:\eg<-1>) +.sp +Note that \eg{...} (Perl syntax) and \eg<...> (Oniguruma syntax) are \fInot\fP +synonymous. The former is a back reference; the latter is a subroutine call. +. +. +.SH CALLOUTS +.rs +.sp +Perl has a feature whereby using the sequence (?{...}) causes arbitrary Perl +code to be obeyed in the middle of matching a regular expression. This makes it +possible, amongst other things, to extract different substrings that match the +same pair of parentheses when there is a repetition. +.P +PCRE provides a similar feature, but of course it cannot obey arbitrary Perl +code. The feature is called "callout". The caller of PCRE provides an external +function by putting its entry point in the global variable \fIpcre_callout\fP +(8-bit library) or \fIpcre[16|32]_callout\fP (16-bit or 32-bit library). +By default, this variable contains NULL, which disables all calling out. +.P +Within a regular expression, (?C) indicates the points at which the external +function is to be called. If you want to identify different callout points, you +can put a number less than 256 after the letter C. The default value is zero. +For example, this pattern has two callout points: +.sp + (?C1)abc(?C2)def +.sp +If the PCRE_AUTO_CALLOUT flag is passed to a compiling function, callouts are +automatically installed before each item in the pattern. They are all numbered +255. If there is a conditional group in the pattern whose condition is an +assertion, an additional callout is inserted just before the condition. An +explicit callout may also be set at this position, as in this example: +.sp + (?(?C9)(?=a)abc|def) +.sp +Note that this applies only to assertion conditions, not to other types of +condition. +.P +During matching, when PCRE reaches a callout point, the external function is +called. It is provided with the number of the callout, the position in the +pattern, and, optionally, one item of data originally supplied by the caller of +the matching function. The callout function may cause matching to proceed, to +backtrack, or to fail altogether. +.P +By default, PCRE implements a number of optimizations at compile time and +matching time, and one side-effect is that sometimes callouts are skipped. If +you need all possible callouts to happen, you need to set options that disable +the relevant optimizations. More details, and a complete description of the +interface to the callout function, are given in the +.\" HREF +\fBpcrecallout\fP +.\" +documentation. +. +. +.\" HTML <a name="backtrackcontrol"></a> +.SH "BACKTRACKING CONTROL" +.rs +.sp +Perl 5.10 introduced a number of "Special Backtracking Control Verbs", which +are still described in the Perl documentation as "experimental and subject to +change or removal in a future version of Perl". It goes on to say: "Their usage +in production code should be noted to avoid problems during upgrades." The same +remarks apply to the PCRE features described in this section. +.P +The new verbs make use of what was previously invalid syntax: an opening +parenthesis followed by an asterisk. They are generally of the form +(*VERB) or (*VERB:NAME). Some may take either form, possibly behaving +differently depending on whether or not a name is present. A name is any +sequence of characters that does not include a closing parenthesis. The maximum +length of name is 255 in the 8-bit library and 65535 in the 16-bit and 32-bit +libraries. If the name is empty, that is, if the closing parenthesis +immediately follows the colon, the effect is as if the colon were not there. +Any number of these verbs may occur in a pattern. +.P +Since these verbs are specifically related to backtracking, most of them can be +used only when the pattern is to be matched using one of the traditional +matching functions, because these use a backtracking algorithm. With the +exception of (*FAIL), which behaves like a failing negative assertion, the +backtracking control verbs cause an error if encountered by a DFA matching +function. +.P +The behaviour of these verbs in +.\" HTML <a href="#btrepeat"> +.\" </a> +repeated groups, +.\" +.\" HTML <a href="#btassert"> +.\" </a> +assertions, +.\" +and in +.\" HTML <a href="#btsub"> +.\" </a> +subpatterns called as subroutines +.\" +(whether or not recursively) is documented below. +. +. +.\" HTML <a name="nooptimize"></a> +.SS "Optimizations that affect backtracking verbs" +.rs +.sp +PCRE contains some optimizations that are used to speed up matching by running +some checks at the start of each match attempt. For example, it may know the +minimum length of matching subject, or that a particular character must be +present. When one of these optimizations bypasses the running of a match, any +included backtracking verbs will not, of course, be processed. You can suppress +the start-of-match optimizations by setting the PCRE_NO_START_OPTIMIZE option +when calling \fBpcre_compile()\fP or \fBpcre_exec()\fP, or by starting the +pattern with (*NO_START_OPT). There is more discussion of this option in the +section entitled +.\" HTML <a href="pcreapi.html#execoptions"> +.\" </a> +"Option bits for \fBpcre_exec()\fP" +.\" +in the +.\" HREF +\fBpcreapi\fP +.\" +documentation. +.P +Experiments with Perl suggest that it too has similar optimizations, sometimes +leading to anomalous results. +. +. +.SS "Verbs that act immediately" +.rs +.sp +The following verbs act as soon as they are encountered. They may not be +followed by a name. +.sp + (*ACCEPT) +.sp +This verb causes the match to end successfully, skipping the remainder of the +pattern. However, when it is inside a subpattern that is called as a +subroutine, only that subpattern is ended successfully. Matching then continues +at the outer level. If (*ACCEPT) in triggered in a positive assertion, the +assertion succeeds; in a negative assertion, the assertion fails. +.P +If (*ACCEPT) is inside capturing parentheses, the data so far is captured. For +example: +.sp + A((?:A|B(*ACCEPT)|C)D) +.sp +This matches "AB", "AAD", or "ACD"; when it matches "AB", "B" is captured by +the outer parentheses. +.sp + (*FAIL) or (*F) +.sp +This verb causes a matching failure, forcing backtracking to occur. It is +equivalent to (?!) but easier to read. The Perl documentation notes that it is +probably useful only when combined with (?{}) or (??{}). Those are, of course, +Perl features that are not present in PCRE. The nearest equivalent is the +callout feature, as for example in this pattern: +.sp + a+(?C)(*FAIL) +.sp +A match with the string "aaaa" always fails, but the callout is taken before +each backtrack happens (in this example, 10 times). +. +. +.SS "Recording which path was taken" +.rs +.sp +There is one verb whose main purpose is to track how a match was arrived at, +though it also has a secondary use in conjunction with advancing the match +starting point (see (*SKIP) below). +.sp + (*MARK:NAME) or (*:NAME) +.sp +A name is always required with this verb. There may be as many instances of +(*MARK) as you like in a pattern, and their names do not have to be unique. +.P +When a match succeeds, the name of the last-encountered (*MARK:NAME), +(*PRUNE:NAME), or (*THEN:NAME) on the matching path is passed back to the +caller as described in the section entitled +.\" HTML <a href="pcreapi.html#extradata"> +.\" </a> +"Extra data for \fBpcre_exec()\fP" +.\" +in the +.\" HREF +\fBpcreapi\fP +.\" +documentation. Here is an example of \fBpcretest\fP output, where the /K +modifier requests the retrieval and outputting of (*MARK) data: +.sp + re> /X(*MARK:A)Y|X(*MARK:B)Z/K + data> XY + 0: XY + MK: A + XZ + 0: XZ + MK: B +.sp +The (*MARK) name is tagged with "MK:" in this output, and in this example it +indicates which of the two alternatives matched. This is a more efficient way +of obtaining this information than putting each alternative in its own +capturing parentheses. +.P +If a verb with a name is encountered in a positive assertion that is true, the +name is recorded and passed back if it is the last-encountered. This does not +happen for negative assertions or failing positive assertions. +.P +After a partial match or a failed match, the last encountered name in the +entire match process is returned. For example: +.sp + re> /X(*MARK:A)Y|X(*MARK:B)Z/K + data> XP + No match, mark = B +.sp +Note that in this unanchored example the mark is retained from the match +attempt that started at the letter "X" in the subject. Subsequent match +attempts starting at "P" and then with an empty string do not get as far as the +(*MARK) item, but nevertheless do not reset it. +.P +If you are interested in (*MARK) values after failed matches, you should +probably set the PCRE_NO_START_OPTIMIZE option +.\" HTML <a href="#nooptimize"> +.\" </a> +(see above) +.\" +to ensure that the match is always attempted. +. +. +.SS "Verbs that act after backtracking" +.rs +.sp +The following verbs do nothing when they are encountered. Matching continues +with what follows, but if there is no subsequent match, causing a backtrack to +the verb, a failure is forced. That is, backtracking cannot pass to the left of +the verb. However, when one of these verbs appears inside an atomic group or an +assertion that is true, its effect is confined to that group, because once the +group has been matched, there is never any backtracking into it. In this +situation, backtracking can "jump back" to the left of the entire atomic group +or assertion. (Remember also, as stated above, that this localization also +applies in subroutine calls.) +.P +These verbs differ in exactly what kind of failure occurs when backtracking +reaches them. The behaviour described below is what happens when the verb is +not in a subroutine or an assertion. Subsequent sections cover these special +cases. +.sp + (*COMMIT) +.sp +This verb, which may not be followed by a name, causes the whole match to fail +outright if there is a later matching failure that causes backtracking to reach +it. Even if the pattern is unanchored, no further attempts to find a match by +advancing the starting point take place. If (*COMMIT) is the only backtracking +verb that is encountered, once it has been passed \fBpcre_exec()\fP is +committed to finding a match at the current starting point, or not at all. For +example: +.sp + a+(*COMMIT)b +.sp +This matches "xxaab" but not "aacaab". It can be thought of as a kind of +dynamic anchor, or "I've started, so I must finish." The name of the most +recently passed (*MARK) in the path is passed back when (*COMMIT) forces a +match failure. +.P +If there is more than one backtracking verb in a pattern, a different one that +follows (*COMMIT) may be triggered first, so merely passing (*COMMIT) during a +match does not always guarantee that a match must be at this starting point. +.P +Note that (*COMMIT) at the start of a pattern is not the same as an anchor, +unless PCRE's start-of-match optimizations are turned off, as shown in this +output from \fBpcretest\fP: +.sp + re> /(*COMMIT)abc/ + data> xyzabc + 0: abc + data> xyzabc\eY + No match +.sp +For this pattern, PCRE knows that any match must start with "a", so the +optimization skips along the subject to "a" before applying the pattern to the +first set of data. The match attempt then succeeds. In the second set of data, +the escape sequence \eY is interpreted by the \fBpcretest\fP program. It causes +the PCRE_NO_START_OPTIMIZE option to be set when \fBpcre_exec()\fP is called. +This disables the optimization that skips along to the first character. The +pattern is now applied starting at "x", and so the (*COMMIT) causes the match +to fail without trying any other starting points. +.sp + (*PRUNE) or (*PRUNE:NAME) +.sp +This verb causes the match to fail at the current starting position in the +subject if there is a later matching failure that causes backtracking to reach +it. If the pattern is unanchored, the normal "bumpalong" advance to the next +starting character then happens. Backtracking can occur as usual to the left of +(*PRUNE), before it is reached, or when matching to the right of (*PRUNE), but +if there is no match to the right, backtracking cannot cross (*PRUNE). In +simple cases, the use of (*PRUNE) is just an alternative to an atomic group or +possessive quantifier, but there are some uses of (*PRUNE) that cannot be +expressed in any other way. In an anchored pattern (*PRUNE) has the same effect +as (*COMMIT). +.P +The behaviour of (*PRUNE:NAME) is the not the same as (*MARK:NAME)(*PRUNE). +It is like (*MARK:NAME) in that the name is remembered for passing back to the +caller. However, (*SKIP:NAME) searches only for names set with (*MARK). +.sp + (*SKIP) +.sp +This verb, when given without a name, is like (*PRUNE), except that if the +pattern is unanchored, the "bumpalong" advance is not to the next character, +but to the position in the subject where (*SKIP) was encountered. (*SKIP) +signifies that whatever text was matched leading up to it cannot be part of a +successful match. Consider: +.sp + a+(*SKIP)b +.sp +If the subject is "aaaac...", after the first match attempt fails (starting at +the first character in the string), the starting point skips on to start the +next attempt at "c". Note that a possessive quantifer does not have the same +effect as this example; although it would suppress backtracking during the +first match attempt, the second attempt would start at the second character +instead of skipping on to "c". +.sp + (*SKIP:NAME) +.sp +When (*SKIP) has an associated name, its behaviour is modified. When it is +triggered, the previous path through the pattern is searched for the most +recent (*MARK) that has the same name. If one is found, the "bumpalong" advance +is to the subject position that corresponds to that (*MARK) instead of to where +(*SKIP) was encountered. If no (*MARK) with a matching name is found, the +(*SKIP) is ignored. +.P +Note that (*SKIP:NAME) searches only for names set by (*MARK:NAME). It ignores +names that are set by (*PRUNE:NAME) or (*THEN:NAME). +.sp + (*THEN) or (*THEN:NAME) +.sp +This verb causes a skip to the next innermost alternative when backtracking +reaches it. That is, it cancels any further backtracking within the current +alternative. Its name comes from the observation that it can be used for a +pattern-based if-then-else block: +.sp + ( COND1 (*THEN) FOO | COND2 (*THEN) BAR | COND3 (*THEN) BAZ ) ... +.sp +If the COND1 pattern matches, FOO is tried (and possibly further items after +the end of the group if FOO succeeds); on failure, the matcher skips to the +second alternative and tries COND2, without backtracking into COND1. If that +succeeds and BAR fails, COND3 is tried. If subsequently BAZ fails, there are no +more alternatives, so there is a backtrack to whatever came before the entire +group. If (*THEN) is not inside an alternation, it acts like (*PRUNE). +.P +The behaviour of (*THEN:NAME) is the not the same as (*MARK:NAME)(*THEN). +It is like (*MARK:NAME) in that the name is remembered for passing back to the +caller. However, (*SKIP:NAME) searches only for names set with (*MARK). +.P +A subpattern that does not contain a | character is just a part of the +enclosing alternative; it is not a nested alternation with only one +alternative. The effect of (*THEN) extends beyond such a subpattern to the +enclosing alternative. Consider this pattern, where A, B, etc. are complex +pattern fragments that do not contain any | characters at this level: +.sp + A (B(*THEN)C) | D +.sp +If A and B are matched, but there is a failure in C, matching does not +backtrack into A; instead it moves to the next alternative, that is, D. +However, if the subpattern containing (*THEN) is given an alternative, it +behaves differently: +.sp + A (B(*THEN)C | (*FAIL)) | D +.sp +The effect of (*THEN) is now confined to the inner subpattern. After a failure +in C, matching moves to (*FAIL), which causes the whole subpattern to fail +because there are no more alternatives to try. In this case, matching does now +backtrack into A. +.P +Note that a conditional subpattern is not considered as having two +alternatives, because only one is ever used. In other words, the | character in +a conditional subpattern has a different meaning. Ignoring white space, +consider: +.sp + ^.*? (?(?=a) a | b(*THEN)c ) +.sp +If the subject is "ba", this pattern does not match. Because .*? is ungreedy, +it initially matches zero characters. The condition (?=a) then fails, the +character "b" is matched, but "c" is not. At this point, matching does not +backtrack to .*? as might perhaps be expected from the presence of the | +character. The conditional subpattern is part of the single alternative that +comprises the whole pattern, and so the match fails. (If there was a backtrack +into .*?, allowing it to match "b", the match would succeed.) +.P +The verbs just described provide four different "strengths" of control when +subsequent matching fails. (*THEN) is the weakest, carrying on the match at the +next alternative. (*PRUNE) comes next, failing the match at the current +starting position, but allowing an advance to the next character (for an +unanchored pattern). (*SKIP) is similar, except that the advance may be more +than one character. (*COMMIT) is the strongest, causing the entire match to +fail. +. +. +.SS "More than one backtracking verb" +.rs +.sp +If more than one backtracking verb is present in a pattern, the one that is +backtracked onto first acts. For example, consider this pattern, where A, B, +etc. are complex pattern fragments: +.sp + (A(*COMMIT)B(*THEN)C|ABD) +.sp +If A matches but B fails, the backtrack to (*COMMIT) causes the entire match to +fail. However, if A and B match, but C fails, the backtrack to (*THEN) causes +the next alternative (ABD) to be tried. This behaviour is consistent, but is +not always the same as Perl's. It means that if two or more backtracking verbs +appear in succession, all the the last of them has no effect. Consider this +example: +.sp + ...(*COMMIT)(*PRUNE)... +.sp +If there is a matching failure to the right, backtracking onto (*PRUNE) causes +it to be triggered, and its action is taken. There can never be a backtrack +onto (*COMMIT). +. +. +.\" HTML <a name="btrepeat"></a> +.SS "Backtracking verbs in repeated groups" +.rs +.sp +PCRE differs from Perl in its handling of backtracking verbs in repeated +groups. For example, consider: +.sp + /(a(*COMMIT)b)+ac/ +.sp +If the subject is "abac", Perl matches, but PCRE fails because the (*COMMIT) in +the second repeat of the group acts. +. +. +.\" HTML <a name="btassert"></a> +.SS "Backtracking verbs in assertions" +.rs +.sp +(*FAIL) in an assertion has its normal effect: it forces an immediate backtrack. +.P +(*ACCEPT) in a positive assertion causes the assertion to succeed without any +further processing. In a negative assertion, (*ACCEPT) causes the assertion to +fail without any further processing. +.P +The other backtracking verbs are not treated specially if they appear in a +positive assertion. In particular, (*THEN) skips to the next alternative in the +innermost enclosing group that has alternations, whether or not this is within +the assertion. +.P +Negative assertions are, however, different, in order to ensure that changing a +positive assertion into a negative assertion changes its result. Backtracking +into (*COMMIT), (*SKIP), or (*PRUNE) causes a negative assertion to be true, +without considering any further alternative branches in the assertion. +Backtracking into (*THEN) causes it to skip to the next enclosing alternative +within the assertion (the normal behaviour), but if the assertion does not have +such an alternative, (*THEN) behaves like (*PRUNE). +. +. +.\" HTML <a name="btsub"></a> +.SS "Backtracking verbs in subroutines" +.rs +.sp +These behaviours occur whether or not the subpattern is called recursively. +Perl's treatment of subroutines is different in some cases. +.P +(*FAIL) in a subpattern called as a subroutine has its normal effect: it forces +an immediate backtrack. +.P +(*ACCEPT) in a subpattern called as a subroutine causes the subroutine match to +succeed without any further processing. Matching then continues after the +subroutine call. +.P +(*COMMIT), (*SKIP), and (*PRUNE) in a subpattern called as a subroutine cause +the subroutine match to fail. +.P +(*THEN) skips to the next alternative in the innermost enclosing group within +the subpattern that has alternatives. If there is no such group within the +subpattern, (*THEN) causes the subroutine match to fail. +. +. +.SH "SEE ALSO" +.rs +.sp +\fBpcreapi\fP(3), \fBpcrecallout\fP(3), \fBpcrematching\fP(3), +\fBpcresyntax\fP(3), \fBpcre\fP(3), \fBpcre16(3)\fP, \fBpcre32(3)\fP. +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 08 January 2014 +Copyright (c) 1997-2014 University of Cambridge. +.fi diff --git a/plugins/Pcre16/docs/doc/pcreperform.3 b/plugins/Pcre16/docs/doc/pcreperform.3 new file mode 100644 index 0000000000..fb2aa95926 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcreperform.3 @@ -0,0 +1,177 @@ +.TH PCREPERFORM 3 "09 January 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH "PCRE PERFORMANCE" +.rs +.sp +Two aspects of performance are discussed below: memory usage and processing +time. The way you express your pattern as a regular expression can affect both +of them. +. +.SH "COMPILED PATTERN MEMORY USAGE" +.rs +.sp +Patterns are compiled by PCRE into a reasonably efficient interpretive code, so +that most simple patterns do not use much memory. However, there is one case +where the memory usage of a compiled pattern can be unexpectedly large. If a +parenthesized subpattern has a quantifier with a minimum greater than 1 and/or +a limited maximum, the whole subpattern is repeated in the compiled code. For +example, the pattern +.sp + (abc|def){2,4} +.sp +is compiled as if it were +.sp + (abc|def)(abc|def)((abc|def)(abc|def)?)? +.sp +(Technical aside: It is done this way so that backtrack points within each of +the repetitions can be independently maintained.) +.P +For regular expressions whose quantifiers use only small numbers, this is not +usually a problem. However, if the numbers are large, and particularly if such +repetitions are nested, the memory usage can become an embarrassment. For +example, the very simple pattern +.sp + ((ab){1,1000}c){1,3} +.sp +uses 51K bytes when compiled using the 8-bit library. When PCRE is compiled +with its default internal pointer size of two bytes, the size limit on a +compiled pattern is 64K data units, and this is reached with the above pattern +if the outer repetition is increased from 3 to 4. PCRE can be compiled to use +larger internal pointers and thus handle larger compiled patterns, but it is +better to try to rewrite your pattern to use less memory if you can. +.P +One way of reducing the memory usage for such patterns is to make use of PCRE's +.\" HTML <a href="pcrepattern.html#subpatternsassubroutines"> +.\" </a> +"subroutine" +.\" +facility. Re-writing the above pattern as +.sp + ((ab)(?2){0,999}c)(?1){0,2} +.sp +reduces the memory requirements to 18K, and indeed it remains under 20K even +with the outer repetition increased to 100. However, this pattern is not +exactly equivalent, because the "subroutine" calls are treated as +.\" HTML <a href="pcrepattern.html#atomicgroup"> +.\" </a> +atomic groups +.\" +into which there can be no backtracking if there is a subsequent matching +failure. Therefore, PCRE cannot do this kind of rewriting automatically. +Furthermore, there is a noticeable loss of speed when executing the modified +pattern. Nevertheless, if the atomic grouping is not a problem and the loss of +speed is acceptable, this kind of rewriting will allow you to process patterns +that PCRE cannot otherwise handle. +. +. +.SH "STACK USAGE AT RUN TIME" +.rs +.sp +When \fBpcre_exec()\fP or \fBpcre[16|32]_exec()\fP is used for matching, certain +kinds of pattern can cause it to use large amounts of the process stack. In +some environments the default process stack is quite small, and if it runs out +the result is often SIGSEGV. This issue is probably the most frequently raised +problem with PCRE. Rewriting your pattern can often help. The +.\" HREF +\fBpcrestack\fP +.\" +documentation discusses this issue in detail. +. +. +.SH "PROCESSING TIME" +.rs +.sp +Certain items in regular expression patterns are processed more efficiently +than others. It is more efficient to use a character class like [aeiou] than a +set of single-character alternatives such as (a|e|i|o|u). In general, the +simplest construction that provides the required behaviour is usually the most +efficient. Jeffrey Friedl's book contains a lot of useful general discussion +about optimizing regular expressions for efficient performance. This document +contains a few observations about PCRE. +.P +Using Unicode character properties (the \ep, \eP, and \eX escapes) is slow, +because PCRE has to use a multi-stage table lookup whenever it needs a +character's property. If you can find an alternative pattern that does not use +character properties, it will probably be faster. +.P +By default, the escape sequences \eb, \ed, \es, and \ew, and the POSIX +character classes such as [:alpha:] do not use Unicode properties, partly for +backwards compatibility, and partly for performance reasons. However, you can +set PCRE_UCP if you want Unicode character properties to be used. This can +double the matching time for items such as \ed, when matched with +a traditional matching function; the performance loss is less with +a DFA matching function, and in both cases there is not much difference for +\eb. +.P +When a pattern begins with .* not in parentheses, or in parentheses that are +not the subject of a backreference, and the PCRE_DOTALL option is set, the +pattern is implicitly anchored by PCRE, since it can match only at the start of +a subject string. However, if PCRE_DOTALL is not set, PCRE cannot make this +optimization, because the . metacharacter does not then match a newline, and if +the subject string contains newlines, the pattern may match from the character +immediately following one of them instead of from the very start. For example, +the pattern +.sp + .*second +.sp +matches the subject "first\enand second" (where \en stands for a newline +character), with the match starting at the seventh character. In order to do +this, PCRE has to retry the match starting after every newline in the subject. +.P +If you are using such a pattern with subject strings that do not contain +newlines, the best performance is obtained by setting PCRE_DOTALL, or starting +the pattern with ^.* or ^.*? to indicate explicit anchoring. That saves PCRE +from having to scan along the subject looking for a newline to restart at. +.P +Beware of patterns that contain nested indefinite repeats. These can take a +long time to run when applied to a string that does not match. Consider the +pattern fragment +.sp + ^(a+)* +.sp +This can match "aaaa" in 16 different ways, and this number increases very +rapidly as the string gets longer. (The * repeat can match 0, 1, 2, 3, or 4 +times, and for each of those cases other than 0 or 4, the + repeats can match +different numbers of times.) When the remainder of the pattern is such that the +entire match is going to fail, PCRE has in principle to try every possible +variation, and this can take an extremely long time, even for relatively short +strings. +.P +An optimization catches some of the more simple cases such as +.sp + (a+)*b +.sp +where a literal character follows. Before embarking on the standard matching +procedure, PCRE checks that there is a "b" later in the subject string, and if +there is not, it fails the match immediately. However, when there is no +following literal this optimization cannot be used. You can see the difference +by comparing the behaviour of +.sp + (a+)*\ed +.sp +with the pattern above. The former gives a failure almost instantly when +applied to a whole line of "a" characters, whereas the latter takes an +appreciable time with strings longer than about 20 characters. +.P +In many cases, the solution to this kind of performance issue is to use an +atomic group or a possessive quantifier. +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 25 August 2012 +Copyright (c) 1997-2012 University of Cambridge. +.fi diff --git a/plugins/Pcre16/docs/doc/pcreposix.3 b/plugins/Pcre16/docs/doc/pcreposix.3 new file mode 100644 index 0000000000..77890f36b4 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcreposix.3 @@ -0,0 +1,267 @@ +.TH PCREPOSIX 3 "09 January 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions. +.SH "SYNOPSIS" +.rs +.sp +.B #include <pcreposix.h> +.PP +.nf +.B int regcomp(regex_t *\fIpreg\fP, const char *\fIpattern\fP, +.B " int \fIcflags\fP);" +.sp +.B int regexec(regex_t *\fIpreg\fP, const char *\fIstring\fP, +.B " size_t \fInmatch\fP, regmatch_t \fIpmatch\fP[], int \fIeflags\fP);" +.B " size_t regerror(int \fIerrcode\fP, const regex_t *\fIpreg\fP," +.B " char *\fIerrbuf\fP, size_t \fIerrbuf_size\fP);" +.sp +.B void regfree(regex_t *\fIpreg\fP); +.fi +. +.SH DESCRIPTION +.rs +.sp +This set of functions provides a POSIX-style API for the PCRE regular +expression 8-bit library. See the +.\" HREF +\fBpcreapi\fP +.\" +documentation for a description of PCRE's native API, which contains much +additional functionality. There is no POSIX-style wrapper for PCRE's 16-bit +and 32-bit library. +.P +The functions described here are just wrapper functions that ultimately call +the PCRE native API. Their prototypes are defined in the \fBpcreposix.h\fP +header file, and on Unix systems the library itself is called +\fBpcreposix.a\fP, so can be accessed by adding \fB-lpcreposix\fP to the +command for linking an application that uses them. Because the POSIX functions +call the native ones, it is also necessary to add \fB-lpcre\fP. +.P +I have implemented only those POSIX option bits that can be reasonably mapped +to PCRE native options. In addition, the option REG_EXTENDED is defined with +the value zero. This has no effect, but since programs that are written to the +POSIX interface often use it, this makes it easier to slot in PCRE as a +replacement library. Other POSIX options are not even defined. +.P +There are also some other options that are not defined by POSIX. These have +been added at the request of users who want to make use of certain +PCRE-specific features via the POSIX calling interface. +.P +When PCRE is called via these functions, it is only the API that is POSIX-like +in style. The syntax and semantics of the regular expressions themselves are +still those of Perl, subject to the setting of various PCRE options, as +described below. "POSIX-like in style" means that the API approximates to the +POSIX definition; it is not fully POSIX-compatible, and in multi-byte encoding +domains it is probably even less compatible. +.P +The header for these functions is supplied as \fBpcreposix.h\fP to avoid any +potential clash with other POSIX libraries. It can, of course, be renamed or +aliased as \fBregex.h\fP, which is the "correct" name. It provides two +structure types, \fIregex_t\fP for compiled internal forms, and +\fIregmatch_t\fP for returning captured substrings. It also defines some +constants whose names start with "REG_"; these are used for setting options and +identifying error codes. +. +. +.SH "COMPILING A PATTERN" +.rs +.sp +The function \fBregcomp()\fP is called to compile a pattern into an +internal form. The pattern is a C string terminated by a binary zero, and +is passed in the argument \fIpattern\fP. The \fIpreg\fP argument is a pointer +to a \fBregex_t\fP structure that is used as a base for storing information +about the compiled regular expression. +.P +The argument \fIcflags\fP is either zero, or contains one or more of the bits +defined by the following macros: +.sp + REG_DOTALL +.sp +The PCRE_DOTALL option is set when the regular expression is passed for +compilation to the native function. Note that REG_DOTALL is not part of the +POSIX standard. +.sp + REG_ICASE +.sp +The PCRE_CASELESS option is set when the regular expression is passed for +compilation to the native function. +.sp + REG_NEWLINE +.sp +The PCRE_MULTILINE option is set when the regular expression is passed for +compilation to the native function. Note that this does \fInot\fP mimic the +defined POSIX behaviour for REG_NEWLINE (see the following section). +.sp + REG_NOSUB +.sp +The PCRE_NO_AUTO_CAPTURE option is set when the regular expression is passed +for compilation to the native function. In addition, when a pattern that is +compiled with this flag is passed to \fBregexec()\fP for matching, the +\fInmatch\fP and \fIpmatch\fP arguments are ignored, and no captured strings +are returned. +.sp + REG_UCP +.sp +The PCRE_UCP option is set when the regular expression is passed for +compilation to the native function. This causes PCRE to use Unicode properties +when matchine \ed, \ew, etc., instead of just recognizing ASCII values. Note +that REG_UTF8 is not part of the POSIX standard. +.sp + REG_UNGREEDY +.sp +The PCRE_UNGREEDY option is set when the regular expression is passed for +compilation to the native function. Note that REG_UNGREEDY is not part of the +POSIX standard. +.sp + REG_UTF8 +.sp +The PCRE_UTF8 option is set when the regular expression is passed for +compilation to the native function. This causes the pattern itself and all data +strings used for matching it to be treated as UTF-8 strings. Note that REG_UTF8 +is not part of the POSIX standard. +.P +In the absence of these flags, no options are passed to the native function. +This means the the regex is compiled with PCRE default semantics. In +particular, the way it handles newline characters in the subject string is the +Perl way, not the POSIX way. Note that setting PCRE_MULTILINE has only +\fIsome\fP of the effects specified for REG_NEWLINE. It does not affect the way +newlines are matched by . (they are not) or by a negative class such as [^a] +(they are). +.P +The yield of \fBregcomp()\fP is zero on success, and non-zero otherwise. The +\fIpreg\fP structure is filled in on success, and one member of the structure +is public: \fIre_nsub\fP contains the number of capturing subpatterns in +the regular expression. Various error codes are defined in the header file. +.P +NOTE: If the yield of \fBregcomp()\fP is non-zero, you must not attempt to +use the contents of the \fIpreg\fP structure. If, for example, you pass it to +\fBregexec()\fP, the result is undefined and your program is likely to crash. +. +. +.SH "MATCHING NEWLINE CHARACTERS" +.rs +.sp +This area is not simple, because POSIX and Perl take different views of things. +It is not possible to get PCRE to obey POSIX semantics, but then PCRE was never +intended to be a POSIX engine. The following table lists the different +possibilities for matching newline characters in PCRE: +.sp + Default Change with +.sp + . matches newline no PCRE_DOTALL + newline matches [^a] yes not changeable + $ matches \en at end yes PCRE_DOLLARENDONLY + $ matches \en in middle no PCRE_MULTILINE + ^ matches \en in middle no PCRE_MULTILINE +.sp +This is the equivalent table for POSIX: +.sp + Default Change with +.sp + . matches newline yes REG_NEWLINE + newline matches [^a] yes REG_NEWLINE + $ matches \en at end no REG_NEWLINE + $ matches \en in middle no REG_NEWLINE + ^ matches \en in middle no REG_NEWLINE +.sp +PCRE's behaviour is the same as Perl's, except that there is no equivalent for +PCRE_DOLLAR_ENDONLY in Perl. In both PCRE and Perl, there is no way to stop +newline from matching [^a]. +.P +The default POSIX newline handling can be obtained by setting PCRE_DOTALL and +PCRE_DOLLAR_ENDONLY, but there is no way to make PCRE behave exactly as for the +REG_NEWLINE action. +. +. +.SH "MATCHING A PATTERN" +.rs +.sp +The function \fBregexec()\fP is called to match a compiled pattern \fIpreg\fP +against a given \fIstring\fP, which is by default terminated by a zero byte +(but see REG_STARTEND below), subject to the options in \fIeflags\fP. These can +be: +.sp + REG_NOTBOL +.sp +The PCRE_NOTBOL option is set when calling the underlying PCRE matching +function. +.sp + REG_NOTEMPTY +.sp +The PCRE_NOTEMPTY option is set when calling the underlying PCRE matching +function. Note that REG_NOTEMPTY is not part of the POSIX standard. However, +setting this option can give more POSIX-like behaviour in some situations. +.sp + REG_NOTEOL +.sp +The PCRE_NOTEOL option is set when calling the underlying PCRE matching +function. +.sp + REG_STARTEND +.sp +The string is considered to start at \fIstring\fP + \fIpmatch[0].rm_so\fP and +to have a terminating NUL located at \fIstring\fP + \fIpmatch[0].rm_eo\fP +(there need not actually be a NUL at that location), regardless of the value of +\fInmatch\fP. This is a BSD extension, compatible with but not specified by +IEEE Standard 1003.2 (POSIX.2), and should be used with caution in software +intended to be portable to other systems. Note that a non-zero \fIrm_so\fP does +not imply REG_NOTBOL; REG_STARTEND affects only the location of the string, not +how it is matched. +.P +If the pattern was compiled with the REG_NOSUB flag, no data about any matched +strings is returned. The \fInmatch\fP and \fIpmatch\fP arguments of +\fBregexec()\fP are ignored. +.P +If the value of \fInmatch\fP is zero, or if the value \fIpmatch\fP is NULL, +no data about any matched strings is returned. +.P +Otherwise,the portion of the string that was matched, and also any captured +substrings, are returned via the \fIpmatch\fP argument, which points to an +array of \fInmatch\fP structures of type \fIregmatch_t\fP, containing the +members \fIrm_so\fP and \fIrm_eo\fP. These contain the offset to the first +character of each substring and the offset to the first character after the end +of each substring, respectively. The 0th element of the vector relates to the +entire portion of \fIstring\fP that was matched; subsequent elements relate to +the capturing subpatterns of the regular expression. Unused entries in the +array have both structure members set to -1. +.P +A successful match yields a zero return; various error codes are defined in the +header file, of which REG_NOMATCH is the "expected" failure code. +. +. +.SH "ERROR MESSAGES" +.rs +.sp +The \fBregerror()\fP function maps a non-zero errorcode from either +\fBregcomp()\fP or \fBregexec()\fP to a printable message. If \fIpreg\fP is not +NULL, the error should have arisen from the use of that structure. A message +terminated by a binary zero is placed in \fIerrbuf\fP. The length of the +message, including the zero, is limited to \fIerrbuf_size\fP. The yield of the +function is the size of buffer needed to hold the whole message. +. +. +.SH MEMORY USAGE +.rs +.sp +Compiling a regular expression causes memory to be allocated and associated +with the \fIpreg\fP structure. The function \fBregfree()\fP frees all such +memory, after which \fIpreg\fP may no longer be used as a compiled expression. +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 09 January 2012 +Copyright (c) 1997-2012 University of Cambridge. +.fi diff --git a/plugins/Pcre16/docs/doc/pcreprecompile.3 b/plugins/Pcre16/docs/doc/pcreprecompile.3 new file mode 100644 index 0000000000..40f257a98c --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcreprecompile.3 @@ -0,0 +1,155 @@ +.TH PCREPRECOMPILE 3 "12 November 2013" "PCRE 8.34" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH "SAVING AND RE-USING PRECOMPILED PCRE PATTERNS" +.rs +.sp +If you are running an application that uses a large number of regular +expression patterns, it may be useful to store them in a precompiled form +instead of having to compile them every time the application is run. +If you are not using any private character tables (see the +.\" HREF +\fBpcre_maketables()\fP +.\" +documentation), this is relatively straightforward. If you are using private +tables, it is a little bit more complicated. However, if you are using the +just-in-time optimization feature, it is not possible to save and reload the +JIT data. +.P +If you save compiled patterns to a file, you can copy them to a different host +and run them there. If the two hosts have different endianness (byte order), +you should run the \fBpcre[16|32]_pattern_to_host_byte_order()\fP function on the +new host before trying to match the pattern. The matching functions return +PCRE_ERROR_BADENDIANNESS if they detect a pattern with the wrong endianness. +.P +Compiling regular expressions with one version of PCRE for use with a different +version is not guaranteed to work and may cause crashes, and saving and +restoring a compiled pattern loses any JIT optimization data. +. +. +.SH "SAVING A COMPILED PATTERN" +.rs +.sp +The value returned by \fBpcre[16|32]_compile()\fP points to a single block of +memory that holds the compiled pattern and associated data. You can find the +length of this block in bytes by calling \fBpcre[16|32]_fullinfo()\fP with an +argument of PCRE_INFO_SIZE. You can then save the data in any appropriate +manner. Here is sample code for the 8-bit library that compiles a pattern and +writes it to a file. It assumes that the variable \fIfd\fP refers to a file +that is open for output: +.sp + int erroroffset, rc, size; + char *error; + pcre *re; +.sp + re = pcre_compile("my pattern", 0, &error, &erroroffset, NULL); + if (re == NULL) { ... handle errors ... } + rc = pcre_fullinfo(re, NULL, PCRE_INFO_SIZE, &size); + if (rc < 0) { ... handle errors ... } + rc = fwrite(re, 1, size, fd); + if (rc != size) { ... handle errors ... } +.sp +In this example, the bytes that comprise the compiled pattern are copied +exactly. Note that this is binary data that may contain any of the 256 possible +byte values. On systems that make a distinction between binary and non-binary +data, be sure that the file is opened for binary output. +.P +If you want to write more than one pattern to a file, you will have to devise a +way of separating them. For binary data, preceding each pattern with its length +is probably the most straightforward approach. Another possibility is to write +out the data in hexadecimal instead of binary, one pattern to a line. +.P +Saving compiled patterns in a file is only one possible way of storing them for +later use. They could equally well be saved in a database, or in the memory of +some daemon process that passes them via sockets to the processes that want +them. +.P +If the pattern has been studied, it is also possible to save the normal study +data in a similar way to the compiled pattern itself. However, if the +PCRE_STUDY_JIT_COMPILE was used, the just-in-time data that is created cannot +be saved because it is too dependent on the current environment. When studying +generates additional information, \fBpcre[16|32]_study()\fP returns a pointer to a +\fBpcre[16|32]_extra\fP data block. Its format is defined in the +.\" HTML <a href="pcreapi.html#extradata"> +.\" </a> +section on matching a pattern +.\" +in the +.\" HREF +\fBpcreapi\fP +.\" +documentation. The \fIstudy_data\fP field points to the binary study data, and +this is what you must save (not the \fBpcre[16|32]_extra\fP block itself). The +length of the study data can be obtained by calling \fBpcre[16|32]_fullinfo()\fP +with an argument of PCRE_INFO_STUDYSIZE. Remember to check that +\fBpcre[16|32]_study()\fP did return a non-NULL value before trying to save the +study data. +. +. +.SH "RE-USING A PRECOMPILED PATTERN" +.rs +.sp +Re-using a precompiled pattern is straightforward. Having reloaded it into main +memory, called \fBpcre[16|32]_pattern_to_host_byte_order()\fP if necessary, you +pass its pointer to \fBpcre[16|32]_exec()\fP or \fBpcre[16|32]_dfa_exec()\fP in +the usual way. +.P +However, if you passed a pointer to custom character tables when the pattern +was compiled (the \fItableptr\fP argument of \fBpcre[16|32]_compile()\fP), you +must now pass a similar pointer to \fBpcre[16|32]_exec()\fP or +\fBpcre[16|32]_dfa_exec()\fP, because the value saved with the compiled pattern +will obviously be nonsense. A field in a \fBpcre[16|32]_extra()\fP block is used +to pass this data, as described in the +.\" HTML <a href="pcreapi.html#extradata"> +.\" </a> +section on matching a pattern +.\" +in the +.\" HREF +\fBpcreapi\fP +.\" +documentation. +.P +\fBWarning:\fP The tables that \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP use +must be the same as those that were used when the pattern was compiled. If this +is not the case, the behaviour is undefined. +.P +If you did not provide custom character tables when the pattern was compiled, +the pointer in the compiled pattern is NULL, which causes the matching +functions to use PCRE's internal tables. Thus, you do not need to take any +special action at run time in this case. +.P +If you saved study data with the compiled pattern, you need to create your own +\fBpcre[16|32]_extra\fP data block and set the \fIstudy_data\fP field to point +to the reloaded study data. You must also set the PCRE_EXTRA_STUDY_DATA bit in +the \fIflags\fP field to indicate that study data is present. Then pass the +\fBpcre[16|32]_extra\fP block to the matching function in the usual way. If the +pattern was studied for just-in-time optimization, that data cannot be saved, +and so is lost by a save/restore cycle. +. +. +.SH "COMPATIBILITY WITH DIFFERENT PCRE RELEASES" +.rs +.sp +In general, it is safest to recompile all saved patterns when you update to a +new PCRE release, though not all updates actually require this. +. +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 12 November 2013 +Copyright (c) 1997-2013 University of Cambridge. +.fi diff --git a/plugins/Pcre16/docs/doc/pcresample.3 b/plugins/Pcre16/docs/doc/pcresample.3 new file mode 100644 index 0000000000..d7fe7ec546 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcresample.3 @@ -0,0 +1,99 @@ +.TH PCRESAMPLE 3 "10 January 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH "PCRE SAMPLE PROGRAM" +.rs +.sp +A simple, complete demonstration program, to get you started with using PCRE, +is supplied in the file \fIpcredemo.c\fP in the PCRE distribution. A listing of +this program is given in the +.\" HREF +\fBpcredemo\fP +.\" +documentation. If you do not have a copy of the PCRE distribution, you can save +this listing to re-create \fIpcredemo.c\fP. +.P +The demonstration program, which uses the original PCRE 8-bit library, compiles +the regular expression that is its first argument, and matches it against the +subject string in its second argument. No PCRE options are set, and default +character tables are used. If matching succeeds, the program outputs the +portion of the subject that matched, together with the contents of any captured +substrings. +.P +If the -g option is given on the command line, the program then goes on to +check for further matches of the same regular expression in the same subject +string. The logic is a little bit tricky because of the possibility of matching +an empty string. Comments in the code explain what is going on. +.P +If PCRE is installed in the standard include and library directories for your +operating system, you should be able to compile the demonstration program using +this command: +.sp + gcc -o pcredemo pcredemo.c -lpcre +.sp +If PCRE is installed elsewhere, you may need to add additional options to the +command line. For example, on a Unix-like system that has PCRE installed in +\fI/usr/local\fP, you can compile the demonstration program using a command +like this: +.sp +.\" JOINSH + gcc -o pcredemo -I/usr/local/include pcredemo.c \e + -L/usr/local/lib -lpcre +.sp +In a Windows environment, if you want to statically link the program against a +non-dll \fBpcre.a\fP file, you must uncomment the line that defines PCRE_STATIC +before including \fBpcre.h\fP, because otherwise the \fBpcre_malloc()\fP and +\fBpcre_free()\fP exported functions will be declared +\fB__declspec(dllimport)\fP, with unwanted results. +.P +Once you have compiled and linked the demonstration program, you can run simple +tests like this: +.sp + ./pcredemo 'cat|dog' 'the cat sat on the mat' + ./pcredemo -g 'cat|dog' 'the dog sat on the cat' +.sp +Note that there is a much more comprehensive test program, called +.\" HREF +\fBpcretest\fP, +.\" +which supports many more facilities for testing regular expressions and both +PCRE libraries. The +.\" HREF +\fBpcredemo\fP +.\" +program is provided as a simple coding example. +.P +If you try to run +.\" HREF +\fBpcredemo\fP +.\" +when PCRE is not installed in the standard library directory, you may get an +error like this on some operating systems (e.g. Solaris): +.sp + ld.so.1: a.out: fatal: libpcre.so.0: open failed: No such file or directory +.sp +This is caused by the way shared library support works on those systems. You +need to add +.sp + -R/usr/local/lib +.sp +(for example) to the compile command to get round this problem. +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 10 January 2012 +Copyright (c) 1997-2012 University of Cambridge. +.fi diff --git a/plugins/Pcre16/docs/doc/pcrestack.3 b/plugins/Pcre16/docs/doc/pcrestack.3 new file mode 100644 index 0000000000..798f0bca63 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcrestack.3 @@ -0,0 +1,215 @@ +.TH PCRESTACK 3 "24 June 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH "PCRE DISCUSSION OF STACK USAGE" +.rs +.sp +When you call \fBpcre[16|32]_exec()\fP, it makes use of an internal function +called \fBmatch()\fP. This calls itself recursively at branch points in the +pattern, in order to remember the state of the match so that it can back up and +try a different alternative if the first one fails. As matching proceeds deeper +and deeper into the tree of possibilities, the recursion depth increases. The +\fBmatch()\fP function is also called in other circumstances, for example, +whenever a parenthesized sub-pattern is entered, and in certain cases of +repetition. +.P +Not all calls of \fBmatch()\fP increase the recursion depth; for an item such +as a* it may be called several times at the same level, after matching +different numbers of a's. Furthermore, in a number of cases where the result of +the recursive call would immediately be passed back as the result of the +current call (a "tail recursion"), the function is just restarted instead. +.P +The above comments apply when \fBpcre[16|32]_exec()\fP is run in its normal +interpretive manner. If the pattern was studied with the +PCRE_STUDY_JIT_COMPILE option, and just-in-time compiling was successful, and +the options passed to \fBpcre[16|32]_exec()\fP were not incompatible, the matching +process uses the JIT-compiled code instead of the \fBmatch()\fP function. In +this case, the memory requirements are handled entirely differently. See the +.\" HREF +\fBpcrejit\fP +.\" +documentation for details. +.P +The \fBpcre[16|32]_dfa_exec()\fP function operates in an entirely different way, +and uses recursion only when there is a regular expression recursion or +subroutine call in the pattern. This includes the processing of assertion and +"once-only" subpatterns, which are handled like subroutine calls. Normally, +these are never very deep, and the limit on the complexity of +\fBpcre[16|32]_dfa_exec()\fP is controlled by the amount of workspace it is given. +However, it is possible to write patterns with runaway infinite recursions; +such patterns will cause \fBpcre[16|32]_dfa_exec()\fP to run out of stack. At +present, there is no protection against this. +.P +The comments that follow do NOT apply to \fBpcre[16|32]_dfa_exec()\fP; they are +relevant only for \fBpcre[16|32]_exec()\fP without the JIT optimization. +. +. +.SS "Reducing \fBpcre[16|32]_exec()\fP's stack usage" +.rs +.sp +Each time that \fBmatch()\fP is actually called recursively, it uses memory +from the process stack. For certain kinds of pattern and data, very large +amounts of stack may be needed, despite the recognition of "tail recursion". +You can often reduce the amount of recursion, and therefore the amount of stack +used, by modifying the pattern that is being matched. Consider, for example, +this pattern: +.sp + ([^<]|<(?!inet))+ +.sp +It matches from wherever it starts until it encounters "<inet" or the end of +the data, and is the kind of pattern that might be used when processing an XML +file. Each iteration of the outer parentheses matches either one character that +is not "<" or a "<" that is not followed by "inet". However, each time a +parenthesis is processed, a recursion occurs, so this formulation uses a stack +frame for each matched character. For a long string, a lot of stack is +required. Consider now this rewritten pattern, which matches exactly the same +strings: +.sp + ([^<]++|<(?!inet))+ +.sp +This uses very much less stack, because runs of characters that do not contain +"<" are "swallowed" in one item inside the parentheses. Recursion happens only +when a "<" character that is not followed by "inet" is encountered (and we +assume this is relatively rare). A possessive quantifier is used to stop any +backtracking into the runs of non-"<" characters, but that is not related to +stack usage. +.P +This example shows that one way of avoiding stack problems when matching long +subject strings is to write repeated parenthesized subpatterns to match more +than one character whenever possible. +. +. +.SS "Compiling PCRE to use heap instead of stack for \fBpcre[16|32]_exec()\fP" +.rs +.sp +In environments where stack memory is constrained, you might want to compile +PCRE to use heap memory instead of stack for remembering back-up points when +\fBpcre[16|32]_exec()\fP is running. This makes it run a lot more slowly, however. +Details of how to do this are given in the +.\" HREF +\fBpcrebuild\fP +.\" +documentation. When built in this way, instead of using the stack, PCRE obtains +and frees memory by calling the functions that are pointed to by the +\fBpcre[16|32]_stack_malloc\fP and \fBpcre[16|32]_stack_free\fP variables. By +default, these point to \fBmalloc()\fP and \fBfree()\fP, but you can replace +the pointers to cause PCRE to use your own functions. Since the block sizes are +always the same, and are always freed in reverse order, it may be possible to +implement customized memory handlers that are more efficient than the standard +functions. +. +. +.SS "Limiting \fBpcre[16|32]_exec()\fP's stack usage" +.rs +.sp +You can set limits on the number of times that \fBmatch()\fP is called, both in +total and recursively. If a limit is exceeded, \fBpcre[16|32]_exec()\fP returns an +error code. Setting suitable limits should prevent it from running out of +stack. The default values of the limits are very large, and unlikely ever to +operate. They can be changed when PCRE is built, and they can also be set when +\fBpcre[16|32]_exec()\fP is called. For details of these interfaces, see the +.\" HREF +\fBpcrebuild\fP +.\" +documentation and the +.\" HTML <a href="pcreapi.html#extradata"> +.\" </a> +section on extra data for \fBpcre[16|32]_exec()\fP +.\" +in the +.\" HREF +\fBpcreapi\fP +.\" +documentation. +.P +As a very rough rule of thumb, you should reckon on about 500 bytes per +recursion. Thus, if you want to limit your stack usage to 8Mb, you should set +the limit at 16000 recursions. A 64Mb stack, on the other hand, can support +around 128000 recursions. +.P +In Unix-like environments, the \fBpcretest\fP test program has a command line +option (\fB-S\fP) that can be used to increase the size of its stack. As long +as the stack is large enough, another option (\fB-M\fP) can be used to find the +smallest limits that allow a particular pattern to match a given subject +string. This is done by calling \fBpcre[16|32]_exec()\fP repeatedly with different +limits. +. +. +.SS "Obtaining an estimate of stack usage" +.rs +.sp +The actual amount of stack used per recursion can vary quite a lot, depending +on the compiler that was used to build PCRE and the optimization or debugging +options that were set for it. The rule of thumb value of 500 bytes mentioned +above may be larger or smaller than what is actually needed. A better +approximation can be obtained by running this command: +.sp + pcretest -m -C +.sp +The \fB-C\fP option causes \fBpcretest\fP to output information about the +options with which PCRE was compiled. When \fB-m\fP is also given (before +\fB-C\fP), information about stack use is given in a line like this: +.sp + Match recursion uses stack: approximate frame size = 640 bytes +.sp +The value is approximate because some recursions need a bit more (up to perhaps +16 more bytes). +.P +If the above command is given when PCRE is compiled to use the heap instead of +the stack for recursion, the value that is output is the size of each block +that is obtained from the heap. +. +. +.SS "Changing stack size in Unix-like systems" +.rs +.sp +In Unix-like environments, there is not often a problem with the stack unless +very long strings are involved, though the default limit on stack size varies +from system to system. Values from 8Mb to 64Mb are common. You can find your +default limit by running the command: +.sp + ulimit -s +.sp +Unfortunately, the effect of running out of stack is often SIGSEGV, though +sometimes a more explicit error message is given. You can normally increase the +limit on stack size by code such as this: +.sp + struct rlimit rlim; + getrlimit(RLIMIT_STACK, &rlim); + rlim.rlim_cur = 100*1024*1024; + setrlimit(RLIMIT_STACK, &rlim); +.sp +This reads the current limits (soft and hard) using \fBgetrlimit()\fP, then +attempts to increase the soft limit to 100Mb using \fBsetrlimit()\fP. You must +do this before calling \fBpcre[16|32]_exec()\fP. +. +. +.SS "Changing stack size in Mac OS X" +.rs +.sp +Using \fBsetrlimit()\fP, as described above, should also work on Mac OS X. It +is also possible to set a stack size when linking a program. There is a +discussion about stack sizes in Mac OS X at this web site: +.\" HTML <a href="http://developer.apple.com/qa/qa2005/qa1419.html"> +.\" </a> +http://developer.apple.com/qa/qa2005/qa1419.html. +.\" +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 24 June 2012 +Copyright (c) 1997-2012 University of Cambridge. +.fi diff --git a/plugins/Pcre16/docs/doc/pcresyntax.3 b/plugins/Pcre16/docs/doc/pcresyntax.3 new file mode 100644 index 0000000000..fd878da4f9 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcresyntax.3 @@ -0,0 +1,517 @@ +.TH PCRESYNTAX 3 "08 January 2014" "PCRE 8.35" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH "PCRE REGULAR EXPRESSION SYNTAX SUMMARY" +.rs +.sp +The full syntax and semantics of the regular expressions that are supported by +PCRE are described in the +.\" HREF +\fBpcrepattern\fP +.\" +documentation. This document contains a quick-reference summary of the syntax. +. +. +.SH "QUOTING" +.rs +.sp + \ex where x is non-alphanumeric is a literal x + \eQ...\eE treat enclosed characters as literal +. +. +.SH "CHARACTERS" +.rs +.sp + \ea alarm, that is, the BEL character (hex 07) + \ecx "control-x", where x is any ASCII character + \ee escape (hex 1B) + \ef form feed (hex 0C) + \en newline (hex 0A) + \er carriage return (hex 0D) + \et tab (hex 09) + \e0dd character with octal code 0dd + \eddd character with octal code ddd, or backreference + \eo{ddd..} character with octal code ddd.. + \exhh character with hex code hh + \ex{hhh..} character with hex code hhh.. +.sp +Note that \e0dd is always an octal code, and that \e8 and \e9 are the literal +characters "8" and "9". +. +. +.SH "CHARACTER TYPES" +.rs +.sp + . any character except newline; + in dotall mode, any character whatsoever + \eC one data unit, even in UTF mode (best avoided) + \ed a decimal digit + \eD a character that is not a decimal digit + \eh a horizontal white space character + \eH a character that is not a horizontal white space character + \eN a character that is not a newline + \ep{\fIxx\fP} a character with the \fIxx\fP property + \eP{\fIxx\fP} a character without the \fIxx\fP property + \eR a newline sequence + \es a white space character + \eS a character that is not a white space character + \ev a vertical white space character + \eV a character that is not a vertical white space character + \ew a "word" character + \eW a "non-word" character + \eX a Unicode extended grapheme cluster +.sp +By default, \ed, \es, and \ew match only ASCII characters, even in UTF-8 mode +or in the 16- bit and 32-bit libraries. However, if locale-specific matching is +happening, \es and \ew may also match characters with code points in the range +128-255. If the PCRE_UCP option is set, the behaviour of these escape sequences +is changed to use Unicode properties and they match many more characters. +. +. +.SH "GENERAL CATEGORY PROPERTIES FOR \ep and \eP" +.rs +.sp + C Other + Cc Control + Cf Format + Cn Unassigned + Co Private use + Cs Surrogate +.sp + L Letter + Ll Lower case letter + Lm Modifier letter + Lo Other letter + Lt Title case letter + Lu Upper case letter + L& Ll, Lu, or Lt +.sp + M Mark + Mc Spacing mark + Me Enclosing mark + Mn Non-spacing mark +.sp + N Number + Nd Decimal number + Nl Letter number + No Other number +.sp + P Punctuation + Pc Connector punctuation + Pd Dash punctuation + Pe Close punctuation + Pf Final punctuation + Pi Initial punctuation + Po Other punctuation + Ps Open punctuation +.sp + S Symbol + Sc Currency symbol + Sk Modifier symbol + Sm Mathematical symbol + So Other symbol +.sp + Z Separator + Zl Line separator + Zp Paragraph separator + Zs Space separator +. +. +.SH "PCRE SPECIAL CATEGORY PROPERTIES FOR \ep and \eP" +.rs +.sp + Xan Alphanumeric: union of properties L and N + Xps POSIX space: property Z or tab, NL, VT, FF, CR + Xsp Perl space: property Z or tab, NL, VT, FF, CR + Xuc Univerally-named character: one that can be + represented by a Universal Character Name + Xwd Perl word: property Xan or underscore +.sp +Perl and POSIX space are now the same. Perl added VT to its space character set +at release 5.18 and PCRE changed at release 8.34. +. +. +.SH "SCRIPT NAMES FOR \ep AND \eP" +.rs +.sp +Arabic, +Armenian, +Avestan, +Balinese, +Bamum, +Batak, +Bengali, +Bopomofo, +Brahmi, +Braille, +Buginese, +Buhid, +Canadian_Aboriginal, +Carian, +Chakma, +Cham, +Cherokee, +Common, +Coptic, +Cuneiform, +Cypriot, +Cyrillic, +Deseret, +Devanagari, +Egyptian_Hieroglyphs, +Ethiopic, +Georgian, +Glagolitic, +Gothic, +Greek, +Gujarati, +Gurmukhi, +Han, +Hangul, +Hanunoo, +Hebrew, +Hiragana, +Imperial_Aramaic, +Inherited, +Inscriptional_Pahlavi, +Inscriptional_Parthian, +Javanese, +Kaithi, +Kannada, +Katakana, +Kayah_Li, +Kharoshthi, +Khmer, +Lao, +Latin, +Lepcha, +Limbu, +Linear_B, +Lisu, +Lycian, +Lydian, +Malayalam, +Mandaic, +Meetei_Mayek, +Meroitic_Cursive, +Meroitic_Hieroglyphs, +Miao, +Mongolian, +Myanmar, +New_Tai_Lue, +Nko, +Ogham, +Old_Italic, +Old_Persian, +Old_South_Arabian, +Old_Turkic, +Ol_Chiki, +Oriya, +Osmanya, +Phags_Pa, +Phoenician, +Rejang, +Runic, +Samaritan, +Saurashtra, +Sharada, +Shavian, +Sinhala, +Sora_Sompeng, +Sundanese, +Syloti_Nagri, +Syriac, +Tagalog, +Tagbanwa, +Tai_Le, +Tai_Tham, +Tai_Viet, +Takri, +Tamil, +Telugu, +Thaana, +Thai, +Tibetan, +Tifinagh, +Ugaritic, +Vai, +Yi. +. +. +.SH "CHARACTER CLASSES" +.rs +.sp + [...] positive character class + [^...] negative character class + [x-y] range (can be used for hex characters) + [[:xxx:]] positive POSIX named set + [[:^xxx:]] negative POSIX named set +.sp + alnum alphanumeric + alpha alphabetic + ascii 0-127 + blank space or tab + cntrl control character + digit decimal digit + graph printing, excluding space + lower lower case letter + print printing, including space + punct printing, excluding alphanumeric + space white space + upper upper case letter + word same as \ew + xdigit hexadecimal digit +.sp +In PCRE, POSIX character set names recognize only ASCII characters by default, +but some of them use Unicode properties if PCRE_UCP is set. You can use +\eQ...\eE inside a character class. +. +. +.SH "QUANTIFIERS" +.rs +.sp + ? 0 or 1, greedy + ?+ 0 or 1, possessive + ?? 0 or 1, lazy + * 0 or more, greedy + *+ 0 or more, possessive + *? 0 or more, lazy + + 1 or more, greedy + ++ 1 or more, possessive + +? 1 or more, lazy + {n} exactly n + {n,m} at least n, no more than m, greedy + {n,m}+ at least n, no more than m, possessive + {n,m}? at least n, no more than m, lazy + {n,} n or more, greedy + {n,}+ n or more, possessive + {n,}? n or more, lazy +. +. +.SH "ANCHORS AND SIMPLE ASSERTIONS" +.rs +.sp + \eb word boundary + \eB not a word boundary + ^ start of subject + also after internal newline in multiline mode + \eA start of subject + $ end of subject + also before newline at end of subject + also before internal newline in multiline mode + \eZ end of subject + also before newline at end of subject + \ez end of subject + \eG first matching position in subject +. +. +.SH "MATCH POINT RESET" +.rs +.sp + \eK reset start of match +.sp +\eK is honoured in positive assertions, but ignored in negative ones. +. +. +.SH "ALTERNATION" +.rs +.sp + expr|expr|expr... +. +. +.SH "CAPTURING" +.rs +.sp + (...) capturing group + (?<name>...) named capturing group (Perl) + (?'name'...) named capturing group (Perl) + (?P<name>...) named capturing group (Python) + (?:...) non-capturing group + (?|...) non-capturing group; reset group numbers for + capturing groups in each alternative +. +. +.SH "ATOMIC GROUPS" +.rs +.sp + (?>...) atomic, non-capturing group +. +. +. +. +.SH "COMMENT" +.rs +.sp + (?#....) comment (not nestable) +. +. +.SH "OPTION SETTING" +.rs +.sp + (?i) caseless + (?J) allow duplicate names + (?m) multiline + (?s) single line (dotall) + (?U) default ungreedy (lazy) + (?x) extended (ignore white space) + (?-...) unset option(s) +.sp +The following are recognized only at the very start of a pattern or after one +of the newline or \eR options with similar syntax. More than one of them may +appear. +.sp + (*LIMIT_MATCH=d) set the match limit to d (decimal number) + (*LIMIT_RECURSION=d) set the recursion limit to d (decimal number) + (*NO_AUTO_POSSESS) no auto-possessification (PCRE_NO_AUTO_POSSESS) + (*NO_START_OPT) no start-match optimization (PCRE_NO_START_OPTIMIZE) + (*UTF8) set UTF-8 mode: 8-bit library (PCRE_UTF8) + (*UTF16) set UTF-16 mode: 16-bit library (PCRE_UTF16) + (*UTF32) set UTF-32 mode: 32-bit library (PCRE_UTF32) + (*UTF) set appropriate UTF mode for the library in use + (*UCP) set PCRE_UCP (use Unicode properties for \ed etc) +.sp +Note that LIMIT_MATCH and LIMIT_RECURSION can only reduce the value of the +limits set by the caller of pcre_exec(), not increase them. +. +. +.SH "NEWLINE CONVENTION" +.rs +.sp +These are recognized only at the very start of the pattern or after option +settings with a similar syntax. +.sp + (*CR) carriage return only + (*LF) linefeed only + (*CRLF) carriage return followed by linefeed + (*ANYCRLF) all three of the above + (*ANY) any Unicode newline sequence +. +. +.SH "WHAT \eR MATCHES" +.rs +.sp +These are recognized only at the very start of the pattern or after option +setting with a similar syntax. +.sp + (*BSR_ANYCRLF) CR, LF, or CRLF + (*BSR_UNICODE) any Unicode newline sequence +. +. +.SH "LOOKAHEAD AND LOOKBEHIND ASSERTIONS" +.rs +.sp + (?=...) positive look ahead + (?!...) negative look ahead + (?<=...) positive look behind + (?<!...) negative look behind +.sp +Each top-level branch of a look behind must be of a fixed length. +. +. +.SH "BACKREFERENCES" +.rs +.sp + \en reference by number (can be ambiguous) + \egn reference by number + \eg{n} reference by number + \eg{-n} relative reference by number + \ek<name> reference by name (Perl) + \ek'name' reference by name (Perl) + \eg{name} reference by name (Perl) + \ek{name} reference by name (.NET) + (?P=name) reference by name (Python) +. +. +.SH "SUBROUTINE REFERENCES (POSSIBLY RECURSIVE)" +.rs +.sp + (?R) recurse whole pattern + (?n) call subpattern by absolute number + (?+n) call subpattern by relative number + (?-n) call subpattern by relative number + (?&name) call subpattern by name (Perl) + (?P>name) call subpattern by name (Python) + \eg<name> call subpattern by name (Oniguruma) + \eg'name' call subpattern by name (Oniguruma) + \eg<n> call subpattern by absolute number (Oniguruma) + \eg'n' call subpattern by absolute number (Oniguruma) + \eg<+n> call subpattern by relative number (PCRE extension) + \eg'+n' call subpattern by relative number (PCRE extension) + \eg<-n> call subpattern by relative number (PCRE extension) + \eg'-n' call subpattern by relative number (PCRE extension) +. +. +.SH "CONDITIONAL PATTERNS" +.rs +.sp + (?(condition)yes-pattern) + (?(condition)yes-pattern|no-pattern) +.sp + (?(n)... absolute reference condition + (?(+n)... relative reference condition + (?(-n)... relative reference condition + (?(<name>)... named reference condition (Perl) + (?('name')... named reference condition (Perl) + (?(name)... named reference condition (PCRE) + (?(R)... overall recursion condition + (?(Rn)... specific group recursion condition + (?(R&name)... specific recursion condition + (?(DEFINE)... define subpattern for reference + (?(assert)... assertion condition +. +. +.SH "BACKTRACKING CONTROL" +.rs +.sp +The following act immediately they are reached: +.sp + (*ACCEPT) force successful match + (*FAIL) force backtrack; synonym (*F) + (*MARK:NAME) set name to be passed back; synonym (*:NAME) +.sp +The following act only when a subsequent match failure causes a backtrack to +reach them. They all force a match failure, but they differ in what happens +afterwards. Those that advance the start-of-match point do so only if the +pattern is not anchored. +.sp + (*COMMIT) overall failure, no advance of starting point + (*PRUNE) advance to next starting character + (*PRUNE:NAME) equivalent to (*MARK:NAME)(*PRUNE) + (*SKIP) advance to current matching position + (*SKIP:NAME) advance to position corresponding to an earlier + (*MARK:NAME); if not found, the (*SKIP) is ignored + (*THEN) local failure, backtrack to next alternation + (*THEN:NAME) equivalent to (*MARK:NAME)(*THEN) +. +. +.SH "CALLOUTS" +.rs +.sp + (?C) callout + (?Cn) callout with data n +. +. +.SH "SEE ALSO" +.rs +.sp +\fBpcrepattern\fP(3), \fBpcreapi\fP(3), \fBpcrecallout\fP(3), +\fBpcrematching\fP(3), \fBpcre\fP(3). +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 08 January 2014 +Copyright (c) 1997-2014 University of Cambridge. +.fi diff --git a/plugins/Pcre16/docs/doc/pcretest.1 b/plugins/Pcre16/docs/doc/pcretest.1 new file mode 100644 index 0000000000..92640da8e1 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcretest.1 @@ -0,0 +1,1156 @@ +.TH PCRETEST 1 "09 February 2014" "PCRE 8.35" +.SH NAME +pcretest - a program for testing Perl-compatible regular expressions. +.SH SYNOPSIS +.rs +.sp +.B pcretest "[options] [input file [output file]]" +.sp +\fBpcretest\fP was written as a test program for the PCRE regular expression +library itself, but it can also be used for experimenting with regular +expressions. This document describes the features of the test program; for +details of the regular expressions themselves, see the +.\" HREF +\fBpcrepattern\fP +.\" +documentation. For details of the PCRE library function calls and their +options, see the +.\" HREF +\fBpcreapi\fP +.\" +, +.\" HREF +\fBpcre16\fP +and +.\" HREF +\fBpcre32\fP +.\" +documentation. +.P +The input for \fBpcretest\fP is a sequence of regular expression patterns and +strings to be matched, as described below. The output shows the result of each +match. Options on the command line and the patterns control PCRE options and +exactly what is output. +.P +As PCRE has evolved, it has acquired many different features, and as a result, +\fBpcretest\fP now has rather a lot of obscure options for testing every +possible feature. Some of these options are specifically designed for use in +conjunction with the test script and data files that are distributed as part of +PCRE, and are unlikely to be of use otherwise. They are all documented here, +but without much justification. +. +. +.SH "INPUT DATA FORMAT" +.rs +.sp +Input to \fBpcretest\fP is processed line by line, either by calling the C +library's \fBfgets()\fP function, or via the \fBlibreadline\fP library (see +below). In Unix-like environments, \fBfgets()\fP treats any bytes other than +newline as data characters. However, in some Windows environments character 26 +(hex 1A) causes an immediate end of file, and no further data is read. For +maximum portability, therefore, it is safest to use only ASCII characters in +\fBpcretest\fP input files. +. +. +.SH "PCRE's 8-BIT, 16-BIT AND 32-BIT LIBRARIES" +.rs +.sp +From release 8.30, two separate PCRE libraries can be built. The original one +supports 8-bit character strings, whereas the newer 16-bit library supports +character strings encoded in 16-bit units. From release 8.32, a third library +can be built, supporting character strings encoded in 32-bit units. The +\fBpcretest\fP program can be used to test all three libraries. However, it is +itself still an 8-bit program, reading 8-bit input and writing 8-bit output. +When testing the 16-bit or 32-bit library, the patterns and data strings are +converted to 16- or 32-bit format before being passed to the PCRE library +functions. Results are converted to 8-bit for output. +.P +References to functions and structures of the form \fBpcre[16|32]_xx\fP below +mean "\fBpcre_xx\fP when using the 8-bit library, \fBpcre16_xx\fP when using +the 16-bit library, or \fBpcre32_xx\fP when using the 32-bit library". +. +. +.SH "COMMAND LINE OPTIONS" +.rs +.TP 10 +\fB-8\fP +If both the 8-bit library has been built, this option causes the 8-bit library +to be used (which is the default); if the 8-bit library has not been built, +this option causes an error. +.TP 10 +\fB-16\fP +If both the 8-bit or the 32-bit, and the 16-bit libraries have been built, this +option causes the 16-bit library to be used. If only the 16-bit library has been +built, this is the default (so has no effect). If only the 8-bit or the 32-bit +library has been built, this option causes an error. +.TP 10 +\fB-32\fP +If both the 8-bit or the 16-bit, and the 32-bit libraries have been built, this +option causes the 32-bit library to be used. If only the 32-bit library has been +built, this is the default (so has no effect). If only the 8-bit or the 16-bit +library has been built, this option causes an error. +.TP 10 +\fB-b\fP +Behave as if each pattern has the \fB/B\fP (show byte code) modifier; the +internal form is output after compilation. +.TP 10 +\fB-C\fP +Output the version number of the PCRE library, and all available information +about the optional features that are included, and then exit with zero exit +code. All other options are ignored. +.TP 10 +\fB-C\fP \fIoption\fP +Output information about a specific build-time option, then exit. This +functionality is intended for use in scripts such as \fBRunTest\fP. The +following options output the value and set the exit code as indicated: +.sp + ebcdic-nl the code for LF (= NL) in an EBCDIC environment: + 0x15 or 0x25 + 0 if used in an ASCII environment + exit code is always 0 + linksize the configured internal link size (2, 3, or 4) + exit code is set to the link size + newline the default newline setting: + CR, LF, CRLF, ANYCRLF, or ANY + exit code is always 0 + bsr the default setting for what \eR matches: + ANYCRLF or ANY + exit code is always 0 +.sp +The following options output 1 for true or 0 for false, and set the exit code +to the same value: +.sp + ebcdic compiled for an EBCDIC environment + jit just-in-time support is available + pcre16 the 16-bit library was built + pcre32 the 32-bit library was built + pcre8 the 8-bit library was built + ucp Unicode property support is available + utf UTF-8 and/or UTF-16 and/or UTF-32 support + is available +.sp +If an unknown option is given, an error message is output; the exit code is 0. +.TP 10 +\fB-d\fP +Behave as if each pattern has the \fB/D\fP (debug) modifier; the internal +form and information about the compiled pattern is output after compilation; +\fB-d\fP is equivalent to \fB-b -i\fP. +.TP 10 +\fB-dfa\fP +Behave as if each data line contains the \eD escape sequence; this causes the +alternative matching function, \fBpcre[16|32]_dfa_exec()\fP, to be used instead +of the standard \fBpcre[16|32]_exec()\fP function (more detail is given below). +.TP 10 +\fB-help\fP +Output a brief summary these options and then exit. +.TP 10 +\fB-i\fP +Behave as if each pattern has the \fB/I\fP modifier; information about the +compiled pattern is given after compilation. +.TP 10 +\fB-M\fP +Behave as if each data line contains the \eM escape sequence; this causes +PCRE to discover the minimum MATCH_LIMIT and MATCH_LIMIT_RECURSION settings by +calling \fBpcre[16|32]_exec()\fP repeatedly with different limits. +.TP 10 +\fB-m\fP +Output the size of each compiled pattern after it has been compiled. This is +equivalent to adding \fB/M\fP to each regular expression. The size is given in +bytes for both libraries. +.TP 10 +\fB-O\fP +Behave as if each pattern has the \fB/O\fP modifier, that is disable +auto-possessification for all patterns. +.TP 10 +\fB-o\fP \fIosize\fP +Set the number of elements in the output vector that is used when calling +\fBpcre[16|32]_exec()\fP or \fBpcre[16|32]_dfa_exec()\fP to be \fIosize\fP. The +default value is 45, which is enough for 14 capturing subexpressions for +\fBpcre[16|32]_exec()\fP or 22 different matches for +\fBpcre[16|32]_dfa_exec()\fP. +The vector size can be changed for individual matching calls by including \eO +in the data line (see below). +.TP 10 +\fB-p\fP +Behave as if each pattern has the \fB/P\fP modifier; the POSIX wrapper API is +used to call PCRE. None of the other options has any effect when \fB-p\fP is +set. This option can be used only with the 8-bit library. +.TP 10 +\fB-q\fP +Do not output the version number of \fBpcretest\fP at the start of execution. +.TP 10 +\fB-S\fP \fIsize\fP +On Unix-like systems, set the size of the run-time stack to \fIsize\fP +megabytes. +.TP 10 +\fB-s\fP or \fB-s+\fP +Behave as if each pattern has the \fB/S\fP modifier; in other words, force each +pattern to be studied. If \fB-s+\fP is used, all the JIT compile options are +passed to \fBpcre[16|32]_study()\fP, causing just-in-time optimization to be set +up if it is available, for both full and partial matching. Specific JIT compile +options can be selected by following \fB-s+\fP with a digit in the range 1 to +7, which selects the JIT compile modes as follows: +.sp + 1 normal match only + 2 soft partial match only + 3 normal match and soft partial match + 4 hard partial match only + 6 soft and hard partial match + 7 all three modes (default) +.sp +If \fB-s++\fP is used instead of \fB-s+\fP (with or without a following digit), +the text "(JIT)" is added to the first output line after a match or no match +when JIT-compiled code was actually used. +.sp +Note that there are pattern options that can override \fB-s\fP, either +specifying no studying at all, or suppressing JIT compilation. +.sp +If the \fB/I\fP or \fB/D\fP option is present on a pattern (requesting output +about the compiled pattern), information about the result of studying is not +included when studying is caused only by \fB-s\fP and neither \fB-i\fP nor +\fB-d\fP is present on the command line. This behaviour means that the output +from tests that are run with and without \fB-s\fP should be identical, except +when options that output information about the actual running of a match are +set. +.sp +The \fB-M\fP, \fB-t\fP, and \fB-tm\fP options, which give information about +resources used, are likely to produce different output with and without +\fB-s\fP. Output may also differ if the \fB/C\fP option is present on an +individual pattern. This uses callouts to trace the the matching process, and +this may be different between studied and non-studied patterns. If the pattern +contains (*MARK) items there may also be differences, for the same reason. The +\fB-s\fP command line option can be overridden for specific patterns that +should never be studied (see the \fB/S\fP pattern modifier below). +.TP 10 +\fB-t\fP +Run each compile, study, and match many times with a timer, and output the +resulting times per compile, study, or match (in milliseconds). Do not set +\fB-m\fP with \fB-t\fP, because you will then get the size output a zillion +times, and the timing will be distorted. You can control the number of +iterations that are used for timing by following \fB-t\fP with a number (as a +separate item on the command line). For example, "-t 1000" iterates 1000 times. +The default is to iterate 500000 times. +.TP 10 +\fB-tm\fP +This is like \fB-t\fP except that it times only the matching phase, not the +compile or study phases. +.TP 10 +\fB-T\fP \fB-TM\fP +These behave like \fB-t\fP and \fB-tm\fP, but in addition, at the end of a run, +the total times for all compiles, studies, and matches are output. +. +. +.SH DESCRIPTION +.rs +.sp +If \fBpcretest\fP is given two filename arguments, it reads from the first and +writes to the second. If it is given only one filename argument, it reads from +that file and writes to stdout. Otherwise, it reads from stdin and writes to +stdout, and prompts for each line of input, using "re>" to prompt for regular +expressions, and "data>" to prompt for data lines. +.P +When \fBpcretest\fP is built, a configuration option can specify that it should +be linked with the \fBlibreadline\fP library. When this is done, if the input +is from a terminal, it is read using the \fBreadline()\fP function. This +provides line-editing and history facilities. The output from the \fB-help\fP +option states whether or not \fBreadline()\fP will be used. +.P +The program handles any number of sets of input on a single input file. Each +set starts with a regular expression, and continues with any number of data +lines to be matched against that pattern. +.P +Each data line is matched separately and independently. If you want to do +multi-line matches, you have to use the \en escape sequence (or \er or \er\en, +etc., depending on the newline setting) in a single line of input to encode the +newline sequences. There is no limit on the length of data lines; the input +buffer is automatically extended if it is too small. +.P +An empty line signals the end of the data lines, at which point a new regular +expression is read. The regular expressions are given enclosed in any +non-alphanumeric delimiters other than backslash, for example: +.sp + /(a|bc)x+yz/ +.sp +White space before the initial delimiter is ignored. A regular expression may +be continued over several input lines, in which case the newline characters are +included within it. It is possible to include the delimiter within the pattern +by escaping it, for example +.sp + /abc\e/def/ +.sp +If you do so, the escape and the delimiter form part of the pattern, but since +delimiters are always non-alphanumeric, this does not affect its interpretation. +If the terminating delimiter is immediately followed by a backslash, for +example, +.sp + /abc/\e +.sp +then a backslash is added to the end of the pattern. This is done to provide a +way of testing the error condition that arises if a pattern finishes with a +backslash, because +.sp + /abc\e/ +.sp +is interpreted as the first line of a pattern that starts with "abc/", causing +pcretest to read the next line as a continuation of the regular expression. +. +. +.SH "PATTERN MODIFIERS" +.rs +.sp +A pattern may be followed by any number of modifiers, which are mostly single +characters, though some of these can be qualified by further characters. +Following Perl usage, these are referred to below as, for example, "the +\fB/i\fP modifier", even though the delimiter of the pattern need not always be +a slash, and no slash is used when writing modifiers. White space may appear +between the final pattern delimiter and the first modifier, and between the +modifiers themselves. For reference, here is a complete list of modifiers. They +fall into several groups that are described in detail in the following +sections. +.sp + \fB/8\fP set UTF mode + \fB/9\fP set PCRE_NEVER_UTF (locks out UTF mode) + \fB/?\fP disable UTF validity check + \fB/+\fP show remainder of subject after match + \fB/=\fP show all captures (not just those that are set) +.sp + \fB/A\fP set PCRE_ANCHORED + \fB/B\fP show compiled code + \fB/C\fP set PCRE_AUTO_CALLOUT + \fB/D\fP same as \fB/B\fP plus \fB/I\fP + \fB/E\fP set PCRE_DOLLAR_ENDONLY + \fB/F\fP flip byte order in compiled pattern + \fB/f\fP set PCRE_FIRSTLINE + \fB/G\fP find all matches (shorten string) + \fB/g\fP find all matches (use startoffset) + \fB/I\fP show information about pattern + \fB/i\fP set PCRE_CASELESS + \fB/J\fP set PCRE_DUPNAMES + \fB/K\fP show backtracking control names + \fB/L\fP set locale + \fB/M\fP show compiled memory size + \fB/m\fP set PCRE_MULTILINE + \fB/N\fP set PCRE_NO_AUTO_CAPTURE + \fB/O\fP set PCRE_NO_AUTO_POSSESS + \fB/P\fP use the POSIX wrapper + \fB/Q\fP test external stack check function + \fB/S\fP study the pattern after compilation + \fB/s\fP set PCRE_DOTALL + \fB/T\fP select character tables + \fB/U\fP set PCRE_UNGREEDY + \fB/W\fP set PCRE_UCP + \fB/X\fP set PCRE_EXTRA + \fB/x\fP set PCRE_EXTENDED + \fB/Y\fP set PCRE_NO_START_OPTIMIZE + \fB/Z\fP don't show lengths in \fB/B\fP output +.sp + \fB/<any>\fP set PCRE_NEWLINE_ANY + \fB/<anycrlf>\fP set PCRE_NEWLINE_ANYCRLF + \fB/<cr>\fP set PCRE_NEWLINE_CR + \fB/<crlf>\fP set PCRE_NEWLINE_CRLF + \fB/<lf>\fP set PCRE_NEWLINE_LF + \fB/<bsr_anycrlf>\fP set PCRE_BSR_ANYCRLF + \fB/<bsr_unicode>\fP set PCRE_BSR_UNICODE + \fB/<JS>\fP set PCRE_JAVASCRIPT_COMPAT +.sp +. +. +.SS "Perl-compatible modifiers" +.rs +.sp +The \fB/i\fP, \fB/m\fP, \fB/s\fP, and \fB/x\fP modifiers set the PCRE_CASELESS, +PCRE_MULTILINE, PCRE_DOTALL, or PCRE_EXTENDED options, respectively, when +\fBpcre[16|32]_compile()\fP is called. These four modifier letters have the same +effect as they do in Perl. For example: +.sp + /caseless/i +.sp +. +. +.SS "Modifiers for other PCRE options" +.rs +.sp +The following table shows additional modifiers for setting PCRE compile-time +options that do not correspond to anything in Perl: +.sp + \fB/8\fP PCRE_UTF8 ) when using the 8-bit + \fB/?\fP PCRE_NO_UTF8_CHECK ) library +.sp + \fB/8\fP PCRE_UTF16 ) when using the 16-bit + \fB/?\fP PCRE_NO_UTF16_CHECK ) library +.sp + \fB/8\fP PCRE_UTF32 ) when using the 32-bit + \fB/?\fP PCRE_NO_UTF32_CHECK ) library +.sp + \fB/9\fP PCRE_NEVER_UTF + \fB/A\fP PCRE_ANCHORED + \fB/C\fP PCRE_AUTO_CALLOUT + \fB/E\fP PCRE_DOLLAR_ENDONLY + \fB/f\fP PCRE_FIRSTLINE + \fB/J\fP PCRE_DUPNAMES + \fB/N\fP PCRE_NO_AUTO_CAPTURE + \fB/O\fP PCRE_NO_AUTO_POSSESS + \fB/U\fP PCRE_UNGREEDY + \fB/W\fP PCRE_UCP + \fB/X\fP PCRE_EXTRA + \fB/Y\fP PCRE_NO_START_OPTIMIZE + \fB/<any>\fP PCRE_NEWLINE_ANY + \fB/<anycrlf>\fP PCRE_NEWLINE_ANYCRLF + \fB/<cr>\fP PCRE_NEWLINE_CR + \fB/<crlf>\fP PCRE_NEWLINE_CRLF + \fB/<lf>\fP PCRE_NEWLINE_LF + \fB/<bsr_anycrlf>\fP PCRE_BSR_ANYCRLF + \fB/<bsr_unicode>\fP PCRE_BSR_UNICODE + \fB/<JS>\fP PCRE_JAVASCRIPT_COMPAT +.sp +The modifiers that are enclosed in angle brackets are literal strings as shown, +including the angle brackets, but the letters within can be in either case. +This example sets multiline matching with CRLF as the line ending sequence: +.sp + /^abc/m<CRLF> +.sp +As well as turning on the PCRE_UTF8/16/32 option, the \fB/8\fP modifier causes +all non-printing characters in output strings to be printed using the +\ex{hh...} notation. Otherwise, those less than 0x100 are output in hex without +the curly brackets. +.P +Full details of the PCRE options are given in the +.\" HREF +\fBpcreapi\fP +.\" +documentation. +. +. +.SS "Finding all matches in a string" +.rs +.sp +Searching for all possible matches within each subject string can be requested +by the \fB/g\fP or \fB/G\fP modifier. After finding a match, PCRE is called +again to search the remainder of the subject string. The difference between +\fB/g\fP and \fB/G\fP is that the former uses the \fIstartoffset\fP argument to +\fBpcre[16|32]_exec()\fP to start searching at a new point within the entire +string (which is in effect what Perl does), whereas the latter passes over a +shortened substring. This makes a difference to the matching process if the +pattern begins with a lookbehind assertion (including \eb or \eB). +.P +If any call to \fBpcre[16|32]_exec()\fP in a \fB/g\fP or \fB/G\fP sequence matches +an empty string, the next call is done with the PCRE_NOTEMPTY_ATSTART and +PCRE_ANCHORED flags set in order to search for another, non-empty, match at the +same point. If this second match fails, the start offset is advanced, and the +normal match is retried. This imitates the way Perl handles such cases when +using the \fB/g\fP modifier or the \fBsplit()\fP function. Normally, the start +offset is advanced by one character, but if the newline convention recognizes +CRLF as a newline, and the current character is CR followed by LF, an advance +of two is used. +. +. +.SS "Other modifiers" +.rs +.sp +There are yet more modifiers for controlling the way \fBpcretest\fP +operates. +.P +The \fB/+\fP modifier requests that as well as outputting the substring that +matched the entire pattern, \fBpcretest\fP should in addition output the +remainder of the subject string. This is useful for tests where the subject +contains multiple copies of the same substring. If the \fB+\fP modifier appears +twice, the same action is taken for captured substrings. In each case the +remainder is output on the following line with a plus character following the +capture number. Note that this modifier must not immediately follow the /S +modifier because /S+ and /S++ have other meanings. +.P +The \fB/=\fP modifier requests that the values of all potential captured +parentheses be output after a match. By default, only those up to the highest +one actually used in the match are output (corresponding to the return code +from \fBpcre[16|32]_exec()\fP). Values in the offsets vector corresponding to +higher numbers should be set to -1, and these are output as "<unset>". This +modifier gives a way of checking that this is happening. +.P +The \fB/B\fP modifier is a debugging feature. It requests that \fBpcretest\fP +output a representation of the compiled code after compilation. Normally this +information contains length and offset values; however, if \fB/Z\fP is also +present, this data is replaced by spaces. This is a special feature for use in +the automatic test scripts; it ensures that the same output is generated for +different internal link sizes. +.P +The \fB/D\fP modifier is a PCRE debugging feature, and is equivalent to +\fB/BI\fP, that is, both the \fB/B\fP and the \fB/I\fP modifiers. +.P +The \fB/F\fP modifier causes \fBpcretest\fP to flip the byte order of the +2-byte and 4-byte fields in the compiled pattern. This facility is for testing +the feature in PCRE that allows it to execute patterns that were compiled on a +host with a different endianness. This feature is not available when the POSIX +interface to PCRE is being used, that is, when the \fB/P\fP pattern modifier is +specified. See also the section about saving and reloading compiled patterns +below. +.P +The \fB/I\fP modifier requests that \fBpcretest\fP output information about the +compiled pattern (whether it is anchored, has a fixed first character, and +so on). It does this by calling \fBpcre[16|32]_fullinfo()\fP after compiling a +pattern. If the pattern is studied, the results of that are also output. In +this output, the word "char" means a non-UTF character, that is, the value of a +single data item (8-bit, 16-bit, or 32-bit, depending on the library that is +being tested). +.P +The \fB/K\fP modifier requests \fBpcretest\fP to show names from backtracking +control verbs that are returned from calls to \fBpcre[16|32]_exec()\fP. It causes +\fBpcretest\fP to create a \fBpcre[16|32]_extra\fP block if one has not already +been created by a call to \fBpcre[16|32]_study()\fP, and to set the +PCRE_EXTRA_MARK flag and the \fBmark\fP field within it, every time that +\fBpcre[16|32]_exec()\fP is called. If the variable that the \fBmark\fP field +points to is non-NULL for a match, non-match, or partial match, \fBpcretest\fP +prints the string to which it points. For a match, this is shown on a line by +itself, tagged with "MK:". For a non-match it is added to the message. +.P +The \fB/L\fP modifier must be followed directly by the name of a locale, for +example, +.sp + /pattern/Lfr_FR +.sp +For this reason, it must be the last modifier. The given locale is set, +\fBpcre[16|32]_maketables()\fP is called to build a set of character tables for +the locale, and this is then passed to \fBpcre[16|32]_compile()\fP when compiling +the regular expression. Without an \fB/L\fP (or \fB/T\fP) modifier, NULL is +passed as the tables pointer; that is, \fB/L\fP applies only to the expression +on which it appears. +.P +The \fB/M\fP modifier causes the size in bytes of the memory block used to hold +the compiled pattern to be output. This does not include the size of the +\fBpcre[16|32]\fP block; it is just the actual compiled data. If the pattern is +successfully studied with the PCRE_STUDY_JIT_COMPILE option, the size of the +JIT compiled code is also output. +.P +The \fB/Q\fP modifier is used to test the use of \fBpcre_stack_guard\fP. It +must be followed by '0' or '1', specifying the return code to be given from an +external function that is passed to PCRE and used for stack checking during +compilation (see the +.\" HREF +\fBpcreapi\fP +.\" +documentation for details). +.P +The \fB/S\fP modifier causes \fBpcre[16|32]_study()\fP to be called after the +expression has been compiled, and the results used when the expression is +matched. There are a number of qualifying characters that may follow \fB/S\fP. +They may appear in any order. +.P +If \fB/S\fP is followed by an exclamation mark, \fBpcre[16|32]_study()\fP is +called with the PCRE_STUDY_EXTRA_NEEDED option, causing it always to return a +\fBpcre_extra\fP block, even when studying discovers no useful information. +.P +If \fB/S\fP is followed by a second S character, it suppresses studying, even +if it was requested externally by the \fB-s\fP command line option. This makes +it possible to specify that certain patterns are always studied, and others are +never studied, independently of \fB-s\fP. This feature is used in the test +files in a few cases where the output is different when the pattern is studied. +.P +If the \fB/S\fP modifier is followed by a + character, the call to +\fBpcre[16|32]_study()\fP is made with all the JIT study options, requesting +just-in-time optimization support if it is available, for both normal and +partial matching. If you want to restrict the JIT compiling modes, you can +follow \fB/S+\fP with a digit in the range 1 to 7: +.sp + 1 normal match only + 2 soft partial match only + 3 normal match and soft partial match + 4 hard partial match only + 6 soft and hard partial match + 7 all three modes (default) +.sp +If \fB/S++\fP is used instead of \fB/S+\fP (with or without a following digit), +the text "(JIT)" is added to the first output line after a match or no match +when JIT-compiled code was actually used. +.P +Note that there is also an independent \fB/+\fP modifier; it must not be given +immediately after \fB/S\fP or \fB/S+\fP because this will be misinterpreted. +.P +If JIT studying is successful, the compiled JIT code will automatically be used +when \fBpcre[16|32]_exec()\fP is run, except when incompatible run-time options +are specified. For more details, see the +.\" HREF +\fBpcrejit\fP +.\" +documentation. See also the \fB\eJ\fP escape sequence below for a way of +setting the size of the JIT stack. +.P +Finally, if \fB/S\fP is followed by a minus character, JIT compilation is +suppressed, even if it was requested externally by the \fB-s\fP command line +option. This makes it possible to specify that JIT is never to be used for +certain patterns. +.P +The \fB/T\fP modifier must be followed by a single digit. It causes a specific +set of built-in character tables to be passed to \fBpcre[16|32]_compile()\fP. It +is used in the standard PCRE tests to check behaviour with different character +tables. The digit specifies the tables as follows: +.sp + 0 the default ASCII tables, as distributed in + pcre_chartables.c.dist + 1 a set of tables defining ISO 8859 characters +.sp +In table 1, some characters whose codes are greater than 128 are identified as +letters, digits, spaces, etc. +. +. +.SS "Using the POSIX wrapper API" +.rs +.sp +The \fB/P\fP modifier causes \fBpcretest\fP to call PCRE via the POSIX wrapper +API rather than its native API. This supports only the 8-bit library. When +\fB/P\fP is set, the following modifiers set options for the \fBregcomp()\fP +function: +.sp + /i REG_ICASE + /m REG_NEWLINE + /N REG_NOSUB + /s REG_DOTALL ) + /U REG_UNGREEDY ) These options are not part of + /W REG_UCP ) the POSIX standard + /8 REG_UTF8 ) +.sp +The \fB/+\fP modifier works as described above. All other modifiers are +ignored. +. +. +.SS "Locking out certain modifiers" +.rs +.sp +PCRE can be compiled with or without support for certain features such as +UTF-8/16/32 or Unicode properties. Accordingly, the standard tests are split up +into a number of different files that are selected for running depending on +which features are available. When updating the tests, it is all too easy to +put a new test into the wrong file by mistake; for example, to put a test that +requires UTF support into a file that is used when it is not available. To help +detect such mistakes as early as possible, there is a facility for locking out +specific modifiers. If an input line for \fBpcretest\fP starts with the string +"< forbid " the following sequence of characters is taken as a list of +forbidden modifiers. For example, in the test files that must not use UTF or +Unicode property support, this line appears: +.sp + < forbid 8W +.sp +This locks out the /8 and /W modifiers. An immediate error is given if they are +subsequently encountered. If the character string contains < but not >, all the +multi-character modifiers that begin with < are locked out. Otherwise, such +modifiers must be explicitly listed, for example: +.sp + < forbid <JS><cr> +.sp +There must be a single space between < and "forbid" for this feature to be +recognised. If there is not, the line is interpreted either as a request to +re-load a pre-compiled pattern (see "SAVING AND RELOADING COMPILED PATTERNS" +below) or, if there is a another < character, as a pattern that uses < as its +delimiter. +. +. +.SH "DATA LINES" +.rs +.sp +Before each data line is passed to \fBpcre[16|32]_exec()\fP, leading and trailing +white space is removed, and it is then scanned for \e escapes. Some of these +are pretty esoteric features, intended for checking out some of the more +complicated features of PCRE. If you are just testing "ordinary" regular +expressions, you probably don't need any of these. The following escapes are +recognized: +.sp + \ea alarm (BEL, \ex07) + \eb backspace (\ex08) + \ee escape (\ex27) + \ef form feed (\ex0c) + \en newline (\ex0a) +.\" JOIN + \eqdd set the PCRE_MATCH_LIMIT limit to dd + (any number of digits) + \er carriage return (\ex0d) + \et tab (\ex09) + \ev vertical tab (\ex0b) + \ennn octal character (up to 3 octal digits); always + a byte unless > 255 in UTF-8 or 16-bit or 32-bit mode + \eo{dd...} octal character (any number of octal digits} + \exhh hexadecimal byte (up to 2 hex digits) + \ex{hh...} hexadecimal character (any number of hex digits) +.\" JOIN + \eA pass the PCRE_ANCHORED option to \fBpcre[16|32]_exec()\fP + or \fBpcre[16|32]_dfa_exec()\fP +.\" JOIN + \eB pass the PCRE_NOTBOL option to \fBpcre[16|32]_exec()\fP + or \fBpcre[16|32]_dfa_exec()\fP +.\" JOIN + \eCdd call pcre[16|32]_copy_substring() for substring dd + after a successful match (number less than 32) +.\" JOIN + \eCname call pcre[16|32]_copy_named_substring() for substring + "name" after a successful match (name termin- + ated by next non alphanumeric character) +.\" JOIN + \eC+ show the current captured substrings at callout + time + \eC- do not supply a callout function +.\" JOIN + \eC!n return 1 instead of 0 when callout number n is + reached +.\" JOIN + \eC!n!m return 1 instead of 0 when callout number n is + reached for the nth time +.\" JOIN + \eC*n pass the number n (may be negative) as callout + data; this is used as the callout return value + \eD use the \fBpcre[16|32]_dfa_exec()\fP match function + \eF only shortest match for \fBpcre[16|32]_dfa_exec()\fP +.\" JOIN + \eGdd call pcre[16|32]_get_substring() for substring dd + after a successful match (number less than 32) +.\" JOIN + \eGname call pcre[16|32]_get_named_substring() for substring + "name" after a successful match (name termin- + ated by next non-alphanumeric character) +.\" JOIN + \eJdd set up a JIT stack of dd kilobytes maximum (any + number of digits) +.\" JOIN + \eL call pcre[16|32]_get_substringlist() after a + successful match +.\" JOIN + \eM discover the minimum MATCH_LIMIT and + MATCH_LIMIT_RECURSION settings +.\" JOIN + \eN pass the PCRE_NOTEMPTY option to \fBpcre[16|32]_exec()\fP + or \fBpcre[16|32]_dfa_exec()\fP; if used twice, pass the + PCRE_NOTEMPTY_ATSTART option +.\" JOIN + \eOdd set the size of the output vector passed to + \fBpcre[16|32]_exec()\fP to dd (any number of digits) +.\" JOIN + \eP pass the PCRE_PARTIAL_SOFT option to \fBpcre[16|32]_exec()\fP + or \fBpcre[16|32]_dfa_exec()\fP; if used twice, pass the + PCRE_PARTIAL_HARD option +.\" JOIN + \eQdd set the PCRE_MATCH_LIMIT_RECURSION limit to dd + (any number of digits) + \eR pass the PCRE_DFA_RESTART option to \fBpcre[16|32]_dfa_exec()\fP + \eS output details of memory get/free calls during matching +.\" JOIN + \eY pass the PCRE_NO_START_OPTIMIZE option to \fBpcre[16|32]_exec()\fP + or \fBpcre[16|32]_dfa_exec()\fP +.\" JOIN + \eZ pass the PCRE_NOTEOL option to \fBpcre[16|32]_exec()\fP + or \fBpcre[16|32]_dfa_exec()\fP +.\" JOIN + \e? pass the PCRE_NO_UTF[8|16|32]_CHECK option to + \fBpcre[16|32]_exec()\fP or \fBpcre[16|32]_dfa_exec()\fP +.\" JOIN + \e>dd start the match at offset dd (optional "-"; then + any number of digits); this sets the \fIstartoffset\fP + argument for \fBpcre[16|32]_exec()\fP or \fBpcre[16|32]_dfa_exec()\fP +.\" JOIN + \e<cr> pass the PCRE_NEWLINE_CR option to \fBpcre[16|32]_exec()\fP + or \fBpcre[16|32]_dfa_exec()\fP +.\" JOIN + \e<lf> pass the PCRE_NEWLINE_LF option to \fBpcre[16|32]_exec()\fP + or \fBpcre[16|32]_dfa_exec()\fP +.\" JOIN + \e<crlf> pass the PCRE_NEWLINE_CRLF option to \fBpcre[16|32]_exec()\fP + or \fBpcre[16|32]_dfa_exec()\fP +.\" JOIN + \e<anycrlf> pass the PCRE_NEWLINE_ANYCRLF option to \fBpcre[16|32]_exec()\fP + or \fBpcre[16|32]_dfa_exec()\fP +.\" JOIN + \e<any> pass the PCRE_NEWLINE_ANY option to \fBpcre[16|32]_exec()\fP + or \fBpcre[16|32]_dfa_exec()\fP +.sp +The use of \ex{hh...} is not dependent on the use of the \fB/8\fP modifier on +the pattern. It is recognized always. There may be any number of hexadecimal +digits inside the braces; invalid values provoke error messages. +.P +Note that \exhh specifies one byte rather than one character in UTF-8 mode; +this makes it possible to construct invalid UTF-8 sequences for testing +purposes. On the other hand, \ex{hh} is interpreted as a UTF-8 character in +UTF-8 mode, generating more than one byte if the value is greater than 127. +When testing the 8-bit library not in UTF-8 mode, \ex{hh} generates one byte +for values less than 256, and causes an error for greater values. +.P +In UTF-16 mode, all 4-digit \ex{hhhh} values are accepted. This makes it +possible to construct invalid UTF-16 sequences for testing purposes. +.P +In UTF-32 mode, all 4- to 8-digit \ex{...} values are accepted. This makes it +possible to construct invalid UTF-32 sequences for testing purposes. +.P +The escapes that specify line ending sequences are literal strings, exactly as +shown. No more than one newline setting should be present in any data line. +.P +A backslash followed by anything else just escapes the anything else. If +the very last character is a backslash, it is ignored. This gives a way of +passing an empty line as data, since a real empty line terminates the data +input. +.P +The \fB\eJ\fP escape provides a way of setting the maximum stack size that is +used by the just-in-time optimization code. It is ignored if JIT optimization +is not being used. Providing a stack that is larger than the default 32K is +necessary only for very complicated patterns. +.P +If \eM is present, \fBpcretest\fP calls \fBpcre[16|32]_exec()\fP several times, +with different values in the \fImatch_limit\fP and \fImatch_limit_recursion\fP +fields of the \fBpcre[16|32]_extra\fP data structure, until it finds the minimum +numbers for each parameter that allow \fBpcre[16|32]_exec()\fP to complete without +error. Because this is testing a specific feature of the normal interpretive +\fBpcre[16|32]_exec()\fP execution, the use of any JIT optimization that might +have been set up by the \fB/S+\fP qualifier of \fB-s+\fP option is disabled. +.P +The \fImatch_limit\fP number is a measure of the amount of backtracking +that takes place, and checking it out can be instructive. For most simple +matches, the number is quite small, but for patterns with very large numbers of +matching possibilities, it can become large very quickly with increasing length +of subject string. The \fImatch_limit_recursion\fP number is a measure of how +much stack (or, if PCRE is compiled with NO_RECURSE, how much heap) memory is +needed to complete the match attempt. +.P +When \eO is used, the value specified may be higher or lower than the size set +by the \fB-O\fP command line option (or defaulted to 45); \eO applies only to +the call of \fBpcre[16|32]_exec()\fP for the line in which it appears. +.P +If the \fB/P\fP modifier was present on the pattern, causing the POSIX wrapper +API to be used, the only option-setting sequences that have any effect are \eB, +\eN, and \eZ, causing REG_NOTBOL, REG_NOTEMPTY, and REG_NOTEOL, respectively, +to be passed to \fBregexec()\fP. +. +. +.SH "THE ALTERNATIVE MATCHING FUNCTION" +.rs +.sp +By default, \fBpcretest\fP uses the standard PCRE matching function, +\fBpcre[16|32]_exec()\fP to match each data line. PCRE also supports an +alternative matching function, \fBpcre[16|32]_dfa_test()\fP, which operates in a +different way, and has some restrictions. The differences between the two +functions are described in the +.\" HREF +\fBpcrematching\fP +.\" +documentation. +.P +If a data line contains the \eD escape sequence, or if the command line +contains the \fB-dfa\fP option, the alternative matching function is used. +This function finds all possible matches at a given point. If, however, the \eF +escape sequence is present in the data line, it stops after the first match is +found. This is always the shortest possible match. +. +. +.SH "DEFAULT OUTPUT FROM PCRETEST" +.rs +.sp +This section describes the output when the normal matching function, +\fBpcre[16|32]_exec()\fP, is being used. +.P +When a match succeeds, \fBpcretest\fP outputs the list of captured substrings +that \fBpcre[16|32]_exec()\fP returns, starting with number 0 for the string that +matched the whole pattern. Otherwise, it outputs "No match" when the return is +PCRE_ERROR_NOMATCH, and "Partial match:" followed by the partially matching +substring when \fBpcre[16|32]_exec()\fP returns PCRE_ERROR_PARTIAL. (Note that +this is the entire substring that was inspected during the partial match; it +may include characters before the actual match start if a lookbehind assertion, +\eK, \eb, or \eB was involved.) For any other return, \fBpcretest\fP outputs +the PCRE negative error number and a short descriptive phrase. If the error is +a failed UTF string check, the offset of the start of the failing character and +the reason code are also output, provided that the size of the output vector is +at least two. Here is an example of an interactive \fBpcretest\fP run. +.sp + $ pcretest + PCRE version 8.13 2011-04-30 +.sp + re> /^abc(\ed+)/ + data> abc123 + 0: abc123 + 1: 123 + data> xyz + No match +.sp +Unset capturing substrings that are not followed by one that is set are not +returned by \fBpcre[16|32]_exec()\fP, and are not shown by \fBpcretest\fP. In the +following example, there are two capturing substrings, but when the first data +line is matched, the second, unset substring is not shown. An "internal" unset +substring is shown as "<unset>", as for the second data line. +.sp + re> /(a)|(b)/ + data> a + 0: a + 1: a + data> b + 0: b + 1: <unset> + 2: b +.sp +If the strings contain any non-printing characters, they are output as \exhh +escapes if the value is less than 256 and UTF mode is not set. Otherwise they +are output as \ex{hh...} escapes. See below for the definition of non-printing +characters. If the pattern has the \fB/+\fP modifier, the output for substring +0 is followed by the the rest of the subject string, identified by "0+" like +this: +.sp + re> /cat/+ + data> cataract + 0: cat + 0+ aract +.sp +If the pattern has the \fB/g\fP or \fB/G\fP modifier, the results of successive +matching attempts are output in sequence, like this: +.sp + re> /\eBi(\ew\ew)/g + data> Mississippi + 0: iss + 1: ss + 0: iss + 1: ss + 0: ipp + 1: pp +.sp +"No match" is output only if the first match attempt fails. Here is an example +of a failure message (the offset 4 that is specified by \e>4 is past the end of +the subject string): +.sp + re> /xyz/ + data> xyz\e>4 + Error -24 (bad offset value) +.P +If any of the sequences \fB\eC\fP, \fB\eG\fP, or \fB\eL\fP are present in a +data line that is successfully matched, the substrings extracted by the +convenience functions are output with C, G, or L after the string number +instead of a colon. This is in addition to the normal full list. The string +length (that is, the return from the extraction function) is given in +parentheses after each string for \fB\eC\fP and \fB\eG\fP. +.P +Note that whereas patterns can be continued over several lines (a plain ">" +prompt is used for continuations), data lines may not. However newlines can be +included in data by means of the \en escape (or \er, \er\en, etc., depending on +the newline sequence setting). +. +. +. +.SH "OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION" +.rs +.sp +When the alternative matching function, \fBpcre[16|32]_dfa_exec()\fP, is used (by +means of the \eD escape sequence or the \fB-dfa\fP command line option), the +output consists of a list of all the matches that start at the first point in +the subject where there is at least one match. For example: +.sp + re> /(tang|tangerine|tan)/ + data> yellow tangerine\eD + 0: tangerine + 1: tang + 2: tan +.sp +(Using the normal matching function on this data finds only "tang".) The +longest matching string is always given first (and numbered zero). After a +PCRE_ERROR_PARTIAL return, the output is "Partial match:", followed by the +partially matching substring. (Note that this is the entire substring that was +inspected during the partial match; it may include characters before the actual +match start if a lookbehind assertion, \eK, \eb, or \eB was involved.) +.P +If \fB/g\fP is present on the pattern, the search for further matches resumes +at the end of the longest match. For example: +.sp + re> /(tang|tangerine|tan)/g + data> yellow tangerine and tangy sultana\eD + 0: tangerine + 1: tang + 2: tan + 0: tang + 1: tan + 0: tan +.sp +Since the matching function does not support substring capture, the escape +sequences that are concerned with captured substrings are not relevant. +. +. +.SH "RESTARTING AFTER A PARTIAL MATCH" +.rs +.sp +When the alternative matching function has given the PCRE_ERROR_PARTIAL return, +indicating that the subject partially matched the pattern, you can restart the +match with additional subject data by means of the \eR escape sequence. For +example: +.sp + re> /^\ed?\ed(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\ed\ed$/ + data> 23ja\eP\eD + Partial match: 23ja + data> n05\eR\eD + 0: n05 +.sp +For further information about partial matching, see the +.\" HREF +\fBpcrepartial\fP +.\" +documentation. +. +. +.SH CALLOUTS +.rs +.sp +If the pattern contains any callout requests, \fBpcretest\fP's callout function +is called during matching. This works with both matching functions. By default, +the called function displays the callout number, the start and current +positions in the text at the callout time, and the next pattern item to be +tested. For example: +.sp + --->pqrabcdef + 0 ^ ^ \ed +.sp +This output indicates that callout number 0 occurred for a match attempt +starting at the fourth character of the subject string, when the pointer was at +the seventh character of the data, and when the next pattern item was \ed. Just +one circumflex is output if the start and current positions are the same. +.P +Callouts numbered 255 are assumed to be automatic callouts, inserted as a +result of the \fB/C\fP pattern modifier. In this case, instead of showing the +callout number, the offset in the pattern, preceded by a plus, is output. For +example: +.sp + re> /\ed?[A-E]\e*/C + data> E* + --->E* + +0 ^ \ed? + +3 ^ [A-E] + +8 ^^ \e* + +10 ^ ^ + 0: E* +.sp +If a pattern contains (*MARK) items, an additional line is output whenever +a change of latest mark is passed to the callout function. For example: +.sp + re> /a(*MARK:X)bc/C + data> abc + --->abc + +0 ^ a + +1 ^^ (*MARK:X) + +10 ^^ b + Latest Mark: X + +11 ^ ^ c + +12 ^ ^ + 0: abc +.sp +The mark changes between matching "a" and "b", but stays the same for the rest +of the match, so nothing more is output. If, as a result of backtracking, the +mark reverts to being unset, the text "<unset>" is output. +.P +The callout function in \fBpcretest\fP returns zero (carry on matching) by +default, but you can use a \eC item in a data line (as described above) to +change this and other parameters of the callout. +.P +Inserting callouts can be helpful when using \fBpcretest\fP to check +complicated regular expressions. For further information about callouts, see +the +.\" HREF +\fBpcrecallout\fP +.\" +documentation. +. +. +. +.SH "NON-PRINTING CHARACTERS" +.rs +.sp +When \fBpcretest\fP is outputting text in the compiled version of a pattern, +bytes other than 32-126 are always treated as non-printing characters are are +therefore shown as hex escapes. +.P +When \fBpcretest\fP is outputting text that is a matched part of a subject +string, it behaves in the same way, unless a different locale has been set for +the pattern (using the \fB/L\fP modifier). In this case, the \fBisprint()\fP +function to distinguish printing and non-printing characters. +. +. +. +.SH "SAVING AND RELOADING COMPILED PATTERNS" +.rs +.sp +The facilities described in this section are not available when the POSIX +interface to PCRE is being used, that is, when the \fB/P\fP pattern modifier is +specified. +.P +When the POSIX interface is not in use, you can cause \fBpcretest\fP to write a +compiled pattern to a file, by following the modifiers with > and a file name. +For example: +.sp + /pattern/im >/some/file +.sp +See the +.\" HREF +\fBpcreprecompile\fP +.\" +documentation for a discussion about saving and re-using compiled patterns. +Note that if the pattern was successfully studied with JIT optimization, the +JIT data cannot be saved. +.P +The data that is written is binary. The first eight bytes are the length of the +compiled pattern data followed by the length of the optional study data, each +written as four bytes in big-endian order (most significant byte first). If +there is no study data (either the pattern was not studied, or studying did not +return any data), the second length is zero. The lengths are followed by an +exact copy of the compiled pattern. If there is additional study data, this +(excluding any JIT data) follows immediately after the compiled pattern. After +writing the file, \fBpcretest\fP expects to read a new pattern. +.P +A saved pattern can be reloaded into \fBpcretest\fP by specifying < and a file +name instead of a pattern. There must be no space between < and the file name, +which must not contain a < character, as otherwise \fBpcretest\fP will +interpret the line as a pattern delimited by < characters. For example: +.sp + re> </some/file + Compiled pattern loaded from /some/file + No study data +.sp +If the pattern was previously studied with the JIT optimization, the JIT +information cannot be saved and restored, and so is lost. When the pattern has +been loaded, \fBpcretest\fP proceeds to read data lines in the usual way. +.P +You can copy a file written by \fBpcretest\fP to a different host and reload it +there, even if the new host has opposite endianness to the one on which the +pattern was compiled. For example, you can compile on an i86 machine and run on +a SPARC machine. When a pattern is reloaded on a host with different +endianness, the confirmation message is changed to: +.sp + Compiled pattern (byte-inverted) loaded from /some/file +.sp +The test suite contains some saved pre-compiled patterns with different +endianness. These are reloaded using "<!" instead of just "<". This suppresses +the "(byte-inverted)" text so that the output is the same on all hosts. It also +forces debugging output once the pattern has been reloaded. +.P +File names for saving and reloading can be absolute or relative, but note that +the shell facility of expanding a file name that starts with a tilde (~) is not +available. +.P +The ability to save and reload files in \fBpcretest\fP is intended for testing +and experimentation. It is not intended for production use because only a +single pattern can be written to a file. Furthermore, there is no facility for +supplying custom character tables for use with a reloaded pattern. If the +original pattern was compiled with custom tables, an attempt to match a subject +string using a reloaded pattern is likely to cause \fBpcretest\fP to crash. +Finally, if you attempt to load a file that is not in the correct format, the +result is undefined. +. +. +.SH "SEE ALSO" +.rs +.sp +\fBpcre\fP(3), \fBpcre16\fP(3), \fBpcre32\fP(3), \fBpcreapi\fP(3), +\fBpcrecallout\fP(3), +\fBpcrejit\fP, \fBpcrematching\fP(3), \fBpcrepartial\fP(d), +\fBpcrepattern\fP(3), \fBpcreprecompile\fP(3). +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 09 February 2014 +Copyright (c) 1997-2014 University of Cambridge. +.fi diff --git a/plugins/Pcre16/docs/doc/pcretest.txt b/plugins/Pcre16/docs/doc/pcretest.txt new file mode 100644 index 0000000000..55de502443 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcretest.txt @@ -0,0 +1,1087 @@ +PCRETEST(1) General Commands Manual PCRETEST(1) + + + +NAME + pcretest - a program for testing Perl-compatible regular expressions. + +SYNOPSIS + + pcretest [options] [input file [output file]] + + pcretest was written as a test program for the PCRE regular expression + library itself, but it can also be used for experimenting with regular + expressions. This document describes the features of the test program; + for details of the regular expressions themselves, see the pcrepattern + documentation. For details of the PCRE library function calls and their + options, see the pcreapi , pcre16 and pcre32 documentation. + + The input for pcretest is a sequence of regular expression patterns and + strings to be matched, as described below. The output shows the result + of each match. Options on the command line and the patterns control + PCRE options and exactly what is output. + + As PCRE has evolved, it has acquired many different features, and as a + result, pcretest now has rather a lot of obscure options for testing + every possible feature. Some of these options are specifically designed + for use in conjunction with the test script and data files that are + distributed as part of PCRE, and are unlikely to be of use otherwise. + They are all documented here, but without much justification. + + +INPUT DATA FORMAT + + Input to pcretest is processed line by line, either by calling the C + library's fgets() function, or via the libreadline library (see below). + In Unix-like environments, fgets() treats any bytes other than newline + as data characters. However, in some Windows environments character 26 + (hex 1A) causes an immediate end of file, and no further data is read. + For maximum portability, therefore, it is safest to use only ASCII + characters in pcretest input files. + + +PCRE's 8-BIT, 16-BIT AND 32-BIT LIBRARIES + + From release 8.30, two separate PCRE libraries can be built. The origi- + nal one supports 8-bit character strings, whereas the newer 16-bit + library supports character strings encoded in 16-bit units. From + release 8.32, a third library can be built, supporting character + strings encoded in 32-bit units. The pcretest program can be used to + test all three libraries. However, it is itself still an 8-bit program, + reading 8-bit input and writing 8-bit output. When testing the 16-bit + or 32-bit library, the patterns and data strings are converted to 16- + or 32-bit format before being passed to the PCRE library functions. + Results are converted to 8-bit for output. + + References to functions and structures of the form pcre[16|32]_xx below + mean "pcre_xx when using the 8-bit library, pcre16_xx when using the + 16-bit library, or pcre32_xx when using the 32-bit library". + + +COMMAND LINE OPTIONS + + -8 If both the 8-bit library has been built, this option causes + the 8-bit library to be used (which is the default); if the + 8-bit library has not been built, this option causes an + error. + + -16 If both the 8-bit or the 32-bit, and the 16-bit libraries + have been built, this option causes the 16-bit library to be + used. If only the 16-bit library has been built, this is the + default (so has no effect). If only the 8-bit or the 32-bit + library has been built, this option causes an error. + + -32 If both the 8-bit or the 16-bit, and the 32-bit libraries + have been built, this option causes the 32-bit library to be + used. If only the 32-bit library has been built, this is the + default (so has no effect). If only the 8-bit or the 16-bit + library has been built, this option causes an error. + + -b Behave as if each pattern has the /B (show byte code) modi- + fier; the internal form is output after compilation. + + -C Output the version number of the PCRE library, and all avail- + able information about the optional features that are + included, and then exit with zero exit code. All other + options are ignored. + + -C option Output information about a specific build-time option, then + exit. This functionality is intended for use in scripts such + as RunTest. The following options output the value and set + the exit code as indicated: + + ebcdic-nl the code for LF (= NL) in an EBCDIC environment: + 0x15 or 0x25 + 0 if used in an ASCII environment + exit code is always 0 + linksize the configured internal link size (2, 3, or 4) + exit code is set to the link size + newline the default newline setting: + CR, LF, CRLF, ANYCRLF, or ANY + exit code is always 0 + bsr the default setting for what \R matches: + ANYCRLF or ANY + exit code is always 0 + + The following options output 1 for true or 0 for false, and + set the exit code to the same value: + + ebcdic compiled for an EBCDIC environment + jit just-in-time support is available + pcre16 the 16-bit library was built + pcre32 the 32-bit library was built + pcre8 the 8-bit library was built + ucp Unicode property support is available + utf UTF-8 and/or UTF-16 and/or UTF-32 support + is available + + If an unknown option is given, an error message is output; + the exit code is 0. + + -d Behave as if each pattern has the /D (debug) modifier; the + internal form and information about the compiled pattern is + output after compilation; -d is equivalent to -b -i. + + -dfa Behave as if each data line contains the \D escape sequence; + this causes the alternative matching function, + pcre[16|32]_dfa_exec(), to be used instead of the standard + pcre[16|32]_exec() function (more detail is given below). + + -help Output a brief summary these options and then exit. + + -i Behave as if each pattern has the /I modifier; information + about the compiled pattern is given after compilation. + + -M Behave as if each data line contains the \M escape sequence; + this causes PCRE to discover the minimum MATCH_LIMIT and + MATCH_LIMIT_RECURSION settings by calling pcre[16|32]_exec() + repeatedly with different limits. + + -m Output the size of each compiled pattern after it has been + compiled. This is equivalent to adding /M to each regular + expression. The size is given in bytes for both libraries. + + -O Behave as if each pattern has the /O modifier, that is dis- + able auto-possessification for all patterns. + + -o osize Set the number of elements in the output vector that is used + when calling pcre[16|32]_exec() or pcre[16|32]_dfa_exec() to + be osize. The default value is 45, which is enough for 14 + capturing subexpressions for pcre[16|32]_exec() or 22 differ- + ent matches for pcre[16|32]_dfa_exec(). The vector size can + be changed for individual matching calls by including \O in + the data line (see below). + + -p Behave as if each pattern has the /P modifier; the POSIX + wrapper API is used to call PCRE. None of the other options + has any effect when -p is set. This option can be used only + with the 8-bit library. + + -q Do not output the version number of pcretest at the start of + execution. + + -S size On Unix-like systems, set the size of the run-time stack to + size megabytes. + + -s or -s+ Behave as if each pattern has the /S modifier; in other + words, force each pattern to be studied. If -s+ is used, all + the JIT compile options are passed to pcre[16|32]_study(), + causing just-in-time optimization to be set up if it is + available, for both full and partial matching. Specific JIT + compile options can be selected by following -s+ with a digit + in the range 1 to 7, which selects the JIT compile modes as + follows: + + 1 normal match only + 2 soft partial match only + 3 normal match and soft partial match + 4 hard partial match only + 6 soft and hard partial match + 7 all three modes (default) + + If -s++ is used instead of -s+ (with or without a following + digit), the text "(JIT)" is added to the first output line + after a match or no match when JIT-compiled code was actually + used. + + Note that there are pattern options that can override -s, + either specifying no studying at all, or suppressing JIT com- + pilation. + + If the /I or /D option is present on a pattern (requesting + output about the compiled pattern), information about the + result of studying is not included when studying is caused + only by -s and neither -i nor -d is present on the command + line. This behaviour means that the output from tests that + are run with and without -s should be identical, except when + options that output information about the actual running of a + match are set. + + The -M, -t, and -tm options, which give information about + resources used, are likely to produce different output with + and without -s. Output may also differ if the /C option is + present on an individual pattern. This uses callouts to trace + the the matching process, and this may be different between + studied and non-studied patterns. If the pattern contains + (*MARK) items there may also be differences, for the same + reason. The -s command line option can be overridden for spe- + cific patterns that should never be studied (see the /S pat- + tern modifier below). + + -t Run each compile, study, and match many times with a timer, + and output the resulting times per compile, study, or match + (in milliseconds). Do not set -m with -t, because you will + then get the size output a zillion times, and the timing will + be distorted. You can control the number of iterations that + are used for timing by following -t with a number (as a sepa- + rate item on the command line). For example, "-t 1000" iter- + ates 1000 times. The default is to iterate 500000 times. + + -tm This is like -t except that it times only the matching phase, + not the compile or study phases. + + -T -TM These behave like -t and -tm, but in addition, at the end of + a run, the total times for all compiles, studies, and matches + are output. + + +DESCRIPTION + + If pcretest is given two filename arguments, it reads from the first + and writes to the second. If it is given only one filename argument, it + reads from that file and writes to stdout. Otherwise, it reads from + stdin and writes to stdout, and prompts for each line of input, using + "re>" to prompt for regular expressions, and "data>" to prompt for data + lines. + + When pcretest is built, a configuration option can specify that it + should be linked with the libreadline library. When this is done, if + the input is from a terminal, it is read using the readline() function. + This provides line-editing and history facilities. The output from the + -help option states whether or not readline() will be used. + + The program handles any number of sets of input on a single input file. + Each set starts with a regular expression, and continues with any num- + ber of data lines to be matched against that pattern. + + Each data line is matched separately and independently. If you want to + do multi-line matches, you have to use the \n escape sequence (or \r or + \r\n, etc., depending on the newline setting) in a single line of input + to encode the newline sequences. There is no limit on the length of + data lines; the input buffer is automatically extended if it is too + small. + + An empty line signals the end of the data lines, at which point a new + regular expression is read. The regular expressions are given enclosed + in any non-alphanumeric delimiters other than backslash, for example: + + /(a|bc)x+yz/ + + White space before the initial delimiter is ignored. A regular expres- + sion may be continued over several input lines, in which case the new- + line characters are included within it. It is possible to include the + delimiter within the pattern by escaping it, for example + + /abc\/def/ + + If you do so, the escape and the delimiter form part of the pattern, + but since delimiters are always non-alphanumeric, this does not affect + its interpretation. If the terminating delimiter is immediately fol- + lowed by a backslash, for example, + + /abc/\ + + then a backslash is added to the end of the pattern. This is done to + provide a way of testing the error condition that arises if a pattern + finishes with a backslash, because + + /abc\/ + + is interpreted as the first line of a pattern that starts with "abc/", + causing pcretest to read the next line as a continuation of the regular + expression. + + +PATTERN MODIFIERS + + A pattern may be followed by any number of modifiers, which are mostly + single characters, though some of these can be qualified by further + characters. Following Perl usage, these are referred to below as, for + example, "the /i modifier", even though the delimiter of the pattern + need not always be a slash, and no slash is used when writing modi- + fiers. White space may appear between the final pattern delimiter and + the first modifier, and between the modifiers themselves. For refer- + ence, here is a complete list of modifiers. They fall into several + groups that are described in detail in the following sections. + + /8 set UTF mode + /9 set PCRE_NEVER_UTF (locks out UTF mode) + /? disable UTF validity check + /+ show remainder of subject after match + /= show all captures (not just those that are set) + + /A set PCRE_ANCHORED + /B show compiled code + /C set PCRE_AUTO_CALLOUT + /D same as /B plus /I + /E set PCRE_DOLLAR_ENDONLY + /F flip byte order in compiled pattern + /f set PCRE_FIRSTLINE + /G find all matches (shorten string) + /g find all matches (use startoffset) + /I show information about pattern + /i set PCRE_CASELESS + /J set PCRE_DUPNAMES + /K show backtracking control names + /L set locale + /M show compiled memory size + /m set PCRE_MULTILINE + /N set PCRE_NO_AUTO_CAPTURE + /O set PCRE_NO_AUTO_POSSESS + /P use the POSIX wrapper + /Q test external stack check function + /S study the pattern after compilation + /s set PCRE_DOTALL + /T select character tables + /U set PCRE_UNGREEDY + /W set PCRE_UCP + /X set PCRE_EXTRA + /x set PCRE_EXTENDED + /Y set PCRE_NO_START_OPTIMIZE + /Z don't show lengths in /B output + + /<any> set PCRE_NEWLINE_ANY + /<anycrlf> set PCRE_NEWLINE_ANYCRLF + /<cr> set PCRE_NEWLINE_CR + /<crlf> set PCRE_NEWLINE_CRLF + /<lf> set PCRE_NEWLINE_LF + /<bsr_anycrlf> set PCRE_BSR_ANYCRLF + /<bsr_unicode> set PCRE_BSR_UNICODE + /<JS> set PCRE_JAVASCRIPT_COMPAT + + + Perl-compatible modifiers + + The /i, /m, /s, and /x modifiers set the PCRE_CASELESS, PCRE_MULTILINE, + PCRE_DOTALL, or PCRE_EXTENDED options, respectively, when + pcre[16|32]_compile() is called. These four modifier letters have the + same effect as they do in Perl. For example: + + /caseless/i + + + Modifiers for other PCRE options + + The following table shows additional modifiers for setting PCRE com- + pile-time options that do not correspond to anything in Perl: + + /8 PCRE_UTF8 ) when using the 8-bit + /? PCRE_NO_UTF8_CHECK ) library + + /8 PCRE_UTF16 ) when using the 16-bit + /? PCRE_NO_UTF16_CHECK ) library + + /8 PCRE_UTF32 ) when using the 32-bit + /? PCRE_NO_UTF32_CHECK ) library + + /9 PCRE_NEVER_UTF + /A PCRE_ANCHORED + /C PCRE_AUTO_CALLOUT + /E PCRE_DOLLAR_ENDONLY + /f PCRE_FIRSTLINE + /J PCRE_DUPNAMES + /N PCRE_NO_AUTO_CAPTURE + /O PCRE_NO_AUTO_POSSESS + /U PCRE_UNGREEDY + /W PCRE_UCP + /X PCRE_EXTRA + /Y PCRE_NO_START_OPTIMIZE + /<any> PCRE_NEWLINE_ANY + /<anycrlf> PCRE_NEWLINE_ANYCRLF + /<cr> PCRE_NEWLINE_CR + /<crlf> PCRE_NEWLINE_CRLF + /<lf> PCRE_NEWLINE_LF + /<bsr_anycrlf> PCRE_BSR_ANYCRLF + /<bsr_unicode> PCRE_BSR_UNICODE + /<JS> PCRE_JAVASCRIPT_COMPAT + + The modifiers that are enclosed in angle brackets are literal strings + as shown, including the angle brackets, but the letters within can be + in either case. This example sets multiline matching with CRLF as the + line ending sequence: + + /^abc/m<CRLF> + + As well as turning on the PCRE_UTF8/16/32 option, the /8 modifier + causes all non-printing characters in output strings to be printed + using the \x{hh...} notation. Otherwise, those less than 0x100 are out- + put in hex without the curly brackets. + + Full details of the PCRE options are given in the pcreapi documenta- + tion. + + Finding all matches in a string + + Searching for all possible matches within each subject string can be + requested by the /g or /G modifier. After finding a match, PCRE is + called again to search the remainder of the subject string. The differ- + ence between /g and /G is that the former uses the startoffset argument + to pcre[16|32]_exec() to start searching at a new point within the + entire string (which is in effect what Perl does), whereas the latter + passes over a shortened substring. This makes a difference to the + matching process if the pattern begins with a lookbehind assertion + (including \b or \B). + + If any call to pcre[16|32]_exec() in a /g or /G sequence matches an + empty string, the next call is done with the PCRE_NOTEMPTY_ATSTART and + PCRE_ANCHORED flags set in order to search for another, non-empty, + match at the same point. If this second match fails, the start offset + is advanced, and the normal match is retried. This imitates the way + Perl handles such cases when using the /g modifier or the split() func- + tion. Normally, the start offset is advanced by one character, but if + the newline convention recognizes CRLF as a newline, and the current + character is CR followed by LF, an advance of two is used. + + Other modifiers + + There are yet more modifiers for controlling the way pcretest operates. + + The /+ modifier requests that as well as outputting the substring that + matched the entire pattern, pcretest should in addition output the + remainder of the subject string. This is useful for tests where the + subject contains multiple copies of the same substring. If the + modi- + fier appears twice, the same action is taken for captured substrings. + In each case the remainder is output on the following line with a plus + character following the capture number. Note that this modifier must + not immediately follow the /S modifier because /S+ and /S++ have other + meanings. + + The /= modifier requests that the values of all potential captured + parentheses be output after a match. By default, only those up to the + highest one actually used in the match are output (corresponding to the + return code from pcre[16|32]_exec()). Values in the offsets vector cor- + responding to higher numbers should be set to -1, and these are output + as "<unset>". This modifier gives a way of checking that this is hap- + pening. + + The /B modifier is a debugging feature. It requests that pcretest out- + put a representation of the compiled code after compilation. Normally + this information contains length and offset values; however, if /Z is + also present, this data is replaced by spaces. This is a special fea- + ture for use in the automatic test scripts; it ensures that the same + output is generated for different internal link sizes. + + The /D modifier is a PCRE debugging feature, and is equivalent to /BI, + that is, both the /B and the /I modifiers. + + The /F modifier causes pcretest to flip the byte order of the 2-byte + and 4-byte fields in the compiled pattern. This facility is for testing + the feature in PCRE that allows it to execute patterns that were com- + piled on a host with a different endianness. This feature is not avail- + able when the POSIX interface to PCRE is being used, that is, when the + /P pattern modifier is specified. See also the section about saving and + reloading compiled patterns below. + + The /I modifier requests that pcretest output information about the + compiled pattern (whether it is anchored, has a fixed first character, + and so on). It does this by calling pcre[16|32]_fullinfo() after com- + piling a pattern. If the pattern is studied, the results of that are + also output. In this output, the word "char" means a non-UTF character, + that is, the value of a single data item (8-bit, 16-bit, or 32-bit, + depending on the library that is being tested). + + The /K modifier requests pcretest to show names from backtracking con- + trol verbs that are returned from calls to pcre[16|32]_exec(). It + causes pcretest to create a pcre[16|32]_extra block if one has not + already been created by a call to pcre[16|32]_study(), and to set the + PCRE_EXTRA_MARK flag and the mark field within it, every time that + pcre[16|32]_exec() is called. If the variable that the mark field + points to is non-NULL for a match, non-match, or partial match, + pcretest prints the string to which it points. For a match, this is + shown on a line by itself, tagged with "MK:". For a non-match it is + added to the message. + + The /L modifier must be followed directly by the name of a locale, for + example, + + /pattern/Lfr_FR + + For this reason, it must be the last modifier. The given locale is set, + pcre[16|32]_maketables() is called to build a set of character tables + for the locale, and this is then passed to pcre[16|32]_compile() when + compiling the regular expression. Without an /L (or /T) modifier, NULL + is passed as the tables pointer; that is, /L applies only to the + expression on which it appears. + + The /M modifier causes the size in bytes of the memory block used to + hold the compiled pattern to be output. This does not include the size + of the pcre[16|32] block; it is just the actual compiled data. If the + pattern is successfully studied with the PCRE_STUDY_JIT_COMPILE option, + the size of the JIT compiled code is also output. + + The /Q modifier is used to test the use of pcre_stack_guard. It must be + followed by '0' or '1', specifying the return code to be given from an + external function that is passed to PCRE and used for stack checking + during compilation (see the pcreapi documentation for details). + + The /S modifier causes pcre[16|32]_study() to be called after the + expression has been compiled, and the results used when the expression + is matched. There are a number of qualifying characters that may follow + /S. They may appear in any order. + + If /S is followed by an exclamation mark, pcre[16|32]_study() is called + with the PCRE_STUDY_EXTRA_NEEDED option, causing it always to return a + pcre_extra block, even when studying discovers no useful information. + + If /S is followed by a second S character, it suppresses studying, even + if it was requested externally by the -s command line option. This + makes it possible to specify that certain patterns are always studied, + and others are never studied, independently of -s. This feature is used + in the test files in a few cases where the output is different when the + pattern is studied. + + If the /S modifier is followed by a + character, the call to + pcre[16|32]_study() is made with all the JIT study options, requesting + just-in-time optimization support if it is available, for both normal + and partial matching. If you want to restrict the JIT compiling modes, + you can follow /S+ with a digit in the range 1 to 7: + + 1 normal match only + 2 soft partial match only + 3 normal match and soft partial match + 4 hard partial match only + 6 soft and hard partial match + 7 all three modes (default) + + If /S++ is used instead of /S+ (with or without a following digit), the + text "(JIT)" is added to the first output line after a match or no + match when JIT-compiled code was actually used. + + Note that there is also an independent /+ modifier; it must not be + given immediately after /S or /S+ because this will be misinterpreted. + + If JIT studying is successful, the compiled JIT code will automatically + be used when pcre[16|32]_exec() is run, except when incompatible run- + time options are specified. For more details, see the pcrejit documen- + tation. See also the \J escape sequence below for a way of setting the + size of the JIT stack. + + Finally, if /S is followed by a minus character, JIT compilation is + suppressed, even if it was requested externally by the -s command line + option. This makes it possible to specify that JIT is never to be used + for certain patterns. + + The /T modifier must be followed by a single digit. It causes a spe- + cific set of built-in character tables to be passed to pcre[16|32]_com- + pile(). It is used in the standard PCRE tests to check behaviour with + different character tables. The digit specifies the tables as follows: + + 0 the default ASCII tables, as distributed in + pcre_chartables.c.dist + 1 a set of tables defining ISO 8859 characters + + In table 1, some characters whose codes are greater than 128 are iden- + tified as letters, digits, spaces, etc. + + Using the POSIX wrapper API + + The /P modifier causes pcretest to call PCRE via the POSIX wrapper API + rather than its native API. This supports only the 8-bit library. When + /P is set, the following modifiers set options for the regcomp() func- + tion: + + /i REG_ICASE + /m REG_NEWLINE + /N REG_NOSUB + /s REG_DOTALL ) + /U REG_UNGREEDY ) These options are not part of + /W REG_UCP ) the POSIX standard + /8 REG_UTF8 ) + + The /+ modifier works as described above. All other modifiers are + ignored. + + Locking out certain modifiers + + PCRE can be compiled with or without support for certain features such + as UTF-8/16/32 or Unicode properties. Accordingly, the standard tests + are split up into a number of different files that are selected for + running depending on which features are available. When updating the + tests, it is all too easy to put a new test into the wrong file by mis- + take; for example, to put a test that requires UTF support into a file + that is used when it is not available. To help detect such mistakes as + early as possible, there is a facility for locking out specific modi- + fiers. If an input line for pcretest starts with the string "< forbid " + the following sequence of characters is taken as a list of forbidden + modifiers. For example, in the test files that must not use UTF or Uni- + code property support, this line appears: + + < forbid 8W + + This locks out the /8 and /W modifiers. An immediate error is given if + they are subsequently encountered. If the character string contains < + but not >, all the multi-character modifiers that begin with < are + locked out. Otherwise, such modifiers must be explicitly listed, for + example: + + < forbid <JS><cr> + + There must be a single space between < and "forbid" for this feature to + be recognised. If there is not, the line is interpreted either as a + request to re-load a pre-compiled pattern (see "SAVING AND RELOADING + COMPILED PATTERNS" below) or, if there is a another < character, as a + pattern that uses < as its delimiter. + + +DATA LINES + + Before each data line is passed to pcre[16|32]_exec(), leading and + trailing white space is removed, and it is then scanned for \ escapes. + Some of these are pretty esoteric features, intended for checking out + some of the more complicated features of PCRE. If you are just testing + "ordinary" regular expressions, you probably don't need any of these. + The following escapes are recognized: + + \a alarm (BEL, \x07) + \b backspace (\x08) + \e escape (\x27) + \f form feed (\x0c) + \n newline (\x0a) + \qdd set the PCRE_MATCH_LIMIT limit to dd + (any number of digits) + \r carriage return (\x0d) + \t tab (\x09) + \v vertical tab (\x0b) + \nnn octal character (up to 3 octal digits); always + a byte unless > 255 in UTF-8 or 16-bit or 32-bit mode + \o{dd...} octal character (any number of octal digits} + \xhh hexadecimal byte (up to 2 hex digits) + \x{hh...} hexadecimal character (any number of hex digits) + \A pass the PCRE_ANCHORED option to pcre[16|32]_exec() + or pcre[16|32]_dfa_exec() + \B pass the PCRE_NOTBOL option to pcre[16|32]_exec() + or pcre[16|32]_dfa_exec() + \Cdd call pcre[16|32]_copy_substring() for substring dd + after a successful match (number less than 32) + \Cname call pcre[16|32]_copy_named_substring() for substring + "name" after a successful match (name termin- + ated by next non alphanumeric character) + \C+ show the current captured substrings at callout + time + \C- do not supply a callout function + \C!n return 1 instead of 0 when callout number n is + reached + \C!n!m return 1 instead of 0 when callout number n is + reached for the nth time + \C*n pass the number n (may be negative) as callout + data; this is used as the callout return value + \D use the pcre[16|32]_dfa_exec() match function + \F only shortest match for pcre[16|32]_dfa_exec() + \Gdd call pcre[16|32]_get_substring() for substring dd + after a successful match (number less than 32) + \Gname call pcre[16|32]_get_named_substring() for substring + "name" after a successful match (name termin- + ated by next non-alphanumeric character) + \Jdd set up a JIT stack of dd kilobytes maximum (any + number of digits) + \L call pcre[16|32]_get_substringlist() after a + successful match + \M discover the minimum MATCH_LIMIT and + MATCH_LIMIT_RECURSION settings + \N pass the PCRE_NOTEMPTY option to pcre[16|32]_exec() + or pcre[16|32]_dfa_exec(); if used twice, pass the + PCRE_NOTEMPTY_ATSTART option + \Odd set the size of the output vector passed to + pcre[16|32]_exec() to dd (any number of digits) + \P pass the PCRE_PARTIAL_SOFT option to pcre[16|32]_exec() + or pcre[16|32]_dfa_exec(); if used twice, pass the + PCRE_PARTIAL_HARD option + \Qdd set the PCRE_MATCH_LIMIT_RECURSION limit to dd + (any number of digits) + \R pass the PCRE_DFA_RESTART option to pcre[16|32]_dfa_exec() + \S output details of memory get/free calls during matching + \Y pass the PCRE_NO_START_OPTIMIZE option to + pcre[16|32]_exec() + or pcre[16|32]_dfa_exec() + \Z pass the PCRE_NOTEOL option to pcre[16|32]_exec() + or pcre[16|32]_dfa_exec() + \? pass the PCRE_NO_UTF[8|16|32]_CHECK option to + pcre[16|32]_exec() or pcre[16|32]_dfa_exec() + \>dd start the match at offset dd (optional "-"; then + any number of digits); this sets the startoffset + argument for pcre[16|32]_exec() or + pcre[16|32]_dfa_exec() + \<cr> pass the PCRE_NEWLINE_CR option to pcre[16|32]_exec() + or pcre[16|32]_dfa_exec() + \<lf> pass the PCRE_NEWLINE_LF option to pcre[16|32]_exec() + or pcre[16|32]_dfa_exec() + \<crlf> pass the PCRE_NEWLINE_CRLF option to pcre[16|32]_exec() + or pcre[16|32]_dfa_exec() + \<anycrlf> pass the PCRE_NEWLINE_ANYCRLF option to pcre[16|32]_exec() + or pcre[16|32]_dfa_exec() + \<any> pass the PCRE_NEWLINE_ANY option to pcre[16|32]_exec() + or pcre[16|32]_dfa_exec() + + The use of \x{hh...} is not dependent on the use of the /8 modifier on + the pattern. It is recognized always. There may be any number of hexa- + decimal digits inside the braces; invalid values provoke error mes- + sages. + + Note that \xhh specifies one byte rather than one character in UTF-8 + mode; this makes it possible to construct invalid UTF-8 sequences for + testing purposes. On the other hand, \x{hh} is interpreted as a UTF-8 + character in UTF-8 mode, generating more than one byte if the value is + greater than 127. When testing the 8-bit library not in UTF-8 mode, + \x{hh} generates one byte for values less than 256, and causes an error + for greater values. + + In UTF-16 mode, all 4-digit \x{hhhh} values are accepted. This makes it + possible to construct invalid UTF-16 sequences for testing purposes. + + In UTF-32 mode, all 4- to 8-digit \x{...} values are accepted. This + makes it possible to construct invalid UTF-32 sequences for testing + purposes. + + The escapes that specify line ending sequences are literal strings, + exactly as shown. No more than one newline setting should be present in + any data line. + + A backslash followed by anything else just escapes the anything else. + If the very last character is a backslash, it is ignored. This gives a + way of passing an empty line as data, since a real empty line termi- + nates the data input. + + The \J escape provides a way of setting the maximum stack size that is + used by the just-in-time optimization code. It is ignored if JIT opti- + mization is not being used. Providing a stack that is larger than the + default 32K is necessary only for very complicated patterns. + + If \M is present, pcretest calls pcre[16|32]_exec() several times, with + different values in the match_limit and match_limit_recursion fields of + the pcre[16|32]_extra data structure, until it finds the minimum num- + bers for each parameter that allow pcre[16|32]_exec() to complete with- + out error. Because this is testing a specific feature of the normal + interpretive pcre[16|32]_exec() execution, the use of any JIT optimiza- + tion that might have been set up by the /S+ qualifier of -s+ option is + disabled. + + The match_limit number is a measure of the amount of backtracking that + takes place, and checking it out can be instructive. For most simple + matches, the number is quite small, but for patterns with very large + numbers of matching possibilities, it can become large very quickly + with increasing length of subject string. The match_limit_recursion + number is a measure of how much stack (or, if PCRE is compiled with + NO_RECURSE, how much heap) memory is needed to complete the match + attempt. + + When \O is used, the value specified may be higher or lower than the + size set by the -O command line option (or defaulted to 45); \O applies + only to the call of pcre[16|32]_exec() for the line in which it + appears. + + If the /P modifier was present on the pattern, causing the POSIX wrap- + per API to be used, the only option-setting sequences that have any + effect are \B, \N, and \Z, causing REG_NOTBOL, REG_NOTEMPTY, and + REG_NOTEOL, respectively, to be passed to regexec(). + + +THE ALTERNATIVE MATCHING FUNCTION + + By default, pcretest uses the standard PCRE matching function, + pcre[16|32]_exec() to match each data line. PCRE also supports an + alternative matching function, pcre[16|32]_dfa_test(), which operates + in a different way, and has some restrictions. The differences between + the two functions are described in the pcrematching documentation. + + If a data line contains the \D escape sequence, or if the command line + contains the -dfa option, the alternative matching function is used. + This function finds all possible matches at a given point. If, however, + the \F escape sequence is present in the data line, it stops after the + first match is found. This is always the shortest possible match. + + +DEFAULT OUTPUT FROM PCRETEST + + This section describes the output when the normal matching function, + pcre[16|32]_exec(), is being used. + + When a match succeeds, pcretest outputs the list of captured substrings + that pcre[16|32]_exec() returns, starting with number 0 for the string + that matched the whole pattern. Otherwise, it outputs "No match" when + the return is PCRE_ERROR_NOMATCH, and "Partial match:" followed by the + partially matching substring when pcre[16|32]_exec() returns + PCRE_ERROR_PARTIAL. (Note that this is the entire substring that was + inspected during the partial match; it may include characters before + the actual match start if a lookbehind assertion, \K, \b, or \B was + involved.) For any other return, pcretest outputs the PCRE negative + error number and a short descriptive phrase. If the error is a failed + UTF string check, the offset of the start of the failing character and + the reason code are also output, provided that the size of the output + vector is at least two. Here is an example of an interactive pcretest + run. + + $ pcretest + PCRE version 8.13 2011-04-30 + + re> /^abc(\d+)/ + data> abc123 + 0: abc123 + 1: 123 + data> xyz + No match + + Unset capturing substrings that are not followed by one that is set are + not returned by pcre[16|32]_exec(), and are not shown by pcretest. In + the following example, there are two capturing substrings, but when the + first data line is matched, the second, unset substring is not shown. + An "internal" unset substring is shown as "<unset>", as for the second + data line. + + re> /(a)|(b)/ + data> a + 0: a + 1: a + data> b + 0: b + 1: <unset> + 2: b + + If the strings contain any non-printing characters, they are output as + \xhh escapes if the value is less than 256 and UTF mode is not set. + Otherwise they are output as \x{hh...} escapes. See below for the defi- + nition of non-printing characters. If the pattern has the /+ modifier, + the output for substring 0 is followed by the the rest of the subject + string, identified by "0+" like this: + + re> /cat/+ + data> cataract + 0: cat + 0+ aract + + If the pattern has the /g or /G modifier, the results of successive + matching attempts are output in sequence, like this: + + re> /\Bi(\w\w)/g + data> Mississippi + 0: iss + 1: ss + 0: iss + 1: ss + 0: ipp + 1: pp + + "No match" is output only if the first match attempt fails. Here is an + example of a failure message (the offset 4 that is specified by \>4 is + past the end of the subject string): + + re> /xyz/ + data> xyz\>4 + Error -24 (bad offset value) + + If any of the sequences \C, \G, or \L are present in a data line that + is successfully matched, the substrings extracted by the convenience + functions are output with C, G, or L after the string number instead of + a colon. This is in addition to the normal full list. The string length + (that is, the return from the extraction function) is given in paren- + theses after each string for \C and \G. + + Note that whereas patterns can be continued over several lines (a plain + ">" prompt is used for continuations), data lines may not. However new- + lines can be included in data by means of the \n escape (or \r, \r\n, + etc., depending on the newline sequence setting). + + +OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION + + When the alternative matching function, pcre[16|32]_dfa_exec(), is used + (by means of the \D escape sequence or the -dfa command line option), + the output consists of a list of all the matches that start at the + first point in the subject where there is at least one match. For exam- + ple: + + re> /(tang|tangerine|tan)/ + data> yellow tangerine\D + 0: tangerine + 1: tang + 2: tan + + (Using the normal matching function on this data finds only "tang".) + The longest matching string is always given first (and numbered zero). + After a PCRE_ERROR_PARTIAL return, the output is "Partial match:", fol- + lowed by the partially matching substring. (Note that this is the + entire substring that was inspected during the partial match; it may + include characters before the actual match start if a lookbehind asser- + tion, \K, \b, or \B was involved.) + + If /g is present on the pattern, the search for further matches resumes + at the end of the longest match. For example: + + re> /(tang|tangerine|tan)/g + data> yellow tangerine and tangy sultana\D + 0: tangerine + 1: tang + 2: tan + 0: tang + 1: tan + 0: tan + + Since the matching function does not support substring capture, the + escape sequences that are concerned with captured substrings are not + relevant. + + +RESTARTING AFTER A PARTIAL MATCH + + When the alternative matching function has given the PCRE_ERROR_PARTIAL + return, indicating that the subject partially matched the pattern, you + can restart the match with additional subject data by means of the \R + escape sequence. For example: + + re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ + data> 23ja\P\D + Partial match: 23ja + data> n05\R\D + 0: n05 + + For further information about partial matching, see the pcrepartial + documentation. + + +CALLOUTS + + If the pattern contains any callout requests, pcretest's callout func- + tion is called during matching. This works with both matching func- + tions. By default, the called function displays the callout number, the + start and current positions in the text at the callout time, and the + next pattern item to be tested. For example: + + --->pqrabcdef + 0 ^ ^ \d + + This output indicates that callout number 0 occurred for a match + attempt starting at the fourth character of the subject string, when + the pointer was at the seventh character of the data, and when the next + pattern item was \d. Just one circumflex is output if the start and + current positions are the same. + + Callouts numbered 255 are assumed to be automatic callouts, inserted as + a result of the /C pattern modifier. In this case, instead of showing + the callout number, the offset in the pattern, preceded by a plus, is + output. For example: + + re> /\d?[A-E]\*/C + data> E* + --->E* + +0 ^ \d? + +3 ^ [A-E] + +8 ^^ \* + +10 ^ ^ + 0: E* + + If a pattern contains (*MARK) items, an additional line is output when- + ever a change of latest mark is passed to the callout function. For + example: + + re> /a(*MARK:X)bc/C + data> abc + --->abc + +0 ^ a + +1 ^^ (*MARK:X) + +10 ^^ b + Latest Mark: X + +11 ^ ^ c + +12 ^ ^ + 0: abc + + The mark changes between matching "a" and "b", but stays the same for + the rest of the match, so nothing more is output. If, as a result of + backtracking, the mark reverts to being unset, the text "<unset>" is + output. + + The callout function in pcretest returns zero (carry on matching) by + default, but you can use a \C item in a data line (as described above) + to change this and other parameters of the callout. + + Inserting callouts can be helpful when using pcretest to check compli- + cated regular expressions. For further information about callouts, see + the pcrecallout documentation. + + +NON-PRINTING CHARACTERS + + When pcretest is outputting text in the compiled version of a pattern, + bytes other than 32-126 are always treated as non-printing characters + are are therefore shown as hex escapes. + + When pcretest is outputting text that is a matched part of a subject + string, it behaves in the same way, unless a different locale has been + set for the pattern (using the /L modifier). In this case, the + isprint() function to distinguish printing and non-printing characters. + + +SAVING AND RELOADING COMPILED PATTERNS + + The facilities described in this section are not available when the + POSIX interface to PCRE is being used, that is, when the /P pattern + modifier is specified. + + When the POSIX interface is not in use, you can cause pcretest to write + a compiled pattern to a file, by following the modifiers with > and a + file name. For example: + + /pattern/im >/some/file + + See the pcreprecompile documentation for a discussion about saving and + re-using compiled patterns. Note that if the pattern was successfully + studied with JIT optimization, the JIT data cannot be saved. + + The data that is written is binary. The first eight bytes are the + length of the compiled pattern data followed by the length of the + optional study data, each written as four bytes in big-endian order + (most significant byte first). If there is no study data (either the + pattern was not studied, or studying did not return any data), the sec- + ond length is zero. The lengths are followed by an exact copy of the + compiled pattern. If there is additional study data, this (excluding + any JIT data) follows immediately after the compiled pattern. After + writing the file, pcretest expects to read a new pattern. + + A saved pattern can be reloaded into pcretest by specifying < and a + file name instead of a pattern. There must be no space between < and + the file name, which must not contain a < character, as otherwise + pcretest will interpret the line as a pattern delimited by < charac- + ters. For example: + + re> </some/file + Compiled pattern loaded from /some/file + No study data + + If the pattern was previously studied with the JIT optimization, the + JIT information cannot be saved and restored, and so is lost. When the + pattern has been loaded, pcretest proceeds to read data lines in the + usual way. + + You can copy a file written by pcretest to a different host and reload + it there, even if the new host has opposite endianness to the one on + which the pattern was compiled. For example, you can compile on an i86 + machine and run on a SPARC machine. When a pattern is reloaded on a + host with different endianness, the confirmation message is changed to: + + Compiled pattern (byte-inverted) loaded from /some/file + + The test suite contains some saved pre-compiled patterns with different + endianness. These are reloaded using "<!" instead of just "<". This + suppresses the "(byte-inverted)" text so that the output is the same on + all hosts. It also forces debugging output once the pattern has been + reloaded. + + File names for saving and reloading can be absolute or relative, but + note that the shell facility of expanding a file name that starts with + a tilde (~) is not available. + + The ability to save and reload files in pcretest is intended for test- + ing and experimentation. It is not intended for production use because + only a single pattern can be written to a file. Furthermore, there is + no facility for supplying custom character tables for use with a + reloaded pattern. If the original pattern was compiled with custom + tables, an attempt to match a subject string using a reloaded pattern + is likely to cause pcretest to crash. Finally, if you attempt to load + a file that is not in the correct format, the result is undefined. + + +SEE ALSO + + pcre(3), pcre16(3), pcre32(3), pcreapi(3), pcrecallout(3), pcrejit, + pcrematching(3), pcrepartial(d), pcrepattern(3), pcreprecompile(3). + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 09 February 2014 + Copyright (c) 1997-2014 University of Cambridge. diff --git a/plugins/Pcre16/docs/doc/pcreunicode.3 b/plugins/Pcre16/docs/doc/pcreunicode.3 new file mode 100644 index 0000000000..cb5e5269a4 --- /dev/null +++ b/plugins/Pcre16/docs/doc/pcreunicode.3 @@ -0,0 +1,249 @@ +.TH PCREUNICODE 3 "27 February 2013" "PCRE 8.33" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH "UTF-8, UTF-16, UTF-32, AND UNICODE PROPERTY SUPPORT" +.rs +.sp +As well as UTF-8 support, PCRE also supports UTF-16 (from release 8.30) and +UTF-32 (from release 8.32), by means of two additional libraries. They can be +built as well as, or instead of, the 8-bit library. +. +. +.SH "UTF-8 SUPPORT" +.rs +.sp +In order process UTF-8 strings, you must build PCRE's 8-bit library with UTF +support, and, in addition, you must call +.\" HREF +\fBpcre_compile()\fP +.\" +with the PCRE_UTF8 option flag, or the pattern must start with the sequence +(*UTF8) or (*UTF). When either of these is the case, both the pattern and any +subject strings that are matched against it are treated as UTF-8 strings +instead of strings of individual 1-byte characters. +. +. +.SH "UTF-16 AND UTF-32 SUPPORT" +.rs +.sp +In order process UTF-16 or UTF-32 strings, you must build PCRE's 16-bit or +32-bit library with UTF support, and, in addition, you must call +.\" HREF +\fBpcre16_compile()\fP +.\" +or +.\" HREF +\fBpcre32_compile()\fP +.\" +with the PCRE_UTF16 or PCRE_UTF32 option flag, as appropriate. Alternatively, +the pattern must start with the sequence (*UTF16), (*UTF32), as appropriate, or +(*UTF), which can be used with either library. When UTF mode is set, both the +pattern and any subject strings that are matched against it are treated as +UTF-16 or UTF-32 strings instead of strings of individual 16-bit or 32-bit +characters. +. +. +.SH "UTF SUPPORT OVERHEAD" +.rs +.sp +If you compile PCRE with UTF support, but do not use it at run time, the +library will be a bit bigger, but the additional run time overhead is limited +to testing the PCRE_UTF[8|16|32] flag occasionally, so should not be very big. +. +. +.SH "UNICODE PROPERTY SUPPORT" +.rs +.sp +If PCRE is built with Unicode character property support (which implies UTF +support), the escape sequences \ep{..}, \eP{..}, and \eX can be used. +The available properties that can be tested are limited to the general +category properties such as Lu for an upper case letter or Nd for a decimal +number, the Unicode script names such as Arabic or Han, and the derived +properties Any and L&. Full lists is given in the +.\" HREF +\fBpcrepattern\fP +.\" +and +.\" HREF +\fBpcresyntax\fP +.\" +documentation. Only the short names for properties are supported. For example, +\ep{L} matches a letter. Its Perl synonym, \ep{Letter}, is not supported. +Furthermore, in Perl, many properties may optionally be prefixed by "Is", for +compatibility with Perl 5.6. PCRE does not support this. +. +. +.\" HTML <a name="utf8strings"></a> +.SS "Validity of UTF-8 strings" +.rs +.sp +When you set the PCRE_UTF8 flag, the byte strings passed as patterns and +subjects are (by default) checked for validity on entry to the relevant +functions. The entire string is checked before any other processing takes +place. From release 7.3 of PCRE, the check is according the rules of RFC 3629, +which are themselves derived from the Unicode specification. Earlier releases +of PCRE followed the rules of RFC 2279, which allows the full range of 31-bit +values (0 to 0x7FFFFFFF). The current check allows only values in the range U+0 +to U+10FFFF, excluding the surrogate area. (From release 8.33 the so-called +"non-character" code points are no longer excluded because Unicode corrigendum +#9 makes it clear that they should not be.) +.P +Characters in the "Surrogate Area" of Unicode are reserved for use by UTF-16, +where they are used in pairs to encode codepoints with values greater than +0xFFFF. The code points that are encoded by UTF-16 pairs are available +independently in the UTF-8 and UTF-32 encodings. (In other words, the whole +surrogate thing is a fudge for UTF-16 which unfortunately messes up UTF-8 and +UTF-32.) +.P +If an invalid UTF-8 string is passed to PCRE, an error return is given. At +compile time, the only additional information is the offset to the first byte +of the failing character. The run-time functions \fBpcre_exec()\fP and +\fBpcre_dfa_exec()\fP also pass back this information, as well as a more +detailed reason code if the caller has provided memory in which to do this. +.P +In some situations, you may already know that your strings are valid, and +therefore want to skip these checks in order to improve performance, for +example in the case of a long subject string that is being scanned repeatedly. +If you set the PCRE_NO_UTF8_CHECK flag at compile time or at run time, PCRE +assumes that the pattern or subject it is given (respectively) contains only +valid UTF-8 codes. In this case, it does not diagnose an invalid UTF-8 string. +.P +Note that passing PCRE_NO_UTF8_CHECK to \fBpcre_compile()\fP just disables the +check for the pattern; it does not also apply to subject strings. If you want +to disable the check for a subject string you must pass this option to +\fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP. +.P +If you pass an invalid UTF-8 string when PCRE_NO_UTF8_CHECK is set, the result +is undefined and your program may crash. +. +. +.\" HTML <a name="utf16strings"></a> +.SS "Validity of UTF-16 strings" +.rs +.sp +When you set the PCRE_UTF16 flag, the strings of 16-bit data units that are +passed as patterns and subjects are (by default) checked for validity on entry +to the relevant functions. Values other than those in the surrogate range +U+D800 to U+DFFF are independent code points. Values in the surrogate range +must be used in pairs in the correct manner. +.P +If an invalid UTF-16 string is passed to PCRE, an error return is given. At +compile time, the only additional information is the offset to the first data +unit of the failing character. The run-time functions \fBpcre16_exec()\fP and +\fBpcre16_dfa_exec()\fP also pass back this information, as well as a more +detailed reason code if the caller has provided memory in which to do this. +.P +In some situations, you may already know that your strings are valid, and +therefore want to skip these checks in order to improve performance. If you set +the PCRE_NO_UTF16_CHECK flag at compile time or at run time, PCRE assumes that +the pattern or subject it is given (respectively) contains only valid UTF-16 +sequences. In this case, it does not diagnose an invalid UTF-16 string. +However, if an invalid string is passed, the result is undefined. +. +. +.\" HTML <a name="utf32strings"></a> +.SS "Validity of UTF-32 strings" +.rs +.sp +When you set the PCRE_UTF32 flag, the strings of 32-bit data units that are +passed as patterns and subjects are (by default) checked for validity on entry +to the relevant functions. This check allows only values in the range U+0 +to U+10FFFF, excluding the surrogate area U+D800 to U+DFFF. +.P +If an invalid UTF-32 string is passed to PCRE, an error return is given. At +compile time, the only additional information is the offset to the first data +unit of the failing character. The run-time functions \fBpcre32_exec()\fP and +\fBpcre32_dfa_exec()\fP also pass back this information, as well as a more +detailed reason code if the caller has provided memory in which to do this. +.P +In some situations, you may already know that your strings are valid, and +therefore want to skip these checks in order to improve performance. If you set +the PCRE_NO_UTF32_CHECK flag at compile time or at run time, PCRE assumes that +the pattern or subject it is given (respectively) contains only valid UTF-32 +sequences. In this case, it does not diagnose an invalid UTF-32 string. +However, if an invalid string is passed, the result is undefined. +. +. +.SS "General comments about UTF modes" +.rs +.sp +1. Codepoints less than 256 can be specified in patterns by either braced or +unbraced hexadecimal escape sequences (for example, \ex{b3} or \exb3). Larger +values have to use braced sequences. +.P +2. Octal numbers up to \e777 are recognized, and in UTF-8 mode they match +two-byte characters for values greater than \e177. +.P +3. Repeat quantifiers apply to complete UTF characters, not to individual +data units, for example: \ex{100}{3}. +.P +4. The dot metacharacter matches one UTF character instead of a single data +unit. +.P +5. The escape sequence \eC can be used to match a single byte in UTF-8 mode, or +a single 16-bit data unit in UTF-16 mode, or a single 32-bit data unit in +UTF-32 mode, but its use can lead to some strange effects because it breaks up +multi-unit characters (see the description of \eC in the +.\" HREF +\fBpcrepattern\fP +.\" +documentation). The use of \eC is not supported in the alternative matching +function \fBpcre[16|32]_dfa_exec()\fP, nor is it supported in UTF mode by the +JIT optimization of \fBpcre[16|32]_exec()\fP. If JIT optimization is requested +for a UTF pattern that contains \eC, it will not succeed, and so the matching +will be carried out by the normal interpretive function. +.P +6. The character escapes \eb, \eB, \ed, \eD, \es, \eS, \ew, and \eW correctly +test characters of any code value, but, by default, the characters that PCRE +recognizes as digits, spaces, or word characters remain the same set as in +non-UTF mode, all with values less than 256. This remains true even when PCRE +is built to include Unicode property support, because to do otherwise would +slow down PCRE in many common cases. Note in particular that this applies to +\eb and \eB, because they are defined in terms of \ew and \eW. If you really +want to test for a wider sense of, say, "digit", you can use explicit Unicode +property tests such as \ep{Nd}. Alternatively, if you set the PCRE_UCP option, +the way that the character escapes work is changed so that Unicode properties +are used to determine which characters match. There are more details in the +section on +.\" HTML <a href="pcrepattern.html#genericchartypes"> +.\" </a> +generic character types +.\" +in the +.\" HREF +\fBpcrepattern\fP +.\" +documentation. +.P +7. Similarly, characters that match the POSIX named character classes are all +low-valued characters, unless the PCRE_UCP option is set. +.P +8. However, the horizontal and vertical white space matching escapes (\eh, \eH, +\ev, and \eV) do match all the appropriate Unicode characters, whether or not +PCRE_UCP is set. +.P +9. Case-insensitive matching applies only to characters whose values are less +than 128, unless PCRE is built with Unicode property support. A few Unicode +characters such as Greek sigma have more than two codepoints that are +case-equivalent. Up to and including PCRE release 8.31, only one-to-one case +mappings were supported, but later releases (with Unicode property support) do +treat as case-equivalent all versions of characters such as Greek sigma. +. +. +.SH AUTHOR +.rs +.sp +.nf +Philip Hazel +University Computing Service +Cambridge CB2 3QH, England. +.fi +. +. +.SH REVISION +.rs +.sp +.nf +Last updated: 27 February 2013 +Copyright (c) 1997-2013 University of Cambridge. +.fi diff --git a/plugins/Pcre16/docs/doc/perltest.txt b/plugins/Pcre16/docs/doc/perltest.txt new file mode 100644 index 0000000000..bb1a52a48e --- /dev/null +++ b/plugins/Pcre16/docs/doc/perltest.txt @@ -0,0 +1,42 @@ +The perltest program +-------------------- + +The perltest.pl script tests Perl's regular expressions; it has the same +specification as pcretest, and so can be given identical input, except that +input patterns can be followed only by Perl's lower case modifiers and certain +other pcretest modifiers that are either handled or ignored: + + /+ recognized and handled by perltest + /++ the second + is ignored + /8 recognized and handled by perltest + /J ignored + /K ignored + /W ignored + /S ignored + /SS ignored + /Y ignored + +The pcretest \Y escape in data lines is removed before matching. The data lines +are processed as Perl double-quoted strings, so if they contain " $ or @ +characters, these have to be escaped. For this reason, all such characters in +the Perl-compatible testinput1 file are escaped so that they can be used for +perltest as well as for pcretest. The special upper case pattern modifiers such +as /A that pcretest recognizes, and its special data line escapes, are not used +in the Perl-compatible test file. The output should be identical, apart from +the initial identifying banner. + +The perltest.pl script can also test UTF-8 features. It recognizes the special +modifier /8 that pcretest uses to invoke UTF-8 functionality. The testinput4 +and testinput6 files can be fed to perltest to run compatible UTF-8 tests. +However, it is necessary to add "use utf8; require Encode" to the script to +make this work correctly. I have not managed to find a way to handle this +automatically. + +The other testinput files are not suitable for feeding to perltest.pl, since +they make use of the special upper case modifiers and escapes that pcretest +uses to test certain features of PCRE. Some of these files also contain +malformed regular expressions, in order to check that PCRE diagnoses them +correctly. + +Philip Hazel +January 2012 diff --git a/plugins/Pcre16/pcre16_12.vcxproj b/plugins/Pcre16/pcre16_12.vcxproj new file mode 100644 index 0000000000..3801d05dd1 --- /dev/null +++ b/plugins/Pcre16/pcre16_12.vcxproj @@ -0,0 +1,173 @@ +<?xml version="1.0" encoding="us-ascii"?>
+<Project DefaultTargets="Build" ToolsVersion="12.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+ <ItemGroup Label="ProjectConfigurations">
+ <ProjectConfiguration Include="Debug|Win32">
+ <Configuration>Debug</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Debug|x64">
+ <Configuration>Debug</Configuration>
+ <Platform>x64</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Release|Win32">
+ <Configuration>Release</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Release|x64">
+ <Configuration>Release</Configuration>
+ <Platform>x64</Platform>
+ </ProjectConfiguration>
+ </ItemGroup>
+ <PropertyGroup Label="Globals">
+ <ProjectGUID>{6124E997-426E-4A0B-9617-D6D577D5E7D7}</ProjectGUID>
+ <ProjectName>Pcre16</ProjectName>
+ </PropertyGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
+ <ConfigurationType>DynamicLibrary</ConfigurationType>
+ <CharacterSet>Unicode</CharacterSet>
+ <PlatformToolset>v120_xp</PlatformToolset>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'" Label="Configuration">
+ <ConfigurationType>DynamicLibrary</ConfigurationType>
+ <CharacterSet>Unicode</CharacterSet>
+ <PlatformToolset>v120_xp</PlatformToolset>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
+ <ConfigurationType>DynamicLibrary</ConfigurationType>
+ <PlatformToolset>v120_xp</PlatformToolset>
+ <CharacterSet>Unicode</CharacterSet>
+ <WholeProgramOptimization>true</WholeProgramOptimization>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'" Label="Configuration">
+ <ConfigurationType>DynamicLibrary</ConfigurationType>
+ <PlatformToolset>v120_xp</PlatformToolset>
+ <CharacterSet>Unicode</CharacterSet>
+ <WholeProgramOptimization>true</WholeProgramOptimization>
+ </PropertyGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
+ <ImportGroup Label="ExtensionSettings">
+ </ImportGroup>
+ <ImportGroup Label="PropertySheets">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ </ImportGroup>
+ <PropertyGroup Label="UserMacros" />
+ <PropertyGroup>
+ <_ProjectFileVersion>10.0.20506.1</_ProjectFileVersion>
+ <OutDir Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">$(SolutionDir)$(Configuration)\</OutDir>
+ <IntDir Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">$(SolutionDir)$(Configuration)\Obj\$(ProjectName)\</IntDir>
+ <OutDir Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">$(SolutionDir)$(Configuration)64\</OutDir>
+ <IntDir Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">$(SolutionDir)$(Configuration)64\Obj\$(ProjectName)\</IntDir>
+ <OutDir Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">$(SolutionDir)$(Configuration)\</OutDir>
+ <IntDir Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">$(SolutionDir)$(Configuration)\Obj\$(ProjectName)\</IntDir>
+ <OutDir Condition="'$(Configuration)|$(Platform)'=='Release|x64'">$(SolutionDir)$(Configuration)64\</OutDir>
+ <IntDir Condition="'$(Configuration)|$(Platform)'=='Release|x64'">$(SolutionDir)$(Configuration)64\Obj\$(ProjectName)\</IntDir>
+ <IgnoreImportLibrary>true</IgnoreImportLibrary>
+ </PropertyGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+ <ClCompile>
+ <AdditionalIncludeDirectories>%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
+ <BasicRuntimeChecks>EnableFastChecks</BasicRuntimeChecks>
+ <Optimization>Disabled</Optimization>
+ <RuntimeLibrary>MultiThreadedDebugDLL</RuntimeLibrary>
+ <WarningLevel>Level3</WarningLevel>
+ <PreprocessorDefinitions>_WINDOWS;_DEBUG;HAVE_CONFIG_H;_CRT_SECURE_NO_DEPRECATE;_CRT_SECURE_NO_WARNINGS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ <DebugInformationFormat>EditAndContinue</DebugInformationFormat>
+ </ClCompile>
+ <Link>
+ <AdditionalLibraryDirectories>$(ProfileDir)..\..\bin12\lib</AdditionalLibraryDirectories>
+ <GenerateDebugInformation>true</GenerateDebugInformation>
+ <ImportLibrary>$(IntDir)$(TargetName).lib</ImportLibrary>
+ <SubSystem>Windows</SubSystem>
+ <RandomizedBaseAddress>false</RandomizedBaseAddress>
+ <ImageHasSafeExceptionHandlers>false</ImageHasSafeExceptionHandlers>
+ </Link>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
+ <ClCompile>
+ <AdditionalIncludeDirectories>%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
+ <BasicRuntimeChecks>EnableFastChecks</BasicRuntimeChecks>
+ <Optimization>Disabled</Optimization>
+ <RuntimeLibrary>MultiThreadedDebugDLL</RuntimeLibrary>
+ <WarningLevel>Level3</WarningLevel>
+ <PreprocessorDefinitions>_WINDOWS;_DEBUG;HAVE_CONFIG_H;_CRT_SECURE_NO_DEPRECATE;_CRT_SECURE_NO_WARNINGS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ </ClCompile>
+ <Link>
+ <AdditionalLibraryDirectories>$(ProfileDir)..\..\bin12\lib</AdditionalLibraryDirectories>
+ <GenerateDebugInformation>true</GenerateDebugInformation>
+ <ImportLibrary>$(IntDir)$(TargetName).lib</ImportLibrary>
+ <SubSystem>Windows</SubSystem>
+ <RandomizedBaseAddress>false</RandomizedBaseAddress>
+ <ImageHasSafeExceptionHandlers>false</ImageHasSafeExceptionHandlers>
+ </Link>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+ <ClCompile>
+ <AdditionalIncludeDirectories>%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
+ <InlineFunctionExpansion>AnySuitable</InlineFunctionExpansion>
+ <Optimization>Full</Optimization>
+ <WarningLevel>Level3</WarningLevel>
+ <PreprocessorDefinitions>_WINDOWS;NDEBUG;HAVE_CONFIG_H;_CRT_SECURE_NO_DEPRECATE;_CRT_SECURE_NO_WARNINGS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ <FavorSizeOrSpeed>Size</FavorSizeOrSpeed>
+ </ClCompile>
+ <Link>
+ <AdditionalLibraryDirectories>$(ProfileDir)..\..\bin12\lib</AdditionalLibraryDirectories>
+ <GenerateDebugInformation>true</GenerateDebugInformation>
+ <ImportLibrary>$(IntDir)$(TargetName).lib</ImportLibrary>
+ <SubSystem>Windows</SubSystem>
+ <OptimizeReferences>true</OptimizeReferences>
+ <EnableCOMDATFolding>true</EnableCOMDATFolding>
+ <RandomizedBaseAddress>false</RandomizedBaseAddress>
+ <ImageHasSafeExceptionHandlers>false</ImageHasSafeExceptionHandlers>
+ </Link>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
+ <ClCompile>
+ <AdditionalIncludeDirectories>%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
+ <InlineFunctionExpansion>AnySuitable</InlineFunctionExpansion>
+ <Optimization>Full</Optimization>
+ <WarningLevel>Level3</WarningLevel>
+ <PreprocessorDefinitions>_WINDOWS;NDEBUG;HAVE_CONFIG_H;_CRT_SECURE_NO_DEPRECATE;_CRT_SECURE_NO_WARNINGS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ <FavorSizeOrSpeed>Size</FavorSizeOrSpeed>
+ </ClCompile>
+ <Link>
+ <AdditionalLibraryDirectories>$(ProfileDir)..\..\bin12\lib</AdditionalLibraryDirectories>
+ <GenerateDebugInformation>true</GenerateDebugInformation>
+ <ImportLibrary>$(IntDir)$(TargetName).lib</ImportLibrary>
+ <SubSystem>Windows</SubSystem>
+ <OptimizeReferences>true</OptimizeReferences>
+ <EnableCOMDATFolding>true</EnableCOMDATFolding>
+ <RandomizedBaseAddress>false</RandomizedBaseAddress>
+ <ImageHasSafeExceptionHandlers>false</ImageHasSafeExceptionHandlers>
+ </Link>
+ </ItemDefinitionGroup>
+ <ItemGroup>
+ <ClInclude Include="src\pcre.h" />
+ <ClInclude Include="src\config.h" />
+ <ClCompile Include="src\pcre16_byte_order.c" />
+ <ClCompile Include="src\pcre16_chartables.c" />
+ <ClCompile Include="src\pcre16_compile.c" />
+ <ClCompile Include="src\pcre16_config.c" />
+ <ClCompile Include="src\pcre16_dfa_exec.c" />
+ <ClCompile Include="src\pcre16_exec.c" />
+ <ClCompile Include="src\pcre16_fullinfo.c" />
+ <ClCompile Include="src\pcre16_get.c" />
+ <ClCompile Include="src\pcre16_globals.c" />
+ <ClCompile Include="src\pcre16_jit_compile.c" />
+ <ClCompile Include="src\pcre16_maketables.c" />
+ <ClCompile Include="src\pcre16_newline.c" />
+ <ClCompile Include="src\pcre16_ord2utf16.c" />
+ <ClCompile Include="src\pcre16_refcount.c" />
+ <ClCompile Include="src\pcre16_string_utils.c" />
+ <ClCompile Include="src\pcre16_study.c" />
+ <ClCompile Include="src\pcre16_tables.c" />
+ <ClCompile Include="src\pcre16_ucd.c" />
+ <ClCompile Include="src\pcre16_utf16_utils.c" />
+ <ClCompile Include="src\pcre16_valid_utf16.c" />
+ <ClCompile Include="src\pcre16_version.c" />
+ <ClCompile Include="src\pcre16_xclass.c" />
+ </ItemGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
+ <ImportGroup Label="ExtensionTargets">
+ </ImportGroup>
+</Project>
\ No newline at end of file diff --git a/plugins/Pcre16/pcre16_12.vcxproj.filters b/plugins/Pcre16/pcre16_12.vcxproj.filters new file mode 100644 index 0000000000..cdcc9ea59b --- /dev/null +++ b/plugins/Pcre16/pcre16_12.vcxproj.filters @@ -0,0 +1,87 @@ +<?xml version="1.0" encoding="Windows-1252"?>
+<Project ToolsVersion="12.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+ <ItemGroup>
+ <ClCompile Include="src\pcre16_byte_order.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="src\pcre16_chartables.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="src\pcre16_compile.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="src\pcre16_config.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="src\pcre16_dfa_exec.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="src\pcre16_exec.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="src\pcre16_fullinfo.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="src\pcre16_get.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="src\pcre16_globals.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="src\pcre16_jit_compile.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="src\pcre16_maketables.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="src\pcre16_newline.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="src\pcre16_ord2utf16.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="src\pcre16_refcount.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="src\pcre16_string_utils.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="src\pcre16_study.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="src\pcre16_tables.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="src\pcre16_ucd.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="src\pcre16_utf16_utils.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="src\pcre16_valid_utf16.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="src\pcre16_version.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="src\pcre16_xclass.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ </ItemGroup>
+ <ItemGroup>
+ <ClInclude Include="src\pcre.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="src\config.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ </ItemGroup>
+ <ItemGroup>
+ <Filter Include="Source Files">
+ <UniqueIdentifier>{E4DC98D5-B82E-4336-B232-8E640F6524EA}</UniqueIdentifier>
+ </Filter>
+ <Filter Include="Header Files">
+ <UniqueIdentifier>{C6E6402B-1E53-4CFA-96A6-AC1DB4FB8E6D}</UniqueIdentifier>
+ </Filter>
+ </ItemGroup>
+</Project>
\ No newline at end of file diff --git a/plugins/Pcre16/src/config.h b/plugins/Pcre16/src/config.h new file mode 100644 index 0000000000..d1e35175fe --- /dev/null +++ b/plugins/Pcre16/src/config.h @@ -0,0 +1,57 @@ +/* config.h for CMake builds */
+
+/* #undef HAVE_DIRENT_H */
+#define HAVE_SYS_STAT_H 1
+#define HAVE_SYS_TYPES_H 1
+/* #undef HAVE_UNISTD_H */
+#define HAVE_WINDOWS_H 1
+#define HAVE_STDINT_H 1
+#define HAVE_INTTYPES_H 1
+
+/* #undef HAVE_TYPE_TRAITS_H */
+/* #undef HAVE_BITS_TYPE_TRAITS_H */
+
+/* #undef HAVE_BCOPY */
+#define HAVE_MEMMOVE 1
+#define HAVE_STRERROR 1
+#define HAVE_STRTOLL 1
+/* #undef HAVE_STRTOQ */
+#define HAVE__STRTOI64 1
+
+/* #undef PCRE_STATIC */
+
+/* #undef SUPPORT_PCRE8 */
+#define SUPPORT_PCRE16 1
+/* #undef SUPPORT_PCRE32 */
+/* #undef SUPPORT_JIT */
+/* #undef SUPPORT_PCREGREP_JIT */
+/* #undef SUPPORT_UTF */
+/* #undef SUPPORT_UCP */
+/* #undef EBCDIC */
+/* #undef EBCDIC_NL25 */
+/* #undef BSR_ANYCRLF */
+/* #undef NO_RECURSE */
+
+#define HAVE_LONG_LONG 1
+#define HAVE_UNSIGNED_LONG_LONG 1
+
+/* #undef SUPPORT_LIBBZ2 */
+/* #undef SUPPORT_LIBZ */
+/* #undef SUPPORT_LIBEDIT */
+/* #undef SUPPORT_LIBREADLINE */
+
+/* #undef SUPPORT_VALGRIND */
+/* #undef SUPPORT_GCOV */
+
+#define NEWLINE 10
+#define POSIX_MALLOC_THRESHOLD 10
+#define LINK_SIZE 2
+#define PARENS_NEST_LIMIT 250
+#define MATCH_LIMIT 10000000
+#define MATCH_LIMIT_RECURSION MATCH_LIMIT
+#define PCREGREP_BUFSIZE 20480
+
+#define MAX_NAME_SIZE 32
+#define MAX_NAME_COUNT 10000
+
+/* end config.h for CMake builds */
diff --git a/plugins/Pcre16/src/pcre.h b/plugins/Pcre16/src/pcre.h new file mode 100644 index 0000000000..7fcea56f4c --- /dev/null +++ b/plugins/Pcre16/src/pcre.h @@ -0,0 +1,677 @@ +/*************************************************
+* Perl-Compatible Regular Expressions *
+*************************************************/
+
+/* This is the public header file for the PCRE library, to be #included by
+applications that call the PCRE functions.
+
+ Copyright (c) 1997-2014 University of Cambridge
+
+-----------------------------------------------------------------------------
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+ * Redistributions of source code must retain the above copyright notice,
+ this list of conditions and the following disclaimer.
+
+ * Redistributions in binary form must reproduce the above copyright
+ notice, this list of conditions and the following disclaimer in the
+ documentation and/or other materials provided with the distribution.
+
+ * Neither the name of the University of Cambridge nor the names of its
+ contributors may be used to endorse or promote products derived from
+ this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+-----------------------------------------------------------------------------
+*/
+
+#ifndef _PCRE_H
+#define _PCRE_H
+
+/* The current PCRE version information. */
+
+#define PCRE_MAJOR 8
+#define PCRE_MINOR 35
+#define PCRE_PRERELEASE
+#define PCRE_DATE 2014-04-04
+
+/* When an application links to a PCRE DLL in Windows, the symbols that are
+imported have to be identified as such. When building PCRE, the appropriate
+export setting is defined in pcre_internal.h, which includes this file. So we
+don't change existing definitions of PCRE_EXP_DECL and PCRECPP_EXP_DECL. */
+
+#if defined(_WIN32) && !defined(PCRE_STATIC)
+# ifndef PCRE_EXP_DECL
+# define PCRE_EXP_DECL extern __declspec(dllimport)
+# endif
+# ifdef __cplusplus
+# ifndef PCRECPP_EXP_DECL
+# define PCRECPP_EXP_DECL extern __declspec(dllimport)
+# endif
+# ifndef PCRECPP_EXP_DEFN
+# define PCRECPP_EXP_DEFN __declspec(dllimport)
+# endif
+# endif
+#endif
+
+/* By default, we use the standard "extern" declarations. */
+
+#ifndef PCRE_EXP_DECL
+# ifdef __cplusplus
+# define PCRE_EXP_DECL extern "C"
+# else
+# define PCRE_EXP_DECL extern
+# endif
+#endif
+
+#ifdef __cplusplus
+# ifndef PCRECPP_EXP_DECL
+# define PCRECPP_EXP_DECL extern
+# endif
+# ifndef PCRECPP_EXP_DEFN
+# define PCRECPP_EXP_DEFN
+# endif
+#endif
+
+/* Have to include stdlib.h in order to ensure that size_t is defined;
+it is needed here for malloc. */
+
+#include <stdlib.h>
+
+/* Allow for C++ users */
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Public options. Some are compile-time only, some are run-time only, and some
+are both. Most of the compile-time options are saved with the compiled regex so
+that they can be inspected during studying (and therefore JIT compiling). Note
+that pcre_study() has its own set of options. Originally, all the options
+defined here used distinct bits. However, almost all the bits in a 32-bit word
+are now used, so in order to conserve them, option bits that were previously
+only recognized at matching time (i.e. by pcre_exec() or pcre_dfa_exec()) may
+also be used for compile-time options that affect only compiling and are not
+relevant for studying or JIT compiling.
+
+Some options for pcre_compile() change its behaviour but do not affect the
+behaviour of the execution functions. Other options are passed through to the
+execution functions and affect their behaviour, with or without affecting the
+behaviour of pcre_compile().
+
+Options that can be passed to pcre_compile() are tagged Cx below, with these
+variants:
+
+C1 Affects compile only
+C2 Does not affect compile; affects exec, dfa_exec
+C3 Affects compile, exec, dfa_exec
+C4 Affects compile, exec, dfa_exec, study
+C5 Affects compile, exec, study
+
+Options that can be set for pcre_exec() and/or pcre_dfa_exec() are flagged with
+E and D, respectively. They take precedence over C3, C4, and C5 settings passed
+from pcre_compile(). Those that are compatible with JIT execution are flagged
+with J. */
+
+#define PCRE_CASELESS 0x00000001 /* C1 */
+#define PCRE_MULTILINE 0x00000002 /* C1 */
+#define PCRE_DOTALL 0x00000004 /* C1 */
+#define PCRE_EXTENDED 0x00000008 /* C1 */
+#define PCRE_ANCHORED 0x00000010 /* C4 E D */
+#define PCRE_DOLLAR_ENDONLY 0x00000020 /* C2 */
+#define PCRE_EXTRA 0x00000040 /* C1 */
+#define PCRE_NOTBOL 0x00000080 /* E D J */
+#define PCRE_NOTEOL 0x00000100 /* E D J */
+#define PCRE_UNGREEDY 0x00000200 /* C1 */
+#define PCRE_NOTEMPTY 0x00000400 /* E D J */
+#define PCRE_UTF8 0x00000800 /* C4 ) */
+#define PCRE_UTF16 0x00000800 /* C4 ) Synonyms */
+#define PCRE_UTF32 0x00000800 /* C4 ) */
+#define PCRE_NO_AUTO_CAPTURE 0x00001000 /* C1 */
+#define PCRE_NO_UTF8_CHECK 0x00002000 /* C1 E D J ) */
+#define PCRE_NO_UTF16_CHECK 0x00002000 /* C1 E D J ) Synonyms */
+#define PCRE_NO_UTF32_CHECK 0x00002000 /* C1 E D J ) */
+#define PCRE_AUTO_CALLOUT 0x00004000 /* C1 */
+#define PCRE_PARTIAL_SOFT 0x00008000 /* E D J ) Synonyms */
+#define PCRE_PARTIAL 0x00008000 /* E D J ) */
+
+/* This pair use the same bit. */
+#define PCRE_NEVER_UTF 0x00010000 /* C1 ) Overlaid */
+#define PCRE_DFA_SHORTEST 0x00010000 /* D ) Overlaid */
+
+/* This pair use the same bit. */
+#define PCRE_NO_AUTO_POSSESS 0x00020000 /* C1 ) Overlaid */
+#define PCRE_DFA_RESTART 0x00020000 /* D ) Overlaid */
+
+#define PCRE_FIRSTLINE 0x00040000 /* C3 */
+#define PCRE_DUPNAMES 0x00080000 /* C1 */
+#define PCRE_NEWLINE_CR 0x00100000 /* C3 E D */
+#define PCRE_NEWLINE_LF 0x00200000 /* C3 E D */
+#define PCRE_NEWLINE_CRLF 0x00300000 /* C3 E D */
+#define PCRE_NEWLINE_ANY 0x00400000 /* C3 E D */
+#define PCRE_NEWLINE_ANYCRLF 0x00500000 /* C3 E D */
+#define PCRE_BSR_ANYCRLF 0x00800000 /* C3 E D */
+#define PCRE_BSR_UNICODE 0x01000000 /* C3 E D */
+#define PCRE_JAVASCRIPT_COMPAT 0x02000000 /* C5 */
+#define PCRE_NO_START_OPTIMIZE 0x04000000 /* C2 E D ) Synonyms */
+#define PCRE_NO_START_OPTIMISE 0x04000000 /* C2 E D ) */
+#define PCRE_PARTIAL_HARD 0x08000000 /* E D J */
+#define PCRE_NOTEMPTY_ATSTART 0x10000000 /* E D J */
+#define PCRE_UCP 0x20000000 /* C3 */
+
+/* Exec-time and get/set-time error codes */
+
+#define PCRE_ERROR_NOMATCH (-1)
+#define PCRE_ERROR_NULL (-2)
+#define PCRE_ERROR_BADOPTION (-3)
+#define PCRE_ERROR_BADMAGIC (-4)
+#define PCRE_ERROR_UNKNOWN_OPCODE (-5)
+#define PCRE_ERROR_UNKNOWN_NODE (-5) /* For backward compatibility */
+#define PCRE_ERROR_NOMEMORY (-6)
+#define PCRE_ERROR_NOSUBSTRING (-7)
+#define PCRE_ERROR_MATCHLIMIT (-8)
+#define PCRE_ERROR_CALLOUT (-9) /* Never used by PCRE itself */
+#define PCRE_ERROR_BADUTF8 (-10) /* Same for 8/16/32 */
+#define PCRE_ERROR_BADUTF16 (-10) /* Same for 8/16/32 */
+#define PCRE_ERROR_BADUTF32 (-10) /* Same for 8/16/32 */
+#define PCRE_ERROR_BADUTF8_OFFSET (-11) /* Same for 8/16 */
+#define PCRE_ERROR_BADUTF16_OFFSET (-11) /* Same for 8/16 */
+#define PCRE_ERROR_PARTIAL (-12)
+#define PCRE_ERROR_BADPARTIAL (-13)
+#define PCRE_ERROR_INTERNAL (-14)
+#define PCRE_ERROR_BADCOUNT (-15)
+#define PCRE_ERROR_DFA_UITEM (-16)
+#define PCRE_ERROR_DFA_UCOND (-17)
+#define PCRE_ERROR_DFA_UMLIMIT (-18)
+#define PCRE_ERROR_DFA_WSSIZE (-19)
+#define PCRE_ERROR_DFA_RECURSE (-20)
+#define PCRE_ERROR_RECURSIONLIMIT (-21)
+#define PCRE_ERROR_NULLWSLIMIT (-22) /* No longer actually used */
+#define PCRE_ERROR_BADNEWLINE (-23)
+#define PCRE_ERROR_BADOFFSET (-24)
+#define PCRE_ERROR_SHORTUTF8 (-25)
+#define PCRE_ERROR_SHORTUTF16 (-25) /* Same for 8/16 */
+#define PCRE_ERROR_RECURSELOOP (-26)
+#define PCRE_ERROR_JIT_STACKLIMIT (-27)
+#define PCRE_ERROR_BADMODE (-28)
+#define PCRE_ERROR_BADENDIANNESS (-29)
+#define PCRE_ERROR_DFA_BADRESTART (-30)
+#define PCRE_ERROR_JIT_BADOPTION (-31)
+#define PCRE_ERROR_BADLENGTH (-32)
+#define PCRE_ERROR_UNSET (-33)
+
+/* Specific error codes for UTF-8 validity checks */
+
+#define PCRE_UTF8_ERR0 0
+#define PCRE_UTF8_ERR1 1
+#define PCRE_UTF8_ERR2 2
+#define PCRE_UTF8_ERR3 3
+#define PCRE_UTF8_ERR4 4
+#define PCRE_UTF8_ERR5 5
+#define PCRE_UTF8_ERR6 6
+#define PCRE_UTF8_ERR7 7
+#define PCRE_UTF8_ERR8 8
+#define PCRE_UTF8_ERR9 9
+#define PCRE_UTF8_ERR10 10
+#define PCRE_UTF8_ERR11 11
+#define PCRE_UTF8_ERR12 12
+#define PCRE_UTF8_ERR13 13
+#define PCRE_UTF8_ERR14 14
+#define PCRE_UTF8_ERR15 15
+#define PCRE_UTF8_ERR16 16
+#define PCRE_UTF8_ERR17 17
+#define PCRE_UTF8_ERR18 18
+#define PCRE_UTF8_ERR19 19
+#define PCRE_UTF8_ERR20 20
+#define PCRE_UTF8_ERR21 21
+#define PCRE_UTF8_ERR22 22 /* Unused (was non-character) */
+
+/* Specific error codes for UTF-16 validity checks */
+
+#define PCRE_UTF16_ERR0 0
+#define PCRE_UTF16_ERR1 1
+#define PCRE_UTF16_ERR2 2
+#define PCRE_UTF16_ERR3 3
+#define PCRE_UTF16_ERR4 4 /* Unused (was non-character) */
+
+/* Specific error codes for UTF-32 validity checks */
+
+#define PCRE_UTF32_ERR0 0
+#define PCRE_UTF32_ERR1 1
+#define PCRE_UTF32_ERR2 2 /* Unused (was non-character) */
+#define PCRE_UTF32_ERR3 3
+
+/* Request types for pcre_fullinfo() */
+
+#define PCRE_INFO_OPTIONS 0
+#define PCRE_INFO_SIZE 1
+#define PCRE_INFO_CAPTURECOUNT 2
+#define PCRE_INFO_BACKREFMAX 3
+#define PCRE_INFO_FIRSTBYTE 4
+#define PCRE_INFO_FIRSTCHAR 4 /* For backwards compatibility */
+#define PCRE_INFO_FIRSTTABLE 5
+#define PCRE_INFO_LASTLITERAL 6
+#define PCRE_INFO_NAMEENTRYSIZE 7
+#define PCRE_INFO_NAMECOUNT 8
+#define PCRE_INFO_NAMETABLE 9
+#define PCRE_INFO_STUDYSIZE 10
+#define PCRE_INFO_DEFAULT_TABLES 11
+#define PCRE_INFO_OKPARTIAL 12
+#define PCRE_INFO_JCHANGED 13
+#define PCRE_INFO_HASCRORLF 14
+#define PCRE_INFO_MINLENGTH 15
+#define PCRE_INFO_JIT 16
+#define PCRE_INFO_JITSIZE 17
+#define PCRE_INFO_MAXLOOKBEHIND 18
+#define PCRE_INFO_FIRSTCHARACTER 19
+#define PCRE_INFO_FIRSTCHARACTERFLAGS 20
+#define PCRE_INFO_REQUIREDCHAR 21
+#define PCRE_INFO_REQUIREDCHARFLAGS 22
+#define PCRE_INFO_MATCHLIMIT 23
+#define PCRE_INFO_RECURSIONLIMIT 24
+#define PCRE_INFO_MATCH_EMPTY 25
+
+/* Request types for pcre_config(). Do not re-arrange, in order to remain
+compatible. */
+
+#define PCRE_CONFIG_UTF8 0
+#define PCRE_CONFIG_NEWLINE 1
+#define PCRE_CONFIG_LINK_SIZE 2
+#define PCRE_CONFIG_POSIX_MALLOC_THRESHOLD 3
+#define PCRE_CONFIG_MATCH_LIMIT 4
+#define PCRE_CONFIG_STACKRECURSE 5
+#define PCRE_CONFIG_UNICODE_PROPERTIES 6
+#define PCRE_CONFIG_MATCH_LIMIT_RECURSION 7
+#define PCRE_CONFIG_BSR 8
+#define PCRE_CONFIG_JIT 9
+#define PCRE_CONFIG_UTF16 10
+#define PCRE_CONFIG_JITTARGET 11
+#define PCRE_CONFIG_UTF32 12
+#define PCRE_CONFIG_PARENS_LIMIT 13
+
+/* Request types for pcre_study(). Do not re-arrange, in order to remain
+compatible. */
+
+#define PCRE_STUDY_JIT_COMPILE 0x0001
+#define PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE 0x0002
+#define PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE 0x0004
+#define PCRE_STUDY_EXTRA_NEEDED 0x0008
+
+/* Bit flags for the pcre[16|32]_extra structure. Do not re-arrange or redefine
+these bits, just add new ones on the end, in order to remain compatible. */
+
+#define PCRE_EXTRA_STUDY_DATA 0x0001
+#define PCRE_EXTRA_MATCH_LIMIT 0x0002
+#define PCRE_EXTRA_CALLOUT_DATA 0x0004
+#define PCRE_EXTRA_TABLES 0x0008
+#define PCRE_EXTRA_MATCH_LIMIT_RECURSION 0x0010
+#define PCRE_EXTRA_MARK 0x0020
+#define PCRE_EXTRA_EXECUTABLE_JIT 0x0040
+
+/* Types */
+
+struct real_pcre; /* declaration; the definition is private */
+typedef struct real_pcre pcre;
+
+struct real_pcre16; /* declaration; the definition is private */
+typedef struct real_pcre16 pcre16;
+
+struct real_pcre32; /* declaration; the definition is private */
+typedef struct real_pcre32 pcre32;
+
+struct real_pcre_jit_stack; /* declaration; the definition is private */
+typedef struct real_pcre_jit_stack pcre_jit_stack;
+
+struct real_pcre16_jit_stack; /* declaration; the definition is private */
+typedef struct real_pcre16_jit_stack pcre16_jit_stack;
+
+struct real_pcre32_jit_stack; /* declaration; the definition is private */
+typedef struct real_pcre32_jit_stack pcre32_jit_stack;
+
+/* If PCRE is compiled with 16 bit character support, PCRE_UCHAR16 must contain
+a 16 bit wide signed data type. Otherwise it can be a dummy data type since
+pcre16 functions are not implemented. There is a check for this in pcre_internal.h. */
+#ifndef PCRE_UCHAR16
+#define PCRE_UCHAR16 unsigned short
+#endif
+
+#ifndef PCRE_SPTR16
+#define PCRE_SPTR16 const PCRE_UCHAR16 *
+#endif
+
+/* If PCRE is compiled with 32 bit character support, PCRE_UCHAR32 must contain
+a 32 bit wide signed data type. Otherwise it can be a dummy data type since
+pcre32 functions are not implemented. There is a check for this in pcre_internal.h. */
+#ifndef PCRE_UCHAR32
+#define PCRE_UCHAR32 unsigned int
+#endif
+
+#ifndef PCRE_SPTR32
+#define PCRE_SPTR32 const PCRE_UCHAR32 *
+#endif
+
+/* When PCRE is compiled as a C++ library, the subject pointer type can be
+replaced with a custom type. For conventional use, the public interface is a
+const char *. */
+
+#ifndef PCRE_SPTR
+#define PCRE_SPTR const char *
+#endif
+
+/* The structure for passing additional data to pcre_exec(). This is defined in
+such as way as to be extensible. Always add new fields at the end, in order to
+remain compatible. */
+
+typedef struct pcre_extra {
+ unsigned long int flags; /* Bits for which fields are set */
+ void *study_data; /* Opaque data from pcre_study() */
+ unsigned long int match_limit; /* Maximum number of calls to match() */
+ void *callout_data; /* Data passed back in callouts */
+ const unsigned char *tables; /* Pointer to character tables */
+ unsigned long int match_limit_recursion; /* Max recursive calls to match() */
+ unsigned char **mark; /* For passing back a mark pointer */
+ void *executable_jit; /* Contains a pointer to a compiled jit code */
+} pcre_extra;
+
+/* Same structure as above, but with 16 bit char pointers. */
+
+typedef struct pcre16_extra {
+ unsigned long int flags; /* Bits for which fields are set */
+ void *study_data; /* Opaque data from pcre_study() */
+ unsigned long int match_limit; /* Maximum number of calls to match() */
+ void *callout_data; /* Data passed back in callouts */
+ const unsigned char *tables; /* Pointer to character tables */
+ unsigned long int match_limit_recursion; /* Max recursive calls to match() */
+ PCRE_UCHAR16 **mark; /* For passing back a mark pointer */
+ void *executable_jit; /* Contains a pointer to a compiled jit code */
+} pcre16_extra;
+
+/* Same structure as above, but with 32 bit char pointers. */
+
+typedef struct pcre32_extra {
+ unsigned long int flags; /* Bits for which fields are set */
+ void *study_data; /* Opaque data from pcre_study() */
+ unsigned long int match_limit; /* Maximum number of calls to match() */
+ void *callout_data; /* Data passed back in callouts */
+ const unsigned char *tables; /* Pointer to character tables */
+ unsigned long int match_limit_recursion; /* Max recursive calls to match() */
+ PCRE_UCHAR32 **mark; /* For passing back a mark pointer */
+ void *executable_jit; /* Contains a pointer to a compiled jit code */
+} pcre32_extra;
+
+/* The structure for passing out data via the pcre_callout_function. We use a
+structure so that new fields can be added on the end in future versions,
+without changing the API of the function, thereby allowing old clients to work
+without modification. */
+
+typedef struct pcre_callout_block {
+ int version; /* Identifies version of block */
+ /* ------------------------ Version 0 ------------------------------- */
+ int callout_number; /* Number compiled into pattern */
+ int *offset_vector; /* The offset vector */
+ PCRE_SPTR subject; /* The subject being matched */
+ int subject_length; /* The length of the subject */
+ int start_match; /* Offset to start of this match attempt */
+ int current_position; /* Where we currently are in the subject */
+ int capture_top; /* Max current capture */
+ int capture_last; /* Most recently closed capture */
+ void *callout_data; /* Data passed in with the call */
+ /* ------------------- Added for Version 1 -------------------------- */
+ int pattern_position; /* Offset to next item in the pattern */
+ int next_item_length; /* Length of next item in the pattern */
+ /* ------------------- Added for Version 2 -------------------------- */
+ const unsigned char *mark; /* Pointer to current mark or NULL */
+ /* ------------------------------------------------------------------ */
+} pcre_callout_block;
+
+/* Same structure as above, but with 16 bit char pointers. */
+
+typedef struct pcre16_callout_block {
+ int version; /* Identifies version of block */
+ /* ------------------------ Version 0 ------------------------------- */
+ int callout_number; /* Number compiled into pattern */
+ int *offset_vector; /* The offset vector */
+ PCRE_SPTR16 subject; /* The subject being matched */
+ int subject_length; /* The length of the subject */
+ int start_match; /* Offset to start of this match attempt */
+ int current_position; /* Where we currently are in the subject */
+ int capture_top; /* Max current capture */
+ int capture_last; /* Most recently closed capture */
+ void *callout_data; /* Data passed in with the call */
+ /* ------------------- Added for Version 1 -------------------------- */
+ int pattern_position; /* Offset to next item in the pattern */
+ int next_item_length; /* Length of next item in the pattern */
+ /* ------------------- Added for Version 2 -------------------------- */
+ const PCRE_UCHAR16 *mark; /* Pointer to current mark or NULL */
+ /* ------------------------------------------------------------------ */
+} pcre16_callout_block;
+
+/* Same structure as above, but with 32 bit char pointers. */
+
+typedef struct pcre32_callout_block {
+ int version; /* Identifies version of block */
+ /* ------------------------ Version 0 ------------------------------- */
+ int callout_number; /* Number compiled into pattern */
+ int *offset_vector; /* The offset vector */
+ PCRE_SPTR32 subject; /* The subject being matched */
+ int subject_length; /* The length of the subject */
+ int start_match; /* Offset to start of this match attempt */
+ int current_position; /* Where we currently are in the subject */
+ int capture_top; /* Max current capture */
+ int capture_last; /* Most recently closed capture */
+ void *callout_data; /* Data passed in with the call */
+ /* ------------------- Added for Version 1 -------------------------- */
+ int pattern_position; /* Offset to next item in the pattern */
+ int next_item_length; /* Length of next item in the pattern */
+ /* ------------------- Added for Version 2 -------------------------- */
+ const PCRE_UCHAR32 *mark; /* Pointer to current mark or NULL */
+ /* ------------------------------------------------------------------ */
+} pcre32_callout_block;
+
+/* Indirection for store get and free functions. These can be set to
+alternative malloc/free functions if required. Special ones are used in the
+non-recursive case for "frames". There is also an optional callout function
+that is triggered by the (?) regex item. For Virtual Pascal, these definitions
+have to take another form. */
+
+#ifndef VPCOMPAT
+PCRE_EXP_DECL void *(*pcre_malloc)(size_t);
+PCRE_EXP_DECL void (*pcre_free)(void *);
+PCRE_EXP_DECL void *(*pcre_stack_malloc)(size_t);
+PCRE_EXP_DECL void (*pcre_stack_free)(void *);
+PCRE_EXP_DECL int (*pcre_callout)(pcre_callout_block *);
+PCRE_EXP_DECL int (*pcre_stack_guard)(void);
+
+PCRE_EXP_DECL void *(*pcre16_malloc)(size_t);
+PCRE_EXP_DECL void (*pcre16_free)(void *);
+PCRE_EXP_DECL void *(*pcre16_stack_malloc)(size_t);
+PCRE_EXP_DECL void (*pcre16_stack_free)(void *);
+PCRE_EXP_DECL int (*pcre16_callout)(pcre16_callout_block *);
+PCRE_EXP_DECL int (*pcre16_stack_guard)(void);
+
+PCRE_EXP_DECL void *(*pcre32_malloc)(size_t);
+PCRE_EXP_DECL void (*pcre32_free)(void *);
+PCRE_EXP_DECL void *(*pcre32_stack_malloc)(size_t);
+PCRE_EXP_DECL void (*pcre32_stack_free)(void *);
+PCRE_EXP_DECL int (*pcre32_callout)(pcre32_callout_block *);
+PCRE_EXP_DECL int (*pcre32_stack_guard)(void);
+#else /* VPCOMPAT */
+PCRE_EXP_DECL void *pcre_malloc(size_t);
+PCRE_EXP_DECL void pcre_free(void *);
+PCRE_EXP_DECL void *pcre_stack_malloc(size_t);
+PCRE_EXP_DECL void pcre_stack_free(void *);
+PCRE_EXP_DECL int pcre_callout(pcre_callout_block *);
+PCRE_EXP_DECL int pcre_stack_guard(void);
+
+PCRE_EXP_DECL void *pcre16_malloc(size_t);
+PCRE_EXP_DECL void pcre16_free(void *);
+PCRE_EXP_DECL void *pcre16_stack_malloc(size_t);
+PCRE_EXP_DECL void pcre16_stack_free(void *);
+PCRE_EXP_DECL int pcre16_callout(pcre16_callout_block *);
+PCRE_EXP_DECL int pcre16_stack_guard(void);
+
+PCRE_EXP_DECL void *pcre32_malloc(size_t);
+PCRE_EXP_DECL void pcre32_free(void *);
+PCRE_EXP_DECL void *pcre32_stack_malloc(size_t);
+PCRE_EXP_DECL void pcre32_stack_free(void *);
+PCRE_EXP_DECL int pcre32_callout(pcre32_callout_block *);
+PCRE_EXP_DECL int pcre32_stack_guard(void);
+#endif /* VPCOMPAT */
+
+/* User defined callback which provides a stack just before the match starts. */
+
+typedef pcre_jit_stack *(*pcre_jit_callback)(void *);
+typedef pcre16_jit_stack *(*pcre16_jit_callback)(void *);
+typedef pcre32_jit_stack *(*pcre32_jit_callback)(void *);
+
+/* Exported PCRE functions */
+
+PCRE_EXP_DECL pcre *pcre_compile(const char *, int, const char **, int *,
+ const unsigned char *);
+PCRE_EXP_DECL pcre16 *pcre16_compile(PCRE_SPTR16, int, const char **, int *,
+ const unsigned char *);
+PCRE_EXP_DECL pcre32 *pcre32_compile(PCRE_SPTR32, int, const char **, int *,
+ const unsigned char *);
+PCRE_EXP_DECL pcre *pcre_compile2(const char *, int, int *, const char **,
+ int *, const unsigned char *);
+PCRE_EXP_DECL pcre16 *pcre16_compile2(PCRE_SPTR16, int, int *, const char **,
+ int *, const unsigned char *);
+PCRE_EXP_DECL pcre32 *pcre32_compile2(PCRE_SPTR32, int, int *, const char **,
+ int *, const unsigned char *);
+PCRE_EXP_DECL int pcre_config(int, void *);
+PCRE_EXP_DECL int pcre16_config(int, void *);
+PCRE_EXP_DECL int pcre32_config(int, void *);
+PCRE_EXP_DECL int pcre_copy_named_substring(const pcre *, const char *,
+ int *, int, const char *, char *, int);
+PCRE_EXP_DECL int pcre16_copy_named_substring(const pcre16 *, PCRE_SPTR16,
+ int *, int, PCRE_SPTR16, PCRE_UCHAR16 *, int);
+PCRE_EXP_DECL int pcre32_copy_named_substring(const pcre32 *, PCRE_SPTR32,
+ int *, int, PCRE_SPTR32, PCRE_UCHAR32 *, int);
+PCRE_EXP_DECL int pcre_copy_substring(const char *, int *, int, int,
+ char *, int);
+PCRE_EXP_DECL int pcre16_copy_substring(PCRE_SPTR16, int *, int, int,
+ PCRE_UCHAR16 *, int);
+PCRE_EXP_DECL int pcre32_copy_substring(PCRE_SPTR32, int *, int, int,
+ PCRE_UCHAR32 *, int);
+PCRE_EXP_DECL int pcre_dfa_exec(const pcre *, const pcre_extra *,
+ const char *, int, int, int, int *, int , int *, int);
+PCRE_EXP_DECL int pcre16_dfa_exec(const pcre16 *, const pcre16_extra *,
+ PCRE_SPTR16, int, int, int, int *, int , int *, int);
+PCRE_EXP_DECL int pcre32_dfa_exec(const pcre32 *, const pcre32_extra *,
+ PCRE_SPTR32, int, int, int, int *, int , int *, int);
+PCRE_EXP_DECL int pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR,
+ int, int, int, int *, int);
+PCRE_EXP_DECL int pcre16_exec(const pcre16 *, const pcre16_extra *,
+ PCRE_SPTR16, int, int, int, int *, int);
+PCRE_EXP_DECL int pcre32_exec(const pcre32 *, const pcre32_extra *,
+ PCRE_SPTR32, int, int, int, int *, int);
+PCRE_EXP_DECL int pcre_jit_exec(const pcre *, const pcre_extra *,
+ PCRE_SPTR, int, int, int, int *, int,
+ pcre_jit_stack *);
+PCRE_EXP_DECL int pcre16_jit_exec(const pcre16 *, const pcre16_extra *,
+ PCRE_SPTR16, int, int, int, int *, int,
+ pcre16_jit_stack *);
+PCRE_EXP_DECL int pcre32_jit_exec(const pcre32 *, const pcre32_extra *,
+ PCRE_SPTR32, int, int, int, int *, int,
+ pcre32_jit_stack *);
+PCRE_EXP_DECL void pcre_free_substring(const char *);
+PCRE_EXP_DECL void pcre16_free_substring(PCRE_SPTR16);
+PCRE_EXP_DECL void pcre32_free_substring(PCRE_SPTR32);
+PCRE_EXP_DECL void pcre_free_substring_list(const char **);
+PCRE_EXP_DECL void pcre16_free_substring_list(PCRE_SPTR16 *);
+PCRE_EXP_DECL void pcre32_free_substring_list(PCRE_SPTR32 *);
+PCRE_EXP_DECL int pcre_fullinfo(const pcre *, const pcre_extra *, int,
+ void *);
+PCRE_EXP_DECL int pcre16_fullinfo(const pcre16 *, const pcre16_extra *, int,
+ void *);
+PCRE_EXP_DECL int pcre32_fullinfo(const pcre32 *, const pcre32_extra *, int,
+ void *);
+PCRE_EXP_DECL int pcre_get_named_substring(const pcre *, const char *,
+ int *, int, const char *, const char **);
+PCRE_EXP_DECL int pcre16_get_named_substring(const pcre16 *, PCRE_SPTR16,
+ int *, int, PCRE_SPTR16, PCRE_SPTR16 *);
+PCRE_EXP_DECL int pcre32_get_named_substring(const pcre32 *, PCRE_SPTR32,
+ int *, int, PCRE_SPTR32, PCRE_SPTR32 *);
+PCRE_EXP_DECL int pcre_get_stringnumber(const pcre *, const char *);
+PCRE_EXP_DECL int pcre16_get_stringnumber(const pcre16 *, PCRE_SPTR16);
+PCRE_EXP_DECL int pcre32_get_stringnumber(const pcre32 *, PCRE_SPTR32);
+PCRE_EXP_DECL int pcre_get_stringtable_entries(const pcre *, const char *,
+ char **, char **);
+PCRE_EXP_DECL int pcre16_get_stringtable_entries(const pcre16 *, PCRE_SPTR16,
+ PCRE_UCHAR16 **, PCRE_UCHAR16 **);
+PCRE_EXP_DECL int pcre32_get_stringtable_entries(const pcre32 *, PCRE_SPTR32,
+ PCRE_UCHAR32 **, PCRE_UCHAR32 **);
+PCRE_EXP_DECL int pcre_get_substring(const char *, int *, int, int,
+ const char **);
+PCRE_EXP_DECL int pcre16_get_substring(PCRE_SPTR16, int *, int, int,
+ PCRE_SPTR16 *);
+PCRE_EXP_DECL int pcre32_get_substring(PCRE_SPTR32, int *, int, int,
+ PCRE_SPTR32 *);
+PCRE_EXP_DECL int pcre_get_substring_list(const char *, int *, int,
+ const char ***);
+PCRE_EXP_DECL int pcre16_get_substring_list(PCRE_SPTR16, int *, int,
+ PCRE_SPTR16 **);
+PCRE_EXP_DECL int pcre32_get_substring_list(PCRE_SPTR32, int *, int,
+ PCRE_SPTR32 **);
+PCRE_EXP_DECL const unsigned char *pcre_maketables(void);
+PCRE_EXP_DECL const unsigned char *pcre16_maketables(void);
+PCRE_EXP_DECL const unsigned char *pcre32_maketables(void);
+PCRE_EXP_DECL int pcre_refcount(pcre *, int);
+PCRE_EXP_DECL int pcre16_refcount(pcre16 *, int);
+PCRE_EXP_DECL int pcre32_refcount(pcre32 *, int);
+PCRE_EXP_DECL pcre_extra *pcre_study(const pcre *, int, const char **);
+PCRE_EXP_DECL pcre16_extra *pcre16_study(const pcre16 *, int, const char **);
+PCRE_EXP_DECL pcre32_extra *pcre32_study(const pcre32 *, int, const char **);
+PCRE_EXP_DECL void pcre_free_study(pcre_extra *);
+PCRE_EXP_DECL void pcre16_free_study(pcre16_extra *);
+PCRE_EXP_DECL void pcre32_free_study(pcre32_extra *);
+PCRE_EXP_DECL const char *pcre_version(void);
+PCRE_EXP_DECL const char *pcre16_version(void);
+PCRE_EXP_DECL const char *pcre32_version(void);
+
+/* Utility functions for byte order swaps. */
+PCRE_EXP_DECL int pcre_pattern_to_host_byte_order(pcre *, pcre_extra *,
+ const unsigned char *);
+PCRE_EXP_DECL int pcre16_pattern_to_host_byte_order(pcre16 *, pcre16_extra *,
+ const unsigned char *);
+PCRE_EXP_DECL int pcre32_pattern_to_host_byte_order(pcre32 *, pcre32_extra *,
+ const unsigned char *);
+PCRE_EXP_DECL int pcre16_utf16_to_host_byte_order(PCRE_UCHAR16 *,
+ PCRE_SPTR16, int, int *, int);
+PCRE_EXP_DECL int pcre32_utf32_to_host_byte_order(PCRE_UCHAR32 *,
+ PCRE_SPTR32, int, int *, int);
+
+/* JIT compiler related functions. */
+
+PCRE_EXP_DECL pcre_jit_stack *pcre_jit_stack_alloc(int, int);
+PCRE_EXP_DECL pcre16_jit_stack *pcre16_jit_stack_alloc(int, int);
+PCRE_EXP_DECL pcre32_jit_stack *pcre32_jit_stack_alloc(int, int);
+PCRE_EXP_DECL void pcre_jit_stack_free(pcre_jit_stack *);
+PCRE_EXP_DECL void pcre16_jit_stack_free(pcre16_jit_stack *);
+PCRE_EXP_DECL void pcre32_jit_stack_free(pcre32_jit_stack *);
+PCRE_EXP_DECL void pcre_assign_jit_stack(pcre_extra *,
+ pcre_jit_callback, void *);
+PCRE_EXP_DECL void pcre16_assign_jit_stack(pcre16_extra *,
+ pcre16_jit_callback, void *);
+PCRE_EXP_DECL void pcre32_assign_jit_stack(pcre32_extra *,
+ pcre32_jit_callback, void *);
+PCRE_EXP_DECL void pcre_jit_free_unused_memory(void);
+PCRE_EXP_DECL void pcre16_jit_free_unused_memory(void);
+PCRE_EXP_DECL void pcre32_jit_free_unused_memory(void);
+
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
+
+#endif /* End of pcre.h */
diff --git a/plugins/Pcre16/src/pcre16_byte_order.c b/plugins/Pcre16/src/pcre16_byte_order.c new file mode 100644 index 0000000000..11d2973a3d --- /dev/null +++ b/plugins/Pcre16/src/pcre16_byte_order.c @@ -0,0 +1,45 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* Generate code with 16 bit character support. */ +#define COMPILE_PCRE16 + +#include "pcre_byte_order.c" + +/* End of pcre16_byte_order.c */ diff --git a/plugins/Pcre16/src/pcre16_chartables.c b/plugins/Pcre16/src/pcre16_chartables.c new file mode 100644 index 0000000000..7c0ff35f5e --- /dev/null +++ b/plugins/Pcre16/src/pcre16_chartables.c @@ -0,0 +1,45 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* Generate code with 16 bit character support. */ +#define COMPILE_PCRE16 + +#include "pcre_chartables.c" + +/* End of pcre16_chartables.c */ diff --git a/plugins/Pcre16/src/pcre16_compile.c b/plugins/Pcre16/src/pcre16_compile.c new file mode 100644 index 0000000000..e499b67087 --- /dev/null +++ b/plugins/Pcre16/src/pcre16_compile.c @@ -0,0 +1,45 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* Generate code with 16 bit character support. */ +#define COMPILE_PCRE16 + +#include "pcre_compile.c" + +/* End of pcre16_compile.c */ diff --git a/plugins/Pcre16/src/pcre16_config.c b/plugins/Pcre16/src/pcre16_config.c new file mode 100644 index 0000000000..b52138764f --- /dev/null +++ b/plugins/Pcre16/src/pcre16_config.c @@ -0,0 +1,45 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* Generate code with 16 bit character support. */ +#define COMPILE_PCRE16 + +#include "pcre_config.c" + +/* End of pcre16_config.c */ diff --git a/plugins/Pcre16/src/pcre16_dfa_exec.c b/plugins/Pcre16/src/pcre16_dfa_exec.c new file mode 100644 index 0000000000..2ba740e972 --- /dev/null +++ b/plugins/Pcre16/src/pcre16_dfa_exec.c @@ -0,0 +1,45 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* Generate code with 16 bit character support. */ +#define COMPILE_PCRE16 + +#include "pcre_dfa_exec.c" + +/* End of pcre16_dfa_exec.c */ diff --git a/plugins/Pcre16/src/pcre16_exec.c b/plugins/Pcre16/src/pcre16_exec.c new file mode 100644 index 0000000000..7417b1770c --- /dev/null +++ b/plugins/Pcre16/src/pcre16_exec.c @@ -0,0 +1,45 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* Generate code with 16 bit character support. */ +#define COMPILE_PCRE16 + +#include "pcre_exec.c" + +/* End of pcre16_exec.c */ diff --git a/plugins/Pcre16/src/pcre16_fullinfo.c b/plugins/Pcre16/src/pcre16_fullinfo.c new file mode 100644 index 0000000000..544dca6ed5 --- /dev/null +++ b/plugins/Pcre16/src/pcre16_fullinfo.c @@ -0,0 +1,45 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* Generate code with 16 bit character support. */ +#define COMPILE_PCRE16 + +#include "pcre_fullinfo.c" + +/* End of pcre16_fullinfo.c */ diff --git a/plugins/Pcre16/src/pcre16_get.c b/plugins/Pcre16/src/pcre16_get.c new file mode 100644 index 0000000000..3ded08c622 --- /dev/null +++ b/plugins/Pcre16/src/pcre16_get.c @@ -0,0 +1,45 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* Generate code with 16 bit character support. */ +#define COMPILE_PCRE16 + +#include "pcre_get.c" + +/* End of pcre16_get.c */ diff --git a/plugins/Pcre16/src/pcre16_globals.c b/plugins/Pcre16/src/pcre16_globals.c new file mode 100644 index 0000000000..a136b3d8c2 --- /dev/null +++ b/plugins/Pcre16/src/pcre16_globals.c @@ -0,0 +1,45 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* Generate code with 16 bit character support. */ +#define COMPILE_PCRE16 + +#include "pcre_globals.c" + +/* End of pcre16_globals.c */ diff --git a/plugins/Pcre16/src/pcre16_jit_compile.c b/plugins/Pcre16/src/pcre16_jit_compile.c new file mode 100644 index 0000000000..ab0cacd764 --- /dev/null +++ b/plugins/Pcre16/src/pcre16_jit_compile.c @@ -0,0 +1,45 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* Generate code with 16 bit character support. */ +#define COMPILE_PCRE16 + +#include "pcre_jit_compile.c" + +/* End of pcre16_jit_compile.c */ diff --git a/plugins/Pcre16/src/pcre16_maketables.c b/plugins/Pcre16/src/pcre16_maketables.c new file mode 100644 index 0000000000..b1cd1c579d --- /dev/null +++ b/plugins/Pcre16/src/pcre16_maketables.c @@ -0,0 +1,45 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* Generate code with 16 bit character support. */ +#define COMPILE_PCRE16 + +#include "pcre_maketables.c" + +/* End of pcre16_maketables.c */ diff --git a/plugins/Pcre16/src/pcre16_newline.c b/plugins/Pcre16/src/pcre16_newline.c new file mode 100644 index 0000000000..7fe201400f --- /dev/null +++ b/plugins/Pcre16/src/pcre16_newline.c @@ -0,0 +1,45 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* Generate code with 16 bit character support. */ +#define COMPILE_PCRE16 + +#include "pcre_newline.c" + +/* End of pcre16_newline.c */ diff --git a/plugins/Pcre16/src/pcre16_ord2utf16.c b/plugins/Pcre16/src/pcre16_ord2utf16.c new file mode 100644 index 0000000000..8e2ce5ea6c --- /dev/null +++ b/plugins/Pcre16/src/pcre16_ord2utf16.c @@ -0,0 +1,90 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This file contains a private PCRE function that converts an ordinal +character value into a UTF16 string. */ + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +/* Generate code with 16 bit character support. */ +#define COMPILE_PCRE16 + +#include "pcre_internal.h" + +/************************************************* +* Convert character value to UTF-16 * +*************************************************/ + +/* This function takes an integer value in the range 0 - 0x10ffff +and encodes it as a UTF-16 character in 1 to 2 pcre_uchars. + +Arguments: + cvalue the character value + buffer pointer to buffer for result - at least 2 pcre_uchars long + +Returns: number of characters placed in the buffer +*/ + +unsigned int +PRIV(ord2utf)(pcre_uint32 cvalue, pcre_uchar *buffer) +{ +#ifdef SUPPORT_UTF + +if (cvalue <= 0xffff) + { + *buffer = (pcre_uchar)cvalue; + return 1; + } + +cvalue -= 0x10000; +*buffer++ = 0xd800 | (cvalue >> 10); +*buffer = 0xdc00 | (cvalue & 0x3ff); +return 2; + +#else /* SUPPORT_UTF */ +(void)(cvalue); /* Keep compiler happy; this function won't ever be */ +(void)(buffer); /* called when SUPPORT_UTF is not defined. */ +return 0; +#endif /* SUPPORT_UTF */ +} + +/* End of pcre16_ord2utf16.c */ diff --git a/plugins/Pcre16/src/pcre16_printint.c b/plugins/Pcre16/src/pcre16_printint.c new file mode 100644 index 0000000000..33d8c34020 --- /dev/null +++ b/plugins/Pcre16/src/pcre16_printint.c @@ -0,0 +1,45 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* Generate code with 16 bit character support. */ +#define COMPILE_PCRE16 + +#include "pcre_printint.c" + +/* End of pcre16_printint.c */ diff --git a/plugins/Pcre16/src/pcre16_refcount.c b/plugins/Pcre16/src/pcre16_refcount.c new file mode 100644 index 0000000000..d3d1543973 --- /dev/null +++ b/plugins/Pcre16/src/pcre16_refcount.c @@ -0,0 +1,45 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* Generate code with 16 bit character support. */ +#define COMPILE_PCRE16 + +#include "pcre_refcount.c" + +/* End of pcre16_refcount.c */ diff --git a/plugins/Pcre16/src/pcre16_string_utils.c b/plugins/Pcre16/src/pcre16_string_utils.c new file mode 100644 index 0000000000..382c40799f --- /dev/null +++ b/plugins/Pcre16/src/pcre16_string_utils.c @@ -0,0 +1,45 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* Generate code with 16 bit character support. */ +#define COMPILE_PCRE16 + +#include "pcre_string_utils.c" + +/* End of pcre16_string_utils.c */ diff --git a/plugins/Pcre16/src/pcre16_study.c b/plugins/Pcre16/src/pcre16_study.c new file mode 100644 index 0000000000..f87de081fc --- /dev/null +++ b/plugins/Pcre16/src/pcre16_study.c @@ -0,0 +1,45 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* Generate code with 16 bit character support. */ +#define COMPILE_PCRE16 + +#include "pcre_study.c" + +/* End of pcre16_study.c */ diff --git a/plugins/Pcre16/src/pcre16_tables.c b/plugins/Pcre16/src/pcre16_tables.c new file mode 100644 index 0000000000..d84297093a --- /dev/null +++ b/plugins/Pcre16/src/pcre16_tables.c @@ -0,0 +1,45 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* Generate code with 16 bit character support. */ +#define COMPILE_PCRE16 + +#include "pcre_tables.c" + +/* End of pcre16_tables.c */ diff --git a/plugins/Pcre16/src/pcre16_ucd.c b/plugins/Pcre16/src/pcre16_ucd.c new file mode 100644 index 0000000000..ee23439a01 --- /dev/null +++ b/plugins/Pcre16/src/pcre16_ucd.c @@ -0,0 +1,45 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* Generate code with 16 bit character support. */ +#define COMPILE_PCRE16 + +#include "pcre_ucd.c" + +/* End of pcre16_ucd.c */ diff --git a/plugins/Pcre16/src/pcre16_utf16_utils.c b/plugins/Pcre16/src/pcre16_utf16_utils.c new file mode 100644 index 0000000000..49ced0c0b1 --- /dev/null +++ b/plugins/Pcre16/src/pcre16_utf16_utils.c @@ -0,0 +1,130 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains a function for converting any UTF-16 character +strings to host byte order. */ + + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +/* Generate code with 16 bit character support. */ +#define COMPILE_PCRE16 + +#include "pcre_internal.h" + +/************************************************* +* Convert any UTF-16 string to host byte order * +*************************************************/ + +/* This function takes an UTF-16 string and converts +it to host byte order. The length can be explicitly set, +or automatically detected for zero terminated strings. +BOMs can be kept or discarded during the conversion. +Conversion can be done in place (output == input). + +Arguments: + output the output buffer, its size must be greater + or equal than the input string + input any UTF-16 string + length the number of 16-bit units in the input string + can be less than zero for zero terminated strings + host_byte_order + A non-zero value means the input is in host byte + order, which can be dynamically changed by BOMs later. + Initially it contains the starting byte order and returns + with the last byte order so it can be used for stream + processing. It can be NULL, which set the host byte + order mode by default. + keep_boms for a non-zero value, the BOM (0xfeff) characters + are copied as well + +Returns: the number of 16-bit units placed into the output buffer, + including the zero-terminator +*/ + +int +pcre16_utf16_to_host_byte_order(PCRE_UCHAR16 *output, PCRE_SPTR16 input, + int length, int *host_byte_order, int keep_boms) +{ +#ifdef SUPPORT_UTF +/* This function converts any UTF-16 string to host byte order and optionally +removes any Byte Order Marks (BOMS). Returns with the remainig length. */ +int host_bo = host_byte_order != NULL ? *host_byte_order : 1; +pcre_uchar *optr = (pcre_uchar *)output; +const pcre_uchar *iptr = (const pcre_uchar *)input; +const pcre_uchar *end; +/* The c variable must be unsigned. */ +register pcre_uchar c; + +if (length < 0) + length = STRLEN_UC(iptr) + 1; +end = iptr + length; + +while (iptr < end) + { + c = *iptr++; + if (c == 0xfeff || c == 0xfffe) + { + /* Detecting the byte order of the machine is unnecessary, it is + enough to know that the UTF-16 string has the same byte order or not. */ + host_bo = c == 0xfeff; + if (keep_boms != 0) + *optr++ = 0xfeff; + else + length--; + } + else + *optr++ = host_bo ? c : ((c >> 8) | (c << 8)); /* Flip bytes if needed. */ + } +if (host_byte_order != NULL) + *host_byte_order = host_bo; + +#else /* Not SUPPORT_UTF */ +(void)(output); /* Keep picky compilers happy */ +(void)(input); +(void)(keep_boms); +(void)(host_byte_order); +#endif /* SUPPORT_UTF */ +return length; +} + +/* End of pcre16_utf16_utils.c */ diff --git a/plugins/Pcre16/src/pcre16_valid_utf16.c b/plugins/Pcre16/src/pcre16_valid_utf16.c new file mode 100644 index 0000000000..09076539d0 --- /dev/null +++ b/plugins/Pcre16/src/pcre16_valid_utf16.c @@ -0,0 +1,137 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2013 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains an internal function for validating UTF-16 character +strings. */ + + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +/* Generate code with 16 bit character support. */ +#define COMPILE_PCRE16 + +#include "pcre_internal.h" + + +/************************************************* +* Validate a UTF-16 string * +*************************************************/ + +/* This function is called (optionally) at the start of compile or match, to +check that a supposed UTF-16 string is actually valid. The early check means +that subsequent code can assume it is dealing with a valid string. The check +can be turned off for maximum performance, but the consequences of supplying an +invalid string are then undefined. + +From release 8.21 more information about the details of the error are passed +back in the returned value: + +PCRE_UTF16_ERR0 No error +PCRE_UTF16_ERR1 Missing low surrogate at the end of the string +PCRE_UTF16_ERR2 Invalid low surrogate +PCRE_UTF16_ERR3 Isolated low surrogate +PCRE_UTF16_ERR4 Unused (was non-character) + +Arguments: + string points to the string + length length of string, or -1 if the string is zero-terminated + errp pointer to an error position offset variable + +Returns: = 0 if the string is a valid UTF-16 string + > 0 otherwise, setting the offset of the bad character +*/ + +int +PRIV(valid_utf)(PCRE_PUCHAR string, int length, int *erroroffset) +{ +#ifdef SUPPORT_UTF +register PCRE_PUCHAR p; +register pcre_uint32 c; + +if (length < 0) + { + for (p = string; *p != 0; p++); + length = p - string; + } + +for (p = string; length-- > 0; p++) + { + c = *p; + + if ((c & 0xf800) != 0xd800) + { + /* Normal UTF-16 code point. Neither high nor low surrogate. */ + } + else if ((c & 0x0400) == 0) + { + /* High surrogate. Must be a followed by a low surrogate. */ + if (length == 0) + { + *erroroffset = p - string; + return PCRE_UTF16_ERR1; + } + p++; + length--; + if ((*p & 0xfc00) != 0xdc00) + { + *erroroffset = p - string; + return PCRE_UTF16_ERR2; + } + } + else + { + /* Isolated low surrogate. Always an error. */ + *erroroffset = p - string; + return PCRE_UTF16_ERR3; + } + } + +#else /* SUPPORT_UTF */ +(void)(string); /* Keep picky compilers happy */ +(void)(length); +(void)(erroroffset); +#endif /* SUPPORT_UTF */ + +return PCRE_UTF16_ERR0; /* This indicates success */ +} + +/* End of pcre16_valid_utf16.c */ diff --git a/plugins/Pcre16/src/pcre16_version.c b/plugins/Pcre16/src/pcre16_version.c new file mode 100644 index 0000000000..e991b1a8cf --- /dev/null +++ b/plugins/Pcre16/src/pcre16_version.c @@ -0,0 +1,45 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* Generate code with 16 bit character support. */ +#define COMPILE_PCRE16 + +#include "pcre_version.c" + +/* End of pcre16_version.c */ diff --git a/plugins/Pcre16/src/pcre16_xclass.c b/plugins/Pcre16/src/pcre16_xclass.c new file mode 100644 index 0000000000..5aac2a36c6 --- /dev/null +++ b/plugins/Pcre16/src/pcre16_xclass.c @@ -0,0 +1,45 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* Generate code with 16 bit character support. */ +#define COMPILE_PCRE16 + +#include "pcre_xclass.c" + +/* End of pcre16_xclass.c */ diff --git a/plugins/Pcre16/src/pcre_byte_order.c b/plugins/Pcre16/src/pcre_byte_order.c new file mode 100644 index 0000000000..cf5f12b04e --- /dev/null +++ b/plugins/Pcre16/src/pcre_byte_order.c @@ -0,0 +1,319 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2014 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains an internal function that tests a compiled pattern to +see if it was compiled with the opposite endianness. If so, it uses an +auxiliary local function to flip the appropriate bytes. */ + + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#include "pcre_internal.h" + + +/************************************************* +* Swap byte functions * +*************************************************/ + +/* The following functions swap the bytes of a pcre_uint16 +and pcre_uint32 value. + +Arguments: + value any number + +Returns: the byte swapped value +*/ + +static pcre_uint32 +swap_uint32(pcre_uint32 value) +{ +return ((value & 0x000000ff) << 24) | + ((value & 0x0000ff00) << 8) | + ((value & 0x00ff0000) >> 8) | + (value >> 24); +} + +static pcre_uint16 +swap_uint16(pcre_uint16 value) +{ +return (value >> 8) | (value << 8); +} + + +/************************************************* +* Test for a byte-flipped compiled regex * +*************************************************/ + +/* This function swaps the bytes of a compiled pattern usually +loaded form the disk. It also sets the tables pointer, which +is likely an invalid pointer after reload. + +Arguments: + argument_re points to the compiled expression + extra_data points to extra data or is NULL + tables points to the character tables or NULL + +Returns: 0 if the swap is successful, negative on error +*/ + +#if defined COMPILE_PCRE8 +PCRE_EXP_DECL int pcre_pattern_to_host_byte_order(pcre *argument_re, + pcre_extra *extra_data, const unsigned char *tables) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DECL int pcre16_pattern_to_host_byte_order(pcre16 *argument_re, + pcre16_extra *extra_data, const unsigned char *tables) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DECL int pcre32_pattern_to_host_byte_order(pcre32 *argument_re, + pcre32_extra *extra_data, const unsigned char *tables) +#endif +{ +REAL_PCRE *re = (REAL_PCRE *)argument_re; +pcre_study_data *study; +#ifndef COMPILE_PCRE8 +pcre_uchar *ptr; +int length; +#if defined SUPPORT_UTF && defined COMPILE_PCRE16 +BOOL utf; +BOOL utf16_char; +#endif /* SUPPORT_UTF && COMPILE_PCRE16 */ +#endif /* !COMPILE_PCRE8 */ + +if (re == NULL) return PCRE_ERROR_NULL; +if (re->magic_number == MAGIC_NUMBER) + { + if ((re->flags & PCRE_MODE) == 0) return PCRE_ERROR_BADMODE; + re->tables = tables; + return 0; + } + +if (re->magic_number != REVERSED_MAGIC_NUMBER) return PCRE_ERROR_BADMAGIC; +if ((swap_uint32(re->flags) & PCRE_MODE) == 0) return PCRE_ERROR_BADMODE; + +re->magic_number = MAGIC_NUMBER; +re->size = swap_uint32(re->size); +re->options = swap_uint32(re->options); +re->flags = swap_uint32(re->flags); +re->limit_match = swap_uint32(re->limit_match); +re->limit_recursion = swap_uint32(re->limit_recursion); + +#if defined COMPILE_PCRE8 || defined COMPILE_PCRE16 +re->first_char = swap_uint16(re->first_char); +re->req_char = swap_uint16(re->req_char); +#elif defined COMPILE_PCRE32 +re->first_char = swap_uint32(re->first_char); +re->req_char = swap_uint32(re->req_char); +#endif + +re->max_lookbehind = swap_uint16(re->max_lookbehind); +re->top_bracket = swap_uint16(re->top_bracket); +re->top_backref = swap_uint16(re->top_backref); +re->name_table_offset = swap_uint16(re->name_table_offset); +re->name_entry_size = swap_uint16(re->name_entry_size); +re->name_count = swap_uint16(re->name_count); +re->ref_count = swap_uint16(re->ref_count); +re->tables = tables; + +if (extra_data != NULL && (extra_data->flags & PCRE_EXTRA_STUDY_DATA) != 0) + { + study = (pcre_study_data *)extra_data->study_data; + study->size = swap_uint32(study->size); + study->flags = swap_uint32(study->flags); + study->minlength = swap_uint32(study->minlength); + } + +#ifndef COMPILE_PCRE8 +ptr = (pcre_uchar *)re + re->name_table_offset; +length = re->name_count * re->name_entry_size; +#if defined SUPPORT_UTF && defined COMPILE_PCRE16 +utf = (re->options & PCRE_UTF16) != 0; +utf16_char = FALSE; +#endif /* SUPPORT_UTF && COMPILE_PCRE16 */ + +while(TRUE) + { + /* Swap previous characters. */ + while (length-- > 0) + { +#if defined COMPILE_PCRE16 + *ptr = swap_uint16(*ptr); +#elif defined COMPILE_PCRE32 + *ptr = swap_uint32(*ptr); +#endif + ptr++; + } +#if defined SUPPORT_UTF && defined COMPILE_PCRE16 + if (utf16_char) + { + if (HAS_EXTRALEN(ptr[-1])) + { + /* We know that there is only one extra character in UTF-16. */ + *ptr = swap_uint16(*ptr); + ptr++; + } + } + utf16_char = FALSE; +#endif /* SUPPORT_UTF */ + + /* Get next opcode. */ + length = 0; +#if defined COMPILE_PCRE16 + *ptr = swap_uint16(*ptr); +#elif defined COMPILE_PCRE32 + *ptr = swap_uint32(*ptr); +#endif + switch (*ptr) + { + case OP_END: + return 0; + +#if defined SUPPORT_UTF && defined COMPILE_PCRE16 + case OP_CHAR: + case OP_CHARI: + case OP_NOT: + case OP_NOTI: + case OP_STAR: + case OP_MINSTAR: + case OP_PLUS: + case OP_MINPLUS: + case OP_QUERY: + case OP_MINQUERY: + case OP_UPTO: + case OP_MINUPTO: + case OP_EXACT: + case OP_POSSTAR: + case OP_POSPLUS: + case OP_POSQUERY: + case OP_POSUPTO: + case OP_STARI: + case OP_MINSTARI: + case OP_PLUSI: + case OP_MINPLUSI: + case OP_QUERYI: + case OP_MINQUERYI: + case OP_UPTOI: + case OP_MINUPTOI: + case OP_EXACTI: + case OP_POSSTARI: + case OP_POSPLUSI: + case OP_POSQUERYI: + case OP_POSUPTOI: + case OP_NOTSTAR: + case OP_NOTMINSTAR: + case OP_NOTPLUS: + case OP_NOTMINPLUS: + case OP_NOTQUERY: + case OP_NOTMINQUERY: + case OP_NOTUPTO: + case OP_NOTMINUPTO: + case OP_NOTEXACT: + case OP_NOTPOSSTAR: + case OP_NOTPOSPLUS: + case OP_NOTPOSQUERY: + case OP_NOTPOSUPTO: + case OP_NOTSTARI: + case OP_NOTMINSTARI: + case OP_NOTPLUSI: + case OP_NOTMINPLUSI: + case OP_NOTQUERYI: + case OP_NOTMINQUERYI: + case OP_NOTUPTOI: + case OP_NOTMINUPTOI: + case OP_NOTEXACTI: + case OP_NOTPOSSTARI: + case OP_NOTPOSPLUSI: + case OP_NOTPOSQUERYI: + case OP_NOTPOSUPTOI: + if (utf) utf16_char = TRUE; +#endif + /* Fall through. */ + + default: + length = PRIV(OP_lengths)[*ptr] - 1; + break; + + case OP_CLASS: + case OP_NCLASS: + /* Skip the character bit map. */ + ptr += 32/sizeof(pcre_uchar); + length = 0; + break; + + case OP_XCLASS: + /* Reverse the size of the XCLASS instance. */ + ptr++; +#if defined COMPILE_PCRE16 + *ptr = swap_uint16(*ptr); +#elif defined COMPILE_PCRE32 + *ptr = swap_uint32(*ptr); +#endif +#ifndef COMPILE_PCRE32 + if (LINK_SIZE > 1) + { + /* LINK_SIZE can be 1 or 2 in 16 bit mode. */ + ptr++; + *ptr = swap_uint16(*ptr); + } +#endif + ptr++; + length = (GET(ptr, -LINK_SIZE)) - (1 + LINK_SIZE + 1); +#if defined COMPILE_PCRE16 + *ptr = swap_uint16(*ptr); +#elif defined COMPILE_PCRE32 + *ptr = swap_uint32(*ptr); +#endif + if ((*ptr & XCL_MAP) != 0) + { + /* Skip the character bit map. */ + ptr += 32/sizeof(pcre_uchar); + length -= 32/sizeof(pcre_uchar); + } + break; + } + ptr++; + } +/* Control should never reach here in 16/32 bit mode. */ +#else /* In 8-bit mode, the pattern does not need to be processed. */ +return 0; +#endif /* !COMPILE_PCRE8 */ +} + +/* End of pcre_byte_order.c */ diff --git a/plugins/Pcre16/src/pcre_chartables.c b/plugins/Pcre16/src/pcre_chartables.c new file mode 100644 index 0000000000..1e20ec29d0 --- /dev/null +++ b/plugins/Pcre16/src/pcre_chartables.c @@ -0,0 +1,198 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* This file contains character tables that are used when no external tables +are passed to PCRE by the application that calls it. The tables are used only +for characters whose code values are less than 256. + +This is a default version of the tables that assumes ASCII encoding. A program +called dftables (which is distributed with PCRE) can be used to build +alternative versions of this file. This is necessary if you are running in an +EBCDIC environment, or if you want to default to a different encoding, for +example ISO-8859-1. When dftables is run, it creates these tables in the +current locale. If PCRE is configured with --enable-rebuild-chartables, this +happens automatically. + +The following #includes are present because without them gcc 4.x may remove the +array definition from the final binary if PCRE is built into a static library +and dead code stripping is activated. This leads to link errors. Pulling in the +header ensures that the array gets flagged as "someone outside this compilation +unit might reference this" and so it will always be supplied to the linker. */ + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#include "pcre_internal.h" + +const pcre_uint8 PRIV(default_tables)[] = { + +/* This table is a lower casing table. */ + + 0, 1, 2, 3, 4, 5, 6, 7, + 8, 9, 10, 11, 12, 13, 14, 15, + 16, 17, 18, 19, 20, 21, 22, 23, + 24, 25, 26, 27, 28, 29, 30, 31, + 32, 33, 34, 35, 36, 37, 38, 39, + 40, 41, 42, 43, 44, 45, 46, 47, + 48, 49, 50, 51, 52, 53, 54, 55, + 56, 57, 58, 59, 60, 61, 62, 63, + 64, 97, 98, 99,100,101,102,103, + 104,105,106,107,108,109,110,111, + 112,113,114,115,116,117,118,119, + 120,121,122, 91, 92, 93, 94, 95, + 96, 97, 98, 99,100,101,102,103, + 104,105,106,107,108,109,110,111, + 112,113,114,115,116,117,118,119, + 120,121,122,123,124,125,126,127, + 128,129,130,131,132,133,134,135, + 136,137,138,139,140,141,142,143, + 144,145,146,147,148,149,150,151, + 152,153,154,155,156,157,158,159, + 160,161,162,163,164,165,166,167, + 168,169,170,171,172,173,174,175, + 176,177,178,179,180,181,182,183, + 184,185,186,187,188,189,190,191, + 192,193,194,195,196,197,198,199, + 200,201,202,203,204,205,206,207, + 208,209,210,211,212,213,214,215, + 216,217,218,219,220,221,222,223, + 224,225,226,227,228,229,230,231, + 232,233,234,235,236,237,238,239, + 240,241,242,243,244,245,246,247, + 248,249,250,251,252,253,254,255, + +/* This table is a case flipping table. */ + + 0, 1, 2, 3, 4, 5, 6, 7, + 8, 9, 10, 11, 12, 13, 14, 15, + 16, 17, 18, 19, 20, 21, 22, 23, + 24, 25, 26, 27, 28, 29, 30, 31, + 32, 33, 34, 35, 36, 37, 38, 39, + 40, 41, 42, 43, 44, 45, 46, 47, + 48, 49, 50, 51, 52, 53, 54, 55, + 56, 57, 58, 59, 60, 61, 62, 63, + 64, 97, 98, 99,100,101,102,103, + 104,105,106,107,108,109,110,111, + 112,113,114,115,116,117,118,119, + 120,121,122, 91, 92, 93, 94, 95, + 96, 65, 66, 67, 68, 69, 70, 71, + 72, 73, 74, 75, 76, 77, 78, 79, + 80, 81, 82, 83, 84, 85, 86, 87, + 88, 89, 90,123,124,125,126,127, + 128,129,130,131,132,133,134,135, + 136,137,138,139,140,141,142,143, + 144,145,146,147,148,149,150,151, + 152,153,154,155,156,157,158,159, + 160,161,162,163,164,165,166,167, + 168,169,170,171,172,173,174,175, + 176,177,178,179,180,181,182,183, + 184,185,186,187,188,189,190,191, + 192,193,194,195,196,197,198,199, + 200,201,202,203,204,205,206,207, + 208,209,210,211,212,213,214,215, + 216,217,218,219,220,221,222,223, + 224,225,226,227,228,229,230,231, + 232,233,234,235,236,237,238,239, + 240,241,242,243,244,245,246,247, + 248,249,250,251,252,253,254,255, + +/* This table contains bit maps for various character classes. Each map is 32 +bytes long and the bits run from the least significant end of each byte. The +classes that have their own maps are: space, xdigit, digit, upper, lower, word, +graph, print, punct, and cntrl. Other classes are built from combinations. */ + + 0x00,0x3e,0x00,0x00,0x01,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, + 0x7e,0x00,0x00,0x00,0x7e,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0xfe,0xff,0xff,0x07,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0x07, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, + 0xfe,0xff,0xff,0x87,0xfe,0xff,0xff,0x07, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0xff, + 0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0xff,0xff,0xff,0xff, + 0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0xfe,0xff,0x00,0xfc, + 0x01,0x00,0x00,0xf8,0x01,0x00,0x00,0x78, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0xff,0xff,0xff,0xff,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x80, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + +/* This table identifies various classes of character by individual bits: + 0x01 white space character + 0x02 letter + 0x04 decimal digit + 0x08 hexadecimal digit + 0x10 alphanumeric or '_' + 0x80 regular expression metacharacter or binary zero +*/ + + 0x80,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */ + 0x00,0x01,0x01,0x01,0x01,0x01,0x00,0x00, /* 8- 15 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ + 0x01,0x00,0x00,0x00,0x80,0x00,0x00,0x00, /* - ' */ + 0x80,0x80,0x80,0x80,0x00,0x00,0x80,0x00, /* ( - / */ + 0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c, /* 0 - 7 */ + 0x1c,0x1c,0x00,0x00,0x00,0x00,0x00,0x80, /* 8 - ? */ + 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* @ - G */ + 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* H - O */ + 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* P - W */ + 0x12,0x12,0x12,0x80,0x80,0x00,0x80,0x10, /* X - _ */ + 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* ` - g */ + 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* h - o */ + 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* p - w */ + 0x12,0x12,0x12,0x80,0x80,0x00,0x00,0x00, /* x -127 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160-167 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 192-199 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 208-215 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 224-231 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */ + +/* End of pcre_chartables.c */ diff --git a/plugins/Pcre16/src/pcre_compile.c b/plugins/Pcre16/src/pcre_compile.c new file mode 100644 index 0000000000..8a5b723347 --- /dev/null +++ b/plugins/Pcre16/src/pcre_compile.c @@ -0,0 +1,9484 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2014 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains the external function pcre_compile(), along with +supporting internal functions that are not used by other modules. */ + + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#define NLBLOCK cd /* Block containing newline information */ +#define PSSTART start_pattern /* Field containing processed string start */ +#define PSEND end_pattern /* Field containing processed string end */ + +#include "pcre_internal.h" + + +/* When PCRE_DEBUG is defined, we need the pcre(16|32)_printint() function, which +is also used by pcretest. PCRE_DEBUG is not defined when building a production +library. We do not need to select pcre16_printint.c specially, because the +COMPILE_PCREx macro will already be appropriately set. */ + +#ifdef PCRE_DEBUG +/* pcre_printint.c should not include any headers */ +#define PCRE_INCLUDED +#include "pcre_printint.c" +#undef PCRE_INCLUDED +#endif + + +/* Macro for setting individual bits in class bitmaps. */ + +#define SETBIT(a,b) a[(b)/8] |= (1 << ((b)&7)) + +/* Maximum length value to check against when making sure that the integer that +holds the compiled pattern length does not overflow. We make it a bit less than +INT_MAX to allow for adding in group terminating bytes, so that we don't have +to check them every time. */ + +#define OFLOW_MAX (INT_MAX - 20) + +/* Definitions to allow mutual recursion */ + +static int + add_list_to_class(pcre_uint8 *, pcre_uchar **, int, compile_data *, + const pcre_uint32 *, unsigned int); + +static BOOL + compile_regex(int, pcre_uchar **, const pcre_uchar **, int *, BOOL, BOOL, int, int, + pcre_uint32 *, pcre_int32 *, pcre_uint32 *, pcre_int32 *, branch_chain *, + compile_data *, int *); + + + +/************************************************* +* Code parameters and static tables * +*************************************************/ + +/* This value specifies the size of stack workspace that is used during the +first pre-compile phase that determines how much memory is required. The regex +is partly compiled into this space, but the compiled parts are discarded as +soon as they can be, so that hopefully there will never be an overrun. The code +does, however, check for an overrun. The largest amount I've seen used is 218, +so this number is very generous. + +The same workspace is used during the second, actual compile phase for +remembering forward references to groups so that they can be filled in at the +end. Each entry in this list occupies LINK_SIZE bytes, so even when LINK_SIZE +is 4 there is plenty of room for most patterns. However, the memory can get +filled up by repetitions of forward references, for example patterns like +/(?1){0,1999}(b)/, and one user did hit the limit. The code has been changed so +that the workspace is expanded using malloc() in this situation. The value +below is therefore a minimum, and we put a maximum on it for safety. The +minimum is now also defined in terms of LINK_SIZE so that the use of malloc() +kicks in at the same number of forward references in all cases. */ + +#define COMPILE_WORK_SIZE (2048*LINK_SIZE) +#define COMPILE_WORK_SIZE_MAX (100*COMPILE_WORK_SIZE) + +/* This value determines the size of the initial vector that is used for +remembering named groups during the pre-compile. It is allocated on the stack, +but if it is too small, it is expanded using malloc(), in a similar way to the +workspace. The value is the number of slots in the list. */ + +#define NAMED_GROUP_LIST_SIZE 20 + +/* The overrun tests check for a slightly smaller size so that they detect the +overrun before it actually does run off the end of the data block. */ + +#define WORK_SIZE_SAFETY_MARGIN (100) + +/* Private flags added to firstchar and reqchar. */ + +#define REQ_CASELESS (1 << 0) /* Indicates caselessness */ +#define REQ_VARY (1 << 1) /* Reqchar followed non-literal item */ +/* Negative values for the firstchar and reqchar flags */ +#define REQ_UNSET (-2) +#define REQ_NONE (-1) + +/* Repeated character flags. */ + +#define UTF_LENGTH 0x10000000l /* The char contains its length. */ + +/* Table for handling escaped characters in the range '0'-'z'. Positive returns +are simple data values; negative values are for special things like \d and so +on. Zero means further processing is needed (for things like \x), or the escape +is invalid. */ + +#ifndef EBCDIC + +/* This is the "normal" table for ASCII systems or for EBCDIC systems running +in UTF-8 mode. */ + +static const short int escapes[] = { + 0, 0, + 0, 0, + 0, 0, + 0, 0, + 0, 0, + CHAR_COLON, CHAR_SEMICOLON, + CHAR_LESS_THAN_SIGN, CHAR_EQUALS_SIGN, + CHAR_GREATER_THAN_SIGN, CHAR_QUESTION_MARK, + CHAR_COMMERCIAL_AT, -ESC_A, + -ESC_B, -ESC_C, + -ESC_D, -ESC_E, + 0, -ESC_G, + -ESC_H, 0, + 0, -ESC_K, + 0, 0, + -ESC_N, 0, + -ESC_P, -ESC_Q, + -ESC_R, -ESC_S, + 0, 0, + -ESC_V, -ESC_W, + -ESC_X, 0, + -ESC_Z, CHAR_LEFT_SQUARE_BRACKET, + CHAR_BACKSLASH, CHAR_RIGHT_SQUARE_BRACKET, + CHAR_CIRCUMFLEX_ACCENT, CHAR_UNDERSCORE, + CHAR_GRAVE_ACCENT, 7, + -ESC_b, 0, + -ESC_d, ESC_e, + ESC_f, 0, + -ESC_h, 0, + 0, -ESC_k, + 0, 0, + ESC_n, 0, + -ESC_p, 0, + ESC_r, -ESC_s, + ESC_tee, 0, + -ESC_v, -ESC_w, + 0, 0, + -ESC_z +}; + +#else + +/* This is the "abnormal" table for EBCDIC systems without UTF-8 support. */ + +static const short int escapes[] = { +/* 48 */ 0, 0, 0, '.', '<', '(', '+', '|', +/* 50 */ '&', 0, 0, 0, 0, 0, 0, 0, +/* 58 */ 0, 0, '!', '$', '*', ')', ';', '~', +/* 60 */ '-', '/', 0, 0, 0, 0, 0, 0, +/* 68 */ 0, 0, '|', ',', '%', '_', '>', '?', +/* 70 */ 0, 0, 0, 0, 0, 0, 0, 0, +/* 78 */ 0, '`', ':', '#', '@', '\'', '=', '"', +/* 80 */ 0, 7, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0, +/* 88 */-ESC_h, 0, 0, '{', 0, 0, 0, 0, +/* 90 */ 0, 0, -ESC_k, 'l', 0, ESC_n, 0, -ESC_p, +/* 98 */ 0, ESC_r, 0, '}', 0, 0, 0, 0, +/* A0 */ 0, '~', -ESC_s, ESC_tee, 0,-ESC_v, -ESC_w, 0, +/* A8 */ 0,-ESC_z, 0, 0, 0, '[', 0, 0, +/* B0 */ 0, 0, 0, 0, 0, 0, 0, 0, +/* B8 */ 0, 0, 0, 0, 0, ']', '=', '-', +/* C0 */ '{',-ESC_A, -ESC_B, -ESC_C, -ESC_D,-ESC_E, 0, -ESC_G, +/* C8 */-ESC_H, 0, 0, 0, 0, 0, 0, 0, +/* D0 */ '}', 0, -ESC_K, 0, 0,-ESC_N, 0, -ESC_P, +/* D8 */-ESC_Q,-ESC_R, 0, 0, 0, 0, 0, 0, +/* E0 */ '\\', 0, -ESC_S, 0, 0,-ESC_V, -ESC_W, -ESC_X, +/* E8 */ 0,-ESC_Z, 0, 0, 0, 0, 0, 0, +/* F0 */ 0, 0, 0, 0, 0, 0, 0, 0, +/* F8 */ 0, 0, 0, 0, 0, 0, 0, 0 +}; +#endif + + +/* Table of special "verbs" like (*PRUNE). This is a short table, so it is +searched linearly. Put all the names into a single string, in order to reduce +the number of relocations when a shared library is dynamically linked. The +string is built from string macros so that it works in UTF-8 mode on EBCDIC +platforms. */ + +typedef struct verbitem { + int len; /* Length of verb name */ + int op; /* Op when no arg, or -1 if arg mandatory */ + int op_arg; /* Op when arg present, or -1 if not allowed */ +} verbitem; + +static const char verbnames[] = + "\0" /* Empty name is a shorthand for MARK */ + STRING_MARK0 + STRING_ACCEPT0 + STRING_COMMIT0 + STRING_F0 + STRING_FAIL0 + STRING_PRUNE0 + STRING_SKIP0 + STRING_THEN; + +static const verbitem verbs[] = { + { 0, -1, OP_MARK }, + { 4, -1, OP_MARK }, + { 6, OP_ACCEPT, -1 }, + { 6, OP_COMMIT, -1 }, + { 1, OP_FAIL, -1 }, + { 4, OP_FAIL, -1 }, + { 5, OP_PRUNE, OP_PRUNE_ARG }, + { 4, OP_SKIP, OP_SKIP_ARG }, + { 4, OP_THEN, OP_THEN_ARG } +}; + +static const int verbcount = sizeof(verbs)/sizeof(verbitem); + + +/* Substitutes for [[:<:]] and [[:>:]], which mean start and end of word in +another regex library. */ + +static const pcre_uchar sub_start_of_word[] = { + CHAR_BACKSLASH, CHAR_b, CHAR_LEFT_PARENTHESIS, CHAR_QUESTION_MARK, + CHAR_EQUALS_SIGN, CHAR_BACKSLASH, CHAR_w, CHAR_RIGHT_PARENTHESIS, '\0' }; + +static const pcre_uchar sub_end_of_word[] = { + CHAR_BACKSLASH, CHAR_b, CHAR_LEFT_PARENTHESIS, CHAR_QUESTION_MARK, + CHAR_LESS_THAN_SIGN, CHAR_EQUALS_SIGN, CHAR_BACKSLASH, CHAR_w, + CHAR_RIGHT_PARENTHESIS, '\0' }; + + +/* Tables of names of POSIX character classes and their lengths. The names are +now all in a single string, to reduce the number of relocations when a shared +library is dynamically loaded. The list of lengths is terminated by a zero +length entry. The first three must be alpha, lower, upper, as this is assumed +for handling case independence. The indices for graph, print, and punct are +needed, so identify them. */ + +static const char posix_names[] = + STRING_alpha0 STRING_lower0 STRING_upper0 STRING_alnum0 + STRING_ascii0 STRING_blank0 STRING_cntrl0 STRING_digit0 + STRING_graph0 STRING_print0 STRING_punct0 STRING_space0 + STRING_word0 STRING_xdigit; + +static const pcre_uint8 posix_name_lengths[] = { + 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 4, 6, 0 }; + +#define PC_GRAPH 8 +#define PC_PRINT 9 +#define PC_PUNCT 10 + + +/* Table of class bit maps for each POSIX class. Each class is formed from a +base map, with an optional addition or removal of another map. Then, for some +classes, there is some additional tweaking: for [:blank:] the vertical space +characters are removed, and for [:alpha:] and [:alnum:] the underscore +character is removed. The triples in the table consist of the base map offset, +second map offset or -1 if no second map, and a non-negative value for map +addition or a negative value for map subtraction (if there are two maps). The +absolute value of the third field has these meanings: 0 => no tweaking, 1 => +remove vertical space characters, 2 => remove underscore. */ + +static const int posix_class_maps[] = { + cbit_word, cbit_digit, -2, /* alpha */ + cbit_lower, -1, 0, /* lower */ + cbit_upper, -1, 0, /* upper */ + cbit_word, -1, 2, /* alnum - word without underscore */ + cbit_print, cbit_cntrl, 0, /* ascii */ + cbit_space, -1, 1, /* blank - a GNU extension */ + cbit_cntrl, -1, 0, /* cntrl */ + cbit_digit, -1, 0, /* digit */ + cbit_graph, -1, 0, /* graph */ + cbit_print, -1, 0, /* print */ + cbit_punct, -1, 0, /* punct */ + cbit_space, -1, 0, /* space */ + cbit_word, -1, 0, /* word - a Perl extension */ + cbit_xdigit,-1, 0 /* xdigit */ +}; + +/* Table of substitutes for \d etc when PCRE_UCP is set. They are replaced by +Unicode property escapes. */ + +#ifdef SUPPORT_UCP +static const pcre_uchar string_PNd[] = { + CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET, + CHAR_N, CHAR_d, CHAR_RIGHT_CURLY_BRACKET, '\0' }; +static const pcre_uchar string_pNd[] = { + CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET, + CHAR_N, CHAR_d, CHAR_RIGHT_CURLY_BRACKET, '\0' }; +static const pcre_uchar string_PXsp[] = { + CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET, + CHAR_X, CHAR_s, CHAR_p, CHAR_RIGHT_CURLY_BRACKET, '\0' }; +static const pcre_uchar string_pXsp[] = { + CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET, + CHAR_X, CHAR_s, CHAR_p, CHAR_RIGHT_CURLY_BRACKET, '\0' }; +static const pcre_uchar string_PXwd[] = { + CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET, + CHAR_X, CHAR_w, CHAR_d, CHAR_RIGHT_CURLY_BRACKET, '\0' }; +static const pcre_uchar string_pXwd[] = { + CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET, + CHAR_X, CHAR_w, CHAR_d, CHAR_RIGHT_CURLY_BRACKET, '\0' }; + +static const pcre_uchar *substitutes[] = { + string_PNd, /* \D */ + string_pNd, /* \d */ + string_PXsp, /* \S */ /* Xsp is Perl space, but from 8.34, Perl */ + string_pXsp, /* \s */ /* space and POSIX space are the same. */ + string_PXwd, /* \W */ + string_pXwd /* \w */ +}; + +/* The POSIX class substitutes must be in the order of the POSIX class names, +defined above, and there are both positive and negative cases. NULL means no +general substitute of a Unicode property escape (\p or \P). However, for some +POSIX classes (e.g. graph, print, punct) a special property code is compiled +directly. */ + +static const pcre_uchar string_pL[] = { + CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET, + CHAR_L, CHAR_RIGHT_CURLY_BRACKET, '\0' }; +static const pcre_uchar string_pLl[] = { + CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET, + CHAR_L, CHAR_l, CHAR_RIGHT_CURLY_BRACKET, '\0' }; +static const pcre_uchar string_pLu[] = { + CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET, + CHAR_L, CHAR_u, CHAR_RIGHT_CURLY_BRACKET, '\0' }; +static const pcre_uchar string_pXan[] = { + CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET, + CHAR_X, CHAR_a, CHAR_n, CHAR_RIGHT_CURLY_BRACKET, '\0' }; +static const pcre_uchar string_h[] = { + CHAR_BACKSLASH, CHAR_h, '\0' }; +static const pcre_uchar string_pXps[] = { + CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET, + CHAR_X, CHAR_p, CHAR_s, CHAR_RIGHT_CURLY_BRACKET, '\0' }; +static const pcre_uchar string_PL[] = { + CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET, + CHAR_L, CHAR_RIGHT_CURLY_BRACKET, '\0' }; +static const pcre_uchar string_PLl[] = { + CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET, + CHAR_L, CHAR_l, CHAR_RIGHT_CURLY_BRACKET, '\0' }; +static const pcre_uchar string_PLu[] = { + CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET, + CHAR_L, CHAR_u, CHAR_RIGHT_CURLY_BRACKET, '\0' }; +static const pcre_uchar string_PXan[] = { + CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET, + CHAR_X, CHAR_a, CHAR_n, CHAR_RIGHT_CURLY_BRACKET, '\0' }; +static const pcre_uchar string_H[] = { + CHAR_BACKSLASH, CHAR_H, '\0' }; +static const pcre_uchar string_PXps[] = { + CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET, + CHAR_X, CHAR_p, CHAR_s, CHAR_RIGHT_CURLY_BRACKET, '\0' }; + +static const pcre_uchar *posix_substitutes[] = { + string_pL, /* alpha */ + string_pLl, /* lower */ + string_pLu, /* upper */ + string_pXan, /* alnum */ + NULL, /* ascii */ + string_h, /* blank */ + NULL, /* cntrl */ + string_pNd, /* digit */ + NULL, /* graph */ + NULL, /* print */ + NULL, /* punct */ + string_pXps, /* space */ /* Xps is POSIX space, but from 8.34 */ + string_pXwd, /* word */ /* Perl and POSIX space are the same */ + NULL, /* xdigit */ + /* Negated cases */ + string_PL, /* ^alpha */ + string_PLl, /* ^lower */ + string_PLu, /* ^upper */ + string_PXan, /* ^alnum */ + NULL, /* ^ascii */ + string_H, /* ^blank */ + NULL, /* ^cntrl */ + string_PNd, /* ^digit */ + NULL, /* ^graph */ + NULL, /* ^print */ + NULL, /* ^punct */ + string_PXps, /* ^space */ /* Xps is POSIX space, but from 8.34 */ + string_PXwd, /* ^word */ /* Perl and POSIX space are the same */ + NULL /* ^xdigit */ +}; +#define POSIX_SUBSIZE (sizeof(posix_substitutes) / sizeof(pcre_uchar *)) +#endif + +#define STRING(a) # a +#define XSTRING(s) STRING(s) + +/* The texts of compile-time error messages. These are "char *" because they +are passed to the outside world. Do not ever re-use any error number, because +they are documented. Always add a new error instead. Messages marked DEAD below +are no longer used. This used to be a table of strings, but in order to reduce +the number of relocations needed when a shared library is loaded dynamically, +it is now one long string. We cannot use a table of offsets, because the +lengths of inserts such as XSTRING(MAX_NAME_SIZE) are not known. Instead, we +simply count through to the one we want - this isn't a performance issue +because these strings are used only when there is a compilation error. + +Each substring ends with \0 to insert a null character. This includes the final +substring, so that the whole string ends with \0\0, which can be detected when +counting through. */ + +static const char error_texts[] = + "no error\0" + "\\ at end of pattern\0" + "\\c at end of pattern\0" + "unrecognized character follows \\\0" + "numbers out of order in {} quantifier\0" + /* 5 */ + "number too big in {} quantifier\0" + "missing terminating ] for character class\0" + "invalid escape sequence in character class\0" + "range out of order in character class\0" + "nothing to repeat\0" + /* 10 */ + "operand of unlimited repeat could match the empty string\0" /** DEAD **/ + "internal error: unexpected repeat\0" + "unrecognized character after (? or (?-\0" + "POSIX named classes are supported only within a class\0" + "missing )\0" + /* 15 */ + "reference to non-existent subpattern\0" + "erroffset passed as NULL\0" + "unknown option bit(s) set\0" + "missing ) after comment\0" + "parentheses nested too deeply\0" /** DEAD **/ + /* 20 */ + "regular expression is too large\0" + "failed to get memory\0" + "unmatched parentheses\0" + "internal error: code overflow\0" + "unrecognized character after (?<\0" + /* 25 */ + "lookbehind assertion is not fixed length\0" + "malformed number or name after (?(\0" + "conditional group contains more than two branches\0" + "assertion expected after (?(\0" + "(?R or (?[+-]digits must be followed by )\0" + /* 30 */ + "unknown POSIX class name\0" + "POSIX collating elements are not supported\0" + "this version of PCRE is compiled without UTF support\0" + "spare error\0" /** DEAD **/ + "character value in \\x{} or \\o{} is too large\0" + /* 35 */ + "invalid condition (?(0)\0" + "\\C not allowed in lookbehind assertion\0" + "PCRE does not support \\L, \\l, \\N{name}, \\U, or \\u\0" + "number after (?C is > 255\0" + "closing ) for (?C expected\0" + /* 40 */ + "recursive call could loop indefinitely\0" + "unrecognized character after (?P\0" + "syntax error in subpattern name (missing terminator)\0" + "two named subpatterns have the same name\0" + "invalid UTF-8 string\0" + /* 45 */ + "support for \\P, \\p, and \\X has not been compiled\0" + "malformed \\P or \\p sequence\0" + "unknown property name after \\P or \\p\0" + "subpattern name is too long (maximum " XSTRING(MAX_NAME_SIZE) " characters)\0" + "too many named subpatterns (maximum " XSTRING(MAX_NAME_COUNT) ")\0" + /* 50 */ + "repeated subpattern is too long\0" /** DEAD **/ + "octal value is greater than \\377 in 8-bit non-UTF-8 mode\0" + "internal error: overran compiling workspace\0" + "internal error: previously-checked referenced subpattern not found\0" + "DEFINE group contains more than one branch\0" + /* 55 */ + "repeating a DEFINE group is not allowed\0" /** DEAD **/ + "inconsistent NEWLINE options\0" + "\\g is not followed by a braced, angle-bracketed, or quoted name/number or by a plain number\0" + "a numbered reference must not be zero\0" + "an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT)\0" + /* 60 */ + "(*VERB) not recognized or malformed\0" + "number is too big\0" + "subpattern name expected\0" + "digit expected after (?+\0" + "] is an invalid data character in JavaScript compatibility mode\0" + /* 65 */ + "different names for subpatterns of the same number are not allowed\0" + "(*MARK) must have an argument\0" + "this version of PCRE is not compiled with Unicode property support\0" + "\\c must be followed by an ASCII character\0" + "\\k is not followed by a braced, angle-bracketed, or quoted name\0" + /* 70 */ + "internal error: unknown opcode in find_fixedlength()\0" + "\\N is not supported in a class\0" + "too many forward references\0" + "disallowed Unicode code point (>= 0xd800 && <= 0xdfff)\0" + "invalid UTF-16 string\0" + /* 75 */ + "name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN)\0" + "character value in \\u.... sequence is too large\0" + "invalid UTF-32 string\0" + "setting UTF is disabled by the application\0" + "non-hex character in \\x{} (closing brace missing?)\0" + /* 80 */ + "non-octal character in \\o{} (closing brace missing?)\0" + "missing opening brace after \\o\0" + "parentheses are too deeply nested\0" + "invalid range in character class\0" + "group name must start with a non-digit\0" + /* 85 */ + "parentheses are too deeply nested (stack check)\0" + ; + +/* Table to identify digits and hex digits. This is used when compiling +patterns. Note that the tables in chartables are dependent on the locale, and +may mark arbitrary characters as digits - but the PCRE compiling code expects +to handle only 0-9, a-z, and A-Z as digits when compiling. That is why we have +a private table here. It costs 256 bytes, but it is a lot faster than doing +character value tests (at least in some simple cases I timed), and in some +applications one wants PCRE to compile efficiently as well as match +efficiently. + +For convenience, we use the same bit definitions as in chartables: + + 0x04 decimal digit + 0x08 hexadecimal digit + +Then we can use ctype_digit and ctype_xdigit in the code. */ + +/* Using a simple comparison for decimal numbers rather than a memory read +is much faster, and the resulting code is simpler (the compiler turns it +into a subtraction and unsigned comparison). */ + +#define IS_DIGIT(x) ((x) >= CHAR_0 && (x) <= CHAR_9) + +#ifndef EBCDIC + +/* This is the "normal" case, for ASCII systems, and EBCDIC systems running in +UTF-8 mode. */ + +static const pcre_uint8 digitab[] = + { + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 8- 15 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - ' */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ( - / */ + 0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c, /* 0 - 7 */ + 0x0c,0x0c,0x00,0x00,0x00,0x00,0x00,0x00, /* 8 - ? */ + 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* @ - G */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* H - O */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* P - W */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* X - _ */ + 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* ` - g */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* h - o */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* p - w */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* x -127 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160-167 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 192-199 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 208-215 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 224-231 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */ + +#else + +/* This is the "abnormal" case, for EBCDIC systems not running in UTF-8 mode. */ + +static const pcre_uint8 digitab[] = + { + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 0 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 8- 15 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 10 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 32- 39 20 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 40- 47 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 48- 55 30 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 56- 63 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - 71 40 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 72- | */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* & - 87 50 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 88- 95 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - -103 60 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 104- ? */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 70 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 120- " */ + 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* 128- g 80 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* h -143 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144- p 90 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* q -159 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160- x A0 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* y -175 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ^ -183 B0 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ + 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* { - G C0 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* H -207 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* } - P D0 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* Q -223 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* \ - X E0 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* Y -239 */ + 0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c, /* 0 - 7 F0 */ + 0x0c,0x0c,0x00,0x00,0x00,0x00,0x00,0x00};/* 8 -255 */ + +static const pcre_uint8 ebcdic_chartab[] = { /* chartable partial dup */ + 0x80,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /* 0- 7 */ + 0x00,0x00,0x00,0x00,0x01,0x01,0x00,0x00, /* 8- 15 */ + 0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /* 16- 23 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ + 0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /* 32- 39 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 40- 47 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 48- 55 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 56- 63 */ + 0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - 71 */ + 0x00,0x00,0x00,0x80,0x00,0x80,0x80,0x80, /* 72- | */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* & - 87 */ + 0x00,0x00,0x00,0x80,0x80,0x80,0x00,0x00, /* 88- 95 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - -103 */ + 0x00,0x00,0x00,0x00,0x00,0x10,0x00,0x80, /* 104- ? */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 120- " */ + 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* 128- g */ + 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* h -143 */ + 0x00,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* 144- p */ + 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* q -159 */ + 0x00,0x00,0x12,0x12,0x12,0x12,0x12,0x12, /* 160- x */ + 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* y -175 */ + 0x80,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ^ -183 */ + 0x00,0x00,0x80,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ + 0x80,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* { - G */ + 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* H -207 */ + 0x00,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* } - P */ + 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* Q -223 */ + 0x00,0x00,0x12,0x12,0x12,0x12,0x12,0x12, /* \ - X */ + 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* Y -239 */ + 0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c, /* 0 - 7 */ + 0x1c,0x1c,0x00,0x00,0x00,0x00,0x00,0x00};/* 8 -255 */ +#endif + + +/* This table is used to check whether auto-possessification is possible +between adjacent character-type opcodes. The left-hand (repeated) opcode is +used to select the row, and the right-hand opcode is use to select the column. +A value of 1 means that auto-possessification is OK. For example, the second +value in the first row means that \D+\d can be turned into \D++\d. + +The Unicode property types (\P and \p) have to be present to fill out the table +because of what their opcode values are, but the table values should always be +zero because property types are handled separately in the code. The last four +columns apply to items that cannot be repeated, so there is no need to have +rows for them. Note that OP_DIGIT etc. are generated only when PCRE_UCP is +*not* set. When it is set, \d etc. are converted into OP_(NOT_)PROP codes. */ + +#define APTROWS (LAST_AUTOTAB_LEFT_OP - FIRST_AUTOTAB_OP + 1) +#define APTCOLS (LAST_AUTOTAB_RIGHT_OP - FIRST_AUTOTAB_OP + 1) + +static const pcre_uint8 autoposstab[APTROWS][APTCOLS] = { +/* \D \d \S \s \W \w . .+ \C \P \p \R \H \h \V \v \X \Z \z $ $M */ + { 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0 }, /* \D */ + { 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1 }, /* \d */ + { 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1 }, /* \S */ + { 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0 }, /* \s */ + { 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0 }, /* \W */ + { 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1 }, /* \w */ + { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0 }, /* . */ + { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0 }, /* .+ */ + { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0 }, /* \C */ + { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, /* \P */ + { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, /* \p */ + { 0, 1, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0 }, /* \R */ + { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0 }, /* \H */ + { 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 1, 0, 0 }, /* \h */ + { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0 }, /* \V */ + { 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0 }, /* \v */ + { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0 } /* \X */ +}; + + +/* This table is used to check whether auto-possessification is possible +between adjacent Unicode property opcodes (OP_PROP and OP_NOTPROP). The +left-hand (repeated) opcode is used to select the row, and the right-hand +opcode is used to select the column. The values are as follows: + + 0 Always return FALSE (never auto-possessify) + 1 Character groups are distinct (possessify if both are OP_PROP) + 2 Check character categories in the same group (general or particular) + 3 TRUE if the two opcodes are not the same (PROP vs NOTPROP) + + 4 Check left general category vs right particular category + 5 Check right general category vs left particular category + + 6 Left alphanum vs right general category + 7 Left space vs right general category + 8 Left word vs right general category + + 9 Right alphanum vs left general category + 10 Right space vs left general category + 11 Right word vs left general category + + 12 Left alphanum vs right particular category + 13 Left space vs right particular category + 14 Left word vs right particular category + + 15 Right alphanum vs left particular category + 16 Right space vs left particular category + 17 Right word vs left particular category +*/ + +static const pcre_uint8 propposstab[PT_TABSIZE][PT_TABSIZE] = { +/* ANY LAMP GC PC SC ALNUM SPACE PXSPACE WORD CLIST UCNC */ + { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, /* PT_ANY */ + { 0, 3, 0, 0, 0, 3, 1, 1, 0, 0, 0 }, /* PT_LAMP */ + { 0, 0, 2, 4, 0, 9, 10, 10, 11, 0, 0 }, /* PT_GC */ + { 0, 0, 5, 2, 0, 15, 16, 16, 17, 0, 0 }, /* PT_PC */ + { 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0 }, /* PT_SC */ + { 0, 3, 6, 12, 0, 3, 1, 1, 0, 0, 0 }, /* PT_ALNUM */ + { 0, 1, 7, 13, 0, 1, 3, 3, 1, 0, 0 }, /* PT_SPACE */ + { 0, 1, 7, 13, 0, 1, 3, 3, 1, 0, 0 }, /* PT_PXSPACE */ + { 0, 0, 8, 14, 0, 0, 1, 1, 3, 0, 0 }, /* PT_WORD */ + { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, /* PT_CLIST */ + { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3 } /* PT_UCNC */ +}; + +/* This table is used to check whether auto-possessification is possible +between adjacent Unicode property opcodes (OP_PROP and OP_NOTPROP) when one +specifies a general category and the other specifies a particular category. The +row is selected by the general category and the column by the particular +category. The value is 1 if the particular category is not part of the general +category. */ + +static const pcre_uint8 catposstab[7][30] = { +/* Cc Cf Cn Co Cs Ll Lm Lo Lt Lu Mc Me Mn Nd Nl No Pc Pd Pe Pf Pi Po Ps Sc Sk Sm So Zl Zp Zs */ + { 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 }, /* C */ + { 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 }, /* L */ + { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 }, /* M */ + { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 }, /* N */ + { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1 }, /* P */ + { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1 }, /* S */ + { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0 } /* Z */ +}; + +/* This table is used when checking ALNUM, (PX)SPACE, SPACE, and WORD against +a general or particular category. The properties in each row are those +that apply to the character set in question. Duplication means that a little +unnecessary work is done when checking, but this keeps things much simpler +because they can all use the same code. For more details see the comment where +this table is used. + +Note: SPACE and PXSPACE used to be different because Perl excluded VT from +"space", but from Perl 5.18 it's included, so both categories are treated the +same here. */ + +static const pcre_uint8 posspropstab[3][4] = { + { ucp_L, ucp_N, ucp_N, ucp_Nl }, /* ALNUM, 3rd and 4th values redundant */ + { ucp_Z, ucp_Z, ucp_C, ucp_Cc }, /* SPACE and PXSPACE, 2nd value redundant */ + { ucp_L, ucp_N, ucp_P, ucp_Po } /* WORD */ +}; + +/* This table is used when converting repeating opcodes into possessified +versions as a result of an explicit possessive quantifier such as ++. A zero +value means there is no possessified version - in those cases the item in +question must be wrapped in ONCE brackets. The table is truncated at OP_CALLOUT +because all relevant opcodes are less than that. */ + +static const pcre_uint8 opcode_possessify[] = { + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 0 - 15 */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 16 - 31 */ + + 0, /* NOTI */ + OP_POSSTAR, 0, /* STAR, MINSTAR */ + OP_POSPLUS, 0, /* PLUS, MINPLUS */ + OP_POSQUERY, 0, /* QUERY, MINQUERY */ + OP_POSUPTO, 0, /* UPTO, MINUPTO */ + 0, /* EXACT */ + 0, 0, 0, 0, /* POS{STAR,PLUS,QUERY,UPTO} */ + + OP_POSSTARI, 0, /* STARI, MINSTARI */ + OP_POSPLUSI, 0, /* PLUSI, MINPLUSI */ + OP_POSQUERYI, 0, /* QUERYI, MINQUERYI */ + OP_POSUPTOI, 0, /* UPTOI, MINUPTOI */ + 0, /* EXACTI */ + 0, 0, 0, 0, /* POS{STARI,PLUSI,QUERYI,UPTOI} */ + + OP_NOTPOSSTAR, 0, /* NOTSTAR, NOTMINSTAR */ + OP_NOTPOSPLUS, 0, /* NOTPLUS, NOTMINPLUS */ + OP_NOTPOSQUERY, 0, /* NOTQUERY, NOTMINQUERY */ + OP_NOTPOSUPTO, 0, /* NOTUPTO, NOTMINUPTO */ + 0, /* NOTEXACT */ + 0, 0, 0, 0, /* NOTPOS{STAR,PLUS,QUERY,UPTO} */ + + OP_NOTPOSSTARI, 0, /* NOTSTARI, NOTMINSTARI */ + OP_NOTPOSPLUSI, 0, /* NOTPLUSI, NOTMINPLUSI */ + OP_NOTPOSQUERYI, 0, /* NOTQUERYI, NOTMINQUERYI */ + OP_NOTPOSUPTOI, 0, /* NOTUPTOI, NOTMINUPTOI */ + 0, /* NOTEXACTI */ + 0, 0, 0, 0, /* NOTPOS{STARI,PLUSI,QUERYI,UPTOI} */ + + OP_TYPEPOSSTAR, 0, /* TYPESTAR, TYPEMINSTAR */ + OP_TYPEPOSPLUS, 0, /* TYPEPLUS, TYPEMINPLUS */ + OP_TYPEPOSQUERY, 0, /* TYPEQUERY, TYPEMINQUERY */ + OP_TYPEPOSUPTO, 0, /* TYPEUPTO, TYPEMINUPTO */ + 0, /* TYPEEXACT */ + 0, 0, 0, 0, /* TYPEPOS{STAR,PLUS,QUERY,UPTO} */ + + OP_CRPOSSTAR, 0, /* CRSTAR, CRMINSTAR */ + OP_CRPOSPLUS, 0, /* CRPLUS, CRMINPLUS */ + OP_CRPOSQUERY, 0, /* CRQUERY, CRMINQUERY */ + OP_CRPOSRANGE, 0, /* CRRANGE, CRMINRANGE */ + 0, 0, 0, 0, /* CRPOS{STAR,PLUS,QUERY,RANGE} */ + + 0, 0, 0, /* CLASS, NCLASS, XCLASS */ + 0, 0, /* REF, REFI */ + 0, 0, /* DNREF, DNREFI */ + 0, 0 /* RECURSE, CALLOUT */ +}; + + + +/************************************************* +* Find an error text * +*************************************************/ + +/* The error texts are now all in one long string, to save on relocations. As +some of the text is of unknown length, we can't use a table of offsets. +Instead, just count through the strings. This is not a performance issue +because it happens only when there has been a compilation error. + +Argument: the error number +Returns: pointer to the error string +*/ + +static const char * +find_error_text(int n) +{ +const char *s = error_texts; +for (; n > 0; n--) + { + while (*s++ != CHAR_NULL) {}; + if (*s == CHAR_NULL) return "Error text not found (please report)"; + } +return s; +} + + + +/************************************************* +* Expand the workspace * +*************************************************/ + +/* This function is called during the second compiling phase, if the number of +forward references fills the existing workspace, which is originally a block on +the stack. A larger block is obtained from malloc() unless the ultimate limit +has been reached or the increase will be rather small. + +Argument: pointer to the compile data block +Returns: 0 if all went well, else an error number +*/ + +static int +expand_workspace(compile_data *cd) +{ +pcre_uchar *newspace; +int newsize = cd->workspace_size * 2; + +if (newsize > COMPILE_WORK_SIZE_MAX) newsize = COMPILE_WORK_SIZE_MAX; +if (cd->workspace_size >= COMPILE_WORK_SIZE_MAX || + newsize - cd->workspace_size < WORK_SIZE_SAFETY_MARGIN) + return ERR72; + +newspace = (PUBL(malloc))(IN_UCHARS(newsize)); +if (newspace == NULL) return ERR21; +memcpy(newspace, cd->start_workspace, cd->workspace_size * sizeof(pcre_uchar)); +cd->hwm = (pcre_uchar *)newspace + (cd->hwm - cd->start_workspace); +if (cd->workspace_size > COMPILE_WORK_SIZE) + (PUBL(free))((void *)cd->start_workspace); +cd->start_workspace = newspace; +cd->workspace_size = newsize; +return 0; +} + + + +/************************************************* +* Check for counted repeat * +*************************************************/ + +/* This function is called when a '{' is encountered in a place where it might +start a quantifier. It looks ahead to see if it really is a quantifier or not. +It is only a quantifier if it is one of the forms {ddd} {ddd,} or {ddd,ddd} +where the ddds are digits. + +Arguments: + p pointer to the first char after '{' + +Returns: TRUE or FALSE +*/ + +static BOOL +is_counted_repeat(const pcre_uchar *p) +{ +if (!IS_DIGIT(*p)) return FALSE; +p++; +while (IS_DIGIT(*p)) p++; +if (*p == CHAR_RIGHT_CURLY_BRACKET) return TRUE; + +if (*p++ != CHAR_COMMA) return FALSE; +if (*p == CHAR_RIGHT_CURLY_BRACKET) return TRUE; + +if (!IS_DIGIT(*p)) return FALSE; +p++; +while (IS_DIGIT(*p)) p++; + +return (*p == CHAR_RIGHT_CURLY_BRACKET); +} + + + +/************************************************* +* Handle escapes * +*************************************************/ + +/* This function is called when a \ has been encountered. It either returns a +positive value for a simple escape such as \n, or 0 for a data character which +will be placed in chptr. A backreference to group n is returned as negative n. +When UTF-8 is enabled, a positive value greater than 255 may be returned in +chptr. On entry, ptr is pointing at the \. On exit, it is on the final +character of the escape sequence. + +Arguments: + ptrptr points to the pattern position pointer + chptr points to a returned data character + errorcodeptr points to the errorcode variable + bracount number of previous extracting brackets + options the options bits + isclass TRUE if inside a character class + +Returns: zero => a data character + positive => a special escape sequence + negative => a back reference + on error, errorcodeptr is set +*/ + +static int +check_escape(const pcre_uchar **ptrptr, pcre_uint32 *chptr, int *errorcodeptr, + int bracount, int options, BOOL isclass) +{ +/* PCRE_UTF16 has the same value as PCRE_UTF8. */ +BOOL utf = (options & PCRE_UTF8) != 0; +const pcre_uchar *ptr = *ptrptr + 1; +pcre_uint32 c; +int escape = 0; +int i; + +GETCHARINCTEST(c, ptr); /* Get character value, increment pointer */ +ptr--; /* Set pointer back to the last byte */ + +/* If backslash is at the end of the pattern, it's an error. */ + +if (c == CHAR_NULL) *errorcodeptr = ERR1; + +/* Non-alphanumerics are literals. For digits or letters, do an initial lookup +in a table. A non-zero result is something that can be returned immediately. +Otherwise further processing may be required. */ + +#ifndef EBCDIC /* ASCII/UTF-8 coding */ +/* Not alphanumeric */ +else if (c < CHAR_0 || c > CHAR_z) {} +else if ((i = escapes[c - CHAR_0]) != 0) + { if (i > 0) c = (pcre_uint32)i; else escape = -i; } + +#else /* EBCDIC coding */ +/* Not alphanumeric */ +else if (c < CHAR_a || (!MAX_255(c) || (ebcdic_chartab[c] & 0x0E) == 0)) {} +else if ((i = escapes[c - 0x48]) != 0) { if (i > 0) c = (pcre_uint32)i; else escape = -i; } +#endif + +/* Escapes that need further processing, or are illegal. */ + +else + { + const pcre_uchar *oldptr; + BOOL braced, negated, overflow; + int s; + + switch (c) + { + /* A number of Perl escapes are not handled by PCRE. We give an explicit + error. */ + + case CHAR_l: + case CHAR_L: + *errorcodeptr = ERR37; + break; + + case CHAR_u: + if ((options & PCRE_JAVASCRIPT_COMPAT) != 0) + { + /* In JavaScript, \u must be followed by four hexadecimal numbers. + Otherwise it is a lowercase u letter. */ + if (MAX_255(ptr[1]) && (digitab[ptr[1]] & ctype_xdigit) != 0 + && MAX_255(ptr[2]) && (digitab[ptr[2]] & ctype_xdigit) != 0 + && MAX_255(ptr[3]) && (digitab[ptr[3]] & ctype_xdigit) != 0 + && MAX_255(ptr[4]) && (digitab[ptr[4]] & ctype_xdigit) != 0) + { + c = 0; + for (i = 0; i < 4; ++i) + { + register pcre_uint32 cc = *(++ptr); +#ifndef EBCDIC /* ASCII/UTF-8 coding */ + if (cc >= CHAR_a) cc -= 32; /* Convert to upper case */ + c = (c << 4) + cc - ((cc < CHAR_A)? CHAR_0 : (CHAR_A - 10)); +#else /* EBCDIC coding */ + if (cc >= CHAR_a && cc <= CHAR_z) cc += 64; /* Convert to upper case */ + c = (c << 4) + cc - ((cc >= CHAR_0)? CHAR_0 : (CHAR_A - 10)); +#endif + } + +#if defined COMPILE_PCRE8 + if (c > (utf ? 0x10ffffU : 0xffU)) +#elif defined COMPILE_PCRE16 + if (c > (utf ? 0x10ffffU : 0xffffU)) +#elif defined COMPILE_PCRE32 + if (utf && c > 0x10ffffU) +#endif + { + *errorcodeptr = ERR76; + } + else if (utf && c >= 0xd800 && c <= 0xdfff) *errorcodeptr = ERR73; + } + } + else + *errorcodeptr = ERR37; + break; + + case CHAR_U: + /* In JavaScript, \U is an uppercase U letter. */ + if ((options & PCRE_JAVASCRIPT_COMPAT) == 0) *errorcodeptr = ERR37; + break; + + /* In a character class, \g is just a literal "g". Outside a character + class, \g must be followed by one of a number of specific things: + + (1) A number, either plain or braced. If positive, it is an absolute + backreference. If negative, it is a relative backreference. This is a Perl + 5.10 feature. + + (2) Perl 5.10 also supports \g{name} as a reference to a named group. This + is part of Perl's movement towards a unified syntax for back references. As + this is synonymous with \k{name}, we fudge it up by pretending it really + was \k. + + (3) For Oniguruma compatibility we also support \g followed by a name or a + number either in angle brackets or in single quotes. However, these are + (possibly recursive) subroutine calls, _not_ backreferences. Just return + the ESC_g code (cf \k). */ + + case CHAR_g: + if (isclass) break; + if (ptr[1] == CHAR_LESS_THAN_SIGN || ptr[1] == CHAR_APOSTROPHE) + { + escape = ESC_g; + break; + } + + /* Handle the Perl-compatible cases */ + + if (ptr[1] == CHAR_LEFT_CURLY_BRACKET) + { + const pcre_uchar *p; + for (p = ptr+2; *p != CHAR_NULL && *p != CHAR_RIGHT_CURLY_BRACKET; p++) + if (*p != CHAR_MINUS && !IS_DIGIT(*p)) break; + if (*p != CHAR_NULL && *p != CHAR_RIGHT_CURLY_BRACKET) + { + escape = ESC_k; + break; + } + braced = TRUE; + ptr++; + } + else braced = FALSE; + + if (ptr[1] == CHAR_MINUS) + { + negated = TRUE; + ptr++; + } + else negated = FALSE; + + /* The integer range is limited by the machine's int representation. */ + s = 0; + overflow = FALSE; + while (IS_DIGIT(ptr[1])) + { + if (s > INT_MAX / 10 - 1) /* Integer overflow */ + { + overflow = TRUE; + break; + } + s = s * 10 + (int)(*(++ptr) - CHAR_0); + } + if (overflow) /* Integer overflow */ + { + while (IS_DIGIT(ptr[1])) + ptr++; + *errorcodeptr = ERR61; + break; + } + + if (braced && *(++ptr) != CHAR_RIGHT_CURLY_BRACKET) + { + *errorcodeptr = ERR57; + break; + } + + if (s == 0) + { + *errorcodeptr = ERR58; + break; + } + + if (negated) + { + if (s > bracount) + { + *errorcodeptr = ERR15; + break; + } + s = bracount - (s - 1); + } + + escape = -s; + break; + + /* The handling of escape sequences consisting of a string of digits + starting with one that is not zero is not straightforward. Perl has changed + over the years. Nowadays \g{} for backreferences and \o{} for octal are + recommended to avoid the ambiguities in the old syntax. + + Outside a character class, the digits are read as a decimal number. If the + number is less than 8 (used to be 10), or if there are that many previous + extracting left brackets, then it is a back reference. Otherwise, up to + three octal digits are read to form an escaped byte. Thus \123 is likely to + be octal 123 (cf \0123, which is octal 012 followed by the literal 3). If + the octal value is greater than 377, the least significant 8 bits are + taken. \8 and \9 are treated as the literal characters 8 and 9. + + Inside a character class, \ followed by a digit is always either a literal + 8 or 9 or an octal number. */ + + case CHAR_1: case CHAR_2: case CHAR_3: case CHAR_4: case CHAR_5: + case CHAR_6: case CHAR_7: case CHAR_8: case CHAR_9: + + if (!isclass) + { + oldptr = ptr; + /* The integer range is limited by the machine's int representation. */ + s = (int)(c -CHAR_0); + overflow = FALSE; + while (IS_DIGIT(ptr[1])) + { + if (s > INT_MAX / 10 - 1) /* Integer overflow */ + { + overflow = TRUE; + break; + } + s = s * 10 + (int)(*(++ptr) - CHAR_0); + } + if (overflow) /* Integer overflow */ + { + while (IS_DIGIT(ptr[1])) + ptr++; + *errorcodeptr = ERR61; + break; + } + if (s < 8 || s <= bracount) /* Check for back reference */ + { + escape = -s; + break; + } + ptr = oldptr; /* Put the pointer back and fall through */ + } + + /* Handle a digit following \ when the number is not a back reference. If + the first digit is 8 or 9, Perl used to generate a binary zero byte and + then treat the digit as a following literal. At least by Perl 5.18 this + changed so as not to insert the binary zero. */ + + if ((c = *ptr) >= CHAR_8) break; + + /* Fall through with a digit less than 8 */ + + /* \0 always starts an octal number, but we may drop through to here with a + larger first octal digit. The original code used just to take the least + significant 8 bits of octal numbers (I think this is what early Perls used + to do). Nowadays we allow for larger numbers in UTF-8 mode and 16-bit mode, + but no more than 3 octal digits. */ + + case CHAR_0: + c -= CHAR_0; + while(i++ < 2 && ptr[1] >= CHAR_0 && ptr[1] <= CHAR_7) + c = c * 8 + *(++ptr) - CHAR_0; +#ifdef COMPILE_PCRE8 + if (!utf && c > 0xff) *errorcodeptr = ERR51; +#endif + break; + + /* \o is a relatively new Perl feature, supporting a more general way of + specifying character codes in octal. The only supported form is \o{ddd}. */ + + case CHAR_o: + if (ptr[1] != CHAR_LEFT_CURLY_BRACKET) *errorcodeptr = ERR81; else + { + ptr += 2; + c = 0; + overflow = FALSE; + while (*ptr >= CHAR_0 && *ptr <= CHAR_7) + { + register pcre_uint32 cc = *ptr++; + if (c == 0 && cc == CHAR_0) continue; /* Leading zeroes */ +#ifdef COMPILE_PCRE32 + if (c >= 0x20000000l) { overflow = TRUE; break; } +#endif + c = (c << 3) + cc - CHAR_0 ; +#if defined COMPILE_PCRE8 + if (c > (utf ? 0x10ffffU : 0xffU)) { overflow = TRUE; break; } +#elif defined COMPILE_PCRE16 + if (c > (utf ? 0x10ffffU : 0xffffU)) { overflow = TRUE; break; } +#elif defined COMPILE_PCRE32 + if (utf && c > 0x10ffffU) { overflow = TRUE; break; } +#endif + } + if (overflow) + { + while (*ptr >= CHAR_0 && *ptr <= CHAR_7) ptr++; + *errorcodeptr = ERR34; + } + else if (*ptr == CHAR_RIGHT_CURLY_BRACKET) + { + if (utf && c >= 0xd800 && c <= 0xdfff) *errorcodeptr = ERR73; + } + else *errorcodeptr = ERR80; + } + break; + + /* \x is complicated. In JavaScript, \x must be followed by two hexadecimal + numbers. Otherwise it is a lowercase x letter. */ + + case CHAR_x: + if ((options & PCRE_JAVASCRIPT_COMPAT) != 0) + { + if (MAX_255(ptr[1]) && (digitab[ptr[1]] & ctype_xdigit) != 0 + && MAX_255(ptr[2]) && (digitab[ptr[2]] & ctype_xdigit) != 0) + { + c = 0; + for (i = 0; i < 2; ++i) + { + register pcre_uint32 cc = *(++ptr); +#ifndef EBCDIC /* ASCII/UTF-8 coding */ + if (cc >= CHAR_a) cc -= 32; /* Convert to upper case */ + c = (c << 4) + cc - ((cc < CHAR_A)? CHAR_0 : (CHAR_A - 10)); +#else /* EBCDIC coding */ + if (cc >= CHAR_a && cc <= CHAR_z) cc += 64; /* Convert to upper case */ + c = (c << 4) + cc - ((cc >= CHAR_0)? CHAR_0 : (CHAR_A - 10)); +#endif + } + } + } /* End JavaScript handling */ + + /* Handle \x in Perl's style. \x{ddd} is a character number which can be + greater than 0xff in utf or non-8bit mode, but only if the ddd are hex + digits. If not, { used to be treated as a data character. However, Perl + seems to read hex digits up to the first non-such, and ignore the rest, so + that, for example \x{zz} matches a binary zero. This seems crazy, so PCRE + now gives an error. */ + + else + { + if (ptr[1] == CHAR_LEFT_CURLY_BRACKET) + { + ptr += 2; + c = 0; + overflow = FALSE; + while (MAX_255(*ptr) && (digitab[*ptr] & ctype_xdigit) != 0) + { + register pcre_uint32 cc = *ptr++; + if (c == 0 && cc == CHAR_0) continue; /* Leading zeroes */ + +#ifdef COMPILE_PCRE32 + if (c >= 0x10000000l) { overflow = TRUE; break; } +#endif + +#ifndef EBCDIC /* ASCII/UTF-8 coding */ + if (cc >= CHAR_a) cc -= 32; /* Convert to upper case */ + c = (c << 4) + cc - ((cc < CHAR_A)? CHAR_0 : (CHAR_A - 10)); +#else /* EBCDIC coding */ + if (cc >= CHAR_a && cc <= CHAR_z) cc += 64; /* Convert to upper case */ + c = (c << 4) + cc - ((cc >= CHAR_0)? CHAR_0 : (CHAR_A - 10)); +#endif + +#if defined COMPILE_PCRE8 + if (c > (utf ? 0x10ffffU : 0xffU)) { overflow = TRUE; break; } +#elif defined COMPILE_PCRE16 + if (c > (utf ? 0x10ffffU : 0xffffU)) { overflow = TRUE; break; } +#elif defined COMPILE_PCRE32 + if (utf && c > 0x10ffffU) { overflow = TRUE; break; } +#endif + } + + if (overflow) + { + while (MAX_255(*ptr) && (digitab[*ptr] & ctype_xdigit) != 0) ptr++; + *errorcodeptr = ERR34; + } + + else if (*ptr == CHAR_RIGHT_CURLY_BRACKET) + { + if (utf && c >= 0xd800 && c <= 0xdfff) *errorcodeptr = ERR73; + } + + /* If the sequence of hex digits does not end with '}', give an error. + We used just to recognize this construct and fall through to the normal + \x handling, but nowadays Perl gives an error, which seems much more + sensible, so we do too. */ + + else *errorcodeptr = ERR79; + } /* End of \x{} processing */ + + /* Read a single-byte hex-defined char (up to two hex digits after \x) */ + + else + { + c = 0; + while (i++ < 2 && MAX_255(ptr[1]) && (digitab[ptr[1]] & ctype_xdigit) != 0) + { + pcre_uint32 cc; /* Some compilers don't like */ + cc = *(++ptr); /* ++ in initializers */ +#ifndef EBCDIC /* ASCII/UTF-8 coding */ + if (cc >= CHAR_a) cc -= 32; /* Convert to upper case */ + c = c * 16 + cc - ((cc < CHAR_A)? CHAR_0 : (CHAR_A - 10)); +#else /* EBCDIC coding */ + if (cc <= CHAR_z) cc += 64; /* Convert to upper case */ + c = c * 16 + cc - ((cc >= CHAR_0)? CHAR_0 : (CHAR_A - 10)); +#endif + } + } /* End of \xdd handling */ + } /* End of Perl-style \x handling */ + break; + + /* For \c, a following letter is upper-cased; then the 0x40 bit is flipped. + An error is given if the byte following \c is not an ASCII character. This + coding is ASCII-specific, but then the whole concept of \cx is + ASCII-specific. (However, an EBCDIC equivalent has now been added.) */ + + case CHAR_c: + c = *(++ptr); + if (c == CHAR_NULL) + { + *errorcodeptr = ERR2; + break; + } +#ifndef EBCDIC /* ASCII/UTF-8 coding */ + if (c > 127) /* Excludes all non-ASCII in either mode */ + { + *errorcodeptr = ERR68; + break; + } + if (c >= CHAR_a && c <= CHAR_z) c -= 32; + c ^= 0x40; +#else /* EBCDIC coding */ + if (c >= CHAR_a && c <= CHAR_z) c += 64; + c ^= 0xC0; +#endif + break; + + /* PCRE_EXTRA enables extensions to Perl in the matter of escapes. Any + other alphanumeric following \ is an error if PCRE_EXTRA was set; + otherwise, for Perl compatibility, it is a literal. This code looks a bit + odd, but there used to be some cases other than the default, and there may + be again in future, so I haven't "optimized" it. */ + + default: + if ((options & PCRE_EXTRA) != 0) switch(c) + { + default: + *errorcodeptr = ERR3; + break; + } + break; + } + } + +/* Perl supports \N{name} for character names, as well as plain \N for "not +newline". PCRE does not support \N{name}. However, it does support +quantification such as \N{2,3}. */ + +if (escape == ESC_N && ptr[1] == CHAR_LEFT_CURLY_BRACKET && + !is_counted_repeat(ptr+2)) + *errorcodeptr = ERR37; + +/* If PCRE_UCP is set, we change the values for \d etc. */ + +if ((options & PCRE_UCP) != 0 && escape >= ESC_D && escape <= ESC_w) + escape += (ESC_DU - ESC_D); + +/* Set the pointer to the final character before returning. */ + +*ptrptr = ptr; +*chptr = c; +return escape; +} + + + +#ifdef SUPPORT_UCP +/************************************************* +* Handle \P and \p * +*************************************************/ + +/* This function is called after \P or \p has been encountered, provided that +PCRE is compiled with support for Unicode properties. On entry, ptrptr is +pointing at the P or p. On exit, it is pointing at the final character of the +escape sequence. + +Argument: + ptrptr points to the pattern position pointer + negptr points to a boolean that is set TRUE for negation else FALSE + ptypeptr points to an unsigned int that is set to the type value + pdataptr points to an unsigned int that is set to the detailed property value + errorcodeptr points to the error code variable + +Returns: TRUE if the type value was found, or FALSE for an invalid type +*/ + +static BOOL +get_ucp(const pcre_uchar **ptrptr, BOOL *negptr, unsigned int *ptypeptr, + unsigned int *pdataptr, int *errorcodeptr) +{ +pcre_uchar c; +int i, bot, top; +const pcre_uchar *ptr = *ptrptr; +pcre_uchar name[32]; + +c = *(++ptr); +if (c == CHAR_NULL) goto ERROR_RETURN; + +*negptr = FALSE; + +/* \P or \p can be followed by a name in {}, optionally preceded by ^ for +negation. */ + +if (c == CHAR_LEFT_CURLY_BRACKET) + { + if (ptr[1] == CHAR_CIRCUMFLEX_ACCENT) + { + *negptr = TRUE; + ptr++; + } + for (i = 0; i < (int)(sizeof(name) / sizeof(pcre_uchar)) - 1; i++) + { + c = *(++ptr); + if (c == CHAR_NULL) goto ERROR_RETURN; + if (c == CHAR_RIGHT_CURLY_BRACKET) break; + name[i] = c; + } + if (c != CHAR_RIGHT_CURLY_BRACKET) goto ERROR_RETURN; + name[i] = 0; + } + +/* Otherwise there is just one following character */ + +else + { + name[0] = c; + name[1] = 0; + } + +*ptrptr = ptr; + +/* Search for a recognized property name using binary chop */ + +bot = 0; +top = PRIV(utt_size); + +while (bot < top) + { + int r; + i = (bot + top) >> 1; + r = STRCMP_UC_C8(name, PRIV(utt_names) + PRIV(utt)[i].name_offset); + if (r == 0) + { + *ptypeptr = PRIV(utt)[i].type; + *pdataptr = PRIV(utt)[i].value; + return TRUE; + } + if (r > 0) bot = i + 1; else top = i; + } + +*errorcodeptr = ERR47; +*ptrptr = ptr; +return FALSE; + +ERROR_RETURN: +*errorcodeptr = ERR46; +*ptrptr = ptr; +return FALSE; +} +#endif + + + +/************************************************* +* Read repeat counts * +*************************************************/ + +/* Read an item of the form {n,m} and return the values. This is called only +after is_counted_repeat() has confirmed that a repeat-count quantifier exists, +so the syntax is guaranteed to be correct, but we need to check the values. + +Arguments: + p pointer to first char after '{' + minp pointer to int for min + maxp pointer to int for max + returned as -1 if no max + errorcodeptr points to error code variable + +Returns: pointer to '}' on success; + current ptr on error, with errorcodeptr set non-zero +*/ + +static const pcre_uchar * +read_repeat_counts(const pcre_uchar *p, int *minp, int *maxp, int *errorcodeptr) +{ +int min = 0; +int max = -1; + +/* Read the minimum value and do a paranoid check: a negative value indicates +an integer overflow. */ + +while (IS_DIGIT(*p)) min = min * 10 + (int)(*p++ - CHAR_0); +if (min < 0 || min > 65535) + { + *errorcodeptr = ERR5; + return p; + } + +/* Read the maximum value if there is one, and again do a paranoid on its size. +Also, max must not be less than min. */ + +if (*p == CHAR_RIGHT_CURLY_BRACKET) max = min; else + { + if (*(++p) != CHAR_RIGHT_CURLY_BRACKET) + { + max = 0; + while(IS_DIGIT(*p)) max = max * 10 + (int)(*p++ - CHAR_0); + if (max < 0 || max > 65535) + { + *errorcodeptr = ERR5; + return p; + } + if (max < min) + { + *errorcodeptr = ERR4; + return p; + } + } + } + +/* Fill in the required variables, and pass back the pointer to the terminating +'}'. */ + +*minp = min; +*maxp = max; +return p; +} + + + +/************************************************* +* Find first significant op code * +*************************************************/ + +/* This is called by several functions that scan a compiled expression looking +for a fixed first character, or an anchoring op code etc. It skips over things +that do not influence this. For some calls, it makes sense to skip negative +forward and all backward assertions, and also the \b assertion; for others it +does not. + +Arguments: + code pointer to the start of the group + skipassert TRUE if certain assertions are to be skipped + +Returns: pointer to the first significant opcode +*/ + +static const pcre_uchar* +first_significant_code(const pcre_uchar *code, BOOL skipassert) +{ +for (;;) + { + switch ((int)*code) + { + case OP_ASSERT_NOT: + case OP_ASSERTBACK: + case OP_ASSERTBACK_NOT: + if (!skipassert) return code; + do code += GET(code, 1); while (*code == OP_ALT); + code += PRIV(OP_lengths)[*code]; + break; + + case OP_WORD_BOUNDARY: + case OP_NOT_WORD_BOUNDARY: + if (!skipassert) return code; + /* Fall through */ + + case OP_CALLOUT: + case OP_CREF: + case OP_DNCREF: + case OP_RREF: + case OP_DNRREF: + case OP_DEF: + code += PRIV(OP_lengths)[*code]; + break; + + default: + return code; + } + } +/* Control never reaches here */ +} + + + +/************************************************* +* Find the fixed length of a branch * +*************************************************/ + +/* Scan a branch and compute the fixed length of subject that will match it, +if the length is fixed. This is needed for dealing with backward assertions. +In UTF8 mode, the result is in characters rather than bytes. The branch is +temporarily terminated with OP_END when this function is called. + +This function is called when a backward assertion is encountered, so that if it +fails, the error message can point to the correct place in the pattern. +However, we cannot do this when the assertion contains subroutine calls, +because they can be forward references. We solve this by remembering this case +and doing the check at the end; a flag specifies which mode we are running in. + +Arguments: + code points to the start of the pattern (the bracket) + utf TRUE in UTF-8 / UTF-16 / UTF-32 mode + atend TRUE if called when the pattern is complete + cd the "compile data" structure + +Returns: the fixed length, + or -1 if there is no fixed length, + or -2 if \C was encountered (in UTF-8 mode only) + or -3 if an OP_RECURSE item was encountered and atend is FALSE + or -4 if an unknown opcode was encountered (internal error) +*/ + +static int +find_fixedlength(pcre_uchar *code, BOOL utf, BOOL atend, compile_data *cd) +{ +int length = -1; + +register int branchlength = 0; +register pcre_uchar *cc = code + 1 + LINK_SIZE; + +/* Scan along the opcodes for this branch. If we get to the end of the +branch, check the length against that of the other branches. */ + +for (;;) + { + int d; + pcre_uchar *ce, *cs; + register pcre_uchar op = *cc; + + switch (op) + { + /* We only need to continue for OP_CBRA (normal capturing bracket) and + OP_BRA (normal non-capturing bracket) because the other variants of these + opcodes are all concerned with unlimited repeated groups, which of course + are not of fixed length. */ + + case OP_CBRA: + case OP_BRA: + case OP_ONCE: + case OP_ONCE_NC: + case OP_COND: + d = find_fixedlength(cc + ((op == OP_CBRA)? IMM2_SIZE : 0), utf, atend, cd); + if (d < 0) return d; + branchlength += d; + do cc += GET(cc, 1); while (*cc == OP_ALT); + cc += 1 + LINK_SIZE; + break; + + /* Reached end of a branch; if it's a ket it is the end of a nested call. + If it's ALT it is an alternation in a nested call. An ACCEPT is effectively + an ALT. If it is END it's the end of the outer call. All can be handled by + the same code. Note that we must not include the OP_KETRxxx opcodes here, + because they all imply an unlimited repeat. */ + + case OP_ALT: + case OP_KET: + case OP_END: + case OP_ACCEPT: + case OP_ASSERT_ACCEPT: + if (length < 0) length = branchlength; + else if (length != branchlength) return -1; + if (*cc != OP_ALT) return length; + cc += 1 + LINK_SIZE; + branchlength = 0; + break; + + /* A true recursion implies not fixed length, but a subroutine call may + be OK. If the subroutine is a forward reference, we can't deal with + it until the end of the pattern, so return -3. */ + + case OP_RECURSE: + if (!atend) return -3; + cs = ce = (pcre_uchar *)cd->start_code + GET(cc, 1); /* Start subpattern */ + do ce += GET(ce, 1); while (*ce == OP_ALT); /* End subpattern */ + if (cc > cs && cc < ce) return -1; /* Recursion */ + d = find_fixedlength(cs + IMM2_SIZE, utf, atend, cd); + if (d < 0) return d; + branchlength += d; + cc += 1 + LINK_SIZE; + break; + + /* Skip over assertive subpatterns */ + + case OP_ASSERT: + case OP_ASSERT_NOT: + case OP_ASSERTBACK: + case OP_ASSERTBACK_NOT: + do cc += GET(cc, 1); while (*cc == OP_ALT); + cc += PRIV(OP_lengths)[*cc]; + break; + + /* Skip over things that don't match chars */ + + case OP_MARK: + case OP_PRUNE_ARG: + case OP_SKIP_ARG: + case OP_THEN_ARG: + cc += cc[1] + PRIV(OP_lengths)[*cc]; + break; + + case OP_CALLOUT: + case OP_CIRC: + case OP_CIRCM: + case OP_CLOSE: + case OP_COMMIT: + case OP_CREF: + case OP_DEF: + case OP_DNCREF: + case OP_DNRREF: + case OP_DOLL: + case OP_DOLLM: + case OP_EOD: + case OP_EODN: + case OP_FAIL: + case OP_NOT_WORD_BOUNDARY: + case OP_PRUNE: + case OP_REVERSE: + case OP_RREF: + case OP_SET_SOM: + case OP_SKIP: + case OP_SOD: + case OP_SOM: + case OP_THEN: + case OP_WORD_BOUNDARY: + cc += PRIV(OP_lengths)[*cc]; + break; + + /* Handle literal characters */ + + case OP_CHAR: + case OP_CHARI: + case OP_NOT: + case OP_NOTI: + branchlength++; + cc += 2; +#ifdef SUPPORT_UTF + if (utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); +#endif + break; + + /* Handle exact repetitions. The count is already in characters, but we + need to skip over a multibyte character in UTF8 mode. */ + + case OP_EXACT: + case OP_EXACTI: + case OP_NOTEXACT: + case OP_NOTEXACTI: + branchlength += (int)GET2(cc,1); + cc += 2 + IMM2_SIZE; +#ifdef SUPPORT_UTF + if (utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); +#endif + break; + + case OP_TYPEEXACT: + branchlength += GET2(cc,1); + if (cc[1 + IMM2_SIZE] == OP_PROP || cc[1 + IMM2_SIZE] == OP_NOTPROP) + cc += 2; + cc += 1 + IMM2_SIZE + 1; + break; + + /* Handle single-char matchers */ + + case OP_PROP: + case OP_NOTPROP: + cc += 2; + /* Fall through */ + + case OP_HSPACE: + case OP_VSPACE: + case OP_NOT_HSPACE: + case OP_NOT_VSPACE: + case OP_NOT_DIGIT: + case OP_DIGIT: + case OP_NOT_WHITESPACE: + case OP_WHITESPACE: + case OP_NOT_WORDCHAR: + case OP_WORDCHAR: + case OP_ANY: + case OP_ALLANY: + branchlength++; + cc++; + break; + + /* The single-byte matcher isn't allowed. This only happens in UTF-8 mode; + otherwise \C is coded as OP_ALLANY. */ + + case OP_ANYBYTE: + return -2; + + /* Check a class for variable quantification */ + + case OP_CLASS: + case OP_NCLASS: +#if defined SUPPORT_UTF || defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + case OP_XCLASS: + /* The original code caused an unsigned overflow in 64 bit systems, + so now we use a conditional statement. */ + if (op == OP_XCLASS) + cc += GET(cc, 1); + else + cc += PRIV(OP_lengths)[OP_CLASS]; +#else + cc += PRIV(OP_lengths)[OP_CLASS]; +#endif + + switch (*cc) + { + case OP_CRSTAR: + case OP_CRMINSTAR: + case OP_CRPLUS: + case OP_CRMINPLUS: + case OP_CRQUERY: + case OP_CRMINQUERY: + case OP_CRPOSSTAR: + case OP_CRPOSPLUS: + case OP_CRPOSQUERY: + return -1; + + case OP_CRRANGE: + case OP_CRMINRANGE: + case OP_CRPOSRANGE: + if (GET2(cc,1) != GET2(cc,1+IMM2_SIZE)) return -1; + branchlength += (int)GET2(cc,1); + cc += 1 + 2 * IMM2_SIZE; + break; + + default: + branchlength++; + } + break; + + /* Anything else is variable length */ + + case OP_ANYNL: + case OP_BRAMINZERO: + case OP_BRAPOS: + case OP_BRAPOSZERO: + case OP_BRAZERO: + case OP_CBRAPOS: + case OP_EXTUNI: + case OP_KETRMAX: + case OP_KETRMIN: + case OP_KETRPOS: + case OP_MINPLUS: + case OP_MINPLUSI: + case OP_MINQUERY: + case OP_MINQUERYI: + case OP_MINSTAR: + case OP_MINSTARI: + case OP_MINUPTO: + case OP_MINUPTOI: + case OP_NOTMINPLUS: + case OP_NOTMINPLUSI: + case OP_NOTMINQUERY: + case OP_NOTMINQUERYI: + case OP_NOTMINSTAR: + case OP_NOTMINSTARI: + case OP_NOTMINUPTO: + case OP_NOTMINUPTOI: + case OP_NOTPLUS: + case OP_NOTPLUSI: + case OP_NOTPOSPLUS: + case OP_NOTPOSPLUSI: + case OP_NOTPOSQUERY: + case OP_NOTPOSQUERYI: + case OP_NOTPOSSTAR: + case OP_NOTPOSSTARI: + case OP_NOTPOSUPTO: + case OP_NOTPOSUPTOI: + case OP_NOTQUERY: + case OP_NOTQUERYI: + case OP_NOTSTAR: + case OP_NOTSTARI: + case OP_NOTUPTO: + case OP_NOTUPTOI: + case OP_PLUS: + case OP_PLUSI: + case OP_POSPLUS: + case OP_POSPLUSI: + case OP_POSQUERY: + case OP_POSQUERYI: + case OP_POSSTAR: + case OP_POSSTARI: + case OP_POSUPTO: + case OP_POSUPTOI: + case OP_QUERY: + case OP_QUERYI: + case OP_REF: + case OP_REFI: + case OP_DNREF: + case OP_DNREFI: + case OP_SBRA: + case OP_SBRAPOS: + case OP_SCBRA: + case OP_SCBRAPOS: + case OP_SCOND: + case OP_SKIPZERO: + case OP_STAR: + case OP_STARI: + case OP_TYPEMINPLUS: + case OP_TYPEMINQUERY: + case OP_TYPEMINSTAR: + case OP_TYPEMINUPTO: + case OP_TYPEPLUS: + case OP_TYPEPOSPLUS: + case OP_TYPEPOSQUERY: + case OP_TYPEPOSSTAR: + case OP_TYPEPOSUPTO: + case OP_TYPEQUERY: + case OP_TYPESTAR: + case OP_TYPEUPTO: + case OP_UPTO: + case OP_UPTOI: + return -1; + + /* Catch unrecognized opcodes so that when new ones are added they + are not forgotten, as has happened in the past. */ + + default: + return -4; + } + } +/* Control never gets here */ +} + + + +/************************************************* +* Scan compiled regex for specific bracket * +*************************************************/ + +/* This little function scans through a compiled pattern until it finds a +capturing bracket with the given number, or, if the number is negative, an +instance of OP_REVERSE for a lookbehind. The function is global in the C sense +so that it can be called from pcre_study() when finding the minimum matching +length. + +Arguments: + code points to start of expression + utf TRUE in UTF-8 / UTF-16 / UTF-32 mode + number the required bracket number or negative to find a lookbehind + +Returns: pointer to the opcode for the bracket, or NULL if not found +*/ + +const pcre_uchar * +PRIV(find_bracket)(const pcre_uchar *code, BOOL utf, int number) +{ +for (;;) + { + register pcre_uchar c = *code; + + if (c == OP_END) return NULL; + + /* XCLASS is used for classes that cannot be represented just by a bit + map. This includes negated single high-valued characters. The length in + the table is zero; the actual length is stored in the compiled code. */ + + if (c == OP_XCLASS) code += GET(code, 1); + + /* Handle recursion */ + + else if (c == OP_REVERSE) + { + if (number < 0) return (pcre_uchar *)code; + code += PRIV(OP_lengths)[c]; + } + + /* Handle capturing bracket */ + + else if (c == OP_CBRA || c == OP_SCBRA || + c == OP_CBRAPOS || c == OP_SCBRAPOS) + { + int n = (int)GET2(code, 1+LINK_SIZE); + if (n == number) return (pcre_uchar *)code; + code += PRIV(OP_lengths)[c]; + } + + /* Otherwise, we can get the item's length from the table, except that for + repeated character types, we have to test for \p and \P, which have an extra + two bytes of parameters, and for MARK/PRUNE/SKIP/THEN with an argument, we + must add in its length. */ + + else + { + switch(c) + { + case OP_TYPESTAR: + case OP_TYPEMINSTAR: + case OP_TYPEPLUS: + case OP_TYPEMINPLUS: + case OP_TYPEQUERY: + case OP_TYPEMINQUERY: + case OP_TYPEPOSSTAR: + case OP_TYPEPOSPLUS: + case OP_TYPEPOSQUERY: + if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2; + break; + + case OP_TYPEUPTO: + case OP_TYPEMINUPTO: + case OP_TYPEEXACT: + case OP_TYPEPOSUPTO: + if (code[1 + IMM2_SIZE] == OP_PROP || code[1 + IMM2_SIZE] == OP_NOTPROP) + code += 2; + break; + + case OP_MARK: + case OP_PRUNE_ARG: + case OP_SKIP_ARG: + case OP_THEN_ARG: + code += code[1]; + break; + } + + /* Add in the fixed length from the table */ + + code += PRIV(OP_lengths)[c]; + + /* In UTF-8 mode, opcodes that are followed by a character may be followed by + a multi-byte character. The length in the table is a minimum, so we have to + arrange to skip the extra bytes. */ + +#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 + if (utf) switch(c) + { + case OP_CHAR: + case OP_CHARI: + case OP_EXACT: + case OP_EXACTI: + case OP_UPTO: + case OP_UPTOI: + case OP_MINUPTO: + case OP_MINUPTOI: + case OP_POSUPTO: + case OP_POSUPTOI: + case OP_STAR: + case OP_STARI: + case OP_MINSTAR: + case OP_MINSTARI: + case OP_POSSTAR: + case OP_POSSTARI: + case OP_PLUS: + case OP_PLUSI: + case OP_MINPLUS: + case OP_MINPLUSI: + case OP_POSPLUS: + case OP_POSPLUSI: + case OP_QUERY: + case OP_QUERYI: + case OP_MINQUERY: + case OP_MINQUERYI: + case OP_POSQUERY: + case OP_POSQUERYI: + if (HAS_EXTRALEN(code[-1])) code += GET_EXTRALEN(code[-1]); + break; + } +#else + (void)(utf); /* Keep compiler happy by referencing function argument */ +#endif + } + } +} + + + +/************************************************* +* Scan compiled regex for recursion reference * +*************************************************/ + +/* This little function scans through a compiled pattern until it finds an +instance of OP_RECURSE. + +Arguments: + code points to start of expression + utf TRUE in UTF-8 / UTF-16 / UTF-32 mode + +Returns: pointer to the opcode for OP_RECURSE, or NULL if not found +*/ + +static const pcre_uchar * +find_recurse(const pcre_uchar *code, BOOL utf) +{ +for (;;) + { + register pcre_uchar c = *code; + if (c == OP_END) return NULL; + if (c == OP_RECURSE) return code; + + /* XCLASS is used for classes that cannot be represented just by a bit + map. This includes negated single high-valued characters. The length in + the table is zero; the actual length is stored in the compiled code. */ + + if (c == OP_XCLASS) code += GET(code, 1); + + /* Otherwise, we can get the item's length from the table, except that for + repeated character types, we have to test for \p and \P, which have an extra + two bytes of parameters, and for MARK/PRUNE/SKIP/THEN with an argument, we + must add in its length. */ + + else + { + switch(c) + { + case OP_TYPESTAR: + case OP_TYPEMINSTAR: + case OP_TYPEPLUS: + case OP_TYPEMINPLUS: + case OP_TYPEQUERY: + case OP_TYPEMINQUERY: + case OP_TYPEPOSSTAR: + case OP_TYPEPOSPLUS: + case OP_TYPEPOSQUERY: + if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2; + break; + + case OP_TYPEPOSUPTO: + case OP_TYPEUPTO: + case OP_TYPEMINUPTO: + case OP_TYPEEXACT: + if (code[1 + IMM2_SIZE] == OP_PROP || code[1 + IMM2_SIZE] == OP_NOTPROP) + code += 2; + break; + + case OP_MARK: + case OP_PRUNE_ARG: + case OP_SKIP_ARG: + case OP_THEN_ARG: + code += code[1]; + break; + } + + /* Add in the fixed length from the table */ + + code += PRIV(OP_lengths)[c]; + + /* In UTF-8 mode, opcodes that are followed by a character may be followed + by a multi-byte character. The length in the table is a minimum, so we have + to arrange to skip the extra bytes. */ + +#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 + if (utf) switch(c) + { + case OP_CHAR: + case OP_CHARI: + case OP_NOT: + case OP_NOTI: + case OP_EXACT: + case OP_EXACTI: + case OP_NOTEXACT: + case OP_NOTEXACTI: + case OP_UPTO: + case OP_UPTOI: + case OP_NOTUPTO: + case OP_NOTUPTOI: + case OP_MINUPTO: + case OP_MINUPTOI: + case OP_NOTMINUPTO: + case OP_NOTMINUPTOI: + case OP_POSUPTO: + case OP_POSUPTOI: + case OP_NOTPOSUPTO: + case OP_NOTPOSUPTOI: + case OP_STAR: + case OP_STARI: + case OP_NOTSTAR: + case OP_NOTSTARI: + case OP_MINSTAR: + case OP_MINSTARI: + case OP_NOTMINSTAR: + case OP_NOTMINSTARI: + case OP_POSSTAR: + case OP_POSSTARI: + case OP_NOTPOSSTAR: + case OP_NOTPOSSTARI: + case OP_PLUS: + case OP_PLUSI: + case OP_NOTPLUS: + case OP_NOTPLUSI: + case OP_MINPLUS: + case OP_MINPLUSI: + case OP_NOTMINPLUS: + case OP_NOTMINPLUSI: + case OP_POSPLUS: + case OP_POSPLUSI: + case OP_NOTPOSPLUS: + case OP_NOTPOSPLUSI: + case OP_QUERY: + case OP_QUERYI: + case OP_NOTQUERY: + case OP_NOTQUERYI: + case OP_MINQUERY: + case OP_MINQUERYI: + case OP_NOTMINQUERY: + case OP_NOTMINQUERYI: + case OP_POSQUERY: + case OP_POSQUERYI: + case OP_NOTPOSQUERY: + case OP_NOTPOSQUERYI: + if (HAS_EXTRALEN(code[-1])) code += GET_EXTRALEN(code[-1]); + break; + } +#else + (void)(utf); /* Keep compiler happy by referencing function argument */ +#endif + } + } +} + + + +/************************************************* +* Scan compiled branch for non-emptiness * +*************************************************/ + +/* This function scans through a branch of a compiled pattern to see whether it +can match the empty string or not. It is called from could_be_empty() +below and from compile_branch() when checking for an unlimited repeat of a +group that can match nothing. Note that first_significant_code() skips over +backward and negative forward assertions when its final argument is TRUE. If we +hit an unclosed bracket, we return "empty" - this means we've struck an inner +bracket whose current branch will already have been scanned. + +Arguments: + code points to start of search + endcode points to where to stop + utf TRUE if in UTF-8 / UTF-16 / UTF-32 mode + cd contains pointers to tables etc. + recurses chain of recurse_check to catch mutual recursion + +Returns: TRUE if what is matched could be empty +*/ + +typedef struct recurse_check { + struct recurse_check *prev; + const pcre_uchar *group; +} recurse_check; + +static BOOL +could_be_empty_branch(const pcre_uchar *code, const pcre_uchar *endcode, + BOOL utf, compile_data *cd, recurse_check *recurses) +{ +register pcre_uchar c; +recurse_check this_recurse; + +for (code = first_significant_code(code + PRIV(OP_lengths)[*code], TRUE); + code < endcode; + code = first_significant_code(code + PRIV(OP_lengths)[c], TRUE)) + { + const pcre_uchar *ccode; + + c = *code; + + /* Skip over forward assertions; the other assertions are skipped by + first_significant_code() with a TRUE final argument. */ + + if (c == OP_ASSERT) + { + do code += GET(code, 1); while (*code == OP_ALT); + c = *code; + continue; + } + + /* For a recursion/subroutine call, if its end has been reached, which + implies a backward reference subroutine call, we can scan it. If it's a + forward reference subroutine call, we can't. To detect forward reference + we have to scan up the list that is kept in the workspace. This function is + called only when doing the real compile, not during the pre-compile that + measures the size of the compiled pattern. */ + + if (c == OP_RECURSE) + { + const pcre_uchar *scode = cd->start_code + GET(code, 1); + BOOL empty_branch; + + /* Test for forward reference or uncompleted reference. This is disabled + when called to scan a completed pattern by setting cd->start_workspace to + NULL. */ + + if (cd->start_workspace != NULL) + { + const pcre_uchar *tcode; + for (tcode = cd->start_workspace; tcode < cd->hwm; tcode += LINK_SIZE) + if ((int)GET(tcode, 0) == (int)(code + 1 - cd->start_code)) return TRUE; + if (GET(scode, 1) == 0) return TRUE; /* Unclosed */ + } + + /* If we are scanning a completed pattern, there are no forward references + and all groups are complete. We need to detect whether this is a recursive + call, as otherwise there will be an infinite loop. If it is a recursion, + just skip over it. Simple recursions are easily detected. For mutual + recursions we keep a chain on the stack. */ + + else + { + recurse_check *r = recurses; + const pcre_uchar *endgroup = scode; + + do endgroup += GET(endgroup, 1); while (*endgroup == OP_ALT); + if (code >= scode && code <= endgroup) continue; /* Simple recursion */ + + for (r = recurses; r != NULL; r = r->prev) + if (r->group == scode) break; + if (r != NULL) continue; /* Mutual recursion */ + } + + /* Completed reference; scan the referenced group, remembering it on the + stack chain to detect mutual recursions. */ + + empty_branch = FALSE; + this_recurse.prev = recurses; + this_recurse.group = scode; + + do + { + if (could_be_empty_branch(scode, endcode, utf, cd, &this_recurse)) + { + empty_branch = TRUE; + break; + } + scode += GET(scode, 1); + } + while (*scode == OP_ALT); + + if (!empty_branch) return FALSE; /* All branches are non-empty */ + continue; + } + + /* Groups with zero repeats can of course be empty; skip them. */ + + if (c == OP_BRAZERO || c == OP_BRAMINZERO || c == OP_SKIPZERO || + c == OP_BRAPOSZERO) + { + code += PRIV(OP_lengths)[c]; + do code += GET(code, 1); while (*code == OP_ALT); + c = *code; + continue; + } + + /* A nested group that is already marked as "could be empty" can just be + skipped. */ + + if (c == OP_SBRA || c == OP_SBRAPOS || + c == OP_SCBRA || c == OP_SCBRAPOS) + { + do code += GET(code, 1); while (*code == OP_ALT); + c = *code; + continue; + } + + /* For other groups, scan the branches. */ + + if (c == OP_BRA || c == OP_BRAPOS || + c == OP_CBRA || c == OP_CBRAPOS || + c == OP_ONCE || c == OP_ONCE_NC || + c == OP_COND) + { + BOOL empty_branch; + if (GET(code, 1) == 0) return TRUE; /* Hit unclosed bracket */ + + /* If a conditional group has only one branch, there is a second, implied, + empty branch, so just skip over the conditional, because it could be empty. + Otherwise, scan the individual branches of the group. */ + + if (c == OP_COND && code[GET(code, 1)] != OP_ALT) + code += GET(code, 1); + else + { + empty_branch = FALSE; + do + { + if (!empty_branch && could_be_empty_branch(code, endcode, utf, cd, NULL)) + empty_branch = TRUE; + code += GET(code, 1); + } + while (*code == OP_ALT); + if (!empty_branch) return FALSE; /* All branches are non-empty */ + } + + c = *code; + continue; + } + + /* Handle the other opcodes */ + + switch (c) + { + /* Check for quantifiers after a class. XCLASS is used for classes that + cannot be represented just by a bit map. This includes negated single + high-valued characters. The length in PRIV(OP_lengths)[] is zero; the + actual length is stored in the compiled code, so we must update "code" + here. */ + +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + case OP_XCLASS: + ccode = code += GET(code, 1); + goto CHECK_CLASS_REPEAT; +#endif + + case OP_CLASS: + case OP_NCLASS: + ccode = code + PRIV(OP_lengths)[OP_CLASS]; + +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + CHECK_CLASS_REPEAT: +#endif + + switch (*ccode) + { + case OP_CRSTAR: /* These could be empty; continue */ + case OP_CRMINSTAR: + case OP_CRQUERY: + case OP_CRMINQUERY: + case OP_CRPOSSTAR: + case OP_CRPOSQUERY: + break; + + default: /* Non-repeat => class must match */ + case OP_CRPLUS: /* These repeats aren't empty */ + case OP_CRMINPLUS: + case OP_CRPOSPLUS: + return FALSE; + + case OP_CRRANGE: + case OP_CRMINRANGE: + case OP_CRPOSRANGE: + if (GET2(ccode, 1) > 0) return FALSE; /* Minimum > 0 */ + break; + } + break; + + /* Opcodes that must match a character */ + + case OP_ANY: + case OP_ALLANY: + case OP_ANYBYTE: + + case OP_PROP: + case OP_NOTPROP: + case OP_ANYNL: + + case OP_NOT_HSPACE: + case OP_HSPACE: + case OP_NOT_VSPACE: + case OP_VSPACE: + case OP_EXTUNI: + + case OP_NOT_DIGIT: + case OP_DIGIT: + case OP_NOT_WHITESPACE: + case OP_WHITESPACE: + case OP_NOT_WORDCHAR: + case OP_WORDCHAR: + + case OP_CHAR: + case OP_CHARI: + case OP_NOT: + case OP_NOTI: + + case OP_PLUS: + case OP_PLUSI: + case OP_MINPLUS: + case OP_MINPLUSI: + + case OP_NOTPLUS: + case OP_NOTPLUSI: + case OP_NOTMINPLUS: + case OP_NOTMINPLUSI: + + case OP_POSPLUS: + case OP_POSPLUSI: + case OP_NOTPOSPLUS: + case OP_NOTPOSPLUSI: + + case OP_EXACT: + case OP_EXACTI: + case OP_NOTEXACT: + case OP_NOTEXACTI: + + case OP_TYPEPLUS: + case OP_TYPEMINPLUS: + case OP_TYPEPOSPLUS: + case OP_TYPEEXACT: + + return FALSE; + + /* These are going to continue, as they may be empty, but we have to + fudge the length for the \p and \P cases. */ + + case OP_TYPESTAR: + case OP_TYPEMINSTAR: + case OP_TYPEPOSSTAR: + case OP_TYPEQUERY: + case OP_TYPEMINQUERY: + case OP_TYPEPOSQUERY: + if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2; + break; + + /* Same for these */ + + case OP_TYPEUPTO: + case OP_TYPEMINUPTO: + case OP_TYPEPOSUPTO: + if (code[1 + IMM2_SIZE] == OP_PROP || code[1 + IMM2_SIZE] == OP_NOTPROP) + code += 2; + break; + + /* End of branch */ + + case OP_KET: + case OP_KETRMAX: + case OP_KETRMIN: + case OP_KETRPOS: + case OP_ALT: + return TRUE; + + /* In UTF-8 mode, STAR, MINSTAR, POSSTAR, QUERY, MINQUERY, POSQUERY, UPTO, + MINUPTO, and POSUPTO and their caseless and negative versions may be + followed by a multibyte character. */ + +#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 + case OP_STAR: + case OP_STARI: + case OP_NOTSTAR: + case OP_NOTSTARI: + + case OP_MINSTAR: + case OP_MINSTARI: + case OP_NOTMINSTAR: + case OP_NOTMINSTARI: + + case OP_POSSTAR: + case OP_POSSTARI: + case OP_NOTPOSSTAR: + case OP_NOTPOSSTARI: + + case OP_QUERY: + case OP_QUERYI: + case OP_NOTQUERY: + case OP_NOTQUERYI: + + case OP_MINQUERY: + case OP_MINQUERYI: + case OP_NOTMINQUERY: + case OP_NOTMINQUERYI: + + case OP_POSQUERY: + case OP_POSQUERYI: + case OP_NOTPOSQUERY: + case OP_NOTPOSQUERYI: + + if (utf && HAS_EXTRALEN(code[1])) code += GET_EXTRALEN(code[1]); + break; + + case OP_UPTO: + case OP_UPTOI: + case OP_NOTUPTO: + case OP_NOTUPTOI: + + case OP_MINUPTO: + case OP_MINUPTOI: + case OP_NOTMINUPTO: + case OP_NOTMINUPTOI: + + case OP_POSUPTO: + case OP_POSUPTOI: + case OP_NOTPOSUPTO: + case OP_NOTPOSUPTOI: + + if (utf && HAS_EXTRALEN(code[1 + IMM2_SIZE])) code += GET_EXTRALEN(code[1 + IMM2_SIZE]); + break; +#endif + + /* MARK, and PRUNE/SKIP/THEN with an argument must skip over the argument + string. */ + + case OP_MARK: + case OP_PRUNE_ARG: + case OP_SKIP_ARG: + case OP_THEN_ARG: + code += code[1]; + break; + + /* None of the remaining opcodes are required to match a character. */ + + default: + break; + } + } + +return TRUE; +} + + + +/************************************************* +* Scan compiled regex for non-emptiness * +*************************************************/ + +/* This function is called to check for left recursive calls. We want to check +the current branch of the current pattern to see if it could match the empty +string. If it could, we must look outwards for branches at other levels, +stopping when we pass beyond the bracket which is the subject of the recursion. +This function is called only during the real compile, not during the +pre-compile. + +Arguments: + code points to start of the recursion + endcode points to where to stop (current RECURSE item) + bcptr points to the chain of current (unclosed) branch starts + utf TRUE if in UTF-8 / UTF-16 / UTF-32 mode + cd pointers to tables etc + +Returns: TRUE if what is matched could be empty +*/ + +static BOOL +could_be_empty(const pcre_uchar *code, const pcre_uchar *endcode, + branch_chain *bcptr, BOOL utf, compile_data *cd) +{ +while (bcptr != NULL && bcptr->current_branch >= code) + { + if (!could_be_empty_branch(bcptr->current_branch, endcode, utf, cd, NULL)) + return FALSE; + bcptr = bcptr->outer; + } +return TRUE; +} + + + +/************************************************* +* Base opcode of repeated opcodes * +*************************************************/ + +/* Returns the base opcode for repeated single character type opcodes. If the +opcode is not a repeated character type, it returns with the original value. + +Arguments: c opcode +Returns: base opcode for the type +*/ + +static pcre_uchar +get_repeat_base(pcre_uchar c) +{ +return (c > OP_TYPEPOSUPTO)? c : + (c >= OP_TYPESTAR)? OP_TYPESTAR : + (c >= OP_NOTSTARI)? OP_NOTSTARI : + (c >= OP_NOTSTAR)? OP_NOTSTAR : + (c >= OP_STARI)? OP_STARI : + OP_STAR; +} + + + +#ifdef SUPPORT_UCP +/************************************************* +* Check a character and a property * +*************************************************/ + +/* This function is called by check_auto_possessive() when a property item +is adjacent to a fixed character. + +Arguments: + c the character + ptype the property type + pdata the data for the type + negated TRUE if it's a negated property (\P or \p{^) + +Returns: TRUE if auto-possessifying is OK +*/ + +static BOOL +check_char_prop(pcre_uint32 c, unsigned int ptype, unsigned int pdata, + BOOL negated) +{ +const pcre_uint32 *p; +const ucd_record *prop = GET_UCD(c); + +switch(ptype) + { + case PT_LAMP: + return (prop->chartype == ucp_Lu || + prop->chartype == ucp_Ll || + prop->chartype == ucp_Lt) == negated; + + case PT_GC: + return (pdata == PRIV(ucp_gentype)[prop->chartype]) == negated; + + case PT_PC: + return (pdata == prop->chartype) == negated; + + case PT_SC: + return (pdata == prop->script) == negated; + + /* These are specials */ + + case PT_ALNUM: + return (PRIV(ucp_gentype)[prop->chartype] == ucp_L || + PRIV(ucp_gentype)[prop->chartype] == ucp_N) == negated; + + /* Perl space used to exclude VT, but from Perl 5.18 it is included, which + means that Perl space and POSIX space are now identical. PCRE was changed + at release 8.34. */ + + case PT_SPACE: /* Perl space */ + case PT_PXSPACE: /* POSIX space */ + switch(c) + { + HSPACE_CASES: + VSPACE_CASES: + return negated; + + default: + return (PRIV(ucp_gentype)[prop->chartype] == ucp_Z) == negated; + } + break; /* Control never reaches here */ + + case PT_WORD: + return (PRIV(ucp_gentype)[prop->chartype] == ucp_L || + PRIV(ucp_gentype)[prop->chartype] == ucp_N || + c == CHAR_UNDERSCORE) == negated; + + case PT_CLIST: + p = PRIV(ucd_caseless_sets) + prop->caseset; + for (;;) + { + if (c < *p) return !negated; + if (c == *p++) return negated; + } + break; /* Control never reaches here */ + } + +return FALSE; +} +#endif /* SUPPORT_UCP */ + + + +/************************************************* +* Fill the character property list * +*************************************************/ + +/* Checks whether the code points to an opcode that can take part in auto- +possessification, and if so, fills a list with its properties. + +Arguments: + code points to start of expression + utf TRUE if in UTF-8 / UTF-16 / UTF-32 mode + fcc points to case-flipping table + list points to output list + list[0] will be filled with the opcode + list[1] will be non-zero if this opcode + can match an empty character string + list[2..7] depends on the opcode + +Returns: points to the start of the next opcode if *code is accepted + NULL if *code is not accepted +*/ + +static const pcre_uchar * +get_chr_property_list(const pcre_uchar *code, BOOL utf, + const pcre_uint8 *fcc, pcre_uint32 *list) +{ +pcre_uchar c = *code; +pcre_uchar base; +const pcre_uchar *end; +pcre_uint32 chr; + +#ifdef SUPPORT_UCP +pcre_uint32 *clist_dest; +const pcre_uint32 *clist_src; +#else +utf = utf; /* Suppress "unused parameter" compiler warning */ +#endif + +list[0] = c; +list[1] = FALSE; +code++; + +if (c >= OP_STAR && c <= OP_TYPEPOSUPTO) + { + base = get_repeat_base(c); + c -= (base - OP_STAR); + + if (c == OP_UPTO || c == OP_MINUPTO || c == OP_EXACT || c == OP_POSUPTO) + code += IMM2_SIZE; + + list[1] = (c != OP_PLUS && c != OP_MINPLUS && c != OP_EXACT && c != OP_POSPLUS); + + switch(base) + { + case OP_STAR: + list[0] = OP_CHAR; + break; + + case OP_STARI: + list[0] = OP_CHARI; + break; + + case OP_NOTSTAR: + list[0] = OP_NOT; + break; + + case OP_NOTSTARI: + list[0] = OP_NOTI; + break; + + case OP_TYPESTAR: + list[0] = *code; + code++; + break; + } + c = list[0]; + } + +switch(c) + { + case OP_NOT_DIGIT: + case OP_DIGIT: + case OP_NOT_WHITESPACE: + case OP_WHITESPACE: + case OP_NOT_WORDCHAR: + case OP_WORDCHAR: + case OP_ANY: + case OP_ALLANY: + case OP_ANYNL: + case OP_NOT_HSPACE: + case OP_HSPACE: + case OP_NOT_VSPACE: + case OP_VSPACE: + case OP_EXTUNI: + case OP_EODN: + case OP_EOD: + case OP_DOLL: + case OP_DOLLM: + return code; + + case OP_CHAR: + case OP_NOT: + GETCHARINCTEST(chr, code); + list[2] = chr; + list[3] = NOTACHAR; + return code; + + case OP_CHARI: + case OP_NOTI: + list[0] = (c == OP_CHARI) ? OP_CHAR : OP_NOT; + GETCHARINCTEST(chr, code); + list[2] = chr; + +#ifdef SUPPORT_UCP + if (chr < 128 || (chr < 256 && !utf)) + list[3] = fcc[chr]; + else + list[3] = UCD_OTHERCASE(chr); +#elif defined SUPPORT_UTF || !defined COMPILE_PCRE8 + list[3] = (chr < 256) ? fcc[chr] : chr; +#else + list[3] = fcc[chr]; +#endif + + /* The othercase might be the same value. */ + + if (chr == list[3]) + list[3] = NOTACHAR; + else + list[4] = NOTACHAR; + return code; + +#ifdef SUPPORT_UCP + case OP_PROP: + case OP_NOTPROP: + if (code[0] != PT_CLIST) + { + list[2] = code[0]; + list[3] = code[1]; + return code + 2; + } + + /* Convert only if we have enough space. */ + + clist_src = PRIV(ucd_caseless_sets) + code[1]; + clist_dest = list + 2; + code += 2; + + do { + if (clist_dest >= list + 8) + { + /* Early return if there is not enough space. This should never + happen, since all clists are shorter than 5 character now. */ + list[2] = code[0]; + list[3] = code[1]; + return code; + } + *clist_dest++ = *clist_src; + } + while(*clist_src++ != NOTACHAR); + + /* All characters are stored. The terminating NOTACHAR + is copied form the clist itself. */ + + list[0] = (c == OP_PROP) ? OP_CHAR : OP_NOT; + return code; +#endif + + case OP_NCLASS: + case OP_CLASS: +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + case OP_XCLASS: + if (c == OP_XCLASS) + end = code + GET(code, 0) - 1; + else +#endif + end = code + 32 / sizeof(pcre_uchar); + + switch(*end) + { + case OP_CRSTAR: + case OP_CRMINSTAR: + case OP_CRQUERY: + case OP_CRMINQUERY: + case OP_CRPOSSTAR: + case OP_CRPOSQUERY: + list[1] = TRUE; + end++; + break; + + case OP_CRPLUS: + case OP_CRMINPLUS: + case OP_CRPOSPLUS: + end++; + break; + + case OP_CRRANGE: + case OP_CRMINRANGE: + case OP_CRPOSRANGE: + list[1] = (GET2(end, 1) == 0); + end += 1 + 2 * IMM2_SIZE; + break; + } + list[2] = end - code; + return end; + } +return NULL; /* Opcode not accepted */ +} + + + +/************************************************* +* Scan further character sets for match * +*************************************************/ + +/* Checks whether the base and the current opcode have a common character, in +which case the base cannot be possessified. + +Arguments: + code points to the byte code + utf TRUE in UTF-8 / UTF-16 / UTF-32 mode + cd static compile data + base_list the data list of the base opcode + +Returns: TRUE if the auto-possessification is possible +*/ + +static BOOL +compare_opcodes(const pcre_uchar *code, BOOL utf, const compile_data *cd, + const pcre_uint32 *base_list, const pcre_uchar *base_end) +{ +pcre_uchar c; +pcre_uint32 list[8]; +const pcre_uint32 *chr_ptr; +const pcre_uint32 *ochr_ptr; +const pcre_uint32 *list_ptr; +const pcre_uchar *next_code; +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 +const pcre_uchar *xclass_flags; +#endif +const pcre_uint8 *class_bitset; +const pcre_uint8 *set1, *set2, *set_end; +pcre_uint32 chr; +BOOL accepted, invert_bits; + +/* Note: the base_list[1] contains whether the current opcode has greedy +(represented by a non-zero value) quantifier. This is a different from +other character type lists, which stores here that the character iterator +matches to an empty string (also represented by a non-zero value). */ + +for(;;) + { + /* All operations move the code pointer forward. + Therefore infinite recursions are not possible. */ + + c = *code; + + /* Skip over callouts */ + + if (c == OP_CALLOUT) + { + code += PRIV(OP_lengths)[c]; + continue; + } + + if (c == OP_ALT) + { + do code += GET(code, 1); while (*code == OP_ALT); + c = *code; + } + + switch(c) + { + case OP_END: + case OP_KETRPOS: + /* TRUE only in greedy case. The non-greedy case could be replaced by + an OP_EXACT, but it is probably not worth it. (And note that OP_EXACT + uses more memory, which we cannot get at this stage.) */ + + return base_list[1] != 0; + + case OP_KET: + /* If the bracket is capturing, and referenced by an OP_RECURSE, or + it is an atomic sub-pattern (assert, once, etc.) the non-greedy case + cannot be converted to a possessive form. */ + + if (base_list[1] == 0) return FALSE; + + switch(*(code - GET(code, 1))) + { + case OP_ASSERT: + case OP_ASSERT_NOT: + case OP_ASSERTBACK: + case OP_ASSERTBACK_NOT: + case OP_ONCE: + case OP_ONCE_NC: + /* Atomic sub-patterns and assertions can always auto-possessify their + last iterator. */ + return TRUE; + } + + code += PRIV(OP_lengths)[c]; + continue; + + case OP_ONCE: + case OP_ONCE_NC: + case OP_BRA: + case OP_CBRA: + next_code = code + GET(code, 1); + code += PRIV(OP_lengths)[c]; + + while (*next_code == OP_ALT) + { + if (!compare_opcodes(code, utf, cd, base_list, base_end)) return FALSE; + code = next_code + 1 + LINK_SIZE; + next_code += GET(next_code, 1); + } + continue; + + case OP_BRAZERO: + case OP_BRAMINZERO: + + next_code = code + 1; + if (*next_code != OP_BRA && *next_code != OP_CBRA + && *next_code != OP_ONCE && *next_code != OP_ONCE_NC) return FALSE; + + do next_code += GET(next_code, 1); while (*next_code == OP_ALT); + + /* The bracket content will be checked by the + OP_BRA/OP_CBRA case above. */ + next_code += 1 + LINK_SIZE; + if (!compare_opcodes(next_code, utf, cd, base_list, base_end)) + return FALSE; + + code += PRIV(OP_lengths)[c]; + continue; + } + + /* Check for a supported opcode, and load its properties. */ + + code = get_chr_property_list(code, utf, cd->fcc, list); + if (code == NULL) return FALSE; /* Unsupported */ + + /* If either opcode is a small character list, set pointers for comparing + characters from that list with another list, or with a property. */ + + if (base_list[0] == OP_CHAR) + { + chr_ptr = base_list + 2; + list_ptr = list; + } + else if (list[0] == OP_CHAR) + { + chr_ptr = list + 2; + list_ptr = base_list; + } + + /* Character bitsets can also be compared to certain opcodes. */ + + else if (base_list[0] == OP_CLASS || list[0] == OP_CLASS +#ifdef COMPILE_PCRE8 + /* In 8 bit, non-UTF mode, OP_CLASS and OP_NCLASS are the same. */ + || (!utf && (base_list[0] == OP_NCLASS || list[0] == OP_NCLASS)) +#endif + ) + { +#ifdef COMPILE_PCRE8 + if (base_list[0] == OP_CLASS || (!utf && base_list[0] == OP_NCLASS)) +#else + if (base_list[0] == OP_CLASS) +#endif + { + set1 = (pcre_uint8 *)(base_end - base_list[2]); + list_ptr = list; + } + else + { + set1 = (pcre_uint8 *)(code - list[2]); + list_ptr = base_list; + } + + invert_bits = FALSE; + switch(list_ptr[0]) + { + case OP_CLASS: + case OP_NCLASS: + set2 = (pcre_uint8 *) + ((list_ptr == list ? code : base_end) - list_ptr[2]); + break; + +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + case OP_XCLASS: + xclass_flags = (list_ptr == list ? code : base_end) - list_ptr[2] + LINK_SIZE; + if ((*xclass_flags & XCL_HASPROP) != 0) return FALSE; + if ((*xclass_flags & XCL_MAP) == 0) + { + /* No bits are set for characters < 256. */ + if (list[1] == 0) return TRUE; + /* Might be an empty repeat. */ + continue; + } + set2 = (pcre_uint8 *)(xclass_flags + 1); + break; +#endif + + case OP_NOT_DIGIT: + invert_bits = TRUE; + /* Fall through */ + case OP_DIGIT: + set2 = (pcre_uint8 *)(cd->cbits + cbit_digit); + break; + + case OP_NOT_WHITESPACE: + invert_bits = TRUE; + /* Fall through */ + case OP_WHITESPACE: + set2 = (pcre_uint8 *)(cd->cbits + cbit_space); + break; + + case OP_NOT_WORDCHAR: + invert_bits = TRUE; + /* Fall through */ + case OP_WORDCHAR: + set2 = (pcre_uint8 *)(cd->cbits + cbit_word); + break; + + default: + return FALSE; + } + + /* Because the sets are unaligned, we need + to perform byte comparison here. */ + set_end = set1 + 32; + if (invert_bits) + { + do + { + if ((*set1++ & ~(*set2++)) != 0) return FALSE; + } + while (set1 < set_end); + } + else + { + do + { + if ((*set1++ & *set2++) != 0) return FALSE; + } + while (set1 < set_end); + } + + if (list[1] == 0) return TRUE; + /* Might be an empty repeat. */ + continue; + } + + /* Some property combinations also acceptable. Unicode property opcodes are + processed specially; the rest can be handled with a lookup table. */ + + else + { + pcre_uint32 leftop, rightop; + + leftop = base_list[0]; + rightop = list[0]; + +#ifdef SUPPORT_UCP + accepted = FALSE; /* Always set in non-unicode case. */ + if (leftop == OP_PROP || leftop == OP_NOTPROP) + { + if (rightop == OP_EOD) + accepted = TRUE; + else if (rightop == OP_PROP || rightop == OP_NOTPROP) + { + int n; + const pcre_uint8 *p; + BOOL same = leftop == rightop; + BOOL lisprop = leftop == OP_PROP; + BOOL risprop = rightop == OP_PROP; + BOOL bothprop = lisprop && risprop; + + /* There's a table that specifies how each combination is to be + processed: + 0 Always return FALSE (never auto-possessify) + 1 Character groups are distinct (possessify if both are OP_PROP) + 2 Check character categories in the same group (general or particular) + 3 Return TRUE if the two opcodes are not the same + ... see comments below + */ + + n = propposstab[base_list[2]][list[2]]; + switch(n) + { + case 0: break; + case 1: accepted = bothprop; break; + case 2: accepted = (base_list[3] == list[3]) != same; break; + case 3: accepted = !same; break; + + case 4: /* Left general category, right particular category */ + accepted = risprop && catposstab[base_list[3]][list[3]] == same; + break; + + case 5: /* Right general category, left particular category */ + accepted = lisprop && catposstab[list[3]][base_list[3]] == same; + break; + + /* This code is logically tricky. Think hard before fiddling with it. + The posspropstab table has four entries per row. Each row relates to + one of PCRE's special properties such as ALNUM or SPACE or WORD. + Only WORD actually needs all four entries, but using repeats for the + others means they can all use the same code below. + + The first two entries in each row are Unicode general categories, and + apply always, because all the characters they include are part of the + PCRE character set. The third and fourth entries are a general and a + particular category, respectively, that include one or more relevant + characters. One or the other is used, depending on whether the check + is for a general or a particular category. However, in both cases the + category contains more characters than the specials that are defined + for the property being tested against. Therefore, it cannot be used + in a NOTPROP case. + + Example: the row for WORD contains ucp_L, ucp_N, ucp_P, ucp_Po. + Underscore is covered by ucp_P or ucp_Po. */ + + case 6: /* Left alphanum vs right general category */ + case 7: /* Left space vs right general category */ + case 8: /* Left word vs right general category */ + p = posspropstab[n-6]; + accepted = risprop && lisprop == + (list[3] != p[0] && + list[3] != p[1] && + (list[3] != p[2] || !lisprop)); + break; + + case 9: /* Right alphanum vs left general category */ + case 10: /* Right space vs left general category */ + case 11: /* Right word vs left general category */ + p = posspropstab[n-9]; + accepted = lisprop && risprop == + (base_list[3] != p[0] && + base_list[3] != p[1] && + (base_list[3] != p[2] || !risprop)); + break; + + case 12: /* Left alphanum vs right particular category */ + case 13: /* Left space vs right particular category */ + case 14: /* Left word vs right particular category */ + p = posspropstab[n-12]; + accepted = risprop && lisprop == + (catposstab[p[0]][list[3]] && + catposstab[p[1]][list[3]] && + (list[3] != p[3] || !lisprop)); + break; + + case 15: /* Right alphanum vs left particular category */ + case 16: /* Right space vs left particular category */ + case 17: /* Right word vs left particular category */ + p = posspropstab[n-15]; + accepted = lisprop && risprop == + (catposstab[p[0]][base_list[3]] && + catposstab[p[1]][base_list[3]] && + (base_list[3] != p[3] || !risprop)); + break; + } + } + } + + else +#endif /* SUPPORT_UCP */ + + accepted = leftop >= FIRST_AUTOTAB_OP && leftop <= LAST_AUTOTAB_LEFT_OP && + rightop >= FIRST_AUTOTAB_OP && rightop <= LAST_AUTOTAB_RIGHT_OP && + autoposstab[leftop - FIRST_AUTOTAB_OP][rightop - FIRST_AUTOTAB_OP]; + + if (!accepted) + return FALSE; + + if (list[1] == 0) return TRUE; + /* Might be an empty repeat. */ + continue; + } + + /* Control reaches here only if one of the items is a small character list. + All characters are checked against the other side. */ + + do + { + chr = *chr_ptr; + + switch(list_ptr[0]) + { + case OP_CHAR: + ochr_ptr = list_ptr + 2; + do + { + if (chr == *ochr_ptr) return FALSE; + ochr_ptr++; + } + while(*ochr_ptr != NOTACHAR); + break; + + case OP_NOT: + ochr_ptr = list_ptr + 2; + do + { + if (chr == *ochr_ptr) + break; + ochr_ptr++; + } + while(*ochr_ptr != NOTACHAR); + if (*ochr_ptr == NOTACHAR) return FALSE; /* Not found */ + break; + + /* Note that OP_DIGIT etc. are generated only when PCRE_UCP is *not* + set. When it is set, \d etc. are converted into OP_(NOT_)PROP codes. */ + + case OP_DIGIT: + if (chr < 256 && (cd->ctypes[chr] & ctype_digit) != 0) return FALSE; + break; + + case OP_NOT_DIGIT: + if (chr > 255 || (cd->ctypes[chr] & ctype_digit) == 0) return FALSE; + break; + + case OP_WHITESPACE: + if (chr < 256 && (cd->ctypes[chr] & ctype_space) != 0) return FALSE; + break; + + case OP_NOT_WHITESPACE: + if (chr > 255 || (cd->ctypes[chr] & ctype_space) == 0) return FALSE; + break; + + case OP_WORDCHAR: + if (chr < 255 && (cd->ctypes[chr] & ctype_word) != 0) return FALSE; + break; + + case OP_NOT_WORDCHAR: + if (chr > 255 || (cd->ctypes[chr] & ctype_word) == 0) return FALSE; + break; + + case OP_HSPACE: + switch(chr) + { + HSPACE_CASES: return FALSE; + default: break; + } + break; + + case OP_NOT_HSPACE: + switch(chr) + { + HSPACE_CASES: break; + default: return FALSE; + } + break; + + case OP_ANYNL: + case OP_VSPACE: + switch(chr) + { + VSPACE_CASES: return FALSE; + default: break; + } + break; + + case OP_NOT_VSPACE: + switch(chr) + { + VSPACE_CASES: break; + default: return FALSE; + } + break; + + case OP_DOLL: + case OP_EODN: + switch (chr) + { + case CHAR_CR: + case CHAR_LF: + case CHAR_VT: + case CHAR_FF: + case CHAR_NEL: +#ifndef EBCDIC + case 0x2028: + case 0x2029: +#endif /* Not EBCDIC */ + return FALSE; + } + break; + + case OP_EOD: /* Can always possessify before \z */ + break; + +#ifdef SUPPORT_UCP + case OP_PROP: + case OP_NOTPROP: + if (!check_char_prop(chr, list_ptr[2], list_ptr[3], + list_ptr[0] == OP_NOTPROP)) + return FALSE; + break; +#endif + + case OP_NCLASS: + if (chr > 255) return FALSE; + /* Fall through */ + + case OP_CLASS: + if (chr > 255) break; + class_bitset = (pcre_uint8 *) + ((list_ptr == list ? code : base_end) - list_ptr[2]); + if ((class_bitset[chr >> 3] & (1 << (chr & 7))) != 0) return FALSE; + break; + +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + case OP_XCLASS: + if (PRIV(xclass)(chr, (list_ptr == list ? code : base_end) - + list_ptr[2] + LINK_SIZE, utf)) return FALSE; + break; +#endif + + default: + return FALSE; + } + + chr_ptr++; + } + while(*chr_ptr != NOTACHAR); + + /* At least one character must be matched from this opcode. */ + + if (list[1] == 0) return TRUE; + } + +/* Control never reaches here. There used to be a fail-save return FALSE; here, +but some compilers complain about an unreachable statement. */ + +} + + + +/************************************************* +* Scan compiled regex for auto-possession * +*************************************************/ + +/* Replaces single character iterations with their possessive alternatives +if appropriate. This function modifies the compiled opcode! + +Arguments: + code points to start of the byte code + utf TRUE in UTF-8 / UTF-16 / UTF-32 mode + cd static compile data + +Returns: nothing +*/ + +static void +auto_possessify(pcre_uchar *code, BOOL utf, const compile_data *cd) +{ +register pcre_uchar c; +const pcre_uchar *end; +pcre_uchar *repeat_opcode; +pcre_uint32 list[8]; + +for (;;) + { + c = *code; + + if (c >= OP_STAR && c <= OP_TYPEPOSUPTO) + { + c -= get_repeat_base(c) - OP_STAR; + end = (c <= OP_MINUPTO) ? + get_chr_property_list(code, utf, cd->fcc, list) : NULL; + list[1] = c == OP_STAR || c == OP_PLUS || c == OP_QUERY || c == OP_UPTO; + + if (end != NULL && compare_opcodes(end, utf, cd, list, end)) + { + switch(c) + { + case OP_STAR: + *code += OP_POSSTAR - OP_STAR; + break; + + case OP_MINSTAR: + *code += OP_POSSTAR - OP_MINSTAR; + break; + + case OP_PLUS: + *code += OP_POSPLUS - OP_PLUS; + break; + + case OP_MINPLUS: + *code += OP_POSPLUS - OP_MINPLUS; + break; + + case OP_QUERY: + *code += OP_POSQUERY - OP_QUERY; + break; + + case OP_MINQUERY: + *code += OP_POSQUERY - OP_MINQUERY; + break; + + case OP_UPTO: + *code += OP_POSUPTO - OP_UPTO; + break; + + case OP_MINUPTO: + *code += OP_POSUPTO - OP_MINUPTO; + break; + } + } + c = *code; + } + else if (c == OP_CLASS || c == OP_NCLASS || c == OP_XCLASS) + { +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + if (c == OP_XCLASS) + repeat_opcode = code + GET(code, 1); + else +#endif + repeat_opcode = code + 1 + (32 / sizeof(pcre_uchar)); + + c = *repeat_opcode; + if (c >= OP_CRSTAR && c <= OP_CRMINRANGE) + { + /* end must not be NULL. */ + end = get_chr_property_list(code, utf, cd->fcc, list); + + list[1] = (c & 1) == 0; + + if (compare_opcodes(end, utf, cd, list, end)) + { + switch (c) + { + case OP_CRSTAR: + case OP_CRMINSTAR: + *repeat_opcode = OP_CRPOSSTAR; + break; + + case OP_CRPLUS: + case OP_CRMINPLUS: + *repeat_opcode = OP_CRPOSPLUS; + break; + + case OP_CRQUERY: + case OP_CRMINQUERY: + *repeat_opcode = OP_CRPOSQUERY; + break; + + case OP_CRRANGE: + case OP_CRMINRANGE: + *repeat_opcode = OP_CRPOSRANGE; + break; + } + } + } + c = *code; + } + + switch(c) + { + case OP_END: + return; + + case OP_TYPESTAR: + case OP_TYPEMINSTAR: + case OP_TYPEPLUS: + case OP_TYPEMINPLUS: + case OP_TYPEQUERY: + case OP_TYPEMINQUERY: + case OP_TYPEPOSSTAR: + case OP_TYPEPOSPLUS: + case OP_TYPEPOSQUERY: + if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2; + break; + + case OP_TYPEUPTO: + case OP_TYPEMINUPTO: + case OP_TYPEEXACT: + case OP_TYPEPOSUPTO: + if (code[1 + IMM2_SIZE] == OP_PROP || code[1 + IMM2_SIZE] == OP_NOTPROP) + code += 2; + break; + +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + case OP_XCLASS: + code += GET(code, 1); + break; +#endif + + case OP_MARK: + case OP_PRUNE_ARG: + case OP_SKIP_ARG: + case OP_THEN_ARG: + code += code[1]; + break; + } + + /* Add in the fixed length from the table */ + + code += PRIV(OP_lengths)[c]; + + /* In UTF-8 mode, opcodes that are followed by a character may be followed by + a multi-byte character. The length in the table is a minimum, so we have to + arrange to skip the extra bytes. */ + +#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 + if (utf) switch(c) + { + case OP_CHAR: + case OP_CHARI: + case OP_NOT: + case OP_NOTI: + case OP_STAR: + case OP_MINSTAR: + case OP_PLUS: + case OP_MINPLUS: + case OP_QUERY: + case OP_MINQUERY: + case OP_UPTO: + case OP_MINUPTO: + case OP_EXACT: + case OP_POSSTAR: + case OP_POSPLUS: + case OP_POSQUERY: + case OP_POSUPTO: + case OP_STARI: + case OP_MINSTARI: + case OP_PLUSI: + case OP_MINPLUSI: + case OP_QUERYI: + case OP_MINQUERYI: + case OP_UPTOI: + case OP_MINUPTOI: + case OP_EXACTI: + case OP_POSSTARI: + case OP_POSPLUSI: + case OP_POSQUERYI: + case OP_POSUPTOI: + case OP_NOTSTAR: + case OP_NOTMINSTAR: + case OP_NOTPLUS: + case OP_NOTMINPLUS: + case OP_NOTQUERY: + case OP_NOTMINQUERY: + case OP_NOTUPTO: + case OP_NOTMINUPTO: + case OP_NOTEXACT: + case OP_NOTPOSSTAR: + case OP_NOTPOSPLUS: + case OP_NOTPOSQUERY: + case OP_NOTPOSUPTO: + case OP_NOTSTARI: + case OP_NOTMINSTARI: + case OP_NOTPLUSI: + case OP_NOTMINPLUSI: + case OP_NOTQUERYI: + case OP_NOTMINQUERYI: + case OP_NOTUPTOI: + case OP_NOTMINUPTOI: + case OP_NOTEXACTI: + case OP_NOTPOSSTARI: + case OP_NOTPOSPLUSI: + case OP_NOTPOSQUERYI: + case OP_NOTPOSUPTOI: + if (HAS_EXTRALEN(code[-1])) code += GET_EXTRALEN(code[-1]); + break; + } +#else + (void)(utf); /* Keep compiler happy by referencing function argument */ +#endif + } +} + + + +/************************************************* +* Check for POSIX class syntax * +*************************************************/ + +/* This function is called when the sequence "[:" or "[." or "[=" is +encountered in a character class. It checks whether this is followed by a +sequence of characters terminated by a matching ":]" or ".]" or "=]". If we +reach an unescaped ']' without the special preceding character, return FALSE. + +Originally, this function only recognized a sequence of letters between the +terminators, but it seems that Perl recognizes any sequence of characters, +though of course unknown POSIX names are subsequently rejected. Perl gives an +"Unknown POSIX class" error for [:f\oo:] for example, where previously PCRE +didn't consider this to be a POSIX class. Likewise for [:1234:]. + +The problem in trying to be exactly like Perl is in the handling of escapes. We +have to be sure that [abc[:x\]pqr] is *not* treated as containing a POSIX +class, but [abc[:x\]pqr:]] is (so that an error can be generated). The code +below handles the special case of \], but does not try to do any other escape +processing. This makes it different from Perl for cases such as [:l\ower:] +where Perl recognizes it as the POSIX class "lower" but PCRE does not recognize +"l\ower". This is a lesser evil than not diagnosing bad classes when Perl does, +I think. + +A user pointed out that PCRE was rejecting [:a[:digit:]] whereas Perl was not. +It seems that the appearance of a nested POSIX class supersedes an apparent +external class. For example, [:a[:digit:]b:] matches "a", "b", ":", or +a digit. + +In Perl, unescaped square brackets may also appear as part of class names. For +example, [:a[:abc]b:] gives unknown POSIX class "[:abc]b:]". However, for +[:a[:abc]b][b:] it gives unknown POSIX class "[:abc]b][b:]", which does not +seem right at all. PCRE does not allow closing square brackets in POSIX class +names. + +Arguments: + ptr pointer to the initial [ + endptr where to return the end pointer + +Returns: TRUE or FALSE +*/ + +static BOOL +check_posix_syntax(const pcre_uchar *ptr, const pcre_uchar **endptr) +{ +pcre_uchar terminator; /* Don't combine these lines; the Solaris cc */ +terminator = *(++ptr); /* compiler warns about "non-constant" initializer. */ +for (++ptr; *ptr != CHAR_NULL; ptr++) + { + if (*ptr == CHAR_BACKSLASH && ptr[1] == CHAR_RIGHT_SQUARE_BRACKET) + ptr++; + else if (*ptr == CHAR_RIGHT_SQUARE_BRACKET) return FALSE; + else + { + if (*ptr == terminator && ptr[1] == CHAR_RIGHT_SQUARE_BRACKET) + { + *endptr = ptr; + return TRUE; + } + if (*ptr == CHAR_LEFT_SQUARE_BRACKET && + (ptr[1] == CHAR_COLON || ptr[1] == CHAR_DOT || + ptr[1] == CHAR_EQUALS_SIGN) && + check_posix_syntax(ptr, endptr)) + return FALSE; + } + } +return FALSE; +} + + + + +/************************************************* +* Check POSIX class name * +*************************************************/ + +/* This function is called to check the name given in a POSIX-style class entry +such as [:alnum:]. + +Arguments: + ptr points to the first letter + len the length of the name + +Returns: a value representing the name, or -1 if unknown +*/ + +static int +check_posix_name(const pcre_uchar *ptr, int len) +{ +const char *pn = posix_names; +register int yield = 0; +while (posix_name_lengths[yield] != 0) + { + if (len == posix_name_lengths[yield] && + STRNCMP_UC_C8(ptr, pn, (unsigned int)len) == 0) return yield; + pn += posix_name_lengths[yield] + 1; + yield++; + } +return -1; +} + + +/************************************************* +* Adjust OP_RECURSE items in repeated group * +*************************************************/ + +/* OP_RECURSE items contain an offset from the start of the regex to the group +that is referenced. This means that groups can be replicated for fixed +repetition simply by copying (because the recursion is allowed to refer to +earlier groups that are outside the current group). However, when a group is +optional (i.e. the minimum quantifier is zero), OP_BRAZERO or OP_SKIPZERO is +inserted before it, after it has been compiled. This means that any OP_RECURSE +items within it that refer to the group itself or any contained groups have to +have their offsets adjusted. That one of the jobs of this function. Before it +is called, the partially compiled regex must be temporarily terminated with +OP_END. + +This function has been extended with the possibility of forward references for +recursions and subroutine calls. It must also check the list of such references +for the group we are dealing with. If it finds that one of the recursions in +the current group is on this list, it adjusts the offset in the list, not the +value in the reference (which is a group number). + +Arguments: + group points to the start of the group + adjust the amount by which the group is to be moved + utf TRUE in UTF-8 / UTF-16 / UTF-32 mode + cd contains pointers to tables etc. + save_hwm the hwm forward reference pointer at the start of the group + +Returns: nothing +*/ + +static void +adjust_recurse(pcre_uchar *group, int adjust, BOOL utf, compile_data *cd, + pcre_uchar *save_hwm) +{ +pcre_uchar *ptr = group; + +while ((ptr = (pcre_uchar *)find_recurse(ptr, utf)) != NULL) + { + int offset; + pcre_uchar *hc; + + /* See if this recursion is on the forward reference list. If so, adjust the + reference. */ + + for (hc = save_hwm; hc < cd->hwm; hc += LINK_SIZE) + { + offset = (int)GET(hc, 0); + if (cd->start_code + offset == ptr + 1) + { + PUT(hc, 0, offset + adjust); + break; + } + } + + /* Otherwise, adjust the recursion offset if it's after the start of this + group. */ + + if (hc >= cd->hwm) + { + offset = (int)GET(ptr, 1); + if (cd->start_code + offset >= group) PUT(ptr, 1, offset + adjust); + } + + ptr += 1 + LINK_SIZE; + } +} + + + +/************************************************* +* Insert an automatic callout point * +*************************************************/ + +/* This function is called when the PCRE_AUTO_CALLOUT option is set, to insert +callout points before each pattern item. + +Arguments: + code current code pointer + ptr current pattern pointer + cd pointers to tables etc + +Returns: new code pointer +*/ + +static pcre_uchar * +auto_callout(pcre_uchar *code, const pcre_uchar *ptr, compile_data *cd) +{ +*code++ = OP_CALLOUT; +*code++ = 255; +PUT(code, 0, (int)(ptr - cd->start_pattern)); /* Pattern offset */ +PUT(code, LINK_SIZE, 0); /* Default length */ +return code + 2 * LINK_SIZE; +} + + + +/************************************************* +* Complete a callout item * +*************************************************/ + +/* A callout item contains the length of the next item in the pattern, which +we can't fill in till after we have reached the relevant point. This is used +for both automatic and manual callouts. + +Arguments: + previous_callout points to previous callout item + ptr current pattern pointer + cd pointers to tables etc + +Returns: nothing +*/ + +static void +complete_callout(pcre_uchar *previous_callout, const pcre_uchar *ptr, compile_data *cd) +{ +int length = (int)(ptr - cd->start_pattern - GET(previous_callout, 2)); +PUT(previous_callout, 2 + LINK_SIZE, length); +} + + + +#ifdef SUPPORT_UCP +/************************************************* +* Get othercase range * +*************************************************/ + +/* This function is passed the start and end of a class range, in UTF-8 mode +with UCP support. It searches up the characters, looking for ranges of +characters in the "other" case. Each call returns the next one, updating the +start address. A character with multiple other cases is returned on its own +with a special return value. + +Arguments: + cptr points to starting character value; updated + d end value + ocptr where to put start of othercase range + odptr where to put end of othercase range + +Yield: -1 when no more + 0 when a range is returned + >0 the CASESET offset for char with multiple other cases + in this case, ocptr contains the original +*/ + +static int +get_othercase_range(pcre_uint32 *cptr, pcre_uint32 d, pcre_uint32 *ocptr, + pcre_uint32 *odptr) +{ +pcre_uint32 c, othercase, next; +unsigned int co; + +/* Find the first character that has an other case. If it has multiple other +cases, return its case offset value. */ + +for (c = *cptr; c <= d; c++) + { + if ((co = UCD_CASESET(c)) != 0) + { + *ocptr = c++; /* Character that has the set */ + *cptr = c; /* Rest of input range */ + return (int)co; + } + if ((othercase = UCD_OTHERCASE(c)) != c) break; + } + +if (c > d) return -1; /* Reached end of range */ + +/* Found a character that has a single other case. Search for the end of the +range, which is either the end of the input range, or a character that has zero +or more than one other cases. */ + +*ocptr = othercase; +next = othercase + 1; + +for (++c; c <= d; c++) + { + if ((co = UCD_CASESET(c)) != 0 || UCD_OTHERCASE(c) != next) break; + next++; + } + +*odptr = next - 1; /* End of othercase range */ +*cptr = c; /* Rest of input range */ +return 0; +} +#endif /* SUPPORT_UCP */ + + + +/************************************************* +* Add a character or range to a class * +*************************************************/ + +/* This function packages up the logic of adding a character or range of +characters to a class. The character values in the arguments will be within the +valid values for the current mode (8-bit, 16-bit, UTF, etc). This function is +mutually recursive with the function immediately below. + +Arguments: + classbits the bit map for characters < 256 + uchardptr points to the pointer for extra data + options the options word + cd contains pointers to tables etc. + start start of range character + end end of range character + +Returns: the number of < 256 characters added + the pointer to extra data is updated +*/ + +static int +add_to_class(pcre_uint8 *classbits, pcre_uchar **uchardptr, int options, + compile_data *cd, pcre_uint32 start, pcre_uint32 end) +{ +pcre_uint32 c; +pcre_uint32 classbits_end = (end <= 0xff ? end : 0xff); +int n8 = 0; + +/* If caseless matching is required, scan the range and process alternate +cases. In Unicode, there are 8-bit characters that have alternate cases that +are greater than 255 and vice-versa. Sometimes we can just extend the original +range. */ + +if ((options & PCRE_CASELESS) != 0) + { +#ifdef SUPPORT_UCP + if ((options & PCRE_UTF8) != 0) + { + int rc; + pcre_uint32 oc, od; + + options &= ~PCRE_CASELESS; /* Remove for recursive calls */ + c = start; + + while ((rc = get_othercase_range(&c, end, &oc, &od)) >= 0) + { + /* Handle a single character that has more than one other case. */ + + if (rc > 0) n8 += add_list_to_class(classbits, uchardptr, options, cd, + PRIV(ucd_caseless_sets) + rc, oc); + + /* Do nothing if the other case range is within the original range. */ + + else if (oc >= start && od <= end) continue; + + /* Extend the original range if there is overlap, noting that if oc < c, we + can't have od > end because a subrange is always shorter than the basic + range. Otherwise, use a recursive call to add the additional range. */ + + else if (oc < start && od >= start - 1) start = oc; /* Extend downwards */ + else if (od > end && oc <= end + 1) end = od; /* Extend upwards */ + else n8 += add_to_class(classbits, uchardptr, options, cd, oc, od); + } + } + else +#endif /* SUPPORT_UCP */ + + /* Not UTF-mode, or no UCP */ + + for (c = start; c <= classbits_end; c++) + { + SETBIT(classbits, cd->fcc[c]); + n8++; + } + } + +/* Now handle the original range. Adjust the final value according to the bit +length - this means that the same lists of (e.g.) horizontal spaces can be used +in all cases. */ + +#if defined COMPILE_PCRE8 +#ifdef SUPPORT_UTF + if ((options & PCRE_UTF8) == 0) +#endif + if (end > 0xff) end = 0xff; + +#elif defined COMPILE_PCRE16 +#ifdef SUPPORT_UTF + if ((options & PCRE_UTF16) == 0) +#endif + if (end > 0xffff) end = 0xffff; + +#endif /* COMPILE_PCRE[8|16] */ + +/* Use the bitmap for characters < 256. Otherwise use extra data.*/ + +for (c = start; c <= classbits_end; c++) + { + /* Regardless of start, c will always be <= 255. */ + SETBIT(classbits, c); + n8++; + } + +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 +if (start <= 0xff) start = 0xff + 1; + +if (end >= start) + { + pcre_uchar *uchardata = *uchardptr; +#ifdef SUPPORT_UTF + if ((options & PCRE_UTF8) != 0) /* All UTFs use the same flag bit */ + { + if (start < end) + { + *uchardata++ = XCL_RANGE; + uchardata += PRIV(ord2utf)(start, uchardata); + uchardata += PRIV(ord2utf)(end, uchardata); + } + else if (start == end) + { + *uchardata++ = XCL_SINGLE; + uchardata += PRIV(ord2utf)(start, uchardata); + } + } + else +#endif /* SUPPORT_UTF */ + + /* Without UTF support, character values are constrained by the bit length, + and can only be > 256 for 16-bit and 32-bit libraries. */ + +#ifdef COMPILE_PCRE8 + {} +#else + if (start < end) + { + *uchardata++ = XCL_RANGE; + *uchardata++ = start; + *uchardata++ = end; + } + else if (start == end) + { + *uchardata++ = XCL_SINGLE; + *uchardata++ = start; + } +#endif + + *uchardptr = uchardata; /* Updata extra data pointer */ + } +#endif /* SUPPORT_UTF || !COMPILE_PCRE8 */ + +return n8; /* Number of 8-bit characters */ +} + + + + +/************************************************* +* Add a list of characters to a class * +*************************************************/ + +/* This function is used for adding a list of case-equivalent characters to a +class, and also for adding a list of horizontal or vertical whitespace. If the +list is in order (which it should be), ranges of characters are detected and +handled appropriately. This function is mutually recursive with the function +above. + +Arguments: + classbits the bit map for characters < 256 + uchardptr points to the pointer for extra data + options the options word + cd contains pointers to tables etc. + p points to row of 32-bit values, terminated by NOTACHAR + except character to omit; this is used when adding lists of + case-equivalent characters to avoid including the one we + already know about + +Returns: the number of < 256 characters added + the pointer to extra data is updated +*/ + +static int +add_list_to_class(pcre_uint8 *classbits, pcre_uchar **uchardptr, int options, + compile_data *cd, const pcre_uint32 *p, unsigned int except) +{ +int n8 = 0; +while (p[0] < NOTACHAR) + { + int n = 0; + if (p[0] != except) + { + while(p[n+1] == p[0] + n + 1) n++; + n8 += add_to_class(classbits, uchardptr, options, cd, p[0], p[n]); + } + p += n + 1; + } +return n8; +} + + + +/************************************************* +* Add characters not in a list to a class * +*************************************************/ + +/* This function is used for adding the complement of a list of horizontal or +vertical whitespace to a class. The list must be in order. + +Arguments: + classbits the bit map for characters < 256 + uchardptr points to the pointer for extra data + options the options word + cd contains pointers to tables etc. + p points to row of 32-bit values, terminated by NOTACHAR + +Returns: the number of < 256 characters added + the pointer to extra data is updated +*/ + +static int +add_not_list_to_class(pcre_uint8 *classbits, pcre_uchar **uchardptr, + int options, compile_data *cd, const pcre_uint32 *p) +{ +BOOL utf = (options & PCRE_UTF8) != 0; +int n8 = 0; +if (p[0] > 0) + n8 += add_to_class(classbits, uchardptr, options, cd, 0, p[0] - 1); +while (p[0] < NOTACHAR) + { + while (p[1] == p[0] + 1) p++; + n8 += add_to_class(classbits, uchardptr, options, cd, p[0] + 1, + (p[1] == NOTACHAR) ? (utf ? 0x10ffffu : 0xffffffffu) : p[1] - 1); + p++; + } +return n8; +} + + + +/************************************************* +* Compile one branch * +*************************************************/ + +/* Scan the pattern, compiling it into the a vector. If the options are +changed during the branch, the pointer is used to change the external options +bits. This function is used during the pre-compile phase when we are trying +to find out the amount of memory needed, as well as during the real compile +phase. The value of lengthptr distinguishes the two phases. + +Arguments: + optionsptr pointer to the option bits + codeptr points to the pointer to the current code point + ptrptr points to the current pattern pointer + errorcodeptr points to error code variable + firstcharptr place to put the first required character + firstcharflagsptr place to put the first character flags, or a negative number + reqcharptr place to put the last required character + reqcharflagsptr place to put the last required character flags, or a negative number + bcptr points to current branch chain + cond_depth conditional nesting depth + cd contains pointers to tables etc. + lengthptr NULL during the real compile phase + points to length accumulator during pre-compile phase + +Returns: TRUE on success + FALSE, with *errorcodeptr set non-zero on error +*/ + +static BOOL +compile_branch(int *optionsptr, pcre_uchar **codeptr, + const pcre_uchar **ptrptr, int *errorcodeptr, + pcre_uint32 *firstcharptr, pcre_int32 *firstcharflagsptr, + pcre_uint32 *reqcharptr, pcre_int32 *reqcharflagsptr, + branch_chain *bcptr, int cond_depth, + compile_data *cd, int *lengthptr) +{ +int repeat_type, op_type; +int repeat_min = 0, repeat_max = 0; /* To please picky compilers */ +int bravalue = 0; +int greedy_default, greedy_non_default; +pcre_uint32 firstchar, reqchar; +pcre_int32 firstcharflags, reqcharflags; +pcre_uint32 zeroreqchar, zerofirstchar; +pcre_int32 zeroreqcharflags, zerofirstcharflags; +pcre_int32 req_caseopt, reqvary, tempreqvary; +int options = *optionsptr; /* May change dynamically */ +int after_manual_callout = 0; +int length_prevgroup = 0; +register pcre_uint32 c; +int escape; +register pcre_uchar *code = *codeptr; +pcre_uchar *last_code = code; +pcre_uchar *orig_code = code; +pcre_uchar *tempcode; +BOOL inescq = FALSE; +BOOL groupsetfirstchar = FALSE; +const pcre_uchar *ptr = *ptrptr; +const pcre_uchar *tempptr; +const pcre_uchar *nestptr = NULL; +pcre_uchar *previous = NULL; +pcre_uchar *previous_callout = NULL; +pcre_uchar *save_hwm = NULL; +pcre_uint8 classbits[32]; + +/* We can fish out the UTF-8 setting once and for all into a BOOL, but we +must not do this for other options (e.g. PCRE_EXTENDED) because they may change +dynamically as we process the pattern. */ + +#ifdef SUPPORT_UTF +/* PCRE_UTF[16|32] have the same value as PCRE_UTF8. */ +BOOL utf = (options & PCRE_UTF8) != 0; +#ifndef COMPILE_PCRE32 +pcre_uchar utf_chars[6]; +#endif +#else +BOOL utf = FALSE; +#endif + +/* Helper variables for OP_XCLASS opcode (for characters > 255). We define +class_uchardata always so that it can be passed to add_to_class() always, +though it will not be used in non-UTF 8-bit cases. This avoids having to supply +alternative calls for the different cases. */ + +pcre_uchar *class_uchardata; +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 +BOOL xclass; +pcre_uchar *class_uchardata_base; +#endif + +#ifdef PCRE_DEBUG +if (lengthptr != NULL) DPRINTF((">> start branch\n")); +#endif + +/* Set up the default and non-default settings for greediness */ + +greedy_default = ((options & PCRE_UNGREEDY) != 0); +greedy_non_default = greedy_default ^ 1; + +/* Initialize no first byte, no required byte. REQ_UNSET means "no char +matching encountered yet". It gets changed to REQ_NONE if we hit something that +matches a non-fixed char first char; reqchar just remains unset if we never +find one. + +When we hit a repeat whose minimum is zero, we may have to adjust these values +to take the zero repeat into account. This is implemented by setting them to +zerofirstbyte and zeroreqchar when such a repeat is encountered. The individual +item types that can be repeated set these backoff variables appropriately. */ + +firstchar = reqchar = zerofirstchar = zeroreqchar = 0; +firstcharflags = reqcharflags = zerofirstcharflags = zeroreqcharflags = REQ_UNSET; + +/* The variable req_caseopt contains either the REQ_CASELESS value +or zero, according to the current setting of the caseless flag. The +REQ_CASELESS leaves the lower 28 bit empty. It is added into the +firstchar or reqchar variables to record the case status of the +value. This is used only for ASCII characters. */ + +req_caseopt = ((options & PCRE_CASELESS) != 0)? REQ_CASELESS:0; + +/* Switch on next character until the end of the branch */ + +for (;; ptr++) + { + BOOL negate_class; + BOOL should_flip_negation; + BOOL possessive_quantifier; + BOOL is_quantifier; + BOOL is_recurse; + BOOL reset_bracount; + int class_has_8bitchar; + int class_one_char; +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + BOOL xclass_has_prop; +#endif + int newoptions; + int recno; + int refsign; + int skipbytes; + pcre_uint32 subreqchar, subfirstchar; + pcre_int32 subreqcharflags, subfirstcharflags; + int terminator; + unsigned int mclength; + unsigned int tempbracount; + pcre_uint32 ec; + pcre_uchar mcbuffer[8]; + + /* Get next character in the pattern */ + + c = *ptr; + + /* If we are at the end of a nested substitution, revert to the outer level + string. Nesting only happens one level deep. */ + + if (c == CHAR_NULL && nestptr != NULL) + { + ptr = nestptr; + nestptr = NULL; + c = *ptr; + } + + /* If we are in the pre-compile phase, accumulate the length used for the + previous cycle of this loop. */ + + if (lengthptr != NULL) + { +#ifdef PCRE_DEBUG + if (code > cd->hwm) cd->hwm = code; /* High water info */ +#endif + if (code > cd->start_workspace + cd->workspace_size - + WORK_SIZE_SAFETY_MARGIN) /* Check for overrun */ + { + *errorcodeptr = ERR52; + goto FAILED; + } + + /* There is at least one situation where code goes backwards: this is the + case of a zero quantifier after a class (e.g. [ab]{0}). At compile time, + the class is simply eliminated. However, it is created first, so we have to + allow memory for it. Therefore, don't ever reduce the length at this point. + */ + + if (code < last_code) code = last_code; + + /* Paranoid check for integer overflow */ + + if (OFLOW_MAX - *lengthptr < code - last_code) + { + *errorcodeptr = ERR20; + goto FAILED; + } + + *lengthptr += (int)(code - last_code); + DPRINTF(("length=%d added %d c=%c (0x%x)\n", *lengthptr, + (int)(code - last_code), c, c)); + + /* If "previous" is set and it is not at the start of the work space, move + it back to there, in order to avoid filling up the work space. Otherwise, + if "previous" is NULL, reset the current code pointer to the start. */ + + if (previous != NULL) + { + if (previous > orig_code) + { + memmove(orig_code, previous, IN_UCHARS(code - previous)); + code -= previous - orig_code; + previous = orig_code; + } + } + else code = orig_code; + + /* Remember where this code item starts so we can pick up the length + next time round. */ + + last_code = code; + } + + /* In the real compile phase, just check the workspace used by the forward + reference list. */ + + else if (cd->hwm > cd->start_workspace + cd->workspace_size - + WORK_SIZE_SAFETY_MARGIN) + { + *errorcodeptr = ERR52; + goto FAILED; + } + + /* If in \Q...\E, check for the end; if not, we have a literal */ + + if (inescq && c != CHAR_NULL) + { + if (c == CHAR_BACKSLASH && ptr[1] == CHAR_E) + { + inescq = FALSE; + ptr++; + continue; + } + else + { + if (previous_callout != NULL) + { + if (lengthptr == NULL) /* Don't attempt in pre-compile phase */ + complete_callout(previous_callout, ptr, cd); + previous_callout = NULL; + } + if ((options & PCRE_AUTO_CALLOUT) != 0) + { + previous_callout = code; + code = auto_callout(code, ptr, cd); + } + goto NORMAL_CHAR; + } + /* Control does not reach here. */ + } + + /* In extended mode, skip white space and comments. We need a loop in order + to check for more white space and more comments after a comment. */ + + if ((options & PCRE_EXTENDED) != 0) + { + for (;;) + { + while (MAX_255(c) && (cd->ctypes[c] & ctype_space) != 0) c = *(++ptr); + if (c != CHAR_NUMBER_SIGN) break; + ptr++; + while (*ptr != CHAR_NULL) + { + if (IS_NEWLINE(ptr)) /* For non-fixed-length newline cases, */ + { /* IS_NEWLINE sets cd->nllen. */ + ptr += cd->nllen; + break; + } + ptr++; +#ifdef SUPPORT_UTF + if (utf) FORWARDCHAR(ptr); +#endif + } + c = *ptr; /* Either NULL or the char after a newline */ + } + } + + /* See if the next thing is a quantifier. */ + + is_quantifier = + c == CHAR_ASTERISK || c == CHAR_PLUS || c == CHAR_QUESTION_MARK || + (c == CHAR_LEFT_CURLY_BRACKET && is_counted_repeat(ptr+1)); + + /* Fill in length of a previous callout, except when the next thing is a + quantifier or when processing a property substitution string in UCP mode. */ + + if (!is_quantifier && previous_callout != NULL && nestptr == NULL && + after_manual_callout-- <= 0) + { + if (lengthptr == NULL) /* Don't attempt in pre-compile phase */ + complete_callout(previous_callout, ptr, cd); + previous_callout = NULL; + } + + /* Create auto callout, except for quantifiers, or while processing property + strings that are substituted for \w etc in UCP mode. */ + + if ((options & PCRE_AUTO_CALLOUT) != 0 && !is_quantifier && nestptr == NULL) + { + previous_callout = code; + code = auto_callout(code, ptr, cd); + } + + /* Process the next pattern item. */ + + switch(c) + { + /* ===================================================================*/ + case CHAR_NULL: /* The branch terminates at string end */ + case CHAR_VERTICAL_LINE: /* or | or ) */ + case CHAR_RIGHT_PARENTHESIS: + *firstcharptr = firstchar; + *firstcharflagsptr = firstcharflags; + *reqcharptr = reqchar; + *reqcharflagsptr = reqcharflags; + *codeptr = code; + *ptrptr = ptr; + if (lengthptr != NULL) + { + if (OFLOW_MAX - *lengthptr < code - last_code) + { + *errorcodeptr = ERR20; + goto FAILED; + } + *lengthptr += (int)(code - last_code); /* To include callout length */ + DPRINTF((">> end branch\n")); + } + return TRUE; + + + /* ===================================================================*/ + /* Handle single-character metacharacters. In multiline mode, ^ disables + the setting of any following char as a first character. */ + + case CHAR_CIRCUMFLEX_ACCENT: + previous = NULL; + if ((options & PCRE_MULTILINE) != 0) + { + if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; + *code++ = OP_CIRCM; + } + else *code++ = OP_CIRC; + break; + + case CHAR_DOLLAR_SIGN: + previous = NULL; + *code++ = ((options & PCRE_MULTILINE) != 0)? OP_DOLLM : OP_DOLL; + break; + + /* There can never be a first char if '.' is first, whatever happens about + repeats. The value of reqchar doesn't change either. */ + + case CHAR_DOT: + if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; + zerofirstchar = firstchar; + zerofirstcharflags = firstcharflags; + zeroreqchar = reqchar; + zeroreqcharflags = reqcharflags; + previous = code; + *code++ = ((options & PCRE_DOTALL) != 0)? OP_ALLANY: OP_ANY; + break; + + + /* ===================================================================*/ + /* Character classes. If the included characters are all < 256, we build a + 32-byte bitmap of the permitted characters, except in the special case + where there is only one such character. For negated classes, we build the + map as usual, then invert it at the end. However, we use a different opcode + so that data characters > 255 can be handled correctly. + + If the class contains characters outside the 0-255 range, a different + opcode is compiled. It may optionally have a bit map for characters < 256, + but those above are are explicitly listed afterwards. A flag byte tells + whether the bitmap is present, and whether this is a negated class or not. + + In JavaScript compatibility mode, an isolated ']' causes an error. In + default (Perl) mode, it is treated as a data character. */ + + case CHAR_RIGHT_SQUARE_BRACKET: + if ((cd->external_options & PCRE_JAVASCRIPT_COMPAT) != 0) + { + *errorcodeptr = ERR64; + goto FAILED; + } + goto NORMAL_CHAR; + + /* In another (POSIX) regex library, the ugly syntax [[:<:]] and [[:>:]] is + used for "start of word" and "end of word". As these are otherwise illegal + sequences, we don't break anything by recognizing them. They are replaced + by \b(?=\w) and \b(?<=\w) respectively. Sequences like [a[:<:]] are + erroneous and are handled by the normal code below. */ + + case CHAR_LEFT_SQUARE_BRACKET: + if (STRNCMP_UC_C8(ptr+1, STRING_WEIRD_STARTWORD, 6) == 0) + { + nestptr = ptr + 7; + ptr = sub_start_of_word - 1; + continue; + } + + if (STRNCMP_UC_C8(ptr+1, STRING_WEIRD_ENDWORD, 6) == 0) + { + nestptr = ptr + 7; + ptr = sub_end_of_word - 1; + continue; + } + + /* Handle a real character class. */ + + previous = code; + + /* PCRE supports POSIX class stuff inside a class. Perl gives an error if + they are encountered at the top level, so we'll do that too. */ + + if ((ptr[1] == CHAR_COLON || ptr[1] == CHAR_DOT || + ptr[1] == CHAR_EQUALS_SIGN) && + check_posix_syntax(ptr, &tempptr)) + { + *errorcodeptr = (ptr[1] == CHAR_COLON)? ERR13 : ERR31; + goto FAILED; + } + + /* If the first character is '^', set the negation flag and skip it. Also, + if the first few characters (either before or after ^) are \Q\E or \E we + skip them too. This makes for compatibility with Perl. */ + + negate_class = FALSE; + for (;;) + { + c = *(++ptr); + if (c == CHAR_BACKSLASH) + { + if (ptr[1] == CHAR_E) + ptr++; + else if (STRNCMP_UC_C8(ptr + 1, STR_Q STR_BACKSLASH STR_E, 3) == 0) + ptr += 3; + else + break; + } + else if (!negate_class && c == CHAR_CIRCUMFLEX_ACCENT) + negate_class = TRUE; + else break; + } + + /* Empty classes are allowed in JavaScript compatibility mode. Otherwise, + an initial ']' is taken as a data character -- the code below handles + that. In JS mode, [] must always fail, so generate OP_FAIL, whereas + [^] must match any character, so generate OP_ALLANY. */ + + if (c == CHAR_RIGHT_SQUARE_BRACKET && + (cd->external_options & PCRE_JAVASCRIPT_COMPAT) != 0) + { + *code++ = negate_class? OP_ALLANY : OP_FAIL; + if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; + zerofirstchar = firstchar; + zerofirstcharflags = firstcharflags; + break; + } + + /* If a class contains a negative special such as \S, we need to flip the + negation flag at the end, so that support for characters > 255 works + correctly (they are all included in the class). */ + + should_flip_negation = FALSE; + + /* Extended class (xclass) will be used when characters > 255 + might match. */ + +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + xclass = FALSE; + class_uchardata = code + LINK_SIZE + 2; /* For XCLASS items */ + class_uchardata_base = class_uchardata; /* Save the start */ +#endif + + /* For optimization purposes, we track some properties of the class: + class_has_8bitchar will be non-zero if the class contains at least one < + 256 character; class_one_char will be 1 if the class contains just one + character; xclass_has_prop will be TRUE if unicode property checks + are present in the class. */ + + class_has_8bitchar = 0; + class_one_char = 0; +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + xclass_has_prop = FALSE; +#endif + + /* Initialize the 32-char bit map to all zeros. We build the map in a + temporary bit of memory, in case the class contains fewer than two + 8-bit characters because in that case the compiled code doesn't use the bit + map. */ + + memset(classbits, 0, 32 * sizeof(pcre_uint8)); + + /* Process characters until ] is reached. By writing this as a "do" it + means that an initial ] is taken as a data character. At the start of the + loop, c contains the first byte of the character. */ + + if (c != CHAR_NULL) do + { + const pcre_uchar *oldptr; + +#ifdef SUPPORT_UTF + if (utf && HAS_EXTRALEN(c)) + { /* Braces are required because the */ + GETCHARLEN(c, ptr, ptr); /* macro generates multiple statements */ + } +#endif + +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + /* In the pre-compile phase, accumulate the length of any extra + data and reset the pointer. This is so that very large classes that + contain a zillion > 255 characters no longer overwrite the work space + (which is on the stack). We have to remember that there was XCLASS data, + however. */ + + if (lengthptr != NULL && class_uchardata > class_uchardata_base) + { + xclass = TRUE; + *lengthptr += class_uchardata - class_uchardata_base; + class_uchardata = class_uchardata_base; + } +#endif + + /* Inside \Q...\E everything is literal except \E */ + + if (inescq) + { + if (c == CHAR_BACKSLASH && ptr[1] == CHAR_E) /* If we are at \E */ + { + inescq = FALSE; /* Reset literal state */ + ptr++; /* Skip the 'E' */ + continue; /* Carry on with next */ + } + goto CHECK_RANGE; /* Could be range if \E follows */ + } + + /* Handle POSIX class names. Perl allows a negation extension of the + form [:^name:]. A square bracket that doesn't match the syntax is + treated as a literal. We also recognize the POSIX constructions + [.ch.] and [=ch=] ("collating elements") and fault them, as Perl + 5.6 and 5.8 do. */ + + if (c == CHAR_LEFT_SQUARE_BRACKET && + (ptr[1] == CHAR_COLON || ptr[1] == CHAR_DOT || + ptr[1] == CHAR_EQUALS_SIGN) && check_posix_syntax(ptr, &tempptr)) + { + BOOL local_negate = FALSE; + int posix_class, taboffset, tabopt; + register const pcre_uint8 *cbits = cd->cbits; + pcre_uint8 pbits[32]; + + if (ptr[1] != CHAR_COLON) + { + *errorcodeptr = ERR31; + goto FAILED; + } + + ptr += 2; + if (*ptr == CHAR_CIRCUMFLEX_ACCENT) + { + local_negate = TRUE; + should_flip_negation = TRUE; /* Note negative special */ + ptr++; + } + + posix_class = check_posix_name(ptr, (int)(tempptr - ptr)); + if (posix_class < 0) + { + *errorcodeptr = ERR30; + goto FAILED; + } + + /* If matching is caseless, upper and lower are converted to + alpha. This relies on the fact that the class table starts with + alpha, lower, upper as the first 3 entries. */ + + if ((options & PCRE_CASELESS) != 0 && posix_class <= 2) + posix_class = 0; + + /* When PCRE_UCP is set, some of the POSIX classes are converted to + different escape sequences that use Unicode properties \p or \P. Others + that are not available via \p or \P generate XCL_PROP/XCL_NOTPROP + directly. */ + +#ifdef SUPPORT_UCP + if ((options & PCRE_UCP) != 0) + { + unsigned int ptype = 0; + int pc = posix_class + ((local_negate)? POSIX_SUBSIZE/2 : 0); + + /* The posix_substitutes table specifies which POSIX classes can be + converted to \p or \P items. */ + + if (posix_substitutes[pc] != NULL) + { + nestptr = tempptr + 1; + ptr = posix_substitutes[pc] - 1; + continue; + } + + /* There are three other classes that generate special property calls + that are recognized only in an XCLASS. */ + + else switch(posix_class) + { + case PC_GRAPH: + ptype = PT_PXGRAPH; + /* Fall through */ + case PC_PRINT: + if (ptype == 0) ptype = PT_PXPRINT; + /* Fall through */ + case PC_PUNCT: + if (ptype == 0) ptype = PT_PXPUNCT; + *class_uchardata++ = local_negate? XCL_NOTPROP : XCL_PROP; + *class_uchardata++ = ptype; + *class_uchardata++ = 0; + xclass_has_prop = TRUE; + ptr = tempptr + 1; + continue; + + /* For all other POSIX classes, no special action is taken in UCP + mode. Fall through to the non_UCP case. */ + + default: + break; + } + } +#endif + /* In the non-UCP case, or when UCP makes no difference, we build the + bit map for the POSIX class in a chunk of local store because we may be + adding and subtracting from it, and we don't want to subtract bits that + may be in the main map already. At the end we or the result into the + bit map that is being built. */ + + posix_class *= 3; + + /* Copy in the first table (always present) */ + + memcpy(pbits, cbits + posix_class_maps[posix_class], + 32 * sizeof(pcre_uint8)); + + /* If there is a second table, add or remove it as required. */ + + taboffset = posix_class_maps[posix_class + 1]; + tabopt = posix_class_maps[posix_class + 2]; + + if (taboffset >= 0) + { + if (tabopt >= 0) + for (c = 0; c < 32; c++) pbits[c] |= cbits[c + taboffset]; + else + for (c = 0; c < 32; c++) pbits[c] &= ~cbits[c + taboffset]; + } + + /* Now see if we need to remove any special characters. An option + value of 1 removes vertical space and 2 removes underscore. */ + + if (tabopt < 0) tabopt = -tabopt; + if (tabopt == 1) pbits[1] &= ~0x3c; + else if (tabopt == 2) pbits[11] &= 0x7f; + + /* Add the POSIX table or its complement into the main table that is + being built and we are done. */ + + if (local_negate) + for (c = 0; c < 32; c++) classbits[c] |= ~pbits[c]; + else + for (c = 0; c < 32; c++) classbits[c] |= pbits[c]; + + ptr = tempptr + 1; + /* Every class contains at least one < 256 character. */ + class_has_8bitchar = 1; + /* Every class contains at least two characters. */ + class_one_char = 2; + continue; /* End of POSIX syntax handling */ + } + + /* Backslash may introduce a single character, or it may introduce one + of the specials, which just set a flag. The sequence \b is a special + case. Inside a class (and only there) it is treated as backspace. We + assume that other escapes have more than one character in them, so + speculatively set both class_has_8bitchar and class_one_char bigger + than one. Unrecognized escapes fall through and are either treated + as literal characters (by default), or are faulted if + PCRE_EXTRA is set. */ + + if (c == CHAR_BACKSLASH) + { + escape = check_escape(&ptr, &ec, errorcodeptr, cd->bracount, options, + TRUE); + if (*errorcodeptr != 0) goto FAILED; + if (escape == 0) c = ec; + else if (escape == ESC_b) c = CHAR_BS; /* \b is backspace in a class */ + else if (escape == ESC_N) /* \N is not supported in a class */ + { + *errorcodeptr = ERR71; + goto FAILED; + } + else if (escape == ESC_Q) /* Handle start of quoted string */ + { + if (ptr[1] == CHAR_BACKSLASH && ptr[2] == CHAR_E) + { + ptr += 2; /* avoid empty string */ + } + else inescq = TRUE; + continue; + } + else if (escape == ESC_E) continue; /* Ignore orphan \E */ + + else + { + register const pcre_uint8 *cbits = cd->cbits; + /* Every class contains at least two < 256 characters. */ + class_has_8bitchar++; + /* Every class contains at least two characters. */ + class_one_char += 2; + + switch (escape) + { +#ifdef SUPPORT_UCP + case ESC_du: /* These are the values given for \d etc */ + case ESC_DU: /* when PCRE_UCP is set. We replace the */ + case ESC_wu: /* escape sequence with an appropriate \p */ + case ESC_WU: /* or \P to test Unicode properties instead */ + case ESC_su: /* of the default ASCII testing. */ + case ESC_SU: + nestptr = ptr; + ptr = substitutes[escape - ESC_DU] - 1; /* Just before substitute */ + class_has_8bitchar--; /* Undo! */ + continue; +#endif + case ESC_d: + for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_digit]; + continue; + + case ESC_D: + should_flip_negation = TRUE; + for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_digit]; + continue; + + case ESC_w: + for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_word]; + continue; + + case ESC_W: + should_flip_negation = TRUE; + for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_word]; + continue; + + /* Perl 5.004 onwards omitted VT from \s, but restored it at Perl + 5.18. Before PCRE 8.34, we had to preserve the VT bit if it was + previously set by something earlier in the character class. + Luckily, the value of CHAR_VT is 0x0b in both ASCII and EBCDIC, so + we could just adjust the appropriate bit. From PCRE 8.34 we no + longer treat \s and \S specially. */ + + case ESC_s: + for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_space]; + continue; + + case ESC_S: + should_flip_negation = TRUE; + for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_space]; + continue; + + /* The rest apply in both UCP and non-UCP cases. */ + + case ESC_h: + (void)add_list_to_class(classbits, &class_uchardata, options, cd, + PRIV(hspace_list), NOTACHAR); + continue; + + case ESC_H: + (void)add_not_list_to_class(classbits, &class_uchardata, options, + cd, PRIV(hspace_list)); + continue; + + case ESC_v: + (void)add_list_to_class(classbits, &class_uchardata, options, cd, + PRIV(vspace_list), NOTACHAR); + continue; + + case ESC_V: + (void)add_not_list_to_class(classbits, &class_uchardata, options, + cd, PRIV(vspace_list)); + continue; + +#ifdef SUPPORT_UCP + case ESC_p: + case ESC_P: + { + BOOL negated; + unsigned int ptype = 0, pdata = 0; + if (!get_ucp(&ptr, &negated, &ptype, &pdata, errorcodeptr)) + goto FAILED; + *class_uchardata++ = ((escape == ESC_p) != negated)? + XCL_PROP : XCL_NOTPROP; + *class_uchardata++ = ptype; + *class_uchardata++ = pdata; + xclass_has_prop = TRUE; + class_has_8bitchar--; /* Undo! */ + continue; + } +#endif + /* Unrecognized escapes are faulted if PCRE is running in its + strict mode. By default, for compatibility with Perl, they are + treated as literals. */ + + default: + if ((options & PCRE_EXTRA) != 0) + { + *errorcodeptr = ERR7; + goto FAILED; + } + class_has_8bitchar--; /* Undo the speculative increase. */ + class_one_char -= 2; /* Undo the speculative increase. */ + c = *ptr; /* Get the final character and fall through */ + break; + } + } + + /* Fall through if the escape just defined a single character (c >= 0). + This may be greater than 256. */ + + escape = 0; + + } /* End of backslash handling */ + + /* A character may be followed by '-' to form a range. However, Perl does + not permit ']' to be the end of the range. A '-' character at the end is + treated as a literal. Perl ignores orphaned \E sequences entirely. The + code for handling \Q and \E is messy. */ + + CHECK_RANGE: + while (ptr[1] == CHAR_BACKSLASH && ptr[2] == CHAR_E) + { + inescq = FALSE; + ptr += 2; + } + oldptr = ptr; + + /* Remember if \r or \n were explicitly used */ + + if (c == CHAR_CR || c == CHAR_NL) cd->external_flags |= PCRE_HASCRORLF; + + /* Check for range */ + + if (!inescq && ptr[1] == CHAR_MINUS) + { + pcre_uint32 d; + ptr += 2; + while (*ptr == CHAR_BACKSLASH && ptr[1] == CHAR_E) ptr += 2; + + /* If we hit \Q (not followed by \E) at this point, go into escaped + mode. */ + + while (*ptr == CHAR_BACKSLASH && ptr[1] == CHAR_Q) + { + ptr += 2; + if (*ptr == CHAR_BACKSLASH && ptr[1] == CHAR_E) + { ptr += 2; continue; } + inescq = TRUE; + break; + } + + /* Minus (hyphen) at the end of a class is treated as a literal, so put + back the pointer and jump to handle the character that preceded it. */ + + if (*ptr == CHAR_NULL || (!inescq && *ptr == CHAR_RIGHT_SQUARE_BRACKET)) + { + ptr = oldptr; + goto CLASS_SINGLE_CHARACTER; + } + + /* Otherwise, we have a potential range; pick up the next character */ + +#ifdef SUPPORT_UTF + if (utf) + { /* Braces are required because the */ + GETCHARLEN(d, ptr, ptr); /* macro generates multiple statements */ + } + else +#endif + d = *ptr; /* Not UTF-8 mode */ + + /* The second part of a range can be a single-character escape + sequence, but not any of the other escapes. Perl treats a hyphen as a + literal in such circumstances. However, in Perl's warning mode, a + warning is given, so PCRE now faults it as it is almost certainly a + mistake on the user's part. */ + + if (!inescq) + { + if (d == CHAR_BACKSLASH) + { + int descape; + descape = check_escape(&ptr, &d, errorcodeptr, cd->bracount, options, TRUE); + if (*errorcodeptr != 0) goto FAILED; + + /* 0 means a character was put into d; \b is backspace; any other + special causes an error. */ + + if (descape != 0) + { + if (descape == ESC_b) d = CHAR_BS; else + { + *errorcodeptr = ERR83; + goto FAILED; + } + } + } + + /* A hyphen followed by a POSIX class is treated in the same way. */ + + else if (d == CHAR_LEFT_SQUARE_BRACKET && + (ptr[1] == CHAR_COLON || ptr[1] == CHAR_DOT || + ptr[1] == CHAR_EQUALS_SIGN) && + check_posix_syntax(ptr, &tempptr)) + { + *errorcodeptr = ERR83; + goto FAILED; + } + } + + /* Check that the two values are in the correct order. Optimize + one-character ranges. */ + + if (d < c) + { + *errorcodeptr = ERR8; + goto FAILED; + } + if (d == c) goto CLASS_SINGLE_CHARACTER; /* A few lines below */ + + /* We have found a character range, so single character optimizations + cannot be done anymore. Any value greater than 1 indicates that there + is more than one character. */ + + class_one_char = 2; + + /* Remember an explicit \r or \n, and add the range to the class. */ + + if (d == CHAR_CR || d == CHAR_NL) cd->external_flags |= PCRE_HASCRORLF; + + class_has_8bitchar += + add_to_class(classbits, &class_uchardata, options, cd, c, d); + + continue; /* Go get the next char in the class */ + } + + /* Handle a single character - we can get here for a normal non-escape + char, or after \ that introduces a single character or for an apparent + range that isn't. Only the value 1 matters for class_one_char, so don't + increase it if it is already 2 or more ... just in case there's a class + with a zillion characters in it. */ + + CLASS_SINGLE_CHARACTER: + if (class_one_char < 2) class_one_char++; + + /* If class_one_char is 1, we have the first single character in the + class, and there have been no prior ranges, or XCLASS items generated by + escapes. If this is the final character in the class, we can optimize by + turning the item into a 1-character OP_CHAR[I] if it's positive, or + OP_NOT[I] if it's negative. In the positive case, it can cause firstchar + to be set. Otherwise, there can be no first char if this item is first, + whatever repeat count may follow. In the case of reqchar, save the + previous value for reinstating. */ + + if (class_one_char == 1 && ptr[1] == CHAR_RIGHT_SQUARE_BRACKET) + { + ptr++; + zeroreqchar = reqchar; + zeroreqcharflags = reqcharflags; + + if (negate_class) + { +#ifdef SUPPORT_UCP + int d; +#endif + if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; + zerofirstchar = firstchar; + zerofirstcharflags = firstcharflags; + + /* For caseless UTF-8 mode when UCP support is available, check + whether this character has more than one other case. If so, generate + a special OP_NOTPROP item instead of OP_NOTI. */ + +#ifdef SUPPORT_UCP + if (utf && (options & PCRE_CASELESS) != 0 && + (d = UCD_CASESET(c)) != 0) + { + *code++ = OP_NOTPROP; + *code++ = PT_CLIST; + *code++ = d; + } + else +#endif + /* Char has only one other case, or UCP not available */ + + { + *code++ = ((options & PCRE_CASELESS) != 0)? OP_NOTI: OP_NOT; +#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 + if (utf && c > MAX_VALUE_FOR_SINGLE_CHAR) + code += PRIV(ord2utf)(c, code); + else +#endif + *code++ = c; + } + + /* We are finished with this character class */ + + goto END_CLASS; + } + + /* For a single, positive character, get the value into mcbuffer, and + then we can handle this with the normal one-character code. */ + +#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 + if (utf && c > MAX_VALUE_FOR_SINGLE_CHAR) + mclength = PRIV(ord2utf)(c, mcbuffer); + else +#endif + { + mcbuffer[0] = c; + mclength = 1; + } + goto ONE_CHAR; + } /* End of 1-char optimization */ + + /* There is more than one character in the class, or an XCLASS item + has been generated. Add this character to the class. */ + + class_has_8bitchar += + add_to_class(classbits, &class_uchardata, options, cd, c, c); + } + + /* Loop until ']' reached. This "while" is the end of the "do" far above. + If we are at the end of an internal nested string, revert to the outer + string. */ + + while (((c = *(++ptr)) != CHAR_NULL || + (nestptr != NULL && + (ptr = nestptr, nestptr = NULL, c = *(++ptr)) != CHAR_NULL)) && + (c != CHAR_RIGHT_SQUARE_BRACKET || inescq)); + + /* Check for missing terminating ']' */ + + if (c == CHAR_NULL) + { + *errorcodeptr = ERR6; + goto FAILED; + } + + /* We will need an XCLASS if data has been placed in class_uchardata. In + the second phase this is a sufficient test. However, in the pre-compile + phase, class_uchardata gets emptied to prevent workspace overflow, so it + only if the very last character in the class needs XCLASS will it contain + anything at this point. For this reason, xclass gets set TRUE above when + uchar_classdata is emptied, and that's why this code is the way it is here + instead of just doing a test on class_uchardata below. */ + +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + if (class_uchardata > class_uchardata_base) xclass = TRUE; +#endif + + /* If this is the first thing in the branch, there can be no first char + setting, whatever the repeat count. Any reqchar setting must remain + unchanged after any kind of repeat. */ + + if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; + zerofirstchar = firstchar; + zerofirstcharflags = firstcharflags; + zeroreqchar = reqchar; + zeroreqcharflags = reqcharflags; + + /* If there are characters with values > 255, we have to compile an + extended class, with its own opcode, unless there was a negated special + such as \S in the class, and PCRE_UCP is not set, because in that case all + characters > 255 are in the class, so any that were explicitly given as + well can be ignored. If (when there are explicit characters > 255 that must + be listed) there are no characters < 256, we can omit the bitmap in the + actual compiled code. */ + +#ifdef SUPPORT_UTF + if (xclass && (!should_flip_negation || (options & PCRE_UCP) != 0)) +#elif !defined COMPILE_PCRE8 + if (xclass && !should_flip_negation) +#endif +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + { + *class_uchardata++ = XCL_END; /* Marks the end of extra data */ + *code++ = OP_XCLASS; + code += LINK_SIZE; + *code = negate_class? XCL_NOT:0; + if (xclass_has_prop) *code |= XCL_HASPROP; + + /* If the map is required, move up the extra data to make room for it; + otherwise just move the code pointer to the end of the extra data. */ + + if (class_has_8bitchar > 0) + { + *code++ |= XCL_MAP; + memmove(code + (32 / sizeof(pcre_uchar)), code, + IN_UCHARS(class_uchardata - code)); + if (negate_class && !xclass_has_prop) + for (c = 0; c < 32; c++) classbits[c] = ~classbits[c]; + memcpy(code, classbits, 32); + code = class_uchardata + (32 / sizeof(pcre_uchar)); + } + else code = class_uchardata; + + /* Now fill in the complete length of the item */ + + PUT(previous, 1, (int)(code - previous)); + break; /* End of class handling */ + } +#endif + + /* If there are no characters > 255, or they are all to be included or + excluded, set the opcode to OP_CLASS or OP_NCLASS, depending on whether the + whole class was negated and whether there were negative specials such as \S + (non-UCP) in the class. Then copy the 32-byte map into the code vector, + negating it if necessary. */ + + *code++ = (negate_class == should_flip_negation) ? OP_CLASS : OP_NCLASS; + if (lengthptr == NULL) /* Save time in the pre-compile phase */ + { + if (negate_class) + for (c = 0; c < 32; c++) classbits[c] = ~classbits[c]; + memcpy(code, classbits, 32); + } + code += 32 / sizeof(pcre_uchar); + + END_CLASS: + break; + + + /* ===================================================================*/ + /* Various kinds of repeat; '{' is not necessarily a quantifier, but this + has been tested above. */ + + case CHAR_LEFT_CURLY_BRACKET: + if (!is_quantifier) goto NORMAL_CHAR; + ptr = read_repeat_counts(ptr+1, &repeat_min, &repeat_max, errorcodeptr); + if (*errorcodeptr != 0) goto FAILED; + goto REPEAT; + + case CHAR_ASTERISK: + repeat_min = 0; + repeat_max = -1; + goto REPEAT; + + case CHAR_PLUS: + repeat_min = 1; + repeat_max = -1; + goto REPEAT; + + case CHAR_QUESTION_MARK: + repeat_min = 0; + repeat_max = 1; + + REPEAT: + if (previous == NULL) + { + *errorcodeptr = ERR9; + goto FAILED; + } + + if (repeat_min == 0) + { + firstchar = zerofirstchar; /* Adjust for zero repeat */ + firstcharflags = zerofirstcharflags; + reqchar = zeroreqchar; /* Ditto */ + reqcharflags = zeroreqcharflags; + } + + /* Remember whether this is a variable length repeat */ + + reqvary = (repeat_min == repeat_max)? 0 : REQ_VARY; + + op_type = 0; /* Default single-char op codes */ + possessive_quantifier = FALSE; /* Default not possessive quantifier */ + + /* Save start of previous item, in case we have to move it up in order to + insert something before it. */ + + tempcode = previous; + + /* Before checking for a possessive quantifier, we must skip over + whitespace and comments in extended mode because Perl allows white space at + this point. */ + + if ((options & PCRE_EXTENDED) != 0) + { + const pcre_uchar *p = ptr + 1; + for (;;) + { + while (MAX_255(*p) && (cd->ctypes[*p] & ctype_space) != 0) p++; + if (*p != CHAR_NUMBER_SIGN) break; + p++; + while (*p != CHAR_NULL) + { + if (IS_NEWLINE(p)) /* For non-fixed-length newline cases, */ + { /* IS_NEWLINE sets cd->nllen. */ + p += cd->nllen; + break; + } + p++; +#ifdef SUPPORT_UTF + if (utf) FORWARDCHAR(p); +#endif + } /* Loop for comment characters */ + } /* Loop for multiple comments */ + ptr = p - 1; /* Character before the next significant one. */ + } + + /* If the next character is '+', we have a possessive quantifier. This + implies greediness, whatever the setting of the PCRE_UNGREEDY option. + If the next character is '?' this is a minimizing repeat, by default, + but if PCRE_UNGREEDY is set, it works the other way round. We change the + repeat type to the non-default. */ + + if (ptr[1] == CHAR_PLUS) + { + repeat_type = 0; /* Force greedy */ + possessive_quantifier = TRUE; + ptr++; + } + else if (ptr[1] == CHAR_QUESTION_MARK) + { + repeat_type = greedy_non_default; + ptr++; + } + else repeat_type = greedy_default; + + /* If previous was a recursion call, wrap it in atomic brackets so that + previous becomes the atomic group. All recursions were so wrapped in the + past, but it no longer happens for non-repeated recursions. In fact, the + repeated ones could be re-implemented independently so as not to need this, + but for the moment we rely on the code for repeating groups. */ + + if (*previous == OP_RECURSE) + { + memmove(previous + 1 + LINK_SIZE, previous, IN_UCHARS(1 + LINK_SIZE)); + *previous = OP_ONCE; + PUT(previous, 1, 2 + 2*LINK_SIZE); + previous[2 + 2*LINK_SIZE] = OP_KET; + PUT(previous, 3 + 2*LINK_SIZE, 2 + 2*LINK_SIZE); + code += 2 + 2 * LINK_SIZE; + length_prevgroup = 3 + 3*LINK_SIZE; + + /* When actually compiling, we need to check whether this was a forward + reference, and if so, adjust the offset. */ + + if (lengthptr == NULL && cd->hwm >= cd->start_workspace + LINK_SIZE) + { + int offset = GET(cd->hwm, -LINK_SIZE); + if (offset == previous + 1 - cd->start_code) + PUT(cd->hwm, -LINK_SIZE, offset + 1 + LINK_SIZE); + } + } + + /* Now handle repetition for the different types of item. */ + + /* If previous was a character or negated character match, abolish the item + and generate a repeat item instead. If a char item has a minimum of more + than one, ensure that it is set in reqchar - it might not be if a sequence + such as x{3} is the first thing in a branch because the x will have gone + into firstchar instead. */ + + if (*previous == OP_CHAR || *previous == OP_CHARI + || *previous == OP_NOT || *previous == OP_NOTI) + { + switch (*previous) + { + default: /* Make compiler happy. */ + case OP_CHAR: op_type = OP_STAR - OP_STAR; break; + case OP_CHARI: op_type = OP_STARI - OP_STAR; break; + case OP_NOT: op_type = OP_NOTSTAR - OP_STAR; break; + case OP_NOTI: op_type = OP_NOTSTARI - OP_STAR; break; + } + + /* Deal with UTF characters that take up more than one character. It's + easier to write this out separately than try to macrify it. Use c to + hold the length of the character in bytes, plus UTF_LENGTH to flag that + it's a length rather than a small character. */ + +#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 + if (utf && NOT_FIRSTCHAR(code[-1])) + { + pcre_uchar *lastchar = code - 1; + BACKCHAR(lastchar); + c = (int)(code - lastchar); /* Length of UTF-8 character */ + memcpy(utf_chars, lastchar, IN_UCHARS(c)); /* Save the char */ + c |= UTF_LENGTH; /* Flag c as a length */ + } + else +#endif /* SUPPORT_UTF */ + + /* Handle the case of a single charater - either with no UTF support, or + with UTF disabled, or for a single character UTF character. */ + { + c = code[-1]; + if (*previous <= OP_CHARI && repeat_min > 1) + { + reqchar = c; + reqcharflags = req_caseopt | cd->req_varyopt; + } + } + + goto OUTPUT_SINGLE_REPEAT; /* Code shared with single character types */ + } + + /* If previous was a character type match (\d or similar), abolish it and + create a suitable repeat item. The code is shared with single-character + repeats by setting op_type to add a suitable offset into repeat_type. Note + the the Unicode property types will be present only when SUPPORT_UCP is + defined, but we don't wrap the little bits of code here because it just + makes it horribly messy. */ + + else if (*previous < OP_EODN) + { + pcre_uchar *oldcode; + int prop_type, prop_value; + op_type = OP_TYPESTAR - OP_STAR; /* Use type opcodes */ + c = *previous; + + OUTPUT_SINGLE_REPEAT: + if (*previous == OP_PROP || *previous == OP_NOTPROP) + { + prop_type = previous[1]; + prop_value = previous[2]; + } + else prop_type = prop_value = -1; + + oldcode = code; + code = previous; /* Usually overwrite previous item */ + + /* If the maximum is zero then the minimum must also be zero; Perl allows + this case, so we do too - by simply omitting the item altogether. */ + + if (repeat_max == 0) goto END_REPEAT; + + /* Combine the op_type with the repeat_type */ + + repeat_type += op_type; + + /* A minimum of zero is handled either as the special case * or ?, or as + an UPTO, with the maximum given. */ + + if (repeat_min == 0) + { + if (repeat_max == -1) *code++ = OP_STAR + repeat_type; + else if (repeat_max == 1) *code++ = OP_QUERY + repeat_type; + else + { + *code++ = OP_UPTO + repeat_type; + PUT2INC(code, 0, repeat_max); + } + } + + /* A repeat minimum of 1 is optimized into some special cases. If the + maximum is unlimited, we use OP_PLUS. Otherwise, the original item is + left in place and, if the maximum is greater than 1, we use OP_UPTO with + one less than the maximum. */ + + else if (repeat_min == 1) + { + if (repeat_max == -1) + *code++ = OP_PLUS + repeat_type; + else + { + code = oldcode; /* leave previous item in place */ + if (repeat_max == 1) goto END_REPEAT; + *code++ = OP_UPTO + repeat_type; + PUT2INC(code, 0, repeat_max - 1); + } + } + + /* The case {n,n} is just an EXACT, while the general case {n,m} is + handled as an EXACT followed by an UPTO. */ + + else + { + *code++ = OP_EXACT + op_type; /* NB EXACT doesn't have repeat_type */ + PUT2INC(code, 0, repeat_min); + + /* If the maximum is unlimited, insert an OP_STAR. Before doing so, + we have to insert the character for the previous code. For a repeated + Unicode property match, there are two extra bytes that define the + required property. In UTF-8 mode, long characters have their length in + c, with the UTF_LENGTH bit as a flag. */ + + if (repeat_max < 0) + { +#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 + if (utf && (c & UTF_LENGTH) != 0) + { + memcpy(code, utf_chars, IN_UCHARS(c & 7)); + code += c & 7; + } + else +#endif + { + *code++ = c; + if (prop_type >= 0) + { + *code++ = prop_type; + *code++ = prop_value; + } + } + *code++ = OP_STAR + repeat_type; + } + + /* Else insert an UPTO if the max is greater than the min, again + preceded by the character, for the previously inserted code. If the + UPTO is just for 1 instance, we can use QUERY instead. */ + + else if (repeat_max != repeat_min) + { +#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 + if (utf && (c & UTF_LENGTH) != 0) + { + memcpy(code, utf_chars, IN_UCHARS(c & 7)); + code += c & 7; + } + else +#endif + *code++ = c; + if (prop_type >= 0) + { + *code++ = prop_type; + *code++ = prop_value; + } + repeat_max -= repeat_min; + + if (repeat_max == 1) + { + *code++ = OP_QUERY + repeat_type; + } + else + { + *code++ = OP_UPTO + repeat_type; + PUT2INC(code, 0, repeat_max); + } + } + } + + /* The character or character type itself comes last in all cases. */ + +#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 + if (utf && (c & UTF_LENGTH) != 0) + { + memcpy(code, utf_chars, IN_UCHARS(c & 7)); + code += c & 7; + } + else +#endif + *code++ = c; + + /* For a repeated Unicode property match, there are two extra bytes that + define the required property. */ + +#ifdef SUPPORT_UCP + if (prop_type >= 0) + { + *code++ = prop_type; + *code++ = prop_value; + } +#endif + } + + /* If previous was a character class or a back reference, we put the repeat + stuff after it, but just skip the item if the repeat was {0,0}. */ + + else if (*previous == OP_CLASS || *previous == OP_NCLASS || +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + *previous == OP_XCLASS || +#endif + *previous == OP_REF || *previous == OP_REFI || + *previous == OP_DNREF || *previous == OP_DNREFI) + { + if (repeat_max == 0) + { + code = previous; + goto END_REPEAT; + } + + if (repeat_min == 0 && repeat_max == -1) + *code++ = OP_CRSTAR + repeat_type; + else if (repeat_min == 1 && repeat_max == -1) + *code++ = OP_CRPLUS + repeat_type; + else if (repeat_min == 0 && repeat_max == 1) + *code++ = OP_CRQUERY + repeat_type; + else + { + *code++ = OP_CRRANGE + repeat_type; + PUT2INC(code, 0, repeat_min); + if (repeat_max == -1) repeat_max = 0; /* 2-byte encoding for max */ + PUT2INC(code, 0, repeat_max); + } + } + + /* If previous was a bracket group, we may have to replicate it in certain + cases. Note that at this point we can encounter only the "basic" bracket + opcodes such as BRA and CBRA, as this is the place where they get converted + into the more special varieties such as BRAPOS and SBRA. A test for >= + OP_ASSERT and <= OP_COND includes ASSERT, ASSERT_NOT, ASSERTBACK, + ASSERTBACK_NOT, ONCE, ONCE_NC, BRA, BRAPOS, CBRA, CBRAPOS, and COND. + Originally, PCRE did not allow repetition of assertions, but now it does, + for Perl compatibility. */ + + else if (*previous >= OP_ASSERT && *previous <= OP_COND) + { + register int i; + int len = (int)(code - previous); + pcre_uchar *bralink = NULL; + pcre_uchar *brazeroptr = NULL; + + /* Repeating a DEFINE group is pointless, but Perl allows the syntax, so + we just ignore the repeat. */ + + if (*previous == OP_COND && previous[LINK_SIZE+1] == OP_DEF) + goto END_REPEAT; + + /* There is no sense in actually repeating assertions. The only potential + use of repetition is in cases when the assertion is optional. Therefore, + if the minimum is greater than zero, just ignore the repeat. If the + maximum is not zero or one, set it to 1. */ + + if (*previous < OP_ONCE) /* Assertion */ + { + if (repeat_min > 0) goto END_REPEAT; + if (repeat_max < 0 || repeat_max > 1) repeat_max = 1; + } + + /* The case of a zero minimum is special because of the need to stick + OP_BRAZERO in front of it, and because the group appears once in the + data, whereas in other cases it appears the minimum number of times. For + this reason, it is simplest to treat this case separately, as otherwise + the code gets far too messy. There are several special subcases when the + minimum is zero. */ + + if (repeat_min == 0) + { + /* If the maximum is also zero, we used to just omit the group from the + output altogether, like this: + + ** if (repeat_max == 0) + ** { + ** code = previous; + ** goto END_REPEAT; + ** } + + However, that fails when a group or a subgroup within it is referenced + as a subroutine from elsewhere in the pattern, so now we stick in + OP_SKIPZERO in front of it so that it is skipped on execution. As we + don't have a list of which groups are referenced, we cannot do this + selectively. + + If the maximum is 1 or unlimited, we just have to stick in the BRAZERO + and do no more at this point. However, we do need to adjust any + OP_RECURSE calls inside the group that refer to the group itself or any + internal or forward referenced group, because the offset is from the + start of the whole regex. Temporarily terminate the pattern while doing + this. */ + + if (repeat_max <= 1) /* Covers 0, 1, and unlimited */ + { + *code = OP_END; + adjust_recurse(previous, 1, utf, cd, save_hwm); + memmove(previous + 1, previous, IN_UCHARS(len)); + code++; + if (repeat_max == 0) + { + *previous++ = OP_SKIPZERO; + goto END_REPEAT; + } + brazeroptr = previous; /* Save for possessive optimizing */ + *previous++ = OP_BRAZERO + repeat_type; + } + + /* If the maximum is greater than 1 and limited, we have to replicate + in a nested fashion, sticking OP_BRAZERO before each set of brackets. + The first one has to be handled carefully because it's the original + copy, which has to be moved up. The remainder can be handled by code + that is common with the non-zero minimum case below. We have to + adjust the value or repeat_max, since one less copy is required. Once + again, we may have to adjust any OP_RECURSE calls inside the group. */ + + else + { + int offset; + *code = OP_END; + adjust_recurse(previous, 2 + LINK_SIZE, utf, cd, save_hwm); + memmove(previous + 2 + LINK_SIZE, previous, IN_UCHARS(len)); + code += 2 + LINK_SIZE; + *previous++ = OP_BRAZERO + repeat_type; + *previous++ = OP_BRA; + + /* We chain together the bracket offset fields that have to be + filled in later when the ends of the brackets are reached. */ + + offset = (bralink == NULL)? 0 : (int)(previous - bralink); + bralink = previous; + PUTINC(previous, 0, offset); + } + + repeat_max--; + } + + /* If the minimum is greater than zero, replicate the group as many + times as necessary, and adjust the maximum to the number of subsequent + copies that we need. If we set a first char from the group, and didn't + set a required char, copy the latter from the former. If there are any + forward reference subroutine calls in the group, there will be entries on + the workspace list; replicate these with an appropriate increment. */ + + else + { + if (repeat_min > 1) + { + /* In the pre-compile phase, we don't actually do the replication. We + just adjust the length as if we had. Do some paranoid checks for + potential integer overflow. The INT64_OR_DOUBLE type is a 64-bit + integer type when available, otherwise double. */ + + if (lengthptr != NULL) + { + int delta = (repeat_min - 1)*length_prevgroup; + if ((INT64_OR_DOUBLE)(repeat_min - 1)* + (INT64_OR_DOUBLE)length_prevgroup > + (INT64_OR_DOUBLE)INT_MAX || + OFLOW_MAX - *lengthptr < delta) + { + *errorcodeptr = ERR20; + goto FAILED; + } + *lengthptr += delta; + } + + /* This is compiling for real. If there is a set first byte for + the group, and we have not yet set a "required byte", set it. Make + sure there is enough workspace for copying forward references before + doing the copy. */ + + else + { + if (groupsetfirstchar && reqcharflags < 0) + { + reqchar = firstchar; + reqcharflags = firstcharflags; + } + + for (i = 1; i < repeat_min; i++) + { + pcre_uchar *hc; + pcre_uchar *this_hwm = cd->hwm; + memcpy(code, previous, IN_UCHARS(len)); + + while (cd->hwm > cd->start_workspace + cd->workspace_size - + WORK_SIZE_SAFETY_MARGIN - (this_hwm - save_hwm)) + { + int save_offset = save_hwm - cd->start_workspace; + int this_offset = this_hwm - cd->start_workspace; + *errorcodeptr = expand_workspace(cd); + if (*errorcodeptr != 0) goto FAILED; + save_hwm = (pcre_uchar *)cd->start_workspace + save_offset; + this_hwm = (pcre_uchar *)cd->start_workspace + this_offset; + } + + for (hc = save_hwm; hc < this_hwm; hc += LINK_SIZE) + { + PUT(cd->hwm, 0, GET(hc, 0) + len); + cd->hwm += LINK_SIZE; + } + save_hwm = this_hwm; + code += len; + } + } + } + + if (repeat_max > 0) repeat_max -= repeat_min; + } + + /* This code is common to both the zero and non-zero minimum cases. If + the maximum is limited, it replicates the group in a nested fashion, + remembering the bracket starts on a stack. In the case of a zero minimum, + the first one was set up above. In all cases the repeat_max now specifies + the number of additional copies needed. Again, we must remember to + replicate entries on the forward reference list. */ + + if (repeat_max >= 0) + { + /* In the pre-compile phase, we don't actually do the replication. We + just adjust the length as if we had. For each repetition we must add 1 + to the length for BRAZERO and for all but the last repetition we must + add 2 + 2*LINKSIZE to allow for the nesting that occurs. Do some + paranoid checks to avoid integer overflow. The INT64_OR_DOUBLE type is + a 64-bit integer type when available, otherwise double. */ + + if (lengthptr != NULL && repeat_max > 0) + { + int delta = repeat_max * (length_prevgroup + 1 + 2 + 2*LINK_SIZE) - + 2 - 2*LINK_SIZE; /* Last one doesn't nest */ + if ((INT64_OR_DOUBLE)repeat_max * + (INT64_OR_DOUBLE)(length_prevgroup + 1 + 2 + 2*LINK_SIZE) + > (INT64_OR_DOUBLE)INT_MAX || + OFLOW_MAX - *lengthptr < delta) + { + *errorcodeptr = ERR20; + goto FAILED; + } + *lengthptr += delta; + } + + /* This is compiling for real */ + + else for (i = repeat_max - 1; i >= 0; i--) + { + pcre_uchar *hc; + pcre_uchar *this_hwm = cd->hwm; + + *code++ = OP_BRAZERO + repeat_type; + + /* All but the final copy start a new nesting, maintaining the + chain of brackets outstanding. */ + + if (i != 0) + { + int offset; + *code++ = OP_BRA; + offset = (bralink == NULL)? 0 : (int)(code - bralink); + bralink = code; + PUTINC(code, 0, offset); + } + + memcpy(code, previous, IN_UCHARS(len)); + + /* Ensure there is enough workspace for forward references before + copying them. */ + + while (cd->hwm > cd->start_workspace + cd->workspace_size - + WORK_SIZE_SAFETY_MARGIN - (this_hwm - save_hwm)) + { + int save_offset = save_hwm - cd->start_workspace; + int this_offset = this_hwm - cd->start_workspace; + *errorcodeptr = expand_workspace(cd); + if (*errorcodeptr != 0) goto FAILED; + save_hwm = (pcre_uchar *)cd->start_workspace + save_offset; + this_hwm = (pcre_uchar *)cd->start_workspace + this_offset; + } + + for (hc = save_hwm; hc < this_hwm; hc += LINK_SIZE) + { + PUT(cd->hwm, 0, GET(hc, 0) + len + ((i != 0)? 2+LINK_SIZE : 1)); + cd->hwm += LINK_SIZE; + } + save_hwm = this_hwm; + code += len; + } + + /* Now chain through the pending brackets, and fill in their length + fields (which are holding the chain links pro tem). */ + + while (bralink != NULL) + { + int oldlinkoffset; + int offset = (int)(code - bralink + 1); + pcre_uchar *bra = code - offset; + oldlinkoffset = GET(bra, 1); + bralink = (oldlinkoffset == 0)? NULL : bralink - oldlinkoffset; + *code++ = OP_KET; + PUTINC(code, 0, offset); + PUT(bra, 1, offset); + } + } + + /* If the maximum is unlimited, set a repeater in the final copy. For + ONCE brackets, that's all we need to do. However, possessively repeated + ONCE brackets can be converted into non-capturing brackets, as the + behaviour of (?:xx)++ is the same as (?>xx)++ and this saves having to + deal with possessive ONCEs specially. + + Otherwise, when we are doing the actual compile phase, check to see + whether this group is one that could match an empty string. If so, + convert the initial operator to the S form (e.g. OP_BRA -> OP_SBRA) so + that runtime checking can be done. [This check is also applied to ONCE + groups at runtime, but in a different way.] + + Then, if the quantifier was possessive and the bracket is not a + conditional, we convert the BRA code to the POS form, and the KET code to + KETRPOS. (It turns out to be convenient at runtime to detect this kind of + subpattern at both the start and at the end.) The use of special opcodes + makes it possible to reduce greatly the stack usage in pcre_exec(). If + the group is preceded by OP_BRAZERO, convert this to OP_BRAPOSZERO. + + Then, if the minimum number of matches is 1 or 0, cancel the possessive + flag so that the default action below, of wrapping everything inside + atomic brackets, does not happen. When the minimum is greater than 1, + there will be earlier copies of the group, and so we still have to wrap + the whole thing. */ + + else + { + pcre_uchar *ketcode = code - 1 - LINK_SIZE; + pcre_uchar *bracode = ketcode - GET(ketcode, 1); + + /* Convert possessive ONCE brackets to non-capturing */ + + if ((*bracode == OP_ONCE || *bracode == OP_ONCE_NC) && + possessive_quantifier) *bracode = OP_BRA; + + /* For non-possessive ONCE brackets, all we need to do is to + set the KET. */ + + if (*bracode == OP_ONCE || *bracode == OP_ONCE_NC) + *ketcode = OP_KETRMAX + repeat_type; + + /* Handle non-ONCE brackets and possessive ONCEs (which have been + converted to non-capturing above). */ + + else + { + /* In the compile phase, check for empty string matching. */ + + if (lengthptr == NULL) + { + pcre_uchar *scode = bracode; + do + { + if (could_be_empty_branch(scode, ketcode, utf, cd, NULL)) + { + *bracode += OP_SBRA - OP_BRA; + break; + } + scode += GET(scode, 1); + } + while (*scode == OP_ALT); + } + + /* Handle possessive quantifiers. */ + + if (possessive_quantifier) + { + /* For COND brackets, we wrap the whole thing in a possessively + repeated non-capturing bracket, because we have not invented POS + versions of the COND opcodes. Because we are moving code along, we + must ensure that any pending recursive references are updated. */ + + if (*bracode == OP_COND || *bracode == OP_SCOND) + { + int nlen = (int)(code - bracode); + *code = OP_END; + adjust_recurse(bracode, 1 + LINK_SIZE, utf, cd, save_hwm); + memmove(bracode + 1 + LINK_SIZE, bracode, IN_UCHARS(nlen)); + code += 1 + LINK_SIZE; + nlen += 1 + LINK_SIZE; + *bracode = OP_BRAPOS; + *code++ = OP_KETRPOS; + PUTINC(code, 0, nlen); + PUT(bracode, 1, nlen); + } + + /* For non-COND brackets, we modify the BRA code and use KETRPOS. */ + + else + { + *bracode += 1; /* Switch to xxxPOS opcodes */ + *ketcode = OP_KETRPOS; + } + + /* If the minimum is zero, mark it as possessive, then unset the + possessive flag when the minimum is 0 or 1. */ + + if (brazeroptr != NULL) *brazeroptr = OP_BRAPOSZERO; + if (repeat_min < 2) possessive_quantifier = FALSE; + } + + /* Non-possessive quantifier */ + + else *ketcode = OP_KETRMAX + repeat_type; + } + } + } + + /* If previous is OP_FAIL, it was generated by an empty class [] in + JavaScript mode. The other ways in which OP_FAIL can be generated, that is + by (*FAIL) or (?!) set previous to NULL, which gives a "nothing to repeat" + error above. We can just ignore the repeat in JS case. */ + + else if (*previous == OP_FAIL) goto END_REPEAT; + + /* Else there's some kind of shambles */ + + else + { + *errorcodeptr = ERR11; + goto FAILED; + } + + /* If the character following a repeat is '+', possessive_quantifier is + TRUE. For some opcodes, there are special alternative opcodes for this + case. For anything else, we wrap the entire repeated item inside OP_ONCE + brackets. Logically, the '+' notation is just syntactic sugar, taken from + Sun's Java package, but the special opcodes can optimize it. + + Some (but not all) possessively repeated subpatterns have already been + completely handled in the code just above. For them, possessive_quantifier + is always FALSE at this stage. Note that the repeated item starts at + tempcode, not at previous, which might be the first part of a string whose + (former) last char we repeated. */ + + if (possessive_quantifier) + { + int len; + + /* Possessifying an EXACT quantifier has no effect, so we can ignore it. + However, QUERY, STAR, or UPTO may follow (for quantifiers such as {5,6}, + {5,}, or {5,10}). We skip over an EXACT item; if the length of what + remains is greater than zero, there's a further opcode that can be + handled. If not, do nothing, leaving the EXACT alone. */ + + switch(*tempcode) + { + case OP_TYPEEXACT: + tempcode += PRIV(OP_lengths)[*tempcode] + + ((tempcode[1 + IMM2_SIZE] == OP_PROP + || tempcode[1 + IMM2_SIZE] == OP_NOTPROP)? 2 : 0); + break; + + /* CHAR opcodes are used for exacts whose count is 1. */ + + case OP_CHAR: + case OP_CHARI: + case OP_NOT: + case OP_NOTI: + case OP_EXACT: + case OP_EXACTI: + case OP_NOTEXACT: + case OP_NOTEXACTI: + tempcode += PRIV(OP_lengths)[*tempcode]; +#ifdef SUPPORT_UTF + if (utf && HAS_EXTRALEN(tempcode[-1])) + tempcode += GET_EXTRALEN(tempcode[-1]); +#endif + break; + + /* For the class opcodes, the repeat operator appears at the end; + adjust tempcode to point to it. */ + + case OP_CLASS: + case OP_NCLASS: + tempcode += 1 + 32/sizeof(pcre_uchar); + break; + +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + case OP_XCLASS: + tempcode += GET(tempcode, 1); + break; +#endif + } + + /* If tempcode is equal to code (which points to the end of the repeated + item), it means we have skipped an EXACT item but there is no following + QUERY, STAR, or UPTO; the value of len will be 0, and we do nothing. In + all other cases, tempcode will be pointing to the repeat opcode, and will + be less than code, so the value of len will be greater than 0. */ + + len = (int)(code - tempcode); + if (len > 0) + { + unsigned int repcode = *tempcode; + + /* There is a table for possessifying opcodes, all of which are less + than OP_CALLOUT. A zero entry means there is no possessified version. + */ + + if (repcode < OP_CALLOUT && opcode_possessify[repcode] > 0) + *tempcode = opcode_possessify[repcode]; + + /* For opcode without a special possessified version, wrap the item in + ONCE brackets. Because we are moving code along, we must ensure that any + pending recursive references are updated. */ + + else + { + *code = OP_END; + adjust_recurse(tempcode, 1 + LINK_SIZE, utf, cd, save_hwm); + memmove(tempcode + 1 + LINK_SIZE, tempcode, IN_UCHARS(len)); + code += 1 + LINK_SIZE; + len += 1 + LINK_SIZE; + tempcode[0] = OP_ONCE; + *code++ = OP_KET; + PUTINC(code, 0, len); + PUT(tempcode, 1, len); + } + } + +#ifdef NEVER + if (len > 0) switch (*tempcode) + { + case OP_STAR: *tempcode = OP_POSSTAR; break; + case OP_PLUS: *tempcode = OP_POSPLUS; break; + case OP_QUERY: *tempcode = OP_POSQUERY; break; + case OP_UPTO: *tempcode = OP_POSUPTO; break; + + case OP_STARI: *tempcode = OP_POSSTARI; break; + case OP_PLUSI: *tempcode = OP_POSPLUSI; break; + case OP_QUERYI: *tempcode = OP_POSQUERYI; break; + case OP_UPTOI: *tempcode = OP_POSUPTOI; break; + + case OP_NOTSTAR: *tempcode = OP_NOTPOSSTAR; break; + case OP_NOTPLUS: *tempcode = OP_NOTPOSPLUS; break; + case OP_NOTQUERY: *tempcode = OP_NOTPOSQUERY; break; + case OP_NOTUPTO: *tempcode = OP_NOTPOSUPTO; break; + + case OP_NOTSTARI: *tempcode = OP_NOTPOSSTARI; break; + case OP_NOTPLUSI: *tempcode = OP_NOTPOSPLUSI; break; + case OP_NOTQUERYI: *tempcode = OP_NOTPOSQUERYI; break; + case OP_NOTUPTOI: *tempcode = OP_NOTPOSUPTOI; break; + + case OP_TYPESTAR: *tempcode = OP_TYPEPOSSTAR; break; + case OP_TYPEPLUS: *tempcode = OP_TYPEPOSPLUS; break; + case OP_TYPEQUERY: *tempcode = OP_TYPEPOSQUERY; break; + case OP_TYPEUPTO: *tempcode = OP_TYPEPOSUPTO; break; + + case OP_CRSTAR: *tempcode = OP_CRPOSSTAR; break; + case OP_CRPLUS: *tempcode = OP_CRPOSPLUS; break; + case OP_CRQUERY: *tempcode = OP_CRPOSQUERY; break; + case OP_CRRANGE: *tempcode = OP_CRPOSRANGE; break; + + /* Because we are moving code along, we must ensure that any + pending recursive references are updated. */ + + default: + *code = OP_END; + adjust_recurse(tempcode, 1 + LINK_SIZE, utf, cd, save_hwm); + memmove(tempcode + 1 + LINK_SIZE, tempcode, IN_UCHARS(len)); + code += 1 + LINK_SIZE; + len += 1 + LINK_SIZE; + tempcode[0] = OP_ONCE; + *code++ = OP_KET; + PUTINC(code, 0, len); + PUT(tempcode, 1, len); + break; + } +#endif + } + + /* In all case we no longer have a previous item. We also set the + "follows varying string" flag for subsequently encountered reqchars if + it isn't already set and we have just passed a varying length item. */ + + END_REPEAT: + previous = NULL; + cd->req_varyopt |= reqvary; + break; + + + /* ===================================================================*/ + /* Start of nested parenthesized sub-expression, or comment or lookahead or + lookbehind or option setting or condition or all the other extended + parenthesis forms. */ + + case CHAR_LEFT_PARENTHESIS: + newoptions = options; + skipbytes = 0; + bravalue = OP_CBRA; + save_hwm = cd->hwm; + reset_bracount = FALSE; + + /* First deal with various "verbs" that can be introduced by '*'. */ + + ptr++; + if (ptr[0] == CHAR_ASTERISK && (ptr[1] == ':' + || (MAX_255(ptr[1]) && ((cd->ctypes[ptr[1]] & ctype_letter) != 0)))) + { + int i, namelen; + int arglen = 0; + const char *vn = verbnames; + const pcre_uchar *name = ptr + 1; + const pcre_uchar *arg = NULL; + previous = NULL; + ptr++; + while (MAX_255(*ptr) && (cd->ctypes[*ptr] & ctype_letter) != 0) ptr++; + namelen = (int)(ptr - name); + + /* It appears that Perl allows any characters whatsoever, other than + a closing parenthesis, to appear in arguments, so we no longer insist on + letters, digits, and underscores. */ + + if (*ptr == CHAR_COLON) + { + arg = ++ptr; + while (*ptr != CHAR_NULL && *ptr != CHAR_RIGHT_PARENTHESIS) ptr++; + arglen = (int)(ptr - arg); + if ((unsigned int)arglen > MAX_MARK) + { + *errorcodeptr = ERR75; + goto FAILED; + } + } + + if (*ptr != CHAR_RIGHT_PARENTHESIS) + { + *errorcodeptr = ERR60; + goto FAILED; + } + + /* Scan the table of verb names */ + + for (i = 0; i < verbcount; i++) + { + if (namelen == verbs[i].len && + STRNCMP_UC_C8(name, vn, namelen) == 0) + { + int setverb; + + /* Check for open captures before ACCEPT and convert it to + ASSERT_ACCEPT if in an assertion. */ + + if (verbs[i].op == OP_ACCEPT) + { + open_capitem *oc; + if (arglen != 0) + { + *errorcodeptr = ERR59; + goto FAILED; + } + cd->had_accept = TRUE; + for (oc = cd->open_caps; oc != NULL; oc = oc->next) + { + *code++ = OP_CLOSE; + PUT2INC(code, 0, oc->number); + } + setverb = *code++ = + (cd->assert_depth > 0)? OP_ASSERT_ACCEPT : OP_ACCEPT; + + /* Do not set firstchar after *ACCEPT */ + if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; + } + + /* Handle other cases with/without an argument */ + + else if (arglen == 0) + { + if (verbs[i].op < 0) /* Argument is mandatory */ + { + *errorcodeptr = ERR66; + goto FAILED; + } + setverb = *code++ = verbs[i].op; + } + + else + { + if (verbs[i].op_arg < 0) /* Argument is forbidden */ + { + *errorcodeptr = ERR59; + goto FAILED; + } + setverb = *code++ = verbs[i].op_arg; + *code++ = arglen; + memcpy(code, arg, IN_UCHARS(arglen)); + code += arglen; + *code++ = 0; + } + + switch (setverb) + { + case OP_THEN: + case OP_THEN_ARG: + cd->external_flags |= PCRE_HASTHEN; + break; + + case OP_PRUNE: + case OP_PRUNE_ARG: + case OP_SKIP: + case OP_SKIP_ARG: + cd->had_pruneorskip = TRUE; + break; + } + + break; /* Found verb, exit loop */ + } + + vn += verbs[i].len + 1; + } + + if (i < verbcount) continue; /* Successfully handled a verb */ + *errorcodeptr = ERR60; /* Verb not recognized */ + goto FAILED; + } + + /* Deal with the extended parentheses; all are introduced by '?', and the + appearance of any of them means that this is not a capturing group. */ + + else if (*ptr == CHAR_QUESTION_MARK) + { + int i, set, unset, namelen; + int *optset; + const pcre_uchar *name; + pcre_uchar *slot; + + switch (*(++ptr)) + { + case CHAR_NUMBER_SIGN: /* Comment; skip to ket */ + ptr++; + while (*ptr != CHAR_NULL && *ptr != CHAR_RIGHT_PARENTHESIS) ptr++; + if (*ptr == CHAR_NULL) + { + *errorcodeptr = ERR18; + goto FAILED; + } + continue; + + + /* ------------------------------------------------------------ */ + case CHAR_VERTICAL_LINE: /* Reset capture count for each branch */ + reset_bracount = TRUE; + /* Fall through */ + + /* ------------------------------------------------------------ */ + case CHAR_COLON: /* Non-capturing bracket */ + bravalue = OP_BRA; + ptr++; + break; + + + /* ------------------------------------------------------------ */ + case CHAR_LEFT_PARENTHESIS: + bravalue = OP_COND; /* Conditional group */ + tempptr = ptr; + + /* A condition can be an assertion, a number (referring to a numbered + group's having been set), a name (referring to a named group), or 'R', + referring to recursion. R<digits> and R&name are also permitted for + recursion tests. + + There are ways of testing a named group: (?(name)) is used by Python; + Perl 5.10 onwards uses (?(<name>) or (?('name')). + + There is one unfortunate ambiguity, caused by history. 'R' can be the + recursive thing or the name 'R' (and similarly for 'R' followed by + digits). We look for a name first; if not found, we try the other case. + + For compatibility with auto-callouts, we allow a callout to be + specified before a condition that is an assertion. First, check for the + syntax of a callout; if found, adjust the temporary pointer that is + used to check for an assertion condition. That's all that is needed! */ + + if (ptr[1] == CHAR_QUESTION_MARK && ptr[2] == CHAR_C) + { + for (i = 3;; i++) if (!IS_DIGIT(ptr[i])) break; + if (ptr[i] == CHAR_RIGHT_PARENTHESIS) + tempptr += i + 1; + } + + /* For conditions that are assertions, check the syntax, and then exit + the switch. This will take control down to where bracketed groups, + including assertions, are processed. */ + + if (tempptr[1] == CHAR_QUESTION_MARK && + (tempptr[2] == CHAR_EQUALS_SIGN || + tempptr[2] == CHAR_EXCLAMATION_MARK || + tempptr[2] == CHAR_LESS_THAN_SIGN)) + break; + + /* Other conditions use OP_CREF/OP_DNCREF/OP_RREF/OP_DNRREF, and all + need to skip at least 1+IMM2_SIZE bytes at the start of the group. */ + + code[1+LINK_SIZE] = OP_CREF; + skipbytes = 1+IMM2_SIZE; + refsign = -1; /* => not a number */ + namelen = -1; /* => not a name; must set to avoid warning */ + name = NULL; /* Always set to avoid warning */ + recno = 0; /* Always set to avoid warning */ + + /* Check for a test for recursion in a named group. */ + + ptr++; + if (*ptr == CHAR_R && ptr[1] == CHAR_AMPERSAND) + { + terminator = -1; + ptr += 2; + code[1+LINK_SIZE] = OP_RREF; /* Change the type of test */ + } + + /* Check for a test for a named group's having been set, using the Perl + syntax (?(<name>) or (?('name'), and also allow for the original PCRE + syntax of (?(name) or for (?(+n), (?(-n), and just (?(n). */ + + else if (*ptr == CHAR_LESS_THAN_SIGN) + { + terminator = CHAR_GREATER_THAN_SIGN; + ptr++; + } + else if (*ptr == CHAR_APOSTROPHE) + { + terminator = CHAR_APOSTROPHE; + ptr++; + } + else + { + terminator = CHAR_NULL; + if (*ptr == CHAR_MINUS || *ptr == CHAR_PLUS) refsign = *ptr++; + else if (IS_DIGIT(*ptr)) refsign = 0; + } + + /* Handle a number */ + + if (refsign >= 0) + { + while (IS_DIGIT(*ptr)) + { + recno = recno * 10 + (int)(*ptr - CHAR_0); + ptr++; + } + } + + /* Otherwise we expect to read a name; anything else is an error. When + a name is one of a number of duplicates, a different opcode is used and + it needs more memory. Unfortunately we cannot tell whether a name is a + duplicate in the first pass, so we have to allow for more memory. */ + + else + { + if (IS_DIGIT(*ptr)) + { + *errorcodeptr = ERR84; + goto FAILED; + } + if (!MAX_255(*ptr) || (cd->ctypes[*ptr] & ctype_word) == 0) + { + *errorcodeptr = ERR28; /* Assertion expected */ + goto FAILED; + } + name = ptr++; + while (MAX_255(*ptr) && (cd->ctypes[*ptr] & ctype_word) != 0) + { + ptr++; + } + namelen = (int)(ptr - name); + if (lengthptr != NULL) *lengthptr += IMM2_SIZE; + } + + /* Check the terminator */ + + if ((terminator > 0 && *ptr++ != (pcre_uchar)terminator) || + *ptr++ != CHAR_RIGHT_PARENTHESIS) + { + ptr--; /* Error offset */ + *errorcodeptr = ERR26; /* Malformed number or name */ + goto FAILED; + } + + /* Do no further checking in the pre-compile phase. */ + + if (lengthptr != NULL) break; + + /* In the real compile we do the work of looking for the actual + reference. If refsign is not negative, it means we have a number in + recno. */ + + if (refsign >= 0) + { + if (recno <= 0) + { + *errorcodeptr = ERR35; + goto FAILED; + } + if (refsign != 0) recno = (refsign == CHAR_MINUS)? + cd->bracount - recno + 1 : recno + cd->bracount; + if (recno <= 0 || recno > cd->final_bracount) + { + *errorcodeptr = ERR15; + goto FAILED; + } + PUT2(code, 2+LINK_SIZE, recno); + break; + } + + /* Otherwise look for the name. */ + + slot = cd->name_table; + for (i = 0; i < cd->names_found; i++) + { + if (STRNCMP_UC_UC(name, slot+IMM2_SIZE, namelen) == 0) break; + slot += cd->name_entry_size; + } + + /* Found the named subpattern. If the name is duplicated, add one to + the opcode to change CREF/RREF into DNCREF/DNRREF and insert + appropriate data values. Otherwise, just insert the unique subpattern + number. */ + + if (i < cd->names_found) + { + int offset = i++; + int count = 1; + recno = GET2(slot, 0); /* Number from first found */ + for (; i < cd->names_found; i++) + { + slot += cd->name_entry_size; + if (STRNCMP_UC_UC(name, slot+IMM2_SIZE, namelen) != 0) break; + count++; + } + if (count > 1) + { + PUT2(code, 2+LINK_SIZE, offset); + PUT2(code, 2+LINK_SIZE+IMM2_SIZE, count); + skipbytes += IMM2_SIZE; + code[1+LINK_SIZE]++; + } + else /* Not a duplicated name */ + { + PUT2(code, 2+LINK_SIZE, recno); + } + } + + /* If terminator == CHAR_NULL it means that the name followed directly + after the opening parenthesis [e.g. (?(abc)...] and in this case there + are some further alternatives to try. For the cases where terminator != + CHAR_NULL [things like (?(<name>... or (?('name')... or (?(R&name)... ] + we have now checked all the possibilities, so give an error. */ + + else if (terminator != CHAR_NULL) + { + *errorcodeptr = ERR15; + goto FAILED; + } + + /* Check for (?(R) for recursion. Allow digits after R to specify a + specific group number. */ + + else if (*name == CHAR_R) + { + recno = 0; + for (i = 1; i < namelen; i++) + { + if (!IS_DIGIT(name[i])) + { + *errorcodeptr = ERR15; + goto FAILED; + } + recno = recno * 10 + name[i] - CHAR_0; + } + if (recno == 0) recno = RREF_ANY; + code[1+LINK_SIZE] = OP_RREF; /* Change test type */ + PUT2(code, 2+LINK_SIZE, recno); + } + + /* Similarly, check for the (?(DEFINE) "condition", which is always + false. */ + + else if (namelen == 6 && STRNCMP_UC_C8(name, STRING_DEFINE, 6) == 0) + { + code[1+LINK_SIZE] = OP_DEF; + skipbytes = 1; + } + + /* Reference to an unidentified subpattern. */ + + else + { + *errorcodeptr = ERR15; + goto FAILED; + } + break; + + + /* ------------------------------------------------------------ */ + case CHAR_EQUALS_SIGN: /* Positive lookahead */ + bravalue = OP_ASSERT; + cd->assert_depth += 1; + ptr++; + break; + + /* Optimize (?!) to (*FAIL) unless it is quantified - which is a weird + thing to do, but Perl allows all assertions to be quantified, and when + they contain capturing parentheses there may be a potential use for + this feature. Not that that applies to a quantified (?!) but we allow + it for uniformity. */ + + /* ------------------------------------------------------------ */ + case CHAR_EXCLAMATION_MARK: /* Negative lookahead */ + ptr++; + if (*ptr == CHAR_RIGHT_PARENTHESIS && ptr[1] != CHAR_ASTERISK && + ptr[1] != CHAR_PLUS && ptr[1] != CHAR_QUESTION_MARK && + (ptr[1] != CHAR_LEFT_CURLY_BRACKET || !is_counted_repeat(ptr+2))) + { + *code++ = OP_FAIL; + previous = NULL; + continue; + } + bravalue = OP_ASSERT_NOT; + cd->assert_depth += 1; + break; + + + /* ------------------------------------------------------------ */ + case CHAR_LESS_THAN_SIGN: /* Lookbehind or named define */ + switch (ptr[1]) + { + case CHAR_EQUALS_SIGN: /* Positive lookbehind */ + bravalue = OP_ASSERTBACK; + cd->assert_depth += 1; + ptr += 2; + break; + + case CHAR_EXCLAMATION_MARK: /* Negative lookbehind */ + bravalue = OP_ASSERTBACK_NOT; + cd->assert_depth += 1; + ptr += 2; + break; + + default: /* Could be name define, else bad */ + if (MAX_255(ptr[1]) && (cd->ctypes[ptr[1]] & ctype_word) != 0) + goto DEFINE_NAME; + ptr++; /* Correct offset for error */ + *errorcodeptr = ERR24; + goto FAILED; + } + break; + + + /* ------------------------------------------------------------ */ + case CHAR_GREATER_THAN_SIGN: /* One-time brackets */ + bravalue = OP_ONCE; + ptr++; + break; + + + /* ------------------------------------------------------------ */ + case CHAR_C: /* Callout - may be followed by digits; */ + previous_callout = code; /* Save for later completion */ + after_manual_callout = 1; /* Skip one item before completing */ + *code++ = OP_CALLOUT; + { + int n = 0; + ptr++; + while(IS_DIGIT(*ptr)) + n = n * 10 + *ptr++ - CHAR_0; + if (*ptr != CHAR_RIGHT_PARENTHESIS) + { + *errorcodeptr = ERR39; + goto FAILED; + } + if (n > 255) + { + *errorcodeptr = ERR38; + goto FAILED; + } + *code++ = n; + PUT(code, 0, (int)(ptr - cd->start_pattern + 1)); /* Pattern offset */ + PUT(code, LINK_SIZE, 0); /* Default length */ + code += 2 * LINK_SIZE; + } + previous = NULL; + continue; + + + /* ------------------------------------------------------------ */ + case CHAR_P: /* Python-style named subpattern handling */ + if (*(++ptr) == CHAR_EQUALS_SIGN || + *ptr == CHAR_GREATER_THAN_SIGN) /* Reference or recursion */ + { + is_recurse = *ptr == CHAR_GREATER_THAN_SIGN; + terminator = CHAR_RIGHT_PARENTHESIS; + goto NAMED_REF_OR_RECURSE; + } + else if (*ptr != CHAR_LESS_THAN_SIGN) /* Test for Python-style defn */ + { + *errorcodeptr = ERR41; + goto FAILED; + } + /* Fall through to handle (?P< as (?< is handled */ + + + /* ------------------------------------------------------------ */ + DEFINE_NAME: /* Come here from (?< handling */ + case CHAR_APOSTROPHE: + terminator = (*ptr == CHAR_LESS_THAN_SIGN)? + CHAR_GREATER_THAN_SIGN : CHAR_APOSTROPHE; + name = ++ptr; + if (IS_DIGIT(*ptr)) + { + *errorcodeptr = ERR84; /* Group name must start with non-digit */ + goto FAILED; + } + while (MAX_255(*ptr) && (cd->ctypes[*ptr] & ctype_word) != 0) ptr++; + namelen = (int)(ptr - name); + + /* In the pre-compile phase, do a syntax check, remember the longest + name, and then remember the group in a vector, expanding it if + necessary. Duplicates for the same number are skipped; other duplicates + are checked for validity. In the actual compile, there is nothing to + do. */ + + if (lengthptr != NULL) + { + named_group *ng; + pcre_uint32 number = cd->bracount + 1; + + if (*ptr != (pcre_uchar)terminator) + { + *errorcodeptr = ERR42; + goto FAILED; + } + + if (cd->names_found >= MAX_NAME_COUNT) + { + *errorcodeptr = ERR49; + goto FAILED; + } + + if (namelen + IMM2_SIZE + 1 > cd->name_entry_size) + { + cd->name_entry_size = namelen + IMM2_SIZE + 1; + if (namelen > MAX_NAME_SIZE) + { + *errorcodeptr = ERR48; + goto FAILED; + } + } + + /* Scan the list to check for duplicates. For duplicate names, if the + number is the same, break the loop, which causes the name to be + discarded; otherwise, if DUPNAMES is not set, give an error. + If it is set, allow the name with a different number, but continue + scanning in case this is a duplicate with the same number. For + non-duplicate names, give an error if the number is duplicated. */ + + ng = cd->named_groups; + for (i = 0; i < cd->names_found; i++, ng++) + { + if (namelen == ng->length && + STRNCMP_UC_UC(name, ng->name, namelen) == 0) + { + if (ng->number == number) break; + if ((options & PCRE_DUPNAMES) == 0) + { + *errorcodeptr = ERR43; + goto FAILED; + } + cd->dupnames = TRUE; /* Duplicate names exist */ + } + else if (ng->number == number) + { + *errorcodeptr = ERR65; + goto FAILED; + } + } + + if (i >= cd->names_found) /* Not a duplicate with same number */ + { + /* Increase the list size if necessary */ + + if (cd->names_found >= cd->named_group_list_size) + { + int newsize = cd->named_group_list_size * 2; + named_group *newspace = (PUBL(malloc)) + (newsize * sizeof(named_group)); + + if (newspace == NULL) + { + *errorcodeptr = ERR21; + goto FAILED; + } + + memcpy(newspace, cd->named_groups, + cd->named_group_list_size * sizeof(named_group)); + if (cd->named_group_list_size > NAMED_GROUP_LIST_SIZE) + (PUBL(free))((void *)cd->named_groups); + cd->named_groups = newspace; + cd->named_group_list_size = newsize; + } + + cd->named_groups[cd->names_found].name = name; + cd->named_groups[cd->names_found].length = namelen; + cd->named_groups[cd->names_found].number = number; + cd->names_found++; + } + } + + ptr++; /* Move past > or ' in both passes. */ + goto NUMBERED_GROUP; + + + /* ------------------------------------------------------------ */ + case CHAR_AMPERSAND: /* Perl recursion/subroutine syntax */ + terminator = CHAR_RIGHT_PARENTHESIS; + is_recurse = TRUE; + /* Fall through */ + + /* We come here from the Python syntax above that handles both + references (?P=name) and recursion (?P>name), as well as falling + through from the Perl recursion syntax (?&name). We also come here from + the Perl \k<name> or \k'name' back reference syntax and the \k{name} + .NET syntax, and the Oniguruma \g<...> and \g'...' subroutine syntax. */ + + NAMED_REF_OR_RECURSE: + name = ++ptr; + if (IS_DIGIT(*ptr)) + { + *errorcodeptr = ERR84; /* Group name must start with non-digit */ + goto FAILED; + } + while (MAX_255(*ptr) && (cd->ctypes[*ptr] & ctype_word) != 0) ptr++; + namelen = (int)(ptr - name); + + /* In the pre-compile phase, do a syntax check. We used to just set + a dummy reference number, because it was not used in the first pass. + However, with the change of recursive back references to be atomic, + we have to look for the number so that this state can be identified, as + otherwise the incorrect length is computed. If it's not a backwards + reference, the dummy number will do. */ + + if (lengthptr != NULL) + { + named_group *ng; + + if (namelen == 0) + { + *errorcodeptr = ERR62; + goto FAILED; + } + if (*ptr != (pcre_uchar)terminator) + { + *errorcodeptr = ERR42; + goto FAILED; + } + if (namelen > MAX_NAME_SIZE) + { + *errorcodeptr = ERR48; + goto FAILED; + } + + /* The name table does not exist in the first pass; instead we must + scan the list of names encountered so far in order to get the + number. If the name is not found, set the value to 0 for a forward + reference. */ + + ng = cd->named_groups; + for (i = 0; i < cd->names_found; i++, ng++) + { + if (namelen == ng->length && + STRNCMP_UC_UC(name, ng->name, namelen) == 0) + break; + } + recno = (i < cd->names_found)? ng->number : 0; + + /* Count named back references. */ + + if (!is_recurse) cd->namedrefcount++; + } + + /* In the real compile, search the name table. We check the name + first, and then check that we have reached the end of the name in the + table. That way, if the name is longer than any in the table, the + comparison will fail without reading beyond the table entry. */ + + else + { + slot = cd->name_table; + for (i = 0; i < cd->names_found; i++) + { + if (STRNCMP_UC_UC(name, slot+IMM2_SIZE, namelen) == 0 && + slot[IMM2_SIZE+namelen] == 0) + break; + slot += cd->name_entry_size; + } + + if (i < cd->names_found) + { + recno = GET2(slot, 0); + } + else + { + *errorcodeptr = ERR15; + goto FAILED; + } + } + + /* In both phases, for recursions, we can now go to the code than + handles numerical recursion. */ + + if (is_recurse) goto HANDLE_RECURSION; + + /* In the second pass we must see if the name is duplicated. If so, we + generate a different opcode. */ + + if (lengthptr == NULL && cd->dupnames) + { + int count = 1; + unsigned int index = i; + pcre_uchar *cslot = slot + cd->name_entry_size; + + for (i++; i < cd->names_found; i++) + { + if (STRCMP_UC_UC(slot + IMM2_SIZE, cslot + IMM2_SIZE) != 0) break; + count++; + cslot += cd->name_entry_size; + } + + if (count > 1) + { + if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; + previous = code; + *code++ = ((options & PCRE_CASELESS) != 0)? OP_DNREFI : OP_DNREF; + PUT2INC(code, 0, index); + PUT2INC(code, 0, count); + + /* Process each potentially referenced group. */ + + for (; slot < cslot; slot += cd->name_entry_size) + { + open_capitem *oc; + recno = GET2(slot, 0); + cd->backref_map |= (recno < 32)? (1 << recno) : 1; + if (recno > cd->top_backref) cd->top_backref = recno; + + /* Check to see if this back reference is recursive, that it, it + is inside the group that it references. A flag is set so that the + group can be made atomic. */ + + for (oc = cd->open_caps; oc != NULL; oc = oc->next) + { + if (oc->number == recno) + { + oc->flag = TRUE; + break; + } + } + } + + continue; /* End of back ref handling */ + } + } + + /* First pass, or a non-duplicated name. */ + + goto HANDLE_REFERENCE; + + + /* ------------------------------------------------------------ */ + case CHAR_R: /* Recursion */ + ptr++; /* Same as (?0) */ + /* Fall through */ + + + /* ------------------------------------------------------------ */ + case CHAR_MINUS: case CHAR_PLUS: /* Recursion or subroutine */ + case CHAR_0: case CHAR_1: case CHAR_2: case CHAR_3: case CHAR_4: + case CHAR_5: case CHAR_6: case CHAR_7: case CHAR_8: case CHAR_9: + { + const pcre_uchar *called; + terminator = CHAR_RIGHT_PARENTHESIS; + + /* Come here from the \g<...> and \g'...' code (Oniguruma + compatibility). However, the syntax has been checked to ensure that + the ... are a (signed) number, so that neither ERR63 nor ERR29 will + be called on this path, nor with the jump to OTHER_CHAR_AFTER_QUERY + ever be taken. */ + + HANDLE_NUMERICAL_RECURSION: + + if ((refsign = *ptr) == CHAR_PLUS) + { + ptr++; + if (!IS_DIGIT(*ptr)) + { + *errorcodeptr = ERR63; + goto FAILED; + } + } + else if (refsign == CHAR_MINUS) + { + if (!IS_DIGIT(ptr[1])) + goto OTHER_CHAR_AFTER_QUERY; + ptr++; + } + + recno = 0; + while(IS_DIGIT(*ptr)) + recno = recno * 10 + *ptr++ - CHAR_0; + + if (*ptr != (pcre_uchar)terminator) + { + *errorcodeptr = ERR29; + goto FAILED; + } + + if (refsign == CHAR_MINUS) + { + if (recno == 0) + { + *errorcodeptr = ERR58; + goto FAILED; + } + recno = cd->bracount - recno + 1; + if (recno <= 0) + { + *errorcodeptr = ERR15; + goto FAILED; + } + } + else if (refsign == CHAR_PLUS) + { + if (recno == 0) + { + *errorcodeptr = ERR58; + goto FAILED; + } + recno += cd->bracount; + } + + /* Come here from code above that handles a named recursion */ + + HANDLE_RECURSION: + + previous = code; + called = cd->start_code; + + /* When we are actually compiling, find the bracket that is being + referenced. Temporarily end the regex in case it doesn't exist before + this point. If we end up with a forward reference, first check that + the bracket does occur later so we can give the error (and position) + now. Then remember this forward reference in the workspace so it can + be filled in at the end. */ + + if (lengthptr == NULL) + { + *code = OP_END; + if (recno != 0) + called = PRIV(find_bracket)(cd->start_code, utf, recno); + + /* Forward reference */ + + if (called == NULL) + { + if (recno > cd->final_bracount) + { + *errorcodeptr = ERR15; + goto FAILED; + } + + /* Fudge the value of "called" so that when it is inserted as an + offset below, what it actually inserted is the reference number + of the group. Then remember the forward reference. */ + + called = cd->start_code + recno; + if (cd->hwm >= cd->start_workspace + cd->workspace_size - + WORK_SIZE_SAFETY_MARGIN) + { + *errorcodeptr = expand_workspace(cd); + if (*errorcodeptr != 0) goto FAILED; + } + PUTINC(cd->hwm, 0, (int)(code + 1 - cd->start_code)); + } + + /* If not a forward reference, and the subpattern is still open, + this is a recursive call. We check to see if this is a left + recursion that could loop for ever, and diagnose that case. We + must not, however, do this check if we are in a conditional + subpattern because the condition might be testing for recursion in + a pattern such as /(?(R)a+|(?R)b)/, which is perfectly valid. + Forever loops are also detected at runtime, so those that occur in + conditional subpatterns will be picked up then. */ + + else if (GET(called, 1) == 0 && cond_depth <= 0 && + could_be_empty(called, code, bcptr, utf, cd)) + { + *errorcodeptr = ERR40; + goto FAILED; + } + } + + /* Insert the recursion/subroutine item. It does not have a set first + character (relevant if it is repeated, because it will then be + wrapped with ONCE brackets). */ + + *code = OP_RECURSE; + PUT(code, 1, (int)(called - cd->start_code)); + code += 1 + LINK_SIZE; + groupsetfirstchar = FALSE; + } + + /* Can't determine a first byte now */ + + if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; + continue; + + + /* ------------------------------------------------------------ */ + default: /* Other characters: check option setting */ + OTHER_CHAR_AFTER_QUERY: + set = unset = 0; + optset = &set; + + while (*ptr != CHAR_RIGHT_PARENTHESIS && *ptr != CHAR_COLON) + { + switch (*ptr++) + { + case CHAR_MINUS: optset = &unset; break; + + case CHAR_J: /* Record that it changed in the external options */ + *optset |= PCRE_DUPNAMES; + cd->external_flags |= PCRE_JCHANGED; + break; + + case CHAR_i: *optset |= PCRE_CASELESS; break; + case CHAR_m: *optset |= PCRE_MULTILINE; break; + case CHAR_s: *optset |= PCRE_DOTALL; break; + case CHAR_x: *optset |= PCRE_EXTENDED; break; + case CHAR_U: *optset |= PCRE_UNGREEDY; break; + case CHAR_X: *optset |= PCRE_EXTRA; break; + + default: *errorcodeptr = ERR12; + ptr--; /* Correct the offset */ + goto FAILED; + } + } + + /* Set up the changed option bits, but don't change anything yet. */ + + newoptions = (options | set) & (~unset); + + /* If the options ended with ')' this is not the start of a nested + group with option changes, so the options change at this level. If this + item is right at the start of the pattern, the options can be + abstracted and made external in the pre-compile phase, and ignored in + the compile phase. This can be helpful when matching -- for instance in + caseless checking of required bytes. + + If the code pointer is not (cd->start_code + 1 + LINK_SIZE), we are + definitely *not* at the start of the pattern because something has been + compiled. In the pre-compile phase, however, the code pointer can have + that value after the start, because it gets reset as code is discarded + during the pre-compile. However, this can happen only at top level - if + we are within parentheses, the starting BRA will still be present. At + any parenthesis level, the length value can be used to test if anything + has been compiled at that level. Thus, a test for both these conditions + is necessary to ensure we correctly detect the start of the pattern in + both phases. + + If we are not at the pattern start, reset the greedy defaults and the + case value for firstchar and reqchar. */ + + if (*ptr == CHAR_RIGHT_PARENTHESIS) + { + if (code == cd->start_code + 1 + LINK_SIZE && + (lengthptr == NULL || *lengthptr == 2 + 2*LINK_SIZE)) + { + cd->external_options = newoptions; + } + else + { + greedy_default = ((newoptions & PCRE_UNGREEDY) != 0); + greedy_non_default = greedy_default ^ 1; + req_caseopt = ((newoptions & PCRE_CASELESS) != 0)? REQ_CASELESS:0; + } + + /* Change options at this level, and pass them back for use + in subsequent branches. */ + + *optionsptr = options = newoptions; + previous = NULL; /* This item can't be repeated */ + continue; /* It is complete */ + } + + /* If the options ended with ':' we are heading into a nested group + with possible change of options. Such groups are non-capturing and are + not assertions of any kind. All we need to do is skip over the ':'; + the newoptions value is handled below. */ + + bravalue = OP_BRA; + ptr++; + } /* End of switch for character following (? */ + } /* End of (? handling */ + + /* Opening parenthesis not followed by '*' or '?'. If PCRE_NO_AUTO_CAPTURE + is set, all unadorned brackets become non-capturing and behave like (?:...) + brackets. */ + + else if ((options & PCRE_NO_AUTO_CAPTURE) != 0) + { + bravalue = OP_BRA; + } + + /* Else we have a capturing group. */ + + else + { + NUMBERED_GROUP: + cd->bracount += 1; + PUT2(code, 1+LINK_SIZE, cd->bracount); + skipbytes = IMM2_SIZE; + } + + /* Process nested bracketed regex. First check for parentheses nested too + deeply. */ + + if ((cd->parens_depth += 1) > PARENS_NEST_LIMIT) + { + *errorcodeptr = ERR82; + goto FAILED; + } + + /* Assertions used not to be repeatable, but this was changed for Perl + compatibility, so all kinds can now be repeated. We copy code into a + non-register variable (tempcode) in order to be able to pass its address + because some compilers complain otherwise. */ + + previous = code; /* For handling repetition */ + *code = bravalue; + tempcode = code; + tempreqvary = cd->req_varyopt; /* Save value before bracket */ + tempbracount = cd->bracount; /* Save value before bracket */ + length_prevgroup = 0; /* Initialize for pre-compile phase */ + + if (!compile_regex( + newoptions, /* The complete new option state */ + &tempcode, /* Where to put code (updated) */ + &ptr, /* Input pointer (updated) */ + errorcodeptr, /* Where to put an error message */ + (bravalue == OP_ASSERTBACK || + bravalue == OP_ASSERTBACK_NOT), /* TRUE if back assert */ + reset_bracount, /* True if (?| group */ + skipbytes, /* Skip over bracket number */ + cond_depth + + ((bravalue == OP_COND)?1:0), /* Depth of condition subpatterns */ + &subfirstchar, /* For possible first char */ + &subfirstcharflags, + &subreqchar, /* For possible last char */ + &subreqcharflags, + bcptr, /* Current branch chain */ + cd, /* Tables block */ + (lengthptr == NULL)? NULL : /* Actual compile phase */ + &length_prevgroup /* Pre-compile phase */ + )) + goto FAILED; + + cd->parens_depth -= 1; + + /* If this was an atomic group and there are no capturing groups within it, + generate OP_ONCE_NC instead of OP_ONCE. */ + + if (bravalue == OP_ONCE && cd->bracount <= tempbracount) + *code = OP_ONCE_NC; + + if (bravalue >= OP_ASSERT && bravalue <= OP_ASSERTBACK_NOT) + cd->assert_depth -= 1; + + /* At the end of compiling, code is still pointing to the start of the + group, while tempcode has been updated to point past the end of the group. + The pattern pointer (ptr) is on the bracket. + + If this is a conditional bracket, check that there are no more than + two branches in the group, or just one if it's a DEFINE group. We do this + in the real compile phase, not in the pre-pass, where the whole group may + not be available. */ + + if (bravalue == OP_COND && lengthptr == NULL) + { + pcre_uchar *tc = code; + int condcount = 0; + + do { + condcount++; + tc += GET(tc,1); + } + while (*tc != OP_KET); + + /* A DEFINE group is never obeyed inline (the "condition" is always + false). It must have only one branch. */ + + if (code[LINK_SIZE+1] == OP_DEF) + { + if (condcount > 1) + { + *errorcodeptr = ERR54; + goto FAILED; + } + bravalue = OP_DEF; /* Just a flag to suppress char handling below */ + } + + /* A "normal" conditional group. If there is just one branch, we must not + make use of its firstchar or reqchar, because this is equivalent to an + empty second branch. */ + + else + { + if (condcount > 2) + { + *errorcodeptr = ERR27; + goto FAILED; + } + if (condcount == 1) subfirstcharflags = subreqcharflags = REQ_NONE; + } + } + + /* Error if hit end of pattern */ + + if (*ptr != CHAR_RIGHT_PARENTHESIS) + { + *errorcodeptr = ERR14; + goto FAILED; + } + + /* In the pre-compile phase, update the length by the length of the group, + less the brackets at either end. Then reduce the compiled code to just a + set of non-capturing brackets so that it doesn't use much memory if it is + duplicated by a quantifier.*/ + + if (lengthptr != NULL) + { + if (OFLOW_MAX - *lengthptr < length_prevgroup - 2 - 2*LINK_SIZE) + { + *errorcodeptr = ERR20; + goto FAILED; + } + *lengthptr += length_prevgroup - 2 - 2*LINK_SIZE; + code++; /* This already contains bravalue */ + PUTINC(code, 0, 1 + LINK_SIZE); + *code++ = OP_KET; + PUTINC(code, 0, 1 + LINK_SIZE); + break; /* No need to waste time with special character handling */ + } + + /* Otherwise update the main code pointer to the end of the group. */ + + code = tempcode; + + /* For a DEFINE group, required and first character settings are not + relevant. */ + + if (bravalue == OP_DEF) break; + + /* Handle updating of the required and first characters for other types of + group. Update for normal brackets of all kinds, and conditions with two + branches (see code above). If the bracket is followed by a quantifier with + zero repeat, we have to back off. Hence the definition of zeroreqchar and + zerofirstchar outside the main loop so that they can be accessed for the + back off. */ + + zeroreqchar = reqchar; + zeroreqcharflags = reqcharflags; + zerofirstchar = firstchar; + zerofirstcharflags = firstcharflags; + groupsetfirstchar = FALSE; + + if (bravalue >= OP_ONCE) + { + /* If we have not yet set a firstchar in this branch, take it from the + subpattern, remembering that it was set here so that a repeat of more + than one can replicate it as reqchar if necessary. If the subpattern has + no firstchar, set "none" for the whole branch. In both cases, a zero + repeat forces firstchar to "none". */ + + if (firstcharflags == REQ_UNSET) + { + if (subfirstcharflags >= 0) + { + firstchar = subfirstchar; + firstcharflags = subfirstcharflags; + groupsetfirstchar = TRUE; + } + else firstcharflags = REQ_NONE; + zerofirstcharflags = REQ_NONE; + } + + /* If firstchar was previously set, convert the subpattern's firstchar + into reqchar if there wasn't one, using the vary flag that was in + existence beforehand. */ + + else if (subfirstcharflags >= 0 && subreqcharflags < 0) + { + subreqchar = subfirstchar; + subreqcharflags = subfirstcharflags | tempreqvary; + } + + /* If the subpattern set a required byte (or set a first byte that isn't + really the first byte - see above), set it. */ + + if (subreqcharflags >= 0) + { + reqchar = subreqchar; + reqcharflags = subreqcharflags; + } + } + + /* For a forward assertion, we take the reqchar, if set. This can be + helpful if the pattern that follows the assertion doesn't set a different + char. For example, it's useful for /(?=abcde).+/. We can't set firstchar + for an assertion, however because it leads to incorrect effect for patterns + such as /(?=a)a.+/ when the "real" "a" would then become a reqchar instead + of a firstchar. This is overcome by a scan at the end if there's no + firstchar, looking for an asserted first char. */ + + else if (bravalue == OP_ASSERT && subreqcharflags >= 0) + { + reqchar = subreqchar; + reqcharflags = subreqcharflags; + } + break; /* End of processing '(' */ + + + /* ===================================================================*/ + /* Handle metasequences introduced by \. For ones like \d, the ESC_ values + are arranged to be the negation of the corresponding OP_values in the + default case when PCRE_UCP is not set. For the back references, the values + are negative the reference number. Only back references and those types + that consume a character may be repeated. We can test for values between + ESC_b and ESC_Z for the latter; this may have to change if any new ones are + ever created. */ + + case CHAR_BACKSLASH: + tempptr = ptr; + escape = check_escape(&ptr, &ec, errorcodeptr, cd->bracount, options, FALSE); + if (*errorcodeptr != 0) goto FAILED; + + if (escape == 0) /* The escape coded a single character */ + c = ec; + else + { + if (escape == ESC_Q) /* Handle start of quoted string */ + { + if (ptr[1] == CHAR_BACKSLASH && ptr[2] == CHAR_E) + ptr += 2; /* avoid empty string */ + else inescq = TRUE; + continue; + } + + if (escape == ESC_E) continue; /* Perl ignores an orphan \E */ + + /* For metasequences that actually match a character, we disable the + setting of a first character if it hasn't already been set. */ + + if (firstcharflags == REQ_UNSET && escape > ESC_b && escape < ESC_Z) + firstcharflags = REQ_NONE; + + /* Set values to reset to if this is followed by a zero repeat. */ + + zerofirstchar = firstchar; + zerofirstcharflags = firstcharflags; + zeroreqchar = reqchar; + zeroreqcharflags = reqcharflags; + + /* \g<name> or \g'name' is a subroutine call by name and \g<n> or \g'n' + is a subroutine call by number (Oniguruma syntax). In fact, the value + ESC_g is returned only for these cases. So we don't need to check for < + or ' if the value is ESC_g. For the Perl syntax \g{n} the value is + -n, and for the Perl syntax \g{name} the result is ESC_k (as + that is a synonym for a named back reference). */ + + if (escape == ESC_g) + { + const pcre_uchar *p; + pcre_uint32 cf; + + save_hwm = cd->hwm; /* Normally this is set when '(' is read */ + terminator = (*(++ptr) == CHAR_LESS_THAN_SIGN)? + CHAR_GREATER_THAN_SIGN : CHAR_APOSTROPHE; + + /* These two statements stop the compiler for warning about possibly + unset variables caused by the jump to HANDLE_NUMERICAL_RECURSION. In + fact, because we do the check for a number below, the paths that + would actually be in error are never taken. */ + + skipbytes = 0; + reset_bracount = FALSE; + + /* If it's not a signed or unsigned number, treat it as a name. */ + + cf = ptr[1]; + if (cf != CHAR_PLUS && cf != CHAR_MINUS && !IS_DIGIT(cf)) + { + is_recurse = TRUE; + goto NAMED_REF_OR_RECURSE; + } + + /* Signed or unsigned number (cf = ptr[1]) is known to be plus or minus + or a digit. */ + + p = ptr + 2; + while (IS_DIGIT(*p)) p++; + if (*p != (pcre_uchar)terminator) + { + *errorcodeptr = ERR57; + break; + } + ptr++; + goto HANDLE_NUMERICAL_RECURSION; + } + + /* \k<name> or \k'name' is a back reference by name (Perl syntax). + We also support \k{name} (.NET syntax). */ + + if (escape == ESC_k) + { + if ((ptr[1] != CHAR_LESS_THAN_SIGN && + ptr[1] != CHAR_APOSTROPHE && ptr[1] != CHAR_LEFT_CURLY_BRACKET)) + { + *errorcodeptr = ERR69; + break; + } + is_recurse = FALSE; + terminator = (*(++ptr) == CHAR_LESS_THAN_SIGN)? + CHAR_GREATER_THAN_SIGN : (*ptr == CHAR_APOSTROPHE)? + CHAR_APOSTROPHE : CHAR_RIGHT_CURLY_BRACKET; + goto NAMED_REF_OR_RECURSE; + } + + /* Back references are handled specially; must disable firstchar if + not set to cope with cases like (?=(\w+))\1: which would otherwise set + ':' later. */ + + if (escape < 0) + { + open_capitem *oc; + recno = -escape; + + /* Come here from named backref handling when the reference is to a + single group (i.e. not to a duplicated name. */ + + HANDLE_REFERENCE: + if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; + previous = code; + *code++ = ((options & PCRE_CASELESS) != 0)? OP_REFI : OP_REF; + PUT2INC(code, 0, recno); + cd->backref_map |= (recno < 32)? (1 << recno) : 1; + if (recno > cd->top_backref) cd->top_backref = recno; + + /* Check to see if this back reference is recursive, that it, it + is inside the group that it references. A flag is set so that the + group can be made atomic. */ + + for (oc = cd->open_caps; oc != NULL; oc = oc->next) + { + if (oc->number == recno) + { + oc->flag = TRUE; + break; + } + } + } + + /* So are Unicode property matches, if supported. */ + +#ifdef SUPPORT_UCP + else if (escape == ESC_P || escape == ESC_p) + { + BOOL negated; + unsigned int ptype = 0, pdata = 0; + if (!get_ucp(&ptr, &negated, &ptype, &pdata, errorcodeptr)) + goto FAILED; + previous = code; + *code++ = ((escape == ESC_p) != negated)? OP_PROP : OP_NOTPROP; + *code++ = ptype; + *code++ = pdata; + } +#else + + /* If Unicode properties are not supported, \X, \P, and \p are not + allowed. */ + + else if (escape == ESC_X || escape == ESC_P || escape == ESC_p) + { + *errorcodeptr = ERR45; + goto FAILED; + } +#endif + + /* For the rest (including \X when Unicode properties are supported), we + can obtain the OP value by negating the escape value in the default + situation when PCRE_UCP is not set. When it *is* set, we substitute + Unicode property tests. Note that \b and \B do a one-character + lookbehind, and \A also behaves as if it does. */ + + else + { + if ((escape == ESC_b || escape == ESC_B || escape == ESC_A) && + cd->max_lookbehind == 0) + cd->max_lookbehind = 1; +#ifdef SUPPORT_UCP + if (escape >= ESC_DU && escape <= ESC_wu) + { + nestptr = ptr + 1; /* Where to resume */ + ptr = substitutes[escape - ESC_DU] - 1; /* Just before substitute */ + } + else +#endif + /* In non-UTF-8 mode, we turn \C into OP_ALLANY instead of OP_ANYBYTE + so that it works in DFA mode and in lookbehinds. */ + + { + previous = (escape > ESC_b && escape < ESC_Z)? code : NULL; + *code++ = (!utf && escape == ESC_C)? OP_ALLANY : escape; + } + } + continue; + } + + /* We have a data character whose value is in c. In UTF-8 mode it may have + a value > 127. We set its representation in the length/buffer, and then + handle it as a data character. */ + +#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 + if (utf && c > MAX_VALUE_FOR_SINGLE_CHAR) + mclength = PRIV(ord2utf)(c, mcbuffer); + else +#endif + + { + mcbuffer[0] = c; + mclength = 1; + } + goto ONE_CHAR; + + + /* ===================================================================*/ + /* Handle a literal character. It is guaranteed not to be whitespace or # + when the extended flag is set. If we are in a UTF mode, it may be a + multi-unit literal character. */ + + default: + NORMAL_CHAR: + mclength = 1; + mcbuffer[0] = c; + +#ifdef SUPPORT_UTF + if (utf && HAS_EXTRALEN(c)) + ACROSSCHAR(TRUE, ptr[1], mcbuffer[mclength++] = *(++ptr)); +#endif + + /* At this point we have the character's bytes in mcbuffer, and the length + in mclength. When not in UTF-8 mode, the length is always 1. */ + + ONE_CHAR: + previous = code; + + /* For caseless UTF-8 mode when UCP support is available, check whether + this character has more than one other case. If so, generate a special + OP_PROP item instead of OP_CHARI. */ + +#ifdef SUPPORT_UCP + if (utf && (options & PCRE_CASELESS) != 0) + { + GETCHAR(c, mcbuffer); + if ((c = UCD_CASESET(c)) != 0) + { + *code++ = OP_PROP; + *code++ = PT_CLIST; + *code++ = c; + if (firstcharflags == REQ_UNSET) + firstcharflags = zerofirstcharflags = REQ_NONE; + break; + } + } +#endif + + /* Caseful matches, or not one of the multicase characters. */ + + *code++ = ((options & PCRE_CASELESS) != 0)? OP_CHARI : OP_CHAR; + for (c = 0; c < mclength; c++) *code++ = mcbuffer[c]; + + /* Remember if \r or \n were seen */ + + if (mcbuffer[0] == CHAR_CR || mcbuffer[0] == CHAR_NL) + cd->external_flags |= PCRE_HASCRORLF; + + /* Set the first and required bytes appropriately. If no previous first + byte, set it from this character, but revert to none on a zero repeat. + Otherwise, leave the firstchar value alone, and don't change it on a zero + repeat. */ + + if (firstcharflags == REQ_UNSET) + { + zerofirstcharflags = REQ_NONE; + zeroreqchar = reqchar; + zeroreqcharflags = reqcharflags; + + /* If the character is more than one byte long, we can set firstchar + only if it is not to be matched caselessly. */ + + if (mclength == 1 || req_caseopt == 0) + { + firstchar = mcbuffer[0] | req_caseopt; + firstchar = mcbuffer[0]; + firstcharflags = req_caseopt; + + if (mclength != 1) + { + reqchar = code[-1]; + reqcharflags = cd->req_varyopt; + } + } + else firstcharflags = reqcharflags = REQ_NONE; + } + + /* firstchar was previously set; we can set reqchar only if the length is + 1 or the matching is caseful. */ + + else + { + zerofirstchar = firstchar; + zerofirstcharflags = firstcharflags; + zeroreqchar = reqchar; + zeroreqcharflags = reqcharflags; + if (mclength == 1 || req_caseopt == 0) + { + reqchar = code[-1]; + reqcharflags = req_caseopt | cd->req_varyopt; + } + } + + break; /* End of literal character handling */ + } + } /* end of big loop */ + + +/* Control never reaches here by falling through, only by a goto for all the +error states. Pass back the position in the pattern so that it can be displayed +to the user for diagnosing the error. */ + +FAILED: +*ptrptr = ptr; +return FALSE; +} + + + +/************************************************* +* Compile sequence of alternatives * +*************************************************/ + +/* On entry, ptr is pointing past the bracket character, but on return it +points to the closing bracket, or vertical bar, or end of string. The code +variable is pointing at the byte into which the BRA operator has been stored. +This function is used during the pre-compile phase when we are trying to find +out the amount of memory needed, as well as during the real compile phase. The +value of lengthptr distinguishes the two phases. + +Arguments: + options option bits, including any changes for this subpattern + codeptr -> the address of the current code pointer + ptrptr -> the address of the current pattern pointer + errorcodeptr -> pointer to error code variable + lookbehind TRUE if this is a lookbehind assertion + reset_bracount TRUE to reset the count for each branch + skipbytes skip this many bytes at start (for brackets and OP_COND) + cond_depth depth of nesting for conditional subpatterns + firstcharptr place to put the first required character + firstcharflagsptr place to put the first character flags, or a negative number + reqcharptr place to put the last required character + reqcharflagsptr place to put the last required character flags, or a negative number + bcptr pointer to the chain of currently open branches + cd points to the data block with tables pointers etc. + lengthptr NULL during the real compile phase + points to length accumulator during pre-compile phase + +Returns: TRUE on success +*/ + +static BOOL +compile_regex(int options, pcre_uchar **codeptr, const pcre_uchar **ptrptr, + int *errorcodeptr, BOOL lookbehind, BOOL reset_bracount, int skipbytes, + int cond_depth, + pcre_uint32 *firstcharptr, pcre_int32 *firstcharflagsptr, + pcre_uint32 *reqcharptr, pcre_int32 *reqcharflagsptr, + branch_chain *bcptr, compile_data *cd, int *lengthptr) +{ +const pcre_uchar *ptr = *ptrptr; +pcre_uchar *code = *codeptr; +pcre_uchar *last_branch = code; +pcre_uchar *start_bracket = code; +pcre_uchar *reverse_count = NULL; +open_capitem capitem; +int capnumber = 0; +pcre_uint32 firstchar, reqchar; +pcre_int32 firstcharflags, reqcharflags; +pcre_uint32 branchfirstchar, branchreqchar; +pcre_int32 branchfirstcharflags, branchreqcharflags; +int length; +unsigned int orig_bracount; +unsigned int max_bracount; +branch_chain bc; + +/* If set, call the external function that checks for stack availability. */ + +if (PUBL(stack_guard) != NULL && PUBL(stack_guard)()) + { + *errorcodeptr= ERR85; + return FALSE; + } + +/* Miscellaneous initialization */ + +bc.outer = bcptr; +bc.current_branch = code; + +firstchar = reqchar = 0; +firstcharflags = reqcharflags = REQ_UNSET; + +/* Accumulate the length for use in the pre-compile phase. Start with the +length of the BRA and KET and any extra bytes that are required at the +beginning. We accumulate in a local variable to save frequent testing of +lenthptr for NULL. We cannot do this by looking at the value of code at the +start and end of each alternative, because compiled items are discarded during +the pre-compile phase so that the work space is not exceeded. */ + +length = 2 + 2*LINK_SIZE + skipbytes; + +/* WARNING: If the above line is changed for any reason, you must also change +the code that abstracts option settings at the start of the pattern and makes +them global. It tests the value of length for (2 + 2*LINK_SIZE) in the +pre-compile phase to find out whether anything has yet been compiled or not. */ + +/* If this is a capturing subpattern, add to the chain of open capturing items +so that we can detect them if (*ACCEPT) is encountered. This is also used to +detect groups that contain recursive back references to themselves. Note that +only OP_CBRA need be tested here; changing this opcode to one of its variants, +e.g. OP_SCBRAPOS, happens later, after the group has been compiled. */ + +if (*code == OP_CBRA) + { + capnumber = GET2(code, 1 + LINK_SIZE); + capitem.number = capnumber; + capitem.next = cd->open_caps; + capitem.flag = FALSE; + cd->open_caps = &capitem; + } + +/* Offset is set zero to mark that this bracket is still open */ + +PUT(code, 1, 0); +code += 1 + LINK_SIZE + skipbytes; + +/* Loop for each alternative branch */ + +orig_bracount = max_bracount = cd->bracount; +for (;;) + { + /* For a (?| group, reset the capturing bracket count so that each branch + uses the same numbers. */ + + if (reset_bracount) cd->bracount = orig_bracount; + + /* Set up dummy OP_REVERSE if lookbehind assertion */ + + if (lookbehind) + { + *code++ = OP_REVERSE; + reverse_count = code; + PUTINC(code, 0, 0); + length += 1 + LINK_SIZE; + } + + /* Now compile the branch; in the pre-compile phase its length gets added + into the length. */ + + if (!compile_branch(&options, &code, &ptr, errorcodeptr, &branchfirstchar, + &branchfirstcharflags, &branchreqchar, &branchreqcharflags, &bc, + cond_depth, cd, (lengthptr == NULL)? NULL : &length)) + { + *ptrptr = ptr; + return FALSE; + } + + /* Keep the highest bracket count in case (?| was used and some branch + has fewer than the rest. */ + + if (cd->bracount > max_bracount) max_bracount = cd->bracount; + + /* In the real compile phase, there is some post-processing to be done. */ + + if (lengthptr == NULL) + { + /* If this is the first branch, the firstchar and reqchar values for the + branch become the values for the regex. */ + + if (*last_branch != OP_ALT) + { + firstchar = branchfirstchar; + firstcharflags = branchfirstcharflags; + reqchar = branchreqchar; + reqcharflags = branchreqcharflags; + } + + /* If this is not the first branch, the first char and reqchar have to + match the values from all the previous branches, except that if the + previous value for reqchar didn't have REQ_VARY set, it can still match, + and we set REQ_VARY for the regex. */ + + else + { + /* If we previously had a firstchar, but it doesn't match the new branch, + we have to abandon the firstchar for the regex, but if there was + previously no reqchar, it takes on the value of the old firstchar. */ + + if (firstcharflags >= 0 && + (firstcharflags != branchfirstcharflags || firstchar != branchfirstchar)) + { + if (reqcharflags < 0) + { + reqchar = firstchar; + reqcharflags = firstcharflags; + } + firstcharflags = REQ_NONE; + } + + /* If we (now or from before) have no firstchar, a firstchar from the + branch becomes a reqchar if there isn't a branch reqchar. */ + + if (firstcharflags < 0 && branchfirstcharflags >= 0 && branchreqcharflags < 0) + { + branchreqchar = branchfirstchar; + branchreqcharflags = branchfirstcharflags; + } + + /* Now ensure that the reqchars match */ + + if (((reqcharflags & ~REQ_VARY) != (branchreqcharflags & ~REQ_VARY)) || + reqchar != branchreqchar) + reqcharflags = REQ_NONE; + else + { + reqchar = branchreqchar; + reqcharflags |= branchreqcharflags; /* To "or" REQ_VARY */ + } + } + + /* If lookbehind, check that this branch matches a fixed-length string, and + put the length into the OP_REVERSE item. Temporarily mark the end of the + branch with OP_END. If the branch contains OP_RECURSE, the result is -3 + because there may be forward references that we can't check here. Set a + flag to cause another lookbehind check at the end. Why not do it all at the + end? Because common, erroneous checks are picked up here and the offset of + the problem can be shown. */ + + if (lookbehind) + { + int fixed_length; + *code = OP_END; + fixed_length = find_fixedlength(last_branch, (options & PCRE_UTF8) != 0, + FALSE, cd); + DPRINTF(("fixed length = %d\n", fixed_length)); + if (fixed_length == -3) + { + cd->check_lookbehind = TRUE; + } + else if (fixed_length < 0) + { + *errorcodeptr = (fixed_length == -2)? ERR36 : + (fixed_length == -4)? ERR70: ERR25; + *ptrptr = ptr; + return FALSE; + } + else + { + if (fixed_length > cd->max_lookbehind) + cd->max_lookbehind = fixed_length; + PUT(reverse_count, 0, fixed_length); + } + } + } + + /* Reached end of expression, either ')' or end of pattern. In the real + compile phase, go back through the alternative branches and reverse the chain + of offsets, with the field in the BRA item now becoming an offset to the + first alternative. If there are no alternatives, it points to the end of the + group. The length in the terminating ket is always the length of the whole + bracketed item. Return leaving the pointer at the terminating char. */ + + if (*ptr != CHAR_VERTICAL_LINE) + { + if (lengthptr == NULL) + { + int branch_length = (int)(code - last_branch); + do + { + int prev_length = GET(last_branch, 1); + PUT(last_branch, 1, branch_length); + branch_length = prev_length; + last_branch -= branch_length; + } + while (branch_length > 0); + } + + /* Fill in the ket */ + + *code = OP_KET; + PUT(code, 1, (int)(code - start_bracket)); + code += 1 + LINK_SIZE; + + /* If it was a capturing subpattern, check to see if it contained any + recursive back references. If so, we must wrap it in atomic brackets. + In any event, remove the block from the chain. */ + + if (capnumber > 0) + { + if (cd->open_caps->flag) + { + memmove(start_bracket + 1 + LINK_SIZE, start_bracket, + IN_UCHARS(code - start_bracket)); + *start_bracket = OP_ONCE; + code += 1 + LINK_SIZE; + PUT(start_bracket, 1, (int)(code - start_bracket)); + *code = OP_KET; + PUT(code, 1, (int)(code - start_bracket)); + code += 1 + LINK_SIZE; + length += 2 + 2*LINK_SIZE; + } + cd->open_caps = cd->open_caps->next; + } + + /* Retain the highest bracket number, in case resetting was used. */ + + cd->bracount = max_bracount; + + /* Set values to pass back */ + + *codeptr = code; + *ptrptr = ptr; + *firstcharptr = firstchar; + *firstcharflagsptr = firstcharflags; + *reqcharptr = reqchar; + *reqcharflagsptr = reqcharflags; + if (lengthptr != NULL) + { + if (OFLOW_MAX - *lengthptr < length) + { + *errorcodeptr = ERR20; + return FALSE; + } + *lengthptr += length; + } + return TRUE; + } + + /* Another branch follows. In the pre-compile phase, we can move the code + pointer back to where it was for the start of the first branch. (That is, + pretend that each branch is the only one.) + + In the real compile phase, insert an ALT node. Its length field points back + to the previous branch while the bracket remains open. At the end the chain + is reversed. It's done like this so that the start of the bracket has a + zero offset until it is closed, making it possible to detect recursion. */ + + if (lengthptr != NULL) + { + code = *codeptr + 1 + LINK_SIZE + skipbytes; + length += 1 + LINK_SIZE; + } + else + { + *code = OP_ALT; + PUT(code, 1, (int)(code - last_branch)); + bc.current_branch = last_branch = code; + code += 1 + LINK_SIZE; + } + + ptr++; + } +/* Control never reaches here */ +} + + + + +/************************************************* +* Check for anchored expression * +*************************************************/ + +/* Try to find out if this is an anchored regular expression. Consider each +alternative branch. If they all start with OP_SOD or OP_CIRC, or with a bracket +all of whose alternatives start with OP_SOD or OP_CIRC (recurse ad lib), then +it's anchored. However, if this is a multiline pattern, then only OP_SOD will +be found, because ^ generates OP_CIRCM in that mode. + +We can also consider a regex to be anchored if OP_SOM starts all its branches. +This is the code for \G, which means "match at start of match position, taking +into account the match offset". + +A branch is also implicitly anchored if it starts with .* and DOTALL is set, +because that will try the rest of the pattern at all possible matching points, +so there is no point trying again.... er .... + +.... except when the .* appears inside capturing parentheses, and there is a +subsequent back reference to those parentheses. We haven't enough information +to catch that case precisely. + +At first, the best we could do was to detect when .* was in capturing brackets +and the highest back reference was greater than or equal to that level. +However, by keeping a bitmap of the first 31 back references, we can catch some +of the more common cases more precisely. + +... A second exception is when the .* appears inside an atomic group, because +this prevents the number of characters it matches from being adjusted. + +Arguments: + code points to start of expression (the bracket) + bracket_map a bitmap of which brackets we are inside while testing; this + handles up to substring 31; after that we just have to take + the less precise approach + cd points to the compile data block + atomcount atomic group level + +Returns: TRUE or FALSE +*/ + +static BOOL +is_anchored(register const pcre_uchar *code, unsigned int bracket_map, + compile_data *cd, int atomcount) +{ +do { + const pcre_uchar *scode = first_significant_code( + code + PRIV(OP_lengths)[*code], FALSE); + register int op = *scode; + + /* Non-capturing brackets */ + + if (op == OP_BRA || op == OP_BRAPOS || + op == OP_SBRA || op == OP_SBRAPOS) + { + if (!is_anchored(scode, bracket_map, cd, atomcount)) return FALSE; + } + + /* Capturing brackets */ + + else if (op == OP_CBRA || op == OP_CBRAPOS || + op == OP_SCBRA || op == OP_SCBRAPOS) + { + int n = GET2(scode, 1+LINK_SIZE); + int new_map = bracket_map | ((n < 32)? (1 << n) : 1); + if (!is_anchored(scode, new_map, cd, atomcount)) return FALSE; + } + + /* Positive forward assertions and conditions */ + + else if (op == OP_ASSERT || op == OP_COND) + { + if (!is_anchored(scode, bracket_map, cd, atomcount)) return FALSE; + } + + /* Atomic groups */ + + else if (op == OP_ONCE || op == OP_ONCE_NC) + { + if (!is_anchored(scode, bracket_map, cd, atomcount + 1)) + return FALSE; + } + + /* .* is not anchored unless DOTALL is set (which generates OP_ALLANY) and + it isn't in brackets that are or may be referenced or inside an atomic + group. */ + + else if ((op == OP_TYPESTAR || op == OP_TYPEMINSTAR || + op == OP_TYPEPOSSTAR)) + { + if (scode[1] != OP_ALLANY || (bracket_map & cd->backref_map) != 0 || + atomcount > 0 || cd->had_pruneorskip) + return FALSE; + } + + /* Check for explicit anchoring */ + + else if (op != OP_SOD && op != OP_SOM && op != OP_CIRC) return FALSE; + + code += GET(code, 1); + } +while (*code == OP_ALT); /* Loop for each alternative */ +return TRUE; +} + + + +/************************************************* +* Check for starting with ^ or .* * +*************************************************/ + +/* This is called to find out if every branch starts with ^ or .* so that +"first char" processing can be done to speed things up in multiline +matching and for non-DOTALL patterns that start with .* (which must start at +the beginning or after \n). As in the case of is_anchored() (see above), we +have to take account of back references to capturing brackets that contain .* +because in that case we can't make the assumption. Also, the appearance of .* +inside atomic brackets or in a pattern that contains *PRUNE or *SKIP does not +count, because once again the assumption no longer holds. + +Arguments: + code points to start of expression (the bracket) + bracket_map a bitmap of which brackets we are inside while testing; this + handles up to substring 31; after that we just have to take + the less precise approach + cd points to the compile data + atomcount atomic group level + +Returns: TRUE or FALSE +*/ + +static BOOL +is_startline(const pcre_uchar *code, unsigned int bracket_map, + compile_data *cd, int atomcount) +{ +do { + const pcre_uchar *scode = first_significant_code( + code + PRIV(OP_lengths)[*code], FALSE); + register int op = *scode; + + /* If we are at the start of a conditional assertion group, *both* the + conditional assertion *and* what follows the condition must satisfy the test + for start of line. Other kinds of condition fail. Note that there may be an + auto-callout at the start of a condition. */ + + if (op == OP_COND) + { + scode += 1 + LINK_SIZE; + if (*scode == OP_CALLOUT) scode += PRIV(OP_lengths)[OP_CALLOUT]; + switch (*scode) + { + case OP_CREF: + case OP_DNCREF: + case OP_RREF: + case OP_DNRREF: + case OP_DEF: + return FALSE; + + default: /* Assertion */ + if (!is_startline(scode, bracket_map, cd, atomcount)) return FALSE; + do scode += GET(scode, 1); while (*scode == OP_ALT); + scode += 1 + LINK_SIZE; + break; + } + scode = first_significant_code(scode, FALSE); + op = *scode; + } + + /* Non-capturing brackets */ + + if (op == OP_BRA || op == OP_BRAPOS || + op == OP_SBRA || op == OP_SBRAPOS) + { + if (!is_startline(scode, bracket_map, cd, atomcount)) return FALSE; + } + + /* Capturing brackets */ + + else if (op == OP_CBRA || op == OP_CBRAPOS || + op == OP_SCBRA || op == OP_SCBRAPOS) + { + int n = GET2(scode, 1+LINK_SIZE); + int new_map = bracket_map | ((n < 32)? (1 << n) : 1); + if (!is_startline(scode, new_map, cd, atomcount)) return FALSE; + } + + /* Positive forward assertions */ + + else if (op == OP_ASSERT) + { + if (!is_startline(scode, bracket_map, cd, atomcount)) return FALSE; + } + + /* Atomic brackets */ + + else if (op == OP_ONCE || op == OP_ONCE_NC) + { + if (!is_startline(scode, bracket_map, cd, atomcount + 1)) return FALSE; + } + + /* .* means "start at start or after \n" if it isn't in atomic brackets or + brackets that may be referenced, as long as the pattern does not contain + *PRUNE or *SKIP, because these break the feature. Consider, for example, + /.*?a(*PRUNE)b/ with the subject "aab", which matches "ab", i.e. not at the + start of a line. */ + + else if (op == OP_TYPESTAR || op == OP_TYPEMINSTAR || op == OP_TYPEPOSSTAR) + { + if (scode[1] != OP_ANY || (bracket_map & cd->backref_map) != 0 || + atomcount > 0 || cd->had_pruneorskip) + return FALSE; + } + + /* Check for explicit circumflex; anything else gives a FALSE result. Note + in particular that this includes atomic brackets OP_ONCE and OP_ONCE_NC + because the number of characters matched by .* cannot be adjusted inside + them. */ + + else if (op != OP_CIRC && op != OP_CIRCM) return FALSE; + + /* Move on to the next alternative */ + + code += GET(code, 1); + } +while (*code == OP_ALT); /* Loop for each alternative */ +return TRUE; +} + + + +/************************************************* +* Check for asserted fixed first char * +*************************************************/ + +/* During compilation, the "first char" settings from forward assertions are +discarded, because they can cause conflicts with actual literals that follow. +However, if we end up without a first char setting for an unanchored pattern, +it is worth scanning the regex to see if there is an initial asserted first +char. If all branches start with the same asserted char, or with a +non-conditional bracket all of whose alternatives start with the same asserted +char (recurse ad lib), then we return that char, with the flags set to zero or +REQ_CASELESS; otherwise return zero with REQ_NONE in the flags. + +Arguments: + code points to start of expression (the bracket) + flags points to the first char flags, or to REQ_NONE + inassert TRUE if in an assertion + +Returns: the fixed first char, or 0 with REQ_NONE in flags +*/ + +static pcre_uint32 +find_firstassertedchar(const pcre_uchar *code, pcre_int32 *flags, + BOOL inassert) +{ +register pcre_uint32 c = 0; +int cflags = REQ_NONE; + +*flags = REQ_NONE; +do { + pcre_uint32 d; + int dflags; + int xl = (*code == OP_CBRA || *code == OP_SCBRA || + *code == OP_CBRAPOS || *code == OP_SCBRAPOS)? IMM2_SIZE:0; + const pcre_uchar *scode = first_significant_code(code + 1+LINK_SIZE + xl, + TRUE); + register pcre_uchar op = *scode; + + switch(op) + { + default: + return 0; + + case OP_BRA: + case OP_BRAPOS: + case OP_CBRA: + case OP_SCBRA: + case OP_CBRAPOS: + case OP_SCBRAPOS: + case OP_ASSERT: + case OP_ONCE: + case OP_ONCE_NC: + d = find_firstassertedchar(scode, &dflags, op == OP_ASSERT); + if (dflags < 0) + return 0; + if (cflags < 0) { c = d; cflags = dflags; } else if (c != d || cflags != dflags) return 0; + break; + + case OP_EXACT: + scode += IMM2_SIZE; + /* Fall through */ + + case OP_CHAR: + case OP_PLUS: + case OP_MINPLUS: + case OP_POSPLUS: + if (!inassert) return 0; + if (cflags < 0) { c = scode[1]; cflags = 0; } + else if (c != scode[1]) return 0; + break; + + case OP_EXACTI: + scode += IMM2_SIZE; + /* Fall through */ + + case OP_CHARI: + case OP_PLUSI: + case OP_MINPLUSI: + case OP_POSPLUSI: + if (!inassert) return 0; + if (cflags < 0) { c = scode[1]; cflags = REQ_CASELESS; } + else if (c != scode[1]) return 0; + break; + } + + code += GET(code, 1); + } +while (*code == OP_ALT); + +*flags = cflags; +return c; +} + + + +/************************************************* +* Add an entry to the name/number table * +*************************************************/ + +/* This function is called between compiling passes to add an entry to the +name/number table, maintaining alphabetical order. Checking for permitted +and forbidden duplicates has already been done. + +Arguments: + cd the compile data block + name the name to add + length the length of the name + groupno the group number + +Returns: nothing +*/ + +static void +add_name(compile_data *cd, const pcre_uchar *name, int length, + unsigned int groupno) +{ +int i; +pcre_uchar *slot = cd->name_table; + +for (i = 0; i < cd->names_found; i++) + { + int crc = memcmp(name, slot+IMM2_SIZE, IN_UCHARS(length)); + if (crc == 0 && slot[IMM2_SIZE+length] != 0) + crc = -1; /* Current name is a substring */ + + /* Make space in the table and break the loop for an earlier name. For a + duplicate or later name, carry on. We do this for duplicates so that in the + simple case (when ?(| is not used) they are in order of their numbers. In all + cases they are in the order in which they appear in the pattern. */ + + if (crc < 0) + { + memmove(slot + cd->name_entry_size, slot, + IN_UCHARS((cd->names_found - i) * cd->name_entry_size)); + break; + } + + /* Continue the loop for a later or duplicate name */ + + slot += cd->name_entry_size; + } + +PUT2(slot, 0, groupno); +memcpy(slot + IMM2_SIZE, name, IN_UCHARS(length)); +slot[IMM2_SIZE + length] = 0; +cd->names_found++; +} + + + +/************************************************* +* Compile a Regular Expression * +*************************************************/ + +/* This function takes a string and returns a pointer to a block of store +holding a compiled version of the expression. The original API for this +function had no error code return variable; it is retained for backwards +compatibility. The new function is given a new name. + +Arguments: + pattern the regular expression + options various option bits + errorcodeptr pointer to error code variable (pcre_compile2() only) + can be NULL if you don't want a code value + errorptr pointer to pointer to error text + erroroffset ptr offset in pattern where error was detected + tables pointer to character tables or NULL + +Returns: pointer to compiled data block, or NULL on error, + with errorptr and erroroffset set +*/ + +#if defined COMPILE_PCRE8 +PCRE_EXP_DEFN pcre * PCRE_CALL_CONVENTION +pcre_compile(const char *pattern, int options, const char **errorptr, + int *erroroffset, const unsigned char *tables) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DEFN pcre16 * PCRE_CALL_CONVENTION +pcre16_compile(PCRE_SPTR16 pattern, int options, const char **errorptr, + int *erroroffset, const unsigned char *tables) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DEFN pcre32 * PCRE_CALL_CONVENTION +pcre32_compile(PCRE_SPTR32 pattern, int options, const char **errorptr, + int *erroroffset, const unsigned char *tables) +#endif +{ +#if defined COMPILE_PCRE8 +return pcre_compile2(pattern, options, NULL, errorptr, erroroffset, tables); +#elif defined COMPILE_PCRE16 +return pcre16_compile2(pattern, options, NULL, errorptr, erroroffset, tables); +#elif defined COMPILE_PCRE32 +return pcre32_compile2(pattern, options, NULL, errorptr, erroroffset, tables); +#endif +} + + +#if defined COMPILE_PCRE8 +PCRE_EXP_DEFN pcre * PCRE_CALL_CONVENTION +pcre_compile2(const char *pattern, int options, int *errorcodeptr, + const char **errorptr, int *erroroffset, const unsigned char *tables) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DEFN pcre16 * PCRE_CALL_CONVENTION +pcre16_compile2(PCRE_SPTR16 pattern, int options, int *errorcodeptr, + const char **errorptr, int *erroroffset, const unsigned char *tables) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DEFN pcre32 * PCRE_CALL_CONVENTION +pcre32_compile2(PCRE_SPTR32 pattern, int options, int *errorcodeptr, + const char **errorptr, int *erroroffset, const unsigned char *tables) +#endif +{ +REAL_PCRE *re; +int length = 1; /* For final END opcode */ +pcre_int32 firstcharflags, reqcharflags; +pcre_uint32 firstchar, reqchar; +pcre_uint32 limit_match = PCRE_UINT32_MAX; +pcre_uint32 limit_recursion = PCRE_UINT32_MAX; +int newline; +int errorcode = 0; +int skipatstart = 0; +BOOL utf; +BOOL never_utf = FALSE; +size_t size; +pcre_uchar *code; +const pcre_uchar *codestart; +const pcre_uchar *ptr; +compile_data compile_block; +compile_data *cd = &compile_block; + +/* This space is used for "compiling" into during the first phase, when we are +computing the amount of memory that is needed. Compiled items are thrown away +as soon as possible, so that a fairly large buffer should be sufficient for +this purpose. The same space is used in the second phase for remembering where +to fill in forward references to subpatterns. That may overflow, in which case +new memory is obtained from malloc(). */ + +pcre_uchar cworkspace[COMPILE_WORK_SIZE]; + +/* This vector is used for remembering name groups during the pre-compile. In a +similar way to cworkspace, it can be expanded using malloc() if necessary. */ + +named_group named_groups[NAMED_GROUP_LIST_SIZE]; + +/* Set this early so that early errors get offset 0. */ + +ptr = (const pcre_uchar *)pattern; + +/* We can't pass back an error message if errorptr is NULL; I guess the best we +can do is just return NULL, but we can set a code value if there is a code +pointer. */ + +if (errorptr == NULL) + { + if (errorcodeptr != NULL) *errorcodeptr = 99; + return NULL; + } + +*errorptr = NULL; +if (errorcodeptr != NULL) *errorcodeptr = ERR0; + +/* However, we can give a message for this error */ + +if (erroroffset == NULL) + { + errorcode = ERR16; + goto PCRE_EARLY_ERROR_RETURN2; + } + +*erroroffset = 0; + +/* Set up pointers to the individual character tables */ + +if (tables == NULL) tables = PRIV(default_tables); +cd->lcc = tables + lcc_offset; +cd->fcc = tables + fcc_offset; +cd->cbits = tables + cbits_offset; +cd->ctypes = tables + ctypes_offset; + +/* Check that all undefined public option bits are zero */ + +if ((options & ~PUBLIC_COMPILE_OPTIONS) != 0) + { + errorcode = ERR17; + goto PCRE_EARLY_ERROR_RETURN; + } + +/* If PCRE_NEVER_UTF is set, remember it. */ + +if ((options & PCRE_NEVER_UTF) != 0) never_utf = TRUE; + +/* Check for global one-time settings at the start of the pattern, and remember +the offset for later. */ + +cd->external_flags = 0; /* Initialize here for LIMIT_MATCH/RECURSION */ + +while (ptr[skipatstart] == CHAR_LEFT_PARENTHESIS && + ptr[skipatstart+1] == CHAR_ASTERISK) + { + int newnl = 0; + int newbsr = 0; + +/* For completeness and backward compatibility, (*UTFn) is supported in the +relevant libraries, but (*UTF) is generic and always supported. Note that +PCRE_UTF8 == PCRE_UTF16 == PCRE_UTF32. */ + +#ifdef COMPILE_PCRE8 + if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_UTF8_RIGHTPAR, 5) == 0) + { skipatstart += 7; options |= PCRE_UTF8; continue; } +#endif +#ifdef COMPILE_PCRE16 + if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_UTF16_RIGHTPAR, 6) == 0) + { skipatstart += 8; options |= PCRE_UTF16; continue; } +#endif +#ifdef COMPILE_PCRE32 + if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_UTF32_RIGHTPAR, 6) == 0) + { skipatstart += 8; options |= PCRE_UTF32; continue; } +#endif + + else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_UTF_RIGHTPAR, 4) == 0) + { skipatstart += 6; options |= PCRE_UTF8; continue; } + else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_UCP_RIGHTPAR, 4) == 0) + { skipatstart += 6; options |= PCRE_UCP; continue; } + else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_NO_AUTO_POSSESS_RIGHTPAR, 16) == 0) + { skipatstart += 18; options |= PCRE_NO_AUTO_POSSESS; continue; } + else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_NO_START_OPT_RIGHTPAR, 13) == 0) + { skipatstart += 15; options |= PCRE_NO_START_OPTIMIZE; continue; } + + else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_LIMIT_MATCH_EQ, 12) == 0) + { + pcre_uint32 c = 0; + int p = skipatstart + 14; + while (isdigit(ptr[p])) + { + if (c > PCRE_UINT32_MAX / 10 - 1) break; /* Integer overflow */ + c = c*10 + ptr[p++] - CHAR_0; + } + if (ptr[p++] != CHAR_RIGHT_PARENTHESIS) break; + if (c < limit_match) + { + limit_match = c; + cd->external_flags |= PCRE_MLSET; + } + skipatstart = p; + continue; + } + + else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_LIMIT_RECURSION_EQ, 16) == 0) + { + pcre_uint32 c = 0; + int p = skipatstart + 18; + while (isdigit(ptr[p])) + { + if (c > PCRE_UINT32_MAX / 10 - 1) break; /* Integer overflow check */ + c = c*10 + ptr[p++] - CHAR_0; + } + if (ptr[p++] != CHAR_RIGHT_PARENTHESIS) break; + if (c < limit_recursion) + { + limit_recursion = c; + cd->external_flags |= PCRE_RLSET; + } + skipatstart = p; + continue; + } + + if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_CR_RIGHTPAR, 3) == 0) + { skipatstart += 5; newnl = PCRE_NEWLINE_CR; } + else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_LF_RIGHTPAR, 3) == 0) + { skipatstart += 5; newnl = PCRE_NEWLINE_LF; } + else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_CRLF_RIGHTPAR, 5) == 0) + { skipatstart += 7; newnl = PCRE_NEWLINE_CR + PCRE_NEWLINE_LF; } + else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_ANY_RIGHTPAR, 4) == 0) + { skipatstart += 6; newnl = PCRE_NEWLINE_ANY; } + else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_ANYCRLF_RIGHTPAR, 8) == 0) + { skipatstart += 10; newnl = PCRE_NEWLINE_ANYCRLF; } + + else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_BSR_ANYCRLF_RIGHTPAR, 12) == 0) + { skipatstart += 14; newbsr = PCRE_BSR_ANYCRLF; } + else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_BSR_UNICODE_RIGHTPAR, 12) == 0) + { skipatstart += 14; newbsr = PCRE_BSR_UNICODE; } + + if (newnl != 0) + options = (options & ~PCRE_NEWLINE_BITS) | newnl; + else if (newbsr != 0) + options = (options & ~(PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) | newbsr; + else break; + } + +/* PCRE_UTF(16|32) have the same value as PCRE_UTF8. */ +utf = (options & PCRE_UTF8) != 0; +if (utf && never_utf) + { + errorcode = ERR78; + goto PCRE_EARLY_ERROR_RETURN2; + } + +/* Can't support UTF unless PCRE has been compiled to include the code. The +return of an error code from PRIV(valid_utf)() is a new feature, introduced in +release 8.13. It is passed back from pcre_[dfa_]exec(), but at the moment is +not used here. */ + +#ifdef SUPPORT_UTF +if (utf && (options & PCRE_NO_UTF8_CHECK) == 0 && + (errorcode = PRIV(valid_utf)((PCRE_PUCHAR)pattern, -1, erroroffset)) != 0) + { +#if defined COMPILE_PCRE8 + errorcode = ERR44; +#elif defined COMPILE_PCRE16 + errorcode = ERR74; +#elif defined COMPILE_PCRE32 + errorcode = ERR77; +#endif + goto PCRE_EARLY_ERROR_RETURN2; + } +#else +if (utf) + { + errorcode = ERR32; + goto PCRE_EARLY_ERROR_RETURN; + } +#endif + +/* Can't support UCP unless PCRE has been compiled to include the code. */ + +#ifndef SUPPORT_UCP +if ((options & PCRE_UCP) != 0) + { + errorcode = ERR67; + goto PCRE_EARLY_ERROR_RETURN; + } +#endif + +/* Check validity of \R options. */ + +if ((options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) == + (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) + { + errorcode = ERR56; + goto PCRE_EARLY_ERROR_RETURN; + } + +/* Handle different types of newline. The three bits give seven cases. The +current code allows for fixed one- or two-byte sequences, plus "any" and +"anycrlf". */ + +switch (options & PCRE_NEWLINE_BITS) + { + case 0: newline = NEWLINE; break; /* Build-time default */ + case PCRE_NEWLINE_CR: newline = CHAR_CR; break; + case PCRE_NEWLINE_LF: newline = CHAR_NL; break; + case PCRE_NEWLINE_CR+ + PCRE_NEWLINE_LF: newline = (CHAR_CR << 8) | CHAR_NL; break; + case PCRE_NEWLINE_ANY: newline = -1; break; + case PCRE_NEWLINE_ANYCRLF: newline = -2; break; + default: errorcode = ERR56; goto PCRE_EARLY_ERROR_RETURN; + } + +if (newline == -2) + { + cd->nltype = NLTYPE_ANYCRLF; + } +else if (newline < 0) + { + cd->nltype = NLTYPE_ANY; + } +else + { + cd->nltype = NLTYPE_FIXED; + if (newline > 255) + { + cd->nllen = 2; + cd->nl[0] = (newline >> 8) & 255; + cd->nl[1] = newline & 255; + } + else + { + cd->nllen = 1; + cd->nl[0] = newline; + } + } + +/* Maximum back reference and backref bitmap. The bitmap records up to 31 back +references to help in deciding whether (.*) can be treated as anchored or not. +*/ + +cd->top_backref = 0; +cd->backref_map = 0; + +/* Reflect pattern for debugging output */ + +DPRINTF(("------------------------------------------------------------------\n")); +#ifdef PCRE_DEBUG +print_puchar(stdout, (PCRE_PUCHAR)pattern); +#endif +DPRINTF(("\n")); + +/* Pretend to compile the pattern while actually just accumulating the length +of memory required. This behaviour is triggered by passing a non-NULL final +argument to compile_regex(). We pass a block of workspace (cworkspace) for it +to compile parts of the pattern into; the compiled code is discarded when it is +no longer needed, so hopefully this workspace will never overflow, though there +is a test for its doing so. */ + +cd->bracount = cd->final_bracount = 0; +cd->names_found = 0; +cd->name_entry_size = 0; +cd->name_table = NULL; +cd->dupnames = FALSE; +cd->namedrefcount = 0; +cd->start_code = cworkspace; +cd->hwm = cworkspace; +cd->start_workspace = cworkspace; +cd->workspace_size = COMPILE_WORK_SIZE; +cd->named_groups = named_groups; +cd->named_group_list_size = NAMED_GROUP_LIST_SIZE; +cd->start_pattern = (const pcre_uchar *)pattern; +cd->end_pattern = (const pcre_uchar *)(pattern + STRLEN_UC((const pcre_uchar *)pattern)); +cd->req_varyopt = 0; +cd->parens_depth = 0; +cd->assert_depth = 0; +cd->max_lookbehind = 0; +cd->external_options = options; +cd->open_caps = NULL; + +/* Now do the pre-compile. On error, errorcode will be set non-zero, so we +don't need to look at the result of the function here. The initial options have +been put into the cd block so that they can be changed if an option setting is +found within the regex right at the beginning. Bringing initial option settings +outside can help speed up starting point checks. */ + +ptr += skipatstart; +code = cworkspace; +*code = OP_BRA; + +(void)compile_regex(cd->external_options, &code, &ptr, &errorcode, FALSE, + FALSE, 0, 0, &firstchar, &firstcharflags, &reqchar, &reqcharflags, NULL, + cd, &length); +if (errorcode != 0) goto PCRE_EARLY_ERROR_RETURN; + +DPRINTF(("end pre-compile: length=%d workspace=%d\n", length, + (int)(cd->hwm - cworkspace))); + +if (length > MAX_PATTERN_SIZE) + { + errorcode = ERR20; + goto PCRE_EARLY_ERROR_RETURN; + } + +/* If there are groups with duplicate names and there are also references by +name, we must allow for the possibility of named references to duplicated +groups. These require an extra data item each. */ + +if (cd->dupnames && cd->namedrefcount > 0) + length += cd->namedrefcount * IMM2_SIZE * sizeof(pcre_uchar); + +/* Compute the size of the data block for storing the compiled pattern. Integer +overflow should no longer be possible because nowadays we limit the maximum +value of cd->names_found and cd->name_entry_size. */ + +size = sizeof(REAL_PCRE) + + (length + cd->names_found * cd->name_entry_size) * sizeof(pcre_uchar); + +/* Get the memory. */ + +re = (REAL_PCRE *)(PUBL(malloc))(size); +if (re == NULL) + { + errorcode = ERR21; + goto PCRE_EARLY_ERROR_RETURN; + } + +/* Put in the magic number, and save the sizes, initial options, internal +flags, and character table pointer. NULL is used for the default character +tables. The nullpad field is at the end; it's there to help in the case when a +regex compiled on a system with 4-byte pointers is run on another with 8-byte +pointers. */ + +re->magic_number = MAGIC_NUMBER; +re->size = (int)size; +re->options = cd->external_options; +re->flags = cd->external_flags; +re->limit_match = limit_match; +re->limit_recursion = limit_recursion; +re->first_char = 0; +re->req_char = 0; +re->name_table_offset = sizeof(REAL_PCRE) / sizeof(pcre_uchar); +re->name_entry_size = cd->name_entry_size; +re->name_count = cd->names_found; +re->ref_count = 0; +re->tables = (tables == PRIV(default_tables))? NULL : tables; +re->nullpad = NULL; +#ifdef COMPILE_PCRE32 +re->dummy = 0; +#else +re->dummy1 = re->dummy2 = re->dummy3 = 0; +#endif + +/* The starting points of the name/number translation table and of the code are +passed around in the compile data block. The start/end pattern and initial +options are already set from the pre-compile phase, as is the name_entry_size +field. Reset the bracket count and the names_found field. Also reset the hwm +field; this time it's used for remembering forward references to subpatterns. +*/ + +cd->final_bracount = cd->bracount; /* Save for checking forward references */ +cd->parens_depth = 0; +cd->assert_depth = 0; +cd->bracount = 0; +cd->max_lookbehind = 0; +cd->name_table = (pcre_uchar *)re + re->name_table_offset; +codestart = cd->name_table + re->name_entry_size * re->name_count; +cd->start_code = codestart; +cd->hwm = (pcre_uchar *)(cd->start_workspace); +cd->req_varyopt = 0; +cd->had_accept = FALSE; +cd->had_pruneorskip = FALSE; +cd->check_lookbehind = FALSE; +cd->open_caps = NULL; + +/* If any named groups were found, create the name/number table from the list +created in the first pass. */ + +if (cd->names_found > 0) + { + int i = cd->names_found; + named_group *ng = cd->named_groups; + cd->names_found = 0; + for (; i > 0; i--, ng++) + add_name(cd, ng->name, ng->length, ng->number); + if (cd->named_group_list_size > NAMED_GROUP_LIST_SIZE) + (PUBL(free))((void *)cd->named_groups); + } + +/* Set up a starting, non-extracting bracket, then compile the expression. On +error, errorcode will be set non-zero, so we don't need to look at the result +of the function here. */ + +ptr = (const pcre_uchar *)pattern + skipatstart; +code = (pcre_uchar *)codestart; +*code = OP_BRA; +(void)compile_regex(re->options, &code, &ptr, &errorcode, FALSE, FALSE, 0, 0, + &firstchar, &firstcharflags, &reqchar, &reqcharflags, NULL, cd, NULL); +re->top_bracket = cd->bracount; +re->top_backref = cd->top_backref; +re->max_lookbehind = cd->max_lookbehind; +re->flags = cd->external_flags | PCRE_MODE; + +if (cd->had_accept) + { + reqchar = 0; /* Must disable after (*ACCEPT) */ + reqcharflags = REQ_NONE; + } + +/* If not reached end of pattern on success, there's an excess bracket. */ + +if (errorcode == 0 && *ptr != CHAR_NULL) errorcode = ERR22; + +/* Fill in the terminating state and check for disastrous overflow, but +if debugging, leave the test till after things are printed out. */ + +*code++ = OP_END; + +#ifndef PCRE_DEBUG +if (code - codestart > length) errorcode = ERR23; +#endif + +#ifdef SUPPORT_VALGRIND +/* If the estimated length exceeds the really used length, mark the extra +allocated memory as unaddressable, so that any out-of-bound reads can be +detected. */ +VALGRIND_MAKE_MEM_NOACCESS(code, (length - (code - codestart)) * sizeof(pcre_uchar)); +#endif + +/* Fill in any forward references that are required. There may be repeated +references; optimize for them, as searching a large regex takes time. */ + +if (cd->hwm > cd->start_workspace) + { + int prev_recno = -1; + const pcre_uchar *groupptr = NULL; + while (errorcode == 0 && cd->hwm > cd->start_workspace) + { + int offset, recno; + cd->hwm -= LINK_SIZE; + offset = GET(cd->hwm, 0); + recno = GET(codestart, offset); + if (recno != prev_recno) + { + groupptr = PRIV(find_bracket)(codestart, utf, recno); + prev_recno = recno; + } + if (groupptr == NULL) errorcode = ERR53; + else PUT(((pcre_uchar *)codestart), offset, (int)(groupptr - codestart)); + } + } + +/* If the workspace had to be expanded, free the new memory. Set the pointer to +NULL to indicate that forward references have been filled in. */ + +if (cd->workspace_size > COMPILE_WORK_SIZE) + (PUBL(free))((void *)cd->start_workspace); +cd->start_workspace = NULL; + +/* Give an error if there's back reference to a non-existent capturing +subpattern. */ + +if (errorcode == 0 && re->top_backref > re->top_bracket) errorcode = ERR15; + +/* Unless disabled, check whether single character iterators can be +auto-possessified. The function overwrites the appropriate opcode values. */ + +if ((options & PCRE_NO_AUTO_POSSESS) == 0) + auto_possessify((pcre_uchar *)codestart, utf, cd); + +/* If there were any lookbehind assertions that contained OP_RECURSE +(recursions or subroutine calls), a flag is set for them to be checked here, +because they may contain forward references. Actual recursions cannot be fixed +length, but subroutine calls can. It is done like this so that those without +OP_RECURSE that are not fixed length get a diagnosic with a useful offset. The +exceptional ones forgo this. We scan the pattern to check that they are fixed +length, and set their lengths. */ + +if (cd->check_lookbehind) + { + pcre_uchar *cc = (pcre_uchar *)codestart; + + /* Loop, searching for OP_REVERSE items, and process those that do not have + their length set. (Actually, it will also re-process any that have a length + of zero, but that is a pathological case, and it does no harm.) When we find + one, we temporarily terminate the branch it is in while we scan it. */ + + for (cc = (pcre_uchar *)PRIV(find_bracket)(codestart, utf, -1); + cc != NULL; + cc = (pcre_uchar *)PRIV(find_bracket)(cc, utf, -1)) + { + if (GET(cc, 1) == 0) + { + int fixed_length; + pcre_uchar *be = cc - 1 - LINK_SIZE + GET(cc, -LINK_SIZE); + int end_op = *be; + *be = OP_END; + fixed_length = find_fixedlength(cc, (re->options & PCRE_UTF8) != 0, TRUE, + cd); + *be = end_op; + DPRINTF(("fixed length = %d\n", fixed_length)); + if (fixed_length < 0) + { + errorcode = (fixed_length == -2)? ERR36 : + (fixed_length == -4)? ERR70 : ERR25; + break; + } + if (fixed_length > cd->max_lookbehind) cd->max_lookbehind = fixed_length; + PUT(cc, 1, fixed_length); + } + cc += 1 + LINK_SIZE; + } + } + +/* Failed to compile, or error while post-processing */ + +if (errorcode != 0) + { + (PUBL(free))(re); + PCRE_EARLY_ERROR_RETURN: + *erroroffset = (int)(ptr - (const pcre_uchar *)pattern); + PCRE_EARLY_ERROR_RETURN2: + *errorptr = find_error_text(errorcode); + if (errorcodeptr != NULL) *errorcodeptr = errorcode; + return NULL; + } + +/* If the anchored option was not passed, set the flag if we can determine that +the pattern is anchored by virtue of ^ characters or \A or anything else, such +as starting with non-atomic .* when DOTALL is set and there are no occurrences +of *PRUNE or *SKIP. + +Otherwise, if we know what the first byte has to be, save it, because that +speeds up unanchored matches no end. If not, see if we can set the +PCRE_STARTLINE flag. This is helpful for multiline matches when all branches +start with ^. and also when all branches start with non-atomic .* for +non-DOTALL matches when *PRUNE and SKIP are not present. */ + +if ((re->options & PCRE_ANCHORED) == 0) + { + if (is_anchored(codestart, 0, cd, 0)) re->options |= PCRE_ANCHORED; + else + { + if (firstcharflags < 0) + firstchar = find_firstassertedchar(codestart, &firstcharflags, FALSE); + if (firstcharflags >= 0) /* Remove caseless flag for non-caseable chars */ + { +#if defined COMPILE_PCRE8 + re->first_char = firstchar & 0xff; +#elif defined COMPILE_PCRE16 + re->first_char = firstchar & 0xffff; +#elif defined COMPILE_PCRE32 + re->first_char = firstchar; +#endif + if ((firstcharflags & REQ_CASELESS) != 0) + { +#if defined SUPPORT_UCP && !(defined COMPILE_PCRE8) + /* We ignore non-ASCII first chars in 8 bit mode. */ + if (utf) + { + if (re->first_char < 128) + { + if (cd->fcc[re->first_char] != re->first_char) + re->flags |= PCRE_FCH_CASELESS; + } + else if (UCD_OTHERCASE(re->first_char) != re->first_char) + re->flags |= PCRE_FCH_CASELESS; + } + else +#endif + if (MAX_255(re->first_char) + && cd->fcc[re->first_char] != re->first_char) + re->flags |= PCRE_FCH_CASELESS; + } + + re->flags |= PCRE_FIRSTSET; + } + + else if (is_startline(codestart, 0, cd, 0)) re->flags |= PCRE_STARTLINE; + } + } + +/* For an anchored pattern, we use the "required byte" only if it follows a +variable length item in the regex. Remove the caseless flag for non-caseable +bytes. */ + +if (reqcharflags >= 0 && + ((re->options & PCRE_ANCHORED) == 0 || (reqcharflags & REQ_VARY) != 0)) + { +#if defined COMPILE_PCRE8 + re->req_char = reqchar & 0xff; +#elif defined COMPILE_PCRE16 + re->req_char = reqchar & 0xffff; +#elif defined COMPILE_PCRE32 + re->req_char = reqchar; +#endif + if ((reqcharflags & REQ_CASELESS) != 0) + { +#if defined SUPPORT_UCP && !(defined COMPILE_PCRE8) + /* We ignore non-ASCII first chars in 8 bit mode. */ + if (utf) + { + if (re->req_char < 128) + { + if (cd->fcc[re->req_char] != re->req_char) + re->flags |= PCRE_RCH_CASELESS; + } + else if (UCD_OTHERCASE(re->req_char) != re->req_char) + re->flags |= PCRE_RCH_CASELESS; + } + else +#endif + if (MAX_255(re->req_char) && cd->fcc[re->req_char] != re->req_char) + re->flags |= PCRE_RCH_CASELESS; + } + + re->flags |= PCRE_REQCHSET; + } + +/* Print out the compiled data if debugging is enabled. This is never the +case when building a production library. */ + +#ifdef PCRE_DEBUG +printf("Length = %d top_bracket = %d top_backref = %d\n", + length, re->top_bracket, re->top_backref); + +printf("Options=%08x\n", re->options); + +if ((re->flags & PCRE_FIRSTSET) != 0) + { + pcre_uchar ch = re->first_char; + const char *caseless = + ((re->flags & PCRE_FCH_CASELESS) == 0)? "" : " (caseless)"; + if (PRINTABLE(ch)) printf("First char = %c%s\n", ch, caseless); + else printf("First char = \\x%02x%s\n", ch, caseless); + } + +if ((re->flags & PCRE_REQCHSET) != 0) + { + pcre_uchar ch = re->req_char; + const char *caseless = + ((re->flags & PCRE_RCH_CASELESS) == 0)? "" : " (caseless)"; + if (PRINTABLE(ch)) printf("Req char = %c%s\n", ch, caseless); + else printf("Req char = \\x%02x%s\n", ch, caseless); + } + +#if defined COMPILE_PCRE8 +pcre_printint((pcre *)re, stdout, TRUE); +#elif defined COMPILE_PCRE16 +pcre16_printint((pcre *)re, stdout, TRUE); +#elif defined COMPILE_PCRE32 +pcre32_printint((pcre *)re, stdout, TRUE); +#endif + +/* This check is done here in the debugging case so that the code that +was compiled can be seen. */ + +if (code - codestart > length) + { + (PUBL(free))(re); + *errorptr = find_error_text(ERR23); + *erroroffset = ptr - (pcre_uchar *)pattern; + if (errorcodeptr != NULL) *errorcodeptr = ERR23; + return NULL; + } +#endif /* PCRE_DEBUG */ + +/* Check for a pattern than can match an empty string, so that this information +can be provided to applications. */ + +do + { + if (could_be_empty_branch(codestart, code, utf, cd, NULL)) + { + re->flags |= PCRE_MATCH_EMPTY; + break; + } + codestart += GET(codestart, 1); + } +while (*codestart == OP_ALT); + +#if defined COMPILE_PCRE8 +return (pcre *)re; +#elif defined COMPILE_PCRE16 +return (pcre16 *)re; +#elif defined COMPILE_PCRE32 +return (pcre32 *)re; +#endif +} + +/* End of pcre_compile.c */ + diff --git a/plugins/Pcre16/src/pcre_config.c b/plugins/Pcre16/src/pcre_config.c new file mode 100644 index 0000000000..1cbdd9c960 --- /dev/null +++ b/plugins/Pcre16/src/pcre_config.c @@ -0,0 +1,190 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains the external function pcre_config(). */ + + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +/* Keep the original link size. */ +static int real_link_size = LINK_SIZE; + +#include "pcre_internal.h" + + +/************************************************* +* Return info about what features are configured * +*************************************************/ + +/* This function has an extensible interface so that additional items can be +added compatibly. + +Arguments: + what what information is required + where where to put the information + +Returns: 0 if data returned, negative on error +*/ + +#if defined COMPILE_PCRE8 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre_config(int what, void *where) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre16_config(int what, void *where) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre32_config(int what, void *where) +#endif +{ +switch (what) + { + case PCRE_CONFIG_UTF8: +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + *((int *)where) = 0; + return PCRE_ERROR_BADOPTION; +#else +#if defined SUPPORT_UTF + *((int *)where) = 1; +#else + *((int *)where) = 0; +#endif + break; +#endif + + case PCRE_CONFIG_UTF16: +#if defined COMPILE_PCRE8 || defined COMPILE_PCRE32 + *((int *)where) = 0; + return PCRE_ERROR_BADOPTION; +#else +#if defined SUPPORT_UTF + *((int *)where) = 1; +#else + *((int *)where) = 0; +#endif + break; +#endif + + case PCRE_CONFIG_UTF32: +#if defined COMPILE_PCRE8 || defined COMPILE_PCRE16 + *((int *)where) = 0; + return PCRE_ERROR_BADOPTION; +#else +#if defined SUPPORT_UTF + *((int *)where) = 1; +#else + *((int *)where) = 0; +#endif + break; +#endif + + case PCRE_CONFIG_UNICODE_PROPERTIES: +#ifdef SUPPORT_UCP + *((int *)where) = 1; +#else + *((int *)where) = 0; +#endif + break; + + case PCRE_CONFIG_JIT: +#ifdef SUPPORT_JIT + *((int *)where) = 1; +#else + *((int *)where) = 0; +#endif + break; + + case PCRE_CONFIG_JITTARGET: +#ifdef SUPPORT_JIT + *((const char **)where) = PRIV(jit_get_target)(); +#else + *((const char **)where) = NULL; +#endif + break; + + case PCRE_CONFIG_NEWLINE: + *((int *)where) = NEWLINE; + break; + + case PCRE_CONFIG_BSR: +#ifdef BSR_ANYCRLF + *((int *)where) = 1; +#else + *((int *)where) = 0; +#endif + break; + + case PCRE_CONFIG_LINK_SIZE: + *((int *)where) = real_link_size; + break; + + case PCRE_CONFIG_POSIX_MALLOC_THRESHOLD: + *((int *)where) = POSIX_MALLOC_THRESHOLD; + break; + + case PCRE_CONFIG_PARENS_LIMIT: + *((unsigned long int *)where) = PARENS_NEST_LIMIT; + break; + + case PCRE_CONFIG_MATCH_LIMIT: + *((unsigned long int *)where) = MATCH_LIMIT; + break; + + case PCRE_CONFIG_MATCH_LIMIT_RECURSION: + *((unsigned long int *)where) = MATCH_LIMIT_RECURSION; + break; + + case PCRE_CONFIG_STACKRECURSE: +#ifdef NO_RECURSE + *((int *)where) = 0; +#else + *((int *)where) = 1; +#endif + break; + + default: return PCRE_ERROR_BADOPTION; + } + +return 0; +} + +/* End of pcre_config.c */ diff --git a/plugins/Pcre16/src/pcre_dfa_exec.c b/plugins/Pcre16/src/pcre_dfa_exec.c new file mode 100644 index 0000000000..fb0c7e805d --- /dev/null +++ b/plugins/Pcre16/src/pcre_dfa_exec.c @@ -0,0 +1,3673 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language (but see +below for why this module is different). + + Written by Philip Hazel + Copyright (c) 1997-2014 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* This module contains the external function pcre_dfa_exec(), which is an +alternative matching function that uses a sort of DFA algorithm (not a true +FSM). This is NOT Perl-compatible, but it has advantages in certain +applications. */ + + +/* NOTE ABOUT PERFORMANCE: A user of this function sent some code that improved +the performance of his patterns greatly. I could not use it as it stood, as it +was not thread safe, and made assumptions about pattern sizes. Also, it caused +test 7 to loop, and test 9 to crash with a segfault. + +The issue is the check for duplicate states, which is done by a simple linear +search up the state list. (Grep for "duplicate" below to find the code.) For +many patterns, there will never be many states active at one time, so a simple +linear search is fine. In patterns that have many active states, it might be a +bottleneck. The suggested code used an indexing scheme to remember which states +had previously been used for each character, and avoided the linear search when +it knew there was no chance of a duplicate. This was implemented when adding +states to the state lists. + +I wrote some thread-safe, not-limited code to try something similar at the time +of checking for duplicates (instead of when adding states), using index vectors +on the stack. It did give a 13% improvement with one specially constructed +pattern for certain subject strings, but on other strings and on many of the +simpler patterns in the test suite it did worse. The major problem, I think, +was the extra time to initialize the index. This had to be done for each call +of internal_dfa_exec(). (The supplied patch used a static vector, initialized +only once - I suspect this was the cause of the problems with the tests.) + +Overall, I concluded that the gains in some cases did not outweigh the losses +in others, so I abandoned this code. */ + + + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#define NLBLOCK md /* Block containing newline information */ +#define PSSTART start_subject /* Field containing processed string start */ +#define PSEND end_subject /* Field containing processed string end */ + +#include "pcre_internal.h" + + +/* For use to indent debugging output */ + +#define SP " " + + +/************************************************* +* Code parameters and static tables * +*************************************************/ + +/* These are offsets that are used to turn the OP_TYPESTAR and friends opcodes +into others, under special conditions. A gap of 20 between the blocks should be +enough. The resulting opcodes don't have to be less than 256 because they are +never stored, so we push them well clear of the normal opcodes. */ + +#define OP_PROP_EXTRA 300 +#define OP_EXTUNI_EXTRA 320 +#define OP_ANYNL_EXTRA 340 +#define OP_HSPACE_EXTRA 360 +#define OP_VSPACE_EXTRA 380 + + +/* This table identifies those opcodes that are followed immediately by a +character that is to be tested in some way. This makes it possible to +centralize the loading of these characters. In the case of Type * etc, the +"character" is the opcode for \D, \d, \S, \s, \W, or \w, which will always be a +small value. Non-zero values in the table are the offsets from the opcode where +the character is to be found. ***NOTE*** If the start of this table is +modified, the three tables that follow must also be modified. */ + +static const pcre_uint8 coptable[] = { + 0, /* End */ + 0, 0, 0, 0, 0, /* \A, \G, \K, \B, \b */ + 0, 0, 0, 0, 0, 0, /* \D, \d, \S, \s, \W, \w */ + 0, 0, 0, /* Any, AllAny, Anybyte */ + 0, 0, /* \P, \p */ + 0, 0, 0, 0, 0, /* \R, \H, \h, \V, \v */ + 0, /* \X */ + 0, 0, 0, 0, 0, 0, /* \Z, \z, $, $M, ^, ^M */ + 1, /* Char */ + 1, /* Chari */ + 1, /* not */ + 1, /* noti */ + /* Positive single-char repeats */ + 1, 1, 1, 1, 1, 1, /* *, *?, +, +?, ?, ?? */ + 1+IMM2_SIZE, 1+IMM2_SIZE, /* upto, minupto */ + 1+IMM2_SIZE, /* exact */ + 1, 1, 1, 1+IMM2_SIZE, /* *+, ++, ?+, upto+ */ + 1, 1, 1, 1, 1, 1, /* *I, *?I, +I, +?I, ?I, ??I */ + 1+IMM2_SIZE, 1+IMM2_SIZE, /* upto I, minupto I */ + 1+IMM2_SIZE, /* exact I */ + 1, 1, 1, 1+IMM2_SIZE, /* *+I, ++I, ?+I, upto+I */ + /* Negative single-char repeats - only for chars < 256 */ + 1, 1, 1, 1, 1, 1, /* NOT *, *?, +, +?, ?, ?? */ + 1+IMM2_SIZE, 1+IMM2_SIZE, /* NOT upto, minupto */ + 1+IMM2_SIZE, /* NOT exact */ + 1, 1, 1, 1+IMM2_SIZE, /* NOT *+, ++, ?+, upto+ */ + 1, 1, 1, 1, 1, 1, /* NOT *I, *?I, +I, +?I, ?I, ??I */ + 1+IMM2_SIZE, 1+IMM2_SIZE, /* NOT upto I, minupto I */ + 1+IMM2_SIZE, /* NOT exact I */ + 1, 1, 1, 1+IMM2_SIZE, /* NOT *+I, ++I, ?+I, upto+I */ + /* Positive type repeats */ + 1, 1, 1, 1, 1, 1, /* Type *, *?, +, +?, ?, ?? */ + 1+IMM2_SIZE, 1+IMM2_SIZE, /* Type upto, minupto */ + 1+IMM2_SIZE, /* Type exact */ + 1, 1, 1, 1+IMM2_SIZE, /* Type *+, ++, ?+, upto+ */ + /* Character class & ref repeats */ + 0, 0, 0, 0, 0, 0, /* *, *?, +, +?, ?, ?? */ + 0, 0, /* CRRANGE, CRMINRANGE */ + 0, 0, 0, 0, /* Possessive *+, ++, ?+, CRPOSRANGE */ + 0, /* CLASS */ + 0, /* NCLASS */ + 0, /* XCLASS - variable length */ + 0, /* REF */ + 0, /* REFI */ + 0, /* DNREF */ + 0, /* DNREFI */ + 0, /* RECURSE */ + 0, /* CALLOUT */ + 0, /* Alt */ + 0, /* Ket */ + 0, /* KetRmax */ + 0, /* KetRmin */ + 0, /* KetRpos */ + 0, /* Reverse */ + 0, /* Assert */ + 0, /* Assert not */ + 0, /* Assert behind */ + 0, /* Assert behind not */ + 0, 0, /* ONCE, ONCE_NC */ + 0, 0, 0, 0, 0, /* BRA, BRAPOS, CBRA, CBRAPOS, COND */ + 0, 0, 0, 0, 0, /* SBRA, SBRAPOS, SCBRA, SCBRAPOS, SCOND */ + 0, 0, /* CREF, DNCREF */ + 0, 0, /* RREF, DNRREF */ + 0, /* DEF */ + 0, 0, 0, /* BRAZERO, BRAMINZERO, BRAPOSZERO */ + 0, 0, 0, /* MARK, PRUNE, PRUNE_ARG */ + 0, 0, 0, 0, /* SKIP, SKIP_ARG, THEN, THEN_ARG */ + 0, 0, 0, 0, /* COMMIT, FAIL, ACCEPT, ASSERT_ACCEPT */ + 0, 0 /* CLOSE, SKIPZERO */ +}; + +/* This table identifies those opcodes that inspect a character. It is used to +remember the fact that a character could have been inspected when the end of +the subject is reached. ***NOTE*** If the start of this table is modified, the +two tables that follow must also be modified. */ + +static const pcre_uint8 poptable[] = { + 0, /* End */ + 0, 0, 0, 1, 1, /* \A, \G, \K, \B, \b */ + 1, 1, 1, 1, 1, 1, /* \D, \d, \S, \s, \W, \w */ + 1, 1, 1, /* Any, AllAny, Anybyte */ + 1, 1, /* \P, \p */ + 1, 1, 1, 1, 1, /* \R, \H, \h, \V, \v */ + 1, /* \X */ + 0, 0, 0, 0, 0, 0, /* \Z, \z, $, $M, ^, ^M */ + 1, /* Char */ + 1, /* Chari */ + 1, /* not */ + 1, /* noti */ + /* Positive single-char repeats */ + 1, 1, 1, 1, 1, 1, /* *, *?, +, +?, ?, ?? */ + 1, 1, 1, /* upto, minupto, exact */ + 1, 1, 1, 1, /* *+, ++, ?+, upto+ */ + 1, 1, 1, 1, 1, 1, /* *I, *?I, +I, +?I, ?I, ??I */ + 1, 1, 1, /* upto I, minupto I, exact I */ + 1, 1, 1, 1, /* *+I, ++I, ?+I, upto+I */ + /* Negative single-char repeats - only for chars < 256 */ + 1, 1, 1, 1, 1, 1, /* NOT *, *?, +, +?, ?, ?? */ + 1, 1, 1, /* NOT upto, minupto, exact */ + 1, 1, 1, 1, /* NOT *+, ++, ?+, upto+ */ + 1, 1, 1, 1, 1, 1, /* NOT *I, *?I, +I, +?I, ?I, ??I */ + 1, 1, 1, /* NOT upto I, minupto I, exact I */ + 1, 1, 1, 1, /* NOT *+I, ++I, ?+I, upto+I */ + /* Positive type repeats */ + 1, 1, 1, 1, 1, 1, /* Type *, *?, +, +?, ?, ?? */ + 1, 1, 1, /* Type upto, minupto, exact */ + 1, 1, 1, 1, /* Type *+, ++, ?+, upto+ */ + /* Character class & ref repeats */ + 1, 1, 1, 1, 1, 1, /* *, *?, +, +?, ?, ?? */ + 1, 1, /* CRRANGE, CRMINRANGE */ + 1, 1, 1, 1, /* Possessive *+, ++, ?+, CRPOSRANGE */ + 1, /* CLASS */ + 1, /* NCLASS */ + 1, /* XCLASS - variable length */ + 0, /* REF */ + 0, /* REFI */ + 0, /* DNREF */ + 0, /* DNREFI */ + 0, /* RECURSE */ + 0, /* CALLOUT */ + 0, /* Alt */ + 0, /* Ket */ + 0, /* KetRmax */ + 0, /* KetRmin */ + 0, /* KetRpos */ + 0, /* Reverse */ + 0, /* Assert */ + 0, /* Assert not */ + 0, /* Assert behind */ + 0, /* Assert behind not */ + 0, 0, /* ONCE, ONCE_NC */ + 0, 0, 0, 0, 0, /* BRA, BRAPOS, CBRA, CBRAPOS, COND */ + 0, 0, 0, 0, 0, /* SBRA, SBRAPOS, SCBRA, SCBRAPOS, SCOND */ + 0, 0, /* CREF, DNCREF */ + 0, 0, /* RREF, DNRREF */ + 0, /* DEF */ + 0, 0, 0, /* BRAZERO, BRAMINZERO, BRAPOSZERO */ + 0, 0, 0, /* MARK, PRUNE, PRUNE_ARG */ + 0, 0, 0, 0, /* SKIP, SKIP_ARG, THEN, THEN_ARG */ + 0, 0, 0, 0, /* COMMIT, FAIL, ACCEPT, ASSERT_ACCEPT */ + 0, 0 /* CLOSE, SKIPZERO */ +}; + +/* These 2 tables allow for compact code for testing for \D, \d, \S, \s, \W, +and \w */ + +static const pcre_uint8 toptable1[] = { + 0, 0, 0, 0, 0, 0, + ctype_digit, ctype_digit, + ctype_space, ctype_space, + ctype_word, ctype_word, + 0, 0 /* OP_ANY, OP_ALLANY */ +}; + +static const pcre_uint8 toptable2[] = { + 0, 0, 0, 0, 0, 0, + ctype_digit, 0, + ctype_space, 0, + ctype_word, 0, + 1, 1 /* OP_ANY, OP_ALLANY */ +}; + + +/* Structure for holding data about a particular state, which is in effect the +current data for an active path through the match tree. It must consist +entirely of ints because the working vector we are passed, and which we put +these structures in, is a vector of ints. */ + +typedef struct stateblock { + int offset; /* Offset to opcode */ + int count; /* Count for repeats */ + int data; /* Some use extra data */ +} stateblock; + +#define INTS_PER_STATEBLOCK (int)(sizeof(stateblock)/sizeof(int)) + + +#ifdef PCRE_DEBUG +/************************************************* +* Print character string * +*************************************************/ + +/* Character string printing function for debugging. + +Arguments: + p points to string + length number of bytes + f where to print + +Returns: nothing +*/ + +static void +pchars(const pcre_uchar *p, int length, FILE *f) +{ +pcre_uint32 c; +while (length-- > 0) + { + if (isprint(c = *(p++))) + fprintf(f, "%c", c); + else + fprintf(f, "\\x{%02x}", c); + } +} +#endif + + + +/************************************************* +* Execute a Regular Expression - DFA engine * +*************************************************/ + +/* This internal function applies a compiled pattern to a subject string, +starting at a given point, using a DFA engine. This function is called from the +external one, possibly multiple times if the pattern is not anchored. The +function calls itself recursively for some kinds of subpattern. + +Arguments: + md the match_data block with fixed information + this_start_code the opening bracket of this subexpression's code + current_subject where we currently are in the subject string + start_offset start offset in the subject string + offsets vector to contain the matching string offsets + offsetcount size of same + workspace vector of workspace + wscount size of same + rlevel function call recursion level + +Returns: > 0 => number of match offset pairs placed in offsets + = 0 => offsets overflowed; longest matches are present + -1 => failed to match + < -1 => some kind of unexpected problem + +The following macros are used for adding states to the two state vectors (one +for the current character, one for the following character). */ + +#define ADD_ACTIVE(x,y) \ + if (active_count++ < wscount) \ + { \ + next_active_state->offset = (x); \ + next_active_state->count = (y); \ + next_active_state++; \ + DPRINTF(("%.*sADD_ACTIVE(%d,%d)\n", rlevel*2-2, SP, (x), (y))); \ + } \ + else return PCRE_ERROR_DFA_WSSIZE + +#define ADD_ACTIVE_DATA(x,y,z) \ + if (active_count++ < wscount) \ + { \ + next_active_state->offset = (x); \ + next_active_state->count = (y); \ + next_active_state->data = (z); \ + next_active_state++; \ + DPRINTF(("%.*sADD_ACTIVE_DATA(%d,%d,%d)\n", rlevel*2-2, SP, (x), (y), (z))); \ + } \ + else return PCRE_ERROR_DFA_WSSIZE + +#define ADD_NEW(x,y) \ + if (new_count++ < wscount) \ + { \ + next_new_state->offset = (x); \ + next_new_state->count = (y); \ + next_new_state++; \ + DPRINTF(("%.*sADD_NEW(%d,%d)\n", rlevel*2-2, SP, (x), (y))); \ + } \ + else return PCRE_ERROR_DFA_WSSIZE + +#define ADD_NEW_DATA(x,y,z) \ + if (new_count++ < wscount) \ + { \ + next_new_state->offset = (x); \ + next_new_state->count = (y); \ + next_new_state->data = (z); \ + next_new_state++; \ + DPRINTF(("%.*sADD_NEW_DATA(%d,%d,%d) line %d\n", rlevel*2-2, SP, \ + (x), (y), (z), __LINE__)); \ + } \ + else return PCRE_ERROR_DFA_WSSIZE + +/* And now, here is the code */ + +static int +internal_dfa_exec( + dfa_match_data *md, + const pcre_uchar *this_start_code, + const pcre_uchar *current_subject, + int start_offset, + int *offsets, + int offsetcount, + int *workspace, + int wscount, + int rlevel) +{ +stateblock *active_states, *new_states, *temp_states; +stateblock *next_active_state, *next_new_state; + +const pcre_uint8 *ctypes, *lcc, *fcc; +const pcre_uchar *ptr; +const pcre_uchar *end_code, *first_op; + +dfa_recursion_info new_recursive; + +int active_count, new_count, match_count; + +/* Some fields in the md block are frequently referenced, so we load them into +independent variables in the hope that this will perform better. */ + +const pcre_uchar *start_subject = md->start_subject; +const pcre_uchar *end_subject = md->end_subject; +const pcre_uchar *start_code = md->start_code; + +#ifdef SUPPORT_UTF +BOOL utf = (md->poptions & PCRE_UTF8) != 0; +#else +BOOL utf = FALSE; +#endif + +BOOL reset_could_continue = FALSE; + +rlevel++; +offsetcount &= (-2); + +wscount -= 2; +wscount = (wscount - (wscount % (INTS_PER_STATEBLOCK * 2))) / + (2 * INTS_PER_STATEBLOCK); + +DPRINTF(("\n%.*s---------------------\n" + "%.*sCall to internal_dfa_exec f=%d\n", + rlevel*2-2, SP, rlevel*2-2, SP, rlevel)); + +ctypes = md->tables + ctypes_offset; +lcc = md->tables + lcc_offset; +fcc = md->tables + fcc_offset; + +match_count = PCRE_ERROR_NOMATCH; /* A negative number */ + +active_states = (stateblock *)(workspace + 2); +next_new_state = new_states = active_states + wscount; +new_count = 0; + +first_op = this_start_code + 1 + LINK_SIZE + + ((*this_start_code == OP_CBRA || *this_start_code == OP_SCBRA || + *this_start_code == OP_CBRAPOS || *this_start_code == OP_SCBRAPOS) + ? IMM2_SIZE:0); + +/* The first thing in any (sub) pattern is a bracket of some sort. Push all +the alternative states onto the list, and find out where the end is. This +makes is possible to use this function recursively, when we want to stop at a +matching internal ket rather than at the end. + +If the first opcode in the first alternative is OP_REVERSE, we are dealing with +a backward assertion. In that case, we have to find out the maximum amount to +move back, and set up each alternative appropriately. */ + +if (*first_op == OP_REVERSE) + { + int max_back = 0; + int gone_back; + + end_code = this_start_code; + do + { + int back = GET(end_code, 2+LINK_SIZE); + if (back > max_back) max_back = back; + end_code += GET(end_code, 1); + } + while (*end_code == OP_ALT); + + /* If we can't go back the amount required for the longest lookbehind + pattern, go back as far as we can; some alternatives may still be viable. */ + +#ifdef SUPPORT_UTF + /* In character mode we have to step back character by character */ + + if (utf) + { + for (gone_back = 0; gone_back < max_back; gone_back++) + { + if (current_subject <= start_subject) break; + current_subject--; + ACROSSCHAR(current_subject > start_subject, *current_subject, current_subject--); + } + } + else +#endif + + /* In byte-mode we can do this quickly. */ + + { + gone_back = (current_subject - max_back < start_subject)? + (int)(current_subject - start_subject) : max_back; + current_subject -= gone_back; + } + + /* Save the earliest consulted character */ + + if (current_subject < md->start_used_ptr) + md->start_used_ptr = current_subject; + + /* Now we can process the individual branches. */ + + end_code = this_start_code; + do + { + int back = GET(end_code, 2+LINK_SIZE); + if (back <= gone_back) + { + int bstate = (int)(end_code - start_code + 2 + 2*LINK_SIZE); + ADD_NEW_DATA(-bstate, 0, gone_back - back); + } + end_code += GET(end_code, 1); + } + while (*end_code == OP_ALT); + } + +/* This is the code for a "normal" subpattern (not a backward assertion). The +start of a whole pattern is always one of these. If we are at the top level, +we may be asked to restart matching from the same point that we reached for a +previous partial match. We still have to scan through the top-level branches to +find the end state. */ + +else + { + end_code = this_start_code; + + /* Restarting */ + + if (rlevel == 1 && (md->moptions & PCRE_DFA_RESTART) != 0) + { + do { end_code += GET(end_code, 1); } while (*end_code == OP_ALT); + new_count = workspace[1]; + if (!workspace[0]) + memcpy(new_states, active_states, new_count * sizeof(stateblock)); + } + + /* Not restarting */ + + else + { + int length = 1 + LINK_SIZE + + ((*this_start_code == OP_CBRA || *this_start_code == OP_SCBRA || + *this_start_code == OP_CBRAPOS || *this_start_code == OP_SCBRAPOS) + ? IMM2_SIZE:0); + do + { + ADD_NEW((int)(end_code - start_code + length), 0); + end_code += GET(end_code, 1); + length = 1 + LINK_SIZE; + } + while (*end_code == OP_ALT); + } + } + +workspace[0] = 0; /* Bit indicating which vector is current */ + +DPRINTF(("%.*sEnd state = %d\n", rlevel*2-2, SP, (int)(end_code - start_code))); + +/* Loop for scanning the subject */ + +ptr = current_subject; +for (;;) + { + int i, j; + int clen, dlen; + pcre_uint32 c, d; + int forced_fail = 0; + BOOL partial_newline = FALSE; + BOOL could_continue = reset_could_continue; + reset_could_continue = FALSE; + + /* Make the new state list into the active state list and empty the + new state list. */ + + temp_states = active_states; + active_states = new_states; + new_states = temp_states; + active_count = new_count; + new_count = 0; + + workspace[0] ^= 1; /* Remember for the restarting feature */ + workspace[1] = active_count; + +#ifdef PCRE_DEBUG + printf("%.*sNext character: rest of subject = \"", rlevel*2-2, SP); + pchars(ptr, STRLEN_UC(ptr), stdout); + printf("\"\n"); + + printf("%.*sActive states: ", rlevel*2-2, SP); + for (i = 0; i < active_count; i++) + printf("%d/%d ", active_states[i].offset, active_states[i].count); + printf("\n"); +#endif + + /* Set the pointers for adding new states */ + + next_active_state = active_states + active_count; + next_new_state = new_states; + + /* Load the current character from the subject outside the loop, as many + different states may want to look at it, and we assume that at least one + will. */ + + if (ptr < end_subject) + { + clen = 1; /* Number of data items in the character */ +#ifdef SUPPORT_UTF + GETCHARLENTEST(c, ptr, clen); +#else + c = *ptr; +#endif /* SUPPORT_UTF */ + } + else + { + clen = 0; /* This indicates the end of the subject */ + c = NOTACHAR; /* This value should never actually be used */ + } + + /* Scan up the active states and act on each one. The result of an action + may be to add more states to the currently active list (e.g. on hitting a + parenthesis) or it may be to put states on the new list, for considering + when we move the character pointer on. */ + + for (i = 0; i < active_count; i++) + { + stateblock *current_state = active_states + i; + BOOL caseless = FALSE; + const pcre_uchar *code; + int state_offset = current_state->offset; + int codevalue, rrc; + int count; + +#ifdef PCRE_DEBUG + printf ("%.*sProcessing state %d c=", rlevel*2-2, SP, state_offset); + if (clen == 0) printf("EOL\n"); + else if (c > 32 && c < 127) printf("'%c'\n", c); + else printf("0x%02x\n", c); +#endif + + /* A negative offset is a special case meaning "hold off going to this + (negated) state until the number of characters in the data field have + been skipped". If the could_continue flag was passed over from a previous + state, arrange for it to passed on. */ + + if (state_offset < 0) + { + if (current_state->data > 0) + { + DPRINTF(("%.*sSkipping this character\n", rlevel*2-2, SP)); + ADD_NEW_DATA(state_offset, current_state->count, + current_state->data - 1); + if (could_continue) reset_could_continue = TRUE; + continue; + } + else + { + current_state->offset = state_offset = -state_offset; + } + } + + /* Check for a duplicate state with the same count, and skip if found. + See the note at the head of this module about the possibility of improving + performance here. */ + + for (j = 0; j < i; j++) + { + if (active_states[j].offset == state_offset && + active_states[j].count == current_state->count) + { + DPRINTF(("%.*sDuplicate state: skipped\n", rlevel*2-2, SP)); + goto NEXT_ACTIVE_STATE; + } + } + + /* The state offset is the offset to the opcode */ + + code = start_code + state_offset; + codevalue = *code; + + /* If this opcode inspects a character, but we are at the end of the + subject, remember the fact for use when testing for a partial match. */ + + if (clen == 0 && poptable[codevalue] != 0) + could_continue = TRUE; + + /* If this opcode is followed by an inline character, load it. It is + tempting to test for the presence of a subject character here, but that + is wrong, because sometimes zero repetitions of the subject are + permitted. + + We also use this mechanism for opcodes such as OP_TYPEPLUS that take an + argument that is not a data character - but is always one byte long because + the values are small. We have to take special action to deal with \P, \p, + \H, \h, \V, \v and \X in this case. To keep the other cases fast, convert + these ones to new opcodes. */ + + if (coptable[codevalue] > 0) + { + dlen = 1; +#ifdef SUPPORT_UTF + if (utf) { GETCHARLEN(d, (code + coptable[codevalue]), dlen); } else +#endif /* SUPPORT_UTF */ + d = code[coptable[codevalue]]; + if (codevalue >= OP_TYPESTAR) + { + switch(d) + { + case OP_ANYBYTE: return PCRE_ERROR_DFA_UITEM; + case OP_NOTPROP: + case OP_PROP: codevalue += OP_PROP_EXTRA; break; + case OP_ANYNL: codevalue += OP_ANYNL_EXTRA; break; + case OP_EXTUNI: codevalue += OP_EXTUNI_EXTRA; break; + case OP_NOT_HSPACE: + case OP_HSPACE: codevalue += OP_HSPACE_EXTRA; break; + case OP_NOT_VSPACE: + case OP_VSPACE: codevalue += OP_VSPACE_EXTRA; break; + default: break; + } + } + } + else + { + dlen = 0; /* Not strictly necessary, but compilers moan */ + d = NOTACHAR; /* if these variables are not set. */ + } + + + /* Now process the individual opcodes */ + + switch (codevalue) + { +/* ========================================================================== */ + /* These cases are never obeyed. This is a fudge that causes a compile- + time error if the vectors coptable or poptable, which are indexed by + opcode, are not the correct length. It seems to be the only way to do + such a check at compile time, as the sizeof() operator does not work + in the C preprocessor. */ + + case OP_TABLE_LENGTH: + case OP_TABLE_LENGTH + + ((sizeof(coptable) == OP_TABLE_LENGTH) && + (sizeof(poptable) == OP_TABLE_LENGTH)): + break; + +/* ========================================================================== */ + /* Reached a closing bracket. If not at the end of the pattern, carry + on with the next opcode. For repeating opcodes, also add the repeat + state. Note that KETRPOS will always be encountered at the end of the + subpattern, because the possessive subpattern repeats are always handled + using recursive calls. Thus, it never adds any new states. + + At the end of the (sub)pattern, unless we have an empty string and + PCRE_NOTEMPTY is set, or PCRE_NOTEMPTY_ATSTART is set and we are at the + start of the subject, save the match data, shifting up all previous + matches so we always have the longest first. */ + + case OP_KET: + case OP_KETRMIN: + case OP_KETRMAX: + case OP_KETRPOS: + if (code != end_code) + { + ADD_ACTIVE(state_offset + 1 + LINK_SIZE, 0); + if (codevalue != OP_KET) + { + ADD_ACTIVE(state_offset - GET(code, 1), 0); + } + } + else + { + if (ptr > current_subject || + ((md->moptions & PCRE_NOTEMPTY) == 0 && + ((md->moptions & PCRE_NOTEMPTY_ATSTART) == 0 || + current_subject > start_subject + md->start_offset))) + { + if (match_count < 0) match_count = (offsetcount >= 2)? 1 : 0; + else if (match_count > 0 && ++match_count * 2 > offsetcount) + match_count = 0; + count = ((match_count == 0)? offsetcount : match_count * 2) - 2; + if (count > 0) memmove(offsets + 2, offsets, count * sizeof(int)); + if (offsetcount >= 2) + { + offsets[0] = (int)(current_subject - start_subject); + offsets[1] = (int)(ptr - start_subject); + DPRINTF(("%.*sSet matched string = \"%.*s\"\n", rlevel*2-2, SP, + offsets[1] - offsets[0], (char *)current_subject)); + } + if ((md->moptions & PCRE_DFA_SHORTEST) != 0) + { + DPRINTF(("%.*sEnd of internal_dfa_exec %d: returning %d\n" + "%.*s---------------------\n\n", rlevel*2-2, SP, rlevel, + match_count, rlevel*2-2, SP)); + return match_count; + } + } + } + break; + +/* ========================================================================== */ + /* These opcodes add to the current list of states without looking + at the current character. */ + + /*-----------------------------------------------------------------*/ + case OP_ALT: + do { code += GET(code, 1); } while (*code == OP_ALT); + ADD_ACTIVE((int)(code - start_code), 0); + break; + + /*-----------------------------------------------------------------*/ + case OP_BRA: + case OP_SBRA: + do + { + ADD_ACTIVE((int)(code - start_code + 1 + LINK_SIZE), 0); + code += GET(code, 1); + } + while (*code == OP_ALT); + break; + + /*-----------------------------------------------------------------*/ + case OP_CBRA: + case OP_SCBRA: + ADD_ACTIVE((int)(code - start_code + 1 + LINK_SIZE + IMM2_SIZE), 0); + code += GET(code, 1); + while (*code == OP_ALT) + { + ADD_ACTIVE((int)(code - start_code + 1 + LINK_SIZE), 0); + code += GET(code, 1); + } + break; + + /*-----------------------------------------------------------------*/ + case OP_BRAZERO: + case OP_BRAMINZERO: + ADD_ACTIVE(state_offset + 1, 0); + code += 1 + GET(code, 2); + while (*code == OP_ALT) code += GET(code, 1); + ADD_ACTIVE((int)(code - start_code + 1 + LINK_SIZE), 0); + break; + + /*-----------------------------------------------------------------*/ + case OP_SKIPZERO: + code += 1 + GET(code, 2); + while (*code == OP_ALT) code += GET(code, 1); + ADD_ACTIVE((int)(code - start_code + 1 + LINK_SIZE), 0); + break; + + /*-----------------------------------------------------------------*/ + case OP_CIRC: + if (ptr == start_subject && (md->moptions & PCRE_NOTBOL) == 0) + { ADD_ACTIVE(state_offset + 1, 0); } + break; + + /*-----------------------------------------------------------------*/ + case OP_CIRCM: + if ((ptr == start_subject && (md->moptions & PCRE_NOTBOL) == 0) || + (ptr != end_subject && WAS_NEWLINE(ptr))) + { ADD_ACTIVE(state_offset + 1, 0); } + break; + + /*-----------------------------------------------------------------*/ + case OP_EOD: + if (ptr >= end_subject) + { + if ((md->moptions & PCRE_PARTIAL_HARD) != 0) + could_continue = TRUE; + else { ADD_ACTIVE(state_offset + 1, 0); } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_SOD: + if (ptr == start_subject) { ADD_ACTIVE(state_offset + 1, 0); } + break; + + /*-----------------------------------------------------------------*/ + case OP_SOM: + if (ptr == start_subject + start_offset) { ADD_ACTIVE(state_offset + 1, 0); } + break; + + +/* ========================================================================== */ + /* These opcodes inspect the next subject character, and sometimes + the previous one as well, but do not have an argument. The variable + clen contains the length of the current character and is zero if we are + at the end of the subject. */ + + /*-----------------------------------------------------------------*/ + case OP_ANY: + if (clen > 0 && !IS_NEWLINE(ptr)) + { + if (ptr + 1 >= md->end_subject && + (md->moptions & (PCRE_PARTIAL_HARD)) != 0 && + NLBLOCK->nltype == NLTYPE_FIXED && + NLBLOCK->nllen == 2 && + c == NLBLOCK->nl[0]) + { + could_continue = partial_newline = TRUE; + } + else + { + ADD_NEW(state_offset + 1, 0); + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_ALLANY: + if (clen > 0) + { ADD_NEW(state_offset + 1, 0); } + break; + + /*-----------------------------------------------------------------*/ + case OP_EODN: + if (clen == 0 && (md->moptions & PCRE_PARTIAL_HARD) != 0) + could_continue = TRUE; + else if (clen == 0 || (IS_NEWLINE(ptr) && ptr == end_subject - md->nllen)) + { ADD_ACTIVE(state_offset + 1, 0); } + break; + + /*-----------------------------------------------------------------*/ + case OP_DOLL: + if ((md->moptions & PCRE_NOTEOL) == 0) + { + if (clen == 0 && (md->moptions & PCRE_PARTIAL_HARD) != 0) + could_continue = TRUE; + else if (clen == 0 || + ((md->poptions & PCRE_DOLLAR_ENDONLY) == 0 && IS_NEWLINE(ptr) && + (ptr == end_subject - md->nllen) + )) + { ADD_ACTIVE(state_offset + 1, 0); } + else if (ptr + 1 >= md->end_subject && + (md->moptions & (PCRE_PARTIAL_HARD|PCRE_PARTIAL_SOFT)) != 0 && + NLBLOCK->nltype == NLTYPE_FIXED && + NLBLOCK->nllen == 2 && + c == NLBLOCK->nl[0]) + { + if ((md->moptions & PCRE_PARTIAL_HARD) != 0) + { + reset_could_continue = TRUE; + ADD_NEW_DATA(-(state_offset + 1), 0, 1); + } + else could_continue = partial_newline = TRUE; + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_DOLLM: + if ((md->moptions & PCRE_NOTEOL) == 0) + { + if (clen == 0 && (md->moptions & PCRE_PARTIAL_HARD) != 0) + could_continue = TRUE; + else if (clen == 0 || + ((md->poptions & PCRE_DOLLAR_ENDONLY) == 0 && IS_NEWLINE(ptr))) + { ADD_ACTIVE(state_offset + 1, 0); } + else if (ptr + 1 >= md->end_subject && + (md->moptions & (PCRE_PARTIAL_HARD|PCRE_PARTIAL_SOFT)) != 0 && + NLBLOCK->nltype == NLTYPE_FIXED && + NLBLOCK->nllen == 2 && + c == NLBLOCK->nl[0]) + { + if ((md->moptions & PCRE_PARTIAL_HARD) != 0) + { + reset_could_continue = TRUE; + ADD_NEW_DATA(-(state_offset + 1), 0, 1); + } + else could_continue = partial_newline = TRUE; + } + } + else if (IS_NEWLINE(ptr)) + { ADD_ACTIVE(state_offset + 1, 0); } + break; + + /*-----------------------------------------------------------------*/ + + case OP_DIGIT: + case OP_WHITESPACE: + case OP_WORDCHAR: + if (clen > 0 && c < 256 && + ((ctypes[c] & toptable1[codevalue]) ^ toptable2[codevalue]) != 0) + { ADD_NEW(state_offset + 1, 0); } + break; + + /*-----------------------------------------------------------------*/ + case OP_NOT_DIGIT: + case OP_NOT_WHITESPACE: + case OP_NOT_WORDCHAR: + if (clen > 0 && (c >= 256 || + ((ctypes[c] & toptable1[codevalue]) ^ toptable2[codevalue]) != 0)) + { ADD_NEW(state_offset + 1, 0); } + break; + + /*-----------------------------------------------------------------*/ + case OP_WORD_BOUNDARY: + case OP_NOT_WORD_BOUNDARY: + { + int left_word, right_word; + + if (ptr > start_subject) + { + const pcre_uchar *temp = ptr - 1; + if (temp < md->start_used_ptr) md->start_used_ptr = temp; +#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 + if (utf) { BACKCHAR(temp); } +#endif + GETCHARTEST(d, temp); +#ifdef SUPPORT_UCP + if ((md->poptions & PCRE_UCP) != 0) + { + if (d == '_') left_word = TRUE; else + { + int cat = UCD_CATEGORY(d); + left_word = (cat == ucp_L || cat == ucp_N); + } + } + else +#endif + left_word = d < 256 && (ctypes[d] & ctype_word) != 0; + } + else left_word = FALSE; + + if (clen > 0) + { +#ifdef SUPPORT_UCP + if ((md->poptions & PCRE_UCP) != 0) + { + if (c == '_') right_word = TRUE; else + { + int cat = UCD_CATEGORY(c); + right_word = (cat == ucp_L || cat == ucp_N); + } + } + else +#endif + right_word = c < 256 && (ctypes[c] & ctype_word) != 0; + } + else right_word = FALSE; + + if ((left_word == right_word) == (codevalue == OP_NOT_WORD_BOUNDARY)) + { ADD_ACTIVE(state_offset + 1, 0); } + } + break; + + + /*-----------------------------------------------------------------*/ + /* Check the next character by Unicode property. We will get here only + if the support is in the binary; otherwise a compile-time error occurs. + */ + +#ifdef SUPPORT_UCP + case OP_PROP: + case OP_NOTPROP: + if (clen > 0) + { + BOOL OK; + const pcre_uint32 *cp; + const ucd_record * prop = GET_UCD(c); + switch(code[1]) + { + case PT_ANY: + OK = TRUE; + break; + + case PT_LAMP: + OK = prop->chartype == ucp_Lu || prop->chartype == ucp_Ll || + prop->chartype == ucp_Lt; + break; + + case PT_GC: + OK = PRIV(ucp_gentype)[prop->chartype] == code[2]; + break; + + case PT_PC: + OK = prop->chartype == code[2]; + break; + + case PT_SC: + OK = prop->script == code[2]; + break; + + /* These are specials for combination cases. */ + + case PT_ALNUM: + OK = PRIV(ucp_gentype)[prop->chartype] == ucp_L || + PRIV(ucp_gentype)[prop->chartype] == ucp_N; + break; + + /* Perl space used to exclude VT, but from Perl 5.18 it is included, + which means that Perl space and POSIX space are now identical. PCRE + was changed at release 8.34. */ + + case PT_SPACE: /* Perl space */ + case PT_PXSPACE: /* POSIX space */ + switch(c) + { + HSPACE_CASES: + VSPACE_CASES: + OK = TRUE; + break; + + default: + OK = PRIV(ucp_gentype)[prop->chartype] == ucp_Z; + break; + } + break; + + case PT_WORD: + OK = PRIV(ucp_gentype)[prop->chartype] == ucp_L || + PRIV(ucp_gentype)[prop->chartype] == ucp_N || + c == CHAR_UNDERSCORE; + break; + + case PT_CLIST: + cp = PRIV(ucd_caseless_sets) + code[2]; + for (;;) + { + if (c < *cp) { OK = FALSE; break; } + if (c == *cp++) { OK = TRUE; break; } + } + break; + + case PT_UCNC: + OK = c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT || + c == CHAR_GRAVE_ACCENT || (c >= 0xa0 && c <= 0xd7ff) || + c >= 0xe000; + break; + + /* Should never occur, but keep compilers from grumbling. */ + + default: + OK = codevalue != OP_PROP; + break; + } + + if (OK == (codevalue == OP_PROP)) { ADD_NEW(state_offset + 3, 0); } + } + break; +#endif + + + +/* ========================================================================== */ + /* These opcodes likewise inspect the subject character, but have an + argument that is not a data character. It is one of these opcodes: + OP_ANY, OP_ALLANY, OP_DIGIT, OP_NOT_DIGIT, OP_WHITESPACE, OP_NOT_SPACE, + OP_WORDCHAR, OP_NOT_WORDCHAR. The value is loaded into d. */ + + case OP_TYPEPLUS: + case OP_TYPEMINPLUS: + case OP_TYPEPOSPLUS: + count = current_state->count; /* Already matched */ + if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } + if (clen > 0) + { + if (d == OP_ANY && ptr + 1 >= md->end_subject && + (md->moptions & (PCRE_PARTIAL_HARD)) != 0 && + NLBLOCK->nltype == NLTYPE_FIXED && + NLBLOCK->nllen == 2 && + c == NLBLOCK->nl[0]) + { + could_continue = partial_newline = TRUE; + } + else if ((c >= 256 && d != OP_DIGIT && d != OP_WHITESPACE && d != OP_WORDCHAR) || + (c < 256 && + (d != OP_ANY || !IS_NEWLINE(ptr)) && + ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) + { + if (count > 0 && codevalue == OP_TYPEPOSPLUS) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + count++; + ADD_NEW(state_offset, count); + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_TYPEQUERY: + case OP_TYPEMINQUERY: + case OP_TYPEPOSQUERY: + ADD_ACTIVE(state_offset + 2, 0); + if (clen > 0) + { + if (d == OP_ANY && ptr + 1 >= md->end_subject && + (md->moptions & (PCRE_PARTIAL_HARD)) != 0 && + NLBLOCK->nltype == NLTYPE_FIXED && + NLBLOCK->nllen == 2 && + c == NLBLOCK->nl[0]) + { + could_continue = partial_newline = TRUE; + } + else if ((c >= 256 && d != OP_DIGIT && d != OP_WHITESPACE && d != OP_WORDCHAR) || + (c < 256 && + (d != OP_ANY || !IS_NEWLINE(ptr)) && + ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) + { + if (codevalue == OP_TYPEPOSQUERY) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + ADD_NEW(state_offset + 2, 0); + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_TYPESTAR: + case OP_TYPEMINSTAR: + case OP_TYPEPOSSTAR: + ADD_ACTIVE(state_offset + 2, 0); + if (clen > 0) + { + if (d == OP_ANY && ptr + 1 >= md->end_subject && + (md->moptions & (PCRE_PARTIAL_HARD)) != 0 && + NLBLOCK->nltype == NLTYPE_FIXED && + NLBLOCK->nllen == 2 && + c == NLBLOCK->nl[0]) + { + could_continue = partial_newline = TRUE; + } + else if ((c >= 256 && d != OP_DIGIT && d != OP_WHITESPACE && d != OP_WORDCHAR) || + (c < 256 && + (d != OP_ANY || !IS_NEWLINE(ptr)) && + ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) + { + if (codevalue == OP_TYPEPOSSTAR) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + ADD_NEW(state_offset, 0); + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_TYPEEXACT: + count = current_state->count; /* Number already matched */ + if (clen > 0) + { + if (d == OP_ANY && ptr + 1 >= md->end_subject && + (md->moptions & (PCRE_PARTIAL_HARD)) != 0 && + NLBLOCK->nltype == NLTYPE_FIXED && + NLBLOCK->nllen == 2 && + c == NLBLOCK->nl[0]) + { + could_continue = partial_newline = TRUE; + } + else if ((c >= 256 && d != OP_DIGIT && d != OP_WHITESPACE && d != OP_WORDCHAR) || + (c < 256 && + (d != OP_ANY || !IS_NEWLINE(ptr)) && + ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) + { + if (++count >= (int)GET2(code, 1)) + { ADD_NEW(state_offset + 1 + IMM2_SIZE + 1, 0); } + else + { ADD_NEW(state_offset, count); } + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_TYPEUPTO: + case OP_TYPEMINUPTO: + case OP_TYPEPOSUPTO: + ADD_ACTIVE(state_offset + 2 + IMM2_SIZE, 0); + count = current_state->count; /* Number already matched */ + if (clen > 0) + { + if (d == OP_ANY && ptr + 1 >= md->end_subject && + (md->moptions & (PCRE_PARTIAL_HARD)) != 0 && + NLBLOCK->nltype == NLTYPE_FIXED && + NLBLOCK->nllen == 2 && + c == NLBLOCK->nl[0]) + { + could_continue = partial_newline = TRUE; + } + else if ((c >= 256 && d != OP_DIGIT && d != OP_WHITESPACE && d != OP_WORDCHAR) || + (c < 256 && + (d != OP_ANY || !IS_NEWLINE(ptr)) && + ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) + { + if (codevalue == OP_TYPEPOSUPTO) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + if (++count >= (int)GET2(code, 1)) + { ADD_NEW(state_offset + 2 + IMM2_SIZE, 0); } + else + { ADD_NEW(state_offset, count); } + } + } + break; + +/* ========================================================================== */ + /* These are virtual opcodes that are used when something like + OP_TYPEPLUS has OP_PROP, OP_NOTPROP, OP_ANYNL, or OP_EXTUNI as its + argument. It keeps the code above fast for the other cases. The argument + is in the d variable. */ + +#ifdef SUPPORT_UCP + case OP_PROP_EXTRA + OP_TYPEPLUS: + case OP_PROP_EXTRA + OP_TYPEMINPLUS: + case OP_PROP_EXTRA + OP_TYPEPOSPLUS: + count = current_state->count; /* Already matched */ + if (count > 0) { ADD_ACTIVE(state_offset + 4, 0); } + if (clen > 0) + { + BOOL OK; + const pcre_uint32 *cp; + const ucd_record * prop = GET_UCD(c); + switch(code[2]) + { + case PT_ANY: + OK = TRUE; + break; + + case PT_LAMP: + OK = prop->chartype == ucp_Lu || prop->chartype == ucp_Ll || + prop->chartype == ucp_Lt; + break; + + case PT_GC: + OK = PRIV(ucp_gentype)[prop->chartype] == code[3]; + break; + + case PT_PC: + OK = prop->chartype == code[3]; + break; + + case PT_SC: + OK = prop->script == code[3]; + break; + + /* These are specials for combination cases. */ + + case PT_ALNUM: + OK = PRIV(ucp_gentype)[prop->chartype] == ucp_L || + PRIV(ucp_gentype)[prop->chartype] == ucp_N; + break; + + /* Perl space used to exclude VT, but from Perl 5.18 it is included, + which means that Perl space and POSIX space are now identical. PCRE + was changed at release 8.34. */ + + case PT_SPACE: /* Perl space */ + case PT_PXSPACE: /* POSIX space */ + switch(c) + { + HSPACE_CASES: + VSPACE_CASES: + OK = TRUE; + break; + + default: + OK = PRIV(ucp_gentype)[prop->chartype] == ucp_Z; + break; + } + break; + + case PT_WORD: + OK = PRIV(ucp_gentype)[prop->chartype] == ucp_L || + PRIV(ucp_gentype)[prop->chartype] == ucp_N || + c == CHAR_UNDERSCORE; + break; + + case PT_CLIST: + cp = PRIV(ucd_caseless_sets) + code[3]; + for (;;) + { + if (c < *cp) { OK = FALSE; break; } + if (c == *cp++) { OK = TRUE; break; } + } + break; + + case PT_UCNC: + OK = c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT || + c == CHAR_GRAVE_ACCENT || (c >= 0xa0 && c <= 0xd7ff) || + c >= 0xe000; + break; + + /* Should never occur, but keep compilers from grumbling. */ + + default: + OK = codevalue != OP_PROP; + break; + } + + if (OK == (d == OP_PROP)) + { + if (count > 0 && codevalue == OP_PROP_EXTRA + OP_TYPEPOSPLUS) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + count++; + ADD_NEW(state_offset, count); + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_EXTUNI_EXTRA + OP_TYPEPLUS: + case OP_EXTUNI_EXTRA + OP_TYPEMINPLUS: + case OP_EXTUNI_EXTRA + OP_TYPEPOSPLUS: + count = current_state->count; /* Already matched */ + if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } + if (clen > 0) + { + int lgb, rgb; + const pcre_uchar *nptr = ptr + clen; + int ncount = 0; + if (count > 0 && codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSPLUS) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + lgb = UCD_GRAPHBREAK(c); + while (nptr < end_subject) + { + dlen = 1; + if (!utf) d = *nptr; else { GETCHARLEN(d, nptr, dlen); } + rgb = UCD_GRAPHBREAK(d); + if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break; + ncount++; + lgb = rgb; + nptr += dlen; + } + count++; + ADD_NEW_DATA(-state_offset, count, ncount); + } + break; +#endif + + /*-----------------------------------------------------------------*/ + case OP_ANYNL_EXTRA + OP_TYPEPLUS: + case OP_ANYNL_EXTRA + OP_TYPEMINPLUS: + case OP_ANYNL_EXTRA + OP_TYPEPOSPLUS: + count = current_state->count; /* Already matched */ + if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } + if (clen > 0) + { + int ncount = 0; + switch (c) + { + case CHAR_VT: + case CHAR_FF: + case CHAR_NEL: +#ifndef EBCDIC + case 0x2028: + case 0x2029: +#endif /* Not EBCDIC */ + if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; + goto ANYNL01; + + case CHAR_CR: + if (ptr + 1 < end_subject && UCHAR21TEST(ptr + 1) == CHAR_LF) ncount = 1; + /* Fall through */ + + ANYNL01: + case CHAR_LF: + if (count > 0 && codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSPLUS) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + count++; + ADD_NEW_DATA(-state_offset, count, ncount); + break; + + default: + break; + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_VSPACE_EXTRA + OP_TYPEPLUS: + case OP_VSPACE_EXTRA + OP_TYPEMINPLUS: + case OP_VSPACE_EXTRA + OP_TYPEPOSPLUS: + count = current_state->count; /* Already matched */ + if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } + if (clen > 0) + { + BOOL OK; + switch (c) + { + VSPACE_CASES: + OK = TRUE; + break; + + default: + OK = FALSE; + break; + } + + if (OK == (d == OP_VSPACE)) + { + if (count > 0 && codevalue == OP_VSPACE_EXTRA + OP_TYPEPOSPLUS) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + count++; + ADD_NEW_DATA(-state_offset, count, 0); + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_HSPACE_EXTRA + OP_TYPEPLUS: + case OP_HSPACE_EXTRA + OP_TYPEMINPLUS: + case OP_HSPACE_EXTRA + OP_TYPEPOSPLUS: + count = current_state->count; /* Already matched */ + if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } + if (clen > 0) + { + BOOL OK; + switch (c) + { + HSPACE_CASES: + OK = TRUE; + break; + + default: + OK = FALSE; + break; + } + + if (OK == (d == OP_HSPACE)) + { + if (count > 0 && codevalue == OP_HSPACE_EXTRA + OP_TYPEPOSPLUS) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + count++; + ADD_NEW_DATA(-state_offset, count, 0); + } + } + break; + + /*-----------------------------------------------------------------*/ +#ifdef SUPPORT_UCP + case OP_PROP_EXTRA + OP_TYPEQUERY: + case OP_PROP_EXTRA + OP_TYPEMINQUERY: + case OP_PROP_EXTRA + OP_TYPEPOSQUERY: + count = 4; + goto QS1; + + case OP_PROP_EXTRA + OP_TYPESTAR: + case OP_PROP_EXTRA + OP_TYPEMINSTAR: + case OP_PROP_EXTRA + OP_TYPEPOSSTAR: + count = 0; + + QS1: + + ADD_ACTIVE(state_offset + 4, 0); + if (clen > 0) + { + BOOL OK; + const pcre_uint32 *cp; + const ucd_record * prop = GET_UCD(c); + switch(code[2]) + { + case PT_ANY: + OK = TRUE; + break; + + case PT_LAMP: + OK = prop->chartype == ucp_Lu || prop->chartype == ucp_Ll || + prop->chartype == ucp_Lt; + break; + + case PT_GC: + OK = PRIV(ucp_gentype)[prop->chartype] == code[3]; + break; + + case PT_PC: + OK = prop->chartype == code[3]; + break; + + case PT_SC: + OK = prop->script == code[3]; + break; + + /* These are specials for combination cases. */ + + case PT_ALNUM: + OK = PRIV(ucp_gentype)[prop->chartype] == ucp_L || + PRIV(ucp_gentype)[prop->chartype] == ucp_N; + break; + + /* Perl space used to exclude VT, but from Perl 5.18 it is included, + which means that Perl space and POSIX space are now identical. PCRE + was changed at release 8.34. */ + + case PT_SPACE: /* Perl space */ + case PT_PXSPACE: /* POSIX space */ + switch(c) + { + HSPACE_CASES: + VSPACE_CASES: + OK = TRUE; + break; + + default: + OK = PRIV(ucp_gentype)[prop->chartype] == ucp_Z; + break; + } + break; + + case PT_WORD: + OK = PRIV(ucp_gentype)[prop->chartype] == ucp_L || + PRIV(ucp_gentype)[prop->chartype] == ucp_N || + c == CHAR_UNDERSCORE; + break; + + case PT_CLIST: + cp = PRIV(ucd_caseless_sets) + code[3]; + for (;;) + { + if (c < *cp) { OK = FALSE; break; } + if (c == *cp++) { OK = TRUE; break; } + } + break; + + case PT_UCNC: + OK = c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT || + c == CHAR_GRAVE_ACCENT || (c >= 0xa0 && c <= 0xd7ff) || + c >= 0xe000; + break; + + /* Should never occur, but keep compilers from grumbling. */ + + default: + OK = codevalue != OP_PROP; + break; + } + + if (OK == (d == OP_PROP)) + { + if (codevalue == OP_PROP_EXTRA + OP_TYPEPOSSTAR || + codevalue == OP_PROP_EXTRA + OP_TYPEPOSQUERY) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + ADD_NEW(state_offset + count, 0); + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_EXTUNI_EXTRA + OP_TYPEQUERY: + case OP_EXTUNI_EXTRA + OP_TYPEMINQUERY: + case OP_EXTUNI_EXTRA + OP_TYPEPOSQUERY: + count = 2; + goto QS2; + + case OP_EXTUNI_EXTRA + OP_TYPESTAR: + case OP_EXTUNI_EXTRA + OP_TYPEMINSTAR: + case OP_EXTUNI_EXTRA + OP_TYPEPOSSTAR: + count = 0; + + QS2: + + ADD_ACTIVE(state_offset + 2, 0); + if (clen > 0) + { + int lgb, rgb; + const pcre_uchar *nptr = ptr + clen; + int ncount = 0; + if (codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSSTAR || + codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSQUERY) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + lgb = UCD_GRAPHBREAK(c); + while (nptr < end_subject) + { + dlen = 1; + if (!utf) d = *nptr; else { GETCHARLEN(d, nptr, dlen); } + rgb = UCD_GRAPHBREAK(d); + if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break; + ncount++; + lgb = rgb; + nptr += dlen; + } + ADD_NEW_DATA(-(state_offset + count), 0, ncount); + } + break; +#endif + + /*-----------------------------------------------------------------*/ + case OP_ANYNL_EXTRA + OP_TYPEQUERY: + case OP_ANYNL_EXTRA + OP_TYPEMINQUERY: + case OP_ANYNL_EXTRA + OP_TYPEPOSQUERY: + count = 2; + goto QS3; + + case OP_ANYNL_EXTRA + OP_TYPESTAR: + case OP_ANYNL_EXTRA + OP_TYPEMINSTAR: + case OP_ANYNL_EXTRA + OP_TYPEPOSSTAR: + count = 0; + + QS3: + ADD_ACTIVE(state_offset + 2, 0); + if (clen > 0) + { + int ncount = 0; + switch (c) + { + case CHAR_VT: + case CHAR_FF: + case CHAR_NEL: +#ifndef EBCDIC + case 0x2028: + case 0x2029: +#endif /* Not EBCDIC */ + if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; + goto ANYNL02; + + case CHAR_CR: + if (ptr + 1 < end_subject && UCHAR21TEST(ptr + 1) == CHAR_LF) ncount = 1; + /* Fall through */ + + ANYNL02: + case CHAR_LF: + if (codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSSTAR || + codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSQUERY) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + ADD_NEW_DATA(-(state_offset + (int)count), 0, ncount); + break; + + default: + break; + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_VSPACE_EXTRA + OP_TYPEQUERY: + case OP_VSPACE_EXTRA + OP_TYPEMINQUERY: + case OP_VSPACE_EXTRA + OP_TYPEPOSQUERY: + count = 2; + goto QS4; + + case OP_VSPACE_EXTRA + OP_TYPESTAR: + case OP_VSPACE_EXTRA + OP_TYPEMINSTAR: + case OP_VSPACE_EXTRA + OP_TYPEPOSSTAR: + count = 0; + + QS4: + ADD_ACTIVE(state_offset + 2, 0); + if (clen > 0) + { + BOOL OK; + switch (c) + { + VSPACE_CASES: + OK = TRUE; + break; + + default: + OK = FALSE; + break; + } + if (OK == (d == OP_VSPACE)) + { + if (codevalue == OP_VSPACE_EXTRA + OP_TYPEPOSSTAR || + codevalue == OP_VSPACE_EXTRA + OP_TYPEPOSQUERY) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + ADD_NEW_DATA(-(state_offset + (int)count), 0, 0); + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_HSPACE_EXTRA + OP_TYPEQUERY: + case OP_HSPACE_EXTRA + OP_TYPEMINQUERY: + case OP_HSPACE_EXTRA + OP_TYPEPOSQUERY: + count = 2; + goto QS5; + + case OP_HSPACE_EXTRA + OP_TYPESTAR: + case OP_HSPACE_EXTRA + OP_TYPEMINSTAR: + case OP_HSPACE_EXTRA + OP_TYPEPOSSTAR: + count = 0; + + QS5: + ADD_ACTIVE(state_offset + 2, 0); + if (clen > 0) + { + BOOL OK; + switch (c) + { + HSPACE_CASES: + OK = TRUE; + break; + + default: + OK = FALSE; + break; + } + + if (OK == (d == OP_HSPACE)) + { + if (codevalue == OP_HSPACE_EXTRA + OP_TYPEPOSSTAR || + codevalue == OP_HSPACE_EXTRA + OP_TYPEPOSQUERY) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + ADD_NEW_DATA(-(state_offset + (int)count), 0, 0); + } + } + break; + + /*-----------------------------------------------------------------*/ +#ifdef SUPPORT_UCP + case OP_PROP_EXTRA + OP_TYPEEXACT: + case OP_PROP_EXTRA + OP_TYPEUPTO: + case OP_PROP_EXTRA + OP_TYPEMINUPTO: + case OP_PROP_EXTRA + OP_TYPEPOSUPTO: + if (codevalue != OP_PROP_EXTRA + OP_TYPEEXACT) + { ADD_ACTIVE(state_offset + 1 + IMM2_SIZE + 3, 0); } + count = current_state->count; /* Number already matched */ + if (clen > 0) + { + BOOL OK; + const pcre_uint32 *cp; + const ucd_record * prop = GET_UCD(c); + switch(code[1 + IMM2_SIZE + 1]) + { + case PT_ANY: + OK = TRUE; + break; + + case PT_LAMP: + OK = prop->chartype == ucp_Lu || prop->chartype == ucp_Ll || + prop->chartype == ucp_Lt; + break; + + case PT_GC: + OK = PRIV(ucp_gentype)[prop->chartype] == code[1 + IMM2_SIZE + 2]; + break; + + case PT_PC: + OK = prop->chartype == code[1 + IMM2_SIZE + 2]; + break; + + case PT_SC: + OK = prop->script == code[1 + IMM2_SIZE + 2]; + break; + + /* These are specials for combination cases. */ + + case PT_ALNUM: + OK = PRIV(ucp_gentype)[prop->chartype] == ucp_L || + PRIV(ucp_gentype)[prop->chartype] == ucp_N; + break; + + /* Perl space used to exclude VT, but from Perl 5.18 it is included, + which means that Perl space and POSIX space are now identical. PCRE + was changed at release 8.34. */ + + case PT_SPACE: /* Perl space */ + case PT_PXSPACE: /* POSIX space */ + switch(c) + { + HSPACE_CASES: + VSPACE_CASES: + OK = TRUE; + break; + + default: + OK = PRIV(ucp_gentype)[prop->chartype] == ucp_Z; + break; + } + break; + + case PT_WORD: + OK = PRIV(ucp_gentype)[prop->chartype] == ucp_L || + PRIV(ucp_gentype)[prop->chartype] == ucp_N || + c == CHAR_UNDERSCORE; + break; + + case PT_CLIST: + cp = PRIV(ucd_caseless_sets) + code[1 + IMM2_SIZE + 2]; + for (;;) + { + if (c < *cp) { OK = FALSE; break; } + if (c == *cp++) { OK = TRUE; break; } + } + break; + + case PT_UCNC: + OK = c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT || + c == CHAR_GRAVE_ACCENT || (c >= 0xa0 && c <= 0xd7ff) || + c >= 0xe000; + break; + + /* Should never occur, but keep compilers from grumbling. */ + + default: + OK = codevalue != OP_PROP; + break; + } + + if (OK == (d == OP_PROP)) + { + if (codevalue == OP_PROP_EXTRA + OP_TYPEPOSUPTO) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + if (++count >= (int)GET2(code, 1)) + { ADD_NEW(state_offset + 1 + IMM2_SIZE + 3, 0); } + else + { ADD_NEW(state_offset, count); } + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_EXTUNI_EXTRA + OP_TYPEEXACT: + case OP_EXTUNI_EXTRA + OP_TYPEUPTO: + case OP_EXTUNI_EXTRA + OP_TYPEMINUPTO: + case OP_EXTUNI_EXTRA + OP_TYPEPOSUPTO: + if (codevalue != OP_EXTUNI_EXTRA + OP_TYPEEXACT) + { ADD_ACTIVE(state_offset + 2 + IMM2_SIZE, 0); } + count = current_state->count; /* Number already matched */ + if (clen > 0) + { + int lgb, rgb; + const pcre_uchar *nptr = ptr + clen; + int ncount = 0; + if (codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSUPTO) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + lgb = UCD_GRAPHBREAK(c); + while (nptr < end_subject) + { + dlen = 1; + if (!utf) d = *nptr; else { GETCHARLEN(d, nptr, dlen); } + rgb = UCD_GRAPHBREAK(d); + if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break; + ncount++; + lgb = rgb; + nptr += dlen; + } + if (nptr >= end_subject && (md->moptions & PCRE_PARTIAL_HARD) != 0) + reset_could_continue = TRUE; + if (++count >= (int)GET2(code, 1)) + { ADD_NEW_DATA(-(state_offset + 2 + IMM2_SIZE), 0, ncount); } + else + { ADD_NEW_DATA(-state_offset, count, ncount); } + } + break; +#endif + + /*-----------------------------------------------------------------*/ + case OP_ANYNL_EXTRA + OP_TYPEEXACT: + case OP_ANYNL_EXTRA + OP_TYPEUPTO: + case OP_ANYNL_EXTRA + OP_TYPEMINUPTO: + case OP_ANYNL_EXTRA + OP_TYPEPOSUPTO: + if (codevalue != OP_ANYNL_EXTRA + OP_TYPEEXACT) + { ADD_ACTIVE(state_offset + 2 + IMM2_SIZE, 0); } + count = current_state->count; /* Number already matched */ + if (clen > 0) + { + int ncount = 0; + switch (c) + { + case CHAR_VT: + case CHAR_FF: + case CHAR_NEL: +#ifndef EBCDIC + case 0x2028: + case 0x2029: +#endif /* Not EBCDIC */ + if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; + goto ANYNL03; + + case CHAR_CR: + if (ptr + 1 < end_subject && UCHAR21TEST(ptr + 1) == CHAR_LF) ncount = 1; + /* Fall through */ + + ANYNL03: + case CHAR_LF: + if (codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSUPTO) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + if (++count >= (int)GET2(code, 1)) + { ADD_NEW_DATA(-(state_offset + 2 + IMM2_SIZE), 0, ncount); } + else + { ADD_NEW_DATA(-state_offset, count, ncount); } + break; + + default: + break; + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_VSPACE_EXTRA + OP_TYPEEXACT: + case OP_VSPACE_EXTRA + OP_TYPEUPTO: + case OP_VSPACE_EXTRA + OP_TYPEMINUPTO: + case OP_VSPACE_EXTRA + OP_TYPEPOSUPTO: + if (codevalue != OP_VSPACE_EXTRA + OP_TYPEEXACT) + { ADD_ACTIVE(state_offset + 2 + IMM2_SIZE, 0); } + count = current_state->count; /* Number already matched */ + if (clen > 0) + { + BOOL OK; + switch (c) + { + VSPACE_CASES: + OK = TRUE; + break; + + default: + OK = FALSE; + } + + if (OK == (d == OP_VSPACE)) + { + if (codevalue == OP_VSPACE_EXTRA + OP_TYPEPOSUPTO) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + if (++count >= (int)GET2(code, 1)) + { ADD_NEW_DATA(-(state_offset + 2 + IMM2_SIZE), 0, 0); } + else + { ADD_NEW_DATA(-state_offset, count, 0); } + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_HSPACE_EXTRA + OP_TYPEEXACT: + case OP_HSPACE_EXTRA + OP_TYPEUPTO: + case OP_HSPACE_EXTRA + OP_TYPEMINUPTO: + case OP_HSPACE_EXTRA + OP_TYPEPOSUPTO: + if (codevalue != OP_HSPACE_EXTRA + OP_TYPEEXACT) + { ADD_ACTIVE(state_offset + 2 + IMM2_SIZE, 0); } + count = current_state->count; /* Number already matched */ + if (clen > 0) + { + BOOL OK; + switch (c) + { + HSPACE_CASES: + OK = TRUE; + break; + + default: + OK = FALSE; + break; + } + + if (OK == (d == OP_HSPACE)) + { + if (codevalue == OP_HSPACE_EXTRA + OP_TYPEPOSUPTO) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + if (++count >= (int)GET2(code, 1)) + { ADD_NEW_DATA(-(state_offset + 2 + IMM2_SIZE), 0, 0); } + else + { ADD_NEW_DATA(-state_offset, count, 0); } + } + } + break; + +/* ========================================================================== */ + /* These opcodes are followed by a character that is usually compared + to the current subject character; it is loaded into d. We still get + here even if there is no subject character, because in some cases zero + repetitions are permitted. */ + + /*-----------------------------------------------------------------*/ + case OP_CHAR: + if (clen > 0 && c == d) { ADD_NEW(state_offset + dlen + 1, 0); } + break; + + /*-----------------------------------------------------------------*/ + case OP_CHARI: + if (clen == 0) break; + +#ifdef SUPPORT_UTF + if (utf) + { + if (c == d) { ADD_NEW(state_offset + dlen + 1, 0); } else + { + unsigned int othercase; + if (c < 128) + othercase = fcc[c]; + else + /* If we have Unicode property support, we can use it to test the + other case of the character. */ +#ifdef SUPPORT_UCP + othercase = UCD_OTHERCASE(c); +#else + othercase = NOTACHAR; +#endif + + if (d == othercase) { ADD_NEW(state_offset + dlen + 1, 0); } + } + } + else +#endif /* SUPPORT_UTF */ + /* Not UTF mode */ + { + if (TABLE_GET(c, lcc, c) == TABLE_GET(d, lcc, d)) + { ADD_NEW(state_offset + 2, 0); } + } + break; + + +#ifdef SUPPORT_UCP + /*-----------------------------------------------------------------*/ + /* This is a tricky one because it can match more than one character. + Find out how many characters to skip, and then set up a negative state + to wait for them to pass before continuing. */ + + case OP_EXTUNI: + if (clen > 0) + { + int lgb, rgb; + const pcre_uchar *nptr = ptr + clen; + int ncount = 0; + lgb = UCD_GRAPHBREAK(c); + while (nptr < end_subject) + { + dlen = 1; + if (!utf) d = *nptr; else { GETCHARLEN(d, nptr, dlen); } + rgb = UCD_GRAPHBREAK(d); + if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break; + ncount++; + lgb = rgb; + nptr += dlen; + } + if (nptr >= end_subject && (md->moptions & PCRE_PARTIAL_HARD) != 0) + reset_could_continue = TRUE; + ADD_NEW_DATA(-(state_offset + 1), 0, ncount); + } + break; +#endif + + /*-----------------------------------------------------------------*/ + /* This is a tricky like EXTUNI because it too can match more than one + character (when CR is followed by LF). In this case, set up a negative + state to wait for one character to pass before continuing. */ + + case OP_ANYNL: + if (clen > 0) switch(c) + { + case CHAR_VT: + case CHAR_FF: + case CHAR_NEL: +#ifndef EBCDIC + case 0x2028: + case 0x2029: +#endif /* Not EBCDIC */ + if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; + + case CHAR_LF: + ADD_NEW(state_offset + 1, 0); + break; + + case CHAR_CR: + if (ptr + 1 >= end_subject) + { + ADD_NEW(state_offset + 1, 0); + if ((md->moptions & PCRE_PARTIAL_HARD) != 0) + reset_could_continue = TRUE; + } + else if (UCHAR21TEST(ptr + 1) == CHAR_LF) + { + ADD_NEW_DATA(-(state_offset + 1), 0, 1); + } + else + { + ADD_NEW(state_offset + 1, 0); + } + break; + } + break; + + /*-----------------------------------------------------------------*/ + case OP_NOT_VSPACE: + if (clen > 0) switch(c) + { + VSPACE_CASES: + break; + + default: + ADD_NEW(state_offset + 1, 0); + break; + } + break; + + /*-----------------------------------------------------------------*/ + case OP_VSPACE: + if (clen > 0) switch(c) + { + VSPACE_CASES: + ADD_NEW(state_offset + 1, 0); + break; + + default: + break; + } + break; + + /*-----------------------------------------------------------------*/ + case OP_NOT_HSPACE: + if (clen > 0) switch(c) + { + HSPACE_CASES: + break; + + default: + ADD_NEW(state_offset + 1, 0); + break; + } + break; + + /*-----------------------------------------------------------------*/ + case OP_HSPACE: + if (clen > 0) switch(c) + { + HSPACE_CASES: + ADD_NEW(state_offset + 1, 0); + break; + + default: + break; + } + break; + + /*-----------------------------------------------------------------*/ + /* Match a negated single character casefully. */ + + case OP_NOT: + if (clen > 0 && c != d) { ADD_NEW(state_offset + dlen + 1, 0); } + break; + + /*-----------------------------------------------------------------*/ + /* Match a negated single character caselessly. */ + + case OP_NOTI: + if (clen > 0) + { + unsigned int otherd; +#ifdef SUPPORT_UTF + if (utf && d >= 128) + { +#ifdef SUPPORT_UCP + otherd = UCD_OTHERCASE(d); +#endif /* SUPPORT_UCP */ + } + else +#endif /* SUPPORT_UTF */ + otherd = TABLE_GET(d, fcc, d); + if (c != d && c != otherd) + { ADD_NEW(state_offset + dlen + 1, 0); } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_PLUSI: + case OP_MINPLUSI: + case OP_POSPLUSI: + case OP_NOTPLUSI: + case OP_NOTMINPLUSI: + case OP_NOTPOSPLUSI: + caseless = TRUE; + codevalue -= OP_STARI - OP_STAR; + + /* Fall through */ + case OP_PLUS: + case OP_MINPLUS: + case OP_POSPLUS: + case OP_NOTPLUS: + case OP_NOTMINPLUS: + case OP_NOTPOSPLUS: + count = current_state->count; /* Already matched */ + if (count > 0) { ADD_ACTIVE(state_offset + dlen + 1, 0); } + if (clen > 0) + { + pcre_uint32 otherd = NOTACHAR; + if (caseless) + { +#ifdef SUPPORT_UTF + if (utf && d >= 128) + { +#ifdef SUPPORT_UCP + otherd = UCD_OTHERCASE(d); +#endif /* SUPPORT_UCP */ + } + else +#endif /* SUPPORT_UTF */ + otherd = TABLE_GET(d, fcc, d); + } + if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) + { + if (count > 0 && + (codevalue == OP_POSPLUS || codevalue == OP_NOTPOSPLUS)) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + count++; + ADD_NEW(state_offset, count); + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_QUERYI: + case OP_MINQUERYI: + case OP_POSQUERYI: + case OP_NOTQUERYI: + case OP_NOTMINQUERYI: + case OP_NOTPOSQUERYI: + caseless = TRUE; + codevalue -= OP_STARI - OP_STAR; + /* Fall through */ + case OP_QUERY: + case OP_MINQUERY: + case OP_POSQUERY: + case OP_NOTQUERY: + case OP_NOTMINQUERY: + case OP_NOTPOSQUERY: + ADD_ACTIVE(state_offset + dlen + 1, 0); + if (clen > 0) + { + pcre_uint32 otherd = NOTACHAR; + if (caseless) + { +#ifdef SUPPORT_UTF + if (utf && d >= 128) + { +#ifdef SUPPORT_UCP + otherd = UCD_OTHERCASE(d); +#endif /* SUPPORT_UCP */ + } + else +#endif /* SUPPORT_UTF */ + otherd = TABLE_GET(d, fcc, d); + } + if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) + { + if (codevalue == OP_POSQUERY || codevalue == OP_NOTPOSQUERY) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + ADD_NEW(state_offset + dlen + 1, 0); + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_STARI: + case OP_MINSTARI: + case OP_POSSTARI: + case OP_NOTSTARI: + case OP_NOTMINSTARI: + case OP_NOTPOSSTARI: + caseless = TRUE; + codevalue -= OP_STARI - OP_STAR; + /* Fall through */ + case OP_STAR: + case OP_MINSTAR: + case OP_POSSTAR: + case OP_NOTSTAR: + case OP_NOTMINSTAR: + case OP_NOTPOSSTAR: + ADD_ACTIVE(state_offset + dlen + 1, 0); + if (clen > 0) + { + pcre_uint32 otherd = NOTACHAR; + if (caseless) + { +#ifdef SUPPORT_UTF + if (utf && d >= 128) + { +#ifdef SUPPORT_UCP + otherd = UCD_OTHERCASE(d); +#endif /* SUPPORT_UCP */ + } + else +#endif /* SUPPORT_UTF */ + otherd = TABLE_GET(d, fcc, d); + } + if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) + { + if (codevalue == OP_POSSTAR || codevalue == OP_NOTPOSSTAR) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + ADD_NEW(state_offset, 0); + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_EXACTI: + case OP_NOTEXACTI: + caseless = TRUE; + codevalue -= OP_STARI - OP_STAR; + /* Fall through */ + case OP_EXACT: + case OP_NOTEXACT: + count = current_state->count; /* Number already matched */ + if (clen > 0) + { + pcre_uint32 otherd = NOTACHAR; + if (caseless) + { +#ifdef SUPPORT_UTF + if (utf && d >= 128) + { +#ifdef SUPPORT_UCP + otherd = UCD_OTHERCASE(d); +#endif /* SUPPORT_UCP */ + } + else +#endif /* SUPPORT_UTF */ + otherd = TABLE_GET(d, fcc, d); + } + if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) + { + if (++count >= (int)GET2(code, 1)) + { ADD_NEW(state_offset + dlen + 1 + IMM2_SIZE, 0); } + else + { ADD_NEW(state_offset, count); } + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_UPTOI: + case OP_MINUPTOI: + case OP_POSUPTOI: + case OP_NOTUPTOI: + case OP_NOTMINUPTOI: + case OP_NOTPOSUPTOI: + caseless = TRUE; + codevalue -= OP_STARI - OP_STAR; + /* Fall through */ + case OP_UPTO: + case OP_MINUPTO: + case OP_POSUPTO: + case OP_NOTUPTO: + case OP_NOTMINUPTO: + case OP_NOTPOSUPTO: + ADD_ACTIVE(state_offset + dlen + 1 + IMM2_SIZE, 0); + count = current_state->count; /* Number already matched */ + if (clen > 0) + { + pcre_uint32 otherd = NOTACHAR; + if (caseless) + { +#ifdef SUPPORT_UTF + if (utf && d >= 128) + { +#ifdef SUPPORT_UCP + otherd = UCD_OTHERCASE(d); +#endif /* SUPPORT_UCP */ + } + else +#endif /* SUPPORT_UTF */ + otherd = TABLE_GET(d, fcc, d); + } + if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) + { + if (codevalue == OP_POSUPTO || codevalue == OP_NOTPOSUPTO) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + if (++count >= (int)GET2(code, 1)) + { ADD_NEW(state_offset + dlen + 1 + IMM2_SIZE, 0); } + else + { ADD_NEW(state_offset, count); } + } + } + break; + + +/* ========================================================================== */ + /* These are the class-handling opcodes */ + + case OP_CLASS: + case OP_NCLASS: + case OP_XCLASS: + { + BOOL isinclass = FALSE; + int next_state_offset; + const pcre_uchar *ecode; + + /* For a simple class, there is always just a 32-byte table, and we + can set isinclass from it. */ + + if (codevalue != OP_XCLASS) + { + ecode = code + 1 + (32 / sizeof(pcre_uchar)); + if (clen > 0) + { + isinclass = (c > 255)? (codevalue == OP_NCLASS) : + ((((pcre_uint8 *)(code + 1))[c/8] & (1 << (c&7))) != 0); + } + } + + /* An extended class may have a table or a list of single characters, + ranges, or both, and it may be positive or negative. There's a + function that sorts all this out. */ + + else + { + ecode = code + GET(code, 1); + if (clen > 0) isinclass = PRIV(xclass)(c, code + 1 + LINK_SIZE, utf); + } + + /* At this point, isinclass is set for all kinds of class, and ecode + points to the byte after the end of the class. If there is a + quantifier, this is where it will be. */ + + next_state_offset = (int)(ecode - start_code); + + switch (*ecode) + { + case OP_CRSTAR: + case OP_CRMINSTAR: + case OP_CRPOSSTAR: + ADD_ACTIVE(next_state_offset + 1, 0); + if (isinclass) + { + if (*ecode == OP_CRPOSSTAR) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + ADD_NEW(state_offset, 0); + } + break; + + case OP_CRPLUS: + case OP_CRMINPLUS: + case OP_CRPOSPLUS: + count = current_state->count; /* Already matched */ + if (count > 0) { ADD_ACTIVE(next_state_offset + 1, 0); } + if (isinclass) + { + if (count > 0 && *ecode == OP_CRPOSPLUS) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + count++; + ADD_NEW(state_offset, count); + } + break; + + case OP_CRQUERY: + case OP_CRMINQUERY: + case OP_CRPOSQUERY: + ADD_ACTIVE(next_state_offset + 1, 0); + if (isinclass) + { + if (*ecode == OP_CRPOSQUERY) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + ADD_NEW(next_state_offset + 1, 0); + } + break; + + case OP_CRRANGE: + case OP_CRMINRANGE: + case OP_CRPOSRANGE: + count = current_state->count; /* Already matched */ + if (count >= (int)GET2(ecode, 1)) + { ADD_ACTIVE(next_state_offset + 1 + 2 * IMM2_SIZE, 0); } + if (isinclass) + { + int max = (int)GET2(ecode, 1 + IMM2_SIZE); + if (*ecode == OP_CRPOSRANGE) + { + active_count--; /* Remove non-match possibility */ + next_active_state--; + } + if (++count >= max && max != 0) /* Max 0 => no limit */ + { ADD_NEW(next_state_offset + 1 + 2 * IMM2_SIZE, 0); } + else + { ADD_NEW(state_offset, count); } + } + break; + + default: + if (isinclass) { ADD_NEW(next_state_offset, 0); } + break; + } + } + break; + +/* ========================================================================== */ + /* These are the opcodes for fancy brackets of various kinds. We have + to use recursion in order to handle them. The "always failing" assertion + (?!) is optimised to OP_FAIL when compiling, so we have to support that, + though the other "backtracking verbs" are not supported. */ + + case OP_FAIL: + forced_fail++; /* Count FAILs for multiple states */ + break; + + case OP_ASSERT: + case OP_ASSERT_NOT: + case OP_ASSERTBACK: + case OP_ASSERTBACK_NOT: + { + int rc; + int local_offsets[2]; + int local_workspace[1000]; + const pcre_uchar *endasscode = code + GET(code, 1); + + while (*endasscode == OP_ALT) endasscode += GET(endasscode, 1); + + rc = internal_dfa_exec( + md, /* static match data */ + code, /* this subexpression's code */ + ptr, /* where we currently are */ + (int)(ptr - start_subject), /* start offset */ + local_offsets, /* offset vector */ + sizeof(local_offsets)/sizeof(int), /* size of same */ + local_workspace, /* workspace vector */ + sizeof(local_workspace)/sizeof(int), /* size of same */ + rlevel); /* function recursion level */ + + if (rc == PCRE_ERROR_DFA_UITEM) return rc; + if ((rc >= 0) == (codevalue == OP_ASSERT || codevalue == OP_ASSERTBACK)) + { ADD_ACTIVE((int)(endasscode + LINK_SIZE + 1 - start_code), 0); } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_COND: + case OP_SCOND: + { + int local_offsets[1000]; + int local_workspace[1000]; + int codelink = GET(code, 1); + int condcode; + + /* Because of the way auto-callout works during compile, a callout item + is inserted between OP_COND and an assertion condition. This does not + happen for the other conditions. */ + + if (code[LINK_SIZE+1] == OP_CALLOUT) + { + rrc = 0; + if (PUBL(callout) != NULL) + { + PUBL(callout_block) cb; + cb.version = 1; /* Version 1 of the callout block */ + cb.callout_number = code[LINK_SIZE+2]; + cb.offset_vector = offsets; +#if defined COMPILE_PCRE8 + cb.subject = (PCRE_SPTR)start_subject; +#elif defined COMPILE_PCRE16 + cb.subject = (PCRE_SPTR16)start_subject; +#elif defined COMPILE_PCRE32 + cb.subject = (PCRE_SPTR32)start_subject; +#endif + cb.subject_length = (int)(end_subject - start_subject); + cb.start_match = (int)(current_subject - start_subject); + cb.current_position = (int)(ptr - start_subject); + cb.pattern_position = GET(code, LINK_SIZE + 3); + cb.next_item_length = GET(code, 3 + 2*LINK_SIZE); + cb.capture_top = 1; + cb.capture_last = -1; + cb.callout_data = md->callout_data; + cb.mark = NULL; /* No (*MARK) support */ + if ((rrc = (*PUBL(callout))(&cb)) < 0) return rrc; /* Abandon */ + } + if (rrc > 0) break; /* Fail this thread */ + code += PRIV(OP_lengths)[OP_CALLOUT]; /* Skip callout data */ + } + + condcode = code[LINK_SIZE+1]; + + /* Back reference conditions and duplicate named recursion conditions + are not supported */ + + if (condcode == OP_CREF || condcode == OP_DNCREF || + condcode == OP_DNRREF) + return PCRE_ERROR_DFA_UCOND; + + /* The DEFINE condition is always false */ + + if (condcode == OP_DEF) + { ADD_ACTIVE(state_offset + codelink + LINK_SIZE + 1, 0); } + + /* The only supported version of OP_RREF is for the value RREF_ANY, + which means "test if in any recursion". We can't test for specifically + recursed groups. */ + + else if (condcode == OP_RREF) + { + int value = GET2(code, LINK_SIZE + 2); + if (value != RREF_ANY) return PCRE_ERROR_DFA_UCOND; + if (md->recursive != NULL) + { ADD_ACTIVE(state_offset + LINK_SIZE + 2 + IMM2_SIZE, 0); } + else { ADD_ACTIVE(state_offset + codelink + LINK_SIZE + 1, 0); } + } + + /* Otherwise, the condition is an assertion */ + + else + { + int rc; + const pcre_uchar *asscode = code + LINK_SIZE + 1; + const pcre_uchar *endasscode = asscode + GET(asscode, 1); + + while (*endasscode == OP_ALT) endasscode += GET(endasscode, 1); + + rc = internal_dfa_exec( + md, /* fixed match data */ + asscode, /* this subexpression's code */ + ptr, /* where we currently are */ + (int)(ptr - start_subject), /* start offset */ + local_offsets, /* offset vector */ + sizeof(local_offsets)/sizeof(int), /* size of same */ + local_workspace, /* workspace vector */ + sizeof(local_workspace)/sizeof(int), /* size of same */ + rlevel); /* function recursion level */ + + if (rc == PCRE_ERROR_DFA_UITEM) return rc; + if ((rc >= 0) == + (condcode == OP_ASSERT || condcode == OP_ASSERTBACK)) + { ADD_ACTIVE((int)(endasscode + LINK_SIZE + 1 - start_code), 0); } + else + { ADD_ACTIVE(state_offset + codelink + LINK_SIZE + 1, 0); } + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_RECURSE: + { + dfa_recursion_info *ri; + int local_offsets[1000]; + int local_workspace[1000]; + const pcre_uchar *callpat = start_code + GET(code, 1); + int recno = (callpat == md->start_code)? 0 : + GET2(callpat, 1 + LINK_SIZE); + int rc; + + DPRINTF(("%.*sStarting regex recursion\n", rlevel*2-2, SP)); + + /* Check for repeating a recursion without advancing the subject + pointer. This should catch convoluted mutual recursions. (Some simple + cases are caught at compile time.) */ + + for (ri = md->recursive; ri != NULL; ri = ri->prevrec) + if (recno == ri->group_num && ptr == ri->subject_position) + return PCRE_ERROR_RECURSELOOP; + + /* Remember this recursion and where we started it so as to + catch infinite loops. */ + + new_recursive.group_num = recno; + new_recursive.subject_position = ptr; + new_recursive.prevrec = md->recursive; + md->recursive = &new_recursive; + + rc = internal_dfa_exec( + md, /* fixed match data */ + callpat, /* this subexpression's code */ + ptr, /* where we currently are */ + (int)(ptr - start_subject), /* start offset */ + local_offsets, /* offset vector */ + sizeof(local_offsets)/sizeof(int), /* size of same */ + local_workspace, /* workspace vector */ + sizeof(local_workspace)/sizeof(int), /* size of same */ + rlevel); /* function recursion level */ + + md->recursive = new_recursive.prevrec; /* Done this recursion */ + + DPRINTF(("%.*sReturn from regex recursion: rc=%d\n", rlevel*2-2, SP, + rc)); + + /* Ran out of internal offsets */ + + if (rc == 0) return PCRE_ERROR_DFA_RECURSE; + + /* For each successful matched substring, set up the next state with a + count of characters to skip before trying it. Note that the count is in + characters, not bytes. */ + + if (rc > 0) + { + for (rc = rc*2 - 2; rc >= 0; rc -= 2) + { + int charcount = local_offsets[rc+1] - local_offsets[rc]; +#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 + if (utf) + { + const pcre_uchar *p = start_subject + local_offsets[rc]; + const pcre_uchar *pp = start_subject + local_offsets[rc+1]; + while (p < pp) if (NOT_FIRSTCHAR(*p++)) charcount--; + } +#endif + if (charcount > 0) + { + ADD_NEW_DATA(-(state_offset + LINK_SIZE + 1), 0, (charcount - 1)); + } + else + { + ADD_ACTIVE(state_offset + LINK_SIZE + 1, 0); + } + } + } + else if (rc != PCRE_ERROR_NOMATCH) return rc; + } + break; + + /*-----------------------------------------------------------------*/ + case OP_BRAPOS: + case OP_SBRAPOS: + case OP_CBRAPOS: + case OP_SCBRAPOS: + case OP_BRAPOSZERO: + { + int charcount, matched_count; + const pcre_uchar *local_ptr = ptr; + BOOL allow_zero; + + if (codevalue == OP_BRAPOSZERO) + { + allow_zero = TRUE; + codevalue = *(++code); /* Codevalue will be one of above BRAs */ + } + else allow_zero = FALSE; + + /* Loop to match the subpattern as many times as possible as if it were + a complete pattern. */ + + for (matched_count = 0;; matched_count++) + { + int local_offsets[2]; + int local_workspace[1000]; + + int rc = internal_dfa_exec( + md, /* fixed match data */ + code, /* this subexpression's code */ + local_ptr, /* where we currently are */ + (int)(ptr - start_subject), /* start offset */ + local_offsets, /* offset vector */ + sizeof(local_offsets)/sizeof(int), /* size of same */ + local_workspace, /* workspace vector */ + sizeof(local_workspace)/sizeof(int), /* size of same */ + rlevel); /* function recursion level */ + + /* Failed to match */ + + if (rc < 0) + { + if (rc != PCRE_ERROR_NOMATCH) return rc; + break; + } + + /* Matched: break the loop if zero characters matched. */ + + charcount = local_offsets[1] - local_offsets[0]; + if (charcount == 0) break; + local_ptr += charcount; /* Advance temporary position ptr */ + } + + /* At this point we have matched the subpattern matched_count + times, and local_ptr is pointing to the character after the end of the + last match. */ + + if (matched_count > 0 || allow_zero) + { + const pcre_uchar *end_subpattern = code; + int next_state_offset; + + do { end_subpattern += GET(end_subpattern, 1); } + while (*end_subpattern == OP_ALT); + next_state_offset = + (int)(end_subpattern - start_code + LINK_SIZE + 1); + + /* Optimization: if there are no more active states, and there + are no new states yet set up, then skip over the subject string + right here, to save looping. Otherwise, set up the new state to swing + into action when the end of the matched substring is reached. */ + + if (i + 1 >= active_count && new_count == 0) + { + ptr = local_ptr; + clen = 0; + ADD_NEW(next_state_offset, 0); + } + else + { + const pcre_uchar *p = ptr; + const pcre_uchar *pp = local_ptr; + charcount = (int)(pp - p); +#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 + if (utf) while (p < pp) if (NOT_FIRSTCHAR(*p++)) charcount--; +#endif + ADD_NEW_DATA(-next_state_offset, 0, (charcount - 1)); + } + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_ONCE: + case OP_ONCE_NC: + { + int local_offsets[2]; + int local_workspace[1000]; + + int rc = internal_dfa_exec( + md, /* fixed match data */ + code, /* this subexpression's code */ + ptr, /* where we currently are */ + (int)(ptr - start_subject), /* start offset */ + local_offsets, /* offset vector */ + sizeof(local_offsets)/sizeof(int), /* size of same */ + local_workspace, /* workspace vector */ + sizeof(local_workspace)/sizeof(int), /* size of same */ + rlevel); /* function recursion level */ + + if (rc >= 0) + { + const pcre_uchar *end_subpattern = code; + int charcount = local_offsets[1] - local_offsets[0]; + int next_state_offset, repeat_state_offset; + + do { end_subpattern += GET(end_subpattern, 1); } + while (*end_subpattern == OP_ALT); + next_state_offset = + (int)(end_subpattern - start_code + LINK_SIZE + 1); + + /* If the end of this subpattern is KETRMAX or KETRMIN, we must + arrange for the repeat state also to be added to the relevant list. + Calculate the offset, or set -1 for no repeat. */ + + repeat_state_offset = (*end_subpattern == OP_KETRMAX || + *end_subpattern == OP_KETRMIN)? + (int)(end_subpattern - start_code - GET(end_subpattern, 1)) : -1; + + /* If we have matched an empty string, add the next state at the + current character pointer. This is important so that the duplicate + checking kicks in, which is what breaks infinite loops that match an + empty string. */ + + if (charcount == 0) + { + ADD_ACTIVE(next_state_offset, 0); + } + + /* Optimization: if there are no more active states, and there + are no new states yet set up, then skip over the subject string + right here, to save looping. Otherwise, set up the new state to swing + into action when the end of the matched substring is reached. */ + + else if (i + 1 >= active_count && new_count == 0) + { + ptr += charcount; + clen = 0; + ADD_NEW(next_state_offset, 0); + + /* If we are adding a repeat state at the new character position, + we must fudge things so that it is the only current state. + Otherwise, it might be a duplicate of one we processed before, and + that would cause it to be skipped. */ + + if (repeat_state_offset >= 0) + { + next_active_state = active_states; + active_count = 0; + i = -1; + ADD_ACTIVE(repeat_state_offset, 0); + } + } + else + { +#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 + if (utf) + { + const pcre_uchar *p = start_subject + local_offsets[0]; + const pcre_uchar *pp = start_subject + local_offsets[1]; + while (p < pp) if (NOT_FIRSTCHAR(*p++)) charcount--; + } +#endif + ADD_NEW_DATA(-next_state_offset, 0, (charcount - 1)); + if (repeat_state_offset >= 0) + { ADD_NEW_DATA(-repeat_state_offset, 0, (charcount - 1)); } + } + } + else if (rc != PCRE_ERROR_NOMATCH) return rc; + } + break; + + +/* ========================================================================== */ + /* Handle callouts */ + + case OP_CALLOUT: + rrc = 0; + if (PUBL(callout) != NULL) + { + PUBL(callout_block) cb; + cb.version = 1; /* Version 1 of the callout block */ + cb.callout_number = code[1]; + cb.offset_vector = offsets; +#if defined COMPILE_PCRE8 + cb.subject = (PCRE_SPTR)start_subject; +#elif defined COMPILE_PCRE16 + cb.subject = (PCRE_SPTR16)start_subject; +#elif defined COMPILE_PCRE32 + cb.subject = (PCRE_SPTR32)start_subject; +#endif + cb.subject_length = (int)(end_subject - start_subject); + cb.start_match = (int)(current_subject - start_subject); + cb.current_position = (int)(ptr - start_subject); + cb.pattern_position = GET(code, 2); + cb.next_item_length = GET(code, 2 + LINK_SIZE); + cb.capture_top = 1; + cb.capture_last = -1; + cb.callout_data = md->callout_data; + cb.mark = NULL; /* No (*MARK) support */ + if ((rrc = (*PUBL(callout))(&cb)) < 0) return rrc; /* Abandon */ + } + if (rrc == 0) + { ADD_ACTIVE(state_offset + PRIV(OP_lengths)[OP_CALLOUT], 0); } + break; + + +/* ========================================================================== */ + default: /* Unsupported opcode */ + return PCRE_ERROR_DFA_UITEM; + } + + NEXT_ACTIVE_STATE: continue; + + } /* End of loop scanning active states */ + + /* We have finished the processing at the current subject character. If no + new states have been set for the next character, we have found all the + matches that we are going to find. If we are at the top level and partial + matching has been requested, check for appropriate conditions. + + The "forced_ fail" variable counts the number of (*F) encountered for the + character. If it is equal to the original active_count (saved in + workspace[1]) it means that (*F) was found on every active state. In this + case we don't want to give a partial match. + + The "could_continue" variable is true if a state could have continued but + for the fact that the end of the subject was reached. */ + + if (new_count <= 0) + { + if (rlevel == 1 && /* Top level, and */ + could_continue && /* Some could go on, and */ + forced_fail != workspace[1] && /* Not all forced fail & */ + ( /* either... */ + (md->moptions & PCRE_PARTIAL_HARD) != 0 /* Hard partial */ + || /* or... */ + ((md->moptions & PCRE_PARTIAL_SOFT) != 0 && /* Soft partial and */ + match_count < 0) /* no matches */ + ) && /* And... */ + ( + partial_newline || /* Either partial NL */ + ( /* or ... */ + ptr >= end_subject && /* End of subject and */ + ptr > md->start_used_ptr) /* Inspected non-empty string */ + ) + ) + match_count = PCRE_ERROR_PARTIAL; + DPRINTF(("%.*sEnd of internal_dfa_exec %d: returning %d\n" + "%.*s---------------------\n\n", rlevel*2-2, SP, rlevel, match_count, + rlevel*2-2, SP)); + break; /* In effect, "return", but see the comment below */ + } + + /* One or more states are active for the next character. */ + + ptr += clen; /* Advance to next subject character */ + } /* Loop to move along the subject string */ + +/* Control gets here from "break" a few lines above. We do it this way because +if we use "return" above, we have compiler trouble. Some compilers warn if +there's nothing here because they think the function doesn't return a value. On +the other hand, if we put a dummy statement here, some more clever compilers +complain that it can't be reached. Sigh. */ + +return match_count; +} + + + + +/************************************************* +* Execute a Regular Expression - DFA engine * +*************************************************/ + +/* This external function applies a compiled re to a subject string using a DFA +engine. This function calls the internal function multiple times if the pattern +is not anchored. + +Arguments: + argument_re points to the compiled expression + extra_data points to extra data or is NULL + subject points to the subject string + length length of subject string (may contain binary zeros) + start_offset where to start in the subject string + options option bits + offsets vector of match offsets + offsetcount size of same + workspace workspace vector + wscount size of same + +Returns: > 0 => number of match offset pairs placed in offsets + = 0 => offsets overflowed; longest matches are present + -1 => failed to match + < -1 => some kind of unexpected problem +*/ + +#if defined COMPILE_PCRE8 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre_dfa_exec(const pcre *argument_re, const pcre_extra *extra_data, + const char *subject, int length, int start_offset, int options, int *offsets, + int offsetcount, int *workspace, int wscount) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre16_dfa_exec(const pcre16 *argument_re, const pcre16_extra *extra_data, + PCRE_SPTR16 subject, int length, int start_offset, int options, int *offsets, + int offsetcount, int *workspace, int wscount) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre32_dfa_exec(const pcre32 *argument_re, const pcre32_extra *extra_data, + PCRE_SPTR32 subject, int length, int start_offset, int options, int *offsets, + int offsetcount, int *workspace, int wscount) +#endif +{ +REAL_PCRE *re = (REAL_PCRE *)argument_re; +dfa_match_data match_block; +dfa_match_data *md = &match_block; +BOOL utf, anchored, startline, firstline; +const pcre_uchar *current_subject, *end_subject; +const pcre_study_data *study = NULL; + +const pcre_uchar *req_char_ptr; +const pcre_uint8 *start_bits = NULL; +BOOL has_first_char = FALSE; +BOOL has_req_char = FALSE; +pcre_uchar first_char = 0; +pcre_uchar first_char2 = 0; +pcre_uchar req_char = 0; +pcre_uchar req_char2 = 0; +int newline; + +/* Plausibility checks */ + +if ((options & ~PUBLIC_DFA_EXEC_OPTIONS) != 0) return PCRE_ERROR_BADOPTION; +if (re == NULL || subject == NULL || workspace == NULL || + (offsets == NULL && offsetcount > 0)) return PCRE_ERROR_NULL; +if (offsetcount < 0) return PCRE_ERROR_BADCOUNT; +if (wscount < 20) return PCRE_ERROR_DFA_WSSIZE; +if (length < 0) return PCRE_ERROR_BADLENGTH; +if (start_offset < 0 || start_offset > length) return PCRE_ERROR_BADOFFSET; + +/* Check that the first field in the block is the magic number. If it is not, +return with PCRE_ERROR_BADMAGIC. However, if the magic number is equal to +REVERSED_MAGIC_NUMBER we return with PCRE_ERROR_BADENDIANNESS, which +means that the pattern is likely compiled with different endianness. */ + +if (re->magic_number != MAGIC_NUMBER) + return re->magic_number == REVERSED_MAGIC_NUMBER? + PCRE_ERROR_BADENDIANNESS:PCRE_ERROR_BADMAGIC; +if ((re->flags & PCRE_MODE) == 0) return PCRE_ERROR_BADMODE; + +/* If restarting after a partial match, do some sanity checks on the contents +of the workspace. */ + +if ((options & PCRE_DFA_RESTART) != 0) + { + if ((workspace[0] & (-2)) != 0 || workspace[1] < 1 || + workspace[1] > (wscount - 2)/INTS_PER_STATEBLOCK) + return PCRE_ERROR_DFA_BADRESTART; + } + +/* Set up study, callout, and table data */ + +md->tables = re->tables; +md->callout_data = NULL; + +if (extra_data != NULL) + { + unsigned int flags = extra_data->flags; + if ((flags & PCRE_EXTRA_STUDY_DATA) != 0) + study = (const pcre_study_data *)extra_data->study_data; + if ((flags & PCRE_EXTRA_MATCH_LIMIT) != 0) return PCRE_ERROR_DFA_UMLIMIT; + if ((flags & PCRE_EXTRA_MATCH_LIMIT_RECURSION) != 0) + return PCRE_ERROR_DFA_UMLIMIT; + if ((flags & PCRE_EXTRA_CALLOUT_DATA) != 0) + md->callout_data = extra_data->callout_data; + if ((flags & PCRE_EXTRA_TABLES) != 0) + md->tables = extra_data->tables; + } + +/* Set some local values */ + +current_subject = (const pcre_uchar *)subject + start_offset; +end_subject = (const pcre_uchar *)subject + length; +req_char_ptr = current_subject - 1; + +#ifdef SUPPORT_UTF +/* PCRE_UTF(16|32) have the same value as PCRE_UTF8. */ +utf = (re->options & PCRE_UTF8) != 0; +#else +utf = FALSE; +#endif + +anchored = (options & (PCRE_ANCHORED|PCRE_DFA_RESTART)) != 0 || + (re->options & PCRE_ANCHORED) != 0; + +/* The remaining fixed data for passing around. */ + +md->start_code = (const pcre_uchar *)argument_re + + re->name_table_offset + re->name_count * re->name_entry_size; +md->start_subject = (const pcre_uchar *)subject; +md->end_subject = end_subject; +md->start_offset = start_offset; +md->moptions = options; +md->poptions = re->options; + +/* If the BSR option is not set at match time, copy what was set +at compile time. */ + +if ((md->moptions & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) == 0) + { + if ((re->options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) != 0) + md->moptions |= re->options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE); +#ifdef BSR_ANYCRLF + else md->moptions |= PCRE_BSR_ANYCRLF; +#endif + } + +/* Handle different types of newline. The three bits give eight cases. If +nothing is set at run time, whatever was used at compile time applies. */ + +switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options : (pcre_uint32)options) & + PCRE_NEWLINE_BITS) + { + case 0: newline = NEWLINE; break; /* Compile-time default */ + case PCRE_NEWLINE_CR: newline = CHAR_CR; break; + case PCRE_NEWLINE_LF: newline = CHAR_NL; break; + case PCRE_NEWLINE_CR+ + PCRE_NEWLINE_LF: newline = (CHAR_CR << 8) | CHAR_NL; break; + case PCRE_NEWLINE_ANY: newline = -1; break; + case PCRE_NEWLINE_ANYCRLF: newline = -2; break; + default: return PCRE_ERROR_BADNEWLINE; + } + +if (newline == -2) + { + md->nltype = NLTYPE_ANYCRLF; + } +else if (newline < 0) + { + md->nltype = NLTYPE_ANY; + } +else + { + md->nltype = NLTYPE_FIXED; + if (newline > 255) + { + md->nllen = 2; + md->nl[0] = (newline >> 8) & 255; + md->nl[1] = newline & 255; + } + else + { + md->nllen = 1; + md->nl[0] = newline; + } + } + +/* Check a UTF-8 string if required. Unfortunately there's no way of passing +back the character offset. */ + +#ifdef SUPPORT_UTF +if (utf && (options & PCRE_NO_UTF8_CHECK) == 0) + { + int erroroffset; + int errorcode = PRIV(valid_utf)((pcre_uchar *)subject, length, &erroroffset); + if (errorcode != 0) + { + if (offsetcount >= 2) + { + offsets[0] = erroroffset; + offsets[1] = errorcode; + } +#if defined COMPILE_PCRE8 + return (errorcode <= PCRE_UTF8_ERR5 && (options & PCRE_PARTIAL_HARD) != 0) ? + PCRE_ERROR_SHORTUTF8 : PCRE_ERROR_BADUTF8; +#elif defined COMPILE_PCRE16 + return (errorcode <= PCRE_UTF16_ERR1 && (options & PCRE_PARTIAL_HARD) != 0) ? + PCRE_ERROR_SHORTUTF16 : PCRE_ERROR_BADUTF16; +#elif defined COMPILE_PCRE32 + return PCRE_ERROR_BADUTF32; +#endif + } +#if defined COMPILE_PCRE8 || defined COMPILE_PCRE16 + if (start_offset > 0 && start_offset < length && + NOT_FIRSTCHAR(((PCRE_PUCHAR)subject)[start_offset])) + return PCRE_ERROR_BADUTF8_OFFSET; +#endif + } +#endif + +/* If the exec call supplied NULL for tables, use the inbuilt ones. This +is a feature that makes it possible to save compiled regex and re-use them +in other programs later. */ + +if (md->tables == NULL) md->tables = PRIV(default_tables); + +/* The "must be at the start of a line" flags are used in a loop when finding +where to start. */ + +startline = (re->flags & PCRE_STARTLINE) != 0; +firstline = (re->options & PCRE_FIRSTLINE) != 0; + +/* Set up the first character to match, if available. The first_byte value is +never set for an anchored regular expression, but the anchoring may be forced +at run time, so we have to test for anchoring. The first char may be unset for +an unanchored pattern, of course. If there's no first char and the pattern was +studied, there may be a bitmap of possible first characters. */ + +if (!anchored) + { + if ((re->flags & PCRE_FIRSTSET) != 0) + { + has_first_char = TRUE; + first_char = first_char2 = (pcre_uchar)(re->first_char); + if ((re->flags & PCRE_FCH_CASELESS) != 0) + { + first_char2 = TABLE_GET(first_char, md->tables + fcc_offset, first_char); +#if defined SUPPORT_UCP && !(defined COMPILE_PCRE8) + if (utf && first_char > 127) + first_char2 = UCD_OTHERCASE(first_char); +#endif + } + } + else + { + if (!startline && study != NULL && + (study->flags & PCRE_STUDY_MAPPED) != 0) + start_bits = study->start_bits; + } + } + +/* For anchored or unanchored matches, there may be a "last known required +character" set. */ + +if ((re->flags & PCRE_REQCHSET) != 0) + { + has_req_char = TRUE; + req_char = req_char2 = (pcre_uchar)(re->req_char); + if ((re->flags & PCRE_RCH_CASELESS) != 0) + { + req_char2 = TABLE_GET(req_char, md->tables + fcc_offset, req_char); +#if defined SUPPORT_UCP && !(defined COMPILE_PCRE8) + if (utf && req_char > 127) + req_char2 = UCD_OTHERCASE(req_char); +#endif + } + } + +/* Call the main matching function, looping for a non-anchored regex after a +failed match. If not restarting, perform certain optimizations at the start of +a match. */ + +for (;;) + { + int rc; + + if ((options & PCRE_DFA_RESTART) == 0) + { + const pcre_uchar *save_end_subject = end_subject; + + /* If firstline is TRUE, the start of the match is constrained to the first + line of a multiline string. Implement this by temporarily adjusting + end_subject so that we stop scanning at a newline. If the match fails at + the newline, later code breaks this loop. */ + + if (firstline) + { + PCRE_PUCHAR t = current_subject; +#ifdef SUPPORT_UTF + if (utf) + { + while (t < md->end_subject && !IS_NEWLINE(t)) + { + t++; + ACROSSCHAR(t < end_subject, *t, t++); + } + } + else +#endif + while (t < md->end_subject && !IS_NEWLINE(t)) t++; + end_subject = t; + } + + /* There are some optimizations that avoid running the match if a known + starting point is not found. However, there is an option that disables + these, for testing and for ensuring that all callouts do actually occur. + The option can be set in the regex by (*NO_START_OPT) or passed in + match-time options. */ + + if (((options | re->options) & PCRE_NO_START_OPTIMIZE) == 0) + { + /* Advance to a known first pcre_uchar (i.e. data item) */ + + if (has_first_char) + { + if (first_char != first_char2) + { + pcre_uchar csc; + while (current_subject < end_subject && + (csc = UCHAR21TEST(current_subject)) != first_char && csc != first_char2) + current_subject++; + } + else + while (current_subject < end_subject && + UCHAR21TEST(current_subject) != first_char) + current_subject++; + } + + /* Or to just after a linebreak for a multiline match if possible */ + + else if (startline) + { + if (current_subject > md->start_subject + start_offset) + { +#ifdef SUPPORT_UTF + if (utf) + { + while (current_subject < end_subject && + !WAS_NEWLINE(current_subject)) + { + current_subject++; + ACROSSCHAR(current_subject < end_subject, *current_subject, + current_subject++); + } + } + else +#endif + while (current_subject < end_subject && !WAS_NEWLINE(current_subject)) + current_subject++; + + /* If we have just passed a CR and the newline option is ANY or + ANYCRLF, and we are now at a LF, advance the match position by one + more character. */ + + if (UCHAR21TEST(current_subject - 1) == CHAR_CR && + (md->nltype == NLTYPE_ANY || md->nltype == NLTYPE_ANYCRLF) && + current_subject < end_subject && + UCHAR21TEST(current_subject) == CHAR_NL) + current_subject++; + } + } + + /* Advance to a non-unique first pcre_uchar after study */ + + else if (start_bits != NULL) + { + while (current_subject < end_subject) + { + register pcre_uint32 c = UCHAR21TEST(current_subject); +#ifndef COMPILE_PCRE8 + if (c > 255) c = 255; +#endif + if ((start_bits[c/8] & (1 << (c&7))) != 0) break; + current_subject++; + } + } + } + + /* Restore fudged end_subject */ + + end_subject = save_end_subject; + + /* The following two optimizations are disabled for partial matching or if + disabling is explicitly requested (and of course, by the test above, this + code is not obeyed when restarting after a partial match). */ + + if (((options | re->options) & PCRE_NO_START_OPTIMIZE) == 0 && + (options & (PCRE_PARTIAL_HARD|PCRE_PARTIAL_SOFT)) == 0) + { + /* If the pattern was studied, a minimum subject length may be set. This + is a lower bound; no actual string of that length may actually match the + pattern. Although the value is, strictly, in characters, we treat it as + in pcre_uchar units to avoid spending too much time in this optimization. + */ + + if (study != NULL && (study->flags & PCRE_STUDY_MINLEN) != 0 && + (pcre_uint32)(end_subject - current_subject) < study->minlength) + return PCRE_ERROR_NOMATCH; + + /* If req_char is set, we know that that pcre_uchar must appear in the + subject for the match to succeed. If the first pcre_uchar is set, + req_char must be later in the subject; otherwise the test starts at the + match point. This optimization can save a huge amount of work in patterns + with nested unlimited repeats that aren't going to match. Writing + separate code for cased/caseless versions makes it go faster, as does + using an autoincrement and backing off on a match. + + HOWEVER: when the subject string is very, very long, searching to its end + can take a long time, and give bad performance on quite ordinary + patterns. This showed up when somebody was matching /^C/ on a 32-megabyte + string... so we don't do this when the string is sufficiently long. */ + + if (has_req_char && end_subject - current_subject < REQ_BYTE_MAX) + { + register PCRE_PUCHAR p = current_subject + (has_first_char? 1:0); + + /* We don't need to repeat the search if we haven't yet reached the + place we found it at last time. */ + + if (p > req_char_ptr) + { + if (req_char != req_char2) + { + while (p < end_subject) + { + register pcre_uint32 pp = UCHAR21INCTEST(p); + if (pp == req_char || pp == req_char2) { p--; break; } + } + } + else + { + while (p < end_subject) + { + if (UCHAR21INCTEST(p) == req_char) { p--; break; } + } + } + + /* If we can't find the required pcre_uchar, break the matching loop, + which will cause a return or PCRE_ERROR_NOMATCH. */ + + if (p >= end_subject) break; + + /* If we have found the required pcre_uchar, save the point where we + found it, so that we don't search again next time round the loop if + the start hasn't passed this point yet. */ + + req_char_ptr = p; + } + } + } + } /* End of optimizations that are done when not restarting */ + + /* OK, now we can do the business */ + + md->start_used_ptr = current_subject; + md->recursive = NULL; + + rc = internal_dfa_exec( + md, /* fixed match data */ + md->start_code, /* this subexpression's code */ + current_subject, /* where we currently are */ + start_offset, /* start offset in subject */ + offsets, /* offset vector */ + offsetcount, /* size of same */ + workspace, /* workspace vector */ + wscount, /* size of same */ + 0); /* function recurse level */ + + /* Anything other than "no match" means we are done, always; otherwise, carry + on only if not anchored. */ + + if (rc != PCRE_ERROR_NOMATCH || anchored) + { + if (rc == PCRE_ERROR_PARTIAL && offsetcount >= 2) + { + offsets[0] = (int)(md->start_used_ptr - (PCRE_PUCHAR)subject); + offsets[1] = (int)(end_subject - (PCRE_PUCHAR)subject); + if (offsetcount > 2) + offsets[2] = (int)(current_subject - (PCRE_PUCHAR)subject); + } + return rc; + } + + /* Advance to the next subject character unless we are at the end of a line + and firstline is set. */ + + if (firstline && IS_NEWLINE(current_subject)) break; + current_subject++; +#ifdef SUPPORT_UTF + if (utf) + { + ACROSSCHAR(current_subject < end_subject, *current_subject, + current_subject++); + } +#endif + if (current_subject > end_subject) break; + + /* If we have just passed a CR and we are now at a LF, and the pattern does + not contain any explicit matches for \r or \n, and the newline option is CRLF + or ANY or ANYCRLF, advance the match position by one more character. */ + + if (UCHAR21TEST(current_subject - 1) == CHAR_CR && + current_subject < end_subject && + UCHAR21TEST(current_subject) == CHAR_NL && + (re->flags & PCRE_HASCRORLF) == 0 && + (md->nltype == NLTYPE_ANY || + md->nltype == NLTYPE_ANYCRLF || + md->nllen == 2)) + current_subject++; + + } /* "Bumpalong" loop */ + +return PCRE_ERROR_NOMATCH; +} + +/* End of pcre_dfa_exec.c */ diff --git a/plugins/Pcre16/src/pcre_exec.c b/plugins/Pcre16/src/pcre_exec.c new file mode 100644 index 0000000000..5dec99234a --- /dev/null +++ b/plugins/Pcre16/src/pcre_exec.c @@ -0,0 +1,7178 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2014 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* This module contains pcre_exec(), the externally visible function that does +pattern matching using an NFA algorithm, trying to mimic Perl as closely as +possible. There are also some static supporting functions. */ + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#define NLBLOCK md /* Block containing newline information */ +#define PSSTART start_subject /* Field containing processed string start */ +#define PSEND end_subject /* Field containing processed string end */ + +#include "pcre_internal.h" + +/* Undefine some potentially clashing cpp symbols */ + +#undef min +#undef max + +/* The md->capture_last field uses the lower 16 bits for the last captured +substring (which can never be greater than 65535) and a bit in the top half +to mean "capture vector overflowed". This odd way of doing things was +implemented when it was realized that preserving and restoring the overflow bit +whenever the last capture number was saved/restored made for a neater +interface, and doing it this way saved on (a) another variable, which would +have increased the stack frame size (a big NO-NO in PCRE) and (b) another +separate set of save/restore instructions. The following defines are used in +implementing this. */ + +#define CAPLMASK 0x0000ffff /* The bits used for last_capture */ +#define OVFLMASK 0xffff0000 /* The bits used for the overflow flag */ +#define OVFLBIT 0x00010000 /* The bit that is set for overflow */ + +/* Values for setting in md->match_function_type to indicate two special types +of call to match(). We do it this way to save on using another stack variable, +as stack usage is to be discouraged. */ + +#define MATCH_CONDASSERT 1 /* Called to check a condition assertion */ +#define MATCH_CBEGROUP 2 /* Could-be-empty unlimited repeat group */ + +/* Non-error returns from the match() function. Error returns are externally +defined PCRE_ERROR_xxx codes, which are all negative. */ + +#define MATCH_MATCH 1 +#define MATCH_NOMATCH 0 + +/* Special internal returns from the match() function. Make them sufficiently +negative to avoid the external error codes. */ + +#define MATCH_ACCEPT (-999) +#define MATCH_KETRPOS (-998) +#define MATCH_ONCE (-997) +/* The next 5 must be kept together and in sequence so that a test that checks +for any one of them can use a range. */ +#define MATCH_COMMIT (-996) +#define MATCH_PRUNE (-995) +#define MATCH_SKIP (-994) +#define MATCH_SKIP_ARG (-993) +#define MATCH_THEN (-992) +#define MATCH_BACKTRACK_MAX MATCH_THEN +#define MATCH_BACKTRACK_MIN MATCH_COMMIT + +/* Maximum number of ints of offset to save on the stack for recursive calls. +If the offset vector is bigger, malloc is used. This should be a multiple of 3, +because the offset vector is always a multiple of 3 long. */ + +#define REC_STACK_SAVE_MAX 30 + +/* Min and max values for the common repeats; for the maxima, 0 => infinity */ + +static const char rep_min[] = { 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, }; +static const char rep_max[] = { 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, }; + +#ifdef PCRE_DEBUG +/************************************************* +* Debugging function to print chars * +*************************************************/ + +/* Print a sequence of chars in printable format, stopping at the end of the +subject if the requested. + +Arguments: + p points to characters + length number to print + is_subject TRUE if printing from within md->start_subject + md pointer to matching data block, if is_subject is TRUE + +Returns: nothing +*/ + +static void +pchars(const pcre_uchar *p, int length, BOOL is_subject, match_data *md) +{ +pcre_uint32 c; +BOOL utf = md->utf; +if (is_subject && length > md->end_subject - p) length = md->end_subject - p; +while (length-- > 0) + if (isprint(c = UCHAR21INCTEST(p))) printf("%c", (char)c); else printf("\\x{%02x}", c); +} +#endif + + + +/************************************************* +* Match a back-reference * +*************************************************/ + +/* Normally, if a back reference hasn't been set, the length that is passed is +negative, so the match always fails. However, in JavaScript compatibility mode, +the length passed is zero. Note that in caseless UTF-8 mode, the number of +subject bytes matched may be different to the number of reference bytes. + +Arguments: + offset index into the offset vector + eptr pointer into the subject + length length of reference to be matched (number of bytes) + md points to match data block + caseless TRUE if caseless + +Returns: >= 0 the number of subject bytes matched + -1 no match + -2 partial match; always given if at end subject +*/ + +static int +match_ref(int offset, register PCRE_PUCHAR eptr, int length, match_data *md, + BOOL caseless) +{ +PCRE_PUCHAR eptr_start = eptr; +register PCRE_PUCHAR p = md->start_subject + md->offset_vector[offset]; +#if defined SUPPORT_UTF && defined SUPPORT_UCP +BOOL utf = md->utf; +#endif + +#ifdef PCRE_DEBUG +if (eptr >= md->end_subject) + printf("matching subject <null>"); +else + { + printf("matching subject "); + pchars(eptr, length, TRUE, md); + } +printf(" against backref "); +pchars(p, length, FALSE, md); +printf("\n"); +#endif + +/* Always fail if reference not set (and not JavaScript compatible - in that +case the length is passed as zero). */ + +if (length < 0) return -1; + +/* Separate the caseless case for speed. In UTF-8 mode we can only do this +properly if Unicode properties are supported. Otherwise, we can check only +ASCII characters. */ + +if (caseless) + { +#if defined SUPPORT_UTF && defined SUPPORT_UCP + if (utf) + { + /* Match characters up to the end of the reference. NOTE: the number of + data units matched may differ, because in UTF-8 there are some characters + whose upper and lower case versions code have different numbers of bytes. + For example, U+023A (2 bytes in UTF-8) is the upper case version of U+2C65 + (3 bytes in UTF-8); a sequence of 3 of the former uses 6 bytes, as does a + sequence of two of the latter. It is important, therefore, to check the + length along the reference, not along the subject (earlier code did this + wrong). */ + + PCRE_PUCHAR endptr = p + length; + while (p < endptr) + { + pcre_uint32 c, d; + const ucd_record *ur; + if (eptr >= md->end_subject) return -2; /* Partial match */ + GETCHARINC(c, eptr); + GETCHARINC(d, p); + ur = GET_UCD(d); + if (c != d && c != d + ur->other_case) + { + const pcre_uint32 *pp = PRIV(ucd_caseless_sets) + ur->caseset; + for (;;) + { + if (c < *pp) return -1; + if (c == *pp++) break; + } + } + } + } + else +#endif + + /* The same code works when not in UTF-8 mode and in UTF-8 mode when there + is no UCP support. */ + { + while (length-- > 0) + { + pcre_uint32 cc, cp; + if (eptr >= md->end_subject) return -2; /* Partial match */ + cc = UCHAR21TEST(eptr); + cp = UCHAR21TEST(p); + if (TABLE_GET(cp, md->lcc, cp) != TABLE_GET(cc, md->lcc, cc)) return -1; + p++; + eptr++; + } + } + } + +/* In the caseful case, we can just compare the bytes, whether or not we +are in UTF-8 mode. */ + +else + { + while (length-- > 0) + { + if (eptr >= md->end_subject) return -2; /* Partial match */ + if (UCHAR21INCTEST(p) != UCHAR21INCTEST(eptr)) return -1; + } + } + +return (int)(eptr - eptr_start); +} + + + +/*************************************************************************** +**************************************************************************** + RECURSION IN THE match() FUNCTION + +The match() function is highly recursive, though not every recursive call +increases the recursive depth. Nevertheless, some regular expressions can cause +it to recurse to a great depth. I was writing for Unix, so I just let it call +itself recursively. This uses the stack for saving everything that has to be +saved for a recursive call. On Unix, the stack can be large, and this works +fine. + +It turns out that on some non-Unix-like systems there are problems with +programs that use a lot of stack. (This despite the fact that every last chip +has oodles of memory these days, and techniques for extending the stack have +been known for decades.) So.... + +There is a fudge, triggered by defining NO_RECURSE, which avoids recursive +calls by keeping local variables that need to be preserved in blocks of memory +obtained from malloc() instead instead of on the stack. Macros are used to +achieve this so that the actual code doesn't look very different to what it +always used to. + +The original heap-recursive code used longjmp(). However, it seems that this +can be very slow on some operating systems. Following a suggestion from Stan +Switzer, the use of longjmp() has been abolished, at the cost of having to +provide a unique number for each call to RMATCH. There is no way of generating +a sequence of numbers at compile time in C. I have given them names, to make +them stand out more clearly. + +Crude tests on x86 Linux show a small speedup of around 5-8%. However, on +FreeBSD, avoiding longjmp() more than halves the time taken to run the standard +tests. Furthermore, not using longjmp() means that local dynamic variables +don't have indeterminate values; this has meant that the frame size can be +reduced because the result can be "passed back" by straight setting of the +variable instead of being passed in the frame. +**************************************************************************** +***************************************************************************/ + +/* Numbers for RMATCH calls. When this list is changed, the code at HEAP_RETURN +below must be updated in sync. */ + +enum { RM1=1, RM2, RM3, RM4, RM5, RM6, RM7, RM8, RM9, RM10, + RM11, RM12, RM13, RM14, RM15, RM16, RM17, RM18, RM19, RM20, + RM21, RM22, RM23, RM24, RM25, RM26, RM27, RM28, RM29, RM30, + RM31, RM32, RM33, RM34, RM35, RM36, RM37, RM38, RM39, RM40, + RM41, RM42, RM43, RM44, RM45, RM46, RM47, RM48, RM49, RM50, + RM51, RM52, RM53, RM54, RM55, RM56, RM57, RM58, RM59, RM60, + RM61, RM62, RM63, RM64, RM65, RM66, RM67 }; + +/* These versions of the macros use the stack, as normal. There are debugging +versions and production versions. Note that the "rw" argument of RMATCH isn't +actually used in this definition. */ + +#ifndef NO_RECURSE +#define REGISTER register + +#ifdef PCRE_DEBUG +#define RMATCH(ra,rb,rc,rd,re,rw) \ + { \ + printf("match() called in line %d\n", __LINE__); \ + rrc = match(ra,rb,mstart,rc,rd,re,rdepth+1); \ + printf("to line %d\n", __LINE__); \ + } +#define RRETURN(ra) \ + { \ + printf("match() returned %d from line %d\n", ra, __LINE__); \ + return ra; \ + } +#else +#define RMATCH(ra,rb,rc,rd,re,rw) \ + rrc = match(ra,rb,mstart,rc,rd,re,rdepth+1) +#define RRETURN(ra) return ra +#endif + +#else + + +/* These versions of the macros manage a private stack on the heap. Note that +the "rd" argument of RMATCH isn't actually used in this definition. It's the md +argument of match(), which never changes. */ + +#define REGISTER + +#define RMATCH(ra,rb,rc,rd,re,rw)\ + {\ + heapframe *newframe = frame->Xnextframe;\ + if (newframe == NULL)\ + {\ + newframe = (heapframe *)(PUBL(stack_malloc))(sizeof(heapframe));\ + if (newframe == NULL) RRETURN(PCRE_ERROR_NOMEMORY);\ + newframe->Xnextframe = NULL;\ + frame->Xnextframe = newframe;\ + }\ + frame->Xwhere = rw;\ + newframe->Xeptr = ra;\ + newframe->Xecode = rb;\ + newframe->Xmstart = mstart;\ + newframe->Xoffset_top = rc;\ + newframe->Xeptrb = re;\ + newframe->Xrdepth = frame->Xrdepth + 1;\ + newframe->Xprevframe = frame;\ + frame = newframe;\ + DPRINTF(("restarting from line %d\n", __LINE__));\ + goto HEAP_RECURSE;\ + L_##rw:\ + DPRINTF(("jumped back to line %d\n", __LINE__));\ + } + +#define RRETURN(ra)\ + {\ + heapframe *oldframe = frame;\ + frame = oldframe->Xprevframe;\ + if (frame != NULL)\ + {\ + rrc = ra;\ + goto HEAP_RETURN;\ + }\ + return ra;\ + } + + +/* Structure for remembering the local variables in a private frame */ + +typedef struct heapframe { + struct heapframe *Xprevframe; + struct heapframe *Xnextframe; + + /* Function arguments that may change */ + + PCRE_PUCHAR Xeptr; + const pcre_uchar *Xecode; + PCRE_PUCHAR Xmstart; + int Xoffset_top; + eptrblock *Xeptrb; + unsigned int Xrdepth; + + /* Function local variables */ + + PCRE_PUCHAR Xcallpat; +#ifdef SUPPORT_UTF + PCRE_PUCHAR Xcharptr; +#endif + PCRE_PUCHAR Xdata; + PCRE_PUCHAR Xnext; + PCRE_PUCHAR Xpp; + PCRE_PUCHAR Xprev; + PCRE_PUCHAR Xsaved_eptr; + + recursion_info Xnew_recursive; + + BOOL Xcur_is_word; + BOOL Xcondition; + BOOL Xprev_is_word; + +#ifdef SUPPORT_UCP + int Xprop_type; + unsigned int Xprop_value; + int Xprop_fail_result; + int Xoclength; + pcre_uchar Xocchars[6]; +#endif + + int Xcodelink; + int Xctype; + unsigned int Xfc; + int Xfi; + int Xlength; + int Xmax; + int Xmin; + unsigned int Xnumber; + int Xoffset; + unsigned int Xop; + pcre_int32 Xsave_capture_last; + int Xsave_offset1, Xsave_offset2, Xsave_offset3; + int Xstacksave[REC_STACK_SAVE_MAX]; + + eptrblock Xnewptrb; + + /* Where to jump back to */ + + int Xwhere; + +} heapframe; + +#endif + + +/*************************************************************************** +***************************************************************************/ + + + +/************************************************* +* Match from current position * +*************************************************/ + +/* This function is called recursively in many circumstances. Whenever it +returns a negative (error) response, the outer incarnation must also return the +same response. */ + +/* These macros pack up tests that are used for partial matching, and which +appear several times in the code. We set the "hit end" flag if the pointer is +at the end of the subject and also past the start of the subject (i.e. +something has been matched). For hard partial matching, we then return +immediately. The second one is used when we already know we are past the end of +the subject. */ + +#define CHECK_PARTIAL()\ + if (md->partial != 0 && eptr >= md->end_subject && \ + eptr > md->start_used_ptr) \ + { \ + md->hitend = TRUE; \ + if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); \ + } + +#define SCHECK_PARTIAL()\ + if (md->partial != 0 && eptr > md->start_used_ptr) \ + { \ + md->hitend = TRUE; \ + if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); \ + } + + +/* Performance note: It might be tempting to extract commonly used fields from +the md structure (e.g. utf, end_subject) into individual variables to improve +performance. Tests using gcc on a SPARC disproved this; in the first case, it +made performance worse. + +Arguments: + eptr pointer to current character in subject + ecode pointer to current position in compiled code + mstart pointer to the current match start position (can be modified + by encountering \K) + offset_top current top pointer + md pointer to "static" info for the match + eptrb pointer to chain of blocks containing eptr at start of + brackets - for testing for empty matches + rdepth the recursion depth + +Returns: MATCH_MATCH if matched ) these values are >= 0 + MATCH_NOMATCH if failed to match ) + a negative MATCH_xxx value for PRUNE, SKIP, etc + a negative PCRE_ERROR_xxx value if aborted by an error condition + (e.g. stopped by repeated call or recursion limit) +*/ + +static int +match(REGISTER PCRE_PUCHAR eptr, REGISTER const pcre_uchar *ecode, + PCRE_PUCHAR mstart, int offset_top, match_data *md, eptrblock *eptrb, + unsigned int rdepth) +{ +/* These variables do not need to be preserved over recursion in this function, +so they can be ordinary variables in all cases. Mark some of them with +"register" because they are used a lot in loops. */ + +register int rrc; /* Returns from recursive calls */ +register int i; /* Used for loops not involving calls to RMATCH() */ +register pcre_uint32 c; /* Character values not kept over RMATCH() calls */ +register BOOL utf; /* Local copy of UTF flag for speed */ + +BOOL minimize, possessive; /* Quantifier options */ +BOOL caseless; +int condcode; + +/* When recursion is not being used, all "local" variables that have to be +preserved over calls to RMATCH() are part of a "frame". We set up the top-level +frame on the stack here; subsequent instantiations are obtained from the heap +whenever RMATCH() does a "recursion". See the macro definitions above. Putting +the top-level on the stack rather than malloc-ing them all gives a performance +boost in many cases where there is not much "recursion". */ + +#ifdef NO_RECURSE +heapframe *frame = (heapframe *)md->match_frames_base; + +/* Copy in the original argument variables */ + +frame->Xeptr = eptr; +frame->Xecode = ecode; +frame->Xmstart = mstart; +frame->Xoffset_top = offset_top; +frame->Xeptrb = eptrb; +frame->Xrdepth = rdepth; + +/* This is where control jumps back to to effect "recursion" */ + +HEAP_RECURSE: + +/* Macros make the argument variables come from the current frame */ + +#define eptr frame->Xeptr +#define ecode frame->Xecode +#define mstart frame->Xmstart +#define offset_top frame->Xoffset_top +#define eptrb frame->Xeptrb +#define rdepth frame->Xrdepth + +/* Ditto for the local variables */ + +#ifdef SUPPORT_UTF +#define charptr frame->Xcharptr +#endif +#define callpat frame->Xcallpat +#define codelink frame->Xcodelink +#define data frame->Xdata +#define next frame->Xnext +#define pp frame->Xpp +#define prev frame->Xprev +#define saved_eptr frame->Xsaved_eptr + +#define new_recursive frame->Xnew_recursive + +#define cur_is_word frame->Xcur_is_word +#define condition frame->Xcondition +#define prev_is_word frame->Xprev_is_word + +#ifdef SUPPORT_UCP +#define prop_type frame->Xprop_type +#define prop_value frame->Xprop_value +#define prop_fail_result frame->Xprop_fail_result +#define oclength frame->Xoclength +#define occhars frame->Xocchars +#endif + +#define ctype frame->Xctype +#define fc frame->Xfc +#define fi frame->Xfi +#define length frame->Xlength +#define max frame->Xmax +#define min frame->Xmin +#define number frame->Xnumber +#define offset frame->Xoffset +#define op frame->Xop +#define save_capture_last frame->Xsave_capture_last +#define save_offset1 frame->Xsave_offset1 +#define save_offset2 frame->Xsave_offset2 +#define save_offset3 frame->Xsave_offset3 +#define stacksave frame->Xstacksave + +#define newptrb frame->Xnewptrb + +/* When recursion is being used, local variables are allocated on the stack and +get preserved during recursion in the normal way. In this environment, fi and +i, and fc and c, can be the same variables. */ + +#else /* NO_RECURSE not defined */ +#define fi i +#define fc c + +/* Many of the following variables are used only in small blocks of the code. +My normal style of coding would have declared them within each of those blocks. +However, in order to accommodate the version of this code that uses an external +"stack" implemented on the heap, it is easier to declare them all here, so the +declarations can be cut out in a block. The only declarations within blocks +below are for variables that do not have to be preserved over a recursive call +to RMATCH(). */ + +#ifdef SUPPORT_UTF +const pcre_uchar *charptr; +#endif +const pcre_uchar *callpat; +const pcre_uchar *data; +const pcre_uchar *next; +PCRE_PUCHAR pp; +const pcre_uchar *prev; +PCRE_PUCHAR saved_eptr; + +recursion_info new_recursive; + +BOOL cur_is_word; +BOOL condition; +BOOL prev_is_word; + +#ifdef SUPPORT_UCP +int prop_type; +unsigned int prop_value; +int prop_fail_result; +int oclength; +pcre_uchar occhars[6]; +#endif + +int codelink; +int ctype; +int length; +int max; +int min; +unsigned int number; +int offset; +unsigned int op; +pcre_int32 save_capture_last; +int save_offset1, save_offset2, save_offset3; +int stacksave[REC_STACK_SAVE_MAX]; + +eptrblock newptrb; + +/* There is a special fudge for calling match() in a way that causes it to +measure the size of its basic stack frame when the stack is being used for +recursion. The second argument (ecode) being NULL triggers this behaviour. It +cannot normally ever be NULL. The return is the negated value of the frame +size. */ + +if (ecode == NULL) + { + if (rdepth == 0) + return match((PCRE_PUCHAR)&rdepth, NULL, NULL, 0, NULL, NULL, 1); + else + { + int len = (char *)&rdepth - (char *)eptr; + return (len > 0)? -len : len; + } + } +#endif /* NO_RECURSE */ + +/* To save space on the stack and in the heap frame, I have doubled up on some +of the local variables that are used only in localised parts of the code, but +still need to be preserved over recursive calls of match(). These macros define +the alternative names that are used. */ + +#define allow_zero cur_is_word +#define cbegroup condition +#define code_offset codelink +#define condassert condition +#define matched_once prev_is_word +#define foc number +#define save_mark data + +/* These statements are here to stop the compiler complaining about unitialized +variables. */ + +#ifdef SUPPORT_UCP +prop_value = 0; +prop_fail_result = 0; +#endif + + +/* This label is used for tail recursion, which is used in a few cases even +when NO_RECURSE is not defined, in order to reduce the amount of stack that is +used. Thanks to Ian Taylor for noticing this possibility and sending the +original patch. */ + +TAIL_RECURSE: + +/* OK, now we can get on with the real code of the function. Recursive calls +are specified by the macro RMATCH and RRETURN is used to return. When +NO_RECURSE is *not* defined, these just turn into a recursive call to match() +and a "return", respectively (possibly with some debugging if PCRE_DEBUG is +defined). However, RMATCH isn't like a function call because it's quite a +complicated macro. It has to be used in one particular way. This shouldn't, +however, impact performance when true recursion is being used. */ + +#ifdef SUPPORT_UTF +utf = md->utf; /* Local copy of the flag */ +#else +utf = FALSE; +#endif + +/* First check that we haven't called match() too many times, or that we +haven't exceeded the recursive call limit. */ + +if (md->match_call_count++ >= md->match_limit) RRETURN(PCRE_ERROR_MATCHLIMIT); +if (rdepth >= md->match_limit_recursion) RRETURN(PCRE_ERROR_RECURSIONLIMIT); + +/* At the start of a group with an unlimited repeat that may match an empty +string, the variable md->match_function_type is set to MATCH_CBEGROUP. It is +done this way to save having to use another function argument, which would take +up space on the stack. See also MATCH_CONDASSERT below. + +When MATCH_CBEGROUP is set, add the current subject pointer to the chain of +such remembered pointers, to be checked when we hit the closing ket, in order +to break infinite loops that match no characters. When match() is called in +other circumstances, don't add to the chain. The MATCH_CBEGROUP feature must +NOT be used with tail recursion, because the memory block that is used is on +the stack, so a new one may be required for each match(). */ + +if (md->match_function_type == MATCH_CBEGROUP) + { + newptrb.epb_saved_eptr = eptr; + newptrb.epb_prev = eptrb; + eptrb = &newptrb; + md->match_function_type = 0; + } + +/* Now start processing the opcodes. */ + +for (;;) + { + minimize = possessive = FALSE; + op = *ecode; + + switch(op) + { + case OP_MARK: + md->nomatch_mark = ecode + 2; + md->mark = NULL; /* In case previously set by assertion */ + RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode] + ecode[1], offset_top, md, + eptrb, RM55); + if ((rrc == MATCH_MATCH || rrc == MATCH_ACCEPT) && + md->mark == NULL) md->mark = ecode + 2; + + /* A return of MATCH_SKIP_ARG means that matching failed at SKIP with an + argument, and we must check whether that argument matches this MARK's + argument. It is passed back in md->start_match_ptr (an overloading of that + variable). If it does match, we reset that variable to the current subject + position and return MATCH_SKIP. Otherwise, pass back the return code + unaltered. */ + + else if (rrc == MATCH_SKIP_ARG && + STRCMP_UC_UC_TEST(ecode + 2, md->start_match_ptr) == 0) + { + md->start_match_ptr = eptr; + RRETURN(MATCH_SKIP); + } + RRETURN(rrc); + + case OP_FAIL: + RRETURN(MATCH_NOMATCH); + + case OP_COMMIT: + RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md, + eptrb, RM52); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + RRETURN(MATCH_COMMIT); + + case OP_PRUNE: + RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md, + eptrb, RM51); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + RRETURN(MATCH_PRUNE); + + case OP_PRUNE_ARG: + md->nomatch_mark = ecode + 2; + md->mark = NULL; /* In case previously set by assertion */ + RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode] + ecode[1], offset_top, md, + eptrb, RM56); + if ((rrc == MATCH_MATCH || rrc == MATCH_ACCEPT) && + md->mark == NULL) md->mark = ecode + 2; + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + RRETURN(MATCH_PRUNE); + + case OP_SKIP: + RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md, + eptrb, RM53); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + md->start_match_ptr = eptr; /* Pass back current position */ + RRETURN(MATCH_SKIP); + + /* Note that, for Perl compatibility, SKIP with an argument does NOT set + nomatch_mark. When a pattern match ends with a SKIP_ARG for which there was + not a matching mark, we have to re-run the match, ignoring the SKIP_ARG + that failed and any that precede it (either they also failed, or were not + triggered). To do this, we maintain a count of executed SKIP_ARGs. If a + SKIP_ARG gets to top level, the match is re-run with md->ignore_skip_arg + set to the count of the one that failed. */ + + case OP_SKIP_ARG: + md->skip_arg_count++; + if (md->skip_arg_count <= md->ignore_skip_arg) + { + ecode += PRIV(OP_lengths)[*ecode] + ecode[1]; + break; + } + RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode] + ecode[1], offset_top, md, + eptrb, RM57); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + + /* Pass back the current skip name by overloading md->start_match_ptr and + returning the special MATCH_SKIP_ARG return code. This will either be + caught by a matching MARK, or get to the top, where it causes a rematch + with md->ignore_skip_arg set to the value of md->skip_arg_count. */ + + md->start_match_ptr = ecode + 2; + RRETURN(MATCH_SKIP_ARG); + + /* For THEN (and THEN_ARG) we pass back the address of the opcode, so that + the branch in which it occurs can be determined. Overload the start of + match pointer to do this. */ + + case OP_THEN: + RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md, + eptrb, RM54); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + md->start_match_ptr = ecode; + RRETURN(MATCH_THEN); + + case OP_THEN_ARG: + md->nomatch_mark = ecode + 2; + md->mark = NULL; /* In case previously set by assertion */ + RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode] + ecode[1], offset_top, + md, eptrb, RM58); + if ((rrc == MATCH_MATCH || rrc == MATCH_ACCEPT) && + md->mark == NULL) md->mark = ecode + 2; + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + md->start_match_ptr = ecode; + RRETURN(MATCH_THEN); + + /* Handle an atomic group that does not contain any capturing parentheses. + This can be handled like an assertion. Prior to 8.13, all atomic groups + were handled this way. In 8.13, the code was changed as below for ONCE, so + that backups pass through the group and thereby reset captured values. + However, this uses a lot more stack, so in 8.20, atomic groups that do not + contain any captures generate OP_ONCE_NC, which can be handled in the old, + less stack intensive way. + + Check the alternative branches in turn - the matching won't pass the KET + for this kind of subpattern. If any one branch matches, we carry on as at + the end of a normal bracket, leaving the subject pointer, but resetting + the start-of-match value in case it was changed by \K. */ + + case OP_ONCE_NC: + prev = ecode; + saved_eptr = eptr; + save_mark = md->mark; + do + { + RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, eptrb, RM64); + if (rrc == MATCH_MATCH) /* Note: _not_ MATCH_ACCEPT */ + { + mstart = md->start_match_ptr; + break; + } + if (rrc == MATCH_THEN) + { + next = ecode + GET(ecode,1); + if (md->start_match_ptr < next && + (*ecode == OP_ALT || *next == OP_ALT)) + rrc = MATCH_NOMATCH; + } + + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + ecode += GET(ecode,1); + md->mark = save_mark; + } + while (*ecode == OP_ALT); + + /* If hit the end of the group (which could be repeated), fail */ + + if (*ecode != OP_ONCE_NC && *ecode != OP_ALT) RRETURN(MATCH_NOMATCH); + + /* Continue as from after the group, updating the offsets high water + mark, since extracts may have been taken. */ + + do ecode += GET(ecode, 1); while (*ecode == OP_ALT); + + offset_top = md->end_offset_top; + eptr = md->end_match_ptr; + + /* For a non-repeating ket, just continue at this level. This also + happens for a repeating ket if no characters were matched in the group. + This is the forcible breaking of infinite loops as implemented in Perl + 5.005. */ + + if (*ecode == OP_KET || eptr == saved_eptr) + { + ecode += 1+LINK_SIZE; + break; + } + + /* The repeating kets try the rest of the pattern or restart from the + preceding bracket, in the appropriate order. The second "call" of match() + uses tail recursion, to avoid using another stack frame. */ + + if (*ecode == OP_KETRMIN) + { + RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, eptrb, RM65); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + ecode = prev; + goto TAIL_RECURSE; + } + else /* OP_KETRMAX */ + { + RMATCH(eptr, prev, offset_top, md, eptrb, RM66); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + ecode += 1 + LINK_SIZE; + goto TAIL_RECURSE; + } + /* Control never gets here */ + + /* Handle a capturing bracket, other than those that are possessive with an + unlimited repeat. If there is space in the offset vector, save the current + subject position in the working slot at the top of the vector. We mustn't + change the current values of the data slot, because they may be set from a + previous iteration of this group, and be referred to by a reference inside + the group. A failure to match might occur after the group has succeeded, + if something later on doesn't match. For this reason, we need to restore + the working value and also the values of the final offsets, in case they + were set by a previous iteration of the same bracket. + + If there isn't enough space in the offset vector, treat this as if it were + a non-capturing bracket. Don't worry about setting the flag for the error + case here; that is handled in the code for KET. */ + + case OP_CBRA: + case OP_SCBRA: + number = GET2(ecode, 1+LINK_SIZE); + offset = number << 1; + +#ifdef PCRE_DEBUG + printf("start bracket %d\n", number); + printf("subject="); + pchars(eptr, 16, TRUE, md); + printf("\n"); +#endif + + if (offset < md->offset_max) + { + save_offset1 = md->offset_vector[offset]; + save_offset2 = md->offset_vector[offset+1]; + save_offset3 = md->offset_vector[md->offset_end - number]; + save_capture_last = md->capture_last; + save_mark = md->mark; + + DPRINTF(("saving %d %d %d\n", save_offset1, save_offset2, save_offset3)); + md->offset_vector[md->offset_end - number] = + (int)(eptr - md->start_subject); + + for (;;) + { + if (op >= OP_SBRA) md->match_function_type = MATCH_CBEGROUP; + RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md, + eptrb, RM1); + if (rrc == MATCH_ONCE) break; /* Backing up through an atomic group */ + + /* If we backed up to a THEN, check whether it is within the current + branch by comparing the address of the THEN that is passed back with + the end of the branch. If it is within the current branch, and the + branch is one of two or more alternatives (it either starts or ends + with OP_ALT), we have reached the limit of THEN's action, so convert + the return code to NOMATCH, which will cause normal backtracking to + happen from now on. Otherwise, THEN is passed back to an outer + alternative. This implements Perl's treatment of parenthesized groups, + where a group not containing | does not affect the current alternative, + that is, (X) is NOT the same as (X|(*F)). */ + + if (rrc == MATCH_THEN) + { + next = ecode + GET(ecode,1); + if (md->start_match_ptr < next && + (*ecode == OP_ALT || *next == OP_ALT)) + rrc = MATCH_NOMATCH; + } + + /* Anything other than NOMATCH is passed back. */ + + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + md->capture_last = save_capture_last; + ecode += GET(ecode, 1); + md->mark = save_mark; + if (*ecode != OP_ALT) break; + } + + DPRINTF(("bracket %d failed\n", number)); + md->offset_vector[offset] = save_offset1; + md->offset_vector[offset+1] = save_offset2; + md->offset_vector[md->offset_end - number] = save_offset3; + + /* At this point, rrc will be one of MATCH_ONCE or MATCH_NOMATCH. */ + + RRETURN(rrc); + } + + /* FALL THROUGH ... Insufficient room for saving captured contents. Treat + as a non-capturing bracket. */ + + /* VVVVVVVVVVVVVVVVVVVVVVVVV */ + /* VVVVVVVVVVVVVVVVVVVVVVVVV */ + + DPRINTF(("insufficient capture room: treat as non-capturing\n")); + + /* VVVVVVVVVVVVVVVVVVVVVVVVV */ + /* VVVVVVVVVVVVVVVVVVVVVVVVV */ + + /* Non-capturing or atomic group, except for possessive with unlimited + repeat and ONCE group with no captures. Loop for all the alternatives. + + When we get to the final alternative within the brackets, we used to return + the result of a recursive call to match() whatever happened so it was + possible to reduce stack usage by turning this into a tail recursion, + except in the case of a possibly empty group. However, now that there is + the possiblity of (*THEN) occurring in the final alternative, this + optimization is no longer always possible. + + We can optimize if we know there are no (*THEN)s in the pattern; at present + this is the best that can be done. + + MATCH_ONCE is returned when the end of an atomic group is successfully + reached, but subsequent matching fails. It passes back up the tree (causing + captured values to be reset) until the original atomic group level is + reached. This is tested by comparing md->once_target with the start of the + group. At this point, the return is converted into MATCH_NOMATCH so that + previous backup points can be taken. */ + + case OP_ONCE: + case OP_BRA: + case OP_SBRA: + DPRINTF(("start non-capturing bracket\n")); + + for (;;) + { + if (op >= OP_SBRA || op == OP_ONCE) + md->match_function_type = MATCH_CBEGROUP; + + /* If this is not a possibly empty group, and there are no (*THEN)s in + the pattern, and this is the final alternative, optimize as described + above. */ + + else if (!md->hasthen && ecode[GET(ecode, 1)] != OP_ALT) + { + ecode += PRIV(OP_lengths)[*ecode]; + goto TAIL_RECURSE; + } + + /* In all other cases, we have to make another call to match(). */ + + save_mark = md->mark; + save_capture_last = md->capture_last; + RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md, eptrb, + RM2); + + /* See comment in the code for capturing groups above about handling + THEN. */ + + if (rrc == MATCH_THEN) + { + next = ecode + GET(ecode,1); + if (md->start_match_ptr < next && + (*ecode == OP_ALT || *next == OP_ALT)) + rrc = MATCH_NOMATCH; + } + + if (rrc != MATCH_NOMATCH) + { + if (rrc == MATCH_ONCE) + { + const pcre_uchar *scode = ecode; + if (*scode != OP_ONCE) /* If not at start, find it */ + { + while (*scode == OP_ALT) scode += GET(scode, 1); + scode -= GET(scode, 1); + } + if (md->once_target == scode) rrc = MATCH_NOMATCH; + } + RRETURN(rrc); + } + ecode += GET(ecode, 1); + md->mark = save_mark; + if (*ecode != OP_ALT) break; + md->capture_last = save_capture_last; + } + + RRETURN(MATCH_NOMATCH); + + /* Handle possessive capturing brackets with an unlimited repeat. We come + here from BRAZERO with allow_zero set TRUE. The offset_vector values are + handled similarly to the normal case above. However, the matching is + different. The end of these brackets will always be OP_KETRPOS, which + returns MATCH_KETRPOS without going further in the pattern. By this means + we can handle the group by iteration rather than recursion, thereby + reducing the amount of stack needed. */ + + case OP_CBRAPOS: + case OP_SCBRAPOS: + allow_zero = FALSE; + + POSSESSIVE_CAPTURE: + number = GET2(ecode, 1+LINK_SIZE); + offset = number << 1; + +#ifdef PCRE_DEBUG + printf("start possessive bracket %d\n", number); + printf("subject="); + pchars(eptr, 16, TRUE, md); + printf("\n"); +#endif + + if (offset < md->offset_max) + { + matched_once = FALSE; + code_offset = (int)(ecode - md->start_code); + + save_offset1 = md->offset_vector[offset]; + save_offset2 = md->offset_vector[offset+1]; + save_offset3 = md->offset_vector[md->offset_end - number]; + save_capture_last = md->capture_last; + + DPRINTF(("saving %d %d %d\n", save_offset1, save_offset2, save_offset3)); + + /* Each time round the loop, save the current subject position for use + when the group matches. For MATCH_MATCH, the group has matched, so we + restart it with a new subject starting position, remembering that we had + at least one match. For MATCH_NOMATCH, carry on with the alternatives, as + usual. If we haven't matched any alternatives in any iteration, check to + see if a previous iteration matched. If so, the group has matched; + continue from afterwards. Otherwise it has failed; restore the previous + capture values before returning NOMATCH. */ + + for (;;) + { + md->offset_vector[md->offset_end - number] = + (int)(eptr - md->start_subject); + if (op >= OP_SBRA) md->match_function_type = MATCH_CBEGROUP; + RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md, + eptrb, RM63); + if (rrc == MATCH_KETRPOS) + { + offset_top = md->end_offset_top; + eptr = md->end_match_ptr; + ecode = md->start_code + code_offset; + save_capture_last = md->capture_last; + matched_once = TRUE; + mstart = md->start_match_ptr; /* In case \K changed it */ + continue; + } + + /* See comment in the code for capturing groups above about handling + THEN. */ + + if (rrc == MATCH_THEN) + { + next = ecode + GET(ecode,1); + if (md->start_match_ptr < next && + (*ecode == OP_ALT || *next == OP_ALT)) + rrc = MATCH_NOMATCH; + } + + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + md->capture_last = save_capture_last; + ecode += GET(ecode, 1); + if (*ecode != OP_ALT) break; + } + + if (!matched_once) + { + md->offset_vector[offset] = save_offset1; + md->offset_vector[offset+1] = save_offset2; + md->offset_vector[md->offset_end - number] = save_offset3; + } + + if (allow_zero || matched_once) + { + ecode += 1 + LINK_SIZE; + break; + } + + RRETURN(MATCH_NOMATCH); + } + + /* FALL THROUGH ... Insufficient room for saving captured contents. Treat + as a non-capturing bracket. */ + + /* VVVVVVVVVVVVVVVVVVVVVVVVV */ + /* VVVVVVVVVVVVVVVVVVVVVVVVV */ + + DPRINTF(("insufficient capture room: treat as non-capturing\n")); + + /* VVVVVVVVVVVVVVVVVVVVVVVVV */ + /* VVVVVVVVVVVVVVVVVVVVVVVVV */ + + /* Non-capturing possessive bracket with unlimited repeat. We come here + from BRAZERO with allow_zero = TRUE. The code is similar to the above, + without the capturing complication. It is written out separately for speed + and cleanliness. */ + + case OP_BRAPOS: + case OP_SBRAPOS: + allow_zero = FALSE; + + POSSESSIVE_NON_CAPTURE: + matched_once = FALSE; + code_offset = (int)(ecode - md->start_code); + save_capture_last = md->capture_last; + + for (;;) + { + if (op >= OP_SBRA) md->match_function_type = MATCH_CBEGROUP; + RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md, + eptrb, RM48); + if (rrc == MATCH_KETRPOS) + { + offset_top = md->end_offset_top; + eptr = md->end_match_ptr; + ecode = md->start_code + code_offset; + matched_once = TRUE; + mstart = md->start_match_ptr; /* In case \K reset it */ + continue; + } + + /* See comment in the code for capturing groups above about handling + THEN. */ + + if (rrc == MATCH_THEN) + { + next = ecode + GET(ecode,1); + if (md->start_match_ptr < next && + (*ecode == OP_ALT || *next == OP_ALT)) + rrc = MATCH_NOMATCH; + } + + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + ecode += GET(ecode, 1); + if (*ecode != OP_ALT) break; + md->capture_last = save_capture_last; + } + + if (matched_once || allow_zero) + { + ecode += 1 + LINK_SIZE; + break; + } + RRETURN(MATCH_NOMATCH); + + /* Control never reaches here. */ + + /* Conditional group: compilation checked that there are no more than two + branches. If the condition is false, skipping the first branch takes us + past the end of the item if there is only one branch, but that's exactly + what we want. */ + + case OP_COND: + case OP_SCOND: + + /* The variable codelink will be added to ecode when the condition is + false, to get to the second branch. Setting it to the offset to the ALT + or KET, then incrementing ecode achieves this effect. We now have ecode + pointing to the condition or callout. */ + + codelink = GET(ecode, 1); /* Offset to the second branch */ + ecode += 1 + LINK_SIZE; /* From this opcode */ + + /* Because of the way auto-callout works during compile, a callout item is + inserted between OP_COND and an assertion condition. */ + + if (*ecode == OP_CALLOUT) + { + if (PUBL(callout) != NULL) + { + PUBL(callout_block) cb; + cb.version = 2; /* Version 1 of the callout block */ + cb.callout_number = ecode[1]; + cb.offset_vector = md->offset_vector; +#if defined COMPILE_PCRE8 + cb.subject = (PCRE_SPTR)md->start_subject; +#elif defined COMPILE_PCRE16 + cb.subject = (PCRE_SPTR16)md->start_subject; +#elif defined COMPILE_PCRE32 + cb.subject = (PCRE_SPTR32)md->start_subject; +#endif + cb.subject_length = (int)(md->end_subject - md->start_subject); + cb.start_match = (int)(mstart - md->start_subject); + cb.current_position = (int)(eptr - md->start_subject); + cb.pattern_position = GET(ecode, 2); + cb.next_item_length = GET(ecode, 2 + LINK_SIZE); + cb.capture_top = offset_top/2; + cb.capture_last = md->capture_last & CAPLMASK; + /* Internal change requires this for API compatibility. */ + if (cb.capture_last == 0) cb.capture_last = -1; + cb.callout_data = md->callout_data; + cb.mark = md->nomatch_mark; + if ((rrc = (*PUBL(callout))(&cb)) > 0) RRETURN(MATCH_NOMATCH); + if (rrc < 0) RRETURN(rrc); + } + + /* Advance ecode past the callout, so it now points to the condition. We + must adjust codelink so that the value of ecode+codelink is unchanged. */ + + ecode += PRIV(OP_lengths)[OP_CALLOUT]; + codelink -= PRIV(OP_lengths)[OP_CALLOUT]; + } + + /* Test the various possible conditions */ + + condition = FALSE; + switch(condcode = *ecode) + { + case OP_RREF: /* Numbered group recursion test */ + if (md->recursive != NULL) /* Not recursing => FALSE */ + { + unsigned int recno = GET2(ecode, 1); /* Recursion group number*/ + condition = (recno == RREF_ANY || recno == md->recursive->group_num); + } + break; + + case OP_DNRREF: /* Duplicate named group recursion test */ + if (md->recursive != NULL) + { + int count = GET2(ecode, 1 + IMM2_SIZE); + pcre_uchar *slot = md->name_table + GET2(ecode, 1) * md->name_entry_size; + while (count-- > 0) + { + unsigned int recno = GET2(slot, 0); + condition = recno == md->recursive->group_num; + if (condition) break; + slot += md->name_entry_size; + } + } + break; + + case OP_CREF: /* Numbered group used test */ + offset = GET2(ecode, 1) << 1; /* Doubled ref number */ + condition = offset < offset_top && md->offset_vector[offset] >= 0; + break; + + case OP_DNCREF: /* Duplicate named group used test */ + { + int count = GET2(ecode, 1 + IMM2_SIZE); + pcre_uchar *slot = md->name_table + GET2(ecode, 1) * md->name_entry_size; + while (count-- > 0) + { + offset = GET2(slot, 0) << 1; + condition = offset < offset_top && md->offset_vector[offset] >= 0; + if (condition) break; + slot += md->name_entry_size; + } + } + break; + + case OP_DEF: /* DEFINE - always false */ + break; + + /* The condition is an assertion. Call match() to evaluate it - setting + md->match_function_type to MATCH_CONDASSERT causes it to stop at the end + of an assertion. */ + + default: + md->match_function_type = MATCH_CONDASSERT; + RMATCH(eptr, ecode, offset_top, md, NULL, RM3); + if (rrc == MATCH_MATCH) + { + if (md->end_offset_top > offset_top) + offset_top = md->end_offset_top; /* Captures may have happened */ + condition = TRUE; + + /* Advance ecode past the assertion to the start of the first branch, + but adjust it so that the general choosing code below works. */ + + ecode += GET(ecode, 1); + while (*ecode == OP_ALT) ecode += GET(ecode, 1); + ecode += 1 + LINK_SIZE - PRIV(OP_lengths)[condcode]; + } + + /* PCRE doesn't allow the effect of (*THEN) to escape beyond an + assertion; it is therefore treated as NOMATCH. Any other return is an + error. */ + + else if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) + { + RRETURN(rrc); /* Need braces because of following else */ + } + break; + } + + /* Choose branch according to the condition */ + + ecode += condition? PRIV(OP_lengths)[condcode] : codelink; + + /* We are now at the branch that is to be obeyed. As there is only one, we + can use tail recursion to avoid using another stack frame, except when + there is unlimited repeat of a possibly empty group. In the latter case, a + recursive call to match() is always required, unless the second alternative + doesn't exist, in which case we can just plough on. Note that, for + compatibility with Perl, the | in a conditional group is NOT treated as + creating two alternatives. If a THEN is encountered in the branch, it + propagates out to the enclosing alternative (unless nested in a deeper set + of alternatives, of course). */ + + if (condition || ecode[-(1+LINK_SIZE)] == OP_ALT) + { + if (op != OP_SCOND) + { + goto TAIL_RECURSE; + } + + md->match_function_type = MATCH_CBEGROUP; + RMATCH(eptr, ecode, offset_top, md, eptrb, RM49); + RRETURN(rrc); + } + + /* Condition false & no alternative; continue after the group. */ + + else + { + } + break; + + + /* Before OP_ACCEPT there may be any number of OP_CLOSE opcodes, + to close any currently open capturing brackets. */ + + case OP_CLOSE: + number = GET2(ecode, 1); /* Must be less than 65536 */ + offset = number << 1; + +#ifdef PCRE_DEBUG + printf("end bracket %d at *ACCEPT", number); + printf("\n"); +#endif + + md->capture_last = (md->capture_last & OVFLMASK) | number; + if (offset >= md->offset_max) md->capture_last |= OVFLBIT; else + { + md->offset_vector[offset] = + md->offset_vector[md->offset_end - number]; + md->offset_vector[offset+1] = (int)(eptr - md->start_subject); + if (offset_top <= offset) offset_top = offset + 2; + } + ecode += 1 + IMM2_SIZE; + break; + + + /* End of the pattern, either real or forced. */ + + case OP_END: + case OP_ACCEPT: + case OP_ASSERT_ACCEPT: + + /* If we have matched an empty string, fail if not in an assertion and not + in a recursion if either PCRE_NOTEMPTY is set, or if PCRE_NOTEMPTY_ATSTART + is set and we have matched at the start of the subject. In both cases, + backtracking will then try other alternatives, if any. */ + + if (eptr == mstart && op != OP_ASSERT_ACCEPT && + md->recursive == NULL && + (md->notempty || + (md->notempty_atstart && + mstart == md->start_subject + md->start_offset))) + RRETURN(MATCH_NOMATCH); + + /* Otherwise, we have a match. */ + + md->end_match_ptr = eptr; /* Record where we ended */ + md->end_offset_top = offset_top; /* and how many extracts were taken */ + md->start_match_ptr = mstart; /* and the start (\K can modify) */ + + /* For some reason, the macros don't work properly if an expression is + given as the argument to RRETURN when the heap is in use. */ + + rrc = (op == OP_END)? MATCH_MATCH : MATCH_ACCEPT; + RRETURN(rrc); + + /* Assertion brackets. Check the alternative branches in turn - the + matching won't pass the KET for an assertion. If any one branch matches, + the assertion is true. Lookbehind assertions have an OP_REVERSE item at the + start of each branch to move the current point backwards, so the code at + this level is identical to the lookahead case. When the assertion is part + of a condition, we want to return immediately afterwards. The caller of + this incarnation of the match() function will have set MATCH_CONDASSERT in + md->match_function type, and one of these opcodes will be the first opcode + that is processed. We use a local variable that is preserved over calls to + match() to remember this case. */ + + case OP_ASSERT: + case OP_ASSERTBACK: + save_mark = md->mark; + if (md->match_function_type == MATCH_CONDASSERT) + { + condassert = TRUE; + md->match_function_type = 0; + } + else condassert = FALSE; + + /* Loop for each branch */ + + do + { + RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, NULL, RM4); + + /* A match means that the assertion is true; break out of the loop + that matches its alternatives. */ + + if (rrc == MATCH_MATCH || rrc == MATCH_ACCEPT) + { + mstart = md->start_match_ptr; /* In case \K reset it */ + break; + } + + /* If not matched, restore the previous mark setting. */ + + md->mark = save_mark; + + /* See comment in the code for capturing groups above about handling + THEN. */ + + if (rrc == MATCH_THEN) + { + next = ecode + GET(ecode,1); + if (md->start_match_ptr < next && + (*ecode == OP_ALT || *next == OP_ALT)) + rrc = MATCH_NOMATCH; + } + + /* Anything other than NOMATCH causes the entire assertion to fail, + passing back the return code. This includes COMMIT, SKIP, PRUNE and an + uncaptured THEN, which means they take their normal effect. This + consistent approach does not always have exactly the same effect as in + Perl. */ + + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + ecode += GET(ecode, 1); + } + while (*ecode == OP_ALT); /* Continue for next alternative */ + + /* If we have tried all the alternative branches, the assertion has + failed. If not, we broke out after a match. */ + + if (*ecode == OP_KET) RRETURN(MATCH_NOMATCH); + + /* If checking an assertion for a condition, return MATCH_MATCH. */ + + if (condassert) RRETURN(MATCH_MATCH); + + /* Continue from after a successful assertion, updating the offsets high + water mark, since extracts may have been taken during the assertion. */ + + do ecode += GET(ecode,1); while (*ecode == OP_ALT); + ecode += 1 + LINK_SIZE; + offset_top = md->end_offset_top; + continue; + + /* Negative assertion: all branches must fail to match for the assertion to + succeed. */ + + case OP_ASSERT_NOT: + case OP_ASSERTBACK_NOT: + save_mark = md->mark; + if (md->match_function_type == MATCH_CONDASSERT) + { + condassert = TRUE; + md->match_function_type = 0; + } + else condassert = FALSE; + + /* Loop for each alternative branch. */ + + do + { + RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, NULL, RM5); + md->mark = save_mark; /* Always restore the mark setting */ + + switch(rrc) + { + case MATCH_MATCH: /* A successful match means */ + case MATCH_ACCEPT: /* the assertion has failed. */ + RRETURN(MATCH_NOMATCH); + + case MATCH_NOMATCH: /* Carry on with next branch */ + break; + + /* See comment in the code for capturing groups above about handling + THEN. */ + + case MATCH_THEN: + next = ecode + GET(ecode,1); + if (md->start_match_ptr < next && + (*ecode == OP_ALT || *next == OP_ALT)) + { + rrc = MATCH_NOMATCH; + break; + } + /* Otherwise fall through. */ + + /* COMMIT, SKIP, PRUNE, and an uncaptured THEN cause the whole + assertion to fail to match, without considering any more alternatives. + Failing to match means the assertion is true. This is a consistent + approach, but does not always have the same effect as in Perl. */ + + case MATCH_COMMIT: + case MATCH_SKIP: + case MATCH_SKIP_ARG: + case MATCH_PRUNE: + do ecode += GET(ecode,1); while (*ecode == OP_ALT); + goto NEG_ASSERT_TRUE; /* Break out of alternation loop */ + + /* Anything else is an error */ + + default: + RRETURN(rrc); + } + + /* Continue with next branch */ + + ecode += GET(ecode,1); + } + while (*ecode == OP_ALT); + + /* All branches in the assertion failed to match. */ + + NEG_ASSERT_TRUE: + if (condassert) RRETURN(MATCH_MATCH); /* Condition assertion */ + ecode += 1 + LINK_SIZE; /* Continue with current branch */ + continue; + + /* Move the subject pointer back. This occurs only at the start of + each branch of a lookbehind assertion. If we are too close to the start to + move back, this match function fails. When working with UTF-8 we move + back a number of characters, not bytes. */ + + case OP_REVERSE: +#ifdef SUPPORT_UTF + if (utf) + { + i = GET(ecode, 1); + while (i-- > 0) + { + eptr--; + if (eptr < md->start_subject) RRETURN(MATCH_NOMATCH); + BACKCHAR(eptr); + } + } + else +#endif + + /* No UTF-8 support, or not in UTF-8 mode: count is byte count */ + + { + eptr -= GET(ecode, 1); + if (eptr < md->start_subject) RRETURN(MATCH_NOMATCH); + } + + /* Save the earliest consulted character, then skip to next op code */ + + if (eptr < md->start_used_ptr) md->start_used_ptr = eptr; + ecode += 1 + LINK_SIZE; + break; + + /* The callout item calls an external function, if one is provided, passing + details of the match so far. This is mainly for debugging, though the + function is able to force a failure. */ + + case OP_CALLOUT: + if (PUBL(callout) != NULL) + { + PUBL(callout_block) cb; + cb.version = 2; /* Version 1 of the callout block */ + cb.callout_number = ecode[1]; + cb.offset_vector = md->offset_vector; +#if defined COMPILE_PCRE8 + cb.subject = (PCRE_SPTR)md->start_subject; +#elif defined COMPILE_PCRE16 + cb.subject = (PCRE_SPTR16)md->start_subject; +#elif defined COMPILE_PCRE32 + cb.subject = (PCRE_SPTR32)md->start_subject; +#endif + cb.subject_length = (int)(md->end_subject - md->start_subject); + cb.start_match = (int)(mstart - md->start_subject); + cb.current_position = (int)(eptr - md->start_subject); + cb.pattern_position = GET(ecode, 2); + cb.next_item_length = GET(ecode, 2 + LINK_SIZE); + cb.capture_top = offset_top/2; + cb.capture_last = md->capture_last & CAPLMASK; + /* Internal change requires this for API compatibility. */ + if (cb.capture_last == 0) cb.capture_last = -1; + cb.callout_data = md->callout_data; + cb.mark = md->nomatch_mark; + if ((rrc = (*PUBL(callout))(&cb)) > 0) RRETURN(MATCH_NOMATCH); + if (rrc < 0) RRETURN(rrc); + } + ecode += 2 + 2*LINK_SIZE; + break; + + /* Recursion either matches the current regex, or some subexpression. The + offset data is the offset to the starting bracket from the start of the + whole pattern. (This is so that it works from duplicated subpatterns.) + + The state of the capturing groups is preserved over recursion, and + re-instated afterwards. We don't know how many are started and not yet + finished (offset_top records the completed total) so we just have to save + all the potential data. There may be up to 65535 such values, which is too + large to put on the stack, but using malloc for small numbers seems + expensive. As a compromise, the stack is used when there are no more than + REC_STACK_SAVE_MAX values to store; otherwise malloc is used. + + There are also other values that have to be saved. We use a chained + sequence of blocks that actually live on the stack. Thanks to Robin Houston + for the original version of this logic. It has, however, been hacked around + a lot, so he is not to blame for the current way it works. */ + + case OP_RECURSE: + { + recursion_info *ri; + unsigned int recno; + + callpat = md->start_code + GET(ecode, 1); + recno = (callpat == md->start_code)? 0 : + GET2(callpat, 1 + LINK_SIZE); + + /* Check for repeating a recursion without advancing the subject pointer. + This should catch convoluted mutual recursions. (Some simple cases are + caught at compile time.) */ + + for (ri = md->recursive; ri != NULL; ri = ri->prevrec) + if (recno == ri->group_num && eptr == ri->subject_position) + RRETURN(PCRE_ERROR_RECURSELOOP); + + /* Add to "recursing stack" */ + + new_recursive.group_num = recno; + new_recursive.saved_capture_last = md->capture_last; + new_recursive.subject_position = eptr; + new_recursive.prevrec = md->recursive; + md->recursive = &new_recursive; + + /* Where to continue from afterwards */ + + ecode += 1 + LINK_SIZE; + + /* Now save the offset data */ + + new_recursive.saved_max = md->offset_end; + if (new_recursive.saved_max <= REC_STACK_SAVE_MAX) + new_recursive.offset_save = stacksave; + else + { + new_recursive.offset_save = + (int *)(PUBL(malloc))(new_recursive.saved_max * sizeof(int)); + if (new_recursive.offset_save == NULL) RRETURN(PCRE_ERROR_NOMEMORY); + } + memcpy(new_recursive.offset_save, md->offset_vector, + new_recursive.saved_max * sizeof(int)); + + /* OK, now we can do the recursion. After processing each alternative, + restore the offset data and the last captured value. If there were nested + recursions, md->recursive might be changed, so reset it before looping. + */ + + DPRINTF(("Recursing into group %d\n", new_recursive.group_num)); + cbegroup = (*callpat >= OP_SBRA); + do + { + if (cbegroup) md->match_function_type = MATCH_CBEGROUP; + RMATCH(eptr, callpat + PRIV(OP_lengths)[*callpat], offset_top, + md, eptrb, RM6); + memcpy(md->offset_vector, new_recursive.offset_save, + new_recursive.saved_max * sizeof(int)); + md->capture_last = new_recursive.saved_capture_last; + md->recursive = new_recursive.prevrec; + if (rrc == MATCH_MATCH || rrc == MATCH_ACCEPT) + { + DPRINTF(("Recursion matched\n")); + if (new_recursive.offset_save != stacksave) + (PUBL(free))(new_recursive.offset_save); + + /* Set where we got to in the subject, and reset the start in case + it was changed by \K. This *is* propagated back out of a recursion, + for Perl compatibility. */ + + eptr = md->end_match_ptr; + mstart = md->start_match_ptr; + goto RECURSION_MATCHED; /* Exit loop; end processing */ + } + + /* PCRE does not allow THEN, SKIP, PRUNE or COMMIT to escape beyond a + recursion; they cause a NOMATCH for the entire recursion. These codes + are defined in a range that can be tested for. */ + + if (rrc >= MATCH_BACKTRACK_MIN && rrc <= MATCH_BACKTRACK_MAX) + RRETURN(MATCH_NOMATCH); + + /* Any return code other than NOMATCH is an error. */ + + if (rrc != MATCH_NOMATCH) + { + DPRINTF(("Recursion gave error %d\n", rrc)); + if (new_recursive.offset_save != stacksave) + (PUBL(free))(new_recursive.offset_save); + RRETURN(rrc); + } + + md->recursive = &new_recursive; + callpat += GET(callpat, 1); + } + while (*callpat == OP_ALT); + + DPRINTF(("Recursion didn't match\n")); + md->recursive = new_recursive.prevrec; + if (new_recursive.offset_save != stacksave) + (PUBL(free))(new_recursive.offset_save); + RRETURN(MATCH_NOMATCH); + } + + RECURSION_MATCHED: + break; + + /* An alternation is the end of a branch; scan along to find the end of the + bracketed group and go to there. */ + + case OP_ALT: + do ecode += GET(ecode,1); while (*ecode == OP_ALT); + break; + + /* BRAZERO, BRAMINZERO and SKIPZERO occur just before a bracket group, + indicating that it may occur zero times. It may repeat infinitely, or not + at all - i.e. it could be ()* or ()? or even (){0} in the pattern. Brackets + with fixed upper repeat limits are compiled as a number of copies, with the + optional ones preceded by BRAZERO or BRAMINZERO. */ + + case OP_BRAZERO: + next = ecode + 1; + RMATCH(eptr, next, offset_top, md, eptrb, RM10); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + do next += GET(next, 1); while (*next == OP_ALT); + ecode = next + 1 + LINK_SIZE; + break; + + case OP_BRAMINZERO: + next = ecode + 1; + do next += GET(next, 1); while (*next == OP_ALT); + RMATCH(eptr, next + 1+LINK_SIZE, offset_top, md, eptrb, RM11); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + ecode++; + break; + + case OP_SKIPZERO: + next = ecode+1; + do next += GET(next,1); while (*next == OP_ALT); + ecode = next + 1 + LINK_SIZE; + break; + + /* BRAPOSZERO occurs before a possessive bracket group. Don't do anything + here; just jump to the group, with allow_zero set TRUE. */ + + case OP_BRAPOSZERO: + op = *(++ecode); + allow_zero = TRUE; + if (op == OP_CBRAPOS || op == OP_SCBRAPOS) goto POSSESSIVE_CAPTURE; + goto POSSESSIVE_NON_CAPTURE; + + /* End of a group, repeated or non-repeating. */ + + case OP_KET: + case OP_KETRMIN: + case OP_KETRMAX: + case OP_KETRPOS: + prev = ecode - GET(ecode, 1); + + /* If this was a group that remembered the subject start, in order to break + infinite repeats of empty string matches, retrieve the subject start from + the chain. Otherwise, set it NULL. */ + + if (*prev >= OP_SBRA || *prev == OP_ONCE) + { + saved_eptr = eptrb->epb_saved_eptr; /* Value at start of group */ + eptrb = eptrb->epb_prev; /* Backup to previous group */ + } + else saved_eptr = NULL; + + /* If we are at the end of an assertion group or a non-capturing atomic + group, stop matching and return MATCH_MATCH, but record the current high + water mark for use by positive assertions. We also need to record the match + start in case it was changed by \K. */ + + if ((*prev >= OP_ASSERT && *prev <= OP_ASSERTBACK_NOT) || + *prev == OP_ONCE_NC) + { + md->end_match_ptr = eptr; /* For ONCE_NC */ + md->end_offset_top = offset_top; + md->start_match_ptr = mstart; + RRETURN(MATCH_MATCH); /* Sets md->mark */ + } + + /* For capturing groups we have to check the group number back at the start + and if necessary complete handling an extraction by setting the offsets and + bumping the high water mark. Whole-pattern recursion is coded as a recurse + into group 0, so it won't be picked up here. Instead, we catch it when the + OP_END is reached. Other recursion is handled here. We just have to record + the current subject position and start match pointer and give a MATCH + return. */ + + if (*prev == OP_CBRA || *prev == OP_SCBRA || + *prev == OP_CBRAPOS || *prev == OP_SCBRAPOS) + { + number = GET2(prev, 1+LINK_SIZE); + offset = number << 1; + +#ifdef PCRE_DEBUG + printf("end bracket %d", number); + printf("\n"); +#endif + + /* Handle a recursively called group. */ + + if (md->recursive != NULL && md->recursive->group_num == number) + { + md->end_match_ptr = eptr; + md->start_match_ptr = mstart; + RRETURN(MATCH_MATCH); + } + + /* Deal with capturing */ + + md->capture_last = (md->capture_last & OVFLMASK) | number; + if (offset >= md->offset_max) md->capture_last |= OVFLBIT; else + { + /* If offset is greater than offset_top, it means that we are + "skipping" a capturing group, and that group's offsets must be marked + unset. In earlier versions of PCRE, all the offsets were unset at the + start of matching, but this doesn't work because atomic groups and + assertions can cause a value to be set that should later be unset. + Example: matching /(?>(a))b|(a)c/ against "ac". This sets group 1 as + part of the atomic group, but this is not on the final matching path, + so must be unset when 2 is set. (If there is no group 2, there is no + problem, because offset_top will then be 2, indicating no capture.) */ + + if (offset > offset_top) + { + register int *iptr = md->offset_vector + offset_top; + register int *iend = md->offset_vector + offset; + while (iptr < iend) *iptr++ = -1; + } + + /* Now make the extraction */ + + md->offset_vector[offset] = + md->offset_vector[md->offset_end - number]; + md->offset_vector[offset+1] = (int)(eptr - md->start_subject); + if (offset_top <= offset) offset_top = offset + 2; + } + } + + /* For an ordinary non-repeating ket, just continue at this level. This + also happens for a repeating ket if no characters were matched in the + group. This is the forcible breaking of infinite loops as implemented in + Perl 5.005. For a non-repeating atomic group that includes captures, + establish a backup point by processing the rest of the pattern at a lower + level. If this results in a NOMATCH return, pass MATCH_ONCE back to the + original OP_ONCE level, thereby bypassing intermediate backup points, but + resetting any captures that happened along the way. */ + + if (*ecode == OP_KET || eptr == saved_eptr) + { + if (*prev == OP_ONCE) + { + RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, eptrb, RM12); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + md->once_target = prev; /* Level at which to change to MATCH_NOMATCH */ + RRETURN(MATCH_ONCE); + } + ecode += 1 + LINK_SIZE; /* Carry on at this level */ + break; + } + + /* OP_KETRPOS is a possessive repeating ket. Remember the current position, + and return the MATCH_KETRPOS. This makes it possible to do the repeats one + at a time from the outer level, thus saving stack. */ + + if (*ecode == OP_KETRPOS) + { + md->start_match_ptr = mstart; /* In case \K reset it */ + md->end_match_ptr = eptr; + md->end_offset_top = offset_top; + RRETURN(MATCH_KETRPOS); + } + + /* The normal repeating kets try the rest of the pattern or restart from + the preceding bracket, in the appropriate order. In the second case, we can + use tail recursion to avoid using another stack frame, unless we have an + an atomic group or an unlimited repeat of a group that can match an empty + string. */ + + if (*ecode == OP_KETRMIN) + { + RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, eptrb, RM7); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (*prev == OP_ONCE) + { + RMATCH(eptr, prev, offset_top, md, eptrb, RM8); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + md->once_target = prev; /* Level at which to change to MATCH_NOMATCH */ + RRETURN(MATCH_ONCE); + } + if (*prev >= OP_SBRA) /* Could match an empty string */ + { + RMATCH(eptr, prev, offset_top, md, eptrb, RM50); + RRETURN(rrc); + } + ecode = prev; + goto TAIL_RECURSE; + } + else /* OP_KETRMAX */ + { + RMATCH(eptr, prev, offset_top, md, eptrb, RM13); + if (rrc == MATCH_ONCE && md->once_target == prev) rrc = MATCH_NOMATCH; + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (*prev == OP_ONCE) + { + RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, eptrb, RM9); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + md->once_target = prev; + RRETURN(MATCH_ONCE); + } + ecode += 1 + LINK_SIZE; + goto TAIL_RECURSE; + } + /* Control never gets here */ + + /* Not multiline mode: start of subject assertion, unless notbol. */ + + case OP_CIRC: + if (md->notbol && eptr == md->start_subject) RRETURN(MATCH_NOMATCH); + + /* Start of subject assertion */ + + case OP_SOD: + if (eptr != md->start_subject) RRETURN(MATCH_NOMATCH); + ecode++; + break; + + /* Multiline mode: start of subject unless notbol, or after any newline. */ + + case OP_CIRCM: + if (md->notbol && eptr == md->start_subject) RRETURN(MATCH_NOMATCH); + if (eptr != md->start_subject && + (eptr == md->end_subject || !WAS_NEWLINE(eptr))) + RRETURN(MATCH_NOMATCH); + ecode++; + break; + + /* Start of match assertion */ + + case OP_SOM: + if (eptr != md->start_subject + md->start_offset) RRETURN(MATCH_NOMATCH); + ecode++; + break; + + /* Reset the start of match point */ + + case OP_SET_SOM: + mstart = eptr; + ecode++; + break; + + /* Multiline mode: assert before any newline, or before end of subject + unless noteol is set. */ + + case OP_DOLLM: + if (eptr < md->end_subject) + { + if (!IS_NEWLINE(eptr)) + { + if (md->partial != 0 && + eptr + 1 >= md->end_subject && + NLBLOCK->nltype == NLTYPE_FIXED && + NLBLOCK->nllen == 2 && + UCHAR21TEST(eptr) == NLBLOCK->nl[0]) + { + md->hitend = TRUE; + if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); + } + RRETURN(MATCH_NOMATCH); + } + } + else + { + if (md->noteol) RRETURN(MATCH_NOMATCH); + SCHECK_PARTIAL(); + } + ecode++; + break; + + /* Not multiline mode: assert before a terminating newline or before end of + subject unless noteol is set. */ + + case OP_DOLL: + if (md->noteol) RRETURN(MATCH_NOMATCH); + if (!md->endonly) goto ASSERT_NL_OR_EOS; + + /* ... else fall through for endonly */ + + /* End of subject assertion (\z) */ + + case OP_EOD: + if (eptr < md->end_subject) RRETURN(MATCH_NOMATCH); + SCHECK_PARTIAL(); + ecode++; + break; + + /* End of subject or ending \n assertion (\Z) */ + + case OP_EODN: + ASSERT_NL_OR_EOS: + if (eptr < md->end_subject && + (!IS_NEWLINE(eptr) || eptr != md->end_subject - md->nllen)) + { + if (md->partial != 0 && + eptr + 1 >= md->end_subject && + NLBLOCK->nltype == NLTYPE_FIXED && + NLBLOCK->nllen == 2 && + UCHAR21TEST(eptr) == NLBLOCK->nl[0]) + { + md->hitend = TRUE; + if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); + } + RRETURN(MATCH_NOMATCH); + } + + /* Either at end of string or \n before end. */ + + SCHECK_PARTIAL(); + ecode++; + break; + + /* Word boundary assertions */ + + case OP_NOT_WORD_BOUNDARY: + case OP_WORD_BOUNDARY: + { + + /* Find out if the previous and current characters are "word" characters. + It takes a bit more work in UTF-8 mode. Characters > 255 are assumed to + be "non-word" characters. Remember the earliest consulted character for + partial matching. */ + +#ifdef SUPPORT_UTF + if (utf) + { + /* Get status of previous character */ + + if (eptr == md->start_subject) prev_is_word = FALSE; else + { + PCRE_PUCHAR lastptr = eptr - 1; + BACKCHAR(lastptr); + if (lastptr < md->start_used_ptr) md->start_used_ptr = lastptr; + GETCHAR(c, lastptr); +#ifdef SUPPORT_UCP + if (md->use_ucp) + { + if (c == '_') prev_is_word = TRUE; else + { + int cat = UCD_CATEGORY(c); + prev_is_word = (cat == ucp_L || cat == ucp_N); + } + } + else +#endif + prev_is_word = c < 256 && (md->ctypes[c] & ctype_word) != 0; + } + + /* Get status of next character */ + + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + cur_is_word = FALSE; + } + else + { + GETCHAR(c, eptr); +#ifdef SUPPORT_UCP + if (md->use_ucp) + { + if (c == '_') cur_is_word = TRUE; else + { + int cat = UCD_CATEGORY(c); + cur_is_word = (cat == ucp_L || cat == ucp_N); + } + } + else +#endif + cur_is_word = c < 256 && (md->ctypes[c] & ctype_word) != 0; + } + } + else +#endif + + /* Not in UTF-8 mode, but we may still have PCRE_UCP set, and for + consistency with the behaviour of \w we do use it in this case. */ + + { + /* Get status of previous character */ + + if (eptr == md->start_subject) prev_is_word = FALSE; else + { + if (eptr <= md->start_used_ptr) md->start_used_ptr = eptr - 1; +#ifdef SUPPORT_UCP + if (md->use_ucp) + { + c = eptr[-1]; + if (c == '_') prev_is_word = TRUE; else + { + int cat = UCD_CATEGORY(c); + prev_is_word = (cat == ucp_L || cat == ucp_N); + } + } + else +#endif + prev_is_word = MAX_255(eptr[-1]) + && ((md->ctypes[eptr[-1]] & ctype_word) != 0); + } + + /* Get status of next character */ + + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + cur_is_word = FALSE; + } + else +#ifdef SUPPORT_UCP + if (md->use_ucp) + { + c = *eptr; + if (c == '_') cur_is_word = TRUE; else + { + int cat = UCD_CATEGORY(c); + cur_is_word = (cat == ucp_L || cat == ucp_N); + } + } + else +#endif + cur_is_word = MAX_255(*eptr) + && ((md->ctypes[*eptr] & ctype_word) != 0); + } + + /* Now see if the situation is what we want */ + + if ((*ecode++ == OP_WORD_BOUNDARY)? + cur_is_word == prev_is_word : cur_is_word != prev_is_word) + RRETURN(MATCH_NOMATCH); + } + break; + + /* Match any single character type except newline; have to take care with + CRLF newlines and partial matching. */ + + case OP_ANY: + if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH); + if (md->partial != 0 && + eptr + 1 >= md->end_subject && + NLBLOCK->nltype == NLTYPE_FIXED && + NLBLOCK->nllen == 2 && + UCHAR21TEST(eptr) == NLBLOCK->nl[0]) + { + md->hitend = TRUE; + if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); + } + + /* Fall through */ + + /* Match any single character whatsoever. */ + + case OP_ALLANY: + if (eptr >= md->end_subject) /* DO NOT merge the eptr++ here; it must */ + { /* not be updated before SCHECK_PARTIAL. */ + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + eptr++; +#ifdef SUPPORT_UTF + if (utf) ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++); +#endif + ecode++; + break; + + /* Match a single byte, even in UTF-8 mode. This opcode really does match + any byte, even newline, independent of the setting of PCRE_DOTALL. */ + + case OP_ANYBYTE: + if (eptr >= md->end_subject) /* DO NOT merge the eptr++ here; it must */ + { /* not be updated before SCHECK_PARTIAL. */ + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + eptr++; + ecode++; + break; + + case OP_NOT_DIGIT: + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + if ( +#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8) + c < 256 && +#endif + (md->ctypes[c] & ctype_digit) != 0 + ) + RRETURN(MATCH_NOMATCH); + ecode++; + break; + + case OP_DIGIT: + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + if ( +#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8) + c > 255 || +#endif + (md->ctypes[c] & ctype_digit) == 0 + ) + RRETURN(MATCH_NOMATCH); + ecode++; + break; + + case OP_NOT_WHITESPACE: + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + if ( +#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8) + c < 256 && +#endif + (md->ctypes[c] & ctype_space) != 0 + ) + RRETURN(MATCH_NOMATCH); + ecode++; + break; + + case OP_WHITESPACE: + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + if ( +#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8) + c > 255 || +#endif + (md->ctypes[c] & ctype_space) == 0 + ) + RRETURN(MATCH_NOMATCH); + ecode++; + break; + + case OP_NOT_WORDCHAR: + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + if ( +#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8) + c < 256 && +#endif + (md->ctypes[c] & ctype_word) != 0 + ) + RRETURN(MATCH_NOMATCH); + ecode++; + break; + + case OP_WORDCHAR: + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + if ( +#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8) + c > 255 || +#endif + (md->ctypes[c] & ctype_word) == 0 + ) + RRETURN(MATCH_NOMATCH); + ecode++; + break; + + case OP_ANYNL: + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + + case CHAR_CR: + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + } + else if (UCHAR21TEST(eptr) == CHAR_LF) eptr++; + break; + + case CHAR_LF: + break; + + case CHAR_VT: + case CHAR_FF: + case CHAR_NEL: +#ifndef EBCDIC + case 0x2028: + case 0x2029: +#endif /* Not EBCDIC */ + if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); + break; + } + ecode++; + break; + + case OP_NOT_HSPACE: + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + switch(c) + { + HSPACE_CASES: RRETURN(MATCH_NOMATCH); /* Byte and multibyte cases */ + default: break; + } + ecode++; + break; + + case OP_HSPACE: + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + switch(c) + { + HSPACE_CASES: break; /* Byte and multibyte cases */ + default: RRETURN(MATCH_NOMATCH); + } + ecode++; + break; + + case OP_NOT_VSPACE: + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + switch(c) + { + VSPACE_CASES: RRETURN(MATCH_NOMATCH); + default: break; + } + ecode++; + break; + + case OP_VSPACE: + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + switch(c) + { + VSPACE_CASES: break; + default: RRETURN(MATCH_NOMATCH); + } + ecode++; + break; + +#ifdef SUPPORT_UCP + /* Check the next character by Unicode property. We will get here only + if the support is in the binary; otherwise a compile-time error occurs. */ + + case OP_PROP: + case OP_NOTPROP: + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + { + const pcre_uint32 *cp; + const ucd_record *prop = GET_UCD(c); + + switch(ecode[1]) + { + case PT_ANY: + if (op == OP_NOTPROP) RRETURN(MATCH_NOMATCH); + break; + + case PT_LAMP: + if ((prop->chartype == ucp_Lu || + prop->chartype == ucp_Ll || + prop->chartype == ucp_Lt) == (op == OP_NOTPROP)) + RRETURN(MATCH_NOMATCH); + break; + + case PT_GC: + if ((ecode[2] != PRIV(ucp_gentype)[prop->chartype]) == (op == OP_PROP)) + RRETURN(MATCH_NOMATCH); + break; + + case PT_PC: + if ((ecode[2] != prop->chartype) == (op == OP_PROP)) + RRETURN(MATCH_NOMATCH); + break; + + case PT_SC: + if ((ecode[2] != prop->script) == (op == OP_PROP)) + RRETURN(MATCH_NOMATCH); + break; + + /* These are specials */ + + case PT_ALNUM: + if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L || + PRIV(ucp_gentype)[prop->chartype] == ucp_N) == (op == OP_NOTPROP)) + RRETURN(MATCH_NOMATCH); + break; + + /* Perl space used to exclude VT, but from Perl 5.18 it is included, + which means that Perl space and POSIX space are now identical. PCRE + was changed at release 8.34. */ + + case PT_SPACE: /* Perl space */ + case PT_PXSPACE: /* POSIX space */ + switch(c) + { + HSPACE_CASES: + VSPACE_CASES: + if (op == OP_NOTPROP) RRETURN(MATCH_NOMATCH); + break; + + default: + if ((PRIV(ucp_gentype)[prop->chartype] == ucp_Z) == + (op == OP_NOTPROP)) RRETURN(MATCH_NOMATCH); + break; + } + break; + + case PT_WORD: + if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L || + PRIV(ucp_gentype)[prop->chartype] == ucp_N || + c == CHAR_UNDERSCORE) == (op == OP_NOTPROP)) + RRETURN(MATCH_NOMATCH); + break; + + case PT_CLIST: + cp = PRIV(ucd_caseless_sets) + ecode[2]; + for (;;) + { + if (c < *cp) + { if (op == OP_PROP) { RRETURN(MATCH_NOMATCH); } else break; } + if (c == *cp++) + { if (op == OP_PROP) break; else { RRETURN(MATCH_NOMATCH); } } + } + break; + + case PT_UCNC: + if ((c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT || + c == CHAR_GRAVE_ACCENT || (c >= 0xa0 && c <= 0xd7ff) || + c >= 0xe000) == (op == OP_NOTPROP)) + RRETURN(MATCH_NOMATCH); + break; + + /* This should never occur */ + + default: + RRETURN(PCRE_ERROR_INTERNAL); + } + + ecode += 3; + } + break; + + /* Match an extended Unicode sequence. We will get here only if the support + is in the binary; otherwise a compile-time error occurs. */ + + case OP_EXTUNI: + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + else + { + int lgb, rgb; + GETCHARINCTEST(c, eptr); + lgb = UCD_GRAPHBREAK(c); + while (eptr < md->end_subject) + { + int len = 1; + if (!utf) c = *eptr; else { GETCHARLEN(c, eptr, len); } + rgb = UCD_GRAPHBREAK(c); + if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break; + lgb = rgb; + eptr += len; + } + } + CHECK_PARTIAL(); + ecode++; + break; +#endif /* SUPPORT_UCP */ + + + /* Match a back reference, possibly repeatedly. Look past the end of the + item to see if there is repeat information following. The code is similar + to that for character classes, but repeated for efficiency. Then obey + similar code to character type repeats - written out again for speed. + However, if the referenced string is the empty string, always treat + it as matched, any number of times (otherwise there could be infinite + loops). If the reference is unset, there are two possibilities: + + (a) In the default, Perl-compatible state, set the length negative; + this ensures that every attempt at a match fails. We can't just fail + here, because of the possibility of quantifiers with zero minima. + + (b) If the JavaScript compatibility flag is set, set the length to zero + so that the back reference matches an empty string. + + Otherwise, set the length to the length of what was matched by the + referenced subpattern. + + The OP_REF and OP_REFI opcodes are used for a reference to a numbered group + or to a non-duplicated named group. For a duplicated named group, OP_DNREF + and OP_DNREFI are used. In this case we must scan the list of groups to + which the name refers, and use the first one that is set. */ + + case OP_DNREF: + case OP_DNREFI: + caseless = op == OP_DNREFI; + { + int count = GET2(ecode, 1+IMM2_SIZE); + pcre_uchar *slot = md->name_table + GET2(ecode, 1) * md->name_entry_size; + ecode += 1 + 2*IMM2_SIZE; + + /* Setting the default length first and initializing 'offset' avoids + compiler warnings in the REF_REPEAT code. */ + + length = (md->jscript_compat)? 0 : -1; + offset = 0; + + while (count-- > 0) + { + offset = GET2(slot, 0) << 1; + if (offset < offset_top && md->offset_vector[offset] >= 0) + { + length = md->offset_vector[offset+1] - md->offset_vector[offset]; + break; + } + slot += md->name_entry_size; + } + } + goto REF_REPEAT; + + case OP_REF: + case OP_REFI: + caseless = op == OP_REFI; + offset = GET2(ecode, 1) << 1; /* Doubled ref number */ + ecode += 1 + IMM2_SIZE; + if (offset >= offset_top || md->offset_vector[offset] < 0) + length = (md->jscript_compat)? 0 : -1; + else + length = md->offset_vector[offset+1] - md->offset_vector[offset]; + + /* Set up for repetition, or handle the non-repeated case */ + + REF_REPEAT: + switch (*ecode) + { + case OP_CRSTAR: + case OP_CRMINSTAR: + case OP_CRPLUS: + case OP_CRMINPLUS: + case OP_CRQUERY: + case OP_CRMINQUERY: + c = *ecode++ - OP_CRSTAR; + minimize = (c & 1) != 0; + min = rep_min[c]; /* Pick up values from tables; */ + max = rep_max[c]; /* zero for max => infinity */ + if (max == 0) max = INT_MAX; + break; + + case OP_CRRANGE: + case OP_CRMINRANGE: + minimize = (*ecode == OP_CRMINRANGE); + min = GET2(ecode, 1); + max = GET2(ecode, 1 + IMM2_SIZE); + if (max == 0) max = INT_MAX; + ecode += 1 + 2 * IMM2_SIZE; + break; + + default: /* No repeat follows */ + if ((length = match_ref(offset, eptr, length, md, caseless)) < 0) + { + if (length == -2) eptr = md->end_subject; /* Partial match */ + CHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + eptr += length; + continue; /* With the main loop */ + } + + /* Handle repeated back references. If the length of the reference is + zero, just continue with the main loop. If the length is negative, it + means the reference is unset in non-Java-compatible mode. If the minimum is + zero, we can continue at the same level without recursion. For any other + minimum, carrying on will result in NOMATCH. */ + + if (length == 0) continue; + if (length < 0 && min == 0) continue; + + /* First, ensure the minimum number of matches are present. We get back + the length of the reference string explicitly rather than passing the + address of eptr, so that eptr can be a register variable. */ + + for (i = 1; i <= min; i++) + { + int slength; + if ((slength = match_ref(offset, eptr, length, md, caseless)) < 0) + { + if (slength == -2) eptr = md->end_subject; /* Partial match */ + CHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + eptr += slength; + } + + /* If min = max, continue at the same level without recursion. + They are not both allowed to be zero. */ + + if (min == max) continue; + + /* If minimizing, keep trying and advancing the pointer */ + + if (minimize) + { + for (fi = min;; fi++) + { + int slength; + RMATCH(eptr, ecode, offset_top, md, eptrb, RM14); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max) RRETURN(MATCH_NOMATCH); + if ((slength = match_ref(offset, eptr, length, md, caseless)) < 0) + { + if (slength == -2) eptr = md->end_subject; /* Partial match */ + CHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + eptr += slength; + } + /* Control never gets here */ + } + + /* If maximizing, find the longest string and work backwards */ + + else + { + pp = eptr; + for (i = min; i < max; i++) + { + int slength; + if ((slength = match_ref(offset, eptr, length, md, caseless)) < 0) + { + /* Can't use CHECK_PARTIAL because we don't want to update eptr in + the soft partial matching case. */ + + if (slength == -2 && md->partial != 0 && + md->end_subject > md->start_used_ptr) + { + md->hitend = TRUE; + if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); + } + break; + } + eptr += slength; + } + + while (eptr >= pp) + { + RMATCH(eptr, ecode, offset_top, md, eptrb, RM15); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + eptr -= length; + } + RRETURN(MATCH_NOMATCH); + } + /* Control never gets here */ + + /* Match a bit-mapped character class, possibly repeatedly. This op code is + used when all the characters in the class have values in the range 0-255, + and either the matching is caseful, or the characters are in the range + 0-127 when UTF-8 processing is enabled. The only difference between + OP_CLASS and OP_NCLASS occurs when a data character outside the range is + encountered. + + First, look past the end of the item to see if there is repeat information + following. Then obey similar code to character type repeats - written out + again for speed. */ + + case OP_NCLASS: + case OP_CLASS: + { + /* The data variable is saved across frames, so the byte map needs to + be stored there. */ +#define BYTE_MAP ((pcre_uint8 *)data) + data = ecode + 1; /* Save for matching */ + ecode += 1 + (32 / sizeof(pcre_uchar)); /* Advance past the item */ + + switch (*ecode) + { + case OP_CRSTAR: + case OP_CRMINSTAR: + case OP_CRPLUS: + case OP_CRMINPLUS: + case OP_CRQUERY: + case OP_CRMINQUERY: + case OP_CRPOSSTAR: + case OP_CRPOSPLUS: + case OP_CRPOSQUERY: + c = *ecode++ - OP_CRSTAR; + if (c < OP_CRPOSSTAR - OP_CRSTAR) minimize = (c & 1) != 0; + else possessive = TRUE; + min = rep_min[c]; /* Pick up values from tables; */ + max = rep_max[c]; /* zero for max => infinity */ + if (max == 0) max = INT_MAX; + break; + + case OP_CRRANGE: + case OP_CRMINRANGE: + case OP_CRPOSRANGE: + minimize = (*ecode == OP_CRMINRANGE); + possessive = (*ecode == OP_CRPOSRANGE); + min = GET2(ecode, 1); + max = GET2(ecode, 1 + IMM2_SIZE); + if (max == 0) max = INT_MAX; + ecode += 1 + 2 * IMM2_SIZE; + break; + + default: /* No repeat follows */ + min = max = 1; + break; + } + + /* First, ensure the minimum number of matches are present. */ + +#ifdef SUPPORT_UTF + if (utf) + { + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINC(c, eptr); + if (c > 255) + { + if (op == OP_CLASS) RRETURN(MATCH_NOMATCH); + } + else + if ((BYTE_MAP[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH); + } + } + else +#endif + /* Not UTF mode */ + { + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + c = *eptr++; +#ifndef COMPILE_PCRE8 + if (c > 255) + { + if (op == OP_CLASS) RRETURN(MATCH_NOMATCH); + } + else +#endif + if ((BYTE_MAP[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH); + } + } + + /* If max == min we can continue with the main loop without the + need to recurse. */ + + if (min == max) continue; + + /* If minimizing, keep testing the rest of the expression and advancing + the pointer while it matches the class. */ + + if (minimize) + { +#ifdef SUPPORT_UTF + if (utf) + { + for (fi = min;; fi++) + { + RMATCH(eptr, ecode, offset_top, md, eptrb, RM16); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max) RRETURN(MATCH_NOMATCH); + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINC(c, eptr); + if (c > 255) + { + if (op == OP_CLASS) RRETURN(MATCH_NOMATCH); + } + else + if ((BYTE_MAP[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH); + } + } + else +#endif + /* Not UTF mode */ + { + for (fi = min;; fi++) + { + RMATCH(eptr, ecode, offset_top, md, eptrb, RM17); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max) RRETURN(MATCH_NOMATCH); + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + c = *eptr++; +#ifndef COMPILE_PCRE8 + if (c > 255) + { + if (op == OP_CLASS) RRETURN(MATCH_NOMATCH); + } + else +#endif + if ((BYTE_MAP[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH); + } + } + /* Control never gets here */ + } + + /* If maximizing, find the longest possible run, then work backwards. */ + + else + { + pp = eptr; + +#ifdef SUPPORT_UTF + if (utf) + { + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + GETCHARLEN(c, eptr, len); + if (c > 255) + { + if (op == OP_CLASS) break; + } + else + if ((BYTE_MAP[c/8] & (1 << (c&7))) == 0) break; + eptr += len; + } + + if (possessive) continue; /* No backtracking */ + + for (;;) + { + RMATCH(eptr, ecode, offset_top, md, eptrb, RM18); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (eptr-- == pp) break; /* Stop if tried at original pos */ + BACKCHAR(eptr); + } + } + else +#endif + /* Not UTF mode */ + { + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + c = *eptr; +#ifndef COMPILE_PCRE8 + if (c > 255) + { + if (op == OP_CLASS) break; + } + else +#endif + if ((BYTE_MAP[c/8] & (1 << (c&7))) == 0) break; + eptr++; + } + + if (possessive) continue; /* No backtracking */ + + while (eptr >= pp) + { + RMATCH(eptr, ecode, offset_top, md, eptrb, RM19); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + eptr--; + } + } + + RRETURN(MATCH_NOMATCH); + } +#undef BYTE_MAP + } + /* Control never gets here */ + + + /* Match an extended character class. In the 8-bit library, this opcode is + encountered only when UTF-8 mode mode is supported. In the 16-bit and + 32-bit libraries, codepoints greater than 255 may be encountered even when + UTF is not supported. */ + +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + case OP_XCLASS: + { + data = ecode + 1 + LINK_SIZE; /* Save for matching */ + ecode += GET(ecode, 1); /* Advance past the item */ + + switch (*ecode) + { + case OP_CRSTAR: + case OP_CRMINSTAR: + case OP_CRPLUS: + case OP_CRMINPLUS: + case OP_CRQUERY: + case OP_CRMINQUERY: + case OP_CRPOSSTAR: + case OP_CRPOSPLUS: + case OP_CRPOSQUERY: + c = *ecode++ - OP_CRSTAR; + if (c < OP_CRPOSSTAR - OP_CRSTAR) minimize = (c & 1) != 0; + else possessive = TRUE; + min = rep_min[c]; /* Pick up values from tables; */ + max = rep_max[c]; /* zero for max => infinity */ + if (max == 0) max = INT_MAX; + break; + + case OP_CRRANGE: + case OP_CRMINRANGE: + case OP_CRPOSRANGE: + minimize = (*ecode == OP_CRMINRANGE); + possessive = (*ecode == OP_CRPOSRANGE); + min = GET2(ecode, 1); + max = GET2(ecode, 1 + IMM2_SIZE); + if (max == 0) max = INT_MAX; + ecode += 1 + 2 * IMM2_SIZE; + break; + + default: /* No repeat follows */ + min = max = 1; + break; + } + + /* First, ensure the minimum number of matches are present. */ + + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + if (!PRIV(xclass)(c, data, utf)) RRETURN(MATCH_NOMATCH); + } + + /* If max == min we can continue with the main loop without the + need to recurse. */ + + if (min == max) continue; + + /* If minimizing, keep testing the rest of the expression and advancing + the pointer while it matches the class. */ + + if (minimize) + { + for (fi = min;; fi++) + { + RMATCH(eptr, ecode, offset_top, md, eptrb, RM20); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max) RRETURN(MATCH_NOMATCH); + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + if (!PRIV(xclass)(c, data, utf)) RRETURN(MATCH_NOMATCH); + } + /* Control never gets here */ + } + + /* If maximizing, find the longest possible run, then work backwards. */ + + else + { + pp = eptr; + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } +#ifdef SUPPORT_UTF + GETCHARLENTEST(c, eptr, len); +#else + c = *eptr; +#endif + if (!PRIV(xclass)(c, data, utf)) break; + eptr += len; + } + + if (possessive) continue; /* No backtracking */ + + for(;;) + { + RMATCH(eptr, ecode, offset_top, md, eptrb, RM21); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (eptr-- == pp) break; /* Stop if tried at original pos */ +#ifdef SUPPORT_UTF + if (utf) BACKCHAR(eptr); +#endif + } + RRETURN(MATCH_NOMATCH); + } + + /* Control never gets here */ + } +#endif /* End of XCLASS */ + + /* Match a single character, casefully */ + + case OP_CHAR: +#ifdef SUPPORT_UTF + if (utf) + { + length = 1; + ecode++; + GETCHARLEN(fc, ecode, length); + if (length > md->end_subject - eptr) + { + CHECK_PARTIAL(); /* Not SCHECK_PARTIAL() */ + RRETURN(MATCH_NOMATCH); + } + while (length-- > 0) if (*ecode++ != UCHAR21INC(eptr)) RRETURN(MATCH_NOMATCH); + } + else +#endif + /* Not UTF mode */ + { + if (md->end_subject - eptr < 1) + { + SCHECK_PARTIAL(); /* This one can use SCHECK_PARTIAL() */ + RRETURN(MATCH_NOMATCH); + } + if (ecode[1] != *eptr++) RRETURN(MATCH_NOMATCH); + ecode += 2; + } + break; + + /* Match a single character, caselessly. If we are at the end of the + subject, give up immediately. */ + + case OP_CHARI: + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + +#ifdef SUPPORT_UTF + if (utf) + { + length = 1; + ecode++; + GETCHARLEN(fc, ecode, length); + + /* If the pattern character's value is < 128, we have only one byte, and + we know that its other case must also be one byte long, so we can use the + fast lookup table. We know that there is at least one byte left in the + subject. */ + + if (fc < 128) + { + pcre_uint32 cc = UCHAR21(eptr); + if (md->lcc[fc] != TABLE_GET(cc, md->lcc, cc)) RRETURN(MATCH_NOMATCH); + ecode++; + eptr++; + } + + /* Otherwise we must pick up the subject character. Note that we cannot + use the value of "length" to check for sufficient bytes left, because the + other case of the character may have more or fewer bytes. */ + + else + { + pcre_uint32 dc; + GETCHARINC(dc, eptr); + ecode += length; + + /* If we have Unicode property support, we can use it to test the other + case of the character, if there is one. */ + + if (fc != dc) + { +#ifdef SUPPORT_UCP + if (dc != UCD_OTHERCASE(fc)) +#endif + RRETURN(MATCH_NOMATCH); + } + } + } + else +#endif /* SUPPORT_UTF */ + + /* Not UTF mode */ + { + if (TABLE_GET(ecode[1], md->lcc, ecode[1]) + != TABLE_GET(*eptr, md->lcc, *eptr)) RRETURN(MATCH_NOMATCH); + eptr++; + ecode += 2; + } + break; + + /* Match a single character repeatedly. */ + + case OP_EXACT: + case OP_EXACTI: + min = max = GET2(ecode, 1); + ecode += 1 + IMM2_SIZE; + goto REPEATCHAR; + + case OP_POSUPTO: + case OP_POSUPTOI: + possessive = TRUE; + /* Fall through */ + + case OP_UPTO: + case OP_UPTOI: + case OP_MINUPTO: + case OP_MINUPTOI: + min = 0; + max = GET2(ecode, 1); + minimize = *ecode == OP_MINUPTO || *ecode == OP_MINUPTOI; + ecode += 1 + IMM2_SIZE; + goto REPEATCHAR; + + case OP_POSSTAR: + case OP_POSSTARI: + possessive = TRUE; + min = 0; + max = INT_MAX; + ecode++; + goto REPEATCHAR; + + case OP_POSPLUS: + case OP_POSPLUSI: + possessive = TRUE; + min = 1; + max = INT_MAX; + ecode++; + goto REPEATCHAR; + + case OP_POSQUERY: + case OP_POSQUERYI: + possessive = TRUE; + min = 0; + max = 1; + ecode++; + goto REPEATCHAR; + + case OP_STAR: + case OP_STARI: + case OP_MINSTAR: + case OP_MINSTARI: + case OP_PLUS: + case OP_PLUSI: + case OP_MINPLUS: + case OP_MINPLUSI: + case OP_QUERY: + case OP_QUERYI: + case OP_MINQUERY: + case OP_MINQUERYI: + c = *ecode++ - ((op < OP_STARI)? OP_STAR : OP_STARI); + minimize = (c & 1) != 0; + min = rep_min[c]; /* Pick up values from tables; */ + max = rep_max[c]; /* zero for max => infinity */ + if (max == 0) max = INT_MAX; + + /* Common code for all repeated single-character matches. We first check + for the minimum number of characters. If the minimum equals the maximum, we + are done. Otherwise, if minimizing, check the rest of the pattern for a + match; if there isn't one, advance up to the maximum, one character at a + time. + + If maximizing, advance up to the maximum number of matching characters, + until eptr is past the end of the maximum run. If possessive, we are + then done (no backing up). Otherwise, match at this position; anything + other than no match is immediately returned. For nomatch, back up one + character, unless we are matching \R and the last thing matched was + \r\n, in which case, back up two bytes. When we reach the first optional + character position, we can save stack by doing a tail recurse. + + The various UTF/non-UTF and caseful/caseless cases are handled separately, + for speed. */ + + REPEATCHAR: +#ifdef SUPPORT_UTF + if (utf) + { + length = 1; + charptr = ecode; + GETCHARLEN(fc, ecode, length); + ecode += length; + + /* Handle multibyte character matching specially here. There is + support for caseless matching if UCP support is present. */ + + if (length > 1) + { +#ifdef SUPPORT_UCP + pcre_uint32 othercase; + if (op >= OP_STARI && /* Caseless */ + (othercase = UCD_OTHERCASE(fc)) != fc) + oclength = PRIV(ord2utf)(othercase, occhars); + else oclength = 0; +#endif /* SUPPORT_UCP */ + + for (i = 1; i <= min; i++) + { + if (eptr <= md->end_subject - length && + memcmp(eptr, charptr, IN_UCHARS(length)) == 0) eptr += length; +#ifdef SUPPORT_UCP + else if (oclength > 0 && + eptr <= md->end_subject - oclength && + memcmp(eptr, occhars, IN_UCHARS(oclength)) == 0) eptr += oclength; +#endif /* SUPPORT_UCP */ + else + { + CHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + } + + if (min == max) continue; + + if (minimize) + { + for (fi = min;; fi++) + { + RMATCH(eptr, ecode, offset_top, md, eptrb, RM22); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max) RRETURN(MATCH_NOMATCH); + if (eptr <= md->end_subject - length && + memcmp(eptr, charptr, IN_UCHARS(length)) == 0) eptr += length; +#ifdef SUPPORT_UCP + else if (oclength > 0 && + eptr <= md->end_subject - oclength && + memcmp(eptr, occhars, IN_UCHARS(oclength)) == 0) eptr += oclength; +#endif /* SUPPORT_UCP */ + else + { + CHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + } + /* Control never gets here */ + } + + else /* Maximize */ + { + pp = eptr; + for (i = min; i < max; i++) + { + if (eptr <= md->end_subject - length && + memcmp(eptr, charptr, IN_UCHARS(length)) == 0) eptr += length; +#ifdef SUPPORT_UCP + else if (oclength > 0 && + eptr <= md->end_subject - oclength && + memcmp(eptr, occhars, IN_UCHARS(oclength)) == 0) eptr += oclength; +#endif /* SUPPORT_UCP */ + else + { + CHECK_PARTIAL(); + break; + } + } + + if (possessive) continue; /* No backtracking */ + for(;;) + { + if (eptr == pp) goto TAIL_RECURSE; + RMATCH(eptr, ecode, offset_top, md, eptrb, RM23); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); +#ifdef SUPPORT_UCP + eptr--; + BACKCHAR(eptr); +#else /* without SUPPORT_UCP */ + eptr -= length; +#endif /* SUPPORT_UCP */ + } + } + /* Control never gets here */ + } + + /* If the length of a UTF-8 character is 1, we fall through here, and + obey the code as for non-UTF-8 characters below, though in this case the + value of fc will always be < 128. */ + } + else +#endif /* SUPPORT_UTF */ + /* When not in UTF-8 mode, load a single-byte character. */ + fc = *ecode++; + + /* The value of fc at this point is always one character, though we may + or may not be in UTF mode. The code is duplicated for the caseless and + caseful cases, for speed, since matching characters is likely to be quite + common. First, ensure the minimum number of matches are present. If min = + max, continue at the same level without recursing. Otherwise, if + minimizing, keep trying the rest of the expression and advancing one + matching character if failing, up to the maximum. Alternatively, if + maximizing, find the maximum number of characters and work backwards. */ + + DPRINTF(("matching %c{%d,%d} against subject %.*s\n", fc, min, max, + max, (char *)eptr)); + + if (op >= OP_STARI) /* Caseless */ + { +#ifdef COMPILE_PCRE8 + /* fc must be < 128 if UTF is enabled. */ + foc = md->fcc[fc]; +#else +#ifdef SUPPORT_UTF +#ifdef SUPPORT_UCP + if (utf && fc > 127) + foc = UCD_OTHERCASE(fc); +#else + if (utf && fc > 127) + foc = fc; +#endif /* SUPPORT_UCP */ + else +#endif /* SUPPORT_UTF */ + foc = TABLE_GET(fc, md->fcc, fc); +#endif /* COMPILE_PCRE8 */ + + for (i = 1; i <= min; i++) + { + pcre_uint32 cc; /* Faster than pcre_uchar */ + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + cc = UCHAR21TEST(eptr); + if (fc != cc && foc != cc) RRETURN(MATCH_NOMATCH); + eptr++; + } + if (min == max) continue; + if (minimize) + { + for (fi = min;; fi++) + { + pcre_uint32 cc; /* Faster than pcre_uchar */ + RMATCH(eptr, ecode, offset_top, md, eptrb, RM24); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max) RRETURN(MATCH_NOMATCH); + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + cc = UCHAR21TEST(eptr); + if (fc != cc && foc != cc) RRETURN(MATCH_NOMATCH); + eptr++; + } + /* Control never gets here */ + } + else /* Maximize */ + { + pp = eptr; + for (i = min; i < max; i++) + { + pcre_uint32 cc; /* Faster than pcre_uchar */ + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + cc = UCHAR21TEST(eptr); + if (fc != cc && foc != cc) break; + eptr++; + } + if (possessive) continue; /* No backtracking */ + for (;;) + { + if (eptr == pp) goto TAIL_RECURSE; + RMATCH(eptr, ecode, offset_top, md, eptrb, RM25); + eptr--; + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + } + /* Control never gets here */ + } + } + + /* Caseful comparisons (includes all multi-byte characters) */ + + else + { + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + if (fc != UCHAR21INCTEST(eptr)) RRETURN(MATCH_NOMATCH); + } + + if (min == max) continue; + + if (minimize) + { + for (fi = min;; fi++) + { + RMATCH(eptr, ecode, offset_top, md, eptrb, RM26); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max) RRETURN(MATCH_NOMATCH); + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + if (fc != UCHAR21INCTEST(eptr)) RRETURN(MATCH_NOMATCH); + } + /* Control never gets here */ + } + else /* Maximize */ + { + pp = eptr; + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + if (fc != UCHAR21TEST(eptr)) break; + eptr++; + } + if (possessive) continue; /* No backtracking */ + for (;;) + { + if (eptr == pp) goto TAIL_RECURSE; + RMATCH(eptr, ecode, offset_top, md, eptrb, RM27); + eptr--; + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + } + /* Control never gets here */ + } + } + /* Control never gets here */ + + /* Match a negated single one-byte character. The character we are + checking can be multibyte. */ + + case OP_NOT: + case OP_NOTI: + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } +#ifdef SUPPORT_UTF + if (utf) + { + register pcre_uint32 ch, och; + + ecode++; + GETCHARINC(ch, ecode); + GETCHARINC(c, eptr); + + if (op == OP_NOT) + { + if (ch == c) RRETURN(MATCH_NOMATCH); + } + else + { +#ifdef SUPPORT_UCP + if (ch > 127) + och = UCD_OTHERCASE(ch); +#else + if (ch > 127) + och = ch; +#endif /* SUPPORT_UCP */ + else + och = TABLE_GET(ch, md->fcc, ch); + if (ch == c || och == c) RRETURN(MATCH_NOMATCH); + } + } + else +#endif + { + register pcre_uint32 ch = ecode[1]; + c = *eptr++; + if (ch == c || (op == OP_NOTI && TABLE_GET(ch, md->fcc, ch) == c)) + RRETURN(MATCH_NOMATCH); + ecode += 2; + } + break; + + /* Match a negated single one-byte character repeatedly. This is almost a + repeat of the code for a repeated single character, but I haven't found a + nice way of commoning these up that doesn't require a test of the + positive/negative option for each character match. Maybe that wouldn't add + very much to the time taken, but character matching *is* what this is all + about... */ + + case OP_NOTEXACT: + case OP_NOTEXACTI: + min = max = GET2(ecode, 1); + ecode += 1 + IMM2_SIZE; + goto REPEATNOTCHAR; + + case OP_NOTUPTO: + case OP_NOTUPTOI: + case OP_NOTMINUPTO: + case OP_NOTMINUPTOI: + min = 0; + max = GET2(ecode, 1); + minimize = *ecode == OP_NOTMINUPTO || *ecode == OP_NOTMINUPTOI; + ecode += 1 + IMM2_SIZE; + goto REPEATNOTCHAR; + + case OP_NOTPOSSTAR: + case OP_NOTPOSSTARI: + possessive = TRUE; + min = 0; + max = INT_MAX; + ecode++; + goto REPEATNOTCHAR; + + case OP_NOTPOSPLUS: + case OP_NOTPOSPLUSI: + possessive = TRUE; + min = 1; + max = INT_MAX; + ecode++; + goto REPEATNOTCHAR; + + case OP_NOTPOSQUERY: + case OP_NOTPOSQUERYI: + possessive = TRUE; + min = 0; + max = 1; + ecode++; + goto REPEATNOTCHAR; + + case OP_NOTPOSUPTO: + case OP_NOTPOSUPTOI: + possessive = TRUE; + min = 0; + max = GET2(ecode, 1); + ecode += 1 + IMM2_SIZE; + goto REPEATNOTCHAR; + + case OP_NOTSTAR: + case OP_NOTSTARI: + case OP_NOTMINSTAR: + case OP_NOTMINSTARI: + case OP_NOTPLUS: + case OP_NOTPLUSI: + case OP_NOTMINPLUS: + case OP_NOTMINPLUSI: + case OP_NOTQUERY: + case OP_NOTQUERYI: + case OP_NOTMINQUERY: + case OP_NOTMINQUERYI: + c = *ecode++ - ((op >= OP_NOTSTARI)? OP_NOTSTARI: OP_NOTSTAR); + minimize = (c & 1) != 0; + min = rep_min[c]; /* Pick up values from tables; */ + max = rep_max[c]; /* zero for max => infinity */ + if (max == 0) max = INT_MAX; + + /* Common code for all repeated single-byte matches. */ + + REPEATNOTCHAR: + GETCHARINCTEST(fc, ecode); + + /* The code is duplicated for the caseless and caseful cases, for speed, + since matching characters is likely to be quite common. First, ensure the + minimum number of matches are present. If min = max, continue at the same + level without recursing. Otherwise, if minimizing, keep trying the rest of + the expression and advancing one matching character if failing, up to the + maximum. Alternatively, if maximizing, find the maximum number of + characters and work backwards. */ + + DPRINTF(("negative matching %c{%d,%d} against subject %.*s\n", fc, min, max, + max, (char *)eptr)); + + if (op >= OP_NOTSTARI) /* Caseless */ + { +#ifdef SUPPORT_UTF +#ifdef SUPPORT_UCP + if (utf && fc > 127) + foc = UCD_OTHERCASE(fc); +#else + if (utf && fc > 127) + foc = fc; +#endif /* SUPPORT_UCP */ + else +#endif /* SUPPORT_UTF */ + foc = TABLE_GET(fc, md->fcc, fc); + +#ifdef SUPPORT_UTF + if (utf) + { + register pcre_uint32 d; + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINC(d, eptr); + if (fc == d || (unsigned int)foc == d) RRETURN(MATCH_NOMATCH); + } + } + else +#endif /* SUPPORT_UTF */ + /* Not UTF mode */ + { + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + if (fc == *eptr || foc == *eptr) RRETURN(MATCH_NOMATCH); + eptr++; + } + } + + if (min == max) continue; + + if (minimize) + { +#ifdef SUPPORT_UTF + if (utf) + { + register pcre_uint32 d; + for (fi = min;; fi++) + { + RMATCH(eptr, ecode, offset_top, md, eptrb, RM28); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max) RRETURN(MATCH_NOMATCH); + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINC(d, eptr); + if (fc == d || (unsigned int)foc == d) RRETURN(MATCH_NOMATCH); + } + } + else +#endif /*SUPPORT_UTF */ + /* Not UTF mode */ + { + for (fi = min;; fi++) + { + RMATCH(eptr, ecode, offset_top, md, eptrb, RM29); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max) RRETURN(MATCH_NOMATCH); + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + if (fc == *eptr || foc == *eptr) RRETURN(MATCH_NOMATCH); + eptr++; + } + } + /* Control never gets here */ + } + + /* Maximize case */ + + else + { + pp = eptr; + +#ifdef SUPPORT_UTF + if (utf) + { + register pcre_uint32 d; + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + GETCHARLEN(d, eptr, len); + if (fc == d || (unsigned int)foc == d) break; + eptr += len; + } + if (possessive) continue; /* No backtracking */ + for(;;) + { + if (eptr == pp) goto TAIL_RECURSE; + RMATCH(eptr, ecode, offset_top, md, eptrb, RM30); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + eptr--; + BACKCHAR(eptr); + } + } + else +#endif /* SUPPORT_UTF */ + /* Not UTF mode */ + { + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + if (fc == *eptr || foc == *eptr) break; + eptr++; + } + if (possessive) continue; /* No backtracking */ + for (;;) + { + if (eptr == pp) goto TAIL_RECURSE; + RMATCH(eptr, ecode, offset_top, md, eptrb, RM31); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + eptr--; + } + } + /* Control never gets here */ + } + } + + /* Caseful comparisons */ + + else + { +#ifdef SUPPORT_UTF + if (utf) + { + register pcre_uint32 d; + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINC(d, eptr); + if (fc == d) RRETURN(MATCH_NOMATCH); + } + } + else +#endif + /* Not UTF mode */ + { + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + if (fc == *eptr++) RRETURN(MATCH_NOMATCH); + } + } + + if (min == max) continue; + + if (minimize) + { +#ifdef SUPPORT_UTF + if (utf) + { + register pcre_uint32 d; + for (fi = min;; fi++) + { + RMATCH(eptr, ecode, offset_top, md, eptrb, RM32); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max) RRETURN(MATCH_NOMATCH); + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINC(d, eptr); + if (fc == d) RRETURN(MATCH_NOMATCH); + } + } + else +#endif + /* Not UTF mode */ + { + for (fi = min;; fi++) + { + RMATCH(eptr, ecode, offset_top, md, eptrb, RM33); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max) RRETURN(MATCH_NOMATCH); + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + if (fc == *eptr++) RRETURN(MATCH_NOMATCH); + } + } + /* Control never gets here */ + } + + /* Maximize case */ + + else + { + pp = eptr; + +#ifdef SUPPORT_UTF + if (utf) + { + register pcre_uint32 d; + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + GETCHARLEN(d, eptr, len); + if (fc == d) break; + eptr += len; + } + if (possessive) continue; /* No backtracking */ + for(;;) + { + if (eptr == pp) goto TAIL_RECURSE; + RMATCH(eptr, ecode, offset_top, md, eptrb, RM34); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + eptr--; + BACKCHAR(eptr); + } + } + else +#endif + /* Not UTF mode */ + { + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + if (fc == *eptr) break; + eptr++; + } + if (possessive) continue; /* No backtracking */ + for (;;) + { + if (eptr == pp) goto TAIL_RECURSE; + RMATCH(eptr, ecode, offset_top, md, eptrb, RM35); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + eptr--; + } + } + /* Control never gets here */ + } + } + /* Control never gets here */ + + /* Match a single character type repeatedly; several different opcodes + share code. This is very similar to the code for single characters, but we + repeat it in the interests of efficiency. */ + + case OP_TYPEEXACT: + min = max = GET2(ecode, 1); + minimize = TRUE; + ecode += 1 + IMM2_SIZE; + goto REPEATTYPE; + + case OP_TYPEUPTO: + case OP_TYPEMINUPTO: + min = 0; + max = GET2(ecode, 1); + minimize = *ecode == OP_TYPEMINUPTO; + ecode += 1 + IMM2_SIZE; + goto REPEATTYPE; + + case OP_TYPEPOSSTAR: + possessive = TRUE; + min = 0; + max = INT_MAX; + ecode++; + goto REPEATTYPE; + + case OP_TYPEPOSPLUS: + possessive = TRUE; + min = 1; + max = INT_MAX; + ecode++; + goto REPEATTYPE; + + case OP_TYPEPOSQUERY: + possessive = TRUE; + min = 0; + max = 1; + ecode++; + goto REPEATTYPE; + + case OP_TYPEPOSUPTO: + possessive = TRUE; + min = 0; + max = GET2(ecode, 1); + ecode += 1 + IMM2_SIZE; + goto REPEATTYPE; + + case OP_TYPESTAR: + case OP_TYPEMINSTAR: + case OP_TYPEPLUS: + case OP_TYPEMINPLUS: + case OP_TYPEQUERY: + case OP_TYPEMINQUERY: + c = *ecode++ - OP_TYPESTAR; + minimize = (c & 1) != 0; + min = rep_min[c]; /* Pick up values from tables; */ + max = rep_max[c]; /* zero for max => infinity */ + if (max == 0) max = INT_MAX; + + /* Common code for all repeated single character type matches. Note that + in UTF-8 mode, '.' matches a character of any length, but for the other + character types, the valid characters are all one-byte long. */ + + REPEATTYPE: + ctype = *ecode++; /* Code for the character type */ + +#ifdef SUPPORT_UCP + if (ctype == OP_PROP || ctype == OP_NOTPROP) + { + prop_fail_result = ctype == OP_NOTPROP; + prop_type = *ecode++; + prop_value = *ecode++; + } + else prop_type = -1; +#endif + + /* First, ensure the minimum number of matches are present. Use inline + code for maximizing the speed, and do the type test once at the start + (i.e. keep it out of the loop). Separate the UTF-8 code completely as that + is tidier. Also separate the UCP code, which can be the same for both UTF-8 + and single-bytes. */ + + if (min > 0) + { +#ifdef SUPPORT_UCP + if (prop_type >= 0) + { + switch(prop_type) + { + case PT_ANY: + if (prop_fail_result) RRETURN(MATCH_NOMATCH); + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + } + break; + + case PT_LAMP: + for (i = 1; i <= min; i++) + { + int chartype; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + chartype = UCD_CHARTYPE(c); + if ((chartype == ucp_Lu || + chartype == ucp_Ll || + chartype == ucp_Lt) == prop_fail_result) + RRETURN(MATCH_NOMATCH); + } + break; + + case PT_GC: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + if ((UCD_CATEGORY(c) == prop_value) == prop_fail_result) + RRETURN(MATCH_NOMATCH); + } + break; + + case PT_PC: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + if ((UCD_CHARTYPE(c) == prop_value) == prop_fail_result) + RRETURN(MATCH_NOMATCH); + } + break; + + case PT_SC: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + if ((UCD_SCRIPT(c) == prop_value) == prop_fail_result) + RRETURN(MATCH_NOMATCH); + } + break; + + case PT_ALNUM: + for (i = 1; i <= min; i++) + { + int category; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + category = UCD_CATEGORY(c); + if ((category == ucp_L || category == ucp_N) == prop_fail_result) + RRETURN(MATCH_NOMATCH); + } + break; + + /* Perl space used to exclude VT, but from Perl 5.18 it is included, + which means that Perl space and POSIX space are now identical. PCRE + was changed at release 8.34. */ + + case PT_SPACE: /* Perl space */ + case PT_PXSPACE: /* POSIX space */ + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + switch(c) + { + HSPACE_CASES: + VSPACE_CASES: + if (prop_fail_result) RRETURN(MATCH_NOMATCH); + break; + + default: + if ((UCD_CATEGORY(c) == ucp_Z) == prop_fail_result) + RRETURN(MATCH_NOMATCH); + break; + } + } + break; + + case PT_WORD: + for (i = 1; i <= min; i++) + { + int category; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + category = UCD_CATEGORY(c); + if ((category == ucp_L || category == ucp_N || c == CHAR_UNDERSCORE) + == prop_fail_result) + RRETURN(MATCH_NOMATCH); + } + break; + + case PT_CLIST: + for (i = 1; i <= min; i++) + { + const pcre_uint32 *cp; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + cp = PRIV(ucd_caseless_sets) + prop_value; + for (;;) + { + if (c < *cp) + { if (prop_fail_result) break; else { RRETURN(MATCH_NOMATCH); } } + if (c == *cp++) + { if (prop_fail_result) { RRETURN(MATCH_NOMATCH); } else break; } + } + } + break; + + case PT_UCNC: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + if ((c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT || + c == CHAR_GRAVE_ACCENT || (c >= 0xa0 && c <= 0xd7ff) || + c >= 0xe000) == prop_fail_result) + RRETURN(MATCH_NOMATCH); + } + break; + + /* This should not occur */ + + default: + RRETURN(PCRE_ERROR_INTERNAL); + } + } + + /* Match extended Unicode sequences. We will get here only if the + support is in the binary; otherwise a compile-time error occurs. */ + + else if (ctype == OP_EXTUNI) + { + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + else + { + int lgb, rgb; + GETCHARINCTEST(c, eptr); + lgb = UCD_GRAPHBREAK(c); + while (eptr < md->end_subject) + { + int len = 1; + if (!utf) c = *eptr; else { GETCHARLEN(c, eptr, len); } + rgb = UCD_GRAPHBREAK(c); + if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break; + lgb = rgb; + eptr += len; + } + } + CHECK_PARTIAL(); + } + } + + else +#endif /* SUPPORT_UCP */ + +/* Handle all other cases when the coding is UTF-8 */ + +#ifdef SUPPORT_UTF + if (utf) switch(ctype) + { + case OP_ANY: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH); + if (md->partial != 0 && + eptr + 1 >= md->end_subject && + NLBLOCK->nltype == NLTYPE_FIXED && + NLBLOCK->nllen == 2 && + UCHAR21(eptr) == NLBLOCK->nl[0]) + { + md->hitend = TRUE; + if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); + } + eptr++; + ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++); + } + break; + + case OP_ALLANY: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + eptr++; + ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++); + } + break; + + case OP_ANYBYTE: + if (eptr > md->end_subject - min) RRETURN(MATCH_NOMATCH); + eptr += min; + break; + + case OP_ANYNL: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINC(c, eptr); + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + + case CHAR_CR: + if (eptr < md->end_subject && UCHAR21(eptr) == CHAR_LF) eptr++; + break; + + case CHAR_LF: + break; + + case CHAR_VT: + case CHAR_FF: + case CHAR_NEL: +#ifndef EBCDIC + case 0x2028: + case 0x2029: +#endif /* Not EBCDIC */ + if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); + break; + } + } + break; + + case OP_NOT_HSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINC(c, eptr); + switch(c) + { + HSPACE_CASES: RRETURN(MATCH_NOMATCH); /* Byte and multibyte cases */ + default: break; + } + } + break; + + case OP_HSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINC(c, eptr); + switch(c) + { + HSPACE_CASES: break; /* Byte and multibyte cases */ + default: RRETURN(MATCH_NOMATCH); + } + } + break; + + case OP_NOT_VSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINC(c, eptr); + switch(c) + { + VSPACE_CASES: RRETURN(MATCH_NOMATCH); + default: break; + } + } + break; + + case OP_VSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINC(c, eptr); + switch(c) + { + VSPACE_CASES: break; + default: RRETURN(MATCH_NOMATCH); + } + } + break; + + case OP_NOT_DIGIT: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINC(c, eptr); + if (c < 128 && (md->ctypes[c] & ctype_digit) != 0) + RRETURN(MATCH_NOMATCH); + } + break; + + case OP_DIGIT: + for (i = 1; i <= min; i++) + { + pcre_uint32 cc; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + cc = UCHAR21(eptr); + if (cc >= 128 || (md->ctypes[cc] & ctype_digit) == 0) + RRETURN(MATCH_NOMATCH); + eptr++; + /* No need to skip more bytes - we know it's a 1-byte character */ + } + break; + + case OP_NOT_WHITESPACE: + for (i = 1; i <= min; i++) + { + pcre_uint32 cc; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + cc = UCHAR21(eptr); + if (cc < 128 && (md->ctypes[cc] & ctype_space) != 0) + RRETURN(MATCH_NOMATCH); + eptr++; + ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++); + } + break; + + case OP_WHITESPACE: + for (i = 1; i <= min; i++) + { + pcre_uint32 cc; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + cc = UCHAR21(eptr); + if (cc >= 128 || (md->ctypes[cc] & ctype_space) == 0) + RRETURN(MATCH_NOMATCH); + eptr++; + /* No need to skip more bytes - we know it's a 1-byte character */ + } + break; + + case OP_NOT_WORDCHAR: + for (i = 1; i <= min; i++) + { + pcre_uint32 cc; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + cc = UCHAR21(eptr); + if (cc < 128 && (md->ctypes[cc] & ctype_word) != 0) + RRETURN(MATCH_NOMATCH); + eptr++; + ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++); + } + break; + + case OP_WORDCHAR: + for (i = 1; i <= min; i++) + { + pcre_uint32 cc; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + cc = UCHAR21(eptr); + if (cc >= 128 || (md->ctypes[cc] & ctype_word) == 0) + RRETURN(MATCH_NOMATCH); + eptr++; + /* No need to skip more bytes - we know it's a 1-byte character */ + } + break; + + default: + RRETURN(PCRE_ERROR_INTERNAL); + } /* End switch(ctype) */ + + else +#endif /* SUPPORT_UTF */ + + /* Code for the non-UTF-8 case for minimum matching of operators other + than OP_PROP and OP_NOTPROP. */ + + switch(ctype) + { + case OP_ANY: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH); + if (md->partial != 0 && + eptr + 1 >= md->end_subject && + NLBLOCK->nltype == NLTYPE_FIXED && + NLBLOCK->nllen == 2 && + *eptr == NLBLOCK->nl[0]) + { + md->hitend = TRUE; + if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); + } + eptr++; + } + break; + + case OP_ALLANY: + if (eptr > md->end_subject - min) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + eptr += min; + break; + + case OP_ANYBYTE: + if (eptr > md->end_subject - min) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + eptr += min; + break; + + case OP_ANYNL: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + switch(*eptr++) + { + default: RRETURN(MATCH_NOMATCH); + + case CHAR_CR: + if (eptr < md->end_subject && *eptr == CHAR_LF) eptr++; + break; + + case CHAR_LF: + break; + + case CHAR_VT: + case CHAR_FF: + case CHAR_NEL: +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + case 0x2028: + case 0x2029: +#endif + if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); + break; + } + } + break; + + case OP_NOT_HSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + switch(*eptr++) + { + default: break; + HSPACE_BYTE_CASES: +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + HSPACE_MULTIBYTE_CASES: +#endif + RRETURN(MATCH_NOMATCH); + } + } + break; + + case OP_HSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + switch(*eptr++) + { + default: RRETURN(MATCH_NOMATCH); + HSPACE_BYTE_CASES: +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + HSPACE_MULTIBYTE_CASES: +#endif + break; + } + } + break; + + case OP_NOT_VSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + switch(*eptr++) + { + VSPACE_BYTE_CASES: +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + VSPACE_MULTIBYTE_CASES: +#endif + RRETURN(MATCH_NOMATCH); + default: break; + } + } + break; + + case OP_VSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + switch(*eptr++) + { + default: RRETURN(MATCH_NOMATCH); + VSPACE_BYTE_CASES: +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + VSPACE_MULTIBYTE_CASES: +#endif + break; + } + } + break; + + case OP_NOT_DIGIT: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + if (MAX_255(*eptr) && (md->ctypes[*eptr] & ctype_digit) != 0) + RRETURN(MATCH_NOMATCH); + eptr++; + } + break; + + case OP_DIGIT: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + if (!MAX_255(*eptr) || (md->ctypes[*eptr] & ctype_digit) == 0) + RRETURN(MATCH_NOMATCH); + eptr++; + } + break; + + case OP_NOT_WHITESPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + if (MAX_255(*eptr) && (md->ctypes[*eptr] & ctype_space) != 0) + RRETURN(MATCH_NOMATCH); + eptr++; + } + break; + + case OP_WHITESPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + if (!MAX_255(*eptr) || (md->ctypes[*eptr] & ctype_space) == 0) + RRETURN(MATCH_NOMATCH); + eptr++; + } + break; + + case OP_NOT_WORDCHAR: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + if (MAX_255(*eptr) && (md->ctypes[*eptr] & ctype_word) != 0) + RRETURN(MATCH_NOMATCH); + eptr++; + } + break; + + case OP_WORDCHAR: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + if (!MAX_255(*eptr) || (md->ctypes[*eptr] & ctype_word) == 0) + RRETURN(MATCH_NOMATCH); + eptr++; + } + break; + + default: + RRETURN(PCRE_ERROR_INTERNAL); + } + } + + /* If min = max, continue at the same level without recursing */ + + if (min == max) continue; + + /* If minimizing, we have to test the rest of the pattern before each + subsequent match. Again, separate the UTF-8 case for speed, and also + separate the UCP cases. */ + + if (minimize) + { +#ifdef SUPPORT_UCP + if (prop_type >= 0) + { + switch(prop_type) + { + case PT_ANY: + for (fi = min;; fi++) + { + RMATCH(eptr, ecode, offset_top, md, eptrb, RM36); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max) RRETURN(MATCH_NOMATCH); + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + if (prop_fail_result) RRETURN(MATCH_NOMATCH); + } + /* Control never gets here */ + + case PT_LAMP: + for (fi = min;; fi++) + { + int chartype; + RMATCH(eptr, ecode, offset_top, md, eptrb, RM37); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max) RRETURN(MATCH_NOMATCH); + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + chartype = UCD_CHARTYPE(c); + if ((chartype == ucp_Lu || + chartype == ucp_Ll || + chartype == ucp_Lt) == prop_fail_result) + RRETURN(MATCH_NOMATCH); + } + /* Control never gets here */ + + case PT_GC: + for (fi = min;; fi++) + { + RMATCH(eptr, ecode, offset_top, md, eptrb, RM38); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max) RRETURN(MATCH_NOMATCH); + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + if ((UCD_CATEGORY(c) == prop_value) == prop_fail_result) + RRETURN(MATCH_NOMATCH); + } + /* Control never gets here */ + + case PT_PC: + for (fi = min;; fi++) + { + RMATCH(eptr, ecode, offset_top, md, eptrb, RM39); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max) RRETURN(MATCH_NOMATCH); + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + if ((UCD_CHARTYPE(c) == prop_value) == prop_fail_result) + RRETURN(MATCH_NOMATCH); + } + /* Control never gets here */ + + case PT_SC: + for (fi = min;; fi++) + { + RMATCH(eptr, ecode, offset_top, md, eptrb, RM40); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max) RRETURN(MATCH_NOMATCH); + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + if ((UCD_SCRIPT(c) == prop_value) == prop_fail_result) + RRETURN(MATCH_NOMATCH); + } + /* Control never gets here */ + + case PT_ALNUM: + for (fi = min;; fi++) + { + int category; + RMATCH(eptr, ecode, offset_top, md, eptrb, RM59); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max) RRETURN(MATCH_NOMATCH); + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + category = UCD_CATEGORY(c); + if ((category == ucp_L || category == ucp_N) == prop_fail_result) + RRETURN(MATCH_NOMATCH); + } + /* Control never gets here */ + + /* Perl space used to exclude VT, but from Perl 5.18 it is included, + which means that Perl space and POSIX space are now identical. PCRE + was changed at release 8.34. */ + + case PT_SPACE: /* Perl space */ + case PT_PXSPACE: /* POSIX space */ + for (fi = min;; fi++) + { + RMATCH(eptr, ecode, offset_top, md, eptrb, RM61); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max) RRETURN(MATCH_NOMATCH); + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + switch(c) + { + HSPACE_CASES: + VSPACE_CASES: + if (prop_fail_result) RRETURN(MATCH_NOMATCH); + break; + + default: + if ((UCD_CATEGORY(c) == ucp_Z) == prop_fail_result) + RRETURN(MATCH_NOMATCH); + break; + } + } + /* Control never gets here */ + + case PT_WORD: + for (fi = min;; fi++) + { + int category; + RMATCH(eptr, ecode, offset_top, md, eptrb, RM62); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max) RRETURN(MATCH_NOMATCH); + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + category = UCD_CATEGORY(c); + if ((category == ucp_L || + category == ucp_N || + c == CHAR_UNDERSCORE) + == prop_fail_result) + RRETURN(MATCH_NOMATCH); + } + /* Control never gets here */ + + case PT_CLIST: + for (fi = min;; fi++) + { + const pcre_uint32 *cp; + RMATCH(eptr, ecode, offset_top, md, eptrb, RM67); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max) RRETURN(MATCH_NOMATCH); + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + cp = PRIV(ucd_caseless_sets) + prop_value; + for (;;) + { + if (c < *cp) + { if (prop_fail_result) break; else { RRETURN(MATCH_NOMATCH); } } + if (c == *cp++) + { if (prop_fail_result) { RRETURN(MATCH_NOMATCH); } else break; } + } + } + /* Control never gets here */ + + case PT_UCNC: + for (fi = min;; fi++) + { + RMATCH(eptr, ecode, offset_top, md, eptrb, RM60); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max) RRETURN(MATCH_NOMATCH); + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + GETCHARINCTEST(c, eptr); + if ((c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT || + c == CHAR_GRAVE_ACCENT || (c >= 0xa0 && c <= 0xd7ff) || + c >= 0xe000) == prop_fail_result) + RRETURN(MATCH_NOMATCH); + } + /* Control never gets here */ + + /* This should never occur */ + default: + RRETURN(PCRE_ERROR_INTERNAL); + } + } + + /* Match extended Unicode sequences. We will get here only if the + support is in the binary; otherwise a compile-time error occurs. */ + + else if (ctype == OP_EXTUNI) + { + for (fi = min;; fi++) + { + RMATCH(eptr, ecode, offset_top, md, eptrb, RM41); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max) RRETURN(MATCH_NOMATCH); + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + else + { + int lgb, rgb; + GETCHARINCTEST(c, eptr); + lgb = UCD_GRAPHBREAK(c); + while (eptr < md->end_subject) + { + int len = 1; + if (!utf) c = *eptr; else { GETCHARLEN(c, eptr, len); } + rgb = UCD_GRAPHBREAK(c); + if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break; + lgb = rgb; + eptr += len; + } + } + CHECK_PARTIAL(); + } + } + else +#endif /* SUPPORT_UCP */ + +#ifdef SUPPORT_UTF + if (utf) + { + for (fi = min;; fi++) + { + RMATCH(eptr, ecode, offset_top, md, eptrb, RM42); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max) RRETURN(MATCH_NOMATCH); + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + if (ctype == OP_ANY && IS_NEWLINE(eptr)) + RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + switch(ctype) + { + case OP_ANY: /* This is the non-NL case */ + if (md->partial != 0 && /* Take care with CRLF partial */ + eptr >= md->end_subject && + NLBLOCK->nltype == NLTYPE_FIXED && + NLBLOCK->nllen == 2 && + c == NLBLOCK->nl[0]) + { + md->hitend = TRUE; + if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); + } + break; + + case OP_ALLANY: + case OP_ANYBYTE: + break; + + case OP_ANYNL: + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case CHAR_CR: + if (eptr < md->end_subject && UCHAR21(eptr) == CHAR_LF) eptr++; + break; + + case CHAR_LF: + break; + + case CHAR_VT: + case CHAR_FF: + case CHAR_NEL: +#ifndef EBCDIC + case 0x2028: + case 0x2029: +#endif /* Not EBCDIC */ + if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); + break; + } + break; + + case OP_NOT_HSPACE: + switch(c) + { + HSPACE_CASES: RRETURN(MATCH_NOMATCH); + default: break; + } + break; + + case OP_HSPACE: + switch(c) + { + HSPACE_CASES: break; + default: RRETURN(MATCH_NOMATCH); + } + break; + + case OP_NOT_VSPACE: + switch(c) + { + VSPACE_CASES: RRETURN(MATCH_NOMATCH); + default: break; + } + break; + + case OP_VSPACE: + switch(c) + { + VSPACE_CASES: break; + default: RRETURN(MATCH_NOMATCH); + } + break; + + case OP_NOT_DIGIT: + if (c < 256 && (md->ctypes[c] & ctype_digit) != 0) + RRETURN(MATCH_NOMATCH); + break; + + case OP_DIGIT: + if (c >= 256 || (md->ctypes[c] & ctype_digit) == 0) + RRETURN(MATCH_NOMATCH); + break; + + case OP_NOT_WHITESPACE: + if (c < 256 && (md->ctypes[c] & ctype_space) != 0) + RRETURN(MATCH_NOMATCH); + break; + + case OP_WHITESPACE: + if (c >= 256 || (md->ctypes[c] & ctype_space) == 0) + RRETURN(MATCH_NOMATCH); + break; + + case OP_NOT_WORDCHAR: + if (c < 256 && (md->ctypes[c] & ctype_word) != 0) + RRETURN(MATCH_NOMATCH); + break; + + case OP_WORDCHAR: + if (c >= 256 || (md->ctypes[c] & ctype_word) == 0) + RRETURN(MATCH_NOMATCH); + break; + + default: + RRETURN(PCRE_ERROR_INTERNAL); + } + } + } + else +#endif + /* Not UTF mode */ + { + for (fi = min;; fi++) + { + RMATCH(eptr, ecode, offset_top, md, eptrb, RM43); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max) RRETURN(MATCH_NOMATCH); + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + RRETURN(MATCH_NOMATCH); + } + if (ctype == OP_ANY && IS_NEWLINE(eptr)) + RRETURN(MATCH_NOMATCH); + c = *eptr++; + switch(ctype) + { + case OP_ANY: /* This is the non-NL case */ + if (md->partial != 0 && /* Take care with CRLF partial */ + eptr >= md->end_subject && + NLBLOCK->nltype == NLTYPE_FIXED && + NLBLOCK->nllen == 2 && + c == NLBLOCK->nl[0]) + { + md->hitend = TRUE; + if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); + } + break; + + case OP_ALLANY: + case OP_ANYBYTE: + break; + + case OP_ANYNL: + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case CHAR_CR: + if (eptr < md->end_subject && *eptr == CHAR_LF) eptr++; + break; + + case CHAR_LF: + break; + + case CHAR_VT: + case CHAR_FF: + case CHAR_NEL: +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + case 0x2028: + case 0x2029: +#endif + if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); + break; + } + break; + + case OP_NOT_HSPACE: + switch(c) + { + default: break; + HSPACE_BYTE_CASES: +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + HSPACE_MULTIBYTE_CASES: +#endif + RRETURN(MATCH_NOMATCH); + } + break; + + case OP_HSPACE: + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + HSPACE_BYTE_CASES: +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + HSPACE_MULTIBYTE_CASES: +#endif + break; + } + break; + + case OP_NOT_VSPACE: + switch(c) + { + default: break; + VSPACE_BYTE_CASES: +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + VSPACE_MULTIBYTE_CASES: +#endif + RRETURN(MATCH_NOMATCH); + } + break; + + case OP_VSPACE: + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + VSPACE_BYTE_CASES: +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + VSPACE_MULTIBYTE_CASES: +#endif + break; + } + break; + + case OP_NOT_DIGIT: + if (MAX_255(c) && (md->ctypes[c] & ctype_digit) != 0) RRETURN(MATCH_NOMATCH); + break; + + case OP_DIGIT: + if (!MAX_255(c) || (md->ctypes[c] & ctype_digit) == 0) RRETURN(MATCH_NOMATCH); + break; + + case OP_NOT_WHITESPACE: + if (MAX_255(c) && (md->ctypes[c] & ctype_space) != 0) RRETURN(MATCH_NOMATCH); + break; + + case OP_WHITESPACE: + if (!MAX_255(c) || (md->ctypes[c] & ctype_space) == 0) RRETURN(MATCH_NOMATCH); + break; + + case OP_NOT_WORDCHAR: + if (MAX_255(c) && (md->ctypes[c] & ctype_word) != 0) RRETURN(MATCH_NOMATCH); + break; + + case OP_WORDCHAR: + if (!MAX_255(c) || (md->ctypes[c] & ctype_word) == 0) RRETURN(MATCH_NOMATCH); + break; + + default: + RRETURN(PCRE_ERROR_INTERNAL); + } + } + } + /* Control never gets here */ + } + + /* If maximizing, it is worth using inline code for speed, doing the type + test once at the start (i.e. keep it out of the loop). Again, keep the + UTF-8 and UCP stuff separate. */ + + else + { + pp = eptr; /* Remember where we started */ + +#ifdef SUPPORT_UCP + if (prop_type >= 0) + { + switch(prop_type) + { + case PT_ANY: + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + GETCHARLENTEST(c, eptr, len); + if (prop_fail_result) break; + eptr+= len; + } + break; + + case PT_LAMP: + for (i = min; i < max; i++) + { + int chartype; + int len = 1; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + GETCHARLENTEST(c, eptr, len); + chartype = UCD_CHARTYPE(c); + if ((chartype == ucp_Lu || + chartype == ucp_Ll || + chartype == ucp_Lt) == prop_fail_result) + break; + eptr+= len; + } + break; + + case PT_GC: + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + GETCHARLENTEST(c, eptr, len); + if ((UCD_CATEGORY(c) == prop_value) == prop_fail_result) break; + eptr+= len; + } + break; + + case PT_PC: + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + GETCHARLENTEST(c, eptr, len); + if ((UCD_CHARTYPE(c) == prop_value) == prop_fail_result) break; + eptr+= len; + } + break; + + case PT_SC: + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + GETCHARLENTEST(c, eptr, len); + if ((UCD_SCRIPT(c) == prop_value) == prop_fail_result) break; + eptr+= len; + } + break; + + case PT_ALNUM: + for (i = min; i < max; i++) + { + int category; + int len = 1; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + GETCHARLENTEST(c, eptr, len); + category = UCD_CATEGORY(c); + if ((category == ucp_L || category == ucp_N) == prop_fail_result) + break; + eptr+= len; + } + break; + + /* Perl space used to exclude VT, but from Perl 5.18 it is included, + which means that Perl space and POSIX space are now identical. PCRE + was changed at release 8.34. */ + + case PT_SPACE: /* Perl space */ + case PT_PXSPACE: /* POSIX space */ + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + GETCHARLENTEST(c, eptr, len); + switch(c) + { + HSPACE_CASES: + VSPACE_CASES: + if (prop_fail_result) goto ENDLOOP99; /* Break the loop */ + break; + + default: + if ((UCD_CATEGORY(c) == ucp_Z) == prop_fail_result) + goto ENDLOOP99; /* Break the loop */ + break; + } + eptr+= len; + } + ENDLOOP99: + break; + + case PT_WORD: + for (i = min; i < max; i++) + { + int category; + int len = 1; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + GETCHARLENTEST(c, eptr, len); + category = UCD_CATEGORY(c); + if ((category == ucp_L || category == ucp_N || + c == CHAR_UNDERSCORE) == prop_fail_result) + break; + eptr+= len; + } + break; + + case PT_CLIST: + for (i = min; i < max; i++) + { + const pcre_uint32 *cp; + int len = 1; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + GETCHARLENTEST(c, eptr, len); + cp = PRIV(ucd_caseless_sets) + prop_value; + for (;;) + { + if (c < *cp) + { if (prop_fail_result) break; else goto GOT_MAX; } + if (c == *cp++) + { if (prop_fail_result) goto GOT_MAX; else break; } + } + eptr += len; + } + GOT_MAX: + break; + + case PT_UCNC: + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + GETCHARLENTEST(c, eptr, len); + if ((c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT || + c == CHAR_GRAVE_ACCENT || (c >= 0xa0 && c <= 0xd7ff) || + c >= 0xe000) == prop_fail_result) + break; + eptr += len; + } + break; + + default: + RRETURN(PCRE_ERROR_INTERNAL); + } + + /* eptr is now past the end of the maximum run */ + + if (possessive) continue; /* No backtracking */ + for(;;) + { + if (eptr == pp) goto TAIL_RECURSE; + RMATCH(eptr, ecode, offset_top, md, eptrb, RM44); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + eptr--; + if (utf) BACKCHAR(eptr); + } + } + + /* Match extended Unicode grapheme clusters. We will get here only if the + support is in the binary; otherwise a compile-time error occurs. */ + + else if (ctype == OP_EXTUNI) + { + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + else + { + int lgb, rgb; + GETCHARINCTEST(c, eptr); + lgb = UCD_GRAPHBREAK(c); + while (eptr < md->end_subject) + { + int len = 1; + if (!utf) c = *eptr; else { GETCHARLEN(c, eptr, len); } + rgb = UCD_GRAPHBREAK(c); + if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break; + lgb = rgb; + eptr += len; + } + } + CHECK_PARTIAL(); + } + + /* eptr is now past the end of the maximum run */ + + if (possessive) continue; /* No backtracking */ + + for(;;) + { + int lgb, rgb; + PCRE_PUCHAR fptr; + + if (eptr == pp) goto TAIL_RECURSE; /* At start of char run */ + RMATCH(eptr, ecode, offset_top, md, eptrb, RM45); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + + /* Backtracking over an extended grapheme cluster involves inspecting + the previous two characters (if present) to see if a break is + permitted between them. */ + + eptr--; + if (!utf) c = *eptr; else + { + BACKCHAR(eptr); + GETCHAR(c, eptr); + } + rgb = UCD_GRAPHBREAK(c); + + for (;;) + { + if (eptr == pp) goto TAIL_RECURSE; /* At start of char run */ + fptr = eptr - 1; + if (!utf) c = *fptr; else + { + BACKCHAR(fptr); + GETCHAR(c, fptr); + } + lgb = UCD_GRAPHBREAK(c); + if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break; + eptr = fptr; + rgb = lgb; + } + } + } + + else +#endif /* SUPPORT_UCP */ + +#ifdef SUPPORT_UTF + if (utf) + { + switch(ctype) + { + case OP_ANY: + if (max < INT_MAX) + { + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + if (IS_NEWLINE(eptr)) break; + if (md->partial != 0 && /* Take care with CRLF partial */ + eptr + 1 >= md->end_subject && + NLBLOCK->nltype == NLTYPE_FIXED && + NLBLOCK->nllen == 2 && + UCHAR21(eptr) == NLBLOCK->nl[0]) + { + md->hitend = TRUE; + if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); + } + eptr++; + ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++); + } + } + + /* Handle unlimited UTF-8 repeat */ + + else + { + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + if (IS_NEWLINE(eptr)) break; + if (md->partial != 0 && /* Take care with CRLF partial */ + eptr + 1 >= md->end_subject && + NLBLOCK->nltype == NLTYPE_FIXED && + NLBLOCK->nllen == 2 && + UCHAR21(eptr) == NLBLOCK->nl[0]) + { + md->hitend = TRUE; + if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); + } + eptr++; + ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++); + } + } + break; + + case OP_ALLANY: + if (max < INT_MAX) + { + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + eptr++; + ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++); + } + } + else + { + eptr = md->end_subject; /* Unlimited UTF-8 repeat */ + SCHECK_PARTIAL(); + } + break; + + /* The byte case is the same as non-UTF8 */ + + case OP_ANYBYTE: + c = max - min; + if (c > (unsigned int)(md->end_subject - eptr)) + { + eptr = md->end_subject; + SCHECK_PARTIAL(); + } + else eptr += c; + break; + + case OP_ANYNL: + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + GETCHARLEN(c, eptr, len); + if (c == CHAR_CR) + { + if (++eptr >= md->end_subject) break; + if (UCHAR21(eptr) == CHAR_LF) eptr++; + } + else + { + if (c != CHAR_LF && + (md->bsr_anycrlf || + (c != CHAR_VT && c != CHAR_FF && c != CHAR_NEL +#ifndef EBCDIC + && c != 0x2028 && c != 0x2029 +#endif /* Not EBCDIC */ + ))) + break; + eptr += len; + } + } + break; + + case OP_NOT_HSPACE: + case OP_HSPACE: + for (i = min; i < max; i++) + { + BOOL gotspace; + int len = 1; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + GETCHARLEN(c, eptr, len); + switch(c) + { + HSPACE_CASES: gotspace = TRUE; break; + default: gotspace = FALSE; break; + } + if (gotspace == (ctype == OP_NOT_HSPACE)) break; + eptr += len; + } + break; + + case OP_NOT_VSPACE: + case OP_VSPACE: + for (i = min; i < max; i++) + { + BOOL gotspace; + int len = 1; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + GETCHARLEN(c, eptr, len); + switch(c) + { + VSPACE_CASES: gotspace = TRUE; break; + default: gotspace = FALSE; break; + } + if (gotspace == (ctype == OP_NOT_VSPACE)) break; + eptr += len; + } + break; + + case OP_NOT_DIGIT: + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + GETCHARLEN(c, eptr, len); + if (c < 256 && (md->ctypes[c] & ctype_digit) != 0) break; + eptr+= len; + } + break; + + case OP_DIGIT: + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + GETCHARLEN(c, eptr, len); + if (c >= 256 ||(md->ctypes[c] & ctype_digit) == 0) break; + eptr+= len; + } + break; + + case OP_NOT_WHITESPACE: + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + GETCHARLEN(c, eptr, len); + if (c < 256 && (md->ctypes[c] & ctype_space) != 0) break; + eptr+= len; + } + break; + + case OP_WHITESPACE: + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + GETCHARLEN(c, eptr, len); + if (c >= 256 ||(md->ctypes[c] & ctype_space) == 0) break; + eptr+= len; + } + break; + + case OP_NOT_WORDCHAR: + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + GETCHARLEN(c, eptr, len); + if (c < 256 && (md->ctypes[c] & ctype_word) != 0) break; + eptr+= len; + } + break; + + case OP_WORDCHAR: + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + GETCHARLEN(c, eptr, len); + if (c >= 256 || (md->ctypes[c] & ctype_word) == 0) break; + eptr+= len; + } + break; + + default: + RRETURN(PCRE_ERROR_INTERNAL); + } + + if (possessive) continue; /* No backtracking */ + for(;;) + { + if (eptr == pp) goto TAIL_RECURSE; + RMATCH(eptr, ecode, offset_top, md, eptrb, RM46); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + eptr--; + BACKCHAR(eptr); + if (ctype == OP_ANYNL && eptr > pp && UCHAR21(eptr) == CHAR_NL && + UCHAR21(eptr - 1) == CHAR_CR) eptr--; + } + } + else +#endif /* SUPPORT_UTF */ + /* Not UTF mode */ + { + switch(ctype) + { + case OP_ANY: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + if (IS_NEWLINE(eptr)) break; + if (md->partial != 0 && /* Take care with CRLF partial */ + eptr + 1 >= md->end_subject && + NLBLOCK->nltype == NLTYPE_FIXED && + NLBLOCK->nllen == 2 && + *eptr == NLBLOCK->nl[0]) + { + md->hitend = TRUE; + if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); + } + eptr++; + } + break; + + case OP_ALLANY: + case OP_ANYBYTE: + c = max - min; + if (c > (unsigned int)(md->end_subject - eptr)) + { + eptr = md->end_subject; + SCHECK_PARTIAL(); + } + else eptr += c; + break; + + case OP_ANYNL: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + c = *eptr; + if (c == CHAR_CR) + { + if (++eptr >= md->end_subject) break; + if (*eptr == CHAR_LF) eptr++; + } + else + { + if (c != CHAR_LF && (md->bsr_anycrlf || + (c != CHAR_VT && c != CHAR_FF && c != CHAR_NEL +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + && c != 0x2028 && c != 0x2029 +#endif + ))) break; + eptr++; + } + } + break; + + case OP_NOT_HSPACE: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + switch(*eptr) + { + default: eptr++; break; + HSPACE_BYTE_CASES: +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + HSPACE_MULTIBYTE_CASES: +#endif + goto ENDLOOP00; + } + } + ENDLOOP00: + break; + + case OP_HSPACE: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + switch(*eptr) + { + default: goto ENDLOOP01; + HSPACE_BYTE_CASES: +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + HSPACE_MULTIBYTE_CASES: +#endif + eptr++; break; + } + } + ENDLOOP01: + break; + + case OP_NOT_VSPACE: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + switch(*eptr) + { + default: eptr++; break; + VSPACE_BYTE_CASES: +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + VSPACE_MULTIBYTE_CASES: +#endif + goto ENDLOOP02; + } + } + ENDLOOP02: + break; + + case OP_VSPACE: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + switch(*eptr) + { + default: goto ENDLOOP03; + VSPACE_BYTE_CASES: +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + VSPACE_MULTIBYTE_CASES: +#endif + eptr++; break; + } + } + ENDLOOP03: + break; + + case OP_NOT_DIGIT: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + if (MAX_255(*eptr) && (md->ctypes[*eptr] & ctype_digit) != 0) break; + eptr++; + } + break; + + case OP_DIGIT: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + if (!MAX_255(*eptr) || (md->ctypes[*eptr] & ctype_digit) == 0) break; + eptr++; + } + break; + + case OP_NOT_WHITESPACE: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + if (MAX_255(*eptr) && (md->ctypes[*eptr] & ctype_space) != 0) break; + eptr++; + } + break; + + case OP_WHITESPACE: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + if (!MAX_255(*eptr) || (md->ctypes[*eptr] & ctype_space) == 0) break; + eptr++; + } + break; + + case OP_NOT_WORDCHAR: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + if (MAX_255(*eptr) && (md->ctypes[*eptr] & ctype_word) != 0) break; + eptr++; + } + break; + + case OP_WORDCHAR: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) + { + SCHECK_PARTIAL(); + break; + } + if (!MAX_255(*eptr) || (md->ctypes[*eptr] & ctype_word) == 0) break; + eptr++; + } + break; + + default: + RRETURN(PCRE_ERROR_INTERNAL); + } + + if (possessive) continue; /* No backtracking */ + for (;;) + { + if (eptr == pp) goto TAIL_RECURSE; + RMATCH(eptr, ecode, offset_top, md, eptrb, RM47); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + eptr--; + if (ctype == OP_ANYNL && eptr > pp && *eptr == CHAR_LF && + eptr[-1] == CHAR_CR) eptr--; + } + } + + /* Control never gets here */ + } + + /* There's been some horrible disaster. Arrival here can only mean there is + something seriously wrong in the code above or the OP_xxx definitions. */ + + default: + DPRINTF(("Unknown opcode %d\n", *ecode)); + RRETURN(PCRE_ERROR_UNKNOWN_OPCODE); + } + + /* Do not stick any code in here without much thought; it is assumed + that "continue" in the code above comes out to here to repeat the main + loop. */ + + } /* End of main loop */ +/* Control never reaches here */ + + +/* When compiling to use the heap rather than the stack for recursive calls to +match(), the RRETURN() macro jumps here. The number that is saved in +frame->Xwhere indicates which label we actually want to return to. */ + +#ifdef NO_RECURSE +#define LBL(val) case val: goto L_RM##val; +HEAP_RETURN: +switch (frame->Xwhere) + { + LBL( 1) LBL( 2) LBL( 3) LBL( 4) LBL( 5) LBL( 6) LBL( 7) LBL( 8) + LBL( 9) LBL(10) LBL(11) LBL(12) LBL(13) LBL(14) LBL(15) LBL(17) + LBL(19) LBL(24) LBL(25) LBL(26) LBL(27) LBL(29) LBL(31) LBL(33) + LBL(35) LBL(43) LBL(47) LBL(48) LBL(49) LBL(50) LBL(51) LBL(52) + LBL(53) LBL(54) LBL(55) LBL(56) LBL(57) LBL(58) LBL(63) LBL(64) + LBL(65) LBL(66) +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + LBL(20) LBL(21) +#endif +#ifdef SUPPORT_UTF + LBL(16) LBL(18) + LBL(22) LBL(23) LBL(28) LBL(30) + LBL(32) LBL(34) LBL(42) LBL(46) +#ifdef SUPPORT_UCP + LBL(36) LBL(37) LBL(38) LBL(39) LBL(40) LBL(41) LBL(44) LBL(45) + LBL(59) LBL(60) LBL(61) LBL(62) LBL(67) +#endif /* SUPPORT_UCP */ +#endif /* SUPPORT_UTF */ + default: + DPRINTF(("jump error in pcre match: label %d non-existent\n", frame->Xwhere)); + return PCRE_ERROR_INTERNAL; + } +#undef LBL +#endif /* NO_RECURSE */ +} + + +/*************************************************************************** +**************************************************************************** + RECURSION IN THE match() FUNCTION + +Undefine all the macros that were defined above to handle this. */ + +#ifdef NO_RECURSE +#undef eptr +#undef ecode +#undef mstart +#undef offset_top +#undef eptrb +#undef flags + +#undef callpat +#undef charptr +#undef data +#undef next +#undef pp +#undef prev +#undef saved_eptr + +#undef new_recursive + +#undef cur_is_word +#undef condition +#undef prev_is_word + +#undef ctype +#undef length +#undef max +#undef min +#undef number +#undef offset +#undef op +#undef save_capture_last +#undef save_offset1 +#undef save_offset2 +#undef save_offset3 +#undef stacksave + +#undef newptrb + +#endif + +/* These two are defined as macros in both cases */ + +#undef fc +#undef fi + +/*************************************************************************** +***************************************************************************/ + + +#ifdef NO_RECURSE +/************************************************* +* Release allocated heap frames * +*************************************************/ + +/* This function releases all the allocated frames. The base frame is on the +machine stack, and so must not be freed. + +Argument: the address of the base frame +Returns: nothing +*/ + +static void +release_match_heapframes (heapframe *frame_base) +{ +heapframe *nextframe = frame_base->Xnextframe; +while (nextframe != NULL) + { + heapframe *oldframe = nextframe; + nextframe = nextframe->Xnextframe; + (PUBL(stack_free))(oldframe); + } +} +#endif + + +/************************************************* +* Execute a Regular Expression * +*************************************************/ + +/* This function applies a compiled re to a subject string and picks out +portions of the string if it matches. Two elements in the vector are set for +each substring: the offsets to the start and end of the substring. + +Arguments: + argument_re points to the compiled expression + extra_data points to extra data or is NULL + subject points to the subject string + length length of subject string (may contain binary zeros) + start_offset where to start in the subject string + options option bits + offsets points to a vector of ints to be filled in with offsets + offsetcount the number of elements in the vector + +Returns: > 0 => success; value is the number of elements filled in + = 0 => success, but offsets is not big enough + -1 => failed to match + < -1 => some kind of unexpected problem +*/ + +#if defined COMPILE_PCRE8 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre_exec(const pcre *argument_re, const pcre_extra *extra_data, + PCRE_SPTR subject, int length, int start_offset, int options, int *offsets, + int offsetcount) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre16_exec(const pcre16 *argument_re, const pcre16_extra *extra_data, + PCRE_SPTR16 subject, int length, int start_offset, int options, int *offsets, + int offsetcount) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre32_exec(const pcre32 *argument_re, const pcre32_extra *extra_data, + PCRE_SPTR32 subject, int length, int start_offset, int options, int *offsets, + int offsetcount) +#endif +{ +int rc, ocount, arg_offset_max; +int newline; +BOOL using_temporary_offsets = FALSE; +BOOL anchored; +BOOL startline; +BOOL firstline; +BOOL utf; +BOOL has_first_char = FALSE; +BOOL has_req_char = FALSE; +pcre_uchar first_char = 0; +pcre_uchar first_char2 = 0; +pcre_uchar req_char = 0; +pcre_uchar req_char2 = 0; +match_data match_block; +match_data *md = &match_block; +const pcre_uint8 *tables; +const pcre_uint8 *start_bits = NULL; +PCRE_PUCHAR start_match = (PCRE_PUCHAR)subject + start_offset; +PCRE_PUCHAR end_subject; +PCRE_PUCHAR start_partial = NULL; +PCRE_PUCHAR match_partial = NULL; +PCRE_PUCHAR req_char_ptr = start_match - 1; + +const pcre_study_data *study; +const REAL_PCRE *re = (const REAL_PCRE *)argument_re; + +#ifdef NO_RECURSE +heapframe frame_zero; +frame_zero.Xprevframe = NULL; /* Marks the top level */ +frame_zero.Xnextframe = NULL; /* None are allocated yet */ +md->match_frames_base = &frame_zero; +#endif + +/* Check for the special magic call that measures the size of the stack used +per recursive call of match(). Without the funny casting for sizeof, a Windows +compiler gave this error: "unary minus operator applied to unsigned type, +result still unsigned". Hopefully the cast fixes that. */ + +if (re == NULL && extra_data == NULL && subject == NULL && length == -999 && + start_offset == -999) +#ifdef NO_RECURSE + return -((int)sizeof(heapframe)); +#else + return match(NULL, NULL, NULL, 0, NULL, NULL, 0); +#endif + +/* Plausibility checks */ + +if ((options & ~PUBLIC_EXEC_OPTIONS) != 0) return PCRE_ERROR_BADOPTION; +if (re == NULL || subject == NULL || (offsets == NULL && offsetcount > 0)) + return PCRE_ERROR_NULL; +if (offsetcount < 0) return PCRE_ERROR_BADCOUNT; +if (length < 0) return PCRE_ERROR_BADLENGTH; +if (start_offset < 0 || start_offset > length) return PCRE_ERROR_BADOFFSET; + +/* Check that the first field in the block is the magic number. If it is not, +return with PCRE_ERROR_BADMAGIC. However, if the magic number is equal to +REVERSED_MAGIC_NUMBER we return with PCRE_ERROR_BADENDIANNESS, which +means that the pattern is likely compiled with different endianness. */ + +if (re->magic_number != MAGIC_NUMBER) + return re->magic_number == REVERSED_MAGIC_NUMBER? + PCRE_ERROR_BADENDIANNESS:PCRE_ERROR_BADMAGIC; +if ((re->flags & PCRE_MODE) == 0) return PCRE_ERROR_BADMODE; + +/* These two settings are used in the code for checking a UTF-8 string that +follows immediately afterwards. Other values in the md block are used only +during "normal" pcre_exec() processing, not when the JIT support is in use, +so they are set up later. */ + +/* PCRE_UTF16 has the same value as PCRE_UTF8. */ +utf = md->utf = (re->options & PCRE_UTF8) != 0; +md->partial = ((options & PCRE_PARTIAL_HARD) != 0)? 2 : + ((options & PCRE_PARTIAL_SOFT) != 0)? 1 : 0; + +/* Check a UTF-8 string if required. Pass back the character offset and error +code for an invalid string if a results vector is available. */ + +#ifdef SUPPORT_UTF +if (utf && (options & PCRE_NO_UTF8_CHECK) == 0) + { + int erroroffset; + int errorcode = PRIV(valid_utf)((PCRE_PUCHAR)subject, length, &erroroffset); + if (errorcode != 0) + { + if (offsetcount >= 2) + { + offsets[0] = erroroffset; + offsets[1] = errorcode; + } +#if defined COMPILE_PCRE8 + return (errorcode <= PCRE_UTF8_ERR5 && md->partial > 1)? + PCRE_ERROR_SHORTUTF8 : PCRE_ERROR_BADUTF8; +#elif defined COMPILE_PCRE16 + return (errorcode <= PCRE_UTF16_ERR1 && md->partial > 1)? + PCRE_ERROR_SHORTUTF16 : PCRE_ERROR_BADUTF16; +#elif defined COMPILE_PCRE32 + return PCRE_ERROR_BADUTF32; +#endif + } +#if defined COMPILE_PCRE8 || defined COMPILE_PCRE16 + /* Check that a start_offset points to the start of a UTF character. */ + if (start_offset > 0 && start_offset < length && + NOT_FIRSTCHAR(((PCRE_PUCHAR)subject)[start_offset])) + return PCRE_ERROR_BADUTF8_OFFSET; +#endif + } +#endif + +/* If the pattern was successfully studied with JIT support, run the JIT +executable instead of the rest of this function. Most options must be set at +compile time for the JIT code to be usable. Fallback to the normal code path if +an unsupported flag is set. */ + +#ifdef SUPPORT_JIT +if (extra_data != NULL + && (extra_data->flags & (PCRE_EXTRA_EXECUTABLE_JIT | + PCRE_EXTRA_TABLES)) == PCRE_EXTRA_EXECUTABLE_JIT + && extra_data->executable_jit != NULL + && (options & ~PUBLIC_JIT_EXEC_OPTIONS) == 0) + { + rc = PRIV(jit_exec)(extra_data, (const pcre_uchar *)subject, length, + start_offset, options, offsets, offsetcount); + + /* PCRE_ERROR_NULL means that the selected normal or partial matching + mode is not compiled. In this case we simply fallback to interpreter. */ + + if (rc != PCRE_ERROR_JIT_BADOPTION) return rc; + } +#endif + +/* Carry on with non-JIT matching. This information is for finding all the +numbers associated with a given name, for condition testing. */ + +md->name_table = (pcre_uchar *)re + re->name_table_offset; +md->name_count = re->name_count; +md->name_entry_size = re->name_entry_size; + +/* Fish out the optional data from the extra_data structure, first setting +the default values. */ + +study = NULL; +md->match_limit = MATCH_LIMIT; +md->match_limit_recursion = MATCH_LIMIT_RECURSION; +md->callout_data = NULL; + +/* The table pointer is always in native byte order. */ + +tables = re->tables; + +/* The two limit values override the defaults, whatever their value. */ + +if (extra_data != NULL) + { + register unsigned int flags = extra_data->flags; + if ((flags & PCRE_EXTRA_STUDY_DATA) != 0) + study = (const pcre_study_data *)extra_data->study_data; + if ((flags & PCRE_EXTRA_MATCH_LIMIT) != 0) + md->match_limit = extra_data->match_limit; + if ((flags & PCRE_EXTRA_MATCH_LIMIT_RECURSION) != 0) + md->match_limit_recursion = extra_data->match_limit_recursion; + if ((flags & PCRE_EXTRA_CALLOUT_DATA) != 0) + md->callout_data = extra_data->callout_data; + if ((flags & PCRE_EXTRA_TABLES) != 0) tables = extra_data->tables; + } + +/* Limits in the regex override only if they are smaller. */ + +if ((re->flags & PCRE_MLSET) != 0 && re->limit_match < md->match_limit) + md->match_limit = re->limit_match; + +if ((re->flags & PCRE_RLSET) != 0 && + re->limit_recursion < md->match_limit_recursion) + md->match_limit_recursion = re->limit_recursion; + +/* If the exec call supplied NULL for tables, use the inbuilt ones. This +is a feature that makes it possible to save compiled regex and re-use them +in other programs later. */ + +if (tables == NULL) tables = PRIV(default_tables); + +/* Set up other data */ + +anchored = ((re->options | options) & PCRE_ANCHORED) != 0; +startline = (re->flags & PCRE_STARTLINE) != 0; +firstline = (re->options & PCRE_FIRSTLINE) != 0; + +/* The code starts after the real_pcre block and the capture name table. */ + +md->start_code = (const pcre_uchar *)re + re->name_table_offset + + re->name_count * re->name_entry_size; + +md->start_subject = (PCRE_PUCHAR)subject; +md->start_offset = start_offset; +md->end_subject = md->start_subject + length; +end_subject = md->end_subject; + +md->endonly = (re->options & PCRE_DOLLAR_ENDONLY) != 0; +md->use_ucp = (re->options & PCRE_UCP) != 0; +md->jscript_compat = (re->options & PCRE_JAVASCRIPT_COMPAT) != 0; +md->ignore_skip_arg = 0; + +/* Some options are unpacked into BOOL variables in the hope that testing +them will be faster than individual option bits. */ + +md->notbol = (options & PCRE_NOTBOL) != 0; +md->noteol = (options & PCRE_NOTEOL) != 0; +md->notempty = (options & PCRE_NOTEMPTY) != 0; +md->notempty_atstart = (options & PCRE_NOTEMPTY_ATSTART) != 0; + +md->hitend = FALSE; +md->mark = md->nomatch_mark = NULL; /* In case never set */ + +md->recursive = NULL; /* No recursion at top level */ +md->hasthen = (re->flags & PCRE_HASTHEN) != 0; + +md->lcc = tables + lcc_offset; +md->fcc = tables + fcc_offset; +md->ctypes = tables + ctypes_offset; + +/* Handle different \R options. */ + +switch (options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) + { + case 0: + if ((re->options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) != 0) + md->bsr_anycrlf = (re->options & PCRE_BSR_ANYCRLF) != 0; + else +#ifdef BSR_ANYCRLF + md->bsr_anycrlf = TRUE; +#else + md->bsr_anycrlf = FALSE; +#endif + break; + + case PCRE_BSR_ANYCRLF: + md->bsr_anycrlf = TRUE; + break; + + case PCRE_BSR_UNICODE: + md->bsr_anycrlf = FALSE; + break; + + default: return PCRE_ERROR_BADNEWLINE; + } + +/* Handle different types of newline. The three bits give eight cases. If +nothing is set at run time, whatever was used at compile time applies. */ + +switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options : + (pcre_uint32)options) & PCRE_NEWLINE_BITS) + { + case 0: newline = NEWLINE; break; /* Compile-time default */ + case PCRE_NEWLINE_CR: newline = CHAR_CR; break; + case PCRE_NEWLINE_LF: newline = CHAR_NL; break; + case PCRE_NEWLINE_CR+ + PCRE_NEWLINE_LF: newline = (CHAR_CR << 8) | CHAR_NL; break; + case PCRE_NEWLINE_ANY: newline = -1; break; + case PCRE_NEWLINE_ANYCRLF: newline = -2; break; + default: return PCRE_ERROR_BADNEWLINE; + } + +if (newline == -2) + { + md->nltype = NLTYPE_ANYCRLF; + } +else if (newline < 0) + { + md->nltype = NLTYPE_ANY; + } +else + { + md->nltype = NLTYPE_FIXED; + if (newline > 255) + { + md->nllen = 2; + md->nl[0] = (newline >> 8) & 255; + md->nl[1] = newline & 255; + } + else + { + md->nllen = 1; + md->nl[0] = newline; + } + } + +/* Partial matching was originally supported only for a restricted set of +regexes; from release 8.00 there are no restrictions, but the bits are still +defined (though never set). So there's no harm in leaving this code. */ + +if (md->partial && (re->flags & PCRE_NOPARTIAL) != 0) + return PCRE_ERROR_BADPARTIAL; + +/* If the expression has got more back references than the offsets supplied can +hold, we get a temporary chunk of working store to use during the matching. +Otherwise, we can use the vector supplied, rounding down its size to a multiple +of 3. */ + +ocount = offsetcount - (offsetcount % 3); +arg_offset_max = (2*ocount)/3; + +if (re->top_backref > 0 && re->top_backref >= ocount/3) + { + ocount = re->top_backref * 3 + 3; + md->offset_vector = (int *)(PUBL(malloc))(ocount * sizeof(int)); + if (md->offset_vector == NULL) return PCRE_ERROR_NOMEMORY; + using_temporary_offsets = TRUE; + DPRINTF(("Got memory to hold back references\n")); + } +else md->offset_vector = offsets; +md->offset_end = ocount; +md->offset_max = (2*ocount)/3; +md->capture_last = 0; + +/* Reset the working variable associated with each extraction. These should +never be used unless previously set, but they get saved and restored, and so we +initialize them to avoid reading uninitialized locations. Also, unset the +offsets for the matched string. This is really just for tidiness with callouts, +in case they inspect these fields. */ + +if (md->offset_vector != NULL) + { + register int *iptr = md->offset_vector + ocount; + register int *iend = iptr - re->top_bracket; + if (iend < md->offset_vector + 2) iend = md->offset_vector + 2; + while (--iptr >= iend) *iptr = -1; + md->offset_vector[0] = md->offset_vector[1] = -1; + } + +/* Set up the first character to match, if available. The first_char value is +never set for an anchored regular expression, but the anchoring may be forced +at run time, so we have to test for anchoring. The first char may be unset for +an unanchored pattern, of course. If there's no first char and the pattern was +studied, there may be a bitmap of possible first characters. */ + +if (!anchored) + { + if ((re->flags & PCRE_FIRSTSET) != 0) + { + has_first_char = TRUE; + first_char = first_char2 = (pcre_uchar)(re->first_char); + if ((re->flags & PCRE_FCH_CASELESS) != 0) + { + first_char2 = TABLE_GET(first_char, md->fcc, first_char); +#if defined SUPPORT_UCP && !(defined COMPILE_PCRE8) + if (utf && first_char > 127) + first_char2 = UCD_OTHERCASE(first_char); +#endif + } + } + else + if (!startline && study != NULL && + (study->flags & PCRE_STUDY_MAPPED) != 0) + start_bits = study->start_bits; + } + +/* For anchored or unanchored matches, there may be a "last known required +character" set. */ + +if ((re->flags & PCRE_REQCHSET) != 0) + { + has_req_char = TRUE; + req_char = req_char2 = (pcre_uchar)(re->req_char); + if ((re->flags & PCRE_RCH_CASELESS) != 0) + { + req_char2 = TABLE_GET(req_char, md->fcc, req_char); +#if defined SUPPORT_UCP && !(defined COMPILE_PCRE8) + if (utf && req_char > 127) + req_char2 = UCD_OTHERCASE(req_char); +#endif + } + } + + +/* ==========================================================================*/ + +/* Loop for handling unanchored repeated matching attempts; for anchored regexs +the loop runs just once. */ + +for(;;) + { + PCRE_PUCHAR save_end_subject = end_subject; + PCRE_PUCHAR new_start_match; + + /* If firstline is TRUE, the start of the match is constrained to the first + line of a multiline string. That is, the match must be before or at the first + newline. Implement this by temporarily adjusting end_subject so that we stop + scanning at a newline. If the match fails at the newline, later code breaks + this loop. */ + + if (firstline) + { + PCRE_PUCHAR t = start_match; +#ifdef SUPPORT_UTF + if (utf) + { + while (t < md->end_subject && !IS_NEWLINE(t)) + { + t++; + ACROSSCHAR(t < end_subject, *t, t++); + } + } + else +#endif + while (t < md->end_subject && !IS_NEWLINE(t)) t++; + end_subject = t; + } + + /* There are some optimizations that avoid running the match if a known + starting point is not found, or if a known later character is not present. + However, there is an option that disables these, for testing and for ensuring + that all callouts do actually occur. The option can be set in the regex by + (*NO_START_OPT) or passed in match-time options. */ + + if (((options | re->options) & PCRE_NO_START_OPTIMIZE) == 0) + { + /* Advance to a unique first char if there is one. */ + + if (has_first_char) + { + pcre_uchar smc; + + if (first_char != first_char2) + while (start_match < end_subject && + (smc = UCHAR21TEST(start_match)) != first_char && smc != first_char2) + start_match++; + else + while (start_match < end_subject && UCHAR21TEST(start_match) != first_char) + start_match++; + } + + /* Or to just after a linebreak for a multiline match */ + + else if (startline) + { + if (start_match > md->start_subject + start_offset) + { +#ifdef SUPPORT_UTF + if (utf) + { + while (start_match < end_subject && !WAS_NEWLINE(start_match)) + { + start_match++; + ACROSSCHAR(start_match < end_subject, *start_match, + start_match++); + } + } + else +#endif + while (start_match < end_subject && !WAS_NEWLINE(start_match)) + start_match++; + + /* If we have just passed a CR and the newline option is ANY or ANYCRLF, + and we are now at a LF, advance the match position by one more character. + */ + + if (start_match[-1] == CHAR_CR && + (md->nltype == NLTYPE_ANY || md->nltype == NLTYPE_ANYCRLF) && + start_match < end_subject && + UCHAR21TEST(start_match) == CHAR_NL) + start_match++; + } + } + + /* Or to a non-unique first byte after study */ + + else if (start_bits != NULL) + { + while (start_match < end_subject) + { + register pcre_uint32 c = UCHAR21TEST(start_match); +#ifndef COMPILE_PCRE8 + if (c > 255) c = 255; +#endif + if ((start_bits[c/8] & (1 << (c&7))) != 0) break; + start_match++; + } + } + } /* Starting optimizations */ + + /* Restore fudged end_subject */ + + end_subject = save_end_subject; + + /* The following two optimizations are disabled for partial matching or if + disabling is explicitly requested. */ + + if (((options | re->options) & PCRE_NO_START_OPTIMIZE) == 0 && !md->partial) + { + /* If the pattern was studied, a minimum subject length may be set. This is + a lower bound; no actual string of that length may actually match the + pattern. Although the value is, strictly, in characters, we treat it as + bytes to avoid spending too much time in this optimization. */ + + if (study != NULL && (study->flags & PCRE_STUDY_MINLEN) != 0 && + (pcre_uint32)(end_subject - start_match) < study->minlength) + { + rc = MATCH_NOMATCH; + break; + } + + /* If req_char is set, we know that that character must appear in the + subject for the match to succeed. If the first character is set, req_char + must be later in the subject; otherwise the test starts at the match point. + This optimization can save a huge amount of backtracking in patterns with + nested unlimited repeats that aren't going to match. Writing separate code + for cased/caseless versions makes it go faster, as does using an + autoincrement and backing off on a match. + + HOWEVER: when the subject string is very, very long, searching to its end + can take a long time, and give bad performance on quite ordinary patterns. + This showed up when somebody was matching something like /^\d+C/ on a + 32-megabyte string... so we don't do this when the string is sufficiently + long. */ + + if (has_req_char && end_subject - start_match < REQ_BYTE_MAX) + { + register PCRE_PUCHAR p = start_match + (has_first_char? 1:0); + + /* We don't need to repeat the search if we haven't yet reached the + place we found it at last time. */ + + if (p > req_char_ptr) + { + if (req_char != req_char2) + { + while (p < end_subject) + { + register pcre_uint32 pp = UCHAR21INCTEST(p); + if (pp == req_char || pp == req_char2) { p--; break; } + } + } + else + { + while (p < end_subject) + { + if (UCHAR21INCTEST(p) == req_char) { p--; break; } + } + } + + /* If we can't find the required character, break the matching loop, + forcing a match failure. */ + + if (p >= end_subject) + { + rc = MATCH_NOMATCH; + break; + } + + /* If we have found the required character, save the point where we + found it, so that we don't search again next time round the loop if + the start hasn't passed this character yet. */ + + req_char_ptr = p; + } + } + } + +#ifdef PCRE_DEBUG /* Sigh. Some compilers never learn. */ + printf(">>>> Match against: "); + pchars(start_match, end_subject - start_match, TRUE, md); + printf("\n"); +#endif + + /* OK, we can now run the match. If "hitend" is set afterwards, remember the + first starting point for which a partial match was found. */ + + md->start_match_ptr = start_match; + md->start_used_ptr = start_match; + md->match_call_count = 0; + md->match_function_type = 0; + md->end_offset_top = 0; + md->skip_arg_count = 0; + rc = match(start_match, md->start_code, start_match, 2, md, NULL, 0); + if (md->hitend && start_partial == NULL) + { + start_partial = md->start_used_ptr; + match_partial = start_match; + } + + switch(rc) + { + /* If MATCH_SKIP_ARG reaches this level it means that a MARK that matched + the SKIP's arg was not found. In this circumstance, Perl ignores the SKIP + entirely. The only way we can do that is to re-do the match at the same + point, with a flag to force SKIP with an argument to be ignored. Just + treating this case as NOMATCH does not work because it does not check other + alternatives in patterns such as A(*SKIP:A)B|AC when the subject is AC. */ + + case MATCH_SKIP_ARG: + new_start_match = start_match; + md->ignore_skip_arg = md->skip_arg_count; + break; + + /* SKIP passes back the next starting point explicitly, but if it is no + greater than the match we have just done, treat it as NOMATCH. */ + + case MATCH_SKIP: + if (md->start_match_ptr > start_match) + { + new_start_match = md->start_match_ptr; + break; + } + /* Fall through */ + + /* NOMATCH and PRUNE advance by one character. THEN at this level acts + exactly like PRUNE. Unset ignore SKIP-with-argument. */ + + case MATCH_NOMATCH: + case MATCH_PRUNE: + case MATCH_THEN: + md->ignore_skip_arg = 0; + new_start_match = start_match + 1; +#ifdef SUPPORT_UTF + if (utf) + ACROSSCHAR(new_start_match < end_subject, *new_start_match, + new_start_match++); +#endif + break; + + /* COMMIT disables the bumpalong, but otherwise behaves as NOMATCH. */ + + case MATCH_COMMIT: + rc = MATCH_NOMATCH; + goto ENDLOOP; + + /* Any other return is either a match, or some kind of error. */ + + default: + goto ENDLOOP; + } + + /* Control reaches here for the various types of "no match at this point" + result. Reset the code to MATCH_NOMATCH for subsequent checking. */ + + rc = MATCH_NOMATCH; + + /* If PCRE_FIRSTLINE is set, the match must happen before or at the first + newline in the subject (though it may continue over the newline). Therefore, + if we have just failed to match, starting at a newline, do not continue. */ + + if (firstline && IS_NEWLINE(start_match)) break; + + /* Advance to new matching position */ + + start_match = new_start_match; + + /* Break the loop if the pattern is anchored or if we have passed the end of + the subject. */ + + if (anchored || start_match > end_subject) break; + + /* If we have just passed a CR and we are now at a LF, and the pattern does + not contain any explicit matches for \r or \n, and the newline option is CRLF + or ANY or ANYCRLF, advance the match position by one more character. In + normal matching start_match will aways be greater than the first position at + this stage, but a failed *SKIP can cause a return at the same point, which is + why the first test exists. */ + + if (start_match > (PCRE_PUCHAR)subject + start_offset && + start_match[-1] == CHAR_CR && + start_match < end_subject && + *start_match == CHAR_NL && + (re->flags & PCRE_HASCRORLF) == 0 && + (md->nltype == NLTYPE_ANY || + md->nltype == NLTYPE_ANYCRLF || + md->nllen == 2)) + start_match++; + + md->mark = NULL; /* Reset for start of next match attempt */ + } /* End of for(;;) "bumpalong" loop */ + +/* ==========================================================================*/ + +/* We reach here when rc is not MATCH_NOMATCH, or if one of the stopping +conditions is true: + +(1) The pattern is anchored or the match was failed by (*COMMIT); + +(2) We are past the end of the subject; + +(3) PCRE_FIRSTLINE is set and we have failed to match at a newline, because + this option requests that a match occur at or before the first newline in + the subject. + +When we have a match and the offset vector is big enough to deal with any +backreferences, captured substring offsets will already be set up. In the case +where we had to get some local store to hold offsets for backreference +processing, copy those that we can. In this case there need not be overflow if +certain parts of the pattern were not used, even though there are more +capturing parentheses than vector slots. */ + +ENDLOOP: + +if (rc == MATCH_MATCH || rc == MATCH_ACCEPT) + { + if (using_temporary_offsets) + { + if (arg_offset_max >= 4) + { + memcpy(offsets + 2, md->offset_vector + 2, + (arg_offset_max - 2) * sizeof(int)); + DPRINTF(("Copied offsets from temporary memory\n")); + } + if (md->end_offset_top > arg_offset_max) md->capture_last |= OVFLBIT; + DPRINTF(("Freeing temporary memory\n")); + (PUBL(free))(md->offset_vector); + } + + /* Set the return code to the number of captured strings, or 0 if there were + too many to fit into the vector. */ + + rc = ((md->capture_last & OVFLBIT) != 0 && + md->end_offset_top >= arg_offset_max)? + 0 : md->end_offset_top/2; + + /* If there is space in the offset vector, set any unused pairs at the end of + the pattern to -1 for backwards compatibility. It is documented that this + happens. In earlier versions, the whole set of potential capturing offsets + was set to -1 each time round the loop, but this is handled differently now. + "Gaps" are set to -1 dynamically instead (this fixes a bug). Thus, it is only + those at the end that need unsetting here. We can't just unset them all at + the start of the whole thing because they may get set in one branch that is + not the final matching branch. */ + + if (md->end_offset_top/2 <= re->top_bracket && offsets != NULL) + { + register int *iptr, *iend; + int resetcount = 2 + re->top_bracket * 2; + if (resetcount > offsetcount) resetcount = offsetcount; + iptr = offsets + md->end_offset_top; + iend = offsets + resetcount; + while (iptr < iend) *iptr++ = -1; + } + + /* If there is space, set up the whole thing as substring 0. The value of + md->start_match_ptr might be modified if \K was encountered on the success + matching path. */ + + if (offsetcount < 2) rc = 0; else + { + offsets[0] = (int)(md->start_match_ptr - md->start_subject); + offsets[1] = (int)(md->end_match_ptr - md->start_subject); + } + + /* Return MARK data if requested */ + + if (extra_data != NULL && (extra_data->flags & PCRE_EXTRA_MARK) != 0) + *(extra_data->mark) = (pcre_uchar *)md->mark; + DPRINTF((">>>> returning %d\n", rc)); +#ifdef NO_RECURSE + release_match_heapframes(&frame_zero); +#endif + return rc; + } + +/* Control gets here if there has been an error, or if the overall match +attempt has failed at all permitted starting positions. */ + +if (using_temporary_offsets) + { + DPRINTF(("Freeing temporary memory\n")); + (PUBL(free))(md->offset_vector); + } + +/* For anything other than nomatch or partial match, just return the code. */ + +if (rc != MATCH_NOMATCH && rc != PCRE_ERROR_PARTIAL) + { + DPRINTF((">>>> error: returning %d\n", rc)); +#ifdef NO_RECURSE + release_match_heapframes(&frame_zero); +#endif + return rc; + } + +/* Handle partial matches - disable any mark data */ + +if (match_partial != NULL) + { + DPRINTF((">>>> returning PCRE_ERROR_PARTIAL\n")); + md->mark = NULL; + if (offsetcount > 1) + { + offsets[0] = (int)(start_partial - (PCRE_PUCHAR)subject); + offsets[1] = (int)(end_subject - (PCRE_PUCHAR)subject); + if (offsetcount > 2) + offsets[2] = (int)(match_partial - (PCRE_PUCHAR)subject); + } + rc = PCRE_ERROR_PARTIAL; + } + +/* This is the classic nomatch case */ + +else + { + DPRINTF((">>>> returning PCRE_ERROR_NOMATCH\n")); + rc = PCRE_ERROR_NOMATCH; + } + +/* Return the MARK data if it has been requested. */ + +if (extra_data != NULL && (extra_data->flags & PCRE_EXTRA_MARK) != 0) + *(extra_data->mark) = (pcre_uchar *)md->nomatch_mark; +#ifdef NO_RECURSE + release_match_heapframes(&frame_zero); +#endif +return rc; +} + +/* End of pcre_exec.c */ diff --git a/plugins/Pcre16/src/pcre_fullinfo.c b/plugins/Pcre16/src/pcre_fullinfo.c new file mode 100644 index 0000000000..a6c2ece6ca --- /dev/null +++ b/plugins/Pcre16/src/pcre_fullinfo.c @@ -0,0 +1,245 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2013 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains the external function pcre_fullinfo(), which returns +information about a compiled pattern. */ + + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#include "pcre_internal.h" + + +/************************************************* +* Return info about compiled pattern * +*************************************************/ + +/* This is a newer "info" function which has an extensible interface so +that additional items can be added compatibly. + +Arguments: + argument_re points to compiled code + extra_data points extra data, or NULL + what what information is required + where where to put the information + +Returns: 0 if data returned, negative on error +*/ + +#if defined COMPILE_PCRE8 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre_fullinfo(const pcre *argument_re, const pcre_extra *extra_data, + int what, void *where) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre16_fullinfo(const pcre16 *argument_re, const pcre16_extra *extra_data, + int what, void *where) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre32_fullinfo(const pcre32 *argument_re, const pcre32_extra *extra_data, + int what, void *where) +#endif +{ +const REAL_PCRE *re = (const REAL_PCRE *)argument_re; +const pcre_study_data *study = NULL; + +if (re == NULL || where == NULL) return PCRE_ERROR_NULL; + +if (extra_data != NULL && (extra_data->flags & PCRE_EXTRA_STUDY_DATA) != 0) + study = (const pcre_study_data *)extra_data->study_data; + +/* Check that the first field in the block is the magic number. If it is not, +return with PCRE_ERROR_BADMAGIC. However, if the magic number is equal to +REVERSED_MAGIC_NUMBER we return with PCRE_ERROR_BADENDIANNESS, which +means that the pattern is likely compiled with different endianness. */ + +if (re->magic_number != MAGIC_NUMBER) + return re->magic_number == REVERSED_MAGIC_NUMBER? + PCRE_ERROR_BADENDIANNESS:PCRE_ERROR_BADMAGIC; + +/* Check that this pattern was compiled in the correct bit mode */ + +if ((re->flags & PCRE_MODE) == 0) return PCRE_ERROR_BADMODE; + +switch (what) + { + case PCRE_INFO_OPTIONS: + *((unsigned long int *)where) = re->options & PUBLIC_COMPILE_OPTIONS; + break; + + case PCRE_INFO_SIZE: + *((size_t *)where) = re->size; + break; + + case PCRE_INFO_STUDYSIZE: + *((size_t *)where) = (study == NULL)? 0 : study->size; + break; + + case PCRE_INFO_JITSIZE: +#ifdef SUPPORT_JIT + *((size_t *)where) = + (extra_data != NULL && + (extra_data->flags & PCRE_EXTRA_EXECUTABLE_JIT) != 0 && + extra_data->executable_jit != NULL)? + PRIV(jit_get_size)(extra_data->executable_jit) : 0; +#else + *((size_t *)where) = 0; +#endif + break; + + case PCRE_INFO_CAPTURECOUNT: + *((int *)where) = re->top_bracket; + break; + + case PCRE_INFO_BACKREFMAX: + *((int *)where) = re->top_backref; + break; + + case PCRE_INFO_FIRSTBYTE: + *((int *)where) = + ((re->flags & PCRE_FIRSTSET) != 0)? (int)re->first_char : + ((re->flags & PCRE_STARTLINE) != 0)? -1 : -2; + break; + + case PCRE_INFO_FIRSTCHARACTER: + *((pcre_uint32 *)where) = + (re->flags & PCRE_FIRSTSET) != 0 ? re->first_char : 0; + break; + + case PCRE_INFO_FIRSTCHARACTERFLAGS: + *((int *)where) = + ((re->flags & PCRE_FIRSTSET) != 0) ? 1 : + ((re->flags & PCRE_STARTLINE) != 0) ? 2 : 0; + break; + + /* Make sure we pass back the pointer to the bit vector in the external + block, not the internal copy (with flipped integer fields). */ + + case PCRE_INFO_FIRSTTABLE: + *((const pcre_uint8 **)where) = + (study != NULL && (study->flags & PCRE_STUDY_MAPPED) != 0)? + ((const pcre_study_data *)extra_data->study_data)->start_bits : NULL; + break; + + case PCRE_INFO_MINLENGTH: + *((int *)where) = + (study != NULL && (study->flags & PCRE_STUDY_MINLEN) != 0)? + (int)(study->minlength) : -1; + break; + + case PCRE_INFO_JIT: + *((int *)where) = extra_data != NULL && + (extra_data->flags & PCRE_EXTRA_EXECUTABLE_JIT) != 0 && + extra_data->executable_jit != NULL; + break; + + case PCRE_INFO_LASTLITERAL: + *((int *)where) = + ((re->flags & PCRE_REQCHSET) != 0)? (int)re->req_char : -1; + break; + + case PCRE_INFO_REQUIREDCHAR: + *((pcre_uint32 *)where) = + ((re->flags & PCRE_REQCHSET) != 0) ? re->req_char : 0; + break; + + case PCRE_INFO_REQUIREDCHARFLAGS: + *((int *)where) = + ((re->flags & PCRE_REQCHSET) != 0); + break; + + case PCRE_INFO_NAMEENTRYSIZE: + *((int *)where) = re->name_entry_size; + break; + + case PCRE_INFO_NAMECOUNT: + *((int *)where) = re->name_count; + break; + + case PCRE_INFO_NAMETABLE: + *((const pcre_uchar **)where) = (const pcre_uchar *)re + re->name_table_offset; + break; + + case PCRE_INFO_DEFAULT_TABLES: + *((const pcre_uint8 **)where) = (const pcre_uint8 *)(PRIV(default_tables)); + break; + + /* From release 8.00 this will always return TRUE because NOPARTIAL is + no longer ever set (the restrictions have been removed). */ + + case PCRE_INFO_OKPARTIAL: + *((int *)where) = (re->flags & PCRE_NOPARTIAL) == 0; + break; + + case PCRE_INFO_JCHANGED: + *((int *)where) = (re->flags & PCRE_JCHANGED) != 0; + break; + + case PCRE_INFO_HASCRORLF: + *((int *)where) = (re->flags & PCRE_HASCRORLF) != 0; + break; + + case PCRE_INFO_MAXLOOKBEHIND: + *((int *)where) = re->max_lookbehind; + break; + + case PCRE_INFO_MATCHLIMIT: + if ((re->flags & PCRE_MLSET) == 0) return PCRE_ERROR_UNSET; + *((pcre_uint32 *)where) = re->limit_match; + break; + + case PCRE_INFO_RECURSIONLIMIT: + if ((re->flags & PCRE_RLSET) == 0) return PCRE_ERROR_UNSET; + *((pcre_uint32 *)where) = re->limit_recursion; + break; + + case PCRE_INFO_MATCH_EMPTY: + *((int *)where) = (re->flags & PCRE_MATCH_EMPTY) != 0; + break; + + default: return PCRE_ERROR_BADOPTION; + } + +return 0; +} + +/* End of pcre_fullinfo.c */ diff --git a/plugins/Pcre16/src/pcre_get.c b/plugins/Pcre16/src/pcre_get.c new file mode 100644 index 0000000000..8094b34bbf --- /dev/null +++ b/plugins/Pcre16/src/pcre_get.c @@ -0,0 +1,662 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains some convenience functions for extracting substrings +from the subject string after a regex match has succeeded. The original idea +for these functions came from Scott Wimer. */ + + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#include "pcre_internal.h" + + +/************************************************* +* Find number for named string * +*************************************************/ + +/* This function is used by the get_first_set() function below, as well +as being generally available. It assumes that names are unique. + +Arguments: + code the compiled regex + stringname the name whose number is required + +Returns: the number of the named parentheses, or a negative number + (PCRE_ERROR_NOSUBSTRING) if not found +*/ + +#if defined COMPILE_PCRE8 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre_get_stringnumber(const pcre *code, const char *stringname) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre16_get_stringnumber(const pcre16 *code, PCRE_SPTR16 stringname) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre32_get_stringnumber(const pcre32 *code, PCRE_SPTR32 stringname) +#endif +{ +int rc; +int entrysize; +int top, bot; +pcre_uchar *nametable; + +#ifdef COMPILE_PCRE8 +if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0) + return rc; +if (top <= 0) return PCRE_ERROR_NOSUBSTRING; + +if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0) + return rc; +if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0) + return rc; +#endif +#ifdef COMPILE_PCRE16 +if ((rc = pcre16_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0) + return rc; +if (top <= 0) return PCRE_ERROR_NOSUBSTRING; + +if ((rc = pcre16_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0) + return rc; +if ((rc = pcre16_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0) + return rc; +#endif +#ifdef COMPILE_PCRE32 +if ((rc = pcre32_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0) + return rc; +if (top <= 0) return PCRE_ERROR_NOSUBSTRING; + +if ((rc = pcre32_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0) + return rc; +if ((rc = pcre32_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0) + return rc; +#endif + +bot = 0; +while (top > bot) + { + int mid = (top + bot) / 2; + pcre_uchar *entry = nametable + entrysize*mid; + int c = STRCMP_UC_UC((pcre_uchar *)stringname, + (pcre_uchar *)(entry + IMM2_SIZE)); + if (c == 0) return GET2(entry, 0); + if (c > 0) bot = mid + 1; else top = mid; + } + +return PCRE_ERROR_NOSUBSTRING; +} + + + +/************************************************* +* Find (multiple) entries for named string * +*************************************************/ + +/* This is used by the get_first_set() function below, as well as being +generally available. It is used when duplicated names are permitted. + +Arguments: + code the compiled regex + stringname the name whose entries required + firstptr where to put the pointer to the first entry + lastptr where to put the pointer to the last entry + +Returns: the length of each entry, or a negative number + (PCRE_ERROR_NOSUBSTRING) if not found +*/ + +#if defined COMPILE_PCRE8 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre_get_stringtable_entries(const pcre *code, const char *stringname, + char **firstptr, char **lastptr) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre16_get_stringtable_entries(const pcre16 *code, PCRE_SPTR16 stringname, + PCRE_UCHAR16 **firstptr, PCRE_UCHAR16 **lastptr) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre32_get_stringtable_entries(const pcre32 *code, PCRE_SPTR32 stringname, + PCRE_UCHAR32 **firstptr, PCRE_UCHAR32 **lastptr) +#endif +{ +int rc; +int entrysize; +int top, bot; +pcre_uchar *nametable, *lastentry; + +#ifdef COMPILE_PCRE8 +if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0) + return rc; +if (top <= 0) return PCRE_ERROR_NOSUBSTRING; + +if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0) + return rc; +if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0) + return rc; +#endif +#ifdef COMPILE_PCRE16 +if ((rc = pcre16_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0) + return rc; +if (top <= 0) return PCRE_ERROR_NOSUBSTRING; + +if ((rc = pcre16_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0) + return rc; +if ((rc = pcre16_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0) + return rc; +#endif +#ifdef COMPILE_PCRE32 +if ((rc = pcre32_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0) + return rc; +if (top <= 0) return PCRE_ERROR_NOSUBSTRING; + +if ((rc = pcre32_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0) + return rc; +if ((rc = pcre32_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0) + return rc; +#endif + +lastentry = nametable + entrysize * (top - 1); +bot = 0; +while (top > bot) + { + int mid = (top + bot) / 2; + pcre_uchar *entry = nametable + entrysize*mid; + int c = STRCMP_UC_UC((pcre_uchar *)stringname, + (pcre_uchar *)(entry + IMM2_SIZE)); + if (c == 0) + { + pcre_uchar *first = entry; + pcre_uchar *last = entry; + while (first > nametable) + { + if (STRCMP_UC_UC((pcre_uchar *)stringname, + (pcre_uchar *)(first - entrysize + IMM2_SIZE)) != 0) break; + first -= entrysize; + } + while (last < lastentry) + { + if (STRCMP_UC_UC((pcre_uchar *)stringname, + (pcre_uchar *)(last + entrysize + IMM2_SIZE)) != 0) break; + last += entrysize; + } +#if defined COMPILE_PCRE8 + *firstptr = (char *)first; + *lastptr = (char *)last; +#elif defined COMPILE_PCRE16 + *firstptr = (PCRE_UCHAR16 *)first; + *lastptr = (PCRE_UCHAR16 *)last; +#elif defined COMPILE_PCRE32 + *firstptr = (PCRE_UCHAR32 *)first; + *lastptr = (PCRE_UCHAR32 *)last; +#endif + return entrysize; + } + if (c > 0) bot = mid + 1; else top = mid; + } + +return PCRE_ERROR_NOSUBSTRING; +} + + + +/************************************************* +* Find first set of multiple named strings * +*************************************************/ + +/* This function allows for duplicate names in the table of named substrings. +It returns the number of the first one that was set in a pattern match. + +Arguments: + code the compiled regex + stringname the name of the capturing substring + ovector the vector of matched substrings + +Returns: the number of the first that is set, + or the number of the last one if none are set, + or a negative number on error +*/ + +#if defined COMPILE_PCRE8 +static int +get_first_set(const pcre *code, const char *stringname, int *ovector) +#elif defined COMPILE_PCRE16 +static int +get_first_set(const pcre16 *code, PCRE_SPTR16 stringname, int *ovector) +#elif defined COMPILE_PCRE32 +static int +get_first_set(const pcre32 *code, PCRE_SPTR32 stringname, int *ovector) +#endif +{ +const REAL_PCRE *re = (const REAL_PCRE *)code; +int entrysize; +pcre_uchar *entry; +#if defined COMPILE_PCRE8 +char *first, *last; +#elif defined COMPILE_PCRE16 +PCRE_UCHAR16 *first, *last; +#elif defined COMPILE_PCRE32 +PCRE_UCHAR32 *first, *last; +#endif + +#if defined COMPILE_PCRE8 +if ((re->options & PCRE_DUPNAMES) == 0 && (re->flags & PCRE_JCHANGED) == 0) + return pcre_get_stringnumber(code, stringname); +entrysize = pcre_get_stringtable_entries(code, stringname, &first, &last); +#elif defined COMPILE_PCRE16 +if ((re->options & PCRE_DUPNAMES) == 0 && (re->flags & PCRE_JCHANGED) == 0) + return pcre16_get_stringnumber(code, stringname); +entrysize = pcre16_get_stringtable_entries(code, stringname, &first, &last); +#elif defined COMPILE_PCRE32 +if ((re->options & PCRE_DUPNAMES) == 0 && (re->flags & PCRE_JCHANGED) == 0) + return pcre32_get_stringnumber(code, stringname); +entrysize = pcre32_get_stringtable_entries(code, stringname, &first, &last); +#endif +if (entrysize <= 0) return entrysize; +for (entry = (pcre_uchar *)first; entry <= (pcre_uchar *)last; entry += entrysize) + { + int n = GET2(entry, 0); + if (ovector[n*2] >= 0) return n; + } +return GET2(entry, 0); +} + + + + +/************************************************* +* Copy captured string to given buffer * +*************************************************/ + +/* This function copies a single captured substring into a given buffer. +Note that we use memcpy() rather than strncpy() in case there are binary zeros +in the string. + +Arguments: + subject the subject string that was matched + ovector pointer to the offsets table + stringcount the number of substrings that were captured + (i.e. the yield of the pcre_exec call, unless + that was zero, in which case it should be 1/3 + of the offset table size) + stringnumber the number of the required substring + buffer where to put the substring + size the size of the buffer + +Returns: if successful: + the length of the copied string, not including the zero + that is put on the end; can be zero + if not successful: + PCRE_ERROR_NOMEMORY (-6) buffer too small + PCRE_ERROR_NOSUBSTRING (-7) no such captured substring +*/ + +#if defined COMPILE_PCRE8 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre_copy_substring(const char *subject, int *ovector, int stringcount, + int stringnumber, char *buffer, int size) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre16_copy_substring(PCRE_SPTR16 subject, int *ovector, int stringcount, + int stringnumber, PCRE_UCHAR16 *buffer, int size) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre32_copy_substring(PCRE_SPTR32 subject, int *ovector, int stringcount, + int stringnumber, PCRE_UCHAR32 *buffer, int size) +#endif +{ +int yield; +if (stringnumber < 0 || stringnumber >= stringcount) + return PCRE_ERROR_NOSUBSTRING; +stringnumber *= 2; +yield = ovector[stringnumber+1] - ovector[stringnumber]; +if (size < yield + 1) return PCRE_ERROR_NOMEMORY; +memcpy(buffer, subject + ovector[stringnumber], IN_UCHARS(yield)); +buffer[yield] = 0; +return yield; +} + + + +/************************************************* +* Copy named captured string to given buffer * +*************************************************/ + +/* This function copies a single captured substring into a given buffer, +identifying it by name. If the regex permits duplicate names, the first +substring that is set is chosen. + +Arguments: + code the compiled regex + subject the subject string that was matched + ovector pointer to the offsets table + stringcount the number of substrings that were captured + (i.e. the yield of the pcre_exec call, unless + that was zero, in which case it should be 1/3 + of the offset table size) + stringname the name of the required substring + buffer where to put the substring + size the size of the buffer + +Returns: if successful: + the length of the copied string, not including the zero + that is put on the end; can be zero + if not successful: + PCRE_ERROR_NOMEMORY (-6) buffer too small + PCRE_ERROR_NOSUBSTRING (-7) no such captured substring +*/ + +#if defined COMPILE_PCRE8 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre_copy_named_substring(const pcre *code, const char *subject, + int *ovector, int stringcount, const char *stringname, + char *buffer, int size) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre16_copy_named_substring(const pcre16 *code, PCRE_SPTR16 subject, + int *ovector, int stringcount, PCRE_SPTR16 stringname, + PCRE_UCHAR16 *buffer, int size) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre32_copy_named_substring(const pcre32 *code, PCRE_SPTR32 subject, + int *ovector, int stringcount, PCRE_SPTR32 stringname, + PCRE_UCHAR32 *buffer, int size) +#endif +{ +int n = get_first_set(code, stringname, ovector); +if (n <= 0) return n; +#if defined COMPILE_PCRE8 +return pcre_copy_substring(subject, ovector, stringcount, n, buffer, size); +#elif defined COMPILE_PCRE16 +return pcre16_copy_substring(subject, ovector, stringcount, n, buffer, size); +#elif defined COMPILE_PCRE32 +return pcre32_copy_substring(subject, ovector, stringcount, n, buffer, size); +#endif +} + + + +/************************************************* +* Copy all captured strings to new store * +*************************************************/ + +/* This function gets one chunk of store and builds a list of pointers and all +of the captured substrings in it. A NULL pointer is put on the end of the list. + +Arguments: + subject the subject string that was matched + ovector pointer to the offsets table + stringcount the number of substrings that were captured + (i.e. the yield of the pcre_exec call, unless + that was zero, in which case it should be 1/3 + of the offset table size) + listptr set to point to the list of pointers + +Returns: if successful: 0 + if not successful: + PCRE_ERROR_NOMEMORY (-6) failed to get store +*/ + +#if defined COMPILE_PCRE8 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre_get_substring_list(const char *subject, int *ovector, int stringcount, + const char ***listptr) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre16_get_substring_list(PCRE_SPTR16 subject, int *ovector, int stringcount, + PCRE_SPTR16 **listptr) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre32_get_substring_list(PCRE_SPTR32 subject, int *ovector, int stringcount, + PCRE_SPTR32 **listptr) +#endif +{ +int i; +int size = sizeof(pcre_uchar *); +int double_count = stringcount * 2; +pcre_uchar **stringlist; +pcre_uchar *p; + +for (i = 0; i < double_count; i += 2) + size += sizeof(pcre_uchar *) + IN_UCHARS(ovector[i+1] - ovector[i] + 1); + +stringlist = (pcre_uchar **)(PUBL(malloc))(size); +if (stringlist == NULL) return PCRE_ERROR_NOMEMORY; + +#if defined COMPILE_PCRE8 +*listptr = (const char **)stringlist; +#elif defined COMPILE_PCRE16 +*listptr = (PCRE_SPTR16 *)stringlist; +#elif defined COMPILE_PCRE32 +*listptr = (PCRE_SPTR32 *)stringlist; +#endif +p = (pcre_uchar *)(stringlist + stringcount + 1); + +for (i = 0; i < double_count; i += 2) + { + int len = ovector[i+1] - ovector[i]; + memcpy(p, subject + ovector[i], IN_UCHARS(len)); + *stringlist++ = p; + p += len; + *p++ = 0; + } + +*stringlist = NULL; +return 0; +} + + + +/************************************************* +* Free store obtained by get_substring_list * +*************************************************/ + +/* This function exists for the benefit of people calling PCRE from non-C +programs that can call its functions, but not free() or (PUBL(free))() +directly. + +Argument: the result of a previous pcre_get_substring_list() +Returns: nothing +*/ + +#if defined COMPILE_PCRE8 +PCRE_EXP_DEFN void PCRE_CALL_CONVENTION +pcre_free_substring_list(const char **pointer) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DEFN void PCRE_CALL_CONVENTION +pcre16_free_substring_list(PCRE_SPTR16 *pointer) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DEFN void PCRE_CALL_CONVENTION +pcre32_free_substring_list(PCRE_SPTR32 *pointer) +#endif +{ +(PUBL(free))((void *)pointer); +} + + + +/************************************************* +* Copy captured string to new store * +*************************************************/ + +/* This function copies a single captured substring into a piece of new +store + +Arguments: + subject the subject string that was matched + ovector pointer to the offsets table + stringcount the number of substrings that were captured + (i.e. the yield of the pcre_exec call, unless + that was zero, in which case it should be 1/3 + of the offset table size) + stringnumber the number of the required substring + stringptr where to put a pointer to the substring + +Returns: if successful: + the length of the string, not including the zero that + is put on the end; can be zero + if not successful: + PCRE_ERROR_NOMEMORY (-6) failed to get store + PCRE_ERROR_NOSUBSTRING (-7) substring not present +*/ + +#if defined COMPILE_PCRE8 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre_get_substring(const char *subject, int *ovector, int stringcount, + int stringnumber, const char **stringptr) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre16_get_substring(PCRE_SPTR16 subject, int *ovector, int stringcount, + int stringnumber, PCRE_SPTR16 *stringptr) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre32_get_substring(PCRE_SPTR32 subject, int *ovector, int stringcount, + int stringnumber, PCRE_SPTR32 *stringptr) +#endif +{ +int yield; +pcre_uchar *substring; +if (stringnumber < 0 || stringnumber >= stringcount) + return PCRE_ERROR_NOSUBSTRING; +stringnumber *= 2; +yield = ovector[stringnumber+1] - ovector[stringnumber]; +substring = (pcre_uchar *)(PUBL(malloc))(IN_UCHARS(yield + 1)); +if (substring == NULL) return PCRE_ERROR_NOMEMORY; +memcpy(substring, subject + ovector[stringnumber], IN_UCHARS(yield)); +substring[yield] = 0; +#if defined COMPILE_PCRE8 +*stringptr = (const char *)substring; +#elif defined COMPILE_PCRE16 +*stringptr = (PCRE_SPTR16)substring; +#elif defined COMPILE_PCRE32 +*stringptr = (PCRE_SPTR32)substring; +#endif +return yield; +} + + + +/************************************************* +* Copy named captured string to new store * +*************************************************/ + +/* This function copies a single captured substring, identified by name, into +new store. If the regex permits duplicate names, the first substring that is +set is chosen. + +Arguments: + code the compiled regex + subject the subject string that was matched + ovector pointer to the offsets table + stringcount the number of substrings that were captured + (i.e. the yield of the pcre_exec call, unless + that was zero, in which case it should be 1/3 + of the offset table size) + stringname the name of the required substring + stringptr where to put the pointer + +Returns: if successful: + the length of the copied string, not including the zero + that is put on the end; can be zero + if not successful: + PCRE_ERROR_NOMEMORY (-6) couldn't get memory + PCRE_ERROR_NOSUBSTRING (-7) no such captured substring +*/ + +#if defined COMPILE_PCRE8 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre_get_named_substring(const pcre *code, const char *subject, + int *ovector, int stringcount, const char *stringname, + const char **stringptr) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre16_get_named_substring(const pcre16 *code, PCRE_SPTR16 subject, + int *ovector, int stringcount, PCRE_SPTR16 stringname, + PCRE_SPTR16 *stringptr) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre32_get_named_substring(const pcre32 *code, PCRE_SPTR32 subject, + int *ovector, int stringcount, PCRE_SPTR32 stringname, + PCRE_SPTR32 *stringptr) +#endif +{ +int n = get_first_set(code, stringname, ovector); +if (n <= 0) return n; +#if defined COMPILE_PCRE8 +return pcre_get_substring(subject, ovector, stringcount, n, stringptr); +#elif defined COMPILE_PCRE16 +return pcre16_get_substring(subject, ovector, stringcount, n, stringptr); +#elif defined COMPILE_PCRE32 +return pcre32_get_substring(subject, ovector, stringcount, n, stringptr); +#endif +} + + + + +/************************************************* +* Free store obtained by get_substring * +*************************************************/ + +/* This function exists for the benefit of people calling PCRE from non-C +programs that can call its functions, but not free() or (PUBL(free))() +directly. + +Argument: the result of a previous pcre_get_substring() +Returns: nothing +*/ + +#if defined COMPILE_PCRE8 +PCRE_EXP_DEFN void PCRE_CALL_CONVENTION +pcre_free_substring(const char *pointer) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DEFN void PCRE_CALL_CONVENTION +pcre16_free_substring(PCRE_SPTR16 pointer) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DEFN void PCRE_CALL_CONVENTION +pcre32_free_substring(PCRE_SPTR32 pointer) +#endif +{ +(PUBL(free))((void *)pointer); +} + +/* End of pcre_get.c */ diff --git a/plugins/Pcre16/src/pcre_globals.c b/plugins/Pcre16/src/pcre_globals.c new file mode 100644 index 0000000000..0f106aa901 --- /dev/null +++ b/plugins/Pcre16/src/pcre_globals.c @@ -0,0 +1,86 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2014 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains global variables that are exported by the PCRE library. +PCRE is thread-clean and doesn't use any global variables in the normal sense. +However, it calls memory allocation and freeing functions via the four +indirections below, and it can optionally do callouts, using the fifth +indirection. These values can be changed by the caller, but are shared between +all threads. + +For MS Visual Studio and Symbian OS, there are problems in initializing these +variables to non-local functions. In these cases, therefore, an indirection via +a local function is used. + +Also, when compiling for Virtual Pascal, things are done differently, and +global variables are not used. */ + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#include "pcre_internal.h" + +#if defined _MSC_VER || defined __SYMBIAN32__ +static void* LocalPcreMalloc(size_t aSize) + { + return malloc(aSize); + } +static void LocalPcreFree(void* aPtr) + { + free(aPtr); + } +PCRE_EXP_DATA_DEFN void *(*PUBL(malloc))(size_t) = LocalPcreMalloc; +PCRE_EXP_DATA_DEFN void (*PUBL(free))(void *) = LocalPcreFree; +PCRE_EXP_DATA_DEFN void *(*PUBL(stack_malloc))(size_t) = LocalPcreMalloc; +PCRE_EXP_DATA_DEFN void (*PUBL(stack_free))(void *) = LocalPcreFree; +PCRE_EXP_DATA_DEFN int (*PUBL(callout))(PUBL(callout_block) *) = NULL; +PCRE_EXP_DATA_DEFN int (*PUBL(stack_guard))(void) = NULL; + +#elif !defined VPCOMPAT +PCRE_EXP_DATA_DEFN void *(*PUBL(malloc))(size_t) = malloc; +PCRE_EXP_DATA_DEFN void (*PUBL(free))(void *) = free; +PCRE_EXP_DATA_DEFN void *(*PUBL(stack_malloc))(size_t) = malloc; +PCRE_EXP_DATA_DEFN void (*PUBL(stack_free))(void *) = free; +PCRE_EXP_DATA_DEFN int (*PUBL(callout))(PUBL(callout_block) *) = NULL; +PCRE_EXP_DATA_DEFN int (*PUBL(stack_guard))(void) = NULL; +#endif + +/* End of pcre_globals.c */ diff --git a/plugins/Pcre16/src/pcre_internal.h b/plugins/Pcre16/src/pcre_internal.h new file mode 100644 index 0000000000..6e915a0e45 --- /dev/null +++ b/plugins/Pcre16/src/pcre_internal.h @@ -0,0 +1,2781 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2014 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* This header contains definitions that are shared between the different +modules, but which are not relevant to the exported API. This includes some +functions whose names all begin with "_pcre_", "_pcre16_" or "_pcre32_" +depending on the PRIV macro. */ + +#ifndef PCRE_INTERNAL_H +#define PCRE_INTERNAL_H + +/* Define PCRE_DEBUG to get debugging output on stdout. */ + +#if 0 +#define PCRE_DEBUG +#endif + +/* PCRE is compiled as an 8 bit library if it is not requested otherwise. */ + +#if !defined COMPILE_PCRE16 && !defined COMPILE_PCRE32 +#define COMPILE_PCRE8 +#endif + +/* If SUPPORT_UCP is defined, SUPPORT_UTF must also be defined. The +"configure" script ensures this, but not everybody uses "configure". */ + +#if defined SUPPORT_UCP && !(defined SUPPORT_UTF) +#define SUPPORT_UTF 1 +#endif + +/* We define SUPPORT_UTF if SUPPORT_UTF8 is enabled for compatibility +reasons with existing code. */ + +#if defined SUPPORT_UTF8 && !(defined SUPPORT_UTF) +#define SUPPORT_UTF 1 +#endif + +/* Fixme: SUPPORT_UTF8 should be eventually disappear from the code. +Until then we define it if SUPPORT_UTF is defined. */ + +#if defined SUPPORT_UTF && !(defined SUPPORT_UTF8) +#define SUPPORT_UTF8 1 +#endif + +/* We do not support both EBCDIC and UTF-8/16/32 at the same time. The "configure" +script prevents both being selected, but not everybody uses "configure". */ + +#if defined EBCDIC && defined SUPPORT_UTF +#error The use of both EBCDIC and SUPPORT_UTF is not supported. +#endif + +/* Use a macro for debugging printing, 'cause that eliminates the use of #ifdef +inline, and there are *still* stupid compilers about that don't like indented +pre-processor statements, or at least there were when I first wrote this. After +all, it had only been about 10 years then... + +It turns out that the Mac Debugging.h header also defines the macro DPRINTF, so +be absolutely sure we get our version. */ + +#undef DPRINTF +#ifdef PCRE_DEBUG +#define DPRINTF(p) printf p +#else +#define DPRINTF(p) /* Nothing */ +#endif + + +/* Standard C headers plus the external interface definition. The only time +setjmp and stdarg are used is when NO_RECURSE is set. */ + +#include <ctype.h> +#include <limits.h> +#include <stddef.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +/* Valgrind (memcheck) support */ + +#ifdef SUPPORT_VALGRIND +#include <valgrind/memcheck.h> +#endif + +/* When compiling a DLL for Windows, the exported symbols have to be declared +using some MS magic. I found some useful information on this web page: +http://msdn2.microsoft.com/en-us/library/y4h7bcy6(VS.80).aspx. According to the +information there, using __declspec(dllexport) without "extern" we have a +definition; with "extern" we have a declaration. The settings here override the +setting in pcre.h (which is included below); it defines only PCRE_EXP_DECL, +which is all that is needed for applications (they just import the symbols). We +use: + + PCRE_EXP_DECL for declarations + PCRE_EXP_DEFN for definitions of exported functions + PCRE_EXP_DATA_DEFN for definitions of exported variables + +The reason for the two DEFN macros is that in non-Windows environments, one +does not want to have "extern" before variable definitions because it leads to +compiler warnings. So we distinguish between functions and variables. In +Windows, the two should always be the same. + +The reason for wrapping this in #ifndef PCRE_EXP_DECL is so that pcretest, +which is an application, but needs to import this file in order to "peek" at +internals, can #include pcre.h first to get an application's-eye view. + +In principle, people compiling for non-Windows, non-Unix-like (i.e. uncommon, +special-purpose environments) might want to stick other stuff in front of +exported symbols. That's why, in the non-Windows case, we set PCRE_EXP_DEFN and +PCRE_EXP_DATA_DEFN only if they are not already set. */ + +#ifndef PCRE_EXP_DECL +# ifdef _WIN32 +# ifndef PCRE_STATIC +# define PCRE_EXP_DECL extern __declspec(dllexport) +# define PCRE_EXP_DEFN __declspec(dllexport) +# define PCRE_EXP_DATA_DEFN __declspec(dllexport) +# else +# define PCRE_EXP_DECL extern +# define PCRE_EXP_DEFN +# define PCRE_EXP_DATA_DEFN +# endif +# else +# ifdef __cplusplus +# define PCRE_EXP_DECL extern "C" +# else +# define PCRE_EXP_DECL extern +# endif +# ifndef PCRE_EXP_DEFN +# define PCRE_EXP_DEFN PCRE_EXP_DECL +# endif +# ifndef PCRE_EXP_DATA_DEFN +# define PCRE_EXP_DATA_DEFN +# endif +# endif +#endif + +/* When compiling with the MSVC compiler, it is sometimes necessary to include +a "calling convention" before exported function names. (This is secondhand +information; I know nothing about MSVC myself). For example, something like + + void __cdecl function(....) + +might be needed. In order so make this easy, all the exported functions have +PCRE_CALL_CONVENTION just before their names. It is rarely needed; if not +set, we ensure here that it has no effect. */ + +#ifndef PCRE_CALL_CONVENTION +#define PCRE_CALL_CONVENTION +#endif + +/* We need to have types that specify unsigned 8, 16 and 32-bit integers. We +cannot determine these outside the compilation (e.g. by running a program as +part of "configure") because PCRE is often cross-compiled for use on other +systems. Instead we make use of the maximum sizes that are available at +preprocessor time in standard C environments. */ + +typedef unsigned char pcre_uint8; + +#if USHRT_MAX == 65535 +typedef unsigned short pcre_uint16; +typedef short pcre_int16; +#define PCRE_UINT16_MAX USHRT_MAX +#define PCRE_INT16_MAX SHRT_MAX +#elif UINT_MAX == 65535 +typedef unsigned int pcre_uint16; +typedef int pcre_int16; +#define PCRE_UINT16_MAX UINT_MAX +#define PCRE_INT16_MAX INT_MAX +#else +#error Cannot determine a type for 16-bit integers +#endif + +#if UINT_MAX == 4294967295U +typedef unsigned int pcre_uint32; +typedef int pcre_int32; +#define PCRE_UINT32_MAX UINT_MAX +#define PCRE_INT32_MAX INT_MAX +#elif ULONG_MAX == 4294967295UL +typedef unsigned long int pcre_uint32; +typedef long int pcre_int32; +#define PCRE_UINT32_MAX ULONG_MAX +#define PCRE_INT32_MAX LONG_MAX +#else +#error Cannot determine a type for 32-bit integers +#endif + +/* When checking for integer overflow in pcre_compile(), we need to handle +large integers. If a 64-bit integer type is available, we can use that. +Otherwise we have to cast to double, which of course requires floating point +arithmetic. Handle this by defining a macro for the appropriate type. If +stdint.h is available, include it; it may define INT64_MAX. Systems that do not +have stdint.h (e.g. Solaris) may have inttypes.h. The macro int64_t may be set +by "configure". */ + +#if defined HAVE_STDINT_H +#include <stdint.h> +#elif defined HAVE_INTTYPES_H +#include <inttypes.h> +#endif + +#if defined INT64_MAX || defined int64_t +#define INT64_OR_DOUBLE int64_t +#else +#define INT64_OR_DOUBLE double +#endif + +/* All character handling must be done as unsigned characters. Otherwise there +are problems with top-bit-set characters and functions such as isspace(). +However, we leave the interface to the outside world as char * or short *, +because that should make things easier for callers. This character type is +called pcre_uchar. + +The IN_UCHARS macro multiply its argument with the byte size of the current +pcre_uchar type. Useful for memcpy and such operations, whose require the +byte size of their input/output buffers. + +The MAX_255 macro checks whether its pcre_uchar input is less than 256. + +The TABLE_GET macro is designed for accessing elements of tables whose contain +exactly 256 items. When the character is able to contain more than 256 +items, some check is needed before accessing these tables. +*/ + +#if defined COMPILE_PCRE8 + +typedef unsigned char pcre_uchar; +#define IN_UCHARS(x) (x) +#define MAX_255(c) 1 +#define TABLE_GET(c, table, default) ((table)[c]) + +#elif defined COMPILE_PCRE16 + +#if USHRT_MAX != 65535 +/* This is a warning message. Change PCRE_UCHAR16 to a 16 bit data type in +pcre.h(.in) and disable (comment out) this message. */ +#error Warning: PCRE_UCHAR16 is not a 16 bit data type. +#endif + +typedef pcre_uint16 pcre_uchar; +#define UCHAR_SHIFT (1) +#define IN_UCHARS(x) ((x) << UCHAR_SHIFT) +#define MAX_255(c) ((c) <= 255u) +#define TABLE_GET(c, table, default) (MAX_255(c)? ((table)[c]):(default)) + +#elif defined COMPILE_PCRE32 + +typedef pcre_uint32 pcre_uchar; +#define UCHAR_SHIFT (2) +#define IN_UCHARS(x) ((x) << UCHAR_SHIFT) +#define MAX_255(c) ((c) <= 255u) +#define TABLE_GET(c, table, default) (MAX_255(c)? ((table)[c]):(default)) + +#else +#error Unsupported compiling mode +#endif /* COMPILE_PCRE[8|16|32] */ + +/* This is an unsigned int value that no character can ever have. UTF-8 +characters only go up to 0x7fffffff (though Unicode doesn't go beyond +0x0010ffff). */ + +#define NOTACHAR 0xffffffff + +/* PCRE is able to support several different kinds of newline (CR, LF, CRLF, +"any" and "anycrlf" at present). The following macros are used to package up +testing for newlines. NLBLOCK, PSSTART, and PSEND are defined in the various +modules to indicate in which datablock the parameters exist, and what the +start/end of string field names are. */ + +#define NLTYPE_FIXED 0 /* Newline is a fixed length string */ +#define NLTYPE_ANY 1 /* Newline is any Unicode line ending */ +#define NLTYPE_ANYCRLF 2 /* Newline is CR, LF, or CRLF */ + +/* This macro checks for a newline at the given position */ + +#define IS_NEWLINE(p) \ + ((NLBLOCK->nltype != NLTYPE_FIXED)? \ + ((p) < NLBLOCK->PSEND && \ + PRIV(is_newline)((p), NLBLOCK->nltype, NLBLOCK->PSEND, \ + &(NLBLOCK->nllen), utf)) \ + : \ + ((p) <= NLBLOCK->PSEND - NLBLOCK->nllen && \ + UCHAR21TEST(p) == NLBLOCK->nl[0] && \ + (NLBLOCK->nllen == 1 || UCHAR21TEST(p+1) == NLBLOCK->nl[1]) \ + ) \ + ) + +/* This macro checks for a newline immediately preceding the given position */ + +#define WAS_NEWLINE(p) \ + ((NLBLOCK->nltype != NLTYPE_FIXED)? \ + ((p) > NLBLOCK->PSSTART && \ + PRIV(was_newline)((p), NLBLOCK->nltype, NLBLOCK->PSSTART, \ + &(NLBLOCK->nllen), utf)) \ + : \ + ((p) >= NLBLOCK->PSSTART + NLBLOCK->nllen && \ + UCHAR21TEST(p - NLBLOCK->nllen) == NLBLOCK->nl[0] && \ + (NLBLOCK->nllen == 1 || UCHAR21TEST(p - NLBLOCK->nllen + 1) == NLBLOCK->nl[1]) \ + ) \ + ) + +/* When PCRE is compiled as a C++ library, the subject pointer can be replaced +with a custom type. This makes it possible, for example, to allow pcre_exec() +to process subject strings that are discontinuous by using a smart pointer +class. It must always be possible to inspect all of the subject string in +pcre_exec() because of the way it backtracks. Two macros are required in the +normal case, for sign-unspecified and unsigned char pointers. The former is +used for the external interface and appears in pcre.h, which is why its name +must begin with PCRE_. */ + +#ifdef CUSTOM_SUBJECT_PTR +#define PCRE_PUCHAR CUSTOM_SUBJECT_PTR +#else +#define PCRE_PUCHAR const pcre_uchar * +#endif + +/* Include the public PCRE header and the definitions of UCP character property +values. */ + +#include "pcre.h" +#include "ucp.h" + +#ifdef COMPILE_PCRE32 +/* Assert that the public PCRE_UCHAR32 is a 32-bit type */ +typedef int __assert_pcre_uchar32_size[sizeof(PCRE_UCHAR32) == 4 ? 1 : -1]; +#endif + +/* When compiling for use with the Virtual Pascal compiler, these functions +need to have their names changed. PCRE must be compiled with the -DVPCOMPAT +option on the command line. */ + +#ifdef VPCOMPAT +#define strlen(s) _strlen(s) +#define strncmp(s1,s2,m) _strncmp(s1,s2,m) +#define memcmp(s,c,n) _memcmp(s,c,n) +#define memcpy(d,s,n) _memcpy(d,s,n) +#define memmove(d,s,n) _memmove(d,s,n) +#define memset(s,c,n) _memset(s,c,n) +#else /* VPCOMPAT */ + +/* To cope with SunOS4 and other systems that lack memmove() but have bcopy(), +define a macro for memmove() if HAVE_MEMMOVE is false, provided that HAVE_BCOPY +is set. Otherwise, include an emulating function for those systems that have +neither (there some non-Unix environments where this is the case). */ + +#ifndef HAVE_MEMMOVE +#undef memmove /* some systems may have a macro */ +#ifdef HAVE_BCOPY +#define memmove(a, b, c) bcopy(b, a, c) +#else /* HAVE_BCOPY */ +static void * +pcre_memmove(void *d, const void *s, size_t n) +{ +size_t i; +unsigned char *dest = (unsigned char *)d; +const unsigned char *src = (const unsigned char *)s; +if (dest > src) + { + dest += n; + src += n; + for (i = 0; i < n; ++i) *(--dest) = *(--src); + return (void *)dest; + } +else + { + for (i = 0; i < n; ++i) *dest++ = *src++; + return (void *)(dest - n); + } +} +#define memmove(a, b, c) pcre_memmove(a, b, c) +#endif /* not HAVE_BCOPY */ +#endif /* not HAVE_MEMMOVE */ +#endif /* not VPCOMPAT */ + + +/* PCRE keeps offsets in its compiled code as 2-byte quantities (always stored +in big-endian order) by default. These are used, for example, to link from the +start of a subpattern to its alternatives and its end. The use of 2 bytes per +offset limits the size of the compiled regex to around 64K, which is big enough +for almost everybody. However, I received a request for an even bigger limit. +For this reason, and also to make the code easier to maintain, the storing and +loading of offsets from the byte string is now handled by the macros that are +defined here. + +The macros are controlled by the value of LINK_SIZE. This defaults to 2 in +the config.h file, but can be overridden by using -D on the command line. This +is automated on Unix systems via the "configure" command. */ + +#if defined COMPILE_PCRE8 + +#if LINK_SIZE == 2 + +#define PUT(a,n,d) \ + (a[n] = (d) >> 8), \ + (a[(n)+1] = (d) & 255) + +#define GET(a,n) \ + (((a)[n] << 8) | (a)[(n)+1]) + +#define MAX_PATTERN_SIZE (1 << 16) + + +#elif LINK_SIZE == 3 + +#define PUT(a,n,d) \ + (a[n] = (d) >> 16), \ + (a[(n)+1] = (d) >> 8), \ + (a[(n)+2] = (d) & 255) + +#define GET(a,n) \ + (((a)[n] << 16) | ((a)[(n)+1] << 8) | (a)[(n)+2]) + +#define MAX_PATTERN_SIZE (1 << 24) + + +#elif LINK_SIZE == 4 + +#define PUT(a,n,d) \ + (a[n] = (d) >> 24), \ + (a[(n)+1] = (d) >> 16), \ + (a[(n)+2] = (d) >> 8), \ + (a[(n)+3] = (d) & 255) + +#define GET(a,n) \ + (((a)[n] << 24) | ((a)[(n)+1] << 16) | ((a)[(n)+2] << 8) | (a)[(n)+3]) + +/* Keep it positive */ +#define MAX_PATTERN_SIZE (1 << 30) + +#else +#error LINK_SIZE must be either 2, 3, or 4 +#endif + +#elif defined COMPILE_PCRE16 + +#if LINK_SIZE == 2 + +/* Redefine LINK_SIZE as a multiple of sizeof(pcre_uchar) */ +#undef LINK_SIZE +#define LINK_SIZE 1 + +#define PUT(a,n,d) \ + (a[n] = (d)) + +#define GET(a,n) \ + (a[n]) + +#define MAX_PATTERN_SIZE (1 << 16) + +#elif LINK_SIZE == 3 || LINK_SIZE == 4 + +/* Redefine LINK_SIZE as a multiple of sizeof(pcre_uchar) */ +#undef LINK_SIZE +#define LINK_SIZE 2 + +#define PUT(a,n,d) \ + (a[n] = (d) >> 16), \ + (a[(n)+1] = (d) & 65535) + +#define GET(a,n) \ + (((a)[n] << 16) | (a)[(n)+1]) + +/* Keep it positive */ +#define MAX_PATTERN_SIZE (1 << 30) + +#else +#error LINK_SIZE must be either 2, 3, or 4 +#endif + +#elif defined COMPILE_PCRE32 + +/* Only supported LINK_SIZE is 4 */ +/* Redefine LINK_SIZE as a multiple of sizeof(pcre_uchar) */ +#undef LINK_SIZE +#define LINK_SIZE 1 + +#define PUT(a,n,d) \ + (a[n] = (d)) + +#define GET(a,n) \ + (a[n]) + +/* Keep it positive */ +#define MAX_PATTERN_SIZE (1 << 30) + +#else +#error Unsupported compiling mode +#endif /* COMPILE_PCRE[8|16|32] */ + +/* Convenience macro defined in terms of the others */ + +#define PUTINC(a,n,d) PUT(a,n,d), a += LINK_SIZE + + +/* PCRE uses some other 2-byte quantities that do not change when the size of +offsets changes. There are used for repeat counts and for other things such as +capturing parenthesis numbers in back references. */ + +#if defined COMPILE_PCRE8 + +#define IMM2_SIZE 2 + +#define PUT2(a,n,d) \ + a[n] = (d) >> 8; \ + a[(n)+1] = (d) & 255 + +/* For reasons that I do not understand, the expression in this GET2 macro is +treated by gcc as a signed expression, even when a is declared as unsigned. It +seems that any kind of arithmetic results in a signed value. */ + +#define GET2(a,n) \ + (unsigned int)(((a)[n] << 8) | (a)[(n)+1]) + +#elif defined COMPILE_PCRE16 + +#define IMM2_SIZE 1 + +#define PUT2(a,n,d) \ + a[n] = d + +#define GET2(a,n) \ + a[n] + +#elif defined COMPILE_PCRE32 + +#define IMM2_SIZE 1 + +#define PUT2(a,n,d) \ + a[n] = d + +#define GET2(a,n) \ + a[n] + +#else +#error Unsupported compiling mode +#endif /* COMPILE_PCRE[8|16|32] */ + +#define PUT2INC(a,n,d) PUT2(a,n,d), a += IMM2_SIZE + +/* The maximum length of a MARK name is currently one data unit; it may be +changed in future to be a fixed number of bytes or to depend on LINK_SIZE. */ + +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 +#define MAX_MARK ((1u << 16) - 1) +#else +#define MAX_MARK ((1u << 8) - 1) +#endif + +/* There is a proposed future special "UTF-21" mode, in which only the lowest +21 bits of a 32-bit character are interpreted as UTF, with the remaining 11 +high-order bits available to the application for other uses. In preparation for +the future implementation of this mode, there are macros that load a data item +and, if in this special mode, mask it to 21 bits. These macros all have names +starting with UCHAR21. In all other modes, including the normal 32-bit +library, the macros all have the same simple definitions. When the new mode is +implemented, it is expected that these definitions will be varied appropriately +using #ifdef when compiling the library that supports the special mode. */ + +#define UCHAR21(eptr) (*(eptr)) +#define UCHAR21TEST(eptr) (*(eptr)) +#define UCHAR21INC(eptr) (*(eptr)++) +#define UCHAR21INCTEST(eptr) (*(eptr)++) + +/* When UTF encoding is being used, a character is no longer just a single +byte in 8-bit mode or a single short in 16-bit mode. The macros for character +handling generate simple sequences when used in the basic mode, and more +complicated ones for UTF characters. GETCHARLENTEST and other macros are not +used when UTF is not supported. To make sure they can never even appear when +UTF support is omitted, we don't even define them. */ + +#ifndef SUPPORT_UTF + +/* #define MAX_VALUE_FOR_SINGLE_CHAR */ +/* #define HAS_EXTRALEN(c) */ +/* #define GET_EXTRALEN(c) */ +/* #define NOT_FIRSTCHAR(c) */ +#define GETCHAR(c, eptr) c = *eptr; +#define GETCHARTEST(c, eptr) c = *eptr; +#define GETCHARINC(c, eptr) c = *eptr++; +#define GETCHARINCTEST(c, eptr) c = *eptr++; +#define GETCHARLEN(c, eptr, len) c = *eptr; +/* #define GETCHARLENTEST(c, eptr, len) */ +/* #define BACKCHAR(eptr) */ +/* #define FORWARDCHAR(eptr) */ +/* #define ACROSSCHAR(condition, eptr, action) */ + +#else /* SUPPORT_UTF */ + +/* Tests whether the code point needs extra characters to decode. */ + +#define HASUTF8EXTRALEN(c) ((c) >= 0xc0) + +/* Base macro to pick up the remaining bytes of a UTF-8 character, not +advancing the pointer. */ + +#define GETUTF8(c, eptr) \ + { \ + if ((c & 0x20) == 0) \ + c = ((c & 0x1f) << 6) | (eptr[1] & 0x3f); \ + else if ((c & 0x10) == 0) \ + c = ((c & 0x0f) << 12) | ((eptr[1] & 0x3f) << 6) | (eptr[2] & 0x3f); \ + else if ((c & 0x08) == 0) \ + c = ((c & 0x07) << 18) | ((eptr[1] & 0x3f) << 12) | \ + ((eptr[2] & 0x3f) << 6) | (eptr[3] & 0x3f); \ + else if ((c & 0x04) == 0) \ + c = ((c & 0x03) << 24) | ((eptr[1] & 0x3f) << 18) | \ + ((eptr[2] & 0x3f) << 12) | ((eptr[3] & 0x3f) << 6) | \ + (eptr[4] & 0x3f); \ + else \ + c = ((c & 0x01) << 30) | ((eptr[1] & 0x3f) << 24) | \ + ((eptr[2] & 0x3f) << 18) | ((eptr[3] & 0x3f) << 12) | \ + ((eptr[4] & 0x3f) << 6) | (eptr[5] & 0x3f); \ + } + +/* Base macro to pick up the remaining bytes of a UTF-8 character, advancing +the pointer. */ + +#define GETUTF8INC(c, eptr) \ + { \ + if ((c & 0x20) == 0) \ + c = ((c & 0x1f) << 6) | (*eptr++ & 0x3f); \ + else if ((c & 0x10) == 0) \ + { \ + c = ((c & 0x0f) << 12) | ((*eptr & 0x3f) << 6) | (eptr[1] & 0x3f); \ + eptr += 2; \ + } \ + else if ((c & 0x08) == 0) \ + { \ + c = ((c & 0x07) << 18) | ((*eptr & 0x3f) << 12) | \ + ((eptr[1] & 0x3f) << 6) | (eptr[2] & 0x3f); \ + eptr += 3; \ + } \ + else if ((c & 0x04) == 0) \ + { \ + c = ((c & 0x03) << 24) | ((*eptr & 0x3f) << 18) | \ + ((eptr[1] & 0x3f) << 12) | ((eptr[2] & 0x3f) << 6) | \ + (eptr[3] & 0x3f); \ + eptr += 4; \ + } \ + else \ + { \ + c = ((c & 0x01) << 30) | ((*eptr & 0x3f) << 24) | \ + ((eptr[1] & 0x3f) << 18) | ((eptr[2] & 0x3f) << 12) | \ + ((eptr[3] & 0x3f) << 6) | (eptr[4] & 0x3f); \ + eptr += 5; \ + } \ + } + +#if defined COMPILE_PCRE8 + +/* These macros were originally written in the form of loops that used data +from the tables whose names start with PRIV(utf8_table). They were rewritten by +a user so as not to use loops, because in some environments this gives a +significant performance advantage, and it seems never to do any harm. */ + +/* Tells the biggest code point which can be encoded as a single character. */ + +#define MAX_VALUE_FOR_SINGLE_CHAR 127 + +/* Tests whether the code point needs extra characters to decode. */ + +#define HAS_EXTRALEN(c) ((c) >= 0xc0) + +/* Returns with the additional number of characters if IS_MULTICHAR(c) is TRUE. +Otherwise it has an undefined behaviour. */ + +#define GET_EXTRALEN(c) (PRIV(utf8_table4)[(c) & 0x3f]) + +/* Returns TRUE, if the given character is not the first character +of a UTF sequence. */ + +#define NOT_FIRSTCHAR(c) (((c) & 0xc0) == 0x80) + +/* Get the next UTF-8 character, not advancing the pointer. This is called when +we know we are in UTF-8 mode. */ + +#define GETCHAR(c, eptr) \ + c = *eptr; \ + if (c >= 0xc0) GETUTF8(c, eptr); + +/* Get the next UTF-8 character, testing for UTF-8 mode, and not advancing the +pointer. */ + +#define GETCHARTEST(c, eptr) \ + c = *eptr; \ + if (utf && c >= 0xc0) GETUTF8(c, eptr); + +/* Get the next UTF-8 character, advancing the pointer. This is called when we +know we are in UTF-8 mode. */ + +#define GETCHARINC(c, eptr) \ + c = *eptr++; \ + if (c >= 0xc0) GETUTF8INC(c, eptr); + +/* Get the next character, testing for UTF-8 mode, and advancing the pointer. +This is called when we don't know if we are in UTF-8 mode. */ + +#define GETCHARINCTEST(c, eptr) \ + c = *eptr++; \ + if (utf && c >= 0xc0) GETUTF8INC(c, eptr); + +/* Base macro to pick up the remaining bytes of a UTF-8 character, not +advancing the pointer, incrementing the length. */ + +#define GETUTF8LEN(c, eptr, len) \ + { \ + if ((c & 0x20) == 0) \ + { \ + c = ((c & 0x1f) << 6) | (eptr[1] & 0x3f); \ + len++; \ + } \ + else if ((c & 0x10) == 0) \ + { \ + c = ((c & 0x0f) << 12) | ((eptr[1] & 0x3f) << 6) | (eptr[2] & 0x3f); \ + len += 2; \ + } \ + else if ((c & 0x08) == 0) \ + {\ + c = ((c & 0x07) << 18) | ((eptr[1] & 0x3f) << 12) | \ + ((eptr[2] & 0x3f) << 6) | (eptr[3] & 0x3f); \ + len += 3; \ + } \ + else if ((c & 0x04) == 0) \ + { \ + c = ((c & 0x03) << 24) | ((eptr[1] & 0x3f) << 18) | \ + ((eptr[2] & 0x3f) << 12) | ((eptr[3] & 0x3f) << 6) | \ + (eptr[4] & 0x3f); \ + len += 4; \ + } \ + else \ + {\ + c = ((c & 0x01) << 30) | ((eptr[1] & 0x3f) << 24) | \ + ((eptr[2] & 0x3f) << 18) | ((eptr[3] & 0x3f) << 12) | \ + ((eptr[4] & 0x3f) << 6) | (eptr[5] & 0x3f); \ + len += 5; \ + } \ + } + +/* Get the next UTF-8 character, not advancing the pointer, incrementing length +if there are extra bytes. This is called when we know we are in UTF-8 mode. */ + +#define GETCHARLEN(c, eptr, len) \ + c = *eptr; \ + if (c >= 0xc0) GETUTF8LEN(c, eptr, len); + +/* Get the next UTF-8 character, testing for UTF-8 mode, not advancing the +pointer, incrementing length if there are extra bytes. This is called when we +do not know if we are in UTF-8 mode. */ + +#define GETCHARLENTEST(c, eptr, len) \ + c = *eptr; \ + if (utf && c >= 0xc0) GETUTF8LEN(c, eptr, len); + +/* If the pointer is not at the start of a character, move it back until +it is. This is called only in UTF-8 mode - we don't put a test within the macro +because almost all calls are already within a block of UTF-8 only code. */ + +#define BACKCHAR(eptr) while((*eptr & 0xc0) == 0x80) eptr-- + +/* Same as above, just in the other direction. */ +#define FORWARDCHAR(eptr) while((*eptr & 0xc0) == 0x80) eptr++ + +/* Same as above, but it allows a fully customizable form. */ +#define ACROSSCHAR(condition, eptr, action) \ + while((condition) && ((eptr) & 0xc0) == 0x80) action + +#elif defined COMPILE_PCRE16 + +/* Tells the biggest code point which can be encoded as a single character. */ + +#define MAX_VALUE_FOR_SINGLE_CHAR 65535 + +/* Tests whether the code point needs extra characters to decode. */ + +#define HAS_EXTRALEN(c) (((c) & 0xfc00) == 0xd800) + +/* Returns with the additional number of characters if IS_MULTICHAR(c) is TRUE. +Otherwise it has an undefined behaviour. */ + +#define GET_EXTRALEN(c) 1 + +/* Returns TRUE, if the given character is not the first character +of a UTF sequence. */ + +#define NOT_FIRSTCHAR(c) (((c) & 0xfc00) == 0xdc00) + +/* Base macro to pick up the low surrogate of a UTF-16 character, not +advancing the pointer. */ + +#define GETUTF16(c, eptr) \ + { c = (((c & 0x3ff) << 10) | (eptr[1] & 0x3ff)) + 0x10000; } + +/* Get the next UTF-16 character, not advancing the pointer. This is called when +we know we are in UTF-16 mode. */ + +#define GETCHAR(c, eptr) \ + c = *eptr; \ + if ((c & 0xfc00) == 0xd800) GETUTF16(c, eptr); + +/* Get the next UTF-16 character, testing for UTF-16 mode, and not advancing the +pointer. */ + +#define GETCHARTEST(c, eptr) \ + c = *eptr; \ + if (utf && (c & 0xfc00) == 0xd800) GETUTF16(c, eptr); + +/* Base macro to pick up the low surrogate of a UTF-16 character, advancing +the pointer. */ + +#define GETUTF16INC(c, eptr) \ + { c = (((c & 0x3ff) << 10) | (*eptr++ & 0x3ff)) + 0x10000; } + +/* Get the next UTF-16 character, advancing the pointer. This is called when we +know we are in UTF-16 mode. */ + +#define GETCHARINC(c, eptr) \ + c = *eptr++; \ + if ((c & 0xfc00) == 0xd800) GETUTF16INC(c, eptr); + +/* Get the next character, testing for UTF-16 mode, and advancing the pointer. +This is called when we don't know if we are in UTF-16 mode. */ + +#define GETCHARINCTEST(c, eptr) \ + c = *eptr++; \ + if (utf && (c & 0xfc00) == 0xd800) GETUTF16INC(c, eptr); + +/* Base macro to pick up the low surrogate of a UTF-16 character, not +advancing the pointer, incrementing the length. */ + +#define GETUTF16LEN(c, eptr, len) \ + { c = (((c & 0x3ff) << 10) | (eptr[1] & 0x3ff)) + 0x10000; len++; } + +/* Get the next UTF-16 character, not advancing the pointer, incrementing +length if there is a low surrogate. This is called when we know we are in +UTF-16 mode. */ + +#define GETCHARLEN(c, eptr, len) \ + c = *eptr; \ + if ((c & 0xfc00) == 0xd800) GETUTF16LEN(c, eptr, len); + +/* Get the next UTF-816character, testing for UTF-16 mode, not advancing the +pointer, incrementing length if there is a low surrogate. This is called when +we do not know if we are in UTF-16 mode. */ + +#define GETCHARLENTEST(c, eptr, len) \ + c = *eptr; \ + if (utf && (c & 0xfc00) == 0xd800) GETUTF16LEN(c, eptr, len); + +/* If the pointer is not at the start of a character, move it back until +it is. This is called only in UTF-16 mode - we don't put a test within the +macro because almost all calls are already within a block of UTF-16 only +code. */ + +#define BACKCHAR(eptr) if ((*eptr & 0xfc00) == 0xdc00) eptr-- + +/* Same as above, just in the other direction. */ +#define FORWARDCHAR(eptr) if ((*eptr & 0xfc00) == 0xdc00) eptr++ + +/* Same as above, but it allows a fully customizable form. */ +#define ACROSSCHAR(condition, eptr, action) \ + if ((condition) && ((eptr) & 0xfc00) == 0xdc00) action + +#elif defined COMPILE_PCRE32 + +/* These are trivial for the 32-bit library, since all UTF-32 characters fit +into one pcre_uchar unit. */ +#define MAX_VALUE_FOR_SINGLE_CHAR (0x10ffffu) +#define HAS_EXTRALEN(c) (0) +#define GET_EXTRALEN(c) (0) +#define NOT_FIRSTCHAR(c) (0) + +/* Get the next UTF-32 character, not advancing the pointer. This is called when +we know we are in UTF-32 mode. */ + +#define GETCHAR(c, eptr) \ + c = *(eptr); + +/* Get the next UTF-32 character, testing for UTF-32 mode, and not advancing the +pointer. */ + +#define GETCHARTEST(c, eptr) \ + c = *(eptr); + +/* Get the next UTF-32 character, advancing the pointer. This is called when we +know we are in UTF-32 mode. */ + +#define GETCHARINC(c, eptr) \ + c = *((eptr)++); + +/* Get the next character, testing for UTF-32 mode, and advancing the pointer. +This is called when we don't know if we are in UTF-32 mode. */ + +#define GETCHARINCTEST(c, eptr) \ + c = *((eptr)++); + +/* Get the next UTF-32 character, not advancing the pointer, not incrementing +length (since all UTF-32 is of length 1). This is called when we know we are in +UTF-32 mode. */ + +#define GETCHARLEN(c, eptr, len) \ + GETCHAR(c, eptr) + +/* Get the next UTF-32character, testing for UTF-32 mode, not advancing the +pointer, not incrementing the length (since all UTF-32 is of length 1). +This is called when we do not know if we are in UTF-32 mode. */ + +#define GETCHARLENTEST(c, eptr, len) \ + GETCHARTEST(c, eptr) + +/* If the pointer is not at the start of a character, move it back until +it is. This is called only in UTF-32 mode - we don't put a test within the +macro because almost all calls are already within a block of UTF-32 only +code. +These are all no-ops since all UTF-32 characters fit into one pcre_uchar. */ + +#define BACKCHAR(eptr) do { } while (0) + +/* Same as above, just in the other direction. */ +#define FORWARDCHAR(eptr) do { } while (0) + +/* Same as above, but it allows a fully customizable form. */ +#define ACROSSCHAR(condition, eptr, action) do { } while (0) + +#else +#error Unsupported compiling mode +#endif /* COMPILE_PCRE[8|16|32] */ + +#endif /* SUPPORT_UTF */ + +/* Tests for Unicode horizontal and vertical whitespace characters must check a +number of different values. Using a switch statement for this generates the +fastest code (no loop, no memory access), and there are several places in the +interpreter code where this happens. In order to ensure that all the case lists +remain in step, we use macros so that there is only one place where the lists +are defined. + +These values are also required as lists in pcre_compile.c when processing \h, +\H, \v and \V in a character class. The lists are defined in pcre_tables.c, but +macros that define the values are here so that all the definitions are +together. The lists must be in ascending character order, terminated by +NOTACHAR (which is 0xffffffff). + +Any changes should ensure that the various macros are kept in step with each +other. NOTE: The values also appear in pcre_jit_compile.c. */ + +/* ------ ASCII/Unicode environments ------ */ + +#ifndef EBCDIC + +#define HSPACE_LIST \ + CHAR_HT, CHAR_SPACE, 0xa0, \ + 0x1680, 0x180e, 0x2000, 0x2001, 0x2002, 0x2003, 0x2004, 0x2005, \ + 0x2006, 0x2007, 0x2008, 0x2009, 0x200A, 0x202f, 0x205f, 0x3000, \ + NOTACHAR + +#define HSPACE_MULTIBYTE_CASES \ + case 0x1680: /* OGHAM SPACE MARK */ \ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ \ + case 0x2000: /* EN QUAD */ \ + case 0x2001: /* EM QUAD */ \ + case 0x2002: /* EN SPACE */ \ + case 0x2003: /* EM SPACE */ \ + case 0x2004: /* THREE-PER-EM SPACE */ \ + case 0x2005: /* FOUR-PER-EM SPACE */ \ + case 0x2006: /* SIX-PER-EM SPACE */ \ + case 0x2007: /* FIGURE SPACE */ \ + case 0x2008: /* PUNCTUATION SPACE */ \ + case 0x2009: /* THIN SPACE */ \ + case 0x200A: /* HAIR SPACE */ \ + case 0x202f: /* NARROW NO-BREAK SPACE */ \ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ \ + case 0x3000 /* IDEOGRAPHIC SPACE */ + +#define HSPACE_BYTE_CASES \ + case CHAR_HT: \ + case CHAR_SPACE: \ + case 0xa0 /* NBSP */ + +#define HSPACE_CASES \ + HSPACE_BYTE_CASES: \ + HSPACE_MULTIBYTE_CASES + +#define VSPACE_LIST \ + CHAR_LF, CHAR_VT, CHAR_FF, CHAR_CR, CHAR_NEL, 0x2028, 0x2029, NOTACHAR + +#define VSPACE_MULTIBYTE_CASES \ + case 0x2028: /* LINE SEPARATOR */ \ + case 0x2029 /* PARAGRAPH SEPARATOR */ + +#define VSPACE_BYTE_CASES \ + case CHAR_LF: \ + case CHAR_VT: \ + case CHAR_FF: \ + case CHAR_CR: \ + case CHAR_NEL + +#define VSPACE_CASES \ + VSPACE_BYTE_CASES: \ + VSPACE_MULTIBYTE_CASES + +/* ------ EBCDIC environments ------ */ + +#else +#define HSPACE_LIST CHAR_HT, CHAR_SPACE + +#define HSPACE_BYTE_CASES \ + case CHAR_HT: \ + case CHAR_SPACE + +#define HSPACE_CASES HSPACE_BYTE_CASES + +#ifdef EBCDIC_NL25 +#define VSPACE_LIST \ + CHAR_VT, CHAR_FF, CHAR_CR, CHAR_NEL, CHAR_LF, NOTACHAR +#else +#define VSPACE_LIST \ + CHAR_VT, CHAR_FF, CHAR_CR, CHAR_LF, CHAR_NEL, NOTACHAR +#endif + +#define VSPACE_BYTE_CASES \ + case CHAR_LF: \ + case CHAR_VT: \ + case CHAR_FF: \ + case CHAR_CR: \ + case CHAR_NEL + +#define VSPACE_CASES VSPACE_BYTE_CASES +#endif /* EBCDIC */ + +/* ------ End of whitespace macros ------ */ + + + +/* Private flags containing information about the compiled regex. They used to +live at the top end of the options word, but that got almost full, so they were +moved to a 16-bit flags word - which got almost full, so now they are in a +32-bit flags word. From release 8.00, PCRE_NOPARTIAL is unused, as the +restrictions on partial matching have been lifted. It remains for backwards +compatibility. */ + +#define PCRE_MODE8 0x00000001 /* compiled in 8 bit mode */ +#define PCRE_MODE16 0x00000002 /* compiled in 16 bit mode */ +#define PCRE_MODE32 0x00000004 /* compiled in 32 bit mode */ +#define PCRE_FIRSTSET 0x00000010 /* first_char is set */ +#define PCRE_FCH_CASELESS 0x00000020 /* caseless first char */ +#define PCRE_REQCHSET 0x00000040 /* req_byte is set */ +#define PCRE_RCH_CASELESS 0x00000080 /* caseless requested char */ +#define PCRE_STARTLINE 0x00000100 /* start after \n for multiline */ +#define PCRE_NOPARTIAL 0x00000200 /* can't use partial with this regex */ +#define PCRE_JCHANGED 0x00000400 /* j option used in regex */ +#define PCRE_HASCRORLF 0x00000800 /* explicit \r or \n in pattern */ +#define PCRE_HASTHEN 0x00001000 /* pattern contains (*THEN) */ +#define PCRE_MLSET 0x00002000 /* match limit set by regex */ +#define PCRE_RLSET 0x00004000 /* recursion limit set by regex */ +#define PCRE_MATCH_EMPTY 0x00008000 /* pattern can match empty string */ + +#if defined COMPILE_PCRE8 +#define PCRE_MODE PCRE_MODE8 +#elif defined COMPILE_PCRE16 +#define PCRE_MODE PCRE_MODE16 +#elif defined COMPILE_PCRE32 +#define PCRE_MODE PCRE_MODE32 +#endif +#define PCRE_MODE_MASK (PCRE_MODE8 | PCRE_MODE16 | PCRE_MODE32) + +/* Flags for the "extra" block produced by pcre_study(). */ + +#define PCRE_STUDY_MAPPED 0x0001 /* a map of starting chars exists */ +#define PCRE_STUDY_MINLEN 0x0002 /* a minimum length field exists */ + +/* Masks for identifying the public options that are permitted at compile +time, run time, or study time, respectively. */ + +#define PCRE_NEWLINE_BITS (PCRE_NEWLINE_CR|PCRE_NEWLINE_LF|PCRE_NEWLINE_ANY| \ + PCRE_NEWLINE_ANYCRLF) + +#define PUBLIC_COMPILE_OPTIONS \ + (PCRE_CASELESS|PCRE_EXTENDED|PCRE_ANCHORED|PCRE_MULTILINE| \ + PCRE_DOTALL|PCRE_DOLLAR_ENDONLY|PCRE_EXTRA|PCRE_UNGREEDY|PCRE_UTF8| \ + PCRE_NO_AUTO_CAPTURE|PCRE_NO_AUTO_POSSESS| \ + PCRE_NO_UTF8_CHECK|PCRE_AUTO_CALLOUT|PCRE_FIRSTLINE| \ + PCRE_DUPNAMES|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE| \ + PCRE_JAVASCRIPT_COMPAT|PCRE_UCP|PCRE_NO_START_OPTIMIZE|PCRE_NEVER_UTF) + +#define PUBLIC_EXEC_OPTIONS \ + (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NOTEMPTY_ATSTART| \ + PCRE_NO_UTF8_CHECK|PCRE_PARTIAL_HARD|PCRE_PARTIAL_SOFT|PCRE_NEWLINE_BITS| \ + PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE|PCRE_NO_START_OPTIMIZE) + +#define PUBLIC_DFA_EXEC_OPTIONS \ + (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NOTEMPTY_ATSTART| \ + PCRE_NO_UTF8_CHECK|PCRE_PARTIAL_HARD|PCRE_PARTIAL_SOFT|PCRE_DFA_SHORTEST| \ + PCRE_DFA_RESTART|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE| \ + PCRE_NO_START_OPTIMIZE) + +#define PUBLIC_STUDY_OPTIONS \ + (PCRE_STUDY_JIT_COMPILE|PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE| \ + PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE|PCRE_STUDY_EXTRA_NEEDED) + +#define PUBLIC_JIT_EXEC_OPTIONS \ + (PCRE_NO_UTF8_CHECK|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|\ + PCRE_NOTEMPTY_ATSTART|PCRE_PARTIAL_SOFT|PCRE_PARTIAL_HARD) + +/* Magic number to provide a small check against being handed junk. */ + +#define MAGIC_NUMBER 0x50435245UL /* 'PCRE' */ + +/* This variable is used to detect a loaded regular expression +in different endianness. */ + +#define REVERSED_MAGIC_NUMBER 0x45524350UL /* 'ERCP' */ + +/* The maximum remaining length of subject we are prepared to search for a +req_byte match. */ + +#define REQ_BYTE_MAX 1000 + +/* Miscellaneous definitions. The #ifndef is to pacify compiler warnings in +environments where these macros are defined elsewhere. Unfortunately, there +is no way to do the same for the typedef. */ + +typedef int BOOL; + +#ifndef FALSE +#define FALSE 0 +#define TRUE 1 +#endif + +/* If PCRE is to support UTF-8 on EBCDIC platforms, we cannot use normal +character constants like '*' because the compiler would emit their EBCDIC code, +which is different from their ASCII/UTF-8 code. Instead we define macros for +the characters so that they always use the ASCII/UTF-8 code when UTF-8 support +is enabled. When UTF-8 support is not enabled, the definitions use character +literals. Both character and string versions of each character are needed, and +there are some longer strings as well. + +This means that, on EBCDIC platforms, the PCRE library can handle either +EBCDIC, or UTF-8, but not both. To support both in the same compiled library +would need different lookups depending on whether PCRE_UTF8 was set or not. +This would make it impossible to use characters in switch/case statements, +which would reduce performance. For a theoretical use (which nobody has asked +for) in a minority area (EBCDIC platforms), this is not sensible. Any +application that did need both could compile two versions of the library, using +macros to give the functions distinct names. */ + +#ifndef SUPPORT_UTF + +/* UTF-8 support is not enabled; use the platform-dependent character literals +so that PCRE works in both ASCII and EBCDIC environments, but only in non-UTF +mode. Newline characters are problematic in EBCDIC. Though it has CR and LF +characters, a common practice has been to use its NL (0x15) character as the +line terminator in C-like processing environments. However, sometimes the LF +(0x25) character is used instead, according to this Unicode document: + +http://unicode.org/standard/reports/tr13/tr13-5.html + +PCRE defaults EBCDIC NL to 0x15, but has a build-time option to select 0x25 +instead. Whichever is *not* chosen is defined as NEL. + +In both ASCII and EBCDIC environments, CHAR_NL and CHAR_LF are synonyms for the +same code point. */ + +#ifdef EBCDIC + +#ifndef EBCDIC_NL25 +#define CHAR_NL '\x15' +#define CHAR_NEL '\x25' +#define STR_NL "\x15" +#define STR_NEL "\x25" +#else +#define CHAR_NL '\x25' +#define CHAR_NEL '\x15' +#define STR_NL "\x25" +#define STR_NEL "\x15" +#endif + +#define CHAR_LF CHAR_NL +#define STR_LF STR_NL + +#define CHAR_ESC '\047' +#define CHAR_DEL '\007' +#define STR_ESC "\047" +#define STR_DEL "\007" + +#else /* Not EBCDIC */ + +/* In ASCII/Unicode, linefeed is '\n' and we equate this to NL for +compatibility. NEL is the Unicode newline character; make sure it is +a positive value. */ + +#define CHAR_LF '\n' +#define CHAR_NL CHAR_LF +#define CHAR_NEL ((unsigned char)'\x85') +#define CHAR_ESC '\033' +#define CHAR_DEL '\177' + +#define STR_LF "\n" +#define STR_NL STR_LF +#define STR_NEL "\x85" +#define STR_ESC "\033" +#define STR_DEL "\177" + +#endif /* EBCDIC */ + +/* The remaining definitions work in both environments. */ + +#define CHAR_NULL '\0' +#define CHAR_HT '\t' +#define CHAR_VT '\v' +#define CHAR_FF '\f' +#define CHAR_CR '\r' +#define CHAR_BS '\b' +#define CHAR_BEL '\a' + +#define CHAR_SPACE ' ' +#define CHAR_EXCLAMATION_MARK '!' +#define CHAR_QUOTATION_MARK '"' +#define CHAR_NUMBER_SIGN '#' +#define CHAR_DOLLAR_SIGN '$' +#define CHAR_PERCENT_SIGN '%' +#define CHAR_AMPERSAND '&' +#define CHAR_APOSTROPHE '\'' +#define CHAR_LEFT_PARENTHESIS '(' +#define CHAR_RIGHT_PARENTHESIS ')' +#define CHAR_ASTERISK '*' +#define CHAR_PLUS '+' +#define CHAR_COMMA ',' +#define CHAR_MINUS '-' +#define CHAR_DOT '.' +#define CHAR_SLASH '/' +#define CHAR_0 '0' +#define CHAR_1 '1' +#define CHAR_2 '2' +#define CHAR_3 '3' +#define CHAR_4 '4' +#define CHAR_5 '5' +#define CHAR_6 '6' +#define CHAR_7 '7' +#define CHAR_8 '8' +#define CHAR_9 '9' +#define CHAR_COLON ':' +#define CHAR_SEMICOLON ';' +#define CHAR_LESS_THAN_SIGN '<' +#define CHAR_EQUALS_SIGN '=' +#define CHAR_GREATER_THAN_SIGN '>' +#define CHAR_QUESTION_MARK '?' +#define CHAR_COMMERCIAL_AT '@' +#define CHAR_A 'A' +#define CHAR_B 'B' +#define CHAR_C 'C' +#define CHAR_D 'D' +#define CHAR_E 'E' +#define CHAR_F 'F' +#define CHAR_G 'G' +#define CHAR_H 'H' +#define CHAR_I 'I' +#define CHAR_J 'J' +#define CHAR_K 'K' +#define CHAR_L 'L' +#define CHAR_M 'M' +#define CHAR_N 'N' +#define CHAR_O 'O' +#define CHAR_P 'P' +#define CHAR_Q 'Q' +#define CHAR_R 'R' +#define CHAR_S 'S' +#define CHAR_T 'T' +#define CHAR_U 'U' +#define CHAR_V 'V' +#define CHAR_W 'W' +#define CHAR_X 'X' +#define CHAR_Y 'Y' +#define CHAR_Z 'Z' +#define CHAR_LEFT_SQUARE_BRACKET '[' +#define CHAR_BACKSLASH '\\' +#define CHAR_RIGHT_SQUARE_BRACKET ']' +#define CHAR_CIRCUMFLEX_ACCENT '^' +#define CHAR_UNDERSCORE '_' +#define CHAR_GRAVE_ACCENT '`' +#define CHAR_a 'a' +#define CHAR_b 'b' +#define CHAR_c 'c' +#define CHAR_d 'd' +#define CHAR_e 'e' +#define CHAR_f 'f' +#define CHAR_g 'g' +#define CHAR_h 'h' +#define CHAR_i 'i' +#define CHAR_j 'j' +#define CHAR_k 'k' +#define CHAR_l 'l' +#define CHAR_m 'm' +#define CHAR_n 'n' +#define CHAR_o 'o' +#define CHAR_p 'p' +#define CHAR_q 'q' +#define CHAR_r 'r' +#define CHAR_s 's' +#define CHAR_t 't' +#define CHAR_u 'u' +#define CHAR_v 'v' +#define CHAR_w 'w' +#define CHAR_x 'x' +#define CHAR_y 'y' +#define CHAR_z 'z' +#define CHAR_LEFT_CURLY_BRACKET '{' +#define CHAR_VERTICAL_LINE '|' +#define CHAR_RIGHT_CURLY_BRACKET '}' +#define CHAR_TILDE '~' + +#define STR_HT "\t" +#define STR_VT "\v" +#define STR_FF "\f" +#define STR_CR "\r" +#define STR_BS "\b" +#define STR_BEL "\a" + +#define STR_SPACE " " +#define STR_EXCLAMATION_MARK "!" +#define STR_QUOTATION_MARK "\"" +#define STR_NUMBER_SIGN "#" +#define STR_DOLLAR_SIGN "$" +#define STR_PERCENT_SIGN "%" +#define STR_AMPERSAND "&" +#define STR_APOSTROPHE "'" +#define STR_LEFT_PARENTHESIS "(" +#define STR_RIGHT_PARENTHESIS ")" +#define STR_ASTERISK "*" +#define STR_PLUS "+" +#define STR_COMMA "," +#define STR_MINUS "-" +#define STR_DOT "." +#define STR_SLASH "/" +#define STR_0 "0" +#define STR_1 "1" +#define STR_2 "2" +#define STR_3 "3" +#define STR_4 "4" +#define STR_5 "5" +#define STR_6 "6" +#define STR_7 "7" +#define STR_8 "8" +#define STR_9 "9" +#define STR_COLON ":" +#define STR_SEMICOLON ";" +#define STR_LESS_THAN_SIGN "<" +#define STR_EQUALS_SIGN "=" +#define STR_GREATER_THAN_SIGN ">" +#define STR_QUESTION_MARK "?" +#define STR_COMMERCIAL_AT "@" +#define STR_A "A" +#define STR_B "B" +#define STR_C "C" +#define STR_D "D" +#define STR_E "E" +#define STR_F "F" +#define STR_G "G" +#define STR_H "H" +#define STR_I "I" +#define STR_J "J" +#define STR_K "K" +#define STR_L "L" +#define STR_M "M" +#define STR_N "N" +#define STR_O "O" +#define STR_P "P" +#define STR_Q "Q" +#define STR_R "R" +#define STR_S "S" +#define STR_T "T" +#define STR_U "U" +#define STR_V "V" +#define STR_W "W" +#define STR_X "X" +#define STR_Y "Y" +#define STR_Z "Z" +#define STR_LEFT_SQUARE_BRACKET "[" +#define STR_BACKSLASH "\\" +#define STR_RIGHT_SQUARE_BRACKET "]" +#define STR_CIRCUMFLEX_ACCENT "^" +#define STR_UNDERSCORE "_" +#define STR_GRAVE_ACCENT "`" +#define STR_a "a" +#define STR_b "b" +#define STR_c "c" +#define STR_d "d" +#define STR_e "e" +#define STR_f "f" +#define STR_g "g" +#define STR_h "h" +#define STR_i "i" +#define STR_j "j" +#define STR_k "k" +#define STR_l "l" +#define STR_m "m" +#define STR_n "n" +#define STR_o "o" +#define STR_p "p" +#define STR_q "q" +#define STR_r "r" +#define STR_s "s" +#define STR_t "t" +#define STR_u "u" +#define STR_v "v" +#define STR_w "w" +#define STR_x "x" +#define STR_y "y" +#define STR_z "z" +#define STR_LEFT_CURLY_BRACKET "{" +#define STR_VERTICAL_LINE "|" +#define STR_RIGHT_CURLY_BRACKET "}" +#define STR_TILDE "~" + +#define STRING_ACCEPT0 "ACCEPT\0" +#define STRING_COMMIT0 "COMMIT\0" +#define STRING_F0 "F\0" +#define STRING_FAIL0 "FAIL\0" +#define STRING_MARK0 "MARK\0" +#define STRING_PRUNE0 "PRUNE\0" +#define STRING_SKIP0 "SKIP\0" +#define STRING_THEN "THEN" + +#define STRING_alpha0 "alpha\0" +#define STRING_lower0 "lower\0" +#define STRING_upper0 "upper\0" +#define STRING_alnum0 "alnum\0" +#define STRING_ascii0 "ascii\0" +#define STRING_blank0 "blank\0" +#define STRING_cntrl0 "cntrl\0" +#define STRING_digit0 "digit\0" +#define STRING_graph0 "graph\0" +#define STRING_print0 "print\0" +#define STRING_punct0 "punct\0" +#define STRING_space0 "space\0" +#define STRING_word0 "word\0" +#define STRING_xdigit "xdigit" + +#define STRING_DEFINE "DEFINE" +#define STRING_WEIRD_STARTWORD "[:<:]]" +#define STRING_WEIRD_ENDWORD "[:>:]]" + +#define STRING_CR_RIGHTPAR "CR)" +#define STRING_LF_RIGHTPAR "LF)" +#define STRING_CRLF_RIGHTPAR "CRLF)" +#define STRING_ANY_RIGHTPAR "ANY)" +#define STRING_ANYCRLF_RIGHTPAR "ANYCRLF)" +#define STRING_BSR_ANYCRLF_RIGHTPAR "BSR_ANYCRLF)" +#define STRING_BSR_UNICODE_RIGHTPAR "BSR_UNICODE)" +#define STRING_UTF8_RIGHTPAR "UTF8)" +#define STRING_UTF16_RIGHTPAR "UTF16)" +#define STRING_UTF32_RIGHTPAR "UTF32)" +#define STRING_UTF_RIGHTPAR "UTF)" +#define STRING_UCP_RIGHTPAR "UCP)" +#define STRING_NO_AUTO_POSSESS_RIGHTPAR "NO_AUTO_POSSESS)" +#define STRING_NO_START_OPT_RIGHTPAR "NO_START_OPT)" +#define STRING_LIMIT_MATCH_EQ "LIMIT_MATCH=" +#define STRING_LIMIT_RECURSION_EQ "LIMIT_RECURSION=" + +#else /* SUPPORT_UTF */ + +/* UTF-8 support is enabled; always use UTF-8 (=ASCII) character codes. This +works in both modes non-EBCDIC platforms, and on EBCDIC platforms in UTF-8 mode +only. */ + +#define CHAR_HT '\011' +#define CHAR_VT '\013' +#define CHAR_FF '\014' +#define CHAR_CR '\015' +#define CHAR_LF '\012' +#define CHAR_NL CHAR_LF +#define CHAR_NEL ((unsigned char)'\x85') +#define CHAR_BS '\010' +#define CHAR_BEL '\007' +#define CHAR_ESC '\033' +#define CHAR_DEL '\177' + +#define CHAR_NULL '\0' +#define CHAR_SPACE '\040' +#define CHAR_EXCLAMATION_MARK '\041' +#define CHAR_QUOTATION_MARK '\042' +#define CHAR_NUMBER_SIGN '\043' +#define CHAR_DOLLAR_SIGN '\044' +#define CHAR_PERCENT_SIGN '\045' +#define CHAR_AMPERSAND '\046' +#define CHAR_APOSTROPHE '\047' +#define CHAR_LEFT_PARENTHESIS '\050' +#define CHAR_RIGHT_PARENTHESIS '\051' +#define CHAR_ASTERISK '\052' +#define CHAR_PLUS '\053' +#define CHAR_COMMA '\054' +#define CHAR_MINUS '\055' +#define CHAR_DOT '\056' +#define CHAR_SLASH '\057' +#define CHAR_0 '\060' +#define CHAR_1 '\061' +#define CHAR_2 '\062' +#define CHAR_3 '\063' +#define CHAR_4 '\064' +#define CHAR_5 '\065' +#define CHAR_6 '\066' +#define CHAR_7 '\067' +#define CHAR_8 '\070' +#define CHAR_9 '\071' +#define CHAR_COLON '\072' +#define CHAR_SEMICOLON '\073' +#define CHAR_LESS_THAN_SIGN '\074' +#define CHAR_EQUALS_SIGN '\075' +#define CHAR_GREATER_THAN_SIGN '\076' +#define CHAR_QUESTION_MARK '\077' +#define CHAR_COMMERCIAL_AT '\100' +#define CHAR_A '\101' +#define CHAR_B '\102' +#define CHAR_C '\103' +#define CHAR_D '\104' +#define CHAR_E '\105' +#define CHAR_F '\106' +#define CHAR_G '\107' +#define CHAR_H '\110' +#define CHAR_I '\111' +#define CHAR_J '\112' +#define CHAR_K '\113' +#define CHAR_L '\114' +#define CHAR_M '\115' +#define CHAR_N '\116' +#define CHAR_O '\117' +#define CHAR_P '\120' +#define CHAR_Q '\121' +#define CHAR_R '\122' +#define CHAR_S '\123' +#define CHAR_T '\124' +#define CHAR_U '\125' +#define CHAR_V '\126' +#define CHAR_W '\127' +#define CHAR_X '\130' +#define CHAR_Y '\131' +#define CHAR_Z '\132' +#define CHAR_LEFT_SQUARE_BRACKET '\133' +#define CHAR_BACKSLASH '\134' +#define CHAR_RIGHT_SQUARE_BRACKET '\135' +#define CHAR_CIRCUMFLEX_ACCENT '\136' +#define CHAR_UNDERSCORE '\137' +#define CHAR_GRAVE_ACCENT '\140' +#define CHAR_a '\141' +#define CHAR_b '\142' +#define CHAR_c '\143' +#define CHAR_d '\144' +#define CHAR_e '\145' +#define CHAR_f '\146' +#define CHAR_g '\147' +#define CHAR_h '\150' +#define CHAR_i '\151' +#define CHAR_j '\152' +#define CHAR_k '\153' +#define CHAR_l '\154' +#define CHAR_m '\155' +#define CHAR_n '\156' +#define CHAR_o '\157' +#define CHAR_p '\160' +#define CHAR_q '\161' +#define CHAR_r '\162' +#define CHAR_s '\163' +#define CHAR_t '\164' +#define CHAR_u '\165' +#define CHAR_v '\166' +#define CHAR_w '\167' +#define CHAR_x '\170' +#define CHAR_y '\171' +#define CHAR_z '\172' +#define CHAR_LEFT_CURLY_BRACKET '\173' +#define CHAR_VERTICAL_LINE '\174' +#define CHAR_RIGHT_CURLY_BRACKET '\175' +#define CHAR_TILDE '\176' + +#define STR_HT "\011" +#define STR_VT "\013" +#define STR_FF "\014" +#define STR_CR "\015" +#define STR_NL "\012" +#define STR_BS "\010" +#define STR_BEL "\007" +#define STR_ESC "\033" +#define STR_DEL "\177" + +#define STR_SPACE "\040" +#define STR_EXCLAMATION_MARK "\041" +#define STR_QUOTATION_MARK "\042" +#define STR_NUMBER_SIGN "\043" +#define STR_DOLLAR_SIGN "\044" +#define STR_PERCENT_SIGN "\045" +#define STR_AMPERSAND "\046" +#define STR_APOSTROPHE "\047" +#define STR_LEFT_PARENTHESIS "\050" +#define STR_RIGHT_PARENTHESIS "\051" +#define STR_ASTERISK "\052" +#define STR_PLUS "\053" +#define STR_COMMA "\054" +#define STR_MINUS "\055" +#define STR_DOT "\056" +#define STR_SLASH "\057" +#define STR_0 "\060" +#define STR_1 "\061" +#define STR_2 "\062" +#define STR_3 "\063" +#define STR_4 "\064" +#define STR_5 "\065" +#define STR_6 "\066" +#define STR_7 "\067" +#define STR_8 "\070" +#define STR_9 "\071" +#define STR_COLON "\072" +#define STR_SEMICOLON "\073" +#define STR_LESS_THAN_SIGN "\074" +#define STR_EQUALS_SIGN "\075" +#define STR_GREATER_THAN_SIGN "\076" +#define STR_QUESTION_MARK "\077" +#define STR_COMMERCIAL_AT "\100" +#define STR_A "\101" +#define STR_B "\102" +#define STR_C "\103" +#define STR_D "\104" +#define STR_E "\105" +#define STR_F "\106" +#define STR_G "\107" +#define STR_H "\110" +#define STR_I "\111" +#define STR_J "\112" +#define STR_K "\113" +#define STR_L "\114" +#define STR_M "\115" +#define STR_N "\116" +#define STR_O "\117" +#define STR_P "\120" +#define STR_Q "\121" +#define STR_R "\122" +#define STR_S "\123" +#define STR_T "\124" +#define STR_U "\125" +#define STR_V "\126" +#define STR_W "\127" +#define STR_X "\130" +#define STR_Y "\131" +#define STR_Z "\132" +#define STR_LEFT_SQUARE_BRACKET "\133" +#define STR_BACKSLASH "\134" +#define STR_RIGHT_SQUARE_BRACKET "\135" +#define STR_CIRCUMFLEX_ACCENT "\136" +#define STR_UNDERSCORE "\137" +#define STR_GRAVE_ACCENT "\140" +#define STR_a "\141" +#define STR_b "\142" +#define STR_c "\143" +#define STR_d "\144" +#define STR_e "\145" +#define STR_f "\146" +#define STR_g "\147" +#define STR_h "\150" +#define STR_i "\151" +#define STR_j "\152" +#define STR_k "\153" +#define STR_l "\154" +#define STR_m "\155" +#define STR_n "\156" +#define STR_o "\157" +#define STR_p "\160" +#define STR_q "\161" +#define STR_r "\162" +#define STR_s "\163" +#define STR_t "\164" +#define STR_u "\165" +#define STR_v "\166" +#define STR_w "\167" +#define STR_x "\170" +#define STR_y "\171" +#define STR_z "\172" +#define STR_LEFT_CURLY_BRACKET "\173" +#define STR_VERTICAL_LINE "\174" +#define STR_RIGHT_CURLY_BRACKET "\175" +#define STR_TILDE "\176" + +#define STRING_ACCEPT0 STR_A STR_C STR_C STR_E STR_P STR_T "\0" +#define STRING_COMMIT0 STR_C STR_O STR_M STR_M STR_I STR_T "\0" +#define STRING_F0 STR_F "\0" +#define STRING_FAIL0 STR_F STR_A STR_I STR_L "\0" +#define STRING_MARK0 STR_M STR_A STR_R STR_K "\0" +#define STRING_PRUNE0 STR_P STR_R STR_U STR_N STR_E "\0" +#define STRING_SKIP0 STR_S STR_K STR_I STR_P "\0" +#define STRING_THEN STR_T STR_H STR_E STR_N + +#define STRING_alpha0 STR_a STR_l STR_p STR_h STR_a "\0" +#define STRING_lower0 STR_l STR_o STR_w STR_e STR_r "\0" +#define STRING_upper0 STR_u STR_p STR_p STR_e STR_r "\0" +#define STRING_alnum0 STR_a STR_l STR_n STR_u STR_m "\0" +#define STRING_ascii0 STR_a STR_s STR_c STR_i STR_i "\0" +#define STRING_blank0 STR_b STR_l STR_a STR_n STR_k "\0" +#define STRING_cntrl0 STR_c STR_n STR_t STR_r STR_l "\0" +#define STRING_digit0 STR_d STR_i STR_g STR_i STR_t "\0" +#define STRING_graph0 STR_g STR_r STR_a STR_p STR_h "\0" +#define STRING_print0 STR_p STR_r STR_i STR_n STR_t "\0" +#define STRING_punct0 STR_p STR_u STR_n STR_c STR_t "\0" +#define STRING_space0 STR_s STR_p STR_a STR_c STR_e "\0" +#define STRING_word0 STR_w STR_o STR_r STR_d "\0" +#define STRING_xdigit STR_x STR_d STR_i STR_g STR_i STR_t + +#define STRING_DEFINE STR_D STR_E STR_F STR_I STR_N STR_E +#define STRING_WEIRD_STARTWORD STR_LEFT_SQUARE_BRACKET STR_COLON STR_LESS_THAN_SIGN STR_COLON STR_RIGHT_SQUARE_BRACKET STR_RIGHT_SQUARE_BRACKET +#define STRING_WEIRD_ENDWORD STR_LEFT_SQUARE_BRACKET STR_COLON STR_GREATER_THAN_SIGN STR_COLON STR_RIGHT_SQUARE_BRACKET STR_RIGHT_SQUARE_BRACKET + +#define STRING_CR_RIGHTPAR STR_C STR_R STR_RIGHT_PARENTHESIS +#define STRING_LF_RIGHTPAR STR_L STR_F STR_RIGHT_PARENTHESIS +#define STRING_CRLF_RIGHTPAR STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS +#define STRING_ANY_RIGHTPAR STR_A STR_N STR_Y STR_RIGHT_PARENTHESIS +#define STRING_ANYCRLF_RIGHTPAR STR_A STR_N STR_Y STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS +#define STRING_BSR_ANYCRLF_RIGHTPAR STR_B STR_S STR_R STR_UNDERSCORE STR_A STR_N STR_Y STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS +#define STRING_BSR_UNICODE_RIGHTPAR STR_B STR_S STR_R STR_UNDERSCORE STR_U STR_N STR_I STR_C STR_O STR_D STR_E STR_RIGHT_PARENTHESIS +#define STRING_UTF8_RIGHTPAR STR_U STR_T STR_F STR_8 STR_RIGHT_PARENTHESIS +#define STRING_UTF16_RIGHTPAR STR_U STR_T STR_F STR_1 STR_6 STR_RIGHT_PARENTHESIS +#define STRING_UTF32_RIGHTPAR STR_U STR_T STR_F STR_3 STR_2 STR_RIGHT_PARENTHESIS +#define STRING_UTF_RIGHTPAR STR_U STR_T STR_F STR_RIGHT_PARENTHESIS +#define STRING_UCP_RIGHTPAR STR_U STR_C STR_P STR_RIGHT_PARENTHESIS +#define STRING_NO_AUTO_POSSESS_RIGHTPAR STR_N STR_O STR_UNDERSCORE STR_A STR_U STR_T STR_O STR_UNDERSCORE STR_P STR_O STR_S STR_S STR_E STR_S STR_S STR_RIGHT_PARENTHESIS +#define STRING_NO_START_OPT_RIGHTPAR STR_N STR_O STR_UNDERSCORE STR_S STR_T STR_A STR_R STR_T STR_UNDERSCORE STR_O STR_P STR_T STR_RIGHT_PARENTHESIS +#define STRING_LIMIT_MATCH_EQ STR_L STR_I STR_M STR_I STR_T STR_UNDERSCORE STR_M STR_A STR_T STR_C STR_H STR_EQUALS_SIGN +#define STRING_LIMIT_RECURSION_EQ STR_L STR_I STR_M STR_I STR_T STR_UNDERSCORE STR_R STR_E STR_C STR_U STR_R STR_S STR_I STR_O STR_N STR_EQUALS_SIGN + +#endif /* SUPPORT_UTF */ + +/* Escape items that are just an encoding of a particular data value. */ + +#ifndef ESC_e +#define ESC_e CHAR_ESC +#endif + +#ifndef ESC_f +#define ESC_f CHAR_FF +#endif + +#ifndef ESC_n +#define ESC_n CHAR_LF +#endif + +#ifndef ESC_r +#define ESC_r CHAR_CR +#endif + +/* We can't officially use ESC_t because it is a POSIX reserved identifier +(presumably because of all the others like size_t). */ + +#ifndef ESC_tee +#define ESC_tee CHAR_HT +#endif + +/* Codes for different types of Unicode property */ + +#define PT_ANY 0 /* Any property - matches all chars */ +#define PT_LAMP 1 /* L& - the union of Lu, Ll, Lt */ +#define PT_GC 2 /* Specified general characteristic (e.g. L) */ +#define PT_PC 3 /* Specified particular characteristic (e.g. Lu) */ +#define PT_SC 4 /* Script (e.g. Han) */ +#define PT_ALNUM 5 /* Alphanumeric - the union of L and N */ +#define PT_SPACE 6 /* Perl space - Z plus 9,10,12,13 */ +#define PT_PXSPACE 7 /* POSIX space - Z plus 9,10,11,12,13 */ +#define PT_WORD 8 /* Word - L plus N plus underscore */ +#define PT_CLIST 9 /* Pseudo-property: match character list */ +#define PT_UCNC 10 /* Universal Character nameable character */ +#define PT_TABSIZE 11 /* Size of square table for autopossessify tests */ + +/* The following special properties are used only in XCLASS items, when POSIX +classes are specified and PCRE_UCP is set - in other words, for Unicode +handling of these classes. They are not available via the \p or \P escapes like +those in the above list, and so they do not take part in the autopossessifying +table. */ + +#define PT_PXGRAPH 11 /* [:graph:] - characters that mark the paper */ +#define PT_PXPRINT 12 /* [:print:] - [:graph:] plus non-control spaces */ +#define PT_PXPUNCT 13 /* [:punct:] - punctuation characters */ + +/* Flag bits and data types for the extended class (OP_XCLASS) for classes that +contain characters with values greater than 255. */ + +#define XCL_NOT 0x01 /* Flag: this is a negative class */ +#define XCL_MAP 0x02 /* Flag: a 32-byte map is present */ +#define XCL_HASPROP 0x04 /* Flag: property checks are present. */ + +#define XCL_END 0 /* Marks end of individual items */ +#define XCL_SINGLE 1 /* Single item (one multibyte char) follows */ +#define XCL_RANGE 2 /* A range (two multibyte chars) follows */ +#define XCL_PROP 3 /* Unicode property (2-byte property code follows) */ +#define XCL_NOTPROP 4 /* Unicode inverted property (ditto) */ + +/* These are escaped items that aren't just an encoding of a particular data +value such as \n. They must have non-zero values, as check_escape() returns 0 +for a data character. Also, they must appear in the same order as in the +opcode definitions below, up to ESC_z. There's a dummy for OP_ALLANY because it +corresponds to "." in DOTALL mode rather than an escape sequence. It is also +used for [^] in JavaScript compatibility mode, and for \C in non-utf mode. In +non-DOTALL mode, "." behaves like \N. + +The special values ESC_DU, ESC_du, etc. are used instead of ESC_D, ESC_d, etc. +when PCRE_UCP is set and replacement of \d etc by \p sequences is required. +They must be contiguous, and remain in order so that the replacements can be +looked up from a table. + +Negative numbers are used to encode a backreference (\1, \2, \3, etc.) in +check_escape(). There are two tests in the code for an escape +greater than ESC_b and less than ESC_Z to detect the types that may be +repeated. These are the types that consume characters. If any new escapes are +put in between that don't consume a character, that code will have to change. +*/ + +enum { ESC_A = 1, ESC_G, ESC_K, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s, + ESC_W, ESC_w, ESC_N, ESC_dum, ESC_C, ESC_P, ESC_p, ESC_R, ESC_H, + ESC_h, ESC_V, ESC_v, ESC_X, ESC_Z, ESC_z, + ESC_E, ESC_Q, ESC_g, ESC_k, + ESC_DU, ESC_du, ESC_SU, ESC_su, ESC_WU, ESC_wu }; + + +/********************** Opcode definitions ******************/ + +/****** NOTE NOTE NOTE ****** + +Starting from 1 (i.e. after OP_END), the values up to OP_EOD must correspond in +order to the list of escapes immediately above. Furthermore, values up to +OP_DOLLM must not be changed without adjusting the table called autoposstab in +pcre_compile.c + +Whenever this list is updated, the two macro definitions that follow must be +updated to match. The possessification table called "opcode_possessify" in +pcre_compile.c must also be updated, and also the tables called "coptable" +and "poptable" in pcre_dfa_exec.c. + +****** NOTE NOTE NOTE ******/ + + +/* The values between FIRST_AUTOTAB_OP and LAST_AUTOTAB_RIGHT_OP, inclusive, +are used in a table for deciding whether a repeated character type can be +auto-possessified. */ + +#define FIRST_AUTOTAB_OP OP_NOT_DIGIT +#define LAST_AUTOTAB_LEFT_OP OP_EXTUNI +#define LAST_AUTOTAB_RIGHT_OP OP_DOLLM + +enum { + OP_END, /* 0 End of pattern */ + + /* Values corresponding to backslashed metacharacters */ + + OP_SOD, /* 1 Start of data: \A */ + OP_SOM, /* 2 Start of match (subject + offset): \G */ + OP_SET_SOM, /* 3 Set start of match (\K) */ + OP_NOT_WORD_BOUNDARY, /* 4 \B */ + OP_WORD_BOUNDARY, /* 5 \b */ + OP_NOT_DIGIT, /* 6 \D */ + OP_DIGIT, /* 7 \d */ + OP_NOT_WHITESPACE, /* 8 \S */ + OP_WHITESPACE, /* 9 \s */ + OP_NOT_WORDCHAR, /* 10 \W */ + OP_WORDCHAR, /* 11 \w */ + + OP_ANY, /* 12 Match any character except newline (\N) */ + OP_ALLANY, /* 13 Match any character */ + OP_ANYBYTE, /* 14 Match any byte (\C); different to OP_ANY for UTF-8 */ + OP_NOTPROP, /* 15 \P (not Unicode property) */ + OP_PROP, /* 16 \p (Unicode property) */ + OP_ANYNL, /* 17 \R (any newline sequence) */ + OP_NOT_HSPACE, /* 18 \H (not horizontal whitespace) */ + OP_HSPACE, /* 19 \h (horizontal whitespace) */ + OP_NOT_VSPACE, /* 20 \V (not vertical whitespace) */ + OP_VSPACE, /* 21 \v (vertical whitespace) */ + OP_EXTUNI, /* 22 \X (extended Unicode sequence */ + OP_EODN, /* 23 End of data or \n at end of data (\Z) */ + OP_EOD, /* 24 End of data (\z) */ + + /* Line end assertions */ + + OP_DOLL, /* 25 End of line - not multiline */ + OP_DOLLM, /* 26 End of line - multiline */ + OP_CIRC, /* 27 Start of line - not multiline */ + OP_CIRCM, /* 28 Start of line - multiline */ + + /* Single characters; caseful must precede the caseless ones */ + + OP_CHAR, /* 29 Match one character, casefully */ + OP_CHARI, /* 30 Match one character, caselessly */ + OP_NOT, /* 31 Match one character, not the given one, casefully */ + OP_NOTI, /* 32 Match one character, not the given one, caselessly */ + + /* The following sets of 13 opcodes must always be kept in step because + the offset from the first one is used to generate the others. */ + + /* Repeated characters; caseful must precede the caseless ones */ + + OP_STAR, /* 33 The maximizing and minimizing versions of */ + OP_MINSTAR, /* 34 these six opcodes must come in pairs, with */ + OP_PLUS, /* 35 the minimizing one second. */ + OP_MINPLUS, /* 36 */ + OP_QUERY, /* 37 */ + OP_MINQUERY, /* 38 */ + + OP_UPTO, /* 39 From 0 to n matches of one character, caseful*/ + OP_MINUPTO, /* 40 */ + OP_EXACT, /* 41 Exactly n matches */ + + OP_POSSTAR, /* 42 Possessified star, caseful */ + OP_POSPLUS, /* 43 Possessified plus, caseful */ + OP_POSQUERY, /* 44 Posesssified query, caseful */ + OP_POSUPTO, /* 45 Possessified upto, caseful */ + + /* Repeated characters; caseless must follow the caseful ones */ + + OP_STARI, /* 46 */ + OP_MINSTARI, /* 47 */ + OP_PLUSI, /* 48 */ + OP_MINPLUSI, /* 49 */ + OP_QUERYI, /* 50 */ + OP_MINQUERYI, /* 51 */ + + OP_UPTOI, /* 52 From 0 to n matches of one character, caseless */ + OP_MINUPTOI, /* 53 */ + OP_EXACTI, /* 54 */ + + OP_POSSTARI, /* 55 Possessified star, caseless */ + OP_POSPLUSI, /* 56 Possessified plus, caseless */ + OP_POSQUERYI, /* 57 Posesssified query, caseless */ + OP_POSUPTOI, /* 58 Possessified upto, caseless */ + + /* The negated ones must follow the non-negated ones, and match them */ + /* Negated repeated character, caseful; must precede the caseless ones */ + + OP_NOTSTAR, /* 59 The maximizing and minimizing versions of */ + OP_NOTMINSTAR, /* 60 these six opcodes must come in pairs, with */ + OP_NOTPLUS, /* 61 the minimizing one second. They must be in */ + OP_NOTMINPLUS, /* 62 exactly the same order as those above. */ + OP_NOTQUERY, /* 63 */ + OP_NOTMINQUERY, /* 64 */ + + OP_NOTUPTO, /* 65 From 0 to n matches, caseful */ + OP_NOTMINUPTO, /* 66 */ + OP_NOTEXACT, /* 67 Exactly n matches */ + + OP_NOTPOSSTAR, /* 68 Possessified versions, caseful */ + OP_NOTPOSPLUS, /* 69 */ + OP_NOTPOSQUERY, /* 70 */ + OP_NOTPOSUPTO, /* 71 */ + + /* Negated repeated character, caseless; must follow the caseful ones */ + + OP_NOTSTARI, /* 72 */ + OP_NOTMINSTARI, /* 73 */ + OP_NOTPLUSI, /* 74 */ + OP_NOTMINPLUSI, /* 75 */ + OP_NOTQUERYI, /* 76 */ + OP_NOTMINQUERYI, /* 77 */ + + OP_NOTUPTOI, /* 78 From 0 to n matches, caseless */ + OP_NOTMINUPTOI, /* 79 */ + OP_NOTEXACTI, /* 80 Exactly n matches */ + + OP_NOTPOSSTARI, /* 81 Possessified versions, caseless */ + OP_NOTPOSPLUSI, /* 82 */ + OP_NOTPOSQUERYI, /* 83 */ + OP_NOTPOSUPTOI, /* 84 */ + + /* Character types */ + + OP_TYPESTAR, /* 85 The maximizing and minimizing versions of */ + OP_TYPEMINSTAR, /* 86 these six opcodes must come in pairs, with */ + OP_TYPEPLUS, /* 87 the minimizing one second. These codes must */ + OP_TYPEMINPLUS, /* 88 be in exactly the same order as those above. */ + OP_TYPEQUERY, /* 89 */ + OP_TYPEMINQUERY, /* 90 */ + + OP_TYPEUPTO, /* 91 From 0 to n matches */ + OP_TYPEMINUPTO, /* 92 */ + OP_TYPEEXACT, /* 93 Exactly n matches */ + + OP_TYPEPOSSTAR, /* 94 Possessified versions */ + OP_TYPEPOSPLUS, /* 95 */ + OP_TYPEPOSQUERY, /* 96 */ + OP_TYPEPOSUPTO, /* 97 */ + + /* These are used for character classes and back references; only the + first six are the same as the sets above. */ + + OP_CRSTAR, /* 98 The maximizing and minimizing versions of */ + OP_CRMINSTAR, /* 99 all these opcodes must come in pairs, with */ + OP_CRPLUS, /* 100 the minimizing one second. These codes must */ + OP_CRMINPLUS, /* 101 be in exactly the same order as those above. */ + OP_CRQUERY, /* 102 */ + OP_CRMINQUERY, /* 103 */ + + OP_CRRANGE, /* 104 These are different to the three sets above. */ + OP_CRMINRANGE, /* 105 */ + + OP_CRPOSSTAR, /* 106 Possessified versions */ + OP_CRPOSPLUS, /* 107 */ + OP_CRPOSQUERY, /* 108 */ + OP_CRPOSRANGE, /* 109 */ + + /* End of quantifier opcodes */ + + OP_CLASS, /* 110 Match a character class, chars < 256 only */ + OP_NCLASS, /* 111 Same, but the bitmap was created from a negative + class - the difference is relevant only when a + character > 255 is encountered. */ + OP_XCLASS, /* 112 Extended class for handling > 255 chars within the + class. This does both positive and negative. */ + OP_REF, /* 113 Match a back reference, casefully */ + OP_REFI, /* 114 Match a back reference, caselessly */ + OP_DNREF, /* 115 Match a duplicate name backref, casefully */ + OP_DNREFI, /* 116 Match a duplicate name backref, caselessly */ + OP_RECURSE, /* 117 Match a numbered subpattern (possibly recursive) */ + OP_CALLOUT, /* 118 Call out to external function if provided */ + + OP_ALT, /* 119 Start of alternation */ + OP_KET, /* 120 End of group that doesn't have an unbounded repeat */ + OP_KETRMAX, /* 121 These two must remain together and in this */ + OP_KETRMIN, /* 122 order. They are for groups the repeat for ever. */ + OP_KETRPOS, /* 123 Possessive unlimited repeat. */ + + /* The assertions must come before BRA, CBRA, ONCE, and COND, and the four + asserts must remain in order. */ + + OP_REVERSE, /* 124 Move pointer back - used in lookbehind assertions */ + OP_ASSERT, /* 125 Positive lookahead */ + OP_ASSERT_NOT, /* 126 Negative lookahead */ + OP_ASSERTBACK, /* 127 Positive lookbehind */ + OP_ASSERTBACK_NOT, /* 128 Negative lookbehind */ + + /* ONCE, ONCE_NC, BRA, BRAPOS, CBRA, CBRAPOS, and COND must come immediately + after the assertions, with ONCE first, as there's a test for >= ONCE for a + subpattern that isn't an assertion. The POS versions must immediately follow + the non-POS versions in each case. */ + + OP_ONCE, /* 129 Atomic group, contains captures */ + OP_ONCE_NC, /* 130 Atomic group containing no captures */ + OP_BRA, /* 131 Start of non-capturing bracket */ + OP_BRAPOS, /* 132 Ditto, with unlimited, possessive repeat */ + OP_CBRA, /* 133 Start of capturing bracket */ + OP_CBRAPOS, /* 134 Ditto, with unlimited, possessive repeat */ + OP_COND, /* 135 Conditional group */ + + /* These five must follow the previous five, in the same order. There's a + check for >= SBRA to distinguish the two sets. */ + + OP_SBRA, /* 136 Start of non-capturing bracket, check empty */ + OP_SBRAPOS, /* 137 Ditto, with unlimited, possessive repeat */ + OP_SCBRA, /* 138 Start of capturing bracket, check empty */ + OP_SCBRAPOS, /* 139 Ditto, with unlimited, possessive repeat */ + OP_SCOND, /* 140 Conditional group, check empty */ + + /* The next two pairs must (respectively) be kept together. */ + + OP_CREF, /* 141 Used to hold a capture number as condition */ + OP_DNCREF, /* 142 Used to point to duplicate names as a condition */ + OP_RREF, /* 143 Used to hold a recursion number as condition */ + OP_DNRREF, /* 144 Used to point to duplicate names as a condition */ + OP_DEF, /* 145 The DEFINE condition */ + + OP_BRAZERO, /* 146 These two must remain together and in this */ + OP_BRAMINZERO, /* 147 order. */ + OP_BRAPOSZERO, /* 148 */ + + /* These are backtracking control verbs */ + + OP_MARK, /* 149 always has an argument */ + OP_PRUNE, /* 150 */ + OP_PRUNE_ARG, /* 151 same, but with argument */ + OP_SKIP, /* 152 */ + OP_SKIP_ARG, /* 153 same, but with argument */ + OP_THEN, /* 154 */ + OP_THEN_ARG, /* 155 same, but with argument */ + OP_COMMIT, /* 156 */ + + /* These are forced failure and success verbs */ + + OP_FAIL, /* 157 */ + OP_ACCEPT, /* 158 */ + OP_ASSERT_ACCEPT, /* 159 Used inside assertions */ + OP_CLOSE, /* 160 Used before OP_ACCEPT to close open captures */ + + /* This is used to skip a subpattern with a {0} quantifier */ + + OP_SKIPZERO, /* 161 */ + + /* This is not an opcode, but is used to check that tables indexed by opcode + are the correct length, in order to catch updating errors - there have been + some in the past. */ + + OP_TABLE_LENGTH +}; + +/* *** NOTE NOTE NOTE *** Whenever the list above is updated, the two macro +definitions that follow must also be updated to match. There are also tables +called "opcode_possessify" in pcre_compile.c and "coptable" and "poptable" in +pcre_dfa_exec.c that must be updated. */ + + +/* This macro defines textual names for all the opcodes. These are used only +for debugging, and some of them are only partial names. The macro is referenced +only in pcre_printint.c, which fills out the full names in many cases (and in +some cases doesn't actually use these names at all). */ + +#define OP_NAME_LIST \ + "End", "\\A", "\\G", "\\K", "\\B", "\\b", "\\D", "\\d", \ + "\\S", "\\s", "\\W", "\\w", "Any", "AllAny", "Anybyte", \ + "notprop", "prop", "\\R", "\\H", "\\h", "\\V", "\\v", \ + "extuni", "\\Z", "\\z", \ + "$", "$", "^", "^", "char", "chari", "not", "noti", \ + "*", "*?", "+", "+?", "?", "??", \ + "{", "{", "{", \ + "*+","++", "?+", "{", \ + "*", "*?", "+", "+?", "?", "??", \ + "{", "{", "{", \ + "*+","++", "?+", "{", \ + "*", "*?", "+", "+?", "?", "??", \ + "{", "{", "{", \ + "*+","++", "?+", "{", \ + "*", "*?", "+", "+?", "?", "??", \ + "{", "{", "{", \ + "*+","++", "?+", "{", \ + "*", "*?", "+", "+?", "?", "??", "{", "{", "{", \ + "*+","++", "?+", "{", \ + "*", "*?", "+", "+?", "?", "??", "{", "{", \ + "*+","++", "?+", "{", \ + "class", "nclass", "xclass", "Ref", "Refi", "DnRef", "DnRefi", \ + "Recurse", "Callout", \ + "Alt", "Ket", "KetRmax", "KetRmin", "KetRpos", \ + "Reverse", "Assert", "Assert not", "AssertB", "AssertB not", \ + "Once", "Once_NC", \ + "Bra", "BraPos", "CBra", "CBraPos", \ + "Cond", \ + "SBra", "SBraPos", "SCBra", "SCBraPos", \ + "SCond", \ + "Cond ref", "Cond dnref", "Cond rec", "Cond dnrec", "Cond def", \ + "Brazero", "Braminzero", "Braposzero", \ + "*MARK", "*PRUNE", "*PRUNE", "*SKIP", "*SKIP", \ + "*THEN", "*THEN", "*COMMIT", "*FAIL", \ + "*ACCEPT", "*ASSERT_ACCEPT", \ + "Close", "Skip zero" + + +/* This macro defines the length of fixed length operations in the compiled +regex. The lengths are used when searching for specific things, and also in the +debugging printing of a compiled regex. We use a macro so that it can be +defined close to the definitions of the opcodes themselves. + +As things have been extended, some of these are no longer fixed lenths, but are +minima instead. For example, the length of a single-character repeat may vary +in UTF-8 mode. The code that uses this table must know about such things. */ + +#define OP_LENGTHS \ + 1, /* End */ \ + 1, 1, 1, 1, 1, /* \A, \G, \K, \B, \b */ \ + 1, 1, 1, 1, 1, 1, /* \D, \d, \S, \s, \W, \w */ \ + 1, 1, 1, /* Any, AllAny, Anybyte */ \ + 3, 3, /* \P, \p */ \ + 1, 1, 1, 1, 1, /* \R, \H, \h, \V, \v */ \ + 1, /* \X */ \ + 1, 1, 1, 1, 1, 1, /* \Z, \z, $, $M ^, ^M */ \ + 2, /* Char - the minimum length */ \ + 2, /* Chari - the minimum length */ \ + 2, /* not */ \ + 2, /* noti */ \ + /* Positive single-char repeats ** These are */ \ + 2, 2, 2, 2, 2, 2, /* *, *?, +, +?, ?, ?? ** minima in */ \ + 2+IMM2_SIZE, 2+IMM2_SIZE, /* upto, minupto ** mode */ \ + 2+IMM2_SIZE, /* exact */ \ + 2, 2, 2, 2+IMM2_SIZE, /* *+, ++, ?+, upto+ */ \ + 2, 2, 2, 2, 2, 2, /* *I, *?I, +I, +?I, ?I, ??I ** UTF-8 */ \ + 2+IMM2_SIZE, 2+IMM2_SIZE, /* upto I, minupto I */ \ + 2+IMM2_SIZE, /* exact I */ \ + 2, 2, 2, 2+IMM2_SIZE, /* *+I, ++I, ?+I, upto+I */ \ + /* Negative single-char repeats - only for chars < 256 */ \ + 2, 2, 2, 2, 2, 2, /* NOT *, *?, +, +?, ?, ?? */ \ + 2+IMM2_SIZE, 2+IMM2_SIZE, /* NOT upto, minupto */ \ + 2+IMM2_SIZE, /* NOT exact */ \ + 2, 2, 2, 2+IMM2_SIZE, /* Possessive NOT *, +, ?, upto */ \ + 2, 2, 2, 2, 2, 2, /* NOT *I, *?I, +I, +?I, ?I, ??I */ \ + 2+IMM2_SIZE, 2+IMM2_SIZE, /* NOT upto I, minupto I */ \ + 2+IMM2_SIZE, /* NOT exact I */ \ + 2, 2, 2, 2+IMM2_SIZE, /* Possessive NOT *I, +I, ?I, upto I */ \ + /* Positive type repeats */ \ + 2, 2, 2, 2, 2, 2, /* Type *, *?, +, +?, ?, ?? */ \ + 2+IMM2_SIZE, 2+IMM2_SIZE, /* Type upto, minupto */ \ + 2+IMM2_SIZE, /* Type exact */ \ + 2, 2, 2, 2+IMM2_SIZE, /* Possessive *+, ++, ?+, upto+ */ \ + /* Character class & ref repeats */ \ + 1, 1, 1, 1, 1, 1, /* *, *?, +, +?, ?, ?? */ \ + 1+2*IMM2_SIZE, 1+2*IMM2_SIZE, /* CRRANGE, CRMINRANGE */ \ + 1, 1, 1, 1+2*IMM2_SIZE, /* Possessive *+, ++, ?+, CRPOSRANGE */ \ + 1+(32/sizeof(pcre_uchar)), /* CLASS */ \ + 1+(32/sizeof(pcre_uchar)), /* NCLASS */ \ + 0, /* XCLASS - variable length */ \ + 1+IMM2_SIZE, /* REF */ \ + 1+IMM2_SIZE, /* REFI */ \ + 1+2*IMM2_SIZE, /* DNREF */ \ + 1+2*IMM2_SIZE, /* DNREFI */ \ + 1+LINK_SIZE, /* RECURSE */ \ + 2+2*LINK_SIZE, /* CALLOUT */ \ + 1+LINK_SIZE, /* Alt */ \ + 1+LINK_SIZE, /* Ket */ \ + 1+LINK_SIZE, /* KetRmax */ \ + 1+LINK_SIZE, /* KetRmin */ \ + 1+LINK_SIZE, /* KetRpos */ \ + 1+LINK_SIZE, /* Reverse */ \ + 1+LINK_SIZE, /* Assert */ \ + 1+LINK_SIZE, /* Assert not */ \ + 1+LINK_SIZE, /* Assert behind */ \ + 1+LINK_SIZE, /* Assert behind not */ \ + 1+LINK_SIZE, /* ONCE */ \ + 1+LINK_SIZE, /* ONCE_NC */ \ + 1+LINK_SIZE, /* BRA */ \ + 1+LINK_SIZE, /* BRAPOS */ \ + 1+LINK_SIZE+IMM2_SIZE, /* CBRA */ \ + 1+LINK_SIZE+IMM2_SIZE, /* CBRAPOS */ \ + 1+LINK_SIZE, /* COND */ \ + 1+LINK_SIZE, /* SBRA */ \ + 1+LINK_SIZE, /* SBRAPOS */ \ + 1+LINK_SIZE+IMM2_SIZE, /* SCBRA */ \ + 1+LINK_SIZE+IMM2_SIZE, /* SCBRAPOS */ \ + 1+LINK_SIZE, /* SCOND */ \ + 1+IMM2_SIZE, 1+2*IMM2_SIZE, /* CREF, DNCREF */ \ + 1+IMM2_SIZE, 1+2*IMM2_SIZE, /* RREF, DNRREF */ \ + 1, /* DEF */ \ + 1, 1, 1, /* BRAZERO, BRAMINZERO, BRAPOSZERO */ \ + 3, 1, 3, /* MARK, PRUNE, PRUNE_ARG */ \ + 1, 3, /* SKIP, SKIP_ARG */ \ + 1, 3, /* THEN, THEN_ARG */ \ + 1, 1, 1, 1, /* COMMIT, FAIL, ACCEPT, ASSERT_ACCEPT */ \ + 1+IMM2_SIZE, 1 /* CLOSE, SKIPZERO */ + +/* A magic value for OP_RREF to indicate the "any recursion" condition. */ + +#define RREF_ANY 0xffff + +/* Compile time error code numbers. They are given names so that they can more +easily be tracked. When a new number is added, the table called eint in +pcreposix.c must be updated. */ + +enum { ERR0, ERR1, ERR2, ERR3, ERR4, ERR5, ERR6, ERR7, ERR8, ERR9, + ERR10, ERR11, ERR12, ERR13, ERR14, ERR15, ERR16, ERR17, ERR18, ERR19, + ERR20, ERR21, ERR22, ERR23, ERR24, ERR25, ERR26, ERR27, ERR28, ERR29, + ERR30, ERR31, ERR32, ERR33, ERR34, ERR35, ERR36, ERR37, ERR38, ERR39, + ERR40, ERR41, ERR42, ERR43, ERR44, ERR45, ERR46, ERR47, ERR48, ERR49, + ERR50, ERR51, ERR52, ERR53, ERR54, ERR55, ERR56, ERR57, ERR58, ERR59, + ERR60, ERR61, ERR62, ERR63, ERR64, ERR65, ERR66, ERR67, ERR68, ERR69, + ERR70, ERR71, ERR72, ERR73, ERR74, ERR75, ERR76, ERR77, ERR78, ERR79, + ERR80, ERR81, ERR82, ERR83, ERR84, ERR85, ERRCOUNT }; + +/* JIT compiling modes. The function list is indexed by them. */ + +enum { JIT_COMPILE, JIT_PARTIAL_SOFT_COMPILE, JIT_PARTIAL_HARD_COMPILE, + JIT_NUMBER_OF_COMPILE_MODES }; + +/* The real format of the start of the pcre block; the index of names and the +code vector run on as long as necessary after the end. We store an explicit +offset to the name table so that if a regex is compiled on one host, saved, and +then run on another where the size of pointers is different, all might still +be well. + +The size of the structure must be a multiple of 8 bytes. For the case of +compiled-on-4 and run-on-8, we include an extra pointer that is always NULL so +that there are an even number of pointers which therefore are a multiple of 8 +bytes. + +It is necessary to fork the struct for the 32 bit library, since it needs to +use pcre_uint32 for first_char and req_char. We can't put an ifdef inside the +typedef because pcretest needs access to the struct of the 8-, 16- and 32-bit +variants. + +*** WARNING *** +When new fields are added to these structures, remember to adjust the code in +pcre_byte_order.c that is concerned with swapping the byte order of the fields +when a compiled regex is reloaded on a host with different endianness. +*** WARNING *** +There is also similar byte-flipping code in pcretest.c, which is used for +testing the byte-flipping features. It must also be kept in step. +*** WARNING *** +*/ + +typedef struct real_pcre8_or_16 { + pcre_uint32 magic_number; + pcre_uint32 size; /* Total that was malloced */ + pcre_uint32 options; /* Public options */ + pcre_uint32 flags; /* Private flags */ + pcre_uint32 limit_match; /* Limit set from regex */ + pcre_uint32 limit_recursion; /* Limit set from regex */ + pcre_uint16 first_char; /* Starting character */ + pcre_uint16 req_char; /* This character must be seen */ + pcre_uint16 max_lookbehind; /* Longest lookbehind (characters) */ + pcre_uint16 top_bracket; /* Highest numbered group */ + pcre_uint16 top_backref; /* Highest numbered back reference */ + pcre_uint16 name_table_offset; /* Offset to name table that follows */ + pcre_uint16 name_entry_size; /* Size of any name items */ + pcre_uint16 name_count; /* Number of name items */ + pcre_uint16 ref_count; /* Reference count */ + pcre_uint16 dummy1; /* To ensure size is a multiple of 8 */ + pcre_uint16 dummy2; /* To ensure size is a multiple of 8 */ + pcre_uint16 dummy3; /* To ensure size is a multiple of 8 */ + const pcre_uint8 *tables; /* Pointer to tables or NULL for std */ + void *nullpad; /* NULL padding */ +} real_pcre8_or_16; + +typedef struct real_pcre8_or_16 real_pcre; +typedef struct real_pcre8_or_16 real_pcre16; + +typedef struct real_pcre32 { + pcre_uint32 magic_number; + pcre_uint32 size; /* Total that was malloced */ + pcre_uint32 options; /* Public options */ + pcre_uint32 flags; /* Private flags */ + pcre_uint32 limit_match; /* Limit set from regex */ + pcre_uint32 limit_recursion; /* Limit set from regex */ + pcre_uint32 first_char; /* Starting character */ + pcre_uint32 req_char; /* This character must be seen */ + pcre_uint16 max_lookbehind; /* Longest lookbehind (characters) */ + pcre_uint16 top_bracket; /* Highest numbered group */ + pcre_uint16 top_backref; /* Highest numbered back reference */ + pcre_uint16 name_table_offset; /* Offset to name table that follows */ + pcre_uint16 name_entry_size; /* Size of any name items */ + pcre_uint16 name_count; /* Number of name items */ + pcre_uint16 ref_count; /* Reference count */ + pcre_uint16 dummy; /* To ensure size is a multiple of 8 */ + const pcre_uint8 *tables; /* Pointer to tables or NULL for std */ + void *nullpad; /* NULL padding */ +} real_pcre32; + +#if defined COMPILE_PCRE8 +#define REAL_PCRE real_pcre +#elif defined COMPILE_PCRE16 +#define REAL_PCRE real_pcre16 +#elif defined COMPILE_PCRE32 +#define REAL_PCRE real_pcre32 +#endif + +/* Assert that the size of REAL_PCRE is divisible by 8 */ +typedef int __assert_real_pcre_size_divisible_8[(sizeof(REAL_PCRE) % 8) == 0 ? 1 : -1]; + +/* Needed in pcretest to access some fields in the real_pcre* structures + * directly. They're unified for 8/16/32 bits since the structs only differ + * after these fields; if that ever changes, need to fork those defines into + * 8/16 and 32 bit versions. */ +#define REAL_PCRE_MAGIC(re) (((REAL_PCRE*)re)->magic_number) +#define REAL_PCRE_SIZE(re) (((REAL_PCRE*)re)->size) +#define REAL_PCRE_OPTIONS(re) (((REAL_PCRE*)re)->options) +#define REAL_PCRE_FLAGS(re) (((REAL_PCRE*)re)->flags) + +/* The format of the block used to store data from pcre_study(). The same +remark (see NOTE above) about extending this structure applies. */ + +typedef struct pcre_study_data { + pcre_uint32 size; /* Total that was malloced */ + pcre_uint32 flags; /* Private flags */ + pcre_uint8 start_bits[32]; /* Starting char bits */ + pcre_uint32 minlength; /* Minimum subject length */ +} pcre_study_data; + +/* Structure for building a chain of open capturing subpatterns during +compiling, so that instructions to close them can be compiled when (*ACCEPT) is +encountered. This is also used to identify subpatterns that contain recursive +back references to themselves, so that they can be made atomic. */ + +typedef struct open_capitem { + struct open_capitem *next; /* Chain link */ + pcre_uint16 number; /* Capture number */ + pcre_uint16 flag; /* Set TRUE if recursive back ref */ +} open_capitem; + +/* Structure for building a list of named groups during the first pass of +compiling. */ + +typedef struct named_group { + const pcre_uchar *name; /* Points to the name in the pattern */ + int length; /* Length of the name */ + pcre_uint32 number; /* Group number */ +} named_group; + +/* Structure for passing "static" information around between the functions +doing the compiling, so that they are thread-safe. */ + +typedef struct compile_data { + const pcre_uint8 *lcc; /* Points to lower casing table */ + const pcre_uint8 *fcc; /* Points to case-flipping table */ + const pcre_uint8 *cbits; /* Points to character type table */ + const pcre_uint8 *ctypes; /* Points to table of type maps */ + const pcre_uchar *start_workspace;/* The start of working space */ + const pcre_uchar *start_code; /* The start of the compiled code */ + const pcre_uchar *start_pattern; /* The start of the pattern */ + const pcre_uchar *end_pattern; /* The end of the pattern */ + pcre_uchar *hwm; /* High watermark of workspace */ + open_capitem *open_caps; /* Chain of open capture items */ + named_group *named_groups; /* Points to vector in pre-compile */ + pcre_uchar *name_table; /* The name/number table */ + int names_found; /* Number of entries so far */ + int name_entry_size; /* Size of each entry */ + int named_group_list_size; /* Number of entries in the list */ + int workspace_size; /* Size of workspace */ + unsigned int bracount; /* Count of capturing parens as we compile */ + int final_bracount; /* Saved value after first pass */ + int max_lookbehind; /* Maximum lookbehind (characters) */ + int top_backref; /* Maximum back reference */ + unsigned int backref_map; /* Bitmap of low back refs */ + unsigned int namedrefcount; /* Number of backreferences by name */ + int parens_depth; /* Depth of nested parentheses */ + int assert_depth; /* Depth of nested assertions */ + pcre_uint32 external_options; /* External (initial) options */ + pcre_uint32 external_flags; /* External flag bits to be set */ + int req_varyopt; /* "After variable item" flag for reqbyte */ + BOOL had_accept; /* (*ACCEPT) encountered */ + BOOL had_pruneorskip; /* (*PRUNE) or (*SKIP) encountered */ + BOOL check_lookbehind; /* Lookbehinds need later checking */ + BOOL dupnames; /* Duplicate names exist */ + int nltype; /* Newline type */ + int nllen; /* Newline string length */ + pcre_uchar nl[4]; /* Newline string when fixed length */ +} compile_data; + +/* Structure for maintaining a chain of pointers to the currently incomplete +branches, for testing for left recursion while compiling. */ + +typedef struct branch_chain { + struct branch_chain *outer; + pcre_uchar *current_branch; +} branch_chain; + +/* Structure for items in a linked list that represents an explicit recursive +call within the pattern; used by pcre_exec(). */ + +typedef struct recursion_info { + struct recursion_info *prevrec; /* Previous recursion record (or NULL) */ + unsigned int group_num; /* Number of group that was called */ + int *offset_save; /* Pointer to start of saved offsets */ + int saved_max; /* Number of saved offsets */ + int saved_capture_last; /* Last capture number */ + PCRE_PUCHAR subject_position; /* Position at start of recursion */ +} recursion_info; + +/* A similar structure for pcre_dfa_exec(). */ + +typedef struct dfa_recursion_info { + struct dfa_recursion_info *prevrec; + int group_num; + PCRE_PUCHAR subject_position; +} dfa_recursion_info; + +/* Structure for building a chain of data for holding the values of the subject +pointer at the start of each subpattern, so as to detect when an empty string +has been matched by a subpattern - to break infinite loops; used by +pcre_exec(). */ + +typedef struct eptrblock { + struct eptrblock *epb_prev; + PCRE_PUCHAR epb_saved_eptr; +} eptrblock; + + +/* Structure for passing "static" information around between the functions +doing traditional NFA matching, so that they are thread-safe. */ + +typedef struct match_data { + unsigned long int match_call_count; /* As it says */ + unsigned long int match_limit; /* As it says */ + unsigned long int match_limit_recursion; /* As it says */ + int *offset_vector; /* Offset vector */ + int offset_end; /* One past the end */ + int offset_max; /* The maximum usable for return data */ + int nltype; /* Newline type */ + int nllen; /* Newline string length */ + int name_count; /* Number of names in name table */ + int name_entry_size; /* Size of entry in names table */ + unsigned int skip_arg_count; /* For counting SKIP_ARGs */ + unsigned int ignore_skip_arg; /* For re-run when SKIP arg name not found */ + pcre_uchar *name_table; /* Table of names */ + pcre_uchar nl[4]; /* Newline string when fixed */ + const pcre_uint8 *lcc; /* Points to lower casing table */ + const pcre_uint8 *fcc; /* Points to case-flipping table */ + const pcre_uint8 *ctypes; /* Points to table of type maps */ + BOOL notbol; /* NOTBOL flag */ + BOOL noteol; /* NOTEOL flag */ + BOOL utf; /* UTF-8 / UTF-16 flag */ + BOOL jscript_compat; /* JAVASCRIPT_COMPAT flag */ + BOOL use_ucp; /* PCRE_UCP flag */ + BOOL endonly; /* Dollar not before final \n */ + BOOL notempty; /* Empty string match not wanted */ + BOOL notempty_atstart; /* Empty string match at start not wanted */ + BOOL hitend; /* Hit the end of the subject at some point */ + BOOL bsr_anycrlf; /* \R is just any CRLF, not full Unicode */ + BOOL hasthen; /* Pattern contains (*THEN) */ + const pcre_uchar *start_code; /* For use when recursing */ + PCRE_PUCHAR start_subject; /* Start of the subject string */ + PCRE_PUCHAR end_subject; /* End of the subject string */ + PCRE_PUCHAR start_match_ptr; /* Start of matched string */ + PCRE_PUCHAR end_match_ptr; /* Subject position at end match */ + PCRE_PUCHAR start_used_ptr; /* Earliest consulted character */ + int partial; /* PARTIAL options */ + int end_offset_top; /* Highwater mark at end of match */ + pcre_int32 capture_last; /* Most recent capture number + overflow flag */ + int start_offset; /* The start offset value */ + int match_function_type; /* Set for certain special calls of MATCH() */ + eptrblock *eptrchain; /* Chain of eptrblocks for tail recursions */ + int eptrn; /* Next free eptrblock */ + recursion_info *recursive; /* Linked list of recursion data */ + void *callout_data; /* To pass back to callouts */ + const pcre_uchar *mark; /* Mark pointer to pass back on success */ + const pcre_uchar *nomatch_mark;/* Mark pointer to pass back on failure */ + const pcre_uchar *once_target; /* Where to back up to for atomic groups */ +#ifdef NO_RECURSE + void *match_frames_base; /* For remembering malloc'd frames */ +#endif +} match_data; + +/* A similar structure is used for the same purpose by the DFA matching +functions. */ + +typedef struct dfa_match_data { + const pcre_uchar *start_code; /* Start of the compiled pattern */ + const pcre_uchar *start_subject ; /* Start of the subject string */ + const pcre_uchar *end_subject; /* End of subject string */ + const pcre_uchar *start_used_ptr; /* Earliest consulted character */ + const pcre_uint8 *tables; /* Character tables */ + int start_offset; /* The start offset value */ + int moptions; /* Match options */ + int poptions; /* Pattern options */ + int nltype; /* Newline type */ + int nllen; /* Newline string length */ + pcre_uchar nl[4]; /* Newline string when fixed */ + void *callout_data; /* To pass back to callouts */ + dfa_recursion_info *recursive; /* Linked list of recursion data */ +} dfa_match_data; + +/* Bit definitions for entries in the pcre_ctypes table. */ + +#define ctype_space 0x01 +#define ctype_letter 0x02 +#define ctype_digit 0x04 +#define ctype_xdigit 0x08 +#define ctype_word 0x10 /* alphanumeric or '_' */ +#define ctype_meta 0x80 /* regexp meta char or zero (end pattern) */ + +/* Offsets for the bitmap tables in pcre_cbits. Each table contains a set +of bits for a class map. Some classes are built by combining these tables. */ + +#define cbit_space 0 /* [:space:] or \s */ +#define cbit_xdigit 32 /* [:xdigit:] */ +#define cbit_digit 64 /* [:digit:] or \d */ +#define cbit_upper 96 /* [:upper:] */ +#define cbit_lower 128 /* [:lower:] */ +#define cbit_word 160 /* [:word:] or \w */ +#define cbit_graph 192 /* [:graph:] */ +#define cbit_print 224 /* [:print:] */ +#define cbit_punct 256 /* [:punct:] */ +#define cbit_cntrl 288 /* [:cntrl:] */ +#define cbit_length 320 /* Length of the cbits table */ + +/* Offsets of the various tables from the base tables pointer, and +total length. */ + +#define lcc_offset 0 +#define fcc_offset 256 +#define cbits_offset 512 +#define ctypes_offset (cbits_offset + cbit_length) +#define tables_length (ctypes_offset + 256) + +/* Internal function and data prefixes. */ + +#if defined COMPILE_PCRE8 +#ifndef PUBL +#define PUBL(name) pcre_##name +#endif +#ifndef PRIV +#define PRIV(name) _pcre_##name +#endif +#elif defined COMPILE_PCRE16 +#ifndef PUBL +#define PUBL(name) pcre16_##name +#endif +#ifndef PRIV +#define PRIV(name) _pcre16_##name +#endif +#elif defined COMPILE_PCRE32 +#ifndef PUBL +#define PUBL(name) pcre32_##name +#endif +#ifndef PRIV +#define PRIV(name) _pcre32_##name +#endif +#else +#error Unsupported compiling mode +#endif /* COMPILE_PCRE[8|16|32] */ + +/* Layout of the UCP type table that translates property names into types and +codes. Each entry used to point directly to a name, but to reduce the number of +relocations in shared libraries, it now has an offset into a single string +instead. */ + +typedef struct { + pcre_uint16 name_offset; + pcre_uint16 type; + pcre_uint16 value; +} ucp_type_table; + + +/* Internal shared data tables. These are tables that are used by more than one +of the exported public functions. They have to be "external" in the C sense, +but are not part of the PCRE public API. The data for these tables is in the +pcre_tables.c module. */ + +#ifdef COMPILE_PCRE8 +extern const int PRIV(utf8_table1)[]; +extern const int PRIV(utf8_table1_size); +extern const int PRIV(utf8_table2)[]; +extern const int PRIV(utf8_table3)[]; +extern const pcre_uint8 PRIV(utf8_table4)[]; +#endif /* COMPILE_PCRE8 */ + +extern const char PRIV(utt_names)[]; +extern const ucp_type_table PRIV(utt)[]; +extern const int PRIV(utt_size); + +extern const pcre_uint8 PRIV(OP_lengths)[]; +extern const pcre_uint8 PRIV(default_tables)[]; + +extern const pcre_uint32 PRIV(hspace_list)[]; +extern const pcre_uint32 PRIV(vspace_list)[]; + + +/* Internal shared functions. These are functions that are used by more than +one of the exported public functions. They have to be "external" in the C +sense, but are not part of the PCRE public API. */ + +/* String comparison functions. */ +#if defined COMPILE_PCRE8 + +#define STRCMP_UC_UC(str1, str2) \ + strcmp((char *)(str1), (char *)(str2)) +#define STRCMP_UC_C8(str1, str2) \ + strcmp((char *)(str1), (str2)) +#define STRNCMP_UC_UC(str1, str2, num) \ + strncmp((char *)(str1), (char *)(str2), (num)) +#define STRNCMP_UC_C8(str1, str2, num) \ + strncmp((char *)(str1), (str2), (num)) +#define STRLEN_UC(str) strlen((const char *)str) + +#elif defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + +extern int PRIV(strcmp_uc_uc)(const pcre_uchar *, + const pcre_uchar *); +extern int PRIV(strcmp_uc_c8)(const pcre_uchar *, + const char *); +extern int PRIV(strncmp_uc_uc)(const pcre_uchar *, + const pcre_uchar *, unsigned int num); +extern int PRIV(strncmp_uc_c8)(const pcre_uchar *, + const char *, unsigned int num); +extern unsigned int PRIV(strlen_uc)(const pcre_uchar *str); + +#define STRCMP_UC_UC(str1, str2) \ + PRIV(strcmp_uc_uc)((str1), (str2)) +#define STRCMP_UC_C8(str1, str2) \ + PRIV(strcmp_uc_c8)((str1), (str2)) +#define STRNCMP_UC_UC(str1, str2, num) \ + PRIV(strncmp_uc_uc)((str1), (str2), (num)) +#define STRNCMP_UC_C8(str1, str2, num) \ + PRIV(strncmp_uc_c8)((str1), (str2), (num)) +#define STRLEN_UC(str) PRIV(strlen_uc)(str) + +#endif /* COMPILE_PCRE[8|16|32] */ + +#if defined COMPILE_PCRE8 || defined COMPILE_PCRE16 + +#define STRCMP_UC_UC_TEST(str1, str2) STRCMP_UC_UC(str1, str2) +#define STRCMP_UC_C8_TEST(str1, str2) STRCMP_UC_C8(str1, str2) + +#elif defined COMPILE_PCRE32 + +extern int PRIV(strcmp_uc_uc_utf)(const pcre_uchar *, + const pcre_uchar *); +extern int PRIV(strcmp_uc_c8_utf)(const pcre_uchar *, + const char *); + +#define STRCMP_UC_UC_TEST(str1, str2) \ + (utf ? PRIV(strcmp_uc_uc_utf)((str1), (str2)) : PRIV(strcmp_uc_uc)((str1), (str2))) +#define STRCMP_UC_C8_TEST(str1, str2) \ + (utf ? PRIV(strcmp_uc_c8_utf)((str1), (str2)) : PRIV(strcmp_uc_c8)((str1), (str2))) + +#endif /* COMPILE_PCRE[8|16|32] */ + +extern const pcre_uchar *PRIV(find_bracket)(const pcre_uchar *, BOOL, int); +extern BOOL PRIV(is_newline)(PCRE_PUCHAR, int, PCRE_PUCHAR, + int *, BOOL); +extern unsigned int PRIV(ord2utf)(pcre_uint32, pcre_uchar *); +extern int PRIV(valid_utf)(PCRE_PUCHAR, int, int *); +extern BOOL PRIV(was_newline)(PCRE_PUCHAR, int, PCRE_PUCHAR, + int *, BOOL); +extern BOOL PRIV(xclass)(pcre_uint32, const pcre_uchar *, BOOL); + +#ifdef SUPPORT_JIT +extern void PRIV(jit_compile)(const REAL_PCRE *, + PUBL(extra) *, int); +extern int PRIV(jit_exec)(const PUBL(extra) *, + const pcre_uchar *, int, int, int, int *, int); +extern void PRIV(jit_free)(void *); +extern int PRIV(jit_get_size)(void *); +extern const char* PRIV(jit_get_target)(void); +#endif + +/* Unicode character database (UCD) */ + +typedef struct { + pcre_uint8 script; /* ucp_Arabic, etc. */ + pcre_uint8 chartype; /* ucp_Cc, etc. (general categories) */ + pcre_uint8 gbprop; /* ucp_gbControl, etc. (grapheme break property) */ + pcre_uint8 caseset; /* offset to multichar other cases or zero */ + pcre_int32 other_case; /* offset to other case, or zero if none */ +} ucd_record; + +extern const pcre_uint32 PRIV(ucd_caseless_sets)[]; +extern const ucd_record PRIV(ucd_records)[]; +extern const pcre_uint8 PRIV(ucd_stage1)[]; +extern const pcre_uint16 PRIV(ucd_stage2)[]; +extern const pcre_uint32 PRIV(ucp_gentype)[]; +extern const pcre_uint32 PRIV(ucp_gbtable)[]; +#ifdef SUPPORT_JIT +extern const int PRIV(ucp_typerange)[]; +#endif + +#ifdef SUPPORT_UCP +/* UCD access macros */ + +#define UCD_BLOCK_SIZE 128 +#define GET_UCD(ch) (PRIV(ucd_records) + \ + PRIV(ucd_stage2)[PRIV(ucd_stage1)[(int)(ch) / UCD_BLOCK_SIZE] * \ + UCD_BLOCK_SIZE + (int)(ch) % UCD_BLOCK_SIZE]) + +#define UCD_CHARTYPE(ch) GET_UCD(ch)->chartype +#define UCD_SCRIPT(ch) GET_UCD(ch)->script +#define UCD_CATEGORY(ch) PRIV(ucp_gentype)[UCD_CHARTYPE(ch)] +#define UCD_GRAPHBREAK(ch) GET_UCD(ch)->gbprop +#define UCD_CASESET(ch) GET_UCD(ch)->caseset +#define UCD_OTHERCASE(ch) ((pcre_uint32)((int)ch + (int)(GET_UCD(ch)->other_case))) + +#endif /* SUPPORT_UCP */ + +#endif + +/* End of pcre_internal.h */ diff --git a/plugins/Pcre16/src/pcre_jit_compile.c b/plugins/Pcre16/src/pcre_jit_compile.c new file mode 100644 index 0000000000..e67071ef79 --- /dev/null +++ b/plugins/Pcre16/src/pcre_jit_compile.c @@ -0,0 +1,10701 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2013 University of Cambridge + + The machine code generator part (this module) was written by Zoltan Herczeg + Copyright (c) 2010-2013 + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#include "pcre_internal.h" + +#if defined SUPPORT_JIT + +/* All-in-one: Since we use the JIT compiler only from here, +we just include it. This way we don't need to touch the build +system files. */ + +#define SLJIT_MALLOC(size) (PUBL(malloc))(size) +#define SLJIT_FREE(ptr) (PUBL(free))(ptr) +#define SLJIT_CONFIG_AUTO 1 +#define SLJIT_CONFIG_STATIC 1 +#define SLJIT_VERBOSE 0 +#define SLJIT_DEBUG 0 + +#include "sljit/sljitLir.c" + +#if defined SLJIT_CONFIG_UNSUPPORTED && SLJIT_CONFIG_UNSUPPORTED +#error Unsupported architecture +#endif + +/* Defines for debugging purposes. */ + +/* 1 - Use unoptimized capturing brackets. + 2 - Enable capture_last_ptr (includes option 1). */ +/* #define DEBUG_FORCE_UNOPTIMIZED_CBRAS 2 */ + +/* 1 - Always have a control head. */ +/* #define DEBUG_FORCE_CONTROL_HEAD 1 */ + +/* Allocate memory for the regex stack on the real machine stack. +Fast, but limited size. */ +#define MACHINE_STACK_SIZE 32768 + +/* Growth rate for stack allocated by the OS. Should be the multiply +of page size. */ +#define STACK_GROWTH_RATE 8192 + +/* Enable to check that the allocation could destroy temporaries. */ +#if defined SLJIT_DEBUG && SLJIT_DEBUG +#define DESTROY_REGISTERS 1 +#endif + +/* +Short summary about the backtracking mechanism empolyed by the jit code generator: + +The code generator follows the recursive nature of the PERL compatible regular +expressions. The basic blocks of regular expressions are condition checkers +whose execute different commands depending on the result of the condition check. +The relationship between the operators can be horizontal (concatenation) and +vertical (sub-expression) (See struct backtrack_common for more details). + + 'ab' - 'a' and 'b' regexps are concatenated + 'a+' - 'a' is the sub-expression of the '+' operator + +The condition checkers are boolean (true/false) checkers. Machine code is generated +for the checker itself and for the actions depending on the result of the checker. +The 'true' case is called as the matching path (expected path), and the other is called as +the 'backtrack' path. Branch instructions are expesive for all CPUs, so we avoid taken +branches on the matching path. + + Greedy star operator (*) : + Matching path: match happens. + Backtrack path: match failed. + Non-greedy star operator (*?) : + Matching path: no need to perform a match. + Backtrack path: match is required. + +The following example shows how the code generated for a capturing bracket +with two alternatives. Let A, B, C, D are arbirary regular expressions, and +we have the following regular expression: + + A(B|C)D + +The generated code will be the following: + + A matching path + '(' matching path (pushing arguments to the stack) + B matching path + ')' matching path (pushing arguments to the stack) + D matching path + return with successful match + + D backtrack path + ')' backtrack path (If we arrived from "C" jump to the backtrack of "C") + B backtrack path + C expected path + jump to D matching path + C backtrack path + A backtrack path + + Notice, that the order of backtrack code paths are the opposite of the fast + code paths. In this way the topmost value on the stack is always belong + to the current backtrack code path. The backtrack path must check + whether there is a next alternative. If so, it needs to jump back to + the matching path eventually. Otherwise it needs to clear out its own stack + frame and continue the execution on the backtrack code paths. +*/ + +/* +Saved stack frames: + +Atomic blocks and asserts require reloading the values of private data +when the backtrack mechanism performed. Because of OP_RECURSE, the data +are not necessarly known in compile time, thus we need a dynamic restore +mechanism. + +The stack frames are stored in a chain list, and have the following format: +([ capturing bracket offset ][ start value ][ end value ])+ ... [ 0 ] [ previous head ] + +Thus we can restore the private data to a particular point in the stack. +*/ + +typedef struct jit_arguments { + /* Pointers first. */ + struct sljit_stack *stack; + const pcre_uchar *str; + const pcre_uchar *begin; + const pcre_uchar *end; + int *offsets; + pcre_uchar *uchar_ptr; + pcre_uchar *mark_ptr; + void *callout_data; + /* Everything else after. */ + pcre_uint32 limit_match; + int real_offset_count; + int offset_count; + pcre_uint8 notbol; + pcre_uint8 noteol; + pcre_uint8 notempty; + pcre_uint8 notempty_atstart; +} jit_arguments; + +typedef struct executable_functions { + void *executable_funcs[JIT_NUMBER_OF_COMPILE_MODES]; + sljit_uw *read_only_data[JIT_NUMBER_OF_COMPILE_MODES]; + sljit_uw executable_sizes[JIT_NUMBER_OF_COMPILE_MODES]; + PUBL(jit_callback) callback; + void *userdata; + pcre_uint32 top_bracket; + pcre_uint32 limit_match; +} executable_functions; + +typedef struct jump_list { + struct sljit_jump *jump; + struct jump_list *next; +} jump_list; + +typedef struct stub_list { + struct sljit_jump *start; + struct sljit_label *quit; + struct stub_list *next; +} stub_list; + +typedef struct label_addr_list { + struct sljit_label *label; + sljit_uw *addr; + struct label_addr_list *next; +} label_addr_list; + +enum frame_types { + no_frame = -1, + no_stack = -2 +}; + +enum control_types { + type_mark = 0, + type_then_trap = 1 +}; + +typedef int (SLJIT_CALL *jit_function)(jit_arguments *args); + +/* The following structure is the key data type for the recursive +code generator. It is allocated by compile_matchingpath, and contains +the arguments for compile_backtrackingpath. Must be the first member +of its descendants. */ +typedef struct backtrack_common { + /* Concatenation stack. */ + struct backtrack_common *prev; + jump_list *nextbacktracks; + /* Internal stack (for component operators). */ + struct backtrack_common *top; + jump_list *topbacktracks; + /* Opcode pointer. */ + pcre_uchar *cc; +} backtrack_common; + +typedef struct assert_backtrack { + backtrack_common common; + jump_list *condfailed; + /* Less than 0 if a frame is not needed. */ + int framesize; + /* Points to our private memory word on the stack. */ + int private_data_ptr; + /* For iterators. */ + struct sljit_label *matchingpath; +} assert_backtrack; + +typedef struct bracket_backtrack { + backtrack_common common; + /* Where to coninue if an alternative is successfully matched. */ + struct sljit_label *alternative_matchingpath; + /* For rmin and rmax iterators. */ + struct sljit_label *recursive_matchingpath; + /* For greedy ? operator. */ + struct sljit_label *zero_matchingpath; + /* Contains the branches of a failed condition. */ + union { + /* Both for OP_COND, OP_SCOND. */ + jump_list *condfailed; + assert_backtrack *assert; + /* For OP_ONCE. Less than 0 if not needed. */ + int framesize; + } u; + /* Points to our private memory word on the stack. */ + int private_data_ptr; +} bracket_backtrack; + +typedef struct bracketpos_backtrack { + backtrack_common common; + /* Points to our private memory word on the stack. */ + int private_data_ptr; + /* Reverting stack is needed. */ + int framesize; + /* Allocated stack size. */ + int stacksize; +} bracketpos_backtrack; + +typedef struct braminzero_backtrack { + backtrack_common common; + struct sljit_label *matchingpath; +} braminzero_backtrack; + +typedef struct iterator_backtrack { + backtrack_common common; + /* Next iteration. */ + struct sljit_label *matchingpath; +} iterator_backtrack; + +typedef struct recurse_entry { + struct recurse_entry *next; + /* Contains the function entry. */ + struct sljit_label *entry; + /* Collects the calls until the function is not created. */ + jump_list *calls; + /* Points to the starting opcode. */ + sljit_sw start; +} recurse_entry; + +typedef struct recurse_backtrack { + backtrack_common common; + BOOL inlined_pattern; +} recurse_backtrack; + +#define OP_THEN_TRAP OP_TABLE_LENGTH + +typedef struct then_trap_backtrack { + backtrack_common common; + /* If then_trap is not NULL, this structure contains the real + then_trap for the backtracking path. */ + struct then_trap_backtrack *then_trap; + /* Points to the starting opcode. */ + sljit_sw start; + /* Exit point for the then opcodes of this alternative. */ + jump_list *quit; + /* Frame size of the current alternative. */ + int framesize; +} then_trap_backtrack; + +#define MAX_RANGE_SIZE 4 + +typedef struct compiler_common { + /* The sljit ceneric compiler. */ + struct sljit_compiler *compiler; + /* First byte code. */ + pcre_uchar *start; + /* Maps private data offset to each opcode. */ + sljit_si *private_data_ptrs; + /* This read-only data is available during runtime. */ + sljit_uw *read_only_data; + /* The total size of the read-only data. */ + sljit_uw read_only_data_size; + /* The next free entry of the read_only_data. */ + sljit_uw *read_only_data_ptr; + /* Tells whether the capturing bracket is optimized. */ + pcre_uint8 *optimized_cbracket; + /* Tells whether the starting offset is a target of then. */ + pcre_uint8 *then_offsets; + /* Current position where a THEN must jump. */ + then_trap_backtrack *then_trap; + /* Starting offset of private data for capturing brackets. */ + int cbra_ptr; + /* Output vector starting point. Must be divisible by 2. */ + int ovector_start; + /* Last known position of the requested byte. */ + int req_char_ptr; + /* Head of the last recursion. */ + int recursive_head_ptr; + /* First inspected character for partial matching. */ + int start_used_ptr; + /* Starting pointer for partial soft matches. */ + int hit_start; + /* End pointer of the first line. */ + int first_line_end; + /* Points to the marked string. */ + int mark_ptr; + /* Recursive control verb management chain. */ + int control_head_ptr; + /* Points to the last matched capture block index. */ + int capture_last_ptr; + /* Points to the starting position of the current match. */ + int start_ptr; + + /* Flipped and lower case tables. */ + const pcre_uint8 *fcc; + sljit_sw lcc; + /* Mode can be PCRE_STUDY_JIT_COMPILE and others. */ + int mode; + /* TRUE, when minlength is greater than 0. */ + BOOL might_be_empty; + /* \K is found in the pattern. */ + BOOL has_set_som; + /* (*SKIP:arg) is found in the pattern. */ + BOOL has_skip_arg; + /* (*THEN) is found in the pattern. */ + BOOL has_then; + /* Needs to know the start position anytime. */ + BOOL needs_start_ptr; + /* Currently in recurse or negative assert. */ + BOOL local_exit; + /* Currently in a positive assert. */ + BOOL positive_assert; + /* Newline control. */ + int nltype; + pcre_uint32 nlmax; + pcre_uint32 nlmin; + int newline; + int bsr_nltype; + pcre_uint32 bsr_nlmax; + pcre_uint32 bsr_nlmin; + /* Dollar endonly. */ + int endonly; + /* Tables. */ + sljit_sw ctypes; + /* Named capturing brackets. */ + pcre_uchar *name_table; + sljit_sw name_count; + sljit_sw name_entry_size; + + /* Labels and jump lists. */ + struct sljit_label *partialmatchlabel; + struct sljit_label *quit_label; + struct sljit_label *forced_quit_label; + struct sljit_label *accept_label; + struct sljit_label *ff_newline_shortcut; + stub_list *stubs; + label_addr_list *label_addrs; + recurse_entry *entries; + recurse_entry *currententry; + jump_list *partialmatch; + jump_list *quit; + jump_list *positive_assert_quit; + jump_list *forced_quit; + jump_list *accept; + jump_list *calllimit; + jump_list *stackalloc; + jump_list *revertframes; + jump_list *wordboundary; + jump_list *anynewline; + jump_list *hspace; + jump_list *vspace; + jump_list *casefulcmp; + jump_list *caselesscmp; + jump_list *reset_match; + BOOL jscript_compat; +#ifdef SUPPORT_UTF + BOOL utf; +#ifdef SUPPORT_UCP + BOOL use_ucp; +#endif +#ifdef COMPILE_PCRE8 + jump_list *utfreadchar; + jump_list *utfreadchar16; + jump_list *utfreadtype8; +#endif +#endif /* SUPPORT_UTF */ +#ifdef SUPPORT_UCP + jump_list *getucd; +#endif +} compiler_common; + +/* For byte_sequence_compare. */ + +typedef struct compare_context { + int length; + int sourcereg; +#if defined SLJIT_UNALIGNED && SLJIT_UNALIGNED + int ucharptr; + union { + sljit_si asint; + sljit_uh asushort; +#if defined COMPILE_PCRE8 + sljit_ub asbyte; + sljit_ub asuchars[4]; +#elif defined COMPILE_PCRE16 + sljit_uh asuchars[2]; +#elif defined COMPILE_PCRE32 + sljit_ui asuchars[1]; +#endif + } c; + union { + sljit_si asint; + sljit_uh asushort; +#if defined COMPILE_PCRE8 + sljit_ub asbyte; + sljit_ub asuchars[4]; +#elif defined COMPILE_PCRE16 + sljit_uh asuchars[2]; +#elif defined COMPILE_PCRE32 + sljit_ui asuchars[1]; +#endif + } oc; +#endif +} compare_context; + +/* Undefine sljit macros. */ +#undef CMP + +/* Used for accessing the elements of the stack. */ +#define STACK(i) ((-(i) - 1) * (int)sizeof(sljit_sw)) + +#define TMP1 SLJIT_SCRATCH_REG1 +#define TMP2 SLJIT_SCRATCH_REG3 +#define TMP3 SLJIT_TEMPORARY_EREG2 +#define STR_PTR SLJIT_SAVED_REG1 +#define STR_END SLJIT_SAVED_REG2 +#define STACK_TOP SLJIT_SCRATCH_REG2 +#define STACK_LIMIT SLJIT_SAVED_REG3 +#define ARGUMENTS SLJIT_SAVED_EREG1 +#define COUNT_MATCH SLJIT_SAVED_EREG2 +#define RETURN_ADDR SLJIT_TEMPORARY_EREG1 + +/* Local space layout. */ +/* These two locals can be used by the current opcode. */ +#define LOCALS0 (0 * sizeof(sljit_sw)) +#define LOCALS1 (1 * sizeof(sljit_sw)) +/* Two local variables for possessive quantifiers (char1 cannot use them). */ +#define POSSESSIVE0 (2 * sizeof(sljit_sw)) +#define POSSESSIVE1 (3 * sizeof(sljit_sw)) +/* Max limit of recursions. */ +#define LIMIT_MATCH (4 * sizeof(sljit_sw)) +/* The output vector is stored on the stack, and contains pointers +to characters. The vector data is divided into two groups: the first +group contains the start / end character pointers, and the second is +the start pointers when the end of the capturing group has not yet reached. */ +#define OVECTOR_START (common->ovector_start) +#define OVECTOR(i) (OVECTOR_START + (i) * (sljit_sw)sizeof(sljit_sw)) +#define OVECTOR_PRIV(i) (common->cbra_ptr + (i) * (sljit_sw)sizeof(sljit_sw)) +#define PRIVATE_DATA(cc) (common->private_data_ptrs[(cc) - common->start]) + +#if defined COMPILE_PCRE8 +#define MOV_UCHAR SLJIT_MOV_UB +#define MOVU_UCHAR SLJIT_MOVU_UB +#elif defined COMPILE_PCRE16 +#define MOV_UCHAR SLJIT_MOV_UH +#define MOVU_UCHAR SLJIT_MOVU_UH +#elif defined COMPILE_PCRE32 +#define MOV_UCHAR SLJIT_MOV_UI +#define MOVU_UCHAR SLJIT_MOVU_UI +#else +#error Unsupported compiling mode +#endif + +/* Shortcuts. */ +#define DEFINE_COMPILER \ + struct sljit_compiler *compiler = common->compiler +#define OP1(op, dst, dstw, src, srcw) \ + sljit_emit_op1(compiler, (op), (dst), (dstw), (src), (srcw)) +#define OP2(op, dst, dstw, src1, src1w, src2, src2w) \ + sljit_emit_op2(compiler, (op), (dst), (dstw), (src1), (src1w), (src2), (src2w)) +#define LABEL() \ + sljit_emit_label(compiler) +#define JUMP(type) \ + sljit_emit_jump(compiler, (type)) +#define JUMPTO(type, label) \ + sljit_set_label(sljit_emit_jump(compiler, (type)), (label)) +#define JUMPHERE(jump) \ + sljit_set_label((jump), sljit_emit_label(compiler)) +#define SET_LABEL(jump, label) \ + sljit_set_label((jump), (label)) +#define CMP(type, src1, src1w, src2, src2w) \ + sljit_emit_cmp(compiler, (type), (src1), (src1w), (src2), (src2w)) +#define CMPTO(type, src1, src1w, src2, src2w, label) \ + sljit_set_label(sljit_emit_cmp(compiler, (type), (src1), (src1w), (src2), (src2w)), (label)) +#define OP_FLAGS(op, dst, dstw, src, srcw, type) \ + sljit_emit_op_flags(compiler, (op), (dst), (dstw), (src), (srcw), (type)) +#define GET_LOCAL_BASE(dst, dstw, offset) \ + sljit_get_local_base(compiler, (dst), (dstw), (offset)) + +#define READ_CHAR_MAX 0x7fffffff + +static pcre_uchar* bracketend(pcre_uchar* cc) +{ +SLJIT_ASSERT((*cc >= OP_ASSERT && *cc <= OP_ASSERTBACK_NOT) || (*cc >= OP_ONCE && *cc <= OP_SCOND)); +do cc += GET(cc, 1); while (*cc == OP_ALT); +SLJIT_ASSERT(*cc >= OP_KET && *cc <= OP_KETRPOS); +cc += 1 + LINK_SIZE; +return cc; +} + +static int no_alternatives(pcre_uchar* cc) +{ +int count = 0; +SLJIT_ASSERT((*cc >= OP_ASSERT && *cc <= OP_ASSERTBACK_NOT) || (*cc >= OP_ONCE && *cc <= OP_SCOND)); +do + { + cc += GET(cc, 1); + count++; + } +while (*cc == OP_ALT); +SLJIT_ASSERT(*cc >= OP_KET && *cc <= OP_KETRPOS); +return count; +} + +static int ones_in_half_byte[16] = { + /* 0 */ 0, 1, 1, 2, /* 4 */ 1, 2, 2, 3, + /* 8 */ 1, 2, 2, 3, /* 12 */ 2, 3, 3, 4 +}; + +/* Functions whose might need modification for all new supported opcodes: + next_opcode + check_opcode_types + set_private_data_ptrs + get_framesize + init_frame + get_private_data_copy_length + copy_private_data + compile_matchingpath + compile_backtrackingpath +*/ + +static pcre_uchar *next_opcode(compiler_common *common, pcre_uchar *cc) +{ +SLJIT_UNUSED_ARG(common); +switch(*cc) + { + case OP_SOD: + case OP_SOM: + case OP_SET_SOM: + case OP_NOT_WORD_BOUNDARY: + case OP_WORD_BOUNDARY: + case OP_NOT_DIGIT: + case OP_DIGIT: + case OP_NOT_WHITESPACE: + case OP_WHITESPACE: + case OP_NOT_WORDCHAR: + case OP_WORDCHAR: + case OP_ANY: + case OP_ALLANY: + case OP_NOTPROP: + case OP_PROP: + case OP_ANYNL: + case OP_NOT_HSPACE: + case OP_HSPACE: + case OP_NOT_VSPACE: + case OP_VSPACE: + case OP_EXTUNI: + case OP_EODN: + case OP_EOD: + case OP_CIRC: + case OP_CIRCM: + case OP_DOLL: + case OP_DOLLM: + case OP_CRSTAR: + case OP_CRMINSTAR: + case OP_CRPLUS: + case OP_CRMINPLUS: + case OP_CRQUERY: + case OP_CRMINQUERY: + case OP_CRRANGE: + case OP_CRMINRANGE: + case OP_CRPOSSTAR: + case OP_CRPOSPLUS: + case OP_CRPOSQUERY: + case OP_CRPOSRANGE: + case OP_CLASS: + case OP_NCLASS: + case OP_REF: + case OP_REFI: + case OP_DNREF: + case OP_DNREFI: + case OP_RECURSE: + case OP_CALLOUT: + case OP_ALT: + case OP_KET: + case OP_KETRMAX: + case OP_KETRMIN: + case OP_KETRPOS: + case OP_REVERSE: + case OP_ASSERT: + case OP_ASSERT_NOT: + case OP_ASSERTBACK: + case OP_ASSERTBACK_NOT: + case OP_ONCE: + case OP_ONCE_NC: + case OP_BRA: + case OP_BRAPOS: + case OP_CBRA: + case OP_CBRAPOS: + case OP_COND: + case OP_SBRA: + case OP_SBRAPOS: + case OP_SCBRA: + case OP_SCBRAPOS: + case OP_SCOND: + case OP_CREF: + case OP_DNCREF: + case OP_RREF: + case OP_DNRREF: + case OP_DEF: + case OP_BRAZERO: + case OP_BRAMINZERO: + case OP_BRAPOSZERO: + case OP_PRUNE: + case OP_SKIP: + case OP_THEN: + case OP_COMMIT: + case OP_FAIL: + case OP_ACCEPT: + case OP_ASSERT_ACCEPT: + case OP_CLOSE: + case OP_SKIPZERO: + return cc + PRIV(OP_lengths)[*cc]; + + case OP_CHAR: + case OP_CHARI: + case OP_NOT: + case OP_NOTI: + case OP_STAR: + case OP_MINSTAR: + case OP_PLUS: + case OP_MINPLUS: + case OP_QUERY: + case OP_MINQUERY: + case OP_UPTO: + case OP_MINUPTO: + case OP_EXACT: + case OP_POSSTAR: + case OP_POSPLUS: + case OP_POSQUERY: + case OP_POSUPTO: + case OP_STARI: + case OP_MINSTARI: + case OP_PLUSI: + case OP_MINPLUSI: + case OP_QUERYI: + case OP_MINQUERYI: + case OP_UPTOI: + case OP_MINUPTOI: + case OP_EXACTI: + case OP_POSSTARI: + case OP_POSPLUSI: + case OP_POSQUERYI: + case OP_POSUPTOI: + case OP_NOTSTAR: + case OP_NOTMINSTAR: + case OP_NOTPLUS: + case OP_NOTMINPLUS: + case OP_NOTQUERY: + case OP_NOTMINQUERY: + case OP_NOTUPTO: + case OP_NOTMINUPTO: + case OP_NOTEXACT: + case OP_NOTPOSSTAR: + case OP_NOTPOSPLUS: + case OP_NOTPOSQUERY: + case OP_NOTPOSUPTO: + case OP_NOTSTARI: + case OP_NOTMINSTARI: + case OP_NOTPLUSI: + case OP_NOTMINPLUSI: + case OP_NOTQUERYI: + case OP_NOTMINQUERYI: + case OP_NOTUPTOI: + case OP_NOTMINUPTOI: + case OP_NOTEXACTI: + case OP_NOTPOSSTARI: + case OP_NOTPOSPLUSI: + case OP_NOTPOSQUERYI: + case OP_NOTPOSUPTOI: + cc += PRIV(OP_lengths)[*cc]; +#ifdef SUPPORT_UTF + if (common->utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); +#endif + return cc; + + /* Special cases. */ + case OP_TYPESTAR: + case OP_TYPEMINSTAR: + case OP_TYPEPLUS: + case OP_TYPEMINPLUS: + case OP_TYPEQUERY: + case OP_TYPEMINQUERY: + case OP_TYPEUPTO: + case OP_TYPEMINUPTO: + case OP_TYPEEXACT: + case OP_TYPEPOSSTAR: + case OP_TYPEPOSPLUS: + case OP_TYPEPOSQUERY: + case OP_TYPEPOSUPTO: + return cc + PRIV(OP_lengths)[*cc] - 1; + + case OP_ANYBYTE: +#ifdef SUPPORT_UTF + if (common->utf) return NULL; +#endif + return cc + 1; + +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + case OP_XCLASS: + return cc + GET(cc, 1); +#endif + + case OP_MARK: + case OP_PRUNE_ARG: + case OP_SKIP_ARG: + case OP_THEN_ARG: + return cc + 1 + 2 + cc[1]; + + default: + /* All opcodes are supported now! */ + SLJIT_ASSERT_STOP(); + return NULL; + } +} + +static BOOL check_opcode_types(compiler_common *common, pcre_uchar *cc, pcre_uchar *ccend) +{ +int count; +pcre_uchar *slot; + +/* Calculate important variables (like stack size) and checks whether all opcodes are supported. */ +while (cc < ccend) + { + switch(*cc) + { + case OP_SET_SOM: + common->has_set_som = TRUE; + common->might_be_empty = TRUE; + cc += 1; + break; + + case OP_REF: + case OP_REFI: + common->optimized_cbracket[GET2(cc, 1)] = 0; + cc += 1 + IMM2_SIZE; + break; + + case OP_BRA: + case OP_CBRA: + case OP_SBRA: + case OP_SCBRA: + count = no_alternatives(cc); + if (count > 4) + common->read_only_data_size += count * sizeof(sljit_uw); + cc += 1 + LINK_SIZE + (*cc == OP_CBRA || *cc == OP_SCBRA ? IMM2_SIZE : 0); + break; + + case OP_CBRAPOS: + case OP_SCBRAPOS: + common->optimized_cbracket[GET2(cc, 1 + LINK_SIZE)] = 0; + cc += 1 + LINK_SIZE + IMM2_SIZE; + break; + + case OP_COND: + case OP_SCOND: + /* Only AUTO_CALLOUT can insert this opcode. We do + not intend to support this case. */ + if (cc[1 + LINK_SIZE] == OP_CALLOUT) + return FALSE; + cc += 1 + LINK_SIZE; + break; + + case OP_CREF: + common->optimized_cbracket[GET2(cc, 1)] = 0; + cc += 1 + IMM2_SIZE; + break; + + case OP_DNREF: + case OP_DNREFI: + case OP_DNCREF: + count = GET2(cc, 1 + IMM2_SIZE); + slot = common->name_table + GET2(cc, 1) * common->name_entry_size; + while (count-- > 0) + { + common->optimized_cbracket[GET2(slot, 0)] = 0; + slot += common->name_entry_size; + } + cc += 1 + 2 * IMM2_SIZE; + break; + + case OP_RECURSE: + /* Set its value only once. */ + if (common->recursive_head_ptr == 0) + { + common->recursive_head_ptr = common->ovector_start; + common->ovector_start += sizeof(sljit_sw); + } + cc += 1 + LINK_SIZE; + break; + + case OP_CALLOUT: + if (common->capture_last_ptr == 0) + { + common->capture_last_ptr = common->ovector_start; + common->ovector_start += sizeof(sljit_sw); + } + cc += 2 + 2 * LINK_SIZE; + break; + + case OP_THEN_ARG: + common->has_then = TRUE; + common->control_head_ptr = 1; + /* Fall through. */ + + case OP_PRUNE_ARG: + common->needs_start_ptr = TRUE; + /* Fall through. */ + + case OP_MARK: + if (common->mark_ptr == 0) + { + common->mark_ptr = common->ovector_start; + common->ovector_start += sizeof(sljit_sw); + } + cc += 1 + 2 + cc[1]; + break; + + case OP_THEN: + common->has_then = TRUE; + common->control_head_ptr = 1; + /* Fall through. */ + + case OP_PRUNE: + case OP_SKIP: + common->needs_start_ptr = TRUE; + cc += 1; + break; + + case OP_SKIP_ARG: + common->control_head_ptr = 1; + common->has_skip_arg = TRUE; + cc += 1 + 2 + cc[1]; + break; + + default: + cc = next_opcode(common, cc); + if (cc == NULL) + return FALSE; + break; + } + } +return TRUE; +} + +static int get_class_iterator_size(pcre_uchar *cc) +{ +switch(*cc) + { + case OP_CRSTAR: + case OP_CRPLUS: + return 2; + + case OP_CRMINSTAR: + case OP_CRMINPLUS: + case OP_CRQUERY: + case OP_CRMINQUERY: + return 1; + + case OP_CRRANGE: + case OP_CRMINRANGE: + if (GET2(cc, 1) == GET2(cc, 1 + IMM2_SIZE)) + return 0; + return 2; + + default: + return 0; + } +} + +static BOOL detect_repeat(compiler_common *common, pcre_uchar *begin) +{ +pcre_uchar *end = bracketend(begin); +pcre_uchar *next; +pcre_uchar *next_end; +pcre_uchar *max_end; +pcre_uchar type; +sljit_sw length = end - begin; +int min, max, i; + +/* Detect fixed iterations first. */ +if (end[-(1 + LINK_SIZE)] != OP_KET) + return FALSE; + +/* Already detected repeat. */ +if (common->private_data_ptrs[end - common->start - LINK_SIZE] != 0) + return TRUE; + +next = end; +min = 1; +while (1) + { + if (*next != *begin) + break; + next_end = bracketend(next); + if (next_end - next != length || memcmp(begin, next, IN_UCHARS(length)) != 0) + break; + next = next_end; + min++; + } + +if (min == 2) + return FALSE; + +max = 0; +max_end = next; +if (*next == OP_BRAZERO || *next == OP_BRAMINZERO) + { + type = *next; + while (1) + { + if (next[0] != type || next[1] != OP_BRA || next[2 + LINK_SIZE] != *begin) + break; + next_end = bracketend(next + 2 + LINK_SIZE); + if (next_end - next != (length + 2 + LINK_SIZE) || memcmp(begin, next + 2 + LINK_SIZE, IN_UCHARS(length)) != 0) + break; + next = next_end; + max++; + } + + if (next[0] == type && next[1] == *begin && max >= 1) + { + next_end = bracketend(next + 1); + if (next_end - next == (length + 1) && memcmp(begin, next + 1, IN_UCHARS(length)) == 0) + { + for (i = 0; i < max; i++, next_end += 1 + LINK_SIZE) + if (*next_end != OP_KET) + break; + + if (i == max) + { + common->private_data_ptrs[max_end - common->start - LINK_SIZE] = next_end - max_end; + common->private_data_ptrs[max_end - common->start - LINK_SIZE + 1] = (type == OP_BRAZERO) ? OP_UPTO : OP_MINUPTO; + /* +2 the original and the last. */ + common->private_data_ptrs[max_end - common->start - LINK_SIZE + 2] = max + 2; + if (min == 1) + return TRUE; + min--; + max_end -= (1 + LINK_SIZE) + GET(max_end, -LINK_SIZE); + } + } + } + } + +if (min >= 3) + { + common->private_data_ptrs[end - common->start - LINK_SIZE] = max_end - end; + common->private_data_ptrs[end - common->start - LINK_SIZE + 1] = OP_EXACT; + common->private_data_ptrs[end - common->start - LINK_SIZE + 2] = min; + return TRUE; + } + +return FALSE; +} + +#define CASE_ITERATOR_PRIVATE_DATA_1 \ + case OP_MINSTAR: \ + case OP_MINPLUS: \ + case OP_QUERY: \ + case OP_MINQUERY: \ + case OP_MINSTARI: \ + case OP_MINPLUSI: \ + case OP_QUERYI: \ + case OP_MINQUERYI: \ + case OP_NOTMINSTAR: \ + case OP_NOTMINPLUS: \ + case OP_NOTQUERY: \ + case OP_NOTMINQUERY: \ + case OP_NOTMINSTARI: \ + case OP_NOTMINPLUSI: \ + case OP_NOTQUERYI: \ + case OP_NOTMINQUERYI: + +#define CASE_ITERATOR_PRIVATE_DATA_2A \ + case OP_STAR: \ + case OP_PLUS: \ + case OP_STARI: \ + case OP_PLUSI: \ + case OP_NOTSTAR: \ + case OP_NOTPLUS: \ + case OP_NOTSTARI: \ + case OP_NOTPLUSI: + +#define CASE_ITERATOR_PRIVATE_DATA_2B \ + case OP_UPTO: \ + case OP_MINUPTO: \ + case OP_UPTOI: \ + case OP_MINUPTOI: \ + case OP_NOTUPTO: \ + case OP_NOTMINUPTO: \ + case OP_NOTUPTOI: \ + case OP_NOTMINUPTOI: + +#define CASE_ITERATOR_TYPE_PRIVATE_DATA_1 \ + case OP_TYPEMINSTAR: \ + case OP_TYPEMINPLUS: \ + case OP_TYPEQUERY: \ + case OP_TYPEMINQUERY: + +#define CASE_ITERATOR_TYPE_PRIVATE_DATA_2A \ + case OP_TYPESTAR: \ + case OP_TYPEPLUS: + +#define CASE_ITERATOR_TYPE_PRIVATE_DATA_2B \ + case OP_TYPEUPTO: \ + case OP_TYPEMINUPTO: + +static void set_private_data_ptrs(compiler_common *common, int *private_data_start, pcre_uchar *ccend) +{ +pcre_uchar *cc = common->start; +pcre_uchar *alternative; +pcre_uchar *end = NULL; +int private_data_ptr = *private_data_start; +int space, size, bracketlen; + +while (cc < ccend) + { + space = 0; + size = 0; + bracketlen = 0; + if (private_data_ptr > SLJIT_MAX_LOCAL_SIZE) + return; + + if (*cc == OP_ONCE || *cc == OP_ONCE_NC || *cc == OP_BRA || *cc == OP_CBRA || *cc == OP_COND) + if (detect_repeat(common, cc)) + { + /* These brackets are converted to repeats, so no global + based single character repeat is allowed. */ + if (cc >= end) + end = bracketend(cc); + } + + switch(*cc) + { + case OP_KET: + if (common->private_data_ptrs[cc + 1 - common->start] != 0) + { + common->private_data_ptrs[cc - common->start] = private_data_ptr; + private_data_ptr += sizeof(sljit_sw); + cc += common->private_data_ptrs[cc + 1 - common->start]; + } + cc += 1 + LINK_SIZE; + break; + + case OP_ASSERT: + case OP_ASSERT_NOT: + case OP_ASSERTBACK: + case OP_ASSERTBACK_NOT: + case OP_ONCE: + case OP_ONCE_NC: + case OP_BRAPOS: + case OP_SBRA: + case OP_SBRAPOS: + case OP_SCOND: + common->private_data_ptrs[cc - common->start] = private_data_ptr; + private_data_ptr += sizeof(sljit_sw); + bracketlen = 1 + LINK_SIZE; + break; + + case OP_CBRAPOS: + case OP_SCBRAPOS: + common->private_data_ptrs[cc - common->start] = private_data_ptr; + private_data_ptr += sizeof(sljit_sw); + bracketlen = 1 + LINK_SIZE + IMM2_SIZE; + break; + + case OP_COND: + /* Might be a hidden SCOND. */ + alternative = cc + GET(cc, 1); + if (*alternative == OP_KETRMAX || *alternative == OP_KETRMIN) + { + common->private_data_ptrs[cc - common->start] = private_data_ptr; + private_data_ptr += sizeof(sljit_sw); + } + bracketlen = 1 + LINK_SIZE; + break; + + case OP_BRA: + bracketlen = 1 + LINK_SIZE; + break; + + case OP_CBRA: + case OP_SCBRA: + bracketlen = 1 + LINK_SIZE + IMM2_SIZE; + break; + + CASE_ITERATOR_PRIVATE_DATA_1 + space = 1; + size = -2; + break; + + CASE_ITERATOR_PRIVATE_DATA_2A + space = 2; + size = -2; + break; + + CASE_ITERATOR_PRIVATE_DATA_2B + space = 2; + size = -(2 + IMM2_SIZE); + break; + + CASE_ITERATOR_TYPE_PRIVATE_DATA_1 + space = 1; + size = 1; + break; + + CASE_ITERATOR_TYPE_PRIVATE_DATA_2A + if (cc[1] != OP_ANYNL && cc[1] != OP_EXTUNI) + space = 2; + size = 1; + break; + + CASE_ITERATOR_TYPE_PRIVATE_DATA_2B + if (cc[1 + IMM2_SIZE] != OP_ANYNL && cc[1 + IMM2_SIZE] != OP_EXTUNI) + space = 2; + size = 1 + IMM2_SIZE; + break; + + case OP_CLASS: + case OP_NCLASS: + size += 1 + 32 / sizeof(pcre_uchar); + space = get_class_iterator_size(cc + size); + break; + +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + case OP_XCLASS: + size = GET(cc, 1); + space = get_class_iterator_size(cc + size); + break; +#endif + + default: + cc = next_opcode(common, cc); + SLJIT_ASSERT(cc != NULL); + break; + } + + /* Character iterators, which are not inside a repeated bracket, + gets a private slot instead of allocating it on the stack. */ + if (space > 0 && cc >= end) + { + common->private_data_ptrs[cc - common->start] = private_data_ptr; + private_data_ptr += sizeof(sljit_sw) * space; + } + + if (size != 0) + { + if (size < 0) + { + cc += -size; +#ifdef SUPPORT_UTF + if (common->utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); +#endif + } + else + cc += size; + } + + if (bracketlen > 0) + { + if (cc >= end) + { + end = bracketend(cc); + if (end[-1 - LINK_SIZE] == OP_KET) + end = NULL; + } + cc += bracketlen; + } + } +*private_data_start = private_data_ptr; +} + +/* Returns with a frame_types (always < 0) if no need for frame. */ +static int get_framesize(compiler_common *common, pcre_uchar *cc, pcre_uchar *ccend, BOOL recursive, BOOL* needs_control_head) +{ +int length = 0; +int possessive = 0; +BOOL stack_restore = FALSE; +BOOL setsom_found = recursive; +BOOL setmark_found = recursive; +/* The last capture is a local variable even for recursions. */ +BOOL capture_last_found = FALSE; + +#if defined DEBUG_FORCE_CONTROL_HEAD && DEBUG_FORCE_CONTROL_HEAD +SLJIT_ASSERT(common->control_head_ptr != 0); +*needs_control_head = TRUE; +#else +*needs_control_head = FALSE; +#endif + +if (ccend == NULL) + { + ccend = bracketend(cc) - (1 + LINK_SIZE); + if (!recursive && (*cc == OP_CBRAPOS || *cc == OP_SCBRAPOS)) + { + possessive = length = (common->capture_last_ptr != 0) ? 5 : 3; + /* This is correct regardless of common->capture_last_ptr. */ + capture_last_found = TRUE; + } + cc = next_opcode(common, cc); + } + +SLJIT_ASSERT(cc != NULL); +while (cc < ccend) + switch(*cc) + { + case OP_SET_SOM: + SLJIT_ASSERT(common->has_set_som); + stack_restore = TRUE; + if (!setsom_found) + { + length += 2; + setsom_found = TRUE; + } + cc += 1; + break; + + case OP_MARK: + case OP_PRUNE_ARG: + case OP_THEN_ARG: + SLJIT_ASSERT(common->mark_ptr != 0); + stack_restore = TRUE; + if (!setmark_found) + { + length += 2; + setmark_found = TRUE; + } + if (common->control_head_ptr != 0) + *needs_control_head = TRUE; + cc += 1 + 2 + cc[1]; + break; + + case OP_RECURSE: + stack_restore = TRUE; + if (common->has_set_som && !setsom_found) + { + length += 2; + setsom_found = TRUE; + } + if (common->mark_ptr != 0 && !setmark_found) + { + length += 2; + setmark_found = TRUE; + } + if (common->capture_last_ptr != 0 && !capture_last_found) + { + length += 2; + capture_last_found = TRUE; + } + cc += 1 + LINK_SIZE; + break; + + case OP_CBRA: + case OP_CBRAPOS: + case OP_SCBRA: + case OP_SCBRAPOS: + stack_restore = TRUE; + if (common->capture_last_ptr != 0 && !capture_last_found) + { + length += 2; + capture_last_found = TRUE; + } + length += 3; + cc += 1 + LINK_SIZE + IMM2_SIZE; + break; + + default: + stack_restore = TRUE; + /* Fall through. */ + + case OP_NOT_WORD_BOUNDARY: + case OP_WORD_BOUNDARY: + case OP_NOT_DIGIT: + case OP_DIGIT: + case OP_NOT_WHITESPACE: + case OP_WHITESPACE: + case OP_NOT_WORDCHAR: + case OP_WORDCHAR: + case OP_ANY: + case OP_ALLANY: + case OP_ANYBYTE: + case OP_NOTPROP: + case OP_PROP: + case OP_ANYNL: + case OP_NOT_HSPACE: + case OP_HSPACE: + case OP_NOT_VSPACE: + case OP_VSPACE: + case OP_EXTUNI: + case OP_EODN: + case OP_EOD: + case OP_CIRC: + case OP_CIRCM: + case OP_DOLL: + case OP_DOLLM: + case OP_CHAR: + case OP_CHARI: + case OP_NOT: + case OP_NOTI: + + case OP_EXACT: + case OP_POSSTAR: + case OP_POSPLUS: + case OP_POSQUERY: + case OP_POSUPTO: + + case OP_EXACTI: + case OP_POSSTARI: + case OP_POSPLUSI: + case OP_POSQUERYI: + case OP_POSUPTOI: + + case OP_NOTEXACT: + case OP_NOTPOSSTAR: + case OP_NOTPOSPLUS: + case OP_NOTPOSQUERY: + case OP_NOTPOSUPTO: + + case OP_NOTEXACTI: + case OP_NOTPOSSTARI: + case OP_NOTPOSPLUSI: + case OP_NOTPOSQUERYI: + case OP_NOTPOSUPTOI: + + case OP_TYPEEXACT: + case OP_TYPEPOSSTAR: + case OP_TYPEPOSPLUS: + case OP_TYPEPOSQUERY: + case OP_TYPEPOSUPTO: + + case OP_CLASS: + case OP_NCLASS: + case OP_XCLASS: + + cc = next_opcode(common, cc); + SLJIT_ASSERT(cc != NULL); + break; + } + +/* Possessive quantifiers can use a special case. */ +if (SLJIT_UNLIKELY(possessive == length)) + return stack_restore ? no_frame : no_stack; + +if (length > 0) + return length + 1; +return stack_restore ? no_frame : no_stack; +} + +static void init_frame(compiler_common *common, pcre_uchar *cc, pcre_uchar *ccend, int stackpos, int stacktop, BOOL recursive) +{ +DEFINE_COMPILER; +BOOL setsom_found = recursive; +BOOL setmark_found = recursive; +/* The last capture is a local variable even for recursions. */ +BOOL capture_last_found = FALSE; +int offset; + +/* >= 1 + shortest item size (2) */ +SLJIT_UNUSED_ARG(stacktop); +SLJIT_ASSERT(stackpos >= stacktop + 2); + +stackpos = STACK(stackpos); +if (ccend == NULL) + { + ccend = bracketend(cc) - (1 + LINK_SIZE); + if (recursive || (*cc != OP_CBRAPOS && *cc != OP_SCBRAPOS)) + cc = next_opcode(common, cc); + } + +SLJIT_ASSERT(cc != NULL); +while (cc < ccend) + switch(*cc) + { + case OP_SET_SOM: + SLJIT_ASSERT(common->has_set_som); + if (!setsom_found) + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(0)); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, SLJIT_IMM, -OVECTOR(0)); + stackpos += (int)sizeof(sljit_sw); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, TMP1, 0); + stackpos += (int)sizeof(sljit_sw); + setsom_found = TRUE; + } + cc += 1; + break; + + case OP_MARK: + case OP_PRUNE_ARG: + case OP_THEN_ARG: + SLJIT_ASSERT(common->mark_ptr != 0); + if (!setmark_found) + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->mark_ptr); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, SLJIT_IMM, -common->mark_ptr); + stackpos += (int)sizeof(sljit_sw); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, TMP1, 0); + stackpos += (int)sizeof(sljit_sw); + setmark_found = TRUE; + } + cc += 1 + 2 + cc[1]; + break; + + case OP_RECURSE: + if (common->has_set_som && !setsom_found) + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(0)); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, SLJIT_IMM, -OVECTOR(0)); + stackpos += (int)sizeof(sljit_sw); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, TMP1, 0); + stackpos += (int)sizeof(sljit_sw); + setsom_found = TRUE; + } + if (common->mark_ptr != 0 && !setmark_found) + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->mark_ptr); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, SLJIT_IMM, -common->mark_ptr); + stackpos += (int)sizeof(sljit_sw); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, TMP1, 0); + stackpos += (int)sizeof(sljit_sw); + setmark_found = TRUE; + } + if (common->capture_last_ptr != 0 && !capture_last_found) + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->capture_last_ptr); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, SLJIT_IMM, -common->capture_last_ptr); + stackpos += (int)sizeof(sljit_sw); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, TMP1, 0); + stackpos += (int)sizeof(sljit_sw); + capture_last_found = TRUE; + } + cc += 1 + LINK_SIZE; + break; + + case OP_CBRA: + case OP_CBRAPOS: + case OP_SCBRA: + case OP_SCBRAPOS: + if (common->capture_last_ptr != 0 && !capture_last_found) + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->capture_last_ptr); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, SLJIT_IMM, -common->capture_last_ptr); + stackpos += (int)sizeof(sljit_sw); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, TMP1, 0); + stackpos += (int)sizeof(sljit_sw); + capture_last_found = TRUE; + } + offset = (GET2(cc, 1 + LINK_SIZE)) << 1; + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, SLJIT_IMM, OVECTOR(offset)); + stackpos += (int)sizeof(sljit_sw); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset)); + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset + 1)); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, TMP1, 0); + stackpos += (int)sizeof(sljit_sw); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, TMP2, 0); + stackpos += (int)sizeof(sljit_sw); + + cc += 1 + LINK_SIZE + IMM2_SIZE; + break; + + default: + cc = next_opcode(common, cc); + SLJIT_ASSERT(cc != NULL); + break; + } + +OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, SLJIT_IMM, 0); +SLJIT_ASSERT(stackpos == STACK(stacktop)); +} + +static SLJIT_INLINE int get_private_data_copy_length(compiler_common *common, pcre_uchar *cc, pcre_uchar *ccend, BOOL needs_control_head) +{ +int private_data_length = needs_control_head ? 3 : 2; +int size; +pcre_uchar *alternative; +/* Calculate the sum of the private machine words. */ +while (cc < ccend) + { + size = 0; + switch(*cc) + { + case OP_KET: + if (PRIVATE_DATA(cc) != 0) + private_data_length++; + cc += 1 + LINK_SIZE; + break; + + case OP_ASSERT: + case OP_ASSERT_NOT: + case OP_ASSERTBACK: + case OP_ASSERTBACK_NOT: + case OP_ONCE: + case OP_ONCE_NC: + case OP_BRAPOS: + case OP_SBRA: + case OP_SBRAPOS: + case OP_SCOND: + private_data_length++; + cc += 1 + LINK_SIZE; + break; + + case OP_CBRA: + case OP_SCBRA: + if (common->optimized_cbracket[GET2(cc, 1 + LINK_SIZE)] == 0) + private_data_length++; + cc += 1 + LINK_SIZE + IMM2_SIZE; + break; + + case OP_CBRAPOS: + case OP_SCBRAPOS: + private_data_length += 2; + cc += 1 + LINK_SIZE + IMM2_SIZE; + break; + + case OP_COND: + /* Might be a hidden SCOND. */ + alternative = cc + GET(cc, 1); + if (*alternative == OP_KETRMAX || *alternative == OP_KETRMIN) + private_data_length++; + cc += 1 + LINK_SIZE; + break; + + CASE_ITERATOR_PRIVATE_DATA_1 + if (PRIVATE_DATA(cc)) + private_data_length++; + cc += 2; +#ifdef SUPPORT_UTF + if (common->utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); +#endif + break; + + CASE_ITERATOR_PRIVATE_DATA_2A + if (PRIVATE_DATA(cc)) + private_data_length += 2; + cc += 2; +#ifdef SUPPORT_UTF + if (common->utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); +#endif + break; + + CASE_ITERATOR_PRIVATE_DATA_2B + if (PRIVATE_DATA(cc)) + private_data_length += 2; + cc += 2 + IMM2_SIZE; +#ifdef SUPPORT_UTF + if (common->utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); +#endif + break; + + CASE_ITERATOR_TYPE_PRIVATE_DATA_1 + if (PRIVATE_DATA(cc)) + private_data_length++; + cc += 1; + break; + + CASE_ITERATOR_TYPE_PRIVATE_DATA_2A + if (PRIVATE_DATA(cc)) + private_data_length += 2; + cc += 1; + break; + + CASE_ITERATOR_TYPE_PRIVATE_DATA_2B + if (PRIVATE_DATA(cc)) + private_data_length += 2; + cc += 1 + IMM2_SIZE; + break; + + case OP_CLASS: + case OP_NCLASS: +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + case OP_XCLASS: + size = (*cc == OP_XCLASS) ? GET(cc, 1) : 1 + 32 / (int)sizeof(pcre_uchar); +#else + size = 1 + 32 / (int)sizeof(pcre_uchar); +#endif + if (PRIVATE_DATA(cc)) + private_data_length += get_class_iterator_size(cc + size); + cc += size; + break; + + default: + cc = next_opcode(common, cc); + SLJIT_ASSERT(cc != NULL); + break; + } + } +SLJIT_ASSERT(cc == ccend); +return private_data_length; +} + +static void copy_private_data(compiler_common *common, pcre_uchar *cc, pcre_uchar *ccend, + BOOL save, int stackptr, int stacktop, BOOL needs_control_head) +{ +DEFINE_COMPILER; +int srcw[2]; +int count, size; +BOOL tmp1next = TRUE; +BOOL tmp1empty = TRUE; +BOOL tmp2empty = TRUE; +pcre_uchar *alternative; +enum { + start, + loop, + end +} status; + +status = save ? start : loop; +stackptr = STACK(stackptr - 2); +stacktop = STACK(stacktop - 1); + +if (!save) + { + stackptr += (needs_control_head ? 2 : 1) * sizeof(sljit_sw); + if (stackptr < stacktop) + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), stackptr); + stackptr += sizeof(sljit_sw); + tmp1empty = FALSE; + } + if (stackptr < stacktop) + { + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), stackptr); + stackptr += sizeof(sljit_sw); + tmp2empty = FALSE; + } + /* The tmp1next must be TRUE in either way. */ + } + +do + { + count = 0; + switch(status) + { + case start: + SLJIT_ASSERT(save && common->recursive_head_ptr != 0); + count = 1; + srcw[0] = common->recursive_head_ptr; + if (needs_control_head) + { + SLJIT_ASSERT(common->control_head_ptr != 0); + count = 2; + srcw[1] = common->control_head_ptr; + } + status = loop; + break; + + case loop: + if (cc >= ccend) + { + status = end; + break; + } + + switch(*cc) + { + case OP_KET: + if (PRIVATE_DATA(cc) != 0) + { + count = 1; + srcw[0] = PRIVATE_DATA(cc); + } + cc += 1 + LINK_SIZE; + break; + + case OP_ASSERT: + case OP_ASSERT_NOT: + case OP_ASSERTBACK: + case OP_ASSERTBACK_NOT: + case OP_ONCE: + case OP_ONCE_NC: + case OP_BRAPOS: + case OP_SBRA: + case OP_SBRAPOS: + case OP_SCOND: + count = 1; + srcw[0] = PRIVATE_DATA(cc); + SLJIT_ASSERT(srcw[0] != 0); + cc += 1 + LINK_SIZE; + break; + + case OP_CBRA: + case OP_SCBRA: + if (common->optimized_cbracket[GET2(cc, 1 + LINK_SIZE)] == 0) + { + count = 1; + srcw[0] = OVECTOR_PRIV(GET2(cc, 1 + LINK_SIZE)); + } + cc += 1 + LINK_SIZE + IMM2_SIZE; + break; + + case OP_CBRAPOS: + case OP_SCBRAPOS: + count = 2; + srcw[0] = PRIVATE_DATA(cc); + srcw[1] = OVECTOR_PRIV(GET2(cc, 1 + LINK_SIZE)); + SLJIT_ASSERT(srcw[0] != 0 && srcw[1] != 0); + cc += 1 + LINK_SIZE + IMM2_SIZE; + break; + + case OP_COND: + /* Might be a hidden SCOND. */ + alternative = cc + GET(cc, 1); + if (*alternative == OP_KETRMAX || *alternative == OP_KETRMIN) + { + count = 1; + srcw[0] = PRIVATE_DATA(cc); + SLJIT_ASSERT(srcw[0] != 0); + } + cc += 1 + LINK_SIZE; + break; + + CASE_ITERATOR_PRIVATE_DATA_1 + if (PRIVATE_DATA(cc)) + { + count = 1; + srcw[0] = PRIVATE_DATA(cc); + } + cc += 2; +#ifdef SUPPORT_UTF + if (common->utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); +#endif + break; + + CASE_ITERATOR_PRIVATE_DATA_2A + if (PRIVATE_DATA(cc)) + { + count = 2; + srcw[0] = PRIVATE_DATA(cc); + srcw[1] = PRIVATE_DATA(cc) + sizeof(sljit_sw); + } + cc += 2; +#ifdef SUPPORT_UTF + if (common->utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); +#endif + break; + + CASE_ITERATOR_PRIVATE_DATA_2B + if (PRIVATE_DATA(cc)) + { + count = 2; + srcw[0] = PRIVATE_DATA(cc); + srcw[1] = PRIVATE_DATA(cc) + sizeof(sljit_sw); + } + cc += 2 + IMM2_SIZE; +#ifdef SUPPORT_UTF + if (common->utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); +#endif + break; + + CASE_ITERATOR_TYPE_PRIVATE_DATA_1 + if (PRIVATE_DATA(cc)) + { + count = 1; + srcw[0] = PRIVATE_DATA(cc); + } + cc += 1; + break; + + CASE_ITERATOR_TYPE_PRIVATE_DATA_2A + if (PRIVATE_DATA(cc)) + { + count = 2; + srcw[0] = PRIVATE_DATA(cc); + srcw[1] = srcw[0] + sizeof(sljit_sw); + } + cc += 1; + break; + + CASE_ITERATOR_TYPE_PRIVATE_DATA_2B + if (PRIVATE_DATA(cc)) + { + count = 2; + srcw[0] = PRIVATE_DATA(cc); + srcw[1] = srcw[0] + sizeof(sljit_sw); + } + cc += 1 + IMM2_SIZE; + break; + + case OP_CLASS: + case OP_NCLASS: +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + case OP_XCLASS: + size = (*cc == OP_XCLASS) ? GET(cc, 1) : 1 + 32 / (int)sizeof(pcre_uchar); +#else + size = 1 + 32 / (int)sizeof(pcre_uchar); +#endif + if (PRIVATE_DATA(cc)) + switch(get_class_iterator_size(cc + size)) + { + case 1: + count = 1; + srcw[0] = PRIVATE_DATA(cc); + break; + + case 2: + count = 2; + srcw[0] = PRIVATE_DATA(cc); + srcw[1] = srcw[0] + sizeof(sljit_sw); + break; + + default: + SLJIT_ASSERT_STOP(); + break; + } + cc += size; + break; + + default: + cc = next_opcode(common, cc); + SLJIT_ASSERT(cc != NULL); + break; + } + break; + + case end: + SLJIT_ASSERT_STOP(); + break; + } + + while (count > 0) + { + count--; + if (save) + { + if (tmp1next) + { + if (!tmp1empty) + { + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackptr, TMP1, 0); + stackptr += sizeof(sljit_sw); + } + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), srcw[count]); + tmp1empty = FALSE; + tmp1next = FALSE; + } + else + { + if (!tmp2empty) + { + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackptr, TMP2, 0); + stackptr += sizeof(sljit_sw); + } + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), srcw[count]); + tmp2empty = FALSE; + tmp1next = TRUE; + } + } + else + { + if (tmp1next) + { + SLJIT_ASSERT(!tmp1empty); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), srcw[count], TMP1, 0); + tmp1empty = stackptr >= stacktop; + if (!tmp1empty) + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), stackptr); + stackptr += sizeof(sljit_sw); + } + tmp1next = FALSE; + } + else + { + SLJIT_ASSERT(!tmp2empty); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), srcw[count], TMP2, 0); + tmp2empty = stackptr >= stacktop; + if (!tmp2empty) + { + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), stackptr); + stackptr += sizeof(sljit_sw); + } + tmp1next = TRUE; + } + } + } + } +while (status != end); + +if (save) + { + if (tmp1next) + { + if (!tmp1empty) + { + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackptr, TMP1, 0); + stackptr += sizeof(sljit_sw); + } + if (!tmp2empty) + { + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackptr, TMP2, 0); + stackptr += sizeof(sljit_sw); + } + } + else + { + if (!tmp2empty) + { + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackptr, TMP2, 0); + stackptr += sizeof(sljit_sw); + } + if (!tmp1empty) + { + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackptr, TMP1, 0); + stackptr += sizeof(sljit_sw); + } + } + } +SLJIT_ASSERT(cc == ccend && stackptr == stacktop && (save || (tmp1empty && tmp2empty))); +} + +static SLJIT_INLINE pcre_uchar *set_then_offsets(compiler_common *common, pcre_uchar *cc, pcre_uint8 *current_offset) +{ +pcre_uchar *end = bracketend(cc); +BOOL has_alternatives = cc[GET(cc, 1)] == OP_ALT; + +/* Assert captures then. */ +if (*cc >= OP_ASSERT && *cc <= OP_ASSERTBACK_NOT) + current_offset = NULL; +/* Conditional block does not. */ +if (*cc == OP_COND || *cc == OP_SCOND) + has_alternatives = FALSE; + +cc = next_opcode(common, cc); +if (has_alternatives) + current_offset = common->then_offsets + (cc - common->start); + +while (cc < end) + { + if ((*cc >= OP_ASSERT && *cc <= OP_ASSERTBACK_NOT) || (*cc >= OP_ONCE && *cc <= OP_SCOND)) + cc = set_then_offsets(common, cc, current_offset); + else + { + if (*cc == OP_ALT && has_alternatives) + current_offset = common->then_offsets + (cc + 1 + LINK_SIZE - common->start); + if (*cc >= OP_THEN && *cc <= OP_THEN_ARG && current_offset != NULL) + *current_offset = 1; + cc = next_opcode(common, cc); + } + } + +return end; +} + +#undef CASE_ITERATOR_PRIVATE_DATA_1 +#undef CASE_ITERATOR_PRIVATE_DATA_2A +#undef CASE_ITERATOR_PRIVATE_DATA_2B +#undef CASE_ITERATOR_TYPE_PRIVATE_DATA_1 +#undef CASE_ITERATOR_TYPE_PRIVATE_DATA_2A +#undef CASE_ITERATOR_TYPE_PRIVATE_DATA_2B + +static SLJIT_INLINE BOOL is_powerof2(unsigned int value) +{ +return (value & (value - 1)) == 0; +} + +static SLJIT_INLINE void set_jumps(jump_list *list, struct sljit_label *label) +{ +while (list) + { + /* sljit_set_label is clever enough to do nothing + if either the jump or the label is NULL. */ + SET_LABEL(list->jump, label); + list = list->next; + } +} + +static SLJIT_INLINE void add_jump(struct sljit_compiler *compiler, jump_list **list, struct sljit_jump* jump) +{ +jump_list *list_item = sljit_alloc_memory(compiler, sizeof(jump_list)); +if (list_item) + { + list_item->next = *list; + list_item->jump = jump; + *list = list_item; + } +} + +static void add_stub(compiler_common *common, struct sljit_jump *start) +{ +DEFINE_COMPILER; +stub_list* list_item = sljit_alloc_memory(compiler, sizeof(stub_list)); + +if (list_item) + { + list_item->start = start; + list_item->quit = LABEL(); + list_item->next = common->stubs; + common->stubs = list_item; + } +} + +static void flush_stubs(compiler_common *common) +{ +DEFINE_COMPILER; +stub_list* list_item = common->stubs; + +while (list_item) + { + JUMPHERE(list_item->start); + add_jump(compiler, &common->stackalloc, JUMP(SLJIT_FAST_CALL)); + JUMPTO(SLJIT_JUMP, list_item->quit); + list_item = list_item->next; + } +common->stubs = NULL; +} + +static void add_label_addr(compiler_common *common) +{ +DEFINE_COMPILER; +label_addr_list *label_addr; + +label_addr = sljit_alloc_memory(compiler, sizeof(label_addr_list)); +if (label_addr == NULL) + return; +label_addr->label = LABEL(); +label_addr->addr = common->read_only_data_ptr; +label_addr->next = common->label_addrs; +common->label_addrs = label_addr; +common->read_only_data_ptr++; +} + +static SLJIT_INLINE void count_match(compiler_common *common) +{ +DEFINE_COMPILER; + +OP2(SLJIT_SUB | SLJIT_SET_E, COUNT_MATCH, 0, COUNT_MATCH, 0, SLJIT_IMM, 1); +add_jump(compiler, &common->calllimit, JUMP(SLJIT_C_ZERO)); +} + +static SLJIT_INLINE void allocate_stack(compiler_common *common, int size) +{ +/* May destroy all locals and registers except TMP2. */ +DEFINE_COMPILER; + +OP2(SLJIT_ADD, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, size * sizeof(sljit_sw)); +#ifdef DESTROY_REGISTERS +OP1(SLJIT_MOV, TMP1, 0, SLJIT_IMM, 12345); +OP1(SLJIT_MOV, TMP3, 0, TMP1, 0); +OP1(SLJIT_MOV, RETURN_ADDR, 0, TMP1, 0); +OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS0, TMP1, 0); +OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS1, TMP1, 0); +#endif +add_stub(common, CMP(SLJIT_C_GREATER, STACK_TOP, 0, STACK_LIMIT, 0)); +} + +static SLJIT_INLINE void free_stack(compiler_common *common, int size) +{ +DEFINE_COMPILER; +OP2(SLJIT_SUB, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, size * sizeof(sljit_sw)); +} + +static SLJIT_INLINE void reset_ovector(compiler_common *common, int length) +{ +DEFINE_COMPILER; +struct sljit_label *loop; +int i; + +/* At this point we can freely use all temporary registers. */ +SLJIT_ASSERT(length > 1); +/* TMP1 returns with begin - 1. */ +OP2(SLJIT_SUB, SLJIT_SCRATCH_REG1, 0, SLJIT_MEM1(SLJIT_SAVED_REG1), SLJIT_OFFSETOF(jit_arguments, begin), SLJIT_IMM, IN_UCHARS(1)); +if (length < 8) + { + for (i = 1; i < length; i++) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(i), SLJIT_SCRATCH_REG1, 0); + } +else + { + GET_LOCAL_BASE(SLJIT_SCRATCH_REG2, 0, OVECTOR_START); + OP1(SLJIT_MOV, SLJIT_SCRATCH_REG3, 0, SLJIT_IMM, length - 1); + loop = LABEL(); + OP1(SLJIT_MOVU, SLJIT_MEM1(SLJIT_SCRATCH_REG2), sizeof(sljit_sw), SLJIT_SCRATCH_REG1, 0); + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_SCRATCH_REG3, 0, SLJIT_SCRATCH_REG3, 0, SLJIT_IMM, 1); + JUMPTO(SLJIT_C_NOT_ZERO, loop); + } +} + +static SLJIT_INLINE void do_reset_match(compiler_common *common, int length) +{ +DEFINE_COMPILER; +struct sljit_label *loop; +int i; + +SLJIT_ASSERT(length > 1); +/* OVECTOR(1) contains the "string begin - 1" constant. */ +if (length > 2) + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(1)); +if (length < 8) + { + for (i = 2; i < length; i++) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(i), TMP1, 0); + } +else + { + GET_LOCAL_BASE(TMP2, 0, OVECTOR_START + sizeof(sljit_sw)); + OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_IMM, length - 2); + loop = LABEL(); + OP1(SLJIT_MOVU, SLJIT_MEM1(TMP2), sizeof(sljit_sw), TMP1, 0); + OP2(SLJIT_SUB | SLJIT_SET_E, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, 1); + JUMPTO(SLJIT_C_NOT_ZERO, loop); + } + +OP1(SLJIT_MOV, STACK_TOP, 0, ARGUMENTS, 0); +if (common->mark_ptr != 0) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->mark_ptr, SLJIT_IMM, 0); +if (common->control_head_ptr != 0) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr, SLJIT_IMM, 0); +OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(STACK_TOP), SLJIT_OFFSETOF(jit_arguments, stack)); +OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->start_ptr); +OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(STACK_TOP), SLJIT_OFFSETOF(struct sljit_stack, base)); +} + +static sljit_sw SLJIT_CALL do_search_mark(sljit_sw *current, const pcre_uchar *skip_arg) +{ +while (current != NULL) + { + switch (current[-2]) + { + case type_then_trap: + break; + + case type_mark: + if (STRCMP_UC_UC(skip_arg, (pcre_uchar *)current[-3]) == 0) + return current[-4]; + break; + + default: + SLJIT_ASSERT_STOP(); + break; + } + current = (sljit_sw*)current[-1]; + } +return -1; +} + +static SLJIT_INLINE void copy_ovector(compiler_common *common, int topbracket) +{ +DEFINE_COMPILER; +struct sljit_label *loop; +struct sljit_jump *early_quit; + +/* At this point we can freely use all registers. */ +OP1(SLJIT_MOV, SLJIT_SAVED_REG3, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(1)); +OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(1), STR_PTR, 0); + +OP1(SLJIT_MOV, SLJIT_SCRATCH_REG1, 0, ARGUMENTS, 0); +if (common->mark_ptr != 0) + OP1(SLJIT_MOV, SLJIT_SCRATCH_REG3, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->mark_ptr); +OP1(SLJIT_MOV_SI, SLJIT_SCRATCH_REG2, 0, SLJIT_MEM1(SLJIT_SCRATCH_REG1), SLJIT_OFFSETOF(jit_arguments, offset_count)); +if (common->mark_ptr != 0) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SCRATCH_REG1), SLJIT_OFFSETOF(jit_arguments, mark_ptr), SLJIT_SCRATCH_REG3, 0); +OP2(SLJIT_SUB, SLJIT_SCRATCH_REG3, 0, SLJIT_MEM1(SLJIT_SCRATCH_REG1), SLJIT_OFFSETOF(jit_arguments, offsets), SLJIT_IMM, sizeof(int)); +OP1(SLJIT_MOV, SLJIT_SCRATCH_REG1, 0, SLJIT_MEM1(SLJIT_SCRATCH_REG1), SLJIT_OFFSETOF(jit_arguments, begin)); +GET_LOCAL_BASE(SLJIT_SAVED_REG1, 0, OVECTOR_START); +/* Unlikely, but possible */ +early_quit = CMP(SLJIT_C_EQUAL, SLJIT_SCRATCH_REG2, 0, SLJIT_IMM, 0); +loop = LABEL(); +OP2(SLJIT_SUB, SLJIT_SAVED_REG2, 0, SLJIT_MEM1(SLJIT_SAVED_REG1), 0, SLJIT_SCRATCH_REG1, 0); +OP2(SLJIT_ADD, SLJIT_SAVED_REG1, 0, SLJIT_SAVED_REG1, 0, SLJIT_IMM, sizeof(sljit_sw)); +/* Copy the integer value to the output buffer */ +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 +OP2(SLJIT_ASHR, SLJIT_SAVED_REG2, 0, SLJIT_SAVED_REG2, 0, SLJIT_IMM, UCHAR_SHIFT); +#endif +OP1(SLJIT_MOVU_SI, SLJIT_MEM1(SLJIT_SCRATCH_REG3), sizeof(int), SLJIT_SAVED_REG2, 0); +OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_SCRATCH_REG2, 0, SLJIT_SCRATCH_REG2, 0, SLJIT_IMM, 1); +JUMPTO(SLJIT_C_NOT_ZERO, loop); +JUMPHERE(early_quit); + +/* Calculate the return value, which is the maximum ovector value. */ +if (topbracket > 1) + { + GET_LOCAL_BASE(SLJIT_SCRATCH_REG1, 0, OVECTOR_START + topbracket * 2 * sizeof(sljit_sw)); + OP1(SLJIT_MOV, SLJIT_SCRATCH_REG2, 0, SLJIT_IMM, topbracket + 1); + + /* OVECTOR(0) is never equal to SLJIT_SAVED_REG3. */ + loop = LABEL(); + OP1(SLJIT_MOVU, SLJIT_SCRATCH_REG3, 0, SLJIT_MEM1(SLJIT_SCRATCH_REG1), -(2 * (sljit_sw)sizeof(sljit_sw))); + OP2(SLJIT_SUB, SLJIT_SCRATCH_REG2, 0, SLJIT_SCRATCH_REG2, 0, SLJIT_IMM, 1); + CMPTO(SLJIT_C_EQUAL, SLJIT_SCRATCH_REG3, 0, SLJIT_SAVED_REG3, 0, loop); + OP1(SLJIT_MOV, SLJIT_RETURN_REG, 0, SLJIT_SCRATCH_REG2, 0); + } +else + OP1(SLJIT_MOV, SLJIT_RETURN_REG, 0, SLJIT_IMM, 1); +} + +static SLJIT_INLINE void return_with_partial_match(compiler_common *common, struct sljit_label *quit) +{ +DEFINE_COMPILER; +struct sljit_jump *jump; + +SLJIT_COMPILE_ASSERT(STR_END == SLJIT_SAVED_REG2, str_end_must_be_saved_reg2); +SLJIT_ASSERT(common->start_used_ptr != 0 && common->start_ptr != 0 + && (common->mode == JIT_PARTIAL_SOFT_COMPILE ? common->hit_start != 0 : common->hit_start == 0)); + +OP1(SLJIT_MOV, SLJIT_SCRATCH_REG2, 0, ARGUMENTS, 0); +OP1(SLJIT_MOV, SLJIT_RETURN_REG, 0, SLJIT_IMM, PCRE_ERROR_PARTIAL); +OP1(SLJIT_MOV_SI, SLJIT_SCRATCH_REG3, 0, SLJIT_MEM1(SLJIT_SCRATCH_REG2), SLJIT_OFFSETOF(jit_arguments, real_offset_count)); +CMPTO(SLJIT_C_SIG_LESS, SLJIT_SCRATCH_REG3, 0, SLJIT_IMM, 2, quit); + +/* Store match begin and end. */ +OP1(SLJIT_MOV, SLJIT_SAVED_REG1, 0, SLJIT_MEM1(SLJIT_SCRATCH_REG2), SLJIT_OFFSETOF(jit_arguments, begin)); +OP1(SLJIT_MOV, SLJIT_SCRATCH_REG2, 0, SLJIT_MEM1(SLJIT_SCRATCH_REG2), SLJIT_OFFSETOF(jit_arguments, offsets)); + +jump = CMP(SLJIT_C_SIG_LESS, SLJIT_SCRATCH_REG3, 0, SLJIT_IMM, 3); +OP2(SLJIT_SUB, SLJIT_SCRATCH_REG3, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->mode == JIT_PARTIAL_HARD_COMPILE ? common->start_ptr : (common->hit_start + (int)sizeof(sljit_sw)), SLJIT_SAVED_REG1, 0); +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 +OP2(SLJIT_ASHR, SLJIT_SCRATCH_REG3, 0, SLJIT_SCRATCH_REG3, 0, SLJIT_IMM, UCHAR_SHIFT); +#endif +OP1(SLJIT_MOV_SI, SLJIT_MEM1(SLJIT_SCRATCH_REG2), 2 * sizeof(int), SLJIT_SCRATCH_REG3, 0); +JUMPHERE(jump); + +OP1(SLJIT_MOV, SLJIT_SCRATCH_REG3, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->mode == JIT_PARTIAL_HARD_COMPILE ? common->start_used_ptr : common->hit_start); +OP2(SLJIT_SUB, SLJIT_SAVED_REG2, 0, STR_END, 0, SLJIT_SAVED_REG1, 0); +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 +OP2(SLJIT_ASHR, SLJIT_SAVED_REG2, 0, SLJIT_SAVED_REG2, 0, SLJIT_IMM, UCHAR_SHIFT); +#endif +OP1(SLJIT_MOV_SI, SLJIT_MEM1(SLJIT_SCRATCH_REG2), sizeof(int), SLJIT_SAVED_REG2, 0); + +OP2(SLJIT_SUB, SLJIT_SCRATCH_REG3, 0, SLJIT_SCRATCH_REG3, 0, SLJIT_SAVED_REG1, 0); +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 +OP2(SLJIT_ASHR, SLJIT_SCRATCH_REG3, 0, SLJIT_SCRATCH_REG3, 0, SLJIT_IMM, UCHAR_SHIFT); +#endif +OP1(SLJIT_MOV_SI, SLJIT_MEM1(SLJIT_SCRATCH_REG2), 0, SLJIT_SCRATCH_REG3, 0); + +JUMPTO(SLJIT_JUMP, quit); +} + +static SLJIT_INLINE void check_start_used_ptr(compiler_common *common) +{ +/* May destroy TMP1. */ +DEFINE_COMPILER; +struct sljit_jump *jump; + +if (common->mode == JIT_PARTIAL_SOFT_COMPILE) + { + /* The value of -1 must be kept for start_used_ptr! */ + OP2(SLJIT_ADD, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->start_used_ptr, SLJIT_IMM, 1); + /* Jumps if start_used_ptr < STR_PTR, or start_used_ptr == -1. Although overwriting + is not necessary if start_used_ptr == STR_PTR, it does not hurt as well. */ + jump = CMP(SLJIT_C_LESS_EQUAL, TMP1, 0, STR_PTR, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->start_used_ptr, STR_PTR, 0); + JUMPHERE(jump); + } +else if (common->mode == JIT_PARTIAL_HARD_COMPILE) + { + jump = CMP(SLJIT_C_LESS_EQUAL, SLJIT_MEM1(SLJIT_LOCALS_REG), common->start_used_ptr, STR_PTR, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->start_used_ptr, STR_PTR, 0); + JUMPHERE(jump); + } +} + +static SLJIT_INLINE BOOL char_has_othercase(compiler_common *common, pcre_uchar* cc) +{ +/* Detects if the character has an othercase. */ +unsigned int c; + +#ifdef SUPPORT_UTF +if (common->utf) + { + GETCHAR(c, cc); + if (c > 127) + { +#ifdef SUPPORT_UCP + return c != UCD_OTHERCASE(c); +#else + return FALSE; +#endif + } +#ifndef COMPILE_PCRE8 + return common->fcc[c] != c; +#endif + } +else +#endif + c = *cc; +return MAX_255(c) ? common->fcc[c] != c : FALSE; +} + +static SLJIT_INLINE unsigned int char_othercase(compiler_common *common, unsigned int c) +{ +/* Returns with the othercase. */ +#ifdef SUPPORT_UTF +if (common->utf && c > 127) + { +#ifdef SUPPORT_UCP + return UCD_OTHERCASE(c); +#else + return c; +#endif + } +#endif +return TABLE_GET(c, common->fcc, c); +} + +static unsigned int char_get_othercase_bit(compiler_common *common, pcre_uchar* cc) +{ +/* Detects if the character and its othercase has only 1 bit difference. */ +unsigned int c, oc, bit; +#if defined SUPPORT_UTF && defined COMPILE_PCRE8 +int n; +#endif + +#ifdef SUPPORT_UTF +if (common->utf) + { + GETCHAR(c, cc); + if (c <= 127) + oc = common->fcc[c]; + else + { +#ifdef SUPPORT_UCP + oc = UCD_OTHERCASE(c); +#else + oc = c; +#endif + } + } +else + { + c = *cc; + oc = TABLE_GET(c, common->fcc, c); + } +#else +c = *cc; +oc = TABLE_GET(c, common->fcc, c); +#endif + +SLJIT_ASSERT(c != oc); + +bit = c ^ oc; +/* Optimized for English alphabet. */ +if (c <= 127 && bit == 0x20) + return (0 << 8) | 0x20; + +/* Since c != oc, they must have at least 1 bit difference. */ +if (!is_powerof2(bit)) + return 0; + +#if defined COMPILE_PCRE8 + +#ifdef SUPPORT_UTF +if (common->utf && c > 127) + { + n = GET_EXTRALEN(*cc); + while ((bit & 0x3f) == 0) + { + n--; + bit >>= 6; + } + return (n << 8) | bit; + } +#endif /* SUPPORT_UTF */ +return (0 << 8) | bit; + +#elif defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + +#ifdef SUPPORT_UTF +if (common->utf && c > 65535) + { + if (bit >= (1 << 10)) + bit >>= 10; + else + return (bit < 256) ? ((2 << 8) | bit) : ((3 << 8) | (bit >> 8)); + } +#endif /* SUPPORT_UTF */ +return (bit < 256) ? ((0 << 8) | bit) : ((1 << 8) | (bit >> 8)); + +#endif /* COMPILE_PCRE[8|16|32] */ +} + +static void check_partial(compiler_common *common, BOOL force) +{ +/* Checks whether a partial matching is occurred. Does not modify registers. */ +DEFINE_COMPILER; +struct sljit_jump *jump = NULL; + +SLJIT_ASSERT(!force || common->mode != JIT_COMPILE); + +if (common->mode == JIT_COMPILE) + return; + +if (!force) + jump = CMP(SLJIT_C_GREATER_EQUAL, SLJIT_MEM1(SLJIT_LOCALS_REG), common->start_used_ptr, STR_PTR, 0); +else if (common->mode == JIT_PARTIAL_SOFT_COMPILE) + jump = CMP(SLJIT_C_EQUAL, SLJIT_MEM1(SLJIT_LOCALS_REG), common->start_used_ptr, SLJIT_IMM, -1); + +if (common->mode == JIT_PARTIAL_SOFT_COMPILE) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->hit_start, SLJIT_IMM, 0); +else + { + if (common->partialmatchlabel != NULL) + JUMPTO(SLJIT_JUMP, common->partialmatchlabel); + else + add_jump(compiler, &common->partialmatch, JUMP(SLJIT_JUMP)); + } + +if (jump != NULL) + JUMPHERE(jump); +} + +static void check_str_end(compiler_common *common, jump_list **end_reached) +{ +/* Does not affect registers. Usually used in a tight spot. */ +DEFINE_COMPILER; +struct sljit_jump *jump; + +if (common->mode == JIT_COMPILE) + { + add_jump(compiler, end_reached, CMP(SLJIT_C_GREATER_EQUAL, STR_PTR, 0, STR_END, 0)); + return; + } + +jump = CMP(SLJIT_C_LESS, STR_PTR, 0, STR_END, 0); +if (common->mode == JIT_PARTIAL_SOFT_COMPILE) + { + add_jump(compiler, end_reached, CMP(SLJIT_C_GREATER_EQUAL, SLJIT_MEM1(SLJIT_LOCALS_REG), common->start_used_ptr, STR_PTR, 0)); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->hit_start, SLJIT_IMM, 0); + add_jump(compiler, end_reached, JUMP(SLJIT_JUMP)); + } +else + { + add_jump(compiler, end_reached, CMP(SLJIT_C_GREATER_EQUAL, SLJIT_MEM1(SLJIT_LOCALS_REG), common->start_used_ptr, STR_PTR, 0)); + if (common->partialmatchlabel != NULL) + JUMPTO(SLJIT_JUMP, common->partialmatchlabel); + else + add_jump(compiler, &common->partialmatch, JUMP(SLJIT_JUMP)); + } +JUMPHERE(jump); +} + +static void detect_partial_match(compiler_common *common, jump_list **backtracks) +{ +DEFINE_COMPILER; +struct sljit_jump *jump; + +if (common->mode == JIT_COMPILE) + { + add_jump(compiler, backtracks, CMP(SLJIT_C_GREATER_EQUAL, STR_PTR, 0, STR_END, 0)); + return; + } + +/* Partial matching mode. */ +jump = CMP(SLJIT_C_LESS, STR_PTR, 0, STR_END, 0); +add_jump(compiler, backtracks, CMP(SLJIT_C_GREATER_EQUAL, SLJIT_MEM1(SLJIT_LOCALS_REG), common->start_used_ptr, STR_PTR, 0)); +if (common->mode == JIT_PARTIAL_SOFT_COMPILE) + { + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->hit_start, SLJIT_IMM, 0); + add_jump(compiler, backtracks, JUMP(SLJIT_JUMP)); + } +else + { + if (common->partialmatchlabel != NULL) + JUMPTO(SLJIT_JUMP, common->partialmatchlabel); + else + add_jump(compiler, &common->partialmatch, JUMP(SLJIT_JUMP)); + } +JUMPHERE(jump); +} + +static void peek_char(compiler_common *common, pcre_uint32 max) +{ +/* Reads the character into TMP1, keeps STR_PTR. +Does not check STR_END. TMP2 Destroyed. */ +DEFINE_COMPILER; +#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 +struct sljit_jump *jump; +#endif + +SLJIT_UNUSED_ARG(max); + +OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), 0); +#if defined SUPPORT_UTF && defined COMPILE_PCRE8 +if (common->utf) + { + if (max < 128) return; + + jump = CMP(SLJIT_C_LESS, TMP1, 0, SLJIT_IMM, 0xc0); + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); + add_jump(compiler, &common->utfreadchar, JUMP(SLJIT_FAST_CALL)); + OP2(SLJIT_SUB, STR_PTR, 0, STR_PTR, 0, TMP2, 0); + JUMPHERE(jump); + } +#endif /* SUPPORT_UTF && !COMPILE_PCRE32 */ + +#if defined SUPPORT_UTF && defined COMPILE_PCRE16 +if (common->utf) + { + if (max < 0xd800) return; + + OP2(SLJIT_SUB, TMP2, 0, TMP1, 0, SLJIT_IMM, 0xd800); + jump = CMP(SLJIT_C_GREATER, TMP2, 0, SLJIT_IMM, 0xdc00 - 0xd800 - 1); + /* TMP2 contains the high surrogate. */ + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); + OP2(SLJIT_ADD, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x40); + OP2(SLJIT_SHL, TMP2, 0, TMP2, 0, SLJIT_IMM, 10); + OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x3ff); + OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); + JUMPHERE(jump); + } +#endif +} + +#if defined SUPPORT_UTF && defined COMPILE_PCRE8 + +static BOOL is_char7_bitset(const pcre_uint8 *bitset, BOOL nclass) +{ +/* Tells whether the character codes below 128 are enough +to determine a match. */ +const pcre_uint8 value = nclass ? 0xff : 0; +const pcre_uint8* end = bitset + 32; + +bitset += 16; +do + { + if (*bitset++ != value) + return FALSE; + } +while (bitset < end); +return TRUE; +} + +static void read_char7_type(compiler_common *common, BOOL full_read) +{ +/* Reads the precise character type of a character into TMP1, if the character +is less than 128. Otherwise it returns with zero. Does not check STR_END. The +full_read argument tells whether characters above max are accepted or not. */ +DEFINE_COMPILER; +struct sljit_jump *jump; + +SLJIT_ASSERT(common->utf); + +OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), 0); +OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); + +OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP2), common->ctypes); + +if (full_read) + { + jump = CMP(SLJIT_C_LESS, TMP2, 0, SLJIT_IMM, 0xc0); + OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP2), (sljit_sw)PRIV(utf8_table4) - 0xc0); + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP2, 0); + JUMPHERE(jump); + } +} + +#endif /* SUPPORT_UTF && COMPILE_PCRE8 */ + +static void read_char_range(compiler_common *common, pcre_uint32 min, pcre_uint32 max, BOOL update_str_ptr) +{ +/* Reads the precise value of a character into TMP1, if the character is +between min and max (c >= min && c <= max). Otherwise it returns with a value +outside the range. Does not check STR_END. */ +DEFINE_COMPILER; +#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 +struct sljit_jump *jump; +#endif +#if defined SUPPORT_UTF && defined COMPILE_PCRE8 +struct sljit_jump *jump2; +#endif + +SLJIT_UNUSED_ARG(update_str_ptr); +SLJIT_UNUSED_ARG(min); +SLJIT_UNUSED_ARG(max); +SLJIT_ASSERT(min <= max); + +OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); +OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); + +#if defined SUPPORT_UTF && defined COMPILE_PCRE8 +if (common->utf) + { + if (max < 128 && !update_str_ptr) return; + + jump = CMP(SLJIT_C_LESS, TMP1, 0, SLJIT_IMM, 0xc0); + if (min >= 0x10000) + { + OP2(SLJIT_SUB, TMP2, 0, TMP1, 0, SLJIT_IMM, 0xf0); + if (update_str_ptr) + OP1(SLJIT_MOV_UB, RETURN_ADDR, 0, SLJIT_MEM1(TMP1), (sljit_sw)PRIV(utf8_table4) - 0xc0); + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); + jump2 = CMP(SLJIT_C_GREATER, TMP2, 0, SLJIT_IMM, 0x7); + OP2(SLJIT_SHL, TMP2, 0, TMP2, 0, SLJIT_IMM, 6); + OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x3f); + OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); + OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(1)); + OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 6); + OP2(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x3f); + OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); + OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(2)); + if (!update_str_ptr) + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(3)); + OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 6); + OP2(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x3f); + OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); + JUMPHERE(jump2); + if (update_str_ptr) + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, RETURN_ADDR, 0); + } + else if (min >= 0x800 && max <= 0xffff) + { + OP2(SLJIT_SUB, TMP2, 0, TMP1, 0, SLJIT_IMM, 0xe0); + if (update_str_ptr) + OP1(SLJIT_MOV_UB, RETURN_ADDR, 0, SLJIT_MEM1(TMP1), (sljit_sw)PRIV(utf8_table4) - 0xc0); + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); + jump2 = CMP(SLJIT_C_GREATER, TMP2, 0, SLJIT_IMM, 0xf); + OP2(SLJIT_SHL, TMP2, 0, TMP2, 0, SLJIT_IMM, 6); + OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x3f); + OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); + OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(1)); + if (!update_str_ptr) + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(2)); + OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 6); + OP2(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x3f); + OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); + JUMPHERE(jump2); + if (update_str_ptr) + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, RETURN_ADDR, 0); + } + else if (max >= 0x800) + add_jump(compiler, (max < 0x10000) ? &common->utfreadchar16 : &common->utfreadchar, JUMP(SLJIT_FAST_CALL)); + else if (max < 128) + { + OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP1), (sljit_sw)PRIV(utf8_table4) - 0xc0); + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP2, 0); + } + else + { + OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); + if (!update_str_ptr) + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); + else + OP1(SLJIT_MOV_UB, RETURN_ADDR, 0, SLJIT_MEM1(TMP1), (sljit_sw)PRIV(utf8_table4) - 0xc0); + OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x3f); + OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 6); + OP2(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x3f); + OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); + if (update_str_ptr) + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, RETURN_ADDR, 0); + } + JUMPHERE(jump); + } +#endif + +#if defined SUPPORT_UTF && defined COMPILE_PCRE16 +if (common->utf) + { + if (max >= 0x10000) + { + OP2(SLJIT_SUB, TMP2, 0, TMP1, 0, SLJIT_IMM, 0xd800); + jump = CMP(SLJIT_C_GREATER, TMP2, 0, SLJIT_IMM, 0xdc00 - 0xd800 - 1); + /* TMP2 contains the high surrogate. */ + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); + OP2(SLJIT_ADD, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x40); + OP2(SLJIT_SHL, TMP2, 0, TMP2, 0, SLJIT_IMM, 10); + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); + OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x3ff); + OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); + JUMPHERE(jump); + return; + } + + if (max < 0xd800 && !update_str_ptr) return; + + /* Skip low surrogate if necessary. */ + OP2(SLJIT_SUB, TMP2, 0, TMP1, 0, SLJIT_IMM, 0xd800); + jump = CMP(SLJIT_C_GREATER, TMP2, 0, SLJIT_IMM, 0xdc00 - 0xd800 - 1); + if (update_str_ptr) + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); + if (max >= 0xd800) + OP1(SLJIT_MOV, TMP1, 0, SLJIT_IMM, 0x10000); + JUMPHERE(jump); + } +#endif +} + +static SLJIT_INLINE void read_char(compiler_common *common) +{ +read_char_range(common, 0, READ_CHAR_MAX, TRUE); +} + +static void read_char8_type(compiler_common *common, BOOL update_str_ptr) +{ +/* Reads the character type into TMP1, updates STR_PTR. Does not check STR_END. */ +DEFINE_COMPILER; +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 +struct sljit_jump *jump; +#endif +#if defined SUPPORT_UTF && defined COMPILE_PCRE8 +struct sljit_jump *jump2; +#endif + +SLJIT_UNUSED_ARG(update_str_ptr); + +OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), 0); +OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); + +#if defined SUPPORT_UTF && defined COMPILE_PCRE8 +if (common->utf) + { + /* This can be an extra read in some situations, but hopefully + it is needed in most cases. */ + OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP2), common->ctypes); + jump = CMP(SLJIT_C_LESS, TMP2, 0, SLJIT_IMM, 0xc0); + if (!update_str_ptr) + { + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); + OP2(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x3f); + OP2(SLJIT_SHL, TMP2, 0, TMP2, 0, SLJIT_IMM, 6); + OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x3f); + OP2(SLJIT_OR, TMP2, 0, TMP2, 0, TMP1, 0); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_IMM, 0); + jump2 = CMP(SLJIT_C_GREATER, TMP2, 0, SLJIT_IMM, 255); + OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP2), common->ctypes); + JUMPHERE(jump2); + } + else + add_jump(compiler, &common->utfreadtype8, JUMP(SLJIT_FAST_CALL)); + JUMPHERE(jump); + return; + } +#endif /* SUPPORT_UTF && COMPILE_PCRE8 */ + +#if !defined COMPILE_PCRE8 +/* The ctypes array contains only 256 values. */ +OP1(SLJIT_MOV, TMP1, 0, SLJIT_IMM, 0); +jump = CMP(SLJIT_C_GREATER, TMP2, 0, SLJIT_IMM, 255); +#endif +OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP2), common->ctypes); +#if !defined COMPILE_PCRE8 +JUMPHERE(jump); +#endif + +#if defined SUPPORT_UTF && defined COMPILE_PCRE16 +if (common->utf && update_str_ptr) + { + /* Skip low surrogate if necessary. */ + OP2(SLJIT_SUB, TMP2, 0, TMP2, 0, SLJIT_IMM, 0xd800); + jump = CMP(SLJIT_C_GREATER, TMP2, 0, SLJIT_IMM, 0xdc00 - 0xd800 - 1); + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); + JUMPHERE(jump); + } +#endif /* SUPPORT_UTF && COMPILE_PCRE16 */ +} + +static void skip_char_back(compiler_common *common) +{ +/* Goes one character back. Affects STR_PTR and TMP1. Does not check begin. */ +DEFINE_COMPILER; +#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 +#if defined COMPILE_PCRE8 +struct sljit_label *label; + +if (common->utf) + { + label = LABEL(); + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), -IN_UCHARS(1)); + OP2(SLJIT_SUB, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); + OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0xc0); + CMPTO(SLJIT_C_EQUAL, TMP1, 0, SLJIT_IMM, 0x80, label); + return; + } +#elif defined COMPILE_PCRE16 +if (common->utf) + { + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), -IN_UCHARS(1)); + OP2(SLJIT_SUB, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); + /* Skip low surrogate if necessary. */ + OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0xfc00); + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0xdc00); + OP_FLAGS(SLJIT_MOV, TMP1, 0, SLJIT_UNUSED, 0, SLJIT_C_EQUAL); + OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 1); + OP2(SLJIT_SUB, STR_PTR, 0, STR_PTR, 0, TMP1, 0); + return; + } +#endif /* COMPILE_PCRE[8|16] */ +#endif /* SUPPORT_UTF && !COMPILE_PCRE32 */ +OP2(SLJIT_SUB, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); +} + +static void check_newlinechar(compiler_common *common, int nltype, jump_list **backtracks, BOOL jumpifmatch) +{ +/* Character comes in TMP1. Checks if it is a newline. TMP2 may be destroyed. */ +DEFINE_COMPILER; +struct sljit_jump *jump; + +if (nltype == NLTYPE_ANY) + { + add_jump(compiler, &common->anynewline, JUMP(SLJIT_FAST_CALL)); + add_jump(compiler, backtracks, JUMP(jumpifmatch ? SLJIT_C_NOT_ZERO : SLJIT_C_ZERO)); + } +else if (nltype == NLTYPE_ANYCRLF) + { + if (jumpifmatch) + { + add_jump(compiler, backtracks, CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_IMM, CHAR_CR)); + add_jump(compiler, backtracks, CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_IMM, CHAR_NL)); + } + else + { + jump = CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_IMM, CHAR_CR); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, TMP1, 0, SLJIT_IMM, CHAR_NL)); + JUMPHERE(jump); + } + } +else + { + SLJIT_ASSERT(nltype == NLTYPE_FIXED && common->newline < 256); + add_jump(compiler, backtracks, CMP(jumpifmatch ? SLJIT_C_EQUAL : SLJIT_C_NOT_EQUAL, TMP1, 0, SLJIT_IMM, common->newline)); + } +} + +#ifdef SUPPORT_UTF + +#if defined COMPILE_PCRE8 +static void do_utfreadchar(compiler_common *common) +{ +/* Fast decoding a UTF-8 character. TMP1 contains the first byte +of the character (>= 0xc0). Return char value in TMP1, length in TMP2. */ +DEFINE_COMPILER; +struct sljit_jump *jump; + +sljit_emit_fast_enter(compiler, RETURN_ADDR, 0); +OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); +OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x3f); +OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 6); +OP2(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x3f); +OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); + +/* Searching for the first zero. */ +OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x800); +jump = JUMP(SLJIT_C_NOT_ZERO); +/* Two byte sequence. */ +OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); +OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, IN_UCHARS(2)); +sljit_emit_fast_return(compiler, RETURN_ADDR, 0); + +JUMPHERE(jump); +OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(1)); +OP2(SLJIT_XOR, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x800); +OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 6); +OP2(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x3f); +OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); + +OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x10000); +jump = JUMP(SLJIT_C_NOT_ZERO); +/* Three byte sequence. */ +OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(2)); +OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, IN_UCHARS(3)); +sljit_emit_fast_return(compiler, RETURN_ADDR, 0); + +/* Four byte sequence. */ +JUMPHERE(jump); +OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(2)); +OP2(SLJIT_XOR, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x10000); +OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 6); +OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(3)); +OP2(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x3f); +OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); +OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, IN_UCHARS(4)); +sljit_emit_fast_return(compiler, RETURN_ADDR, 0); +} + +static void do_utfreadchar16(compiler_common *common) +{ +/* Fast decoding a UTF-8 character. TMP1 contains the first byte +of the character (>= 0xc0). Return value in TMP1. */ +DEFINE_COMPILER; +struct sljit_jump *jump; + +sljit_emit_fast_enter(compiler, RETURN_ADDR, 0); +OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); +OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x3f); +OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 6); +OP2(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x3f); +OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); + +/* Searching for the first zero. */ +OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x800); +jump = JUMP(SLJIT_C_NOT_ZERO); +/* Two byte sequence. */ +OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); +sljit_emit_fast_return(compiler, RETURN_ADDR, 0); + +JUMPHERE(jump); +OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x400); +OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_C_NOT_ZERO); +/* This code runs only in 8 bit mode. No need to shift the value. */ +OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP2, 0); +OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(1)); +OP2(SLJIT_XOR, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x800); +OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 6); +OP2(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x3f); +OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); +/* Three byte sequence. */ +OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(2)); +sljit_emit_fast_return(compiler, RETURN_ADDR, 0); +} + +static void do_utfreadtype8(compiler_common *common) +{ +/* Fast decoding a UTF-8 character type. TMP2 contains the first byte +of the character (>= 0xc0). Return value in TMP1. */ +DEFINE_COMPILER; +struct sljit_jump *jump; +struct sljit_jump *compare; + +sljit_emit_fast_enter(compiler, RETURN_ADDR, 0); + +OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP2, 0, SLJIT_IMM, 0x20); +jump = JUMP(SLJIT_C_NOT_ZERO); +/* Two byte sequence. */ +OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); +OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); +OP2(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x1f); +/* The upper 5 bits are known at this point. */ +compare = CMP(SLJIT_C_GREATER, TMP2, 0, SLJIT_IMM, 0x3); +OP2(SLJIT_SHL, TMP2, 0, TMP2, 0, SLJIT_IMM, 6); +OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x3f); +OP2(SLJIT_OR, TMP2, 0, TMP2, 0, TMP1, 0); +OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP2), common->ctypes); +sljit_emit_fast_return(compiler, RETURN_ADDR, 0); + +JUMPHERE(compare); +OP1(SLJIT_MOV, TMP1, 0, SLJIT_IMM, 0); +sljit_emit_fast_return(compiler, RETURN_ADDR, 0); + +/* We only have types for characters less than 256. */ +JUMPHERE(jump); +OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP2), (sljit_sw)PRIV(utf8_table4) - 0xc0); +OP1(SLJIT_MOV, TMP1, 0, SLJIT_IMM, 0); +OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP2, 0); +sljit_emit_fast_return(compiler, RETURN_ADDR, 0); +} + +#endif /* COMPILE_PCRE8 */ + +#endif /* SUPPORT_UTF */ + +#ifdef SUPPORT_UCP + +/* UCD_BLOCK_SIZE must be 128 (see the assert below). */ +#define UCD_BLOCK_MASK 127 +#define UCD_BLOCK_SHIFT 7 + +static void do_getucd(compiler_common *common) +{ +/* Search the UCD record for the character comes in TMP1. +Returns chartype in TMP1 and UCD offset in TMP2. */ +DEFINE_COMPILER; + +SLJIT_ASSERT(UCD_BLOCK_SIZE == 128 && sizeof(ucd_record) == 8); + +sljit_emit_fast_enter(compiler, RETURN_ADDR, 0); +OP2(SLJIT_LSHR, TMP2, 0, TMP1, 0, SLJIT_IMM, UCD_BLOCK_SHIFT); +OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP2), (sljit_sw)PRIV(ucd_stage1)); +OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, UCD_BLOCK_MASK); +OP2(SLJIT_SHL, TMP2, 0, TMP2, 0, SLJIT_IMM, UCD_BLOCK_SHIFT); +OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, TMP2, 0); +OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, (sljit_sw)PRIV(ucd_stage2)); +OP1(SLJIT_MOV_UH, TMP2, 0, SLJIT_MEM2(TMP2, TMP1), 1); +OP1(SLJIT_MOV, TMP1, 0, SLJIT_IMM, (sljit_sw)PRIV(ucd_records) + SLJIT_OFFSETOF(ucd_record, chartype)); +OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM2(TMP1, TMP2), 3); +sljit_emit_fast_return(compiler, RETURN_ADDR, 0); +} +#endif + +static SLJIT_INLINE struct sljit_label *mainloop_entry(compiler_common *common, BOOL hascrorlf, BOOL firstline) +{ +DEFINE_COMPILER; +struct sljit_label *mainloop; +struct sljit_label *newlinelabel = NULL; +struct sljit_jump *start; +struct sljit_jump *end = NULL; +struct sljit_jump *nl = NULL; +#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 +struct sljit_jump *singlechar; +#endif +jump_list *newline = NULL; +BOOL newlinecheck = FALSE; +BOOL readuchar = FALSE; + +if (!(hascrorlf || firstline) && (common->nltype == NLTYPE_ANY || + common->nltype == NLTYPE_ANYCRLF || common->newline > 255)) + newlinecheck = TRUE; + +if (firstline) + { + /* Search for the end of the first line. */ + SLJIT_ASSERT(common->first_line_end != 0); + OP1(SLJIT_MOV, TMP3, 0, STR_PTR, 0); + + if (common->nltype == NLTYPE_FIXED && common->newline > 255) + { + mainloop = LABEL(); + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); + end = CMP(SLJIT_C_GREATER_EQUAL, STR_PTR, 0, STR_END, 0); + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(-1)); + OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); + CMPTO(SLJIT_C_NOT_EQUAL, TMP1, 0, SLJIT_IMM, (common->newline >> 8) & 0xff, mainloop); + CMPTO(SLJIT_C_NOT_EQUAL, TMP2, 0, SLJIT_IMM, common->newline & 0xff, mainloop); + JUMPHERE(end); + OP2(SLJIT_SUB, SLJIT_MEM1(SLJIT_LOCALS_REG), common->first_line_end, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); + } + else + { + end = CMP(SLJIT_C_GREATER_EQUAL, STR_PTR, 0, STR_END, 0); + mainloop = LABEL(); + /* Continual stores does not cause data dependency. */ + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->first_line_end, STR_PTR, 0); + read_char_range(common, common->nlmin, common->nlmax, TRUE); + check_newlinechar(common, common->nltype, &newline, TRUE); + CMPTO(SLJIT_C_LESS, STR_PTR, 0, STR_END, 0, mainloop); + JUMPHERE(end); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->first_line_end, STR_PTR, 0); + set_jumps(newline, LABEL()); + } + + OP1(SLJIT_MOV, STR_PTR, 0, TMP3, 0); + } + +start = JUMP(SLJIT_JUMP); + +if (newlinecheck) + { + newlinelabel = LABEL(); + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); + end = CMP(SLJIT_C_GREATER_EQUAL, STR_PTR, 0, STR_END, 0); + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), 0); + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, common->newline & 0xff); + OP_FLAGS(SLJIT_MOV, TMP1, 0, SLJIT_UNUSED, 0, SLJIT_C_EQUAL); +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, UCHAR_SHIFT); +#endif + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP1, 0); + nl = JUMP(SLJIT_JUMP); + } + +mainloop = LABEL(); + +/* Increasing the STR_PTR here requires one less jump in the most common case. */ +#ifdef SUPPORT_UTF +if (common->utf) readuchar = TRUE; +#endif +if (newlinecheck) readuchar = TRUE; + +if (readuchar) + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), 0); + +if (newlinecheck) + CMPTO(SLJIT_C_EQUAL, TMP1, 0, SLJIT_IMM, (common->newline >> 8) & 0xff, newlinelabel); + +OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); +#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 +#if defined COMPILE_PCRE8 +if (common->utf) + { + singlechar = CMP(SLJIT_C_LESS, TMP1, 0, SLJIT_IMM, 0xc0); + OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP1), (sljit_sw)PRIV(utf8_table4) - 0xc0); + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP1, 0); + JUMPHERE(singlechar); + } +#elif defined COMPILE_PCRE16 +if (common->utf) + { + singlechar = CMP(SLJIT_C_LESS, TMP1, 0, SLJIT_IMM, 0xd800); + OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0xfc00); + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0xd800); + OP_FLAGS(SLJIT_MOV, TMP1, 0, SLJIT_UNUSED, 0, SLJIT_C_EQUAL); + OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 1); + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP1, 0); + JUMPHERE(singlechar); + } +#endif /* COMPILE_PCRE[8|16] */ +#endif /* SUPPORT_UTF && !COMPILE_PCRE32 */ +JUMPHERE(start); + +if (newlinecheck) + { + JUMPHERE(end); + JUMPHERE(nl); + } + +return mainloop; +} + +#define MAX_N_CHARS 16 +#define MAX_N_BYTES 8 + +static SLJIT_INLINE void add_prefix_byte(pcre_uint8 byte, pcre_uint8 *bytes) +{ +pcre_uint8 len = bytes[0]; +int i; + +if (len == 255) + return; + +if (len == 0) + { + bytes[0] = 1; + bytes[1] = byte; + return; + } + +for (i = len; i > 0; i--) + if (bytes[i] == byte) + return; + +if (len >= MAX_N_BYTES - 1) + { + bytes[0] = 255; + return; + } + +len++; +bytes[len] = byte; +bytes[0] = len; +} + +static int scan_prefix(compiler_common *common, pcre_uchar *cc, pcre_uint32 *chars, pcre_uint8 *bytes, int max_chars) +{ +/* Recursive function, which scans prefix literals. */ +BOOL last, any, caseless; +int len, repeat, len_save, consumed = 0; +pcre_uint32 chr, mask; +pcre_uchar *alternative, *cc_save, *oc; +#if defined SUPPORT_UTF && defined COMPILE_PCRE8 +pcre_uchar othercase[8]; +#elif defined SUPPORT_UTF && defined COMPILE_PCRE16 +pcre_uchar othercase[2]; +#else +pcre_uchar othercase[1]; +#endif + +repeat = 1; +while (TRUE) + { + last = TRUE; + any = FALSE; + caseless = FALSE; + switch (*cc) + { + case OP_CHARI: + caseless = TRUE; + case OP_CHAR: + last = FALSE; + cc++; + break; + + case OP_SOD: + case OP_SOM: + case OP_SET_SOM: + case OP_NOT_WORD_BOUNDARY: + case OP_WORD_BOUNDARY: + case OP_EODN: + case OP_EOD: + case OP_CIRC: + case OP_CIRCM: + case OP_DOLL: + case OP_DOLLM: + /* Zero width assertions. */ + cc++; + continue; + + case OP_ASSERT: + case OP_ASSERT_NOT: + case OP_ASSERTBACK: + case OP_ASSERTBACK_NOT: + cc = bracketend(cc); + continue; + + case OP_PLUSI: + case OP_MINPLUSI: + case OP_POSPLUSI: + caseless = TRUE; + case OP_PLUS: + case OP_MINPLUS: + case OP_POSPLUS: + cc++; + break; + + case OP_EXACTI: + caseless = TRUE; + case OP_EXACT: + repeat = GET2(cc, 1); + last = FALSE; + cc += 1 + IMM2_SIZE; + break; + + case OP_QUERYI: + case OP_MINQUERYI: + case OP_POSQUERYI: + caseless = TRUE; + case OP_QUERY: + case OP_MINQUERY: + case OP_POSQUERY: + len = 1; + cc++; +#ifdef SUPPORT_UTF + if (common->utf && HAS_EXTRALEN(*cc)) len += GET_EXTRALEN(*cc); +#endif + max_chars = scan_prefix(common, cc + len, chars, bytes, max_chars); + if (max_chars == 0) + return consumed; + last = FALSE; + break; + + case OP_KET: + cc += 1 + LINK_SIZE; + continue; + + case OP_ALT: + cc += GET(cc, 1); + continue; + + case OP_ONCE: + case OP_ONCE_NC: + case OP_BRA: + case OP_BRAPOS: + case OP_CBRA: + case OP_CBRAPOS: + alternative = cc + GET(cc, 1); + while (*alternative == OP_ALT) + { + max_chars = scan_prefix(common, alternative + 1 + LINK_SIZE, chars, bytes, max_chars); + if (max_chars == 0) + return consumed; + alternative += GET(alternative, 1); + } + + if (*cc == OP_CBRA || *cc == OP_CBRAPOS) + cc += IMM2_SIZE; + cc += 1 + LINK_SIZE; + continue; + + case OP_CLASS: +#if defined SUPPORT_UTF && defined COMPILE_PCRE8 + if (common->utf && !is_char7_bitset((const pcre_uint8 *)(cc + 1), FALSE)) return consumed; +#endif + any = TRUE; + cc += 1 + 32 / sizeof(pcre_uchar); + break; + + case OP_NCLASS: +#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 + if (common->utf) return consumed; +#endif + any = TRUE; + cc += 1 + 32 / sizeof(pcre_uchar); + break; + +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + case OP_XCLASS: +#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 + if (common->utf) return consumed; +#endif + any = TRUE; + cc += GET(cc, 1); + break; +#endif + + case OP_DIGIT: +#if defined SUPPORT_UTF && defined COMPILE_PCRE8 + if (common->utf && !is_char7_bitset((const pcre_uint8 *)common->ctypes - cbit_length + cbit_digit, FALSE)) + return consumed; +#endif + any = TRUE; + cc++; + break; + + case OP_WHITESPACE: +#if defined SUPPORT_UTF && defined COMPILE_PCRE8 + if (common->utf && !is_char7_bitset((const pcre_uint8 *)common->ctypes - cbit_length + cbit_space, FALSE)) + return consumed; +#endif + any = TRUE; + cc++; + break; + + case OP_WORDCHAR: +#if defined SUPPORT_UTF && defined COMPILE_PCRE8 + if (common->utf && !is_char7_bitset((const pcre_uint8 *)common->ctypes - cbit_length + cbit_word, FALSE)) + return consumed; +#endif + any = TRUE; + cc++; + break; + + case OP_NOT: + case OP_NOTI: + cc++; + /* Fall through. */ + case OP_NOT_DIGIT: + case OP_NOT_WHITESPACE: + case OP_NOT_WORDCHAR: + case OP_ANY: + case OP_ALLANY: +#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 + if (common->utf) return consumed; +#endif + any = TRUE; + cc++; + break; + +#ifdef SUPPORT_UCP + case OP_NOTPROP: + case OP_PROP: +#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 + if (common->utf) return consumed; +#endif + any = TRUE; + cc += 1 + 2; + break; +#endif + + case OP_TYPEEXACT: + repeat = GET2(cc, 1); + cc += 1 + IMM2_SIZE; + continue; + + case OP_NOTEXACT: + case OP_NOTEXACTI: +#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 + if (common->utf) return consumed; +#endif + any = TRUE; + repeat = GET2(cc, 1); + cc += 1 + IMM2_SIZE + 1; + break; + + default: + return consumed; + } + + if (any) + { +#if defined COMPILE_PCRE8 + mask = 0xff; +#elif defined COMPILE_PCRE16 + mask = 0xffff; +#elif defined COMPILE_PCRE32 + mask = 0xffffffff; +#else + SLJIT_ASSERT_STOP(); +#endif + + do + { + chars[0] = mask; + chars[1] = mask; + bytes[0] = 255; + + consumed++; + if (--max_chars == 0) + return consumed; + chars += 2; + bytes += MAX_N_BYTES; + } + while (--repeat > 0); + + repeat = 1; + continue; + } + + len = 1; +#ifdef SUPPORT_UTF + if (common->utf && HAS_EXTRALEN(*cc)) len += GET_EXTRALEN(*cc); +#endif + + if (caseless && char_has_othercase(common, cc)) + { +#ifdef SUPPORT_UTF + if (common->utf) + { + GETCHAR(chr, cc); + if ((int)PRIV(ord2utf)(char_othercase(common, chr), othercase) != len) + return consumed; + } + else +#endif + { + chr = *cc; + othercase[0] = TABLE_GET(chr, common->fcc, chr); + } + } + else + caseless = FALSE; + + len_save = len; + cc_save = cc; + while (TRUE) + { + oc = othercase; + do + { + chr = *cc; +#ifdef COMPILE_PCRE32 + if (SLJIT_UNLIKELY(chr == NOTACHAR)) + return consumed; +#endif + add_prefix_byte((pcre_uint8)chr, bytes); + + mask = 0; + if (caseless) + { + add_prefix_byte((pcre_uint8)*oc, bytes); + mask = *cc ^ *oc; + chr |= mask; + } + +#ifdef COMPILE_PCRE32 + if (chars[0] == NOTACHAR && chars[1] == 0) +#else + if (chars[0] == NOTACHAR) +#endif + { + chars[0] = chr; + chars[1] = mask; + } + else + { + mask |= chars[0] ^ chr; + chr |= mask; + chars[0] = chr; + chars[1] |= mask; + } + + len--; + consumed++; + if (--max_chars == 0) + return consumed; + chars += 2; + bytes += MAX_N_BYTES; + cc++; + oc++; + } + while (len > 0); + + if (--repeat == 0) + break; + + len = len_save; + cc = cc_save; + } + + repeat = 1; + if (last) + return consumed; + } +} + +static SLJIT_INLINE BOOL fast_forward_first_n_chars(compiler_common *common, BOOL firstline) +{ +DEFINE_COMPILER; +struct sljit_label *start; +struct sljit_jump *quit; +pcre_uint32 chars[MAX_N_CHARS * 2]; +pcre_uint8 bytes[MAX_N_CHARS * MAX_N_BYTES]; +pcre_uint8 ones[MAX_N_CHARS]; +int offsets[3]; +pcre_uint32 mask; +pcre_uint8 *byte_set, *byte_set_end; +int i, max, from; +int range_right = -1, range_len = 3 - 1; +sljit_ub *update_table = NULL; +BOOL in_range; + +/* This is even TRUE, if both are NULL. */ +SLJIT_ASSERT(common->read_only_data_ptr == common->read_only_data); + +for (i = 0; i < MAX_N_CHARS; i++) + { + chars[i << 1] = NOTACHAR; + chars[(i << 1) + 1] = 0; + bytes[i * MAX_N_BYTES] = 0; + } + +max = scan_prefix(common, common->start, chars, bytes, MAX_N_CHARS); + +if (max <= 1) + return FALSE; + +for (i = 0; i < max; i++) + { + mask = chars[(i << 1) + 1]; + ones[i] = ones_in_half_byte[mask & 0xf]; + mask >>= 4; + while (mask != 0) + { + ones[i] += ones_in_half_byte[mask & 0xf]; + mask >>= 4; + } + } + +in_range = FALSE; +from = 0; /* Prevent compiler "uninitialized" warning */ +for (i = 0; i <= max; i++) + { + if (in_range && (i - from) > range_len && (bytes[(i - 1) * MAX_N_BYTES] <= 4)) + { + range_len = i - from; + range_right = i - 1; + } + + if (i < max && bytes[i * MAX_N_BYTES] < 255) + { + if (!in_range) + { + in_range = TRUE; + from = i; + } + } + else if (in_range) + in_range = FALSE; + } + +if (range_right >= 0) + { + /* Since no data is consumed (see the assert in the beginning + of this function), this space can be reallocated. */ + if (common->read_only_data) + SLJIT_FREE(common->read_only_data); + + common->read_only_data_size += 256; + common->read_only_data = (sljit_uw *)SLJIT_MALLOC(common->read_only_data_size); + if (common->read_only_data == NULL) + return TRUE; + + update_table = (sljit_ub *)common->read_only_data; + common->read_only_data_ptr = (sljit_uw *)(update_table + 256); + memset(update_table, IN_UCHARS(range_len), 256); + + for (i = 0; i < range_len; i++) + { + byte_set = bytes + ((range_right - i) * MAX_N_BYTES); + SLJIT_ASSERT(byte_set[0] > 0 && byte_set[0] < 255); + byte_set_end = byte_set + byte_set[0]; + byte_set++; + while (byte_set <= byte_set_end) + { + if (update_table[*byte_set] > IN_UCHARS(i)) + update_table[*byte_set] = IN_UCHARS(i); + byte_set++; + } + } + } + +offsets[0] = -1; +/* Scan forward. */ +for (i = 0; i < max; i++) + if (ones[i] <= 2) { + offsets[0] = i; + break; + } + +if (offsets[0] < 0 && range_right < 0) + return FALSE; + +if (offsets[0] >= 0) + { + /* Scan backward. */ + offsets[1] = -1; + for (i = max - 1; i > offsets[0]; i--) + if (ones[i] <= 2 && i != range_right) + { + offsets[1] = i; + break; + } + + /* This case is handled better by fast_forward_first_char. */ + if (offsets[1] == -1 && offsets[0] == 0 && range_right < 0) + return FALSE; + + offsets[2] = -1; + /* We only search for a middle character if there is no range check. */ + if (offsets[1] >= 0 && range_right == -1) + { + /* Scan from middle. */ + for (i = (offsets[0] + offsets[1]) / 2 + 1; i < offsets[1]; i++) + if (ones[i] <= 2) + { + offsets[2] = i; + break; + } + + if (offsets[2] == -1) + { + for (i = (offsets[0] + offsets[1]) / 2; i > offsets[0]; i--) + if (ones[i] <= 2) + { + offsets[2] = i; + break; + } + } + } + + SLJIT_ASSERT(offsets[1] == -1 || (offsets[0] < offsets[1])); + SLJIT_ASSERT(offsets[2] == -1 || (offsets[0] < offsets[2] && offsets[1] > offsets[2])); + + chars[0] = chars[offsets[0] << 1]; + chars[1] = chars[(offsets[0] << 1) + 1]; + if (offsets[2] >= 0) + { + chars[2] = chars[offsets[2] << 1]; + chars[3] = chars[(offsets[2] << 1) + 1]; + } + if (offsets[1] >= 0) + { + chars[4] = chars[offsets[1] << 1]; + chars[5] = chars[(offsets[1] << 1) + 1]; + } + } + +max -= 1; +if (firstline) + { + SLJIT_ASSERT(common->first_line_end != 0); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->first_line_end); + OP1(SLJIT_MOV, TMP3, 0, STR_END, 0); + OP2(SLJIT_SUB, STR_END, 0, STR_END, 0, SLJIT_IMM, IN_UCHARS(max)); + quit = CMP(SLJIT_C_LESS_EQUAL, STR_END, 0, TMP1, 0); + OP1(SLJIT_MOV, STR_END, 0, TMP1, 0); + JUMPHERE(quit); + } +else + OP2(SLJIT_SUB, STR_END, 0, STR_END, 0, SLJIT_IMM, IN_UCHARS(max)); + +#if !(defined SLJIT_CONFIG_X86_32 && SLJIT_CONFIG_X86_32) +if (range_right >= 0) + OP1(SLJIT_MOV, RETURN_ADDR, 0, SLJIT_IMM, (sljit_sw)update_table); +#endif + +start = LABEL(); +quit = CMP(SLJIT_C_GREATER_EQUAL, STR_PTR, 0, STR_END, 0); + +SLJIT_ASSERT(range_right >= 0 || offsets[0] >= 0); + +if (range_right >= 0) + { +#if defined COMPILE_PCRE8 || (defined SLJIT_LITTLE_ENDIAN && SLJIT_LITTLE_ENDIAN) + OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(range_right)); +#else + OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(range_right + 1) - 1); +#endif + +#if !(defined SLJIT_CONFIG_X86_32 && SLJIT_CONFIG_X86_32) + OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM2(RETURN_ADDR, TMP1), 0); +#else + OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP1), (sljit_sw)update_table); +#endif + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP1, 0); + CMPTO(SLJIT_C_NOT_EQUAL, TMP1, 0, SLJIT_IMM, 0, start); + } + +if (offsets[0] >= 0) + { + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(offsets[0])); + if (offsets[1] >= 0) + OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(offsets[1])); + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); + + if (chars[1] != 0) + OP2(SLJIT_OR, TMP1, 0, TMP1, 0, SLJIT_IMM, chars[1]); + CMPTO(SLJIT_C_NOT_EQUAL, TMP1, 0, SLJIT_IMM, chars[0], start); + if (offsets[2] >= 0) + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(offsets[2] - 1)); + + if (offsets[1] >= 0) + { + if (chars[5] != 0) + OP2(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_IMM, chars[5]); + CMPTO(SLJIT_C_NOT_EQUAL, TMP2, 0, SLJIT_IMM, chars[4], start); + } + + if (offsets[2] >= 0) + { + if (chars[3] != 0) + OP2(SLJIT_OR, TMP1, 0, TMP1, 0, SLJIT_IMM, chars[3]); + CMPTO(SLJIT_C_NOT_EQUAL, TMP1, 0, SLJIT_IMM, chars[2], start); + } + OP2(SLJIT_SUB, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); + } + +JUMPHERE(quit); + +if (firstline) + { + if (range_right >= 0) + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->first_line_end); + OP1(SLJIT_MOV, STR_END, 0, TMP3, 0); + if (range_right >= 0) + { + quit = CMP(SLJIT_C_LESS_EQUAL, STR_PTR, 0, TMP1, 0); + OP1(SLJIT_MOV, STR_PTR, 0, TMP1, 0); + JUMPHERE(quit); + } + } +else + OP2(SLJIT_ADD, STR_END, 0, STR_END, 0, SLJIT_IMM, IN_UCHARS(max)); +return TRUE; +} + +#undef MAX_N_CHARS +#undef MAX_N_BYTES + +static SLJIT_INLINE void fast_forward_first_char(compiler_common *common, pcre_uchar first_char, BOOL caseless, BOOL firstline) +{ +DEFINE_COMPILER; +struct sljit_label *start; +struct sljit_jump *quit; +struct sljit_jump *found; +pcre_uchar oc, bit; + +if (firstline) + { + SLJIT_ASSERT(common->first_line_end != 0); + OP1(SLJIT_MOV, TMP3, 0, STR_END, 0); + OP1(SLJIT_MOV, STR_END, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->first_line_end); + } + +start = LABEL(); +quit = CMP(SLJIT_C_GREATER_EQUAL, STR_PTR, 0, STR_END, 0); +OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), 0); + +oc = first_char; +if (caseless) + { + oc = TABLE_GET(first_char, common->fcc, first_char); +#if defined SUPPORT_UCP && !(defined COMPILE_PCRE8) + if (first_char > 127 && common->utf) + oc = UCD_OTHERCASE(first_char); +#endif + } +if (first_char == oc) + found = CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_IMM, first_char); +else + { + bit = first_char ^ oc; + if (is_powerof2(bit)) + { + OP2(SLJIT_OR, TMP2, 0, TMP1, 0, SLJIT_IMM, bit); + found = CMP(SLJIT_C_EQUAL, TMP2, 0, SLJIT_IMM, first_char | bit); + } + else + { + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, first_char); + OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_C_EQUAL); + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, oc); + OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_C_EQUAL); + found = JUMP(SLJIT_C_NOT_ZERO); + } + } + +OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); +JUMPTO(SLJIT_JUMP, start); +JUMPHERE(found); +JUMPHERE(quit); + +if (firstline) + OP1(SLJIT_MOV, STR_END, 0, TMP3, 0); +} + +static SLJIT_INLINE void fast_forward_newline(compiler_common *common, BOOL firstline) +{ +DEFINE_COMPILER; +struct sljit_label *loop; +struct sljit_jump *lastchar; +struct sljit_jump *firstchar; +struct sljit_jump *quit; +struct sljit_jump *foundcr = NULL; +struct sljit_jump *notfoundnl; +jump_list *newline = NULL; + +if (firstline) + { + SLJIT_ASSERT(common->first_line_end != 0); + OP1(SLJIT_MOV, TMP3, 0, STR_END, 0); + OP1(SLJIT_MOV, STR_END, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->first_line_end); + } + +if (common->nltype == NLTYPE_FIXED && common->newline > 255) + { + lastchar = CMP(SLJIT_C_GREATER_EQUAL, STR_PTR, 0, STR_END, 0); + OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, str)); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, begin)); + firstchar = CMP(SLJIT_C_LESS_EQUAL, STR_PTR, 0, TMP2, 0); + + OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, SLJIT_IMM, IN_UCHARS(2)); + OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, STR_PTR, 0, TMP1, 0); + OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_C_GREATER_EQUAL); +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + OP2(SLJIT_SHL, TMP2, 0, TMP2, 0, SLJIT_IMM, UCHAR_SHIFT); +#endif + OP2(SLJIT_SUB, STR_PTR, 0, STR_PTR, 0, TMP2, 0); + + loop = LABEL(); + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); + quit = CMP(SLJIT_C_GREATER_EQUAL, STR_PTR, 0, STR_END, 0); + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(-2)); + OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(-1)); + CMPTO(SLJIT_C_NOT_EQUAL, TMP1, 0, SLJIT_IMM, (common->newline >> 8) & 0xff, loop); + CMPTO(SLJIT_C_NOT_EQUAL, TMP2, 0, SLJIT_IMM, common->newline & 0xff, loop); + + JUMPHERE(quit); + JUMPHERE(firstchar); + JUMPHERE(lastchar); + + if (firstline) + OP1(SLJIT_MOV, STR_END, 0, TMP3, 0); + return; + } + +OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); +OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, str)); +firstchar = CMP(SLJIT_C_LESS_EQUAL, STR_PTR, 0, TMP2, 0); +skip_char_back(common); + +loop = LABEL(); +common->ff_newline_shortcut = loop; + +read_char_range(common, common->nlmin, common->nlmax, TRUE); +lastchar = CMP(SLJIT_C_GREATER_EQUAL, STR_PTR, 0, STR_END, 0); +if (common->nltype == NLTYPE_ANY || common->nltype == NLTYPE_ANYCRLF) + foundcr = CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_IMM, CHAR_CR); +check_newlinechar(common, common->nltype, &newline, FALSE); +set_jumps(newline, loop); + +if (common->nltype == NLTYPE_ANY || common->nltype == NLTYPE_ANYCRLF) + { + quit = JUMP(SLJIT_JUMP); + JUMPHERE(foundcr); + notfoundnl = CMP(SLJIT_C_GREATER_EQUAL, STR_PTR, 0, STR_END, 0); + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), 0); + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, CHAR_NL); + OP_FLAGS(SLJIT_MOV, TMP1, 0, SLJIT_UNUSED, 0, SLJIT_C_EQUAL); +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, UCHAR_SHIFT); +#endif + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP1, 0); + JUMPHERE(notfoundnl); + JUMPHERE(quit); + } +JUMPHERE(lastchar); +JUMPHERE(firstchar); + +if (firstline) + OP1(SLJIT_MOV, STR_END, 0, TMP3, 0); +} + +static BOOL check_class_ranges(compiler_common *common, const pcre_uint8 *bits, BOOL nclass, BOOL invert, jump_list **backtracks); + +static SLJIT_INLINE void fast_forward_start_bits(compiler_common *common, pcre_uint8 *start_bits, BOOL firstline) +{ +DEFINE_COMPILER; +struct sljit_label *start; +struct sljit_jump *quit; +struct sljit_jump *found = NULL; +jump_list *matches = NULL; +#ifndef COMPILE_PCRE8 +struct sljit_jump *jump; +#endif + +if (firstline) + { + SLJIT_ASSERT(common->first_line_end != 0); + OP1(SLJIT_MOV, RETURN_ADDR, 0, STR_END, 0); + OP1(SLJIT_MOV, STR_END, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->first_line_end); + } + +start = LABEL(); +quit = CMP(SLJIT_C_GREATER_EQUAL, STR_PTR, 0, STR_END, 0); +OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), 0); +#ifdef SUPPORT_UTF +if (common->utf) + OP1(SLJIT_MOV, TMP3, 0, TMP1, 0); +#endif + +if (!check_class_ranges(common, start_bits, (start_bits[31] & 0x80) != 0, TRUE, &matches)) + { +#ifndef COMPILE_PCRE8 + jump = CMP(SLJIT_C_LESS, TMP1, 0, SLJIT_IMM, 255); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_IMM, 255); + JUMPHERE(jump); +#endif + OP2(SLJIT_AND, TMP2, 0, TMP1, 0, SLJIT_IMM, 0x7); + OP2(SLJIT_LSHR, TMP1, 0, TMP1, 0, SLJIT_IMM, 3); + OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP1), (sljit_sw)start_bits); + OP2(SLJIT_SHL, TMP2, 0, SLJIT_IMM, 1, TMP2, 0); + OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, TMP2, 0); + found = JUMP(SLJIT_C_NOT_ZERO); + } + +#ifdef SUPPORT_UTF +if (common->utf) + OP1(SLJIT_MOV, TMP1, 0, TMP3, 0); +#endif +OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); +#ifdef SUPPORT_UTF +#if defined COMPILE_PCRE8 +if (common->utf) + { + CMPTO(SLJIT_C_LESS, TMP1, 0, SLJIT_IMM, 0xc0, start); + OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP1), (sljit_sw)PRIV(utf8_table4) - 0xc0); + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP1, 0); + } +#elif defined COMPILE_PCRE16 +if (common->utf) + { + CMPTO(SLJIT_C_LESS, TMP1, 0, SLJIT_IMM, 0xd800, start); + OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0xfc00); + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0xd800); + OP_FLAGS(SLJIT_MOV, TMP1, 0, SLJIT_UNUSED, 0, SLJIT_C_EQUAL); + OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 1); + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP1, 0); + } +#endif /* COMPILE_PCRE[8|16] */ +#endif /* SUPPORT_UTF */ +JUMPTO(SLJIT_JUMP, start); +if (found != NULL) + JUMPHERE(found); +if (matches != NULL) + set_jumps(matches, LABEL()); +JUMPHERE(quit); + +if (firstline) + OP1(SLJIT_MOV, STR_END, 0, RETURN_ADDR, 0); +} + +static SLJIT_INLINE struct sljit_jump *search_requested_char(compiler_common *common, pcre_uchar req_char, BOOL caseless, BOOL has_firstchar) +{ +DEFINE_COMPILER; +struct sljit_label *loop; +struct sljit_jump *toolong; +struct sljit_jump *alreadyfound; +struct sljit_jump *found; +struct sljit_jump *foundoc = NULL; +struct sljit_jump *notfound; +pcre_uint32 oc, bit; + +SLJIT_ASSERT(common->req_char_ptr != 0); +OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->req_char_ptr); +OP2(SLJIT_ADD, TMP1, 0, STR_PTR, 0, SLJIT_IMM, REQ_BYTE_MAX); +toolong = CMP(SLJIT_C_LESS, TMP1, 0, STR_END, 0); +alreadyfound = CMP(SLJIT_C_LESS, STR_PTR, 0, TMP2, 0); + +if (has_firstchar) + OP2(SLJIT_ADD, TMP1, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); +else + OP1(SLJIT_MOV, TMP1, 0, STR_PTR, 0); + +loop = LABEL(); +notfound = CMP(SLJIT_C_GREATER_EQUAL, TMP1, 0, STR_END, 0); + +OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(TMP1), 0); +oc = req_char; +if (caseless) + { + oc = TABLE_GET(req_char, common->fcc, req_char); +#if defined SUPPORT_UCP && !(defined COMPILE_PCRE8) + if (req_char > 127 && common->utf) + oc = UCD_OTHERCASE(req_char); +#endif + } +if (req_char == oc) + found = CMP(SLJIT_C_EQUAL, TMP2, 0, SLJIT_IMM, req_char); +else + { + bit = req_char ^ oc; + if (is_powerof2(bit)) + { + OP2(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_IMM, bit); + found = CMP(SLJIT_C_EQUAL, TMP2, 0, SLJIT_IMM, req_char | bit); + } + else + { + found = CMP(SLJIT_C_EQUAL, TMP2, 0, SLJIT_IMM, req_char); + foundoc = CMP(SLJIT_C_EQUAL, TMP2, 0, SLJIT_IMM, oc); + } + } +OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, SLJIT_IMM, IN_UCHARS(1)); +JUMPTO(SLJIT_JUMP, loop); + +JUMPHERE(found); +if (foundoc) + JUMPHERE(foundoc); +OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->req_char_ptr, TMP1, 0); +JUMPHERE(alreadyfound); +JUMPHERE(toolong); +return notfound; +} + +static void do_revertframes(compiler_common *common) +{ +DEFINE_COMPILER; +struct sljit_jump *jump; +struct sljit_label *mainloop; + +sljit_emit_fast_enter(compiler, RETURN_ADDR, 0); +OP1(SLJIT_MOV, TMP1, 0, STACK_TOP, 0); +GET_LOCAL_BASE(TMP3, 0, 0); + +/* Drop frames until we reach STACK_TOP. */ +mainloop = LABEL(); +OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(TMP1), 0); +OP2(SLJIT_SUB | SLJIT_SET_S, SLJIT_UNUSED, 0, TMP2, 0, SLJIT_IMM, 0); +jump = JUMP(SLJIT_C_SIG_LESS_EQUAL); + +OP2(SLJIT_ADD, TMP2, 0, TMP2, 0, TMP3, 0); +OP1(SLJIT_MOV, SLJIT_MEM1(TMP2), 0, SLJIT_MEM1(TMP1), sizeof(sljit_sw)); +OP1(SLJIT_MOV, SLJIT_MEM1(TMP2), sizeof(sljit_sw), SLJIT_MEM1(TMP1), 2 * sizeof(sljit_sw)); +OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, SLJIT_IMM, 3 * sizeof(sljit_sw)); +JUMPTO(SLJIT_JUMP, mainloop); + +JUMPHERE(jump); +jump = JUMP(SLJIT_C_SIG_LESS); +/* End of dropping frames. */ +sljit_emit_fast_return(compiler, RETURN_ADDR, 0); + +JUMPHERE(jump); +OP1(SLJIT_NEG, TMP2, 0, TMP2, 0); +OP2(SLJIT_ADD, TMP2, 0, TMP2, 0, TMP3, 0); +OP1(SLJIT_MOV, SLJIT_MEM1(TMP2), 0, SLJIT_MEM1(TMP1), sizeof(sljit_sw)); +OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, SLJIT_IMM, 2 * sizeof(sljit_sw)); +JUMPTO(SLJIT_JUMP, mainloop); +} + +static void check_wordboundary(compiler_common *common) +{ +DEFINE_COMPILER; +struct sljit_jump *skipread; +jump_list *skipread_list = NULL; +#if !(defined COMPILE_PCRE8) || defined SUPPORT_UTF +struct sljit_jump *jump; +#endif + +SLJIT_COMPILE_ASSERT(ctype_word == 0x10, ctype_word_must_be_16); + +sljit_emit_fast_enter(compiler, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS0); +/* Get type of the previous char, and put it to LOCALS1. */ +OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); +OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, begin)); +OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS1, SLJIT_IMM, 0); +skipread = CMP(SLJIT_C_LESS_EQUAL, STR_PTR, 0, TMP1, 0); +skip_char_back(common); +check_start_used_ptr(common); +read_char(common); + +/* Testing char type. */ +#ifdef SUPPORT_UCP +if (common->use_ucp) + { + OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, 1); + jump = CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_IMM, CHAR_UNDERSCORE); + add_jump(compiler, &common->getucd, JUMP(SLJIT_FAST_CALL)); + OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, ucp_Ll); + OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, ucp_Lu - ucp_Ll); + OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_C_LESS_EQUAL); + OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, ucp_Nd - ucp_Ll); + OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, ucp_No - ucp_Nd); + OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_C_LESS_EQUAL); + JUMPHERE(jump); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS1, TMP2, 0); + } +else +#endif + { +#ifndef COMPILE_PCRE8 + jump = CMP(SLJIT_C_GREATER, TMP1, 0, SLJIT_IMM, 255); +#elif defined SUPPORT_UTF + /* Here LOCALS1 has already been zeroed. */ + jump = NULL; + if (common->utf) + jump = CMP(SLJIT_C_GREATER, TMP1, 0, SLJIT_IMM, 255); +#endif /* COMPILE_PCRE8 */ + OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP1), common->ctypes); + OP2(SLJIT_LSHR, TMP1, 0, TMP1, 0, SLJIT_IMM, 4 /* ctype_word */); + OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 1); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS1, TMP1, 0); +#ifndef COMPILE_PCRE8 + JUMPHERE(jump); +#elif defined SUPPORT_UTF + if (jump != NULL) + JUMPHERE(jump); +#endif /* COMPILE_PCRE8 */ + } +JUMPHERE(skipread); + +OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, 0); +check_str_end(common, &skipread_list); +peek_char(common, READ_CHAR_MAX); + +/* Testing char type. This is a code duplication. */ +#ifdef SUPPORT_UCP +if (common->use_ucp) + { + OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, 1); + jump = CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_IMM, CHAR_UNDERSCORE); + add_jump(compiler, &common->getucd, JUMP(SLJIT_FAST_CALL)); + OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, ucp_Ll); + OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, ucp_Lu - ucp_Ll); + OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_C_LESS_EQUAL); + OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, ucp_Nd - ucp_Ll); + OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, ucp_No - ucp_Nd); + OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_C_LESS_EQUAL); + JUMPHERE(jump); + } +else +#endif + { +#ifndef COMPILE_PCRE8 + /* TMP2 may be destroyed by peek_char. */ + OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, 0); + jump = CMP(SLJIT_C_GREATER, TMP1, 0, SLJIT_IMM, 255); +#elif defined SUPPORT_UTF + OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, 0); + jump = NULL; + if (common->utf) + jump = CMP(SLJIT_C_GREATER, TMP1, 0, SLJIT_IMM, 255); +#endif + OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP1), common->ctypes); + OP2(SLJIT_LSHR, TMP2, 0, TMP2, 0, SLJIT_IMM, 4 /* ctype_word */); + OP2(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_IMM, 1); +#ifndef COMPILE_PCRE8 + JUMPHERE(jump); +#elif defined SUPPORT_UTF + if (jump != NULL) + JUMPHERE(jump); +#endif /* COMPILE_PCRE8 */ + } +set_jumps(skipread_list, LABEL()); + +OP2(SLJIT_XOR | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS1); +sljit_emit_fast_return(compiler, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS0); +} + +static BOOL check_class_ranges(compiler_common *common, const pcre_uint8 *bits, BOOL nclass, BOOL invert, jump_list **backtracks) +{ +DEFINE_COMPILER; +int ranges[MAX_RANGE_SIZE]; +pcre_uint8 bit, cbit, all; +int i, byte, length = 0; + +bit = bits[0] & 0x1; +/* All bits will be zero or one (since bit is zero or one). */ +all = -bit; + +for (i = 0; i < 256; ) + { + byte = i >> 3; + if ((i & 0x7) == 0 && bits[byte] == all) + i += 8; + else + { + cbit = (bits[byte] >> (i & 0x7)) & 0x1; + if (cbit != bit) + { + if (length >= MAX_RANGE_SIZE) + return FALSE; + ranges[length] = i; + length++; + bit = cbit; + all = -cbit; + } + i++; + } + } + +if (((bit == 0) && nclass) || ((bit == 1) && !nclass)) + { + if (length >= MAX_RANGE_SIZE) + return FALSE; + ranges[length] = 256; + length++; + } + +if (length < 0 || length > 4) + return FALSE; + +bit = bits[0] & 0x1; +if (invert) bit ^= 0x1; + +/* No character is accepted. */ +if (length == 0 && bit == 0) + add_jump(compiler, backtracks, JUMP(SLJIT_JUMP)); + +switch(length) + { + case 0: + /* When bit != 0, all characters are accepted. */ + return TRUE; + + case 1: + add_jump(compiler, backtracks, CMP(bit == 0 ? SLJIT_C_LESS : SLJIT_C_GREATER_EQUAL, TMP1, 0, SLJIT_IMM, ranges[0])); + return TRUE; + + case 2: + if (ranges[0] + 1 != ranges[1]) + { + OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, ranges[0]); + add_jump(compiler, backtracks, CMP(bit != 0 ? SLJIT_C_LESS : SLJIT_C_GREATER_EQUAL, TMP1, 0, SLJIT_IMM, ranges[1] - ranges[0])); + } + else + add_jump(compiler, backtracks, CMP(bit != 0 ? SLJIT_C_EQUAL : SLJIT_C_NOT_EQUAL, TMP1, 0, SLJIT_IMM, ranges[0])); + return TRUE; + + case 3: + if (bit != 0) + { + add_jump(compiler, backtracks, CMP(SLJIT_C_GREATER_EQUAL, TMP1, 0, SLJIT_IMM, ranges[2])); + if (ranges[0] + 1 != ranges[1]) + { + OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, ranges[0]); + add_jump(compiler, backtracks, CMP(SLJIT_C_LESS, TMP1, 0, SLJIT_IMM, ranges[1] - ranges[0])); + } + else + add_jump(compiler, backtracks, CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_IMM, ranges[0])); + return TRUE; + } + + add_jump(compiler, backtracks, CMP(SLJIT_C_LESS, TMP1, 0, SLJIT_IMM, ranges[0])); + if (ranges[1] + 1 != ranges[2]) + { + OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, ranges[1]); + add_jump(compiler, backtracks, CMP(SLJIT_C_LESS, TMP1, 0, SLJIT_IMM, ranges[2] - ranges[1])); + } + else + add_jump(compiler, backtracks, CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_IMM, ranges[1])); + return TRUE; + + case 4: + if ((ranges[1] - ranges[0]) == (ranges[3] - ranges[2]) + && (ranges[0] | (ranges[2] - ranges[0])) == ranges[2] + && is_powerof2(ranges[2] - ranges[0])) + { + OP2(SLJIT_OR, TMP1, 0, TMP1, 0, SLJIT_IMM, ranges[2] - ranges[0]); + if (ranges[2] + 1 != ranges[3]) + { + OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, ranges[2]); + add_jump(compiler, backtracks, CMP(bit != 0 ? SLJIT_C_LESS : SLJIT_C_GREATER_EQUAL, TMP1, 0, SLJIT_IMM, ranges[3] - ranges[2])); + } + else + add_jump(compiler, backtracks, CMP(bit != 0 ? SLJIT_C_EQUAL : SLJIT_C_NOT_EQUAL, TMP1, 0, SLJIT_IMM, ranges[2])); + return TRUE; + } + + if (bit != 0) + { + i = 0; + if (ranges[0] + 1 != ranges[1]) + { + OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, ranges[0]); + add_jump(compiler, backtracks, CMP(SLJIT_C_LESS, TMP1, 0, SLJIT_IMM, ranges[1] - ranges[0])); + i = ranges[0]; + } + else + add_jump(compiler, backtracks, CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_IMM, ranges[0])); + + if (ranges[2] + 1 != ranges[3]) + { + OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, ranges[2] - i); + add_jump(compiler, backtracks, CMP(SLJIT_C_LESS, TMP1, 0, SLJIT_IMM, ranges[3] - ranges[2])); + } + else + add_jump(compiler, backtracks, CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_IMM, ranges[2] - i)); + return TRUE; + } + + OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, ranges[0]); + add_jump(compiler, backtracks, CMP(SLJIT_C_GREATER_EQUAL, TMP1, 0, SLJIT_IMM, ranges[3] - ranges[0])); + if (ranges[1] + 1 != ranges[2]) + { + OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, ranges[1] - ranges[0]); + add_jump(compiler, backtracks, CMP(SLJIT_C_LESS, TMP1, 0, SLJIT_IMM, ranges[2] - ranges[1])); + } + else + add_jump(compiler, backtracks, CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_IMM, ranges[1] - ranges[0])); + return TRUE; + + default: + SLJIT_ASSERT_STOP(); + return FALSE; + } +} + +static void check_anynewline(compiler_common *common) +{ +/* Check whether TMP1 contains a newline character. TMP2 destroyed. */ +DEFINE_COMPILER; + +sljit_emit_fast_enter(compiler, RETURN_ADDR, 0); + +OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x0a); +OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x0d - 0x0a); +OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_C_LESS_EQUAL); +OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x85 - 0x0a); +#if defined SUPPORT_UTF || defined COMPILE_PCRE16 || defined COMPILE_PCRE32 +#ifdef COMPILE_PCRE8 +if (common->utf) + { +#endif + OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_C_EQUAL); + OP2(SLJIT_OR, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x1); + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x2029 - 0x0a); +#ifdef COMPILE_PCRE8 + } +#endif +#endif /* SUPPORT_UTF || COMPILE_PCRE16 || COMPILE_PCRE32 */ +OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_C_EQUAL); +sljit_emit_fast_return(compiler, RETURN_ADDR, 0); +} + +static void check_hspace(compiler_common *common) +{ +/* Check whether TMP1 contains a newline character. TMP2 destroyed. */ +DEFINE_COMPILER; + +sljit_emit_fast_enter(compiler, RETURN_ADDR, 0); + +OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x09); +OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_C_EQUAL); +OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x20); +OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_C_EQUAL); +OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0xa0); +#if defined SUPPORT_UTF || defined COMPILE_PCRE16 || defined COMPILE_PCRE32 +#ifdef COMPILE_PCRE8 +if (common->utf) + { +#endif + OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_C_EQUAL); + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x1680); + OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_C_EQUAL); + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x180e); + OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_C_EQUAL); + OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x2000); + OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x200A - 0x2000); + OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_C_LESS_EQUAL); + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x202f - 0x2000); + OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_C_EQUAL); + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x205f - 0x2000); + OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_C_EQUAL); + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x3000 - 0x2000); +#ifdef COMPILE_PCRE8 + } +#endif +#endif /* SUPPORT_UTF || COMPILE_PCRE16 || COMPILE_PCRE32 */ +OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_C_EQUAL); + +sljit_emit_fast_return(compiler, RETURN_ADDR, 0); +} + +static void check_vspace(compiler_common *common) +{ +/* Check whether TMP1 contains a newline character. TMP2 destroyed. */ +DEFINE_COMPILER; + +sljit_emit_fast_enter(compiler, RETURN_ADDR, 0); + +OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x0a); +OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x0d - 0x0a); +OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_C_LESS_EQUAL); +OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x85 - 0x0a); +#if defined SUPPORT_UTF || defined COMPILE_PCRE16 || defined COMPILE_PCRE32 +#ifdef COMPILE_PCRE8 +if (common->utf) + { +#endif + OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_C_EQUAL); + OP2(SLJIT_OR, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x1); + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x2029 - 0x0a); +#ifdef COMPILE_PCRE8 + } +#endif +#endif /* SUPPORT_UTF || COMPILE_PCRE16 || COMPILE_PCRE32 */ +OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_C_EQUAL); + +sljit_emit_fast_return(compiler, RETURN_ADDR, 0); +} + +#define CHAR1 STR_END +#define CHAR2 STACK_TOP + +static void do_casefulcmp(compiler_common *common) +{ +DEFINE_COMPILER; +struct sljit_jump *jump; +struct sljit_label *label; + +sljit_emit_fast_enter(compiler, RETURN_ADDR, 0); +OP2(SLJIT_SUB, STR_PTR, 0, STR_PTR, 0, TMP2, 0); +OP1(SLJIT_MOV, TMP3, 0, CHAR1, 0); +OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS0, CHAR2, 0); +OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, IN_UCHARS(1)); +OP2(SLJIT_SUB, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); + +label = LABEL(); +OP1(MOVU_UCHAR, CHAR1, 0, SLJIT_MEM1(TMP1), IN_UCHARS(1)); +OP1(MOVU_UCHAR, CHAR2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(1)); +jump = CMP(SLJIT_C_NOT_EQUAL, CHAR1, 0, CHAR2, 0); +OP2(SLJIT_SUB | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_IMM, IN_UCHARS(1)); +JUMPTO(SLJIT_C_NOT_ZERO, label); + +JUMPHERE(jump); +OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); +OP1(SLJIT_MOV, CHAR1, 0, TMP3, 0); +OP1(SLJIT_MOV, CHAR2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS0); +sljit_emit_fast_return(compiler, RETURN_ADDR, 0); +} + +#define LCC_TABLE STACK_LIMIT + +static void do_caselesscmp(compiler_common *common) +{ +DEFINE_COMPILER; +struct sljit_jump *jump; +struct sljit_label *label; + +sljit_emit_fast_enter(compiler, RETURN_ADDR, 0); +OP2(SLJIT_SUB, STR_PTR, 0, STR_PTR, 0, TMP2, 0); + +OP1(SLJIT_MOV, TMP3, 0, LCC_TABLE, 0); +OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS0, CHAR1, 0); +OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS1, CHAR2, 0); +OP1(SLJIT_MOV, LCC_TABLE, 0, SLJIT_IMM, common->lcc); +OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, IN_UCHARS(1)); +OP2(SLJIT_SUB, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); + +label = LABEL(); +OP1(MOVU_UCHAR, CHAR1, 0, SLJIT_MEM1(TMP1), IN_UCHARS(1)); +OP1(MOVU_UCHAR, CHAR2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(1)); +#ifndef COMPILE_PCRE8 +jump = CMP(SLJIT_C_GREATER, CHAR1, 0, SLJIT_IMM, 255); +#endif +OP1(SLJIT_MOV_UB, CHAR1, 0, SLJIT_MEM2(LCC_TABLE, CHAR1), 0); +#ifndef COMPILE_PCRE8 +JUMPHERE(jump); +jump = CMP(SLJIT_C_GREATER, CHAR2, 0, SLJIT_IMM, 255); +#endif +OP1(SLJIT_MOV_UB, CHAR2, 0, SLJIT_MEM2(LCC_TABLE, CHAR2), 0); +#ifndef COMPILE_PCRE8 +JUMPHERE(jump); +#endif +jump = CMP(SLJIT_C_NOT_EQUAL, CHAR1, 0, CHAR2, 0); +OP2(SLJIT_SUB | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_IMM, IN_UCHARS(1)); +JUMPTO(SLJIT_C_NOT_ZERO, label); + +JUMPHERE(jump); +OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); +OP1(SLJIT_MOV, LCC_TABLE, 0, TMP3, 0); +OP1(SLJIT_MOV, CHAR1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS0); +OP1(SLJIT_MOV, CHAR2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS1); +sljit_emit_fast_return(compiler, RETURN_ADDR, 0); +} + +#undef LCC_TABLE +#undef CHAR1 +#undef CHAR2 + +#if defined SUPPORT_UTF && defined SUPPORT_UCP + +static const pcre_uchar * SLJIT_CALL do_utf_caselesscmp(pcre_uchar *src1, jit_arguments *args, pcre_uchar *end1) +{ +/* This function would be ineffective to do in JIT level. */ +pcre_uint32 c1, c2; +const pcre_uchar *src2 = args->uchar_ptr; +const pcre_uchar *end2 = args->end; +const ucd_record *ur; +const pcre_uint32 *pp; + +while (src1 < end1) + { + if (src2 >= end2) + return (pcre_uchar*)1; + GETCHARINC(c1, src1); + GETCHARINC(c2, src2); + ur = GET_UCD(c2); + if (c1 != c2 && c1 != c2 + ur->other_case) + { + pp = PRIV(ucd_caseless_sets) + ur->caseset; + for (;;) + { + if (c1 < *pp) return NULL; + if (c1 == *pp++) break; + } + } + } +return src2; +} + +#endif /* SUPPORT_UTF && SUPPORT_UCP */ + +static pcre_uchar *byte_sequence_compare(compiler_common *common, BOOL caseless, pcre_uchar *cc, + compare_context* context, jump_list **backtracks) +{ +DEFINE_COMPILER; +unsigned int othercasebit = 0; +pcre_uchar *othercasechar = NULL; +#ifdef SUPPORT_UTF +int utflength; +#endif + +if (caseless && char_has_othercase(common, cc)) + { + othercasebit = char_get_othercase_bit(common, cc); + SLJIT_ASSERT(othercasebit); + /* Extracting bit difference info. */ +#if defined COMPILE_PCRE8 + othercasechar = cc + (othercasebit >> 8); + othercasebit &= 0xff; +#elif defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + /* Note that this code only handles characters in the BMP. If there + ever are characters outside the BMP whose othercase differs in only one + bit from itself (there currently are none), this code will need to be + revised for COMPILE_PCRE32. */ + othercasechar = cc + (othercasebit >> 9); + if ((othercasebit & 0x100) != 0) + othercasebit = (othercasebit & 0xff) << 8; + else + othercasebit &= 0xff; +#endif /* COMPILE_PCRE[8|16|32] */ + } + +if (context->sourcereg == -1) + { +#if defined COMPILE_PCRE8 +#if defined SLJIT_UNALIGNED && SLJIT_UNALIGNED + if (context->length >= 4) + OP1(SLJIT_MOV_SI, TMP1, 0, SLJIT_MEM1(STR_PTR), -context->length); + else if (context->length >= 2) + OP1(SLJIT_MOV_UH, TMP1, 0, SLJIT_MEM1(STR_PTR), -context->length); + else +#endif + OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(STR_PTR), -context->length); +#elif defined COMPILE_PCRE16 +#if defined SLJIT_UNALIGNED && SLJIT_UNALIGNED + if (context->length >= 4) + OP1(SLJIT_MOV_SI, TMP1, 0, SLJIT_MEM1(STR_PTR), -context->length); + else +#endif + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), -context->length); +#elif defined COMPILE_PCRE32 + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), -context->length); +#endif /* COMPILE_PCRE[8|16|32] */ + context->sourcereg = TMP2; + } + +#ifdef SUPPORT_UTF +utflength = 1; +if (common->utf && HAS_EXTRALEN(*cc)) + utflength += GET_EXTRALEN(*cc); + +do + { +#endif + + context->length -= IN_UCHARS(1); +#if (defined SLJIT_UNALIGNED && SLJIT_UNALIGNED) && (defined COMPILE_PCRE8 || defined COMPILE_PCRE16) + + /* Unaligned read is supported. */ + if (othercasebit != 0 && othercasechar == cc) + { + context->c.asuchars[context->ucharptr] = *cc | othercasebit; + context->oc.asuchars[context->ucharptr] = othercasebit; + } + else + { + context->c.asuchars[context->ucharptr] = *cc; + context->oc.asuchars[context->ucharptr] = 0; + } + context->ucharptr++; + +#if defined COMPILE_PCRE8 + if (context->ucharptr >= 4 || context->length == 0 || (context->ucharptr == 2 && context->length == 1)) +#else + if (context->ucharptr >= 2 || context->length == 0) +#endif + { + if (context->length >= 4) + OP1(SLJIT_MOV_SI, context->sourcereg, 0, SLJIT_MEM1(STR_PTR), -context->length); + else if (context->length >= 2) + OP1(SLJIT_MOV_UH, context->sourcereg, 0, SLJIT_MEM1(STR_PTR), -context->length); +#if defined COMPILE_PCRE8 + else if (context->length >= 1) + OP1(SLJIT_MOV_UB, context->sourcereg, 0, SLJIT_MEM1(STR_PTR), -context->length); +#endif /* COMPILE_PCRE8 */ + context->sourcereg = context->sourcereg == TMP1 ? TMP2 : TMP1; + + switch(context->ucharptr) + { + case 4 / sizeof(pcre_uchar): + if (context->oc.asint != 0) + OP2(SLJIT_OR, context->sourcereg, 0, context->sourcereg, 0, SLJIT_IMM, context->oc.asint); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, context->sourcereg, 0, SLJIT_IMM, context->c.asint | context->oc.asint)); + break; + + case 2 / sizeof(pcre_uchar): + if (context->oc.asushort != 0) + OP2(SLJIT_OR, context->sourcereg, 0, context->sourcereg, 0, SLJIT_IMM, context->oc.asushort); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, context->sourcereg, 0, SLJIT_IMM, context->c.asushort | context->oc.asushort)); + break; + +#ifdef COMPILE_PCRE8 + case 1: + if (context->oc.asbyte != 0) + OP2(SLJIT_OR, context->sourcereg, 0, context->sourcereg, 0, SLJIT_IMM, context->oc.asbyte); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, context->sourcereg, 0, SLJIT_IMM, context->c.asbyte | context->oc.asbyte)); + break; +#endif + + default: + SLJIT_ASSERT_STOP(); + break; + } + context->ucharptr = 0; + } + +#else + + /* Unaligned read is unsupported or in 32 bit mode. */ + if (context->length >= 1) + OP1(MOV_UCHAR, context->sourcereg, 0, SLJIT_MEM1(STR_PTR), -context->length); + + context->sourcereg = context->sourcereg == TMP1 ? TMP2 : TMP1; + + if (othercasebit != 0 && othercasechar == cc) + { + OP2(SLJIT_OR, context->sourcereg, 0, context->sourcereg, 0, SLJIT_IMM, othercasebit); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, context->sourcereg, 0, SLJIT_IMM, *cc | othercasebit)); + } + else + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, context->sourcereg, 0, SLJIT_IMM, *cc)); + +#endif + + cc++; +#ifdef SUPPORT_UTF + utflength--; + } +while (utflength > 0); +#endif + +return cc; +} + +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + +#define SET_TYPE_OFFSET(value) \ + if ((value) != typeoffset) \ + { \ + if ((value) < typeoffset) \ + OP2(SLJIT_ADD, typereg, 0, typereg, 0, SLJIT_IMM, typeoffset - (value)); \ + else \ + OP2(SLJIT_SUB, typereg, 0, typereg, 0, SLJIT_IMM, (value) - typeoffset); \ + } \ + typeoffset = (value); + +#define SET_CHAR_OFFSET(value) \ + if ((value) != charoffset) \ + { \ + if ((value) < charoffset) \ + OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(charoffset - (value))); \ + else \ + OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)((value) - charoffset)); \ + } \ + charoffset = (value); + +static void compile_xclass_matchingpath(compiler_common *common, pcre_uchar *cc, jump_list **backtracks) +{ +DEFINE_COMPILER; +jump_list *found = NULL; +jump_list **list = (cc[0] & XCL_NOT) == 0 ? &found : backtracks; +sljit_uw c, charoffset, max = 256, min = READ_CHAR_MAX; +struct sljit_jump *jump = NULL; +pcre_uchar *ccbegin; +int compares, invertcmp, numberofcmps; +#if defined SUPPORT_UTF && (defined COMPILE_PCRE8 || defined COMPILE_PCRE16) +BOOL utf = common->utf; +#endif + +#ifdef SUPPORT_UCP +BOOL needstype = FALSE, needsscript = FALSE, needschar = FALSE; +BOOL charsaved = FALSE; +int typereg = TMP1, scriptreg = TMP1; +const pcre_uint32 *other_cases; +sljit_uw typeoffset; +#endif + +/* Scanning the necessary info. */ +cc++; +ccbegin = cc; +compares = 0; +if (cc[-1] & XCL_MAP) + { + min = 0; + cc += 32 / sizeof(pcre_uchar); + } + +while (*cc != XCL_END) + { + compares++; + if (*cc == XCL_SINGLE) + { + cc ++; + GETCHARINCTEST(c, cc); + if (c > max) max = c; + if (c < min) min = c; +#ifdef SUPPORT_UCP + needschar = TRUE; +#endif + } + else if (*cc == XCL_RANGE) + { + cc ++; + GETCHARINCTEST(c, cc); + if (c < min) min = c; + GETCHARINCTEST(c, cc); + if (c > max) max = c; +#ifdef SUPPORT_UCP + needschar = TRUE; +#endif + } +#ifdef SUPPORT_UCP + else + { + SLJIT_ASSERT(*cc == XCL_PROP || *cc == XCL_NOTPROP); + cc++; + if (*cc == PT_CLIST) + { + other_cases = PRIV(ucd_caseless_sets) + cc[1]; + while (*other_cases != NOTACHAR) + { + if (*other_cases > max) max = *other_cases; + if (*other_cases < min) min = *other_cases; + other_cases++; + } + } + else + { + max = READ_CHAR_MAX; + min = 0; + } + + switch(*cc) + { + case PT_ANY: + break; + + case PT_LAMP: + case PT_GC: + case PT_PC: + case PT_ALNUM: + needstype = TRUE; + break; + + case PT_SC: + needsscript = TRUE; + break; + + case PT_SPACE: + case PT_PXSPACE: + case PT_WORD: + case PT_PXGRAPH: + case PT_PXPRINT: + case PT_PXPUNCT: + needstype = TRUE; + needschar = TRUE; + break; + + case PT_CLIST: + case PT_UCNC: + needschar = TRUE; + break; + + default: + SLJIT_ASSERT_STOP(); + break; + } + cc += 2; + } +#endif + } + +/* We are not necessary in utf mode even in 8 bit mode. */ +cc = ccbegin; +detect_partial_match(common, backtracks); +read_char_range(common, min, max, (cc[-1] & XCL_NOT) != 0); + +if ((cc[-1] & XCL_HASPROP) == 0) + { + if ((cc[-1] & XCL_MAP) != 0) + { + jump = CMP(SLJIT_C_GREATER, TMP1, 0, SLJIT_IMM, 255); + if (!check_class_ranges(common, (const pcre_uint8 *)cc, (((const pcre_uint8 *)cc)[31] & 0x80) != 0, TRUE, &found)) + { + OP2(SLJIT_AND, TMP2, 0, TMP1, 0, SLJIT_IMM, 0x7); + OP2(SLJIT_LSHR, TMP1, 0, TMP1, 0, SLJIT_IMM, 3); + OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP1), (sljit_sw)cc); + OP2(SLJIT_SHL, TMP2, 0, SLJIT_IMM, 1, TMP2, 0); + OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, TMP2, 0); + add_jump(compiler, &found, JUMP(SLJIT_C_NOT_ZERO)); + } + + add_jump(compiler, backtracks, JUMP(SLJIT_JUMP)); + JUMPHERE(jump); + + cc += 32 / sizeof(pcre_uchar); + } + else + { + OP2(SLJIT_SUB, TMP2, 0, TMP1, 0, SLJIT_IMM, min); + add_jump(compiler, (cc[-1] & XCL_NOT) == 0 ? backtracks : &found, CMP(SLJIT_C_GREATER, TMP2, 0, SLJIT_IMM, max - min)); + } + } +else if ((cc[-1] & XCL_MAP) != 0) + { + OP1(SLJIT_MOV, TMP3, 0, TMP1, 0); +#ifdef SUPPORT_UCP + charsaved = TRUE; +#endif + if (!check_class_ranges(common, (const pcre_uint8 *)cc, FALSE, TRUE, list)) + { +#ifdef COMPILE_PCRE8 + SLJIT_ASSERT(common->utf); +#endif + jump = CMP(SLJIT_C_GREATER, TMP1, 0, SLJIT_IMM, 255); + + OP2(SLJIT_AND, TMP2, 0, TMP1, 0, SLJIT_IMM, 0x7); + OP2(SLJIT_LSHR, TMP1, 0, TMP1, 0, SLJIT_IMM, 3); + OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP1), (sljit_sw)cc); + OP2(SLJIT_SHL, TMP2, 0, SLJIT_IMM, 1, TMP2, 0); + OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, TMP2, 0); + add_jump(compiler, list, JUMP(SLJIT_C_NOT_ZERO)); + + JUMPHERE(jump); + } + + OP1(SLJIT_MOV, TMP1, 0, TMP3, 0); + cc += 32 / sizeof(pcre_uchar); + } + +#ifdef SUPPORT_UCP +/* Simple register allocation. TMP1 is preferred if possible. */ +if (needstype || needsscript) + { + if (needschar && !charsaved) + OP1(SLJIT_MOV, TMP3, 0, TMP1, 0); + add_jump(compiler, &common->getucd, JUMP(SLJIT_FAST_CALL)); + if (needschar) + { + if (needstype) + { + OP1(SLJIT_MOV, RETURN_ADDR, 0, TMP1, 0); + typereg = RETURN_ADDR; + } + + if (needsscript) + scriptreg = TMP3; + OP1(SLJIT_MOV, TMP1, 0, TMP3, 0); + } + else if (needstype && needsscript) + scriptreg = TMP3; + /* In all other cases only one of them was specified, and that can goes to TMP1. */ + + if (needsscript) + { + if (scriptreg == TMP1) + { + OP1(SLJIT_MOV, scriptreg, 0, SLJIT_IMM, (sljit_sw)PRIV(ucd_records) + SLJIT_OFFSETOF(ucd_record, script)); + OP1(SLJIT_MOV_UB, scriptreg, 0, SLJIT_MEM2(scriptreg, TMP2), 3); + } + else + { + OP2(SLJIT_SHL, TMP2, 0, TMP2, 0, SLJIT_IMM, 3); + OP2(SLJIT_ADD, TMP2, 0, TMP2, 0, SLJIT_IMM, (sljit_sw)PRIV(ucd_records) + SLJIT_OFFSETOF(ucd_record, script)); + OP1(SLJIT_MOV_UB, scriptreg, 0, SLJIT_MEM1(TMP2), 0); + } + } + } +#endif + +/* Generating code. */ +charoffset = 0; +numberofcmps = 0; +#ifdef SUPPORT_UCP +typeoffset = 0; +#endif + +while (*cc != XCL_END) + { + compares--; + invertcmp = (compares == 0 && list != backtracks); + jump = NULL; + + if (*cc == XCL_SINGLE) + { + cc ++; + GETCHARINCTEST(c, cc); + + if (numberofcmps < 3 && (*cc == XCL_SINGLE || *cc == XCL_RANGE)) + { + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(c - charoffset)); + OP_FLAGS(numberofcmps == 0 ? SLJIT_MOV : SLJIT_OR, TMP2, 0, numberofcmps == 0 ? SLJIT_UNUSED : TMP2, 0, SLJIT_C_EQUAL); + numberofcmps++; + } + else if (numberofcmps > 0) + { + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(c - charoffset)); + OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_C_EQUAL); + jump = JUMP(SLJIT_C_NOT_ZERO ^ invertcmp); + numberofcmps = 0; + } + else + { + jump = CMP(SLJIT_C_EQUAL ^ invertcmp, TMP1, 0, SLJIT_IMM, (sljit_sw)(c - charoffset)); + numberofcmps = 0; + } + } + else if (*cc == XCL_RANGE) + { + cc ++; + GETCHARINCTEST(c, cc); + SET_CHAR_OFFSET(c); + GETCHARINCTEST(c, cc); + + if (numberofcmps < 3 && (*cc == XCL_SINGLE || *cc == XCL_RANGE)) + { + OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(c - charoffset)); + OP_FLAGS(numberofcmps == 0 ? SLJIT_MOV : SLJIT_OR, TMP2, 0, numberofcmps == 0 ? SLJIT_UNUSED : TMP2, 0, SLJIT_C_LESS_EQUAL); + numberofcmps++; + } + else if (numberofcmps > 0) + { + OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(c - charoffset)); + OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_C_LESS_EQUAL); + jump = JUMP(SLJIT_C_NOT_ZERO ^ invertcmp); + numberofcmps = 0; + } + else + { + jump = CMP(SLJIT_C_LESS_EQUAL ^ invertcmp, TMP1, 0, SLJIT_IMM, (sljit_sw)(c - charoffset)); + numberofcmps = 0; + } + } +#ifdef SUPPORT_UCP + else + { + if (*cc == XCL_NOTPROP) + invertcmp ^= 0x1; + cc++; + switch(*cc) + { + case PT_ANY: + if (list != backtracks) + { + if ((cc[-1] == XCL_NOTPROP && compares > 0) || (cc[-1] == XCL_PROP && compares == 0)) + continue; + } + else if (cc[-1] == XCL_NOTPROP) + continue; + jump = JUMP(SLJIT_JUMP); + break; + + case PT_LAMP: + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, typereg, 0, SLJIT_IMM, ucp_Lu - typeoffset); + OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_C_EQUAL); + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, typereg, 0, SLJIT_IMM, ucp_Ll - typeoffset); + OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_C_EQUAL); + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, typereg, 0, SLJIT_IMM, ucp_Lt - typeoffset); + OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_C_EQUAL); + jump = JUMP(SLJIT_C_NOT_ZERO ^ invertcmp); + break; + + case PT_GC: + c = PRIV(ucp_typerange)[(int)cc[1] * 2]; + SET_TYPE_OFFSET(c); + jump = CMP(SLJIT_C_LESS_EQUAL ^ invertcmp, typereg, 0, SLJIT_IMM, PRIV(ucp_typerange)[(int)cc[1] * 2 + 1] - c); + break; + + case PT_PC: + jump = CMP(SLJIT_C_EQUAL ^ invertcmp, typereg, 0, SLJIT_IMM, (int)cc[1] - typeoffset); + break; + + case PT_SC: + jump = CMP(SLJIT_C_EQUAL ^ invertcmp, scriptreg, 0, SLJIT_IMM, (int)cc[1]); + break; + + case PT_SPACE: + case PT_PXSPACE: + SET_CHAR_OFFSET(9); + OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0xd - 0x9); + OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_C_LESS_EQUAL); + + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x85 - 0x9); + OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_C_EQUAL); + + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x180e - 0x9); + OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_C_EQUAL); + + SET_TYPE_OFFSET(ucp_Zl); + OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, typereg, 0, SLJIT_IMM, ucp_Zs - ucp_Zl); + OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_C_LESS_EQUAL); + jump = JUMP(SLJIT_C_NOT_ZERO ^ invertcmp); + break; + + case PT_WORD: + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(CHAR_UNDERSCORE - charoffset)); + OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_C_EQUAL); + /* Fall through. */ + + case PT_ALNUM: + SET_TYPE_OFFSET(ucp_Ll); + OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, typereg, 0, SLJIT_IMM, ucp_Lu - ucp_Ll); + OP_FLAGS((*cc == PT_ALNUM) ? SLJIT_MOV : SLJIT_OR, TMP2, 0, (*cc == PT_ALNUM) ? SLJIT_UNUSED : TMP2, 0, SLJIT_C_LESS_EQUAL); + SET_TYPE_OFFSET(ucp_Nd); + OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, typereg, 0, SLJIT_IMM, ucp_No - ucp_Nd); + OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_C_LESS_EQUAL); + jump = JUMP(SLJIT_C_NOT_ZERO ^ invertcmp); + break; + + case PT_CLIST: + other_cases = PRIV(ucd_caseless_sets) + cc[1]; + + /* At least three characters are required. + Otherwise this case would be handled by the normal code path. */ + SLJIT_ASSERT(other_cases[0] != NOTACHAR && other_cases[1] != NOTACHAR && other_cases[2] != NOTACHAR); + SLJIT_ASSERT(other_cases[0] < other_cases[1] && other_cases[1] < other_cases[2]); + + /* Optimizing character pairs, if their difference is power of 2. */ + if (is_powerof2(other_cases[1] ^ other_cases[0])) + { + if (charoffset == 0) + OP2(SLJIT_OR, TMP2, 0, TMP1, 0, SLJIT_IMM, other_cases[1] ^ other_cases[0]); + else + { + OP2(SLJIT_ADD, TMP2, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)charoffset); + OP2(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_IMM, other_cases[1] ^ other_cases[0]); + } + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP2, 0, SLJIT_IMM, other_cases[1]); + OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_C_EQUAL); + other_cases += 2; + } + else if (is_powerof2(other_cases[2] ^ other_cases[1])) + { + if (charoffset == 0) + OP2(SLJIT_OR, TMP2, 0, TMP1, 0, SLJIT_IMM, other_cases[2] ^ other_cases[1]); + else + { + OP2(SLJIT_ADD, TMP2, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)charoffset); + OP2(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_IMM, other_cases[1] ^ other_cases[0]); + } + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP2, 0, SLJIT_IMM, other_cases[2]); + OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_C_EQUAL); + + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(other_cases[0] - charoffset)); + OP_FLAGS(SLJIT_OR | ((other_cases[3] == NOTACHAR) ? SLJIT_SET_E : 0), TMP2, 0, TMP2, 0, SLJIT_C_EQUAL); + + other_cases += 3; + } + else + { + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(*other_cases++ - charoffset)); + OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_C_EQUAL); + } + + while (*other_cases != NOTACHAR) + { + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(*other_cases++ - charoffset)); + OP_FLAGS(SLJIT_OR | ((*other_cases == NOTACHAR) ? SLJIT_SET_E : 0), TMP2, 0, TMP2, 0, SLJIT_C_EQUAL); + } + jump = JUMP(SLJIT_C_NOT_ZERO ^ invertcmp); + break; + + case PT_UCNC: + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(CHAR_DOLLAR_SIGN - charoffset)); + OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_C_EQUAL); + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(CHAR_COMMERCIAL_AT - charoffset)); + OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_C_EQUAL); + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(CHAR_GRAVE_ACCENT - charoffset)); + OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_C_EQUAL); + + SET_CHAR_OFFSET(0xa0); + OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(0xd7ff - charoffset)); + OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_C_LESS_EQUAL); + SET_CHAR_OFFSET(0); + OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0xe000 - 0); + OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_C_GREATER_EQUAL); + jump = JUMP(SLJIT_C_NOT_ZERO ^ invertcmp); + break; + + case PT_PXGRAPH: + /* C and Z groups are the farthest two groups. */ + SET_TYPE_OFFSET(ucp_Ll); + OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, typereg, 0, SLJIT_IMM, ucp_So - ucp_Ll); + OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_C_GREATER); + + jump = CMP(SLJIT_C_NOT_EQUAL, typereg, 0, SLJIT_IMM, ucp_Cf - ucp_Ll); + + /* In case of ucp_Cf, we overwrite the result. */ + SET_CHAR_OFFSET(0x2066); + OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x2069 - 0x2066); + OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_C_LESS_EQUAL); + + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x061c - 0x2066); + OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_C_EQUAL); + + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x180e - 0x2066); + OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_C_EQUAL); + + JUMPHERE(jump); + jump = CMP(SLJIT_C_ZERO ^ invertcmp, TMP2, 0, SLJIT_IMM, 0); + break; + + case PT_PXPRINT: + /* C and Z groups are the farthest two groups. */ + SET_TYPE_OFFSET(ucp_Ll); + OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, typereg, 0, SLJIT_IMM, ucp_So - ucp_Ll); + OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_C_GREATER); + + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, typereg, 0, SLJIT_IMM, ucp_Zs - ucp_Ll); + OP_FLAGS(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_C_NOT_EQUAL); + + jump = CMP(SLJIT_C_NOT_EQUAL, typereg, 0, SLJIT_IMM, ucp_Cf - ucp_Ll); + + /* In case of ucp_Cf, we overwrite the result. */ + SET_CHAR_OFFSET(0x2066); + OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x2069 - 0x2066); + OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_C_LESS_EQUAL); + + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x061c - 0x2066); + OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_C_EQUAL); + + JUMPHERE(jump); + jump = CMP(SLJIT_C_ZERO ^ invertcmp, TMP2, 0, SLJIT_IMM, 0); + break; + + case PT_PXPUNCT: + SET_TYPE_OFFSET(ucp_Sc); + OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, typereg, 0, SLJIT_IMM, ucp_So - ucp_Sc); + OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_C_LESS_EQUAL); + + SET_CHAR_OFFSET(0); + OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0xff); + OP_FLAGS(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_C_LESS_EQUAL); + + SET_TYPE_OFFSET(ucp_Pc); + OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, typereg, 0, SLJIT_IMM, ucp_Ps - ucp_Pc); + OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_C_LESS_EQUAL); + jump = JUMP(SLJIT_C_NOT_ZERO ^ invertcmp); + break; + } + cc += 2; + } +#endif + + if (jump != NULL) + add_jump(compiler, compares > 0 ? list : backtracks, jump); + } + +if (found != NULL) + set_jumps(found, LABEL()); +} + +#undef SET_TYPE_OFFSET +#undef SET_CHAR_OFFSET + +#endif + +static pcre_uchar *compile_char1_matchingpath(compiler_common *common, pcre_uchar type, pcre_uchar *cc, jump_list **backtracks) +{ +DEFINE_COMPILER; +int length; +unsigned int c, oc, bit; +compare_context context; +struct sljit_jump *jump[4]; +jump_list *end_list; +#ifdef SUPPORT_UTF +struct sljit_label *label; +#ifdef SUPPORT_UCP +pcre_uchar propdata[5]; +#endif +#endif /* SUPPORT_UTF */ + +switch(type) + { + case OP_SOD: + OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, begin)); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, STR_PTR, 0, TMP1, 0)); + return cc; + + case OP_SOM: + OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, str)); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, STR_PTR, 0, TMP1, 0)); + return cc; + + case OP_NOT_WORD_BOUNDARY: + case OP_WORD_BOUNDARY: + add_jump(compiler, &common->wordboundary, JUMP(SLJIT_FAST_CALL)); + add_jump(compiler, backtracks, JUMP(type == OP_NOT_WORD_BOUNDARY ? SLJIT_C_NOT_ZERO : SLJIT_C_ZERO)); + return cc; + + case OP_NOT_DIGIT: + case OP_DIGIT: + /* Digits are usually 0-9, so it is worth to optimize them. */ + detect_partial_match(common, backtracks); +#if defined SUPPORT_UTF && defined COMPILE_PCRE8 + if (common->utf && is_char7_bitset((const pcre_uint8*)common->ctypes - cbit_length + cbit_digit, FALSE)) + read_char7_type(common, type == OP_NOT_DIGIT); + else +#endif + read_char8_type(common, type == OP_NOT_DIGIT); + /* Flip the starting bit in the negative case. */ + OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, ctype_digit); + add_jump(compiler, backtracks, JUMP(type == OP_DIGIT ? SLJIT_C_ZERO : SLJIT_C_NOT_ZERO)); + return cc; + + case OP_NOT_WHITESPACE: + case OP_WHITESPACE: + detect_partial_match(common, backtracks); +#if defined SUPPORT_UTF && defined COMPILE_PCRE8 + if (common->utf && is_char7_bitset((const pcre_uint8*)common->ctypes - cbit_length + cbit_space, FALSE)) + read_char7_type(common, type == OP_NOT_WHITESPACE); + else +#endif + read_char8_type(common, type == OP_NOT_WHITESPACE); + OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, ctype_space); + add_jump(compiler, backtracks, JUMP(type == OP_WHITESPACE ? SLJIT_C_ZERO : SLJIT_C_NOT_ZERO)); + return cc; + + case OP_NOT_WORDCHAR: + case OP_WORDCHAR: + detect_partial_match(common, backtracks); +#if defined SUPPORT_UTF && defined COMPILE_PCRE8 + if (common->utf && is_char7_bitset((const pcre_uint8*)common->ctypes - cbit_length + cbit_word, FALSE)) + read_char7_type(common, type == OP_NOT_WORDCHAR); + else +#endif + read_char8_type(common, type == OP_NOT_WORDCHAR); + OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, ctype_word); + add_jump(compiler, backtracks, JUMP(type == OP_WORDCHAR ? SLJIT_C_ZERO : SLJIT_C_NOT_ZERO)); + return cc; + + case OP_ANY: + detect_partial_match(common, backtracks); + read_char_range(common, common->nlmin, common->nlmax, TRUE); + if (common->nltype == NLTYPE_FIXED && common->newline > 255) + { + jump[0] = CMP(SLJIT_C_NOT_EQUAL, TMP1, 0, SLJIT_IMM, (common->newline >> 8) & 0xff); + end_list = NULL; + if (common->mode != JIT_PARTIAL_HARD_COMPILE) + add_jump(compiler, &end_list, CMP(SLJIT_C_GREATER_EQUAL, STR_PTR, 0, STR_END, 0)); + else + check_str_end(common, &end_list); + + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), 0); + add_jump(compiler, backtracks, CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_IMM, common->newline & 0xff)); + set_jumps(end_list, LABEL()); + JUMPHERE(jump[0]); + } + else + check_newlinechar(common, common->nltype, backtracks, TRUE); + return cc; + + case OP_ALLANY: + detect_partial_match(common, backtracks); +#ifdef SUPPORT_UTF + if (common->utf) + { + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), 0); + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); +#if defined COMPILE_PCRE8 || defined COMPILE_PCRE16 +#if defined COMPILE_PCRE8 + jump[0] = CMP(SLJIT_C_LESS, TMP1, 0, SLJIT_IMM, 0xc0); + OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP1), (sljit_sw)PRIV(utf8_table4) - 0xc0); + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP1, 0); +#elif defined COMPILE_PCRE16 + jump[0] = CMP(SLJIT_C_LESS, TMP1, 0, SLJIT_IMM, 0xd800); + OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0xfc00); + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0xd800); + OP_FLAGS(SLJIT_MOV, TMP1, 0, SLJIT_UNUSED, 0, SLJIT_C_EQUAL); + OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 1); + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP1, 0); +#endif + JUMPHERE(jump[0]); +#endif /* COMPILE_PCRE[8|16] */ + return cc; + } +#endif + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); + return cc; + + case OP_ANYBYTE: + detect_partial_match(common, backtracks); + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); + return cc; + +#ifdef SUPPORT_UTF +#ifdef SUPPORT_UCP + case OP_NOTPROP: + case OP_PROP: + propdata[0] = XCL_HASPROP; + propdata[1] = type == OP_NOTPROP ? XCL_NOTPROP : XCL_PROP; + propdata[2] = cc[0]; + propdata[3] = cc[1]; + propdata[4] = XCL_END; + compile_xclass_matchingpath(common, propdata, backtracks); + return cc + 2; +#endif +#endif + + case OP_ANYNL: + detect_partial_match(common, backtracks); + read_char_range(common, common->bsr_nlmin, common->bsr_nlmax, FALSE); + jump[0] = CMP(SLJIT_C_NOT_EQUAL, TMP1, 0, SLJIT_IMM, CHAR_CR); + /* We don't need to handle soft partial matching case. */ + end_list = NULL; + if (common->mode != JIT_PARTIAL_HARD_COMPILE) + add_jump(compiler, &end_list, CMP(SLJIT_C_GREATER_EQUAL, STR_PTR, 0, STR_END, 0)); + else + check_str_end(common, &end_list); + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), 0); + jump[1] = CMP(SLJIT_C_NOT_EQUAL, TMP1, 0, SLJIT_IMM, CHAR_NL); + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); + jump[2] = JUMP(SLJIT_JUMP); + JUMPHERE(jump[0]); + check_newlinechar(common, common->bsr_nltype, backtracks, FALSE); + set_jumps(end_list, LABEL()); + JUMPHERE(jump[1]); + JUMPHERE(jump[2]); + return cc; + + case OP_NOT_HSPACE: + case OP_HSPACE: + detect_partial_match(common, backtracks); + read_char_range(common, 0x9, 0x3000, type == OP_NOT_HSPACE); + add_jump(compiler, &common->hspace, JUMP(SLJIT_FAST_CALL)); + add_jump(compiler, backtracks, JUMP(type == OP_NOT_HSPACE ? SLJIT_C_NOT_ZERO : SLJIT_C_ZERO)); + return cc; + + case OP_NOT_VSPACE: + case OP_VSPACE: + detect_partial_match(common, backtracks); + read_char_range(common, 0xa, 0x2029, type == OP_NOT_VSPACE); + add_jump(compiler, &common->vspace, JUMP(SLJIT_FAST_CALL)); + add_jump(compiler, backtracks, JUMP(type == OP_NOT_VSPACE ? SLJIT_C_NOT_ZERO : SLJIT_C_ZERO)); + return cc; + +#ifdef SUPPORT_UCP + case OP_EXTUNI: + detect_partial_match(common, backtracks); + read_char(common); + add_jump(compiler, &common->getucd, JUMP(SLJIT_FAST_CALL)); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_IMM, (sljit_sw)PRIV(ucd_records) + SLJIT_OFFSETOF(ucd_record, gbprop)); + /* Optimize register allocation: use a real register. */ + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS0, STACK_TOP, 0); + OP1(SLJIT_MOV_UB, STACK_TOP, 0, SLJIT_MEM2(TMP1, TMP2), 3); + + label = LABEL(); + jump[0] = CMP(SLJIT_C_GREATER_EQUAL, STR_PTR, 0, STR_END, 0); + OP1(SLJIT_MOV, TMP3, 0, STR_PTR, 0); + read_char(common); + add_jump(compiler, &common->getucd, JUMP(SLJIT_FAST_CALL)); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_IMM, (sljit_sw)PRIV(ucd_records) + SLJIT_OFFSETOF(ucd_record, gbprop)); + OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM2(TMP1, TMP2), 3); + + OP2(SLJIT_SHL, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, 2); + OP1(SLJIT_MOV_UI, TMP1, 0, SLJIT_MEM1(STACK_TOP), (sljit_sw)PRIV(ucp_gbtable)); + OP1(SLJIT_MOV, STACK_TOP, 0, TMP2, 0); + OP2(SLJIT_SHL, TMP2, 0, SLJIT_IMM, 1, TMP2, 0); + OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, TMP2, 0); + JUMPTO(SLJIT_C_NOT_ZERO, label); + + OP1(SLJIT_MOV, STR_PTR, 0, TMP3, 0); + JUMPHERE(jump[0]); + OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS0); + + if (common->mode == JIT_PARTIAL_HARD_COMPILE) + { + jump[0] = CMP(SLJIT_C_LESS, STR_PTR, 0, STR_END, 0); + /* Since we successfully read a char above, partial matching must occure. */ + check_partial(common, TRUE); + JUMPHERE(jump[0]); + } + return cc; +#endif + + case OP_EODN: + /* Requires rather complex checks. */ + jump[0] = CMP(SLJIT_C_GREATER_EQUAL, STR_PTR, 0, STR_END, 0); + if (common->nltype == NLTYPE_FIXED && common->newline > 255) + { + OP2(SLJIT_ADD, TMP2, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(2)); + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); + if (common->mode == JIT_COMPILE) + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, TMP2, 0, STR_END, 0)); + else + { + jump[1] = CMP(SLJIT_C_EQUAL, TMP2, 0, STR_END, 0); + OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP2, 0, STR_END, 0); + OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_C_LESS); + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (common->newline >> 8) & 0xff); + OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_C_NOT_EQUAL); + add_jump(compiler, backtracks, JUMP(SLJIT_C_NOT_EQUAL)); + check_partial(common, TRUE); + add_jump(compiler, backtracks, JUMP(SLJIT_JUMP)); + JUMPHERE(jump[1]); + } + OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(1)); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, TMP1, 0, SLJIT_IMM, (common->newline >> 8) & 0xff)); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, TMP2, 0, SLJIT_IMM, common->newline & 0xff)); + } + else if (common->nltype == NLTYPE_FIXED) + { + OP2(SLJIT_ADD, TMP2, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, TMP2, 0, STR_END, 0)); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, TMP1, 0, SLJIT_IMM, common->newline)); + } + else + { + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); + jump[1] = CMP(SLJIT_C_NOT_EQUAL, TMP1, 0, SLJIT_IMM, CHAR_CR); + OP2(SLJIT_ADD, TMP2, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(2)); + OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP2, 0, STR_END, 0); + jump[2] = JUMP(SLJIT_C_GREATER); + add_jump(compiler, backtracks, JUMP(SLJIT_C_LESS)); + /* Equal. */ + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(1)); + jump[3] = CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_IMM, CHAR_NL); + add_jump(compiler, backtracks, JUMP(SLJIT_JUMP)); + + JUMPHERE(jump[1]); + if (common->nltype == NLTYPE_ANYCRLF) + { + OP2(SLJIT_ADD, TMP2, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); + add_jump(compiler, backtracks, CMP(SLJIT_C_LESS, TMP2, 0, STR_END, 0)); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, TMP1, 0, SLJIT_IMM, CHAR_NL)); + } + else + { + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS1, STR_PTR, 0); + read_char_range(common, common->nlmin, common->nlmax, TRUE); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, STR_PTR, 0, STR_END, 0)); + add_jump(compiler, &common->anynewline, JUMP(SLJIT_FAST_CALL)); + add_jump(compiler, backtracks, JUMP(SLJIT_C_ZERO)); + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS1); + } + JUMPHERE(jump[2]); + JUMPHERE(jump[3]); + } + JUMPHERE(jump[0]); + check_partial(common, FALSE); + return cc; + + case OP_EOD: + add_jump(compiler, backtracks, CMP(SLJIT_C_LESS, STR_PTR, 0, STR_END, 0)); + check_partial(common, FALSE); + return cc; + + case OP_CIRC: + OP1(SLJIT_MOV, TMP2, 0, ARGUMENTS, 0); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP2), SLJIT_OFFSETOF(jit_arguments, begin)); + add_jump(compiler, backtracks, CMP(SLJIT_C_GREATER, STR_PTR, 0, TMP1, 0)); + OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP2), SLJIT_OFFSETOF(jit_arguments, notbol)); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, TMP2, 0, SLJIT_IMM, 0)); + return cc; + + case OP_CIRCM: + OP1(SLJIT_MOV, TMP2, 0, ARGUMENTS, 0); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP2), SLJIT_OFFSETOF(jit_arguments, begin)); + jump[1] = CMP(SLJIT_C_GREATER, STR_PTR, 0, TMP1, 0); + OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP2), SLJIT_OFFSETOF(jit_arguments, notbol)); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, TMP2, 0, SLJIT_IMM, 0)); + jump[0] = JUMP(SLJIT_JUMP); + JUMPHERE(jump[1]); + + add_jump(compiler, backtracks, CMP(SLJIT_C_GREATER_EQUAL, STR_PTR, 0, STR_END, 0)); + if (common->nltype == NLTYPE_FIXED && common->newline > 255) + { + OP2(SLJIT_SUB, TMP2, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(2)); + add_jump(compiler, backtracks, CMP(SLJIT_C_LESS, TMP2, 0, TMP1, 0)); + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(-2)); + OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(-1)); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, TMP1, 0, SLJIT_IMM, (common->newline >> 8) & 0xff)); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, TMP2, 0, SLJIT_IMM, common->newline & 0xff)); + } + else + { + skip_char_back(common); + read_char_range(common, common->nlmin, common->nlmax, TRUE); + check_newlinechar(common, common->nltype, backtracks, FALSE); + } + JUMPHERE(jump[0]); + return cc; + + case OP_DOLL: + OP1(SLJIT_MOV, TMP2, 0, ARGUMENTS, 0); + OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP2), SLJIT_OFFSETOF(jit_arguments, noteol)); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, TMP2, 0, SLJIT_IMM, 0)); + + if (!common->endonly) + compile_char1_matchingpath(common, OP_EODN, cc, backtracks); + else + { + add_jump(compiler, backtracks, CMP(SLJIT_C_LESS, STR_PTR, 0, STR_END, 0)); + check_partial(common, FALSE); + } + return cc; + + case OP_DOLLM: + jump[1] = CMP(SLJIT_C_LESS, STR_PTR, 0, STR_END, 0); + OP1(SLJIT_MOV, TMP2, 0, ARGUMENTS, 0); + OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP2), SLJIT_OFFSETOF(jit_arguments, noteol)); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, TMP2, 0, SLJIT_IMM, 0)); + check_partial(common, FALSE); + jump[0] = JUMP(SLJIT_JUMP); + JUMPHERE(jump[1]); + + if (common->nltype == NLTYPE_FIXED && common->newline > 255) + { + OP2(SLJIT_ADD, TMP2, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(2)); + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); + if (common->mode == JIT_COMPILE) + add_jump(compiler, backtracks, CMP(SLJIT_C_GREATER, TMP2, 0, STR_END, 0)); + else + { + jump[1] = CMP(SLJIT_C_LESS_EQUAL, TMP2, 0, STR_END, 0); + /* STR_PTR = STR_END - IN_UCHARS(1) */ + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, TMP1, 0, SLJIT_IMM, (common->newline >> 8) & 0xff)); + check_partial(common, TRUE); + add_jump(compiler, backtracks, JUMP(SLJIT_JUMP)); + JUMPHERE(jump[1]); + } + + OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(1)); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, TMP1, 0, SLJIT_IMM, (common->newline >> 8) & 0xff)); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, TMP2, 0, SLJIT_IMM, common->newline & 0xff)); + } + else + { + peek_char(common, common->nlmax); + check_newlinechar(common, common->nltype, backtracks, FALSE); + } + JUMPHERE(jump[0]); + return cc; + + case OP_CHAR: + case OP_CHARI: + length = 1; +#ifdef SUPPORT_UTF + if (common->utf && HAS_EXTRALEN(*cc)) length += GET_EXTRALEN(*cc); +#endif + if (common->mode == JIT_COMPILE && (type == OP_CHAR || !char_has_othercase(common, cc) || char_get_othercase_bit(common, cc) != 0)) + { + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(length)); + add_jump(compiler, backtracks, CMP(SLJIT_C_GREATER, STR_PTR, 0, STR_END, 0)); + + context.length = IN_UCHARS(length); + context.sourcereg = -1; +#if defined SLJIT_UNALIGNED && SLJIT_UNALIGNED + context.ucharptr = 0; +#endif + return byte_sequence_compare(common, type == OP_CHARI, cc, &context, backtracks); + } + + detect_partial_match(common, backtracks); +#ifdef SUPPORT_UTF + if (common->utf) + { + GETCHAR(c, cc); + } + else +#endif + c = *cc; + + if (type == OP_CHAR || !char_has_othercase(common, cc)) + { + read_char_range(common, c, c, FALSE); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, TMP1, 0, SLJIT_IMM, c)); + return cc + length; + } + oc = char_othercase(common, c); + read_char_range(common, c < oc ? c : oc, c > oc ? c : oc, FALSE); + bit = c ^ oc; + if (is_powerof2(bit)) + { + OP2(SLJIT_OR, TMP1, 0, TMP1, 0, SLJIT_IMM, bit); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, TMP1, 0, SLJIT_IMM, c | bit)); + return cc + length; + } + jump[0] = CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_IMM, c); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, TMP1, 0, SLJIT_IMM, oc)); + JUMPHERE(jump[0]); + return cc + length; + + case OP_NOT: + case OP_NOTI: + detect_partial_match(common, backtracks); + length = 1; +#ifdef SUPPORT_UTF + if (common->utf) + { +#ifdef COMPILE_PCRE8 + c = *cc; + if (c < 128) + { + OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(STR_PTR), 0); + if (type == OP_NOT || !char_has_othercase(common, cc)) + add_jump(compiler, backtracks, CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_IMM, c)); + else + { + /* Since UTF8 code page is fixed, we know that c is in [a-z] or [A-Z] range. */ + OP2(SLJIT_OR, TMP2, 0, TMP1, 0, SLJIT_IMM, 0x20); + add_jump(compiler, backtracks, CMP(SLJIT_C_EQUAL, TMP2, 0, SLJIT_IMM, c | 0x20)); + } + /* Skip the variable-length character. */ + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); + jump[0] = CMP(SLJIT_C_LESS, TMP1, 0, SLJIT_IMM, 0xc0); + OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(TMP1), (sljit_sw)PRIV(utf8_table4) - 0xc0); + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP1, 0); + JUMPHERE(jump[0]); + return cc + 1; + } + else +#endif /* COMPILE_PCRE8 */ + { + GETCHARLEN(c, cc, length); + } + } + else +#endif /* SUPPORT_UTF */ + c = *cc; + + if (type == OP_NOT || !char_has_othercase(common, cc)) + { + read_char_range(common, c, c, TRUE); + add_jump(compiler, backtracks, CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_IMM, c)); + } + else + { + oc = char_othercase(common, c); + read_char_range(common, c < oc ? c : oc, c > oc ? c : oc, TRUE); + bit = c ^ oc; + if (is_powerof2(bit)) + { + OP2(SLJIT_OR, TMP1, 0, TMP1, 0, SLJIT_IMM, bit); + add_jump(compiler, backtracks, CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_IMM, c | bit)); + } + else + { + add_jump(compiler, backtracks, CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_IMM, c)); + add_jump(compiler, backtracks, CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_IMM, oc)); + } + } + return cc + length; + + case OP_CLASS: + case OP_NCLASS: + detect_partial_match(common, backtracks); + +#if defined SUPPORT_UTF && defined COMPILE_PCRE8 + bit = (common->utf && is_char7_bitset((const pcre_uint8 *)cc, type == OP_NCLASS)) ? 127 : 255; + read_char_range(common, 0, bit, type == OP_NCLASS); +#else + read_char_range(common, 0, 255, type == OP_NCLASS); +#endif + + if (check_class_ranges(common, (const pcre_uint8 *)cc, type == OP_NCLASS, FALSE, backtracks)) + return cc + 32 / sizeof(pcre_uchar); + +#if defined SUPPORT_UTF && defined COMPILE_PCRE8 + jump[0] = NULL; + if (common->utf) + { + jump[0] = CMP(SLJIT_C_GREATER, TMP1, 0, SLJIT_IMM, bit); + if (type == OP_CLASS) + { + add_jump(compiler, backtracks, jump[0]); + jump[0] = NULL; + } + } +#elif !defined COMPILE_PCRE8 + jump[0] = CMP(SLJIT_C_GREATER, TMP1, 0, SLJIT_IMM, 255); + if (type == OP_CLASS) + { + add_jump(compiler, backtracks, jump[0]); + jump[0] = NULL; + } +#endif /* SUPPORT_UTF && COMPILE_PCRE8 */ + + OP2(SLJIT_AND, TMP2, 0, TMP1, 0, SLJIT_IMM, 0x7); + OP2(SLJIT_LSHR, TMP1, 0, TMP1, 0, SLJIT_IMM, 3); + OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP1), (sljit_sw)cc); + OP2(SLJIT_SHL, TMP2, 0, SLJIT_IMM, 1, TMP2, 0); + OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, TMP2, 0); + add_jump(compiler, backtracks, JUMP(SLJIT_C_ZERO)); + +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + if (jump[0] != NULL) + JUMPHERE(jump[0]); +#endif + + return cc + 32 / sizeof(pcre_uchar); + +#if defined SUPPORT_UTF || defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + case OP_XCLASS: + compile_xclass_matchingpath(common, cc + LINK_SIZE, backtracks); + return cc + GET(cc, 0) - 1; +#endif + + case OP_REVERSE: + length = GET(cc, 0); + if (length == 0) + return cc + LINK_SIZE; + OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); +#ifdef SUPPORT_UTF + if (common->utf) + { + OP1(SLJIT_MOV, TMP3, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, begin)); + OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, length); + label = LABEL(); + add_jump(compiler, backtracks, CMP(SLJIT_C_LESS_EQUAL, STR_PTR, 0, TMP3, 0)); + skip_char_back(common); + OP2(SLJIT_SUB | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_IMM, 1); + JUMPTO(SLJIT_C_NOT_ZERO, label); + } + else +#endif + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, begin)); + OP2(SLJIT_SUB, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(length)); + add_jump(compiler, backtracks, CMP(SLJIT_C_LESS, STR_PTR, 0, TMP1, 0)); + } + check_start_used_ptr(common); + return cc + LINK_SIZE; + } +SLJIT_ASSERT_STOP(); +return cc; +} + +static SLJIT_INLINE pcre_uchar *compile_charn_matchingpath(compiler_common *common, pcre_uchar *cc, pcre_uchar *ccend, jump_list **backtracks) +{ +/* This function consumes at least one input character. */ +/* To decrease the number of length checks, we try to concatenate the fixed length character sequences. */ +DEFINE_COMPILER; +pcre_uchar *ccbegin = cc; +compare_context context; +int size; + +context.length = 0; +do + { + if (cc >= ccend) + break; + + if (*cc == OP_CHAR) + { + size = 1; +#ifdef SUPPORT_UTF + if (common->utf && HAS_EXTRALEN(cc[1])) + size += GET_EXTRALEN(cc[1]); +#endif + } + else if (*cc == OP_CHARI) + { + size = 1; +#ifdef SUPPORT_UTF + if (common->utf) + { + if (char_has_othercase(common, cc + 1) && char_get_othercase_bit(common, cc + 1) == 0) + size = 0; + else if (HAS_EXTRALEN(cc[1])) + size += GET_EXTRALEN(cc[1]); + } + else +#endif + if (char_has_othercase(common, cc + 1) && char_get_othercase_bit(common, cc + 1) == 0) + size = 0; + } + else + size = 0; + + cc += 1 + size; + context.length += IN_UCHARS(size); + } +while (size > 0 && context.length <= 128); + +cc = ccbegin; +if (context.length > 0) + { + /* We have a fixed-length byte sequence. */ + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, context.length); + add_jump(compiler, backtracks, CMP(SLJIT_C_GREATER, STR_PTR, 0, STR_END, 0)); + + context.sourcereg = -1; +#if defined SLJIT_UNALIGNED && SLJIT_UNALIGNED + context.ucharptr = 0; +#endif + do cc = byte_sequence_compare(common, *cc == OP_CHARI, cc + 1, &context, backtracks); while (context.length > 0); + return cc; + } + +/* A non-fixed length character will be checked if length == 0. */ +return compile_char1_matchingpath(common, *cc, cc + 1, backtracks); +} + +/* Forward definitions. */ +static void compile_matchingpath(compiler_common *, pcre_uchar *, pcre_uchar *, backtrack_common *); +static void compile_backtrackingpath(compiler_common *, struct backtrack_common *); + +#define PUSH_BACKTRACK(size, ccstart, error) \ + do \ + { \ + backtrack = sljit_alloc_memory(compiler, (size)); \ + if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) \ + return error; \ + memset(backtrack, 0, size); \ + backtrack->prev = parent->top; \ + backtrack->cc = (ccstart); \ + parent->top = backtrack; \ + } \ + while (0) + +#define PUSH_BACKTRACK_NOVALUE(size, ccstart) \ + do \ + { \ + backtrack = sljit_alloc_memory(compiler, (size)); \ + if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) \ + return; \ + memset(backtrack, 0, size); \ + backtrack->prev = parent->top; \ + backtrack->cc = (ccstart); \ + parent->top = backtrack; \ + } \ + while (0) + +#define BACKTRACK_AS(type) ((type *)backtrack) + +static void compile_dnref_search(compiler_common *common, pcre_uchar *cc, jump_list **backtracks) +{ +/* The OVECTOR offset goes to TMP2. */ +DEFINE_COMPILER; +int count = GET2(cc, 1 + IMM2_SIZE); +pcre_uchar *slot = common->name_table + GET2(cc, 1) * common->name_entry_size; +unsigned int offset; +jump_list *found = NULL; + +SLJIT_ASSERT(*cc == OP_DNREF || *cc == OP_DNREFI); + +OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(1)); + +count--; +while (count-- > 0) + { + offset = GET2(slot, 0) << 1; + GET_LOCAL_BASE(TMP2, 0, OVECTOR(offset)); + add_jump(compiler, &found, CMP(SLJIT_C_NOT_EQUAL, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset), TMP1, 0)); + slot += common->name_entry_size; + } + +offset = GET2(slot, 0) << 1; +GET_LOCAL_BASE(TMP2, 0, OVECTOR(offset)); +if (backtracks != NULL && !common->jscript_compat) + add_jump(compiler, backtracks, CMP(SLJIT_C_EQUAL, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset), TMP1, 0)); + +set_jumps(found, LABEL()); +} + +static void compile_ref_matchingpath(compiler_common *common, pcre_uchar *cc, jump_list **backtracks, BOOL withchecks, BOOL emptyfail) +{ +DEFINE_COMPILER; +BOOL ref = (*cc == OP_REF || *cc == OP_REFI); +int offset = 0; +struct sljit_jump *jump = NULL; +struct sljit_jump *partial; +struct sljit_jump *nopartial; + +if (ref) + { + offset = GET2(cc, 1) << 1; + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset)); + /* OVECTOR(1) contains the "string begin - 1" constant. */ + if (withchecks && !common->jscript_compat) + add_jump(compiler, backtracks, CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(1))); + } +else + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP2), 0); + +#if defined SUPPORT_UTF && defined SUPPORT_UCP +if (common->utf && *cc == OP_REFI) + { + SLJIT_ASSERT(TMP1 == SLJIT_SCRATCH_REG1 && STACK_TOP == SLJIT_SCRATCH_REG2 && TMP2 == SLJIT_SCRATCH_REG3); + if (ref) + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset + 1)); + else + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(TMP2), sizeof(sljit_sw)); + + if (withchecks) + jump = CMP(SLJIT_C_EQUAL, TMP1, 0, TMP2, 0); + + /* Needed to save important temporary registers. */ + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS0, STACK_TOP, 0); + OP1(SLJIT_MOV, SLJIT_SCRATCH_REG2, 0, ARGUMENTS, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SCRATCH_REG2), SLJIT_OFFSETOF(jit_arguments, uchar_ptr), STR_PTR, 0); + sljit_emit_ijump(compiler, SLJIT_CALL3, SLJIT_IMM, SLJIT_FUNC_OFFSET(do_utf_caselesscmp)); + OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS0); + if (common->mode == JIT_COMPILE) + add_jump(compiler, backtracks, CMP(SLJIT_C_LESS_EQUAL, SLJIT_RETURN_REG, 0, SLJIT_IMM, 1)); + else + { + add_jump(compiler, backtracks, CMP(SLJIT_C_EQUAL, SLJIT_RETURN_REG, 0, SLJIT_IMM, 0)); + nopartial = CMP(SLJIT_C_NOT_EQUAL, SLJIT_RETURN_REG, 0, SLJIT_IMM, 1); + check_partial(common, FALSE); + add_jump(compiler, backtracks, JUMP(SLJIT_JUMP)); + JUMPHERE(nopartial); + } + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_RETURN_REG, 0); + } +else +#endif /* SUPPORT_UTF && SUPPORT_UCP */ + { + if (ref) + OP2(SLJIT_SUB | SLJIT_SET_E, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset + 1), TMP1, 0); + else + OP2(SLJIT_SUB | SLJIT_SET_E, TMP2, 0, SLJIT_MEM1(TMP2), sizeof(sljit_sw), TMP1, 0); + + if (withchecks) + jump = JUMP(SLJIT_C_ZERO); + + OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP2, 0); + partial = CMP(SLJIT_C_GREATER, STR_PTR, 0, STR_END, 0); + if (common->mode == JIT_COMPILE) + add_jump(compiler, backtracks, partial); + + add_jump(compiler, *cc == OP_REF ? &common->casefulcmp : &common->caselesscmp, JUMP(SLJIT_FAST_CALL)); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, TMP2, 0, SLJIT_IMM, 0)); + + if (common->mode != JIT_COMPILE) + { + nopartial = JUMP(SLJIT_JUMP); + JUMPHERE(partial); + /* TMP2 -= STR_END - STR_PTR */ + OP2(SLJIT_SUB, TMP2, 0, TMP2, 0, STR_PTR, 0); + OP2(SLJIT_ADD, TMP2, 0, TMP2, 0, STR_END, 0); + partial = CMP(SLJIT_C_EQUAL, TMP2, 0, SLJIT_IMM, 0); + OP1(SLJIT_MOV, STR_PTR, 0, STR_END, 0); + add_jump(compiler, *cc == OP_REF ? &common->casefulcmp : &common->caselesscmp, JUMP(SLJIT_FAST_CALL)); + add_jump(compiler, backtracks, CMP(SLJIT_C_NOT_EQUAL, TMP2, 0, SLJIT_IMM, 0)); + JUMPHERE(partial); + check_partial(common, FALSE); + add_jump(compiler, backtracks, JUMP(SLJIT_JUMP)); + JUMPHERE(nopartial); + } + } + +if (jump != NULL) + { + if (emptyfail) + add_jump(compiler, backtracks, jump); + else + JUMPHERE(jump); + } +} + +static SLJIT_INLINE pcre_uchar *compile_ref_iterator_matchingpath(compiler_common *common, pcre_uchar *cc, backtrack_common *parent) +{ +DEFINE_COMPILER; +BOOL ref = (*cc == OP_REF || *cc == OP_REFI); +backtrack_common *backtrack; +pcre_uchar type; +int offset = 0; +struct sljit_label *label; +struct sljit_jump *zerolength; +struct sljit_jump *jump = NULL; +pcre_uchar *ccbegin = cc; +int min = 0, max = 0; +BOOL minimize; + +PUSH_BACKTRACK(sizeof(iterator_backtrack), cc, NULL); + +if (ref) + offset = GET2(cc, 1) << 1; +else + cc += IMM2_SIZE; +type = cc[1 + IMM2_SIZE]; + +SLJIT_COMPILE_ASSERT((OP_CRSTAR & 0x1) == 0, crstar_opcode_must_be_even); +minimize = (type & 0x1) != 0; +switch(type) + { + case OP_CRSTAR: + case OP_CRMINSTAR: + min = 0; + max = 0; + cc += 1 + IMM2_SIZE + 1; + break; + case OP_CRPLUS: + case OP_CRMINPLUS: + min = 1; + max = 0; + cc += 1 + IMM2_SIZE + 1; + break; + case OP_CRQUERY: + case OP_CRMINQUERY: + min = 0; + max = 1; + cc += 1 + IMM2_SIZE + 1; + break; + case OP_CRRANGE: + case OP_CRMINRANGE: + min = GET2(cc, 1 + IMM2_SIZE + 1); + max = GET2(cc, 1 + IMM2_SIZE + 1 + IMM2_SIZE); + cc += 1 + IMM2_SIZE + 1 + 2 * IMM2_SIZE; + break; + default: + SLJIT_ASSERT_STOP(); + break; + } + +if (!minimize) + { + if (min == 0) + { + allocate_stack(common, 2); + if (ref) + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset)); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(1), SLJIT_IMM, 0); + /* Temporary release of STR_PTR. */ + OP2(SLJIT_SUB, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, sizeof(sljit_sw)); + /* Handles both invalid and empty cases. Since the minimum repeat, + is zero the invalid case is basically the same as an empty case. */ + if (ref) + zerolength = CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset + 1)); + else + { + compile_dnref_search(common, ccbegin, NULL); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP2), 0); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), POSSESSIVE1, TMP2, 0); + zerolength = CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_MEM1(TMP2), sizeof(sljit_sw)); + } + /* Restore if not zero length. */ + OP2(SLJIT_ADD, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, sizeof(sljit_sw)); + } + else + { + allocate_stack(common, 1); + if (ref) + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset)); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); + if (ref) + { + add_jump(compiler, &backtrack->topbacktracks, CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(1))); + zerolength = CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset + 1)); + } + else + { + compile_dnref_search(common, ccbegin, &backtrack->topbacktracks); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP2), 0); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), POSSESSIVE1, TMP2, 0); + zerolength = CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_MEM1(TMP2), sizeof(sljit_sw)); + } + } + + if (min > 1 || max > 1) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), POSSESSIVE0, SLJIT_IMM, 0); + + label = LABEL(); + if (!ref) + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), POSSESSIVE1); + compile_ref_matchingpath(common, ccbegin, &backtrack->topbacktracks, FALSE, FALSE); + + if (min > 1 || max > 1) + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), POSSESSIVE0); + OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, SLJIT_IMM, 1); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), POSSESSIVE0, TMP1, 0); + if (min > 1) + CMPTO(SLJIT_C_LESS, TMP1, 0, SLJIT_IMM, min, label); + if (max > 1) + { + jump = CMP(SLJIT_C_GREATER_EQUAL, TMP1, 0, SLJIT_IMM, max); + allocate_stack(common, 1); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); + JUMPTO(SLJIT_JUMP, label); + JUMPHERE(jump); + } + } + + if (max == 0) + { + /* Includes min > 1 case as well. */ + allocate_stack(common, 1); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); + JUMPTO(SLJIT_JUMP, label); + } + + JUMPHERE(zerolength); + BACKTRACK_AS(iterator_backtrack)->matchingpath = LABEL(); + + count_match(common); + return cc; + } + +allocate_stack(common, ref ? 2 : 3); +if (ref) + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset)); +OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); +if (type != OP_CRMINSTAR) + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(1), SLJIT_IMM, 0); + +if (min == 0) + { + /* Handles both invalid and empty cases. Since the minimum repeat, + is zero the invalid case is basically the same as an empty case. */ + if (ref) + zerolength = CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset + 1)); + else + { + compile_dnref_search(common, ccbegin, NULL); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP2), 0); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(2), TMP2, 0); + zerolength = CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_MEM1(TMP2), sizeof(sljit_sw)); + } + /* Length is non-zero, we can match real repeats. */ + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); + jump = JUMP(SLJIT_JUMP); + } +else + { + if (ref) + { + add_jump(compiler, &backtrack->topbacktracks, CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(1))); + zerolength = CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset + 1)); + } + else + { + compile_dnref_search(common, ccbegin, &backtrack->topbacktracks); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP2), 0); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(2), TMP2, 0); + zerolength = CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_MEM1(TMP2), sizeof(sljit_sw)); + } + } + +BACKTRACK_AS(iterator_backtrack)->matchingpath = LABEL(); +if (max > 0) + add_jump(compiler, &backtrack->topbacktracks, CMP(SLJIT_C_GREATER_EQUAL, SLJIT_MEM1(STACK_TOP), STACK(1), SLJIT_IMM, max)); + +if (!ref) + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), STACK(2)); +compile_ref_matchingpath(common, ccbegin, &backtrack->topbacktracks, TRUE, TRUE); +OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); + +if (min > 1) + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(1)); + OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, SLJIT_IMM, 1); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(1), TMP1, 0); + CMPTO(SLJIT_C_LESS, TMP1, 0, SLJIT_IMM, min, BACKTRACK_AS(iterator_backtrack)->matchingpath); + } +else if (max > 0) + OP2(SLJIT_ADD, SLJIT_MEM1(STACK_TOP), STACK(1), SLJIT_MEM1(STACK_TOP), STACK(1), SLJIT_IMM, 1); + +if (jump != NULL) + JUMPHERE(jump); +JUMPHERE(zerolength); + +count_match(common); +return cc; +} + +static SLJIT_INLINE pcre_uchar *compile_recurse_matchingpath(compiler_common *common, pcre_uchar *cc, backtrack_common *parent) +{ +DEFINE_COMPILER; +backtrack_common *backtrack; +recurse_entry *entry = common->entries; +recurse_entry *prev = NULL; +sljit_sw start = GET(cc, 1); +pcre_uchar *start_cc; +BOOL needs_control_head; + +PUSH_BACKTRACK(sizeof(recurse_backtrack), cc, NULL); + +/* Inlining simple patterns. */ +if (get_framesize(common, common->start + start, NULL, TRUE, &needs_control_head) == no_stack) + { + start_cc = common->start + start; + compile_matchingpath(common, next_opcode(common, start_cc), bracketend(start_cc) - (1 + LINK_SIZE), backtrack); + BACKTRACK_AS(recurse_backtrack)->inlined_pattern = TRUE; + return cc + 1 + LINK_SIZE; + } + +while (entry != NULL) + { + if (entry->start == start) + break; + prev = entry; + entry = entry->next; + } + +if (entry == NULL) + { + entry = sljit_alloc_memory(compiler, sizeof(recurse_entry)); + if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) + return NULL; + entry->next = NULL; + entry->entry = NULL; + entry->calls = NULL; + entry->start = start; + + if (prev != NULL) + prev->next = entry; + else + common->entries = entry; + } + +if (common->has_set_som && common->mark_ptr != 0) + { + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(0)); + allocate_stack(common, 2); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->mark_ptr); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), TMP2, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(1), TMP1, 0); + } +else if (common->has_set_som || common->mark_ptr != 0) + { + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->has_set_som ? (int)(OVECTOR(0)) : common->mark_ptr); + allocate_stack(common, 1); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), TMP2, 0); + } + +if (entry->entry == NULL) + add_jump(compiler, &entry->calls, JUMP(SLJIT_FAST_CALL)); +else + JUMPTO(SLJIT_FAST_CALL, entry->entry); +/* Leave if the match is failed. */ +add_jump(compiler, &backtrack->topbacktracks, CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_IMM, 0)); +return cc + 1 + LINK_SIZE; +} + +static int SLJIT_CALL do_callout(struct jit_arguments* arguments, PUBL(callout_block) *callout_block, pcre_uchar **jit_ovector) +{ +const pcre_uchar *begin = arguments->begin; +int *offset_vector = arguments->offsets; +int offset_count = arguments->offset_count; +int i; + +if (PUBL(callout) == NULL) + return 0; + +callout_block->version = 2; +callout_block->callout_data = arguments->callout_data; + +/* Offsets in subject. */ +callout_block->subject_length = arguments->end - arguments->begin; +callout_block->start_match = (pcre_uchar*)callout_block->subject - arguments->begin; +callout_block->current_position = (pcre_uchar*)callout_block->offset_vector - arguments->begin; +#if defined COMPILE_PCRE8 +callout_block->subject = (PCRE_SPTR)begin; +#elif defined COMPILE_PCRE16 +callout_block->subject = (PCRE_SPTR16)begin; +#elif defined COMPILE_PCRE32 +callout_block->subject = (PCRE_SPTR32)begin; +#endif + +/* Convert and copy the JIT offset vector to the offset_vector array. */ +callout_block->capture_top = 0; +callout_block->offset_vector = offset_vector; +for (i = 2; i < offset_count; i += 2) + { + offset_vector[i] = jit_ovector[i] - begin; + offset_vector[i + 1] = jit_ovector[i + 1] - begin; + if (jit_ovector[i] >= begin) + callout_block->capture_top = i; + } + +callout_block->capture_top = (callout_block->capture_top >> 1) + 1; +if (offset_count > 0) + offset_vector[0] = -1; +if (offset_count > 1) + offset_vector[1] = -1; +return (*PUBL(callout))(callout_block); +} + +/* Aligning to 8 byte. */ +#define CALLOUT_ARG_SIZE \ + (((int)sizeof(PUBL(callout_block)) + 7) & ~7) + +#define CALLOUT_ARG_OFFSET(arg) \ + (-CALLOUT_ARG_SIZE + SLJIT_OFFSETOF(PUBL(callout_block), arg)) + +static SLJIT_INLINE pcre_uchar *compile_callout_matchingpath(compiler_common *common, pcre_uchar *cc, backtrack_common *parent) +{ +DEFINE_COMPILER; +backtrack_common *backtrack; + +PUSH_BACKTRACK(sizeof(backtrack_common), cc, NULL); + +allocate_stack(common, CALLOUT_ARG_SIZE / sizeof(sljit_sw)); + +OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->capture_last_ptr); +OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); +SLJIT_ASSERT(common->capture_last_ptr != 0); +OP1(SLJIT_MOV_SI, SLJIT_MEM1(STACK_TOP), CALLOUT_ARG_OFFSET(callout_number), SLJIT_IMM, cc[1]); +OP1(SLJIT_MOV_SI, SLJIT_MEM1(STACK_TOP), CALLOUT_ARG_OFFSET(capture_last), TMP2, 0); + +/* These pointer sized fields temporarly stores internal variables. */ +OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(0)); +OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), CALLOUT_ARG_OFFSET(offset_vector), STR_PTR, 0); +OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), CALLOUT_ARG_OFFSET(subject), TMP2, 0); + +if (common->mark_ptr != 0) + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, mark_ptr)); +OP1(SLJIT_MOV_SI, SLJIT_MEM1(STACK_TOP), CALLOUT_ARG_OFFSET(pattern_position), SLJIT_IMM, GET(cc, 2)); +OP1(SLJIT_MOV_SI, SLJIT_MEM1(STACK_TOP), CALLOUT_ARG_OFFSET(next_item_length), SLJIT_IMM, GET(cc, 2 + LINK_SIZE)); +OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), CALLOUT_ARG_OFFSET(mark), (common->mark_ptr != 0) ? TMP2 : SLJIT_IMM, 0); + +/* Needed to save important temporary registers. */ +OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS0, STACK_TOP, 0); +OP2(SLJIT_SUB, SLJIT_SCRATCH_REG2, 0, STACK_TOP, 0, SLJIT_IMM, CALLOUT_ARG_SIZE); +GET_LOCAL_BASE(SLJIT_SCRATCH_REG3, 0, OVECTOR_START); +sljit_emit_ijump(compiler, SLJIT_CALL3, SLJIT_IMM, SLJIT_FUNC_OFFSET(do_callout)); +OP1(SLJIT_MOV_SI, SLJIT_RETURN_REG, 0, SLJIT_RETURN_REG, 0); +OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS0); +free_stack(common, CALLOUT_ARG_SIZE / sizeof(sljit_sw)); + +/* Check return value. */ +OP2(SLJIT_SUB | SLJIT_SET_S, SLJIT_UNUSED, 0, SLJIT_RETURN_REG, 0, SLJIT_IMM, 0); +add_jump(compiler, &backtrack->topbacktracks, JUMP(SLJIT_C_SIG_GREATER)); +if (common->forced_quit_label == NULL) + add_jump(compiler, &common->forced_quit, JUMP(SLJIT_C_SIG_LESS)); +else + JUMPTO(SLJIT_C_SIG_LESS, common->forced_quit_label); +return cc + 2 + 2 * LINK_SIZE; +} + +#undef CALLOUT_ARG_SIZE +#undef CALLOUT_ARG_OFFSET + +static pcre_uchar *compile_assert_matchingpath(compiler_common *common, pcre_uchar *cc, assert_backtrack *backtrack, BOOL conditional) +{ +DEFINE_COMPILER; +int framesize; +int extrasize; +BOOL needs_control_head; +int private_data_ptr; +backtrack_common altbacktrack; +pcre_uchar *ccbegin; +pcre_uchar opcode; +pcre_uchar bra = OP_BRA; +jump_list *tmp = NULL; +jump_list **target = (conditional) ? &backtrack->condfailed : &backtrack->common.topbacktracks; +jump_list **found; +/* Saving previous accept variables. */ +BOOL save_local_exit = common->local_exit; +BOOL save_positive_assert = common->positive_assert; +then_trap_backtrack *save_then_trap = common->then_trap; +struct sljit_label *save_quit_label = common->quit_label; +struct sljit_label *save_accept_label = common->accept_label; +jump_list *save_quit = common->quit; +jump_list *save_positive_assert_quit = common->positive_assert_quit; +jump_list *save_accept = common->accept; +struct sljit_jump *jump; +struct sljit_jump *brajump = NULL; + +/* Assert captures then. */ +common->then_trap = NULL; + +if (*cc == OP_BRAZERO || *cc == OP_BRAMINZERO) + { + SLJIT_ASSERT(!conditional); + bra = *cc; + cc++; + } +private_data_ptr = PRIVATE_DATA(cc); +SLJIT_ASSERT(private_data_ptr != 0); +framesize = get_framesize(common, cc, NULL, FALSE, &needs_control_head); +backtrack->framesize = framesize; +backtrack->private_data_ptr = private_data_ptr; +opcode = *cc; +SLJIT_ASSERT(opcode >= OP_ASSERT && opcode <= OP_ASSERTBACK_NOT); +found = (opcode == OP_ASSERT || opcode == OP_ASSERTBACK) ? &tmp : target; +ccbegin = cc; +cc += GET(cc, 1); + +if (bra == OP_BRAMINZERO) + { + /* This is a braminzero backtrack path. */ + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + free_stack(common, 1); + brajump = CMP(SLJIT_C_EQUAL, STR_PTR, 0, SLJIT_IMM, 0); + } + +if (framesize < 0) + { + extrasize = needs_control_head ? 2 : 1; + if (framesize == no_frame) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, STACK_TOP, 0); + allocate_stack(common, extrasize); + if (needs_control_head) + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); + if (needs_control_head) + { + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr, SLJIT_IMM, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(1), TMP1, 0); + } + } +else + { + extrasize = needs_control_head ? 3 : 2; + allocate_stack(common, framesize + extrasize); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr); + OP2(SLJIT_SUB, TMP2, 0, STACK_TOP, 0, SLJIT_IMM, (framesize + extrasize) * sizeof(sljit_sw)); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, TMP2, 0); + if (needs_control_head) + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); + if (needs_control_head) + { + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(2), TMP1, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(1), TMP2, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr, SLJIT_IMM, 0); + } + else + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(1), TMP1, 0); + init_frame(common, ccbegin, NULL, framesize + extrasize - 1, extrasize, FALSE); + } + +memset(&altbacktrack, 0, sizeof(backtrack_common)); +if (opcode == OP_ASSERT_NOT || opcode == OP_ASSERTBACK_NOT) + { + /* Negative assert is stronger than positive assert. */ + common->local_exit = TRUE; + common->quit_label = NULL; + common->quit = NULL; + common->positive_assert = FALSE; + } +else + common->positive_assert = TRUE; +common->positive_assert_quit = NULL; + +while (1) + { + common->accept_label = NULL; + common->accept = NULL; + altbacktrack.top = NULL; + altbacktrack.topbacktracks = NULL; + + if (*ccbegin == OP_ALT) + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + + altbacktrack.cc = ccbegin; + compile_matchingpath(common, ccbegin + 1 + LINK_SIZE, cc, &altbacktrack); + if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) + { + if (opcode == OP_ASSERT_NOT || opcode == OP_ASSERTBACK_NOT) + { + common->local_exit = save_local_exit; + common->quit_label = save_quit_label; + common->quit = save_quit; + } + common->positive_assert = save_positive_assert; + common->then_trap = save_then_trap; + common->accept_label = save_accept_label; + common->positive_assert_quit = save_positive_assert_quit; + common->accept = save_accept; + return NULL; + } + common->accept_label = LABEL(); + if (common->accept != NULL) + set_jumps(common->accept, common->accept_label); + + /* Reset stack. */ + if (framesize < 0) + { + if (framesize == no_frame) + OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr); + else + free_stack(common, extrasize); + if (needs_control_head) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr, SLJIT_MEM1(STACK_TOP), 0); + } + else + { + if ((opcode != OP_ASSERT_NOT && opcode != OP_ASSERTBACK_NOT) || conditional) + { + /* We don't need to keep the STR_PTR, only the previous private_data_ptr. */ + OP2(SLJIT_ADD, STACK_TOP, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, SLJIT_IMM, (framesize + 1) * sizeof(sljit_sw)); + if (needs_control_head) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr, SLJIT_MEM1(STACK_TOP), 0); + } + else + { + OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr); + if (needs_control_head) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr, SLJIT_MEM1(STACK_TOP), (framesize + 1) * sizeof(sljit_sw)); + add_jump(compiler, &common->revertframes, JUMP(SLJIT_FAST_CALL)); + } + } + + if (opcode == OP_ASSERT_NOT || opcode == OP_ASSERTBACK_NOT) + { + /* We know that STR_PTR was stored on the top of the stack. */ + if (conditional) + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), needs_control_head ? sizeof(sljit_sw) : 0); + else if (bra == OP_BRAZERO) + { + if (framesize < 0) + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), (extrasize - 1) * sizeof(sljit_sw)); + else + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), framesize * sizeof(sljit_sw)); + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), (framesize + extrasize - 1) * sizeof(sljit_sw)); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, TMP1, 0); + } + OP2(SLJIT_ADD, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, sizeof(sljit_sw)); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); + } + else if (framesize >= 0) + { + /* For OP_BRA and OP_BRAMINZERO. */ + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, SLJIT_MEM1(STACK_TOP), framesize * sizeof(sljit_sw)); + } + } + add_jump(compiler, found, JUMP(SLJIT_JUMP)); + + compile_backtrackingpath(common, altbacktrack.top); + if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) + { + if (opcode == OP_ASSERT_NOT || opcode == OP_ASSERTBACK_NOT) + { + common->local_exit = save_local_exit; + common->quit_label = save_quit_label; + common->quit = save_quit; + } + common->positive_assert = save_positive_assert; + common->then_trap = save_then_trap; + common->accept_label = save_accept_label; + common->positive_assert_quit = save_positive_assert_quit; + common->accept = save_accept; + return NULL; + } + set_jumps(altbacktrack.topbacktracks, LABEL()); + + if (*cc != OP_ALT) + break; + + ccbegin = cc; + cc += GET(cc, 1); + } + +if (opcode == OP_ASSERT_NOT || opcode == OP_ASSERTBACK_NOT) + { + SLJIT_ASSERT(common->positive_assert_quit == NULL); + /* Makes the check less complicated below. */ + common->positive_assert_quit = common->quit; + } + +/* None of them matched. */ +if (common->positive_assert_quit != NULL) + { + jump = JUMP(SLJIT_JUMP); + set_jumps(common->positive_assert_quit, LABEL()); + SLJIT_ASSERT(framesize != no_stack); + if (framesize < 0) + OP2(SLJIT_ADD, STACK_TOP, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, SLJIT_IMM, extrasize * sizeof(sljit_sw)); + else + { + OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr); + add_jump(compiler, &common->revertframes, JUMP(SLJIT_FAST_CALL)); + OP2(SLJIT_ADD, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, (framesize + extrasize) * sizeof(sljit_sw)); + } + JUMPHERE(jump); + } + +if (needs_control_head) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr, SLJIT_MEM1(STACK_TOP), STACK(1)); + +if (opcode == OP_ASSERT || opcode == OP_ASSERTBACK) + { + /* Assert is failed. */ + if (conditional || bra == OP_BRAZERO) + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + + if (framesize < 0) + { + /* The topmost item should be 0. */ + if (bra == OP_BRAZERO) + { + if (extrasize == 2) + free_stack(common, 1); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); + } + else + free_stack(common, extrasize); + } + else + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(extrasize - 1)); + /* The topmost item should be 0. */ + if (bra == OP_BRAZERO) + { + free_stack(common, framesize + extrasize - 1); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); + } + else + free_stack(common, framesize + extrasize); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, TMP1, 0); + } + jump = JUMP(SLJIT_JUMP); + if (bra != OP_BRAZERO) + add_jump(compiler, target, jump); + + /* Assert is successful. */ + set_jumps(tmp, LABEL()); + if (framesize < 0) + { + /* We know that STR_PTR was stored on the top of the stack. */ + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), (extrasize - 1) * sizeof(sljit_sw)); + /* Keep the STR_PTR on the top of the stack. */ + if (bra == OP_BRAZERO) + { + OP2(SLJIT_ADD, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, sizeof(sljit_sw)); + if (extrasize == 2) + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); + } + else if (bra == OP_BRAMINZERO) + { + OP2(SLJIT_ADD, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, sizeof(sljit_sw)); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); + } + } + else + { + if (bra == OP_BRA) + { + /* We don't need to keep the STR_PTR, only the previous private_data_ptr. */ + OP2(SLJIT_ADD, STACK_TOP, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, SLJIT_IMM, (framesize + 1) * sizeof(sljit_sw)); + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), (extrasize - 2) * sizeof(sljit_sw)); + } + else + { + /* We don't need to keep the STR_PTR, only the previous private_data_ptr. */ + OP2(SLJIT_ADD, STACK_TOP, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, SLJIT_IMM, (framesize + 2) * sizeof(sljit_sw)); + if (extrasize == 2) + { + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + if (bra == OP_BRAMINZERO) + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); + } + else + { + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), 0); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), bra == OP_BRAZERO ? STR_PTR : SLJIT_IMM, 0); + } + } + } + + if (bra == OP_BRAZERO) + { + backtrack->matchingpath = LABEL(); + SET_LABEL(jump, backtrack->matchingpath); + } + else if (bra == OP_BRAMINZERO) + { + JUMPTO(SLJIT_JUMP, backtrack->matchingpath); + JUMPHERE(brajump); + if (framesize >= 0) + { + OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr); + add_jump(compiler, &common->revertframes, JUMP(SLJIT_FAST_CALL)); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, SLJIT_MEM1(STACK_TOP), framesize * sizeof(sljit_sw)); + } + set_jumps(backtrack->common.topbacktracks, LABEL()); + } + } +else + { + /* AssertNot is successful. */ + if (framesize < 0) + { + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + if (bra != OP_BRA) + { + if (extrasize == 2) + free_stack(common, 1); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); + } + else + free_stack(common, extrasize); + } + else + { + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(extrasize - 1)); + /* The topmost item should be 0. */ + if (bra != OP_BRA) + { + free_stack(common, framesize + extrasize - 1); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); + } + else + free_stack(common, framesize + extrasize); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, TMP1, 0); + } + + if (bra == OP_BRAZERO) + backtrack->matchingpath = LABEL(); + else if (bra == OP_BRAMINZERO) + { + JUMPTO(SLJIT_JUMP, backtrack->matchingpath); + JUMPHERE(brajump); + } + + if (bra != OP_BRA) + { + SLJIT_ASSERT(found == &backtrack->common.topbacktracks); + set_jumps(backtrack->common.topbacktracks, LABEL()); + backtrack->common.topbacktracks = NULL; + } + } + +if (opcode == OP_ASSERT_NOT || opcode == OP_ASSERTBACK_NOT) + { + common->local_exit = save_local_exit; + common->quit_label = save_quit_label; + common->quit = save_quit; + } +common->positive_assert = save_positive_assert; +common->then_trap = save_then_trap; +common->accept_label = save_accept_label; +common->positive_assert_quit = save_positive_assert_quit; +common->accept = save_accept; +return cc + 1 + LINK_SIZE; +} + +static SLJIT_INLINE void match_once_common(compiler_common *common, pcre_uchar ket, int framesize, int private_data_ptr, BOOL has_alternatives, BOOL needs_control_head) +{ +DEFINE_COMPILER; +int stacksize; + +if (framesize < 0) + { + if (framesize == no_frame) + OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr); + else + { + stacksize = needs_control_head ? 1 : 0; + if (ket != OP_KET || has_alternatives) + stacksize++; + free_stack(common, stacksize); + } + + if (needs_control_head) + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), (ket != OP_KET || has_alternatives) ? sizeof(sljit_sw) : 0); + + /* TMP2 which is set here used by OP_KETRMAX below. */ + if (ket == OP_KETRMAX) + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), 0); + else if (ket == OP_KETRMIN) + { + /* Move the STR_PTR to the private_data_ptr. */ + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, SLJIT_MEM1(STACK_TOP), 0); + } + } +else + { + stacksize = (ket != OP_KET || has_alternatives) ? 2 : 1; + OP2(SLJIT_ADD, STACK_TOP, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, SLJIT_IMM, (framesize + stacksize) * sizeof(sljit_sw)); + if (needs_control_head) + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), 0); + + if (ket == OP_KETRMAX) + { + /* TMP2 which is set here used by OP_KETRMAX below. */ + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + } + } +if (needs_control_head) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr, TMP1, 0); +} + +static SLJIT_INLINE int match_capture_common(compiler_common *common, int stacksize, int offset, int private_data_ptr) +{ +DEFINE_COMPILER; + +if (common->capture_last_ptr != 0) + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->capture_last_ptr); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->capture_last_ptr, SLJIT_IMM, offset >> 1); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), TMP1, 0); + stacksize++; + } +if (common->optimized_cbracket[offset >> 1] == 0) + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset)); + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset + 1)); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), TMP1, 0); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize + 1), TMP2, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset + 1), STR_PTR, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset), TMP1, 0); + stacksize += 2; + } +return stacksize; +} + +/* + Handling bracketed expressions is probably the most complex part. + + Stack layout naming characters: + S - Push the current STR_PTR + 0 - Push a 0 (NULL) + A - Push the current STR_PTR. Needed for restoring the STR_PTR + before the next alternative. Not pushed if there are no alternatives. + M - Any values pushed by the current alternative. Can be empty, or anything. + C - Push the previous OVECTOR(i), OVECTOR(i+1) and OVECTOR_PRIV(i) to the stack. + L - Push the previous local (pointed by localptr) to the stack + () - opional values stored on the stack + ()* - optonal, can be stored multiple times + + The following list shows the regular expression templates, their PCRE byte codes + and stack layout supported by pcre-sljit. + + (?:) OP_BRA | OP_KET A M + () OP_CBRA | OP_KET C M + (?:)+ OP_BRA | OP_KETRMAX 0 A M S ( A M S )* + OP_SBRA | OP_KETRMAX 0 L M S ( L M S )* + (?:)+? OP_BRA | OP_KETRMIN 0 A M S ( A M S )* + OP_SBRA | OP_KETRMIN 0 L M S ( L M S )* + ()+ OP_CBRA | OP_KETRMAX 0 C M S ( C M S )* + OP_SCBRA | OP_KETRMAX 0 C M S ( C M S )* + ()+? OP_CBRA | OP_KETRMIN 0 C M S ( C M S )* + OP_SCBRA | OP_KETRMIN 0 C M S ( C M S )* + (?:)? OP_BRAZERO | OP_BRA | OP_KET S ( A M 0 ) + (?:)?? OP_BRAMINZERO | OP_BRA | OP_KET S ( A M 0 ) + ()? OP_BRAZERO | OP_CBRA | OP_KET S ( C M 0 ) + ()?? OP_BRAMINZERO | OP_CBRA | OP_KET S ( C M 0 ) + (?:)* OP_BRAZERO | OP_BRA | OP_KETRMAX S 0 ( A M S )* + OP_BRAZERO | OP_SBRA | OP_KETRMAX S 0 ( L M S )* + (?:)*? OP_BRAMINZERO | OP_BRA | OP_KETRMIN S 0 ( A M S )* + OP_BRAMINZERO | OP_SBRA | OP_KETRMIN S 0 ( L M S )* + ()* OP_BRAZERO | OP_CBRA | OP_KETRMAX S 0 ( C M S )* + OP_BRAZERO | OP_SCBRA | OP_KETRMAX S 0 ( C M S )* + ()*? OP_BRAMINZERO | OP_CBRA | OP_KETRMIN S 0 ( C M S )* + OP_BRAMINZERO | OP_SCBRA | OP_KETRMIN S 0 ( C M S )* + + + Stack layout naming characters: + A - Push the alternative index (starting from 0) on the stack. + Not pushed if there is no alternatives. + M - Any values pushed by the current alternative. Can be empty, or anything. + + The next list shows the possible content of a bracket: + (|) OP_*BRA | OP_ALT ... M A + (?()|) OP_*COND | OP_ALT M A + (?>|) OP_ONCE | OP_ALT ... [stack trace] M A + (?>|) OP_ONCE_NC | OP_ALT ... [stack trace] M A + Or nothing, if trace is unnecessary +*/ + +static pcre_uchar *compile_bracket_matchingpath(compiler_common *common, pcre_uchar *cc, backtrack_common *parent) +{ +DEFINE_COMPILER; +backtrack_common *backtrack; +pcre_uchar opcode; +int private_data_ptr = 0; +int offset = 0; +int i, stacksize; +int repeat_ptr = 0, repeat_length = 0; +int repeat_type = 0, repeat_count = 0; +pcre_uchar *ccbegin; +pcre_uchar *matchingpath; +pcre_uchar *slot; +pcre_uchar bra = OP_BRA; +pcre_uchar ket; +assert_backtrack *assert; +BOOL has_alternatives; +BOOL needs_control_head = FALSE; +struct sljit_jump *jump; +struct sljit_jump *skip; +struct sljit_label *rmax_label = NULL; +struct sljit_jump *braminzero = NULL; + +PUSH_BACKTRACK(sizeof(bracket_backtrack), cc, NULL); + +if (*cc == OP_BRAZERO || *cc == OP_BRAMINZERO) + { + bra = *cc; + cc++; + opcode = *cc; + } + +opcode = *cc; +ccbegin = cc; +matchingpath = bracketend(cc) - 1 - LINK_SIZE; +ket = *matchingpath; +if (ket == OP_KET && PRIVATE_DATA(matchingpath) != 0) + { + repeat_ptr = PRIVATE_DATA(matchingpath); + repeat_length = PRIVATE_DATA(matchingpath + 1); + repeat_type = PRIVATE_DATA(matchingpath + 2); + repeat_count = PRIVATE_DATA(matchingpath + 3); + SLJIT_ASSERT(repeat_length != 0 && repeat_type != 0 && repeat_count != 0); + if (repeat_type == OP_UPTO) + ket = OP_KETRMAX; + if (repeat_type == OP_MINUPTO) + ket = OP_KETRMIN; + } + +if ((opcode == OP_COND || opcode == OP_SCOND) && cc[1 + LINK_SIZE] == OP_DEF) + { + /* Drop this bracket_backtrack. */ + parent->top = backtrack->prev; + return matchingpath + 1 + LINK_SIZE + repeat_length; + } + +matchingpath = ccbegin + 1 + LINK_SIZE; +SLJIT_ASSERT(ket == OP_KET || ket == OP_KETRMAX || ket == OP_KETRMIN); +SLJIT_ASSERT(!((bra == OP_BRAZERO && ket == OP_KETRMIN) || (bra == OP_BRAMINZERO && ket == OP_KETRMAX))); +cc += GET(cc, 1); + +has_alternatives = *cc == OP_ALT; +if (SLJIT_UNLIKELY(opcode == OP_COND || opcode == OP_SCOND)) + has_alternatives = (*matchingpath == OP_RREF || *matchingpath == OP_DNRREF) ? FALSE : TRUE; + +if (SLJIT_UNLIKELY(opcode == OP_COND) && (*cc == OP_KETRMAX || *cc == OP_KETRMIN)) + opcode = OP_SCOND; +if (SLJIT_UNLIKELY(opcode == OP_ONCE_NC)) + opcode = OP_ONCE; + +if (opcode == OP_CBRA || opcode == OP_SCBRA) + { + /* Capturing brackets has a pre-allocated space. */ + offset = GET2(ccbegin, 1 + LINK_SIZE); + if (common->optimized_cbracket[offset] == 0) + { + private_data_ptr = OVECTOR_PRIV(offset); + offset <<= 1; + } + else + { + offset <<= 1; + private_data_ptr = OVECTOR(offset); + } + BACKTRACK_AS(bracket_backtrack)->private_data_ptr = private_data_ptr; + matchingpath += IMM2_SIZE; + } +else if (opcode == OP_ONCE || opcode == OP_SBRA || opcode == OP_SCOND) + { + /* Other brackets simply allocate the next entry. */ + private_data_ptr = PRIVATE_DATA(ccbegin); + SLJIT_ASSERT(private_data_ptr != 0); + BACKTRACK_AS(bracket_backtrack)->private_data_ptr = private_data_ptr; + if (opcode == OP_ONCE) + BACKTRACK_AS(bracket_backtrack)->u.framesize = get_framesize(common, ccbegin, NULL, FALSE, &needs_control_head); + } + +/* Instructions before the first alternative. */ +stacksize = 0; +if (ket == OP_KETRMAX || (ket == OP_KETRMIN && bra != OP_BRAMINZERO)) + stacksize++; +if (bra == OP_BRAZERO) + stacksize++; + +if (stacksize > 0) + allocate_stack(common, stacksize); + +stacksize = 0; +if (ket == OP_KETRMAX || (ket == OP_KETRMIN && bra != OP_BRAMINZERO)) + { + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), SLJIT_IMM, 0); + stacksize++; + } + +if (bra == OP_BRAZERO) + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), STR_PTR, 0); + +if (bra == OP_BRAMINZERO) + { + /* This is a backtrack path! (Since the try-path of OP_BRAMINZERO matches to the empty string) */ + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + if (ket != OP_KETRMIN) + { + free_stack(common, 1); + braminzero = CMP(SLJIT_C_EQUAL, STR_PTR, 0, SLJIT_IMM, 0); + } + else + { + if (opcode == OP_ONCE || opcode >= OP_SBRA) + { + jump = CMP(SLJIT_C_NOT_EQUAL, STR_PTR, 0, SLJIT_IMM, 0); + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(1)); + /* Nothing stored during the first run. */ + skip = JUMP(SLJIT_JUMP); + JUMPHERE(jump); + /* Checking zero-length iteration. */ + if (opcode != OP_ONCE || BACKTRACK_AS(bracket_backtrack)->u.framesize < 0) + { + /* When we come from outside, private_data_ptr contains the previous STR_PTR. */ + braminzero = CMP(SLJIT_C_EQUAL, STR_PTR, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr); + } + else + { + /* Except when the whole stack frame must be saved. */ + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr); + braminzero = CMP(SLJIT_C_EQUAL, STR_PTR, 0, SLJIT_MEM1(TMP1), (BACKTRACK_AS(bracket_backtrack)->u.framesize + 1) * sizeof(sljit_sw)); + } + JUMPHERE(skip); + } + else + { + jump = CMP(SLJIT_C_NOT_EQUAL, STR_PTR, 0, SLJIT_IMM, 0); + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(1)); + JUMPHERE(jump); + } + } + } + +if (repeat_type != 0) + { + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), repeat_ptr, SLJIT_IMM, repeat_count); + if (repeat_type == OP_EXACT) + rmax_label = LABEL(); + } + +if (ket == OP_KETRMIN) + BACKTRACK_AS(bracket_backtrack)->recursive_matchingpath = LABEL(); + +if (ket == OP_KETRMAX) + { + rmax_label = LABEL(); + if (has_alternatives && opcode != OP_ONCE && opcode < OP_SBRA && repeat_type == 0) + BACKTRACK_AS(bracket_backtrack)->alternative_matchingpath = rmax_label; + } + +/* Handling capturing brackets and alternatives. */ +if (opcode == OP_ONCE) + { + stacksize = 0; + if (needs_control_head) + { + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr); + stacksize++; + } + + if (BACKTRACK_AS(bracket_backtrack)->u.framesize < 0) + { + /* Neither capturing brackets nor recursions are found in the block. */ + if (ket == OP_KETRMIN) + { + stacksize += 2; + if (!needs_control_head) + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr); + } + else + { + if (BACKTRACK_AS(bracket_backtrack)->u.framesize == no_frame) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, STACK_TOP, 0); + if (ket == OP_KETRMAX || has_alternatives) + stacksize++; + } + + if (stacksize > 0) + allocate_stack(common, stacksize); + + stacksize = 0; + if (needs_control_head) + { + stacksize++; + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), TMP2, 0); + } + + if (ket == OP_KETRMIN) + { + if (needs_control_head) + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), STR_PTR, 0); + if (BACKTRACK_AS(bracket_backtrack)->u.framesize == no_frame) + OP2(SLJIT_SUB, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, STACK_TOP, 0, SLJIT_IMM, needs_control_head ? (2 * sizeof(sljit_sw)) : sizeof(sljit_sw)); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize + 1), TMP2, 0); + } + else if (ket == OP_KETRMAX || has_alternatives) + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), STR_PTR, 0); + } + else + { + if (ket != OP_KET || has_alternatives) + stacksize++; + + stacksize += BACKTRACK_AS(bracket_backtrack)->u.framesize + 1; + allocate_stack(common, stacksize); + + if (needs_control_head) + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), TMP2, 0); + + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr); + OP2(SLJIT_SUB, TMP2, 0, STACK_TOP, 0, SLJIT_IMM, stacksize * sizeof(sljit_sw)); + + stacksize = needs_control_head ? 1 : 0; + if (ket != OP_KET || has_alternatives) + { + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), STR_PTR, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, TMP2, 0); + stacksize++; + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), TMP1, 0); + } + else + { + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, TMP2, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), TMP1, 0); + } + init_frame(common, ccbegin, NULL, BACKTRACK_AS(bracket_backtrack)->u.framesize + stacksize, stacksize + 1, FALSE); + } + } +else if (opcode == OP_CBRA || opcode == OP_SCBRA) + { + /* Saving the previous values. */ + if (common->optimized_cbracket[offset >> 1] != 0) + { + SLJIT_ASSERT(private_data_ptr == OVECTOR(offset)); + allocate_stack(common, 2); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr); + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr + sizeof(sljit_sw)); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, STR_PTR, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), TMP1, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(1), TMP2, 0); + } + else + { + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr); + allocate_stack(common, 1); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, STR_PTR, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), TMP2, 0); + } + } +else if (opcode == OP_SBRA || opcode == OP_SCOND) + { + /* Saving the previous value. */ + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr); + allocate_stack(common, 1); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, STR_PTR, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), TMP2, 0); + } +else if (has_alternatives) + { + /* Pushing the starting string pointer. */ + allocate_stack(common, 1); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); + } + +/* Generating code for the first alternative. */ +if (opcode == OP_COND || opcode == OP_SCOND) + { + if (*matchingpath == OP_CREF) + { + SLJIT_ASSERT(has_alternatives); + add_jump(compiler, &(BACKTRACK_AS(bracket_backtrack)->u.condfailed), + CMP(SLJIT_C_EQUAL, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(GET2(matchingpath, 1) << 1), SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(1))); + matchingpath += 1 + IMM2_SIZE; + } + else if (*matchingpath == OP_DNCREF) + { + SLJIT_ASSERT(has_alternatives); + + i = GET2(matchingpath, 1 + IMM2_SIZE); + slot = common->name_table + GET2(matchingpath, 1) * common->name_entry_size; + OP1(SLJIT_MOV, TMP3, 0, STR_PTR, 0); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(1)); + OP2(SLJIT_SUB | SLJIT_SET_E, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(GET2(slot, 0) << 1), TMP1, 0); + slot += common->name_entry_size; + i--; + while (i-- > 0) + { + OP2(SLJIT_SUB, STR_PTR, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(GET2(slot, 0) << 1), TMP1, 0); + OP2(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, STR_PTR, 0); + slot += common->name_entry_size; + } + OP1(SLJIT_MOV, STR_PTR, 0, TMP3, 0); + add_jump(compiler, &(BACKTRACK_AS(bracket_backtrack)->u.condfailed), JUMP(SLJIT_C_ZERO)); + matchingpath += 1 + 2 * IMM2_SIZE; + } + else if (*matchingpath == OP_RREF || *matchingpath == OP_DNRREF) + { + /* Never has other case. */ + BACKTRACK_AS(bracket_backtrack)->u.condfailed = NULL; + SLJIT_ASSERT(!has_alternatives); + + if (*matchingpath == OP_RREF) + { + stacksize = GET2(matchingpath, 1); + if (common->currententry == NULL) + stacksize = 0; + else if (stacksize == RREF_ANY) + stacksize = 1; + else if (common->currententry->start == 0) + stacksize = stacksize == 0; + else + stacksize = stacksize == (int)GET2(common->start, common->currententry->start + 1 + LINK_SIZE); + + if (stacksize != 0) + matchingpath += 1 + IMM2_SIZE; + } + else + { + if (common->currententry == NULL || common->currententry->start == 0) + stacksize = 0; + else + { + stacksize = GET2(matchingpath, 1 + IMM2_SIZE); + slot = common->name_table + GET2(matchingpath, 1) * common->name_entry_size; + i = (int)GET2(common->start, common->currententry->start + 1 + LINK_SIZE); + while (stacksize > 0) + { + if ((int)GET2(slot, 0) == i) + break; + slot += common->name_entry_size; + stacksize--; + } + } + + if (stacksize != 0) + matchingpath += 1 + 2 * IMM2_SIZE; + } + + /* The stacksize == 0 is a common "else" case. */ + if (stacksize == 0) + { + if (*cc == OP_ALT) + { + matchingpath = cc + 1 + LINK_SIZE; + cc += GET(cc, 1); + } + else + matchingpath = cc; + } + } + else + { + SLJIT_ASSERT(has_alternatives && *matchingpath >= OP_ASSERT && *matchingpath <= OP_ASSERTBACK_NOT); + /* Similar code as PUSH_BACKTRACK macro. */ + assert = sljit_alloc_memory(compiler, sizeof(assert_backtrack)); + if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) + return NULL; + memset(assert, 0, sizeof(assert_backtrack)); + assert->common.cc = matchingpath; + BACKTRACK_AS(bracket_backtrack)->u.assert = assert; + matchingpath = compile_assert_matchingpath(common, matchingpath, assert, TRUE); + } + } + +compile_matchingpath(common, matchingpath, cc, backtrack); +if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) + return NULL; + +if (opcode == OP_ONCE) + match_once_common(common, ket, BACKTRACK_AS(bracket_backtrack)->u.framesize, private_data_ptr, has_alternatives, needs_control_head); + +stacksize = 0; +if (repeat_type == OP_MINUPTO) + { + /* We need to preserve the counter. TMP2 will be used below. */ + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), repeat_ptr); + stacksize++; + } +if (ket != OP_KET || bra != OP_BRA) + stacksize++; +if (offset != 0) + { + if (common->capture_last_ptr != 0) + stacksize++; + if (common->optimized_cbracket[offset >> 1] == 0) + stacksize += 2; + } +if (has_alternatives && opcode != OP_ONCE) + stacksize++; + +if (stacksize > 0) + allocate_stack(common, stacksize); + +stacksize = 0; +if (repeat_type == OP_MINUPTO) + { + /* TMP2 was set above. */ + OP2(SLJIT_SUB, SLJIT_MEM1(STACK_TOP), STACK(stacksize), TMP2, 0, SLJIT_IMM, 1); + stacksize++; + } + +if (ket != OP_KET || bra != OP_BRA) + { + if (ket != OP_KET) + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), STR_PTR, 0); + else + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), SLJIT_IMM, 0); + stacksize++; + } + +if (offset != 0) + stacksize = match_capture_common(common, stacksize, offset, private_data_ptr); + +if (has_alternatives) + { + if (opcode != OP_ONCE) + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), SLJIT_IMM, 0); + if (ket != OP_KETRMAX) + BACKTRACK_AS(bracket_backtrack)->alternative_matchingpath = LABEL(); + } + +/* Must be after the matchingpath label. */ +if (offset != 0 && common->optimized_cbracket[offset >> 1] != 0) + { + SLJIT_ASSERT(private_data_ptr == OVECTOR(offset + 0)); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset + 1), STR_PTR, 0); + } + +if (ket == OP_KETRMAX) + { + if (repeat_type != 0) + { + if (has_alternatives) + BACKTRACK_AS(bracket_backtrack)->alternative_matchingpath = LABEL(); + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_MEM1(SLJIT_LOCALS_REG), repeat_ptr, SLJIT_MEM1(SLJIT_LOCALS_REG), repeat_ptr, SLJIT_IMM, 1); + JUMPTO(SLJIT_C_NOT_ZERO, rmax_label); + /* Drop STR_PTR for greedy plus quantifier. */ + if (opcode != OP_ONCE) + free_stack(common, 1); + } + else if (opcode == OP_ONCE || opcode >= OP_SBRA) + { + if (has_alternatives) + BACKTRACK_AS(bracket_backtrack)->alternative_matchingpath = LABEL(); + /* Checking zero-length iteration. */ + if (opcode != OP_ONCE) + { + CMPTO(SLJIT_C_NOT_EQUAL, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, STR_PTR, 0, rmax_label); + /* Drop STR_PTR for greedy plus quantifier. */ + if (bra != OP_BRAZERO) + free_stack(common, 1); + } + else + /* TMP2 must contain the starting STR_PTR. */ + CMPTO(SLJIT_C_NOT_EQUAL, TMP2, 0, STR_PTR, 0, rmax_label); + } + else + JUMPTO(SLJIT_JUMP, rmax_label); + BACKTRACK_AS(bracket_backtrack)->recursive_matchingpath = LABEL(); + } + +if (repeat_type == OP_EXACT) + { + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_MEM1(SLJIT_LOCALS_REG), repeat_ptr, SLJIT_MEM1(SLJIT_LOCALS_REG), repeat_ptr, SLJIT_IMM, 1); + JUMPTO(SLJIT_C_NOT_ZERO, rmax_label); + } +else if (repeat_type == OP_UPTO) + { + /* We need to preserve the counter. */ + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), repeat_ptr); + allocate_stack(common, 1); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), TMP2, 0); + } + +if (bra == OP_BRAZERO) + BACKTRACK_AS(bracket_backtrack)->zero_matchingpath = LABEL(); + +if (bra == OP_BRAMINZERO) + { + /* This is a backtrack path! (From the viewpoint of OP_BRAMINZERO) */ + JUMPTO(SLJIT_JUMP, ((braminzero_backtrack *)parent)->matchingpath); + if (braminzero != NULL) + { + JUMPHERE(braminzero); + /* We need to release the end pointer to perform the + backtrack for the zero-length iteration. When + framesize is < 0, OP_ONCE will do the release itself. */ + if (opcode == OP_ONCE && BACKTRACK_AS(bracket_backtrack)->u.framesize >= 0) + { + OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr); + add_jump(compiler, &common->revertframes, JUMP(SLJIT_FAST_CALL)); + } + else if (ket == OP_KETRMIN && opcode != OP_ONCE) + free_stack(common, 1); + } + /* Continue to the normal backtrack. */ + } + +if ((ket != OP_KET && bra != OP_BRAMINZERO) || bra == OP_BRAZERO) + count_match(common); + +/* Skip the other alternatives. */ +while (*cc == OP_ALT) + cc += GET(cc, 1); +cc += 1 + LINK_SIZE; + +/* Temporarily encoding the needs_control_head in framesize. */ +if (opcode == OP_ONCE) + BACKTRACK_AS(bracket_backtrack)->u.framesize = (BACKTRACK_AS(bracket_backtrack)->u.framesize << 1) | (needs_control_head ? 1 : 0); +return cc + repeat_length; +} + +static pcre_uchar *compile_bracketpos_matchingpath(compiler_common *common, pcre_uchar *cc, backtrack_common *parent) +{ +DEFINE_COMPILER; +backtrack_common *backtrack; +pcre_uchar opcode; +int private_data_ptr; +int cbraprivptr = 0; +BOOL needs_control_head; +int framesize; +int stacksize; +int offset = 0; +BOOL zero = FALSE; +pcre_uchar *ccbegin = NULL; +int stack; /* Also contains the offset of control head. */ +struct sljit_label *loop = NULL; +struct jump_list *emptymatch = NULL; + +PUSH_BACKTRACK(sizeof(bracketpos_backtrack), cc, NULL); +if (*cc == OP_BRAPOSZERO) + { + zero = TRUE; + cc++; + } + +opcode = *cc; +private_data_ptr = PRIVATE_DATA(cc); +SLJIT_ASSERT(private_data_ptr != 0); +BACKTRACK_AS(bracketpos_backtrack)->private_data_ptr = private_data_ptr; +switch(opcode) + { + case OP_BRAPOS: + case OP_SBRAPOS: + ccbegin = cc + 1 + LINK_SIZE; + break; + + case OP_CBRAPOS: + case OP_SCBRAPOS: + offset = GET2(cc, 1 + LINK_SIZE); + /* This case cannot be optimized in the same was as + normal capturing brackets. */ + SLJIT_ASSERT(common->optimized_cbracket[offset] == 0); + cbraprivptr = OVECTOR_PRIV(offset); + offset <<= 1; + ccbegin = cc + 1 + LINK_SIZE + IMM2_SIZE; + break; + + default: + SLJIT_ASSERT_STOP(); + break; + } + +framesize = get_framesize(common, cc, NULL, FALSE, &needs_control_head); +BACKTRACK_AS(bracketpos_backtrack)->framesize = framesize; +if (framesize < 0) + { + if (offset != 0) + { + stacksize = 2; + if (common->capture_last_ptr != 0) + stacksize++; + } + else + stacksize = 1; + + if (needs_control_head) + stacksize++; + if (!zero) + stacksize++; + + BACKTRACK_AS(bracketpos_backtrack)->stacksize = stacksize; + allocate_stack(common, stacksize); + if (framesize == no_frame) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, STACK_TOP, 0); + + stack = 0; + if (offset != 0) + { + stack = 2; + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset)); + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset + 1)); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), TMP1, 0); + if (common->capture_last_ptr != 0) + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->capture_last_ptr); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(1), TMP2, 0); + if (needs_control_head) + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr); + if (common->capture_last_ptr != 0) + { + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(2), TMP1, 0); + stack = 3; + } + } + else + { + if (needs_control_head) + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); + stack = 1; + } + + if (needs_control_head) + stack++; + if (!zero) + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stack), SLJIT_IMM, 1); + if (needs_control_head) + { + stack--; + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stack), TMP2, 0); + } + } +else + { + stacksize = framesize + 1; + if (!zero) + stacksize++; + if (needs_control_head) + stacksize++; + if (offset == 0) + stacksize++; + BACKTRACK_AS(bracketpos_backtrack)->stacksize = stacksize; + + allocate_stack(common, stacksize); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr); + if (needs_control_head) + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr); + OP2(SLJIT_SUB, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, STACK_TOP, 0, SLJIT_IMM, -STACK(stacksize - 1)); + + stack = 0; + if (!zero) + { + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 1); + stack = 1; + } + if (needs_control_head) + { + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stack), TMP2, 0); + stack++; + } + if (offset == 0) + { + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stack), STR_PTR, 0); + stack++; + } + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stack), TMP1, 0); + init_frame(common, cc, NULL, stacksize - 1, stacksize - framesize, FALSE); + stack -= 1 + (offset == 0); + } + +if (offset != 0) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), cbraprivptr, STR_PTR, 0); + +loop = LABEL(); +while (*cc != OP_KETRPOS) + { + backtrack->top = NULL; + backtrack->topbacktracks = NULL; + cc += GET(cc, 1); + + compile_matchingpath(common, ccbegin, cc, backtrack); + if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) + return NULL; + + if (framesize < 0) + { + if (framesize == no_frame) + OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr); + + if (offset != 0) + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), cbraprivptr); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset + 1), STR_PTR, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), cbraprivptr, STR_PTR, 0); + if (common->capture_last_ptr != 0) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->capture_last_ptr, SLJIT_IMM, offset >> 1); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset), TMP1, 0); + } + else + { + if (opcode == OP_SBRAPOS) + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); + } + + if (opcode == OP_SBRAPOS || opcode == OP_SCBRAPOS) + add_jump(compiler, &emptymatch, CMP(SLJIT_C_EQUAL, TMP1, 0, STR_PTR, 0)); + + if (!zero) + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize - 1), SLJIT_IMM, 0); + } + else + { + if (offset != 0) + { + OP2(SLJIT_ADD, STACK_TOP, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, SLJIT_IMM, stacksize * sizeof(sljit_sw)); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), cbraprivptr); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset + 1), STR_PTR, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), cbraprivptr, STR_PTR, 0); + if (common->capture_last_ptr != 0) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->capture_last_ptr, SLJIT_IMM, offset >> 1); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset), TMP1, 0); + } + else + { + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr); + OP2(SLJIT_ADD, STACK_TOP, 0, TMP2, 0, SLJIT_IMM, stacksize * sizeof(sljit_sw)); + if (opcode == OP_SBRAPOS) + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP2), (framesize + 1) * sizeof(sljit_sw)); + OP1(SLJIT_MOV, SLJIT_MEM1(TMP2), (framesize + 1) * sizeof(sljit_sw), STR_PTR, 0); + } + + if (opcode == OP_SBRAPOS || opcode == OP_SCBRAPOS) + add_jump(compiler, &emptymatch, CMP(SLJIT_C_EQUAL, TMP1, 0, STR_PTR, 0)); + + if (!zero) + { + if (framesize < 0) + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize - 1), SLJIT_IMM, 0); + else + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); + } + } + + if (needs_control_head) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr, SLJIT_MEM1(STACK_TOP), STACK(stack)); + + JUMPTO(SLJIT_JUMP, loop); + flush_stubs(common); + + compile_backtrackingpath(common, backtrack->top); + if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) + return NULL; + set_jumps(backtrack->topbacktracks, LABEL()); + + if (framesize < 0) + { + if (offset != 0) + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), cbraprivptr); + else + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + } + else + { + if (offset != 0) + { + /* Last alternative. */ + if (*cc == OP_KETRPOS) + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr); + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), cbraprivptr); + } + else + { + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr); + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(TMP2), (framesize + 1) * sizeof(sljit_sw)); + } + } + + if (*cc == OP_KETRPOS) + break; + ccbegin = cc + 1 + LINK_SIZE; + } + +/* We don't have to restore the control head in case of a failed match. */ + +backtrack->topbacktracks = NULL; +if (!zero) + { + if (framesize < 0) + add_jump(compiler, &backtrack->topbacktracks, CMP(SLJIT_C_NOT_EQUAL, SLJIT_MEM1(STACK_TOP), STACK(stacksize - 1), SLJIT_IMM, 0)); + else /* TMP2 is set to [private_data_ptr] above. */ + add_jump(compiler, &backtrack->topbacktracks, CMP(SLJIT_C_NOT_EQUAL, SLJIT_MEM1(TMP2), (stacksize - 1) * sizeof(sljit_sw), SLJIT_IMM, 0)); + } + +/* None of them matched. */ +set_jumps(emptymatch, LABEL()); +count_match(common); +return cc + 1 + LINK_SIZE; +} + +static SLJIT_INLINE pcre_uchar *get_iterator_parameters(compiler_common *common, pcre_uchar *cc, pcre_uchar *opcode, pcre_uchar *type, int *max, int *min, pcre_uchar **end) +{ +int class_len; + +*opcode = *cc; +if (*opcode >= OP_STAR && *opcode <= OP_POSUPTO) + { + cc++; + *type = OP_CHAR; + } +else if (*opcode >= OP_STARI && *opcode <= OP_POSUPTOI) + { + cc++; + *type = OP_CHARI; + *opcode -= OP_STARI - OP_STAR; + } +else if (*opcode >= OP_NOTSTAR && *opcode <= OP_NOTPOSUPTO) + { + cc++; + *type = OP_NOT; + *opcode -= OP_NOTSTAR - OP_STAR; + } +else if (*opcode >= OP_NOTSTARI && *opcode <= OP_NOTPOSUPTOI) + { + cc++; + *type = OP_NOTI; + *opcode -= OP_NOTSTARI - OP_STAR; + } +else if (*opcode >= OP_TYPESTAR && *opcode <= OP_TYPEPOSUPTO) + { + cc++; + *opcode -= OP_TYPESTAR - OP_STAR; + *type = 0; + } +else + { + SLJIT_ASSERT(*opcode == OP_CLASS || *opcode == OP_NCLASS || *opcode == OP_XCLASS); + *type = *opcode; + cc++; + class_len = (*type < OP_XCLASS) ? (int)(1 + (32 / sizeof(pcre_uchar))) : GET(cc, 0); + *opcode = cc[class_len - 1]; + if (*opcode >= OP_CRSTAR && *opcode <= OP_CRMINQUERY) + { + *opcode -= OP_CRSTAR - OP_STAR; + if (end != NULL) + *end = cc + class_len; + } + else if (*opcode >= OP_CRPOSSTAR && *opcode <= OP_CRPOSQUERY) + { + *opcode -= OP_CRPOSSTAR - OP_POSSTAR; + if (end != NULL) + *end = cc + class_len; + } + else + { + SLJIT_ASSERT(*opcode == OP_CRRANGE || *opcode == OP_CRMINRANGE || *opcode == OP_CRPOSRANGE); + *max = GET2(cc, (class_len + IMM2_SIZE)); + *min = GET2(cc, class_len); + + if (*min == 0) + { + SLJIT_ASSERT(*max != 0); + *opcode = (*opcode == OP_CRRANGE) ? OP_UPTO : (*opcode == OP_CRMINRANGE ? OP_MINUPTO : OP_POSUPTO); + } + if (*max == *min) + *opcode = OP_EXACT; + + if (end != NULL) + *end = cc + class_len + 2 * IMM2_SIZE; + } + return cc; + } + +if (*opcode == OP_UPTO || *opcode == OP_MINUPTO || *opcode == OP_EXACT || *opcode == OP_POSUPTO) + { + *max = GET2(cc, 0); + cc += IMM2_SIZE; + } + +if (*type == 0) + { + *type = *cc; + if (end != NULL) + *end = next_opcode(common, cc); + cc++; + return cc; + } + +if (end != NULL) + { + *end = cc + 1; +#ifdef SUPPORT_UTF + if (common->utf && HAS_EXTRALEN(*cc)) *end += GET_EXTRALEN(*cc); +#endif + } +return cc; +} + +static pcre_uchar *compile_iterator_matchingpath(compiler_common *common, pcre_uchar *cc, backtrack_common *parent) +{ +DEFINE_COMPILER; +backtrack_common *backtrack; +pcre_uchar opcode; +pcre_uchar type; +int max = -1, min = -1; +pcre_uchar* end; +jump_list *nomatch = NULL; +struct sljit_jump *jump = NULL; +struct sljit_label *label; +int private_data_ptr = PRIVATE_DATA(cc); +int base = (private_data_ptr == 0) ? SLJIT_MEM1(STACK_TOP) : SLJIT_MEM1(SLJIT_LOCALS_REG); +int offset0 = (private_data_ptr == 0) ? STACK(0) : private_data_ptr; +int offset1 = (private_data_ptr == 0) ? STACK(1) : private_data_ptr + (int)sizeof(sljit_sw); +int tmp_base, tmp_offset; + +PUSH_BACKTRACK(sizeof(iterator_backtrack), cc, NULL); + +cc = get_iterator_parameters(common, cc, &opcode, &type, &max, &min, &end); + +switch(type) + { + case OP_NOT_DIGIT: + case OP_DIGIT: + case OP_NOT_WHITESPACE: + case OP_WHITESPACE: + case OP_NOT_WORDCHAR: + case OP_WORDCHAR: + case OP_ANY: + case OP_ALLANY: + case OP_ANYBYTE: + case OP_ANYNL: + case OP_NOT_HSPACE: + case OP_HSPACE: + case OP_NOT_VSPACE: + case OP_VSPACE: + case OP_CHAR: + case OP_CHARI: + case OP_NOT: + case OP_NOTI: + case OP_CLASS: + case OP_NCLASS: + tmp_base = TMP3; + tmp_offset = 0; + break; + + default: + SLJIT_ASSERT_STOP(); + /* Fall through. */ + + case OP_EXTUNI: + case OP_XCLASS: + case OP_NOTPROP: + case OP_PROP: + tmp_base = SLJIT_MEM1(SLJIT_LOCALS_REG); + tmp_offset = POSSESSIVE0; + break; + } + +switch(opcode) + { + case OP_STAR: + case OP_PLUS: + case OP_UPTO: + case OP_CRRANGE: + if (type == OP_ANYNL || type == OP_EXTUNI) + { + SLJIT_ASSERT(private_data_ptr == 0); + if (opcode == OP_STAR || opcode == OP_UPTO) + { + allocate_stack(common, 2); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(1), SLJIT_IMM, 0); + } + else + { + allocate_stack(common, 1); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); + } + + if (opcode == OP_UPTO || opcode == OP_CRRANGE) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), POSSESSIVE0, SLJIT_IMM, 0); + + label = LABEL(); + compile_char1_matchingpath(common, type, cc, &backtrack->topbacktracks); + if (opcode == OP_UPTO || opcode == OP_CRRANGE) + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), POSSESSIVE0); + OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, SLJIT_IMM, 1); + if (opcode == OP_CRRANGE && min > 0) + CMPTO(SLJIT_C_LESS, TMP1, 0, SLJIT_IMM, min, label); + if (opcode == OP_UPTO || (opcode == OP_CRRANGE && max > 0)) + jump = CMP(SLJIT_C_GREATER_EQUAL, TMP1, 0, SLJIT_IMM, max); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), POSSESSIVE0, TMP1, 0); + } + + /* We cannot use TMP3 because of this allocate_stack. */ + allocate_stack(common, 1); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); + JUMPTO(SLJIT_JUMP, label); + if (jump != NULL) + JUMPHERE(jump); + } + else + { + if (opcode == OP_PLUS) + compile_char1_matchingpath(common, type, cc, &backtrack->topbacktracks); + if (private_data_ptr == 0) + allocate_stack(common, 2); + OP1(SLJIT_MOV, base, offset0, STR_PTR, 0); + if (opcode <= OP_PLUS) + OP1(SLJIT_MOV, base, offset1, STR_PTR, 0); + else + OP1(SLJIT_MOV, base, offset1, SLJIT_IMM, 1); + label = LABEL(); + compile_char1_matchingpath(common, type, cc, &nomatch); + OP1(SLJIT_MOV, base, offset0, STR_PTR, 0); + if (opcode <= OP_PLUS) + JUMPTO(SLJIT_JUMP, label); + else if (opcode == OP_CRRANGE && max == 0) + { + OP2(SLJIT_ADD, base, offset1, base, offset1, SLJIT_IMM, 1); + JUMPTO(SLJIT_JUMP, label); + } + else + { + OP1(SLJIT_MOV, TMP1, 0, base, offset1); + OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, SLJIT_IMM, 1); + OP1(SLJIT_MOV, base, offset1, TMP1, 0); + CMPTO(SLJIT_C_LESS, TMP1, 0, SLJIT_IMM, max + 1, label); + } + set_jumps(nomatch, LABEL()); + if (opcode == OP_CRRANGE) + add_jump(compiler, &backtrack->topbacktracks, CMP(SLJIT_C_LESS, base, offset1, SLJIT_IMM, min + 1)); + OP1(SLJIT_MOV, STR_PTR, 0, base, offset0); + } + BACKTRACK_AS(iterator_backtrack)->matchingpath = LABEL(); + break; + + case OP_MINSTAR: + case OP_MINPLUS: + if (opcode == OP_MINPLUS) + compile_char1_matchingpath(common, type, cc, &backtrack->topbacktracks); + if (private_data_ptr == 0) + allocate_stack(common, 1); + OP1(SLJIT_MOV, base, offset0, STR_PTR, 0); + BACKTRACK_AS(iterator_backtrack)->matchingpath = LABEL(); + break; + + case OP_MINUPTO: + case OP_CRMINRANGE: + if (private_data_ptr == 0) + allocate_stack(common, 2); + OP1(SLJIT_MOV, base, offset0, STR_PTR, 0); + OP1(SLJIT_MOV, base, offset1, SLJIT_IMM, 1); + if (opcode == OP_CRMINRANGE) + add_jump(compiler, &backtrack->topbacktracks, JUMP(SLJIT_JUMP)); + BACKTRACK_AS(iterator_backtrack)->matchingpath = LABEL(); + break; + + case OP_QUERY: + case OP_MINQUERY: + if (private_data_ptr == 0) + allocate_stack(common, 1); + OP1(SLJIT_MOV, base, offset0, STR_PTR, 0); + if (opcode == OP_QUERY) + compile_char1_matchingpath(common, type, cc, &backtrack->topbacktracks); + BACKTRACK_AS(iterator_backtrack)->matchingpath = LABEL(); + break; + + case OP_EXACT: + OP1(SLJIT_MOV, tmp_base, tmp_offset, SLJIT_IMM, max); + label = LABEL(); + compile_char1_matchingpath(common, type, cc, &backtrack->topbacktracks); + OP2(SLJIT_SUB | SLJIT_SET_E, tmp_base, tmp_offset, tmp_base, tmp_offset, SLJIT_IMM, 1); + JUMPTO(SLJIT_C_NOT_ZERO, label); + break; + + case OP_POSSTAR: + case OP_POSPLUS: + case OP_POSUPTO: + if (opcode == OP_POSPLUS) + compile_char1_matchingpath(common, type, cc, &backtrack->topbacktracks); + if (opcode == OP_POSUPTO) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), POSSESSIVE1, SLJIT_IMM, max); + OP1(SLJIT_MOV, tmp_base, tmp_offset, STR_PTR, 0); + label = LABEL(); + compile_char1_matchingpath(common, type, cc, &nomatch); + OP1(SLJIT_MOV, tmp_base, tmp_offset, STR_PTR, 0); + if (opcode != OP_POSUPTO) + JUMPTO(SLJIT_JUMP, label); + else + { + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_MEM1(SLJIT_LOCALS_REG), POSSESSIVE1, SLJIT_MEM1(SLJIT_LOCALS_REG), POSSESSIVE1, SLJIT_IMM, 1); + JUMPTO(SLJIT_C_NOT_ZERO, label); + } + set_jumps(nomatch, LABEL()); + OP1(SLJIT_MOV, STR_PTR, 0, tmp_base, tmp_offset); + break; + + case OP_POSQUERY: + OP1(SLJIT_MOV, tmp_base, tmp_offset, STR_PTR, 0); + compile_char1_matchingpath(common, type, cc, &nomatch); + OP1(SLJIT_MOV, tmp_base, tmp_offset, STR_PTR, 0); + set_jumps(nomatch, LABEL()); + OP1(SLJIT_MOV, STR_PTR, 0, tmp_base, tmp_offset); + break; + + case OP_CRPOSRANGE: + /* Combination of OP_EXACT and OP_POSSTAR or OP_POSUPTO */ + OP1(SLJIT_MOV, tmp_base, tmp_offset, SLJIT_IMM, min); + label = LABEL(); + compile_char1_matchingpath(common, type, cc, &backtrack->topbacktracks); + OP2(SLJIT_SUB | SLJIT_SET_E, tmp_base, tmp_offset, tmp_base, tmp_offset, SLJIT_IMM, 1); + JUMPTO(SLJIT_C_NOT_ZERO, label); + + if (max != 0) + { + SLJIT_ASSERT(max - min > 0); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), POSSESSIVE1, SLJIT_IMM, max - min); + } + OP1(SLJIT_MOV, tmp_base, tmp_offset, STR_PTR, 0); + label = LABEL(); + compile_char1_matchingpath(common, type, cc, &nomatch); + OP1(SLJIT_MOV, tmp_base, tmp_offset, STR_PTR, 0); + if (max == 0) + JUMPTO(SLJIT_JUMP, label); + else + { + OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_MEM1(SLJIT_LOCALS_REG), POSSESSIVE1, SLJIT_MEM1(SLJIT_LOCALS_REG), POSSESSIVE1, SLJIT_IMM, 1); + JUMPTO(SLJIT_C_NOT_ZERO, label); + } + set_jumps(nomatch, LABEL()); + OP1(SLJIT_MOV, STR_PTR, 0, tmp_base, tmp_offset); + break; + + default: + SLJIT_ASSERT_STOP(); + break; + } + +count_match(common); +return end; +} + +static SLJIT_INLINE pcre_uchar *compile_fail_accept_matchingpath(compiler_common *common, pcre_uchar *cc, backtrack_common *parent) +{ +DEFINE_COMPILER; +backtrack_common *backtrack; + +PUSH_BACKTRACK(sizeof(backtrack_common), cc, NULL); + +if (*cc == OP_FAIL) + { + add_jump(compiler, &backtrack->topbacktracks, JUMP(SLJIT_JUMP)); + return cc + 1; + } + +if (*cc == OP_ASSERT_ACCEPT || common->currententry != NULL || !common->might_be_empty) + { + /* No need to check notempty conditions. */ + if (common->accept_label == NULL) + add_jump(compiler, &common->accept, JUMP(SLJIT_JUMP)); + else + JUMPTO(SLJIT_JUMP, common->accept_label); + return cc + 1; + } + +if (common->accept_label == NULL) + add_jump(compiler, &common->accept, CMP(SLJIT_C_NOT_EQUAL, STR_PTR, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(0))); +else + CMPTO(SLJIT_C_NOT_EQUAL, STR_PTR, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(0), common->accept_label); +OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); +OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, notempty)); +add_jump(compiler, &backtrack->topbacktracks, CMP(SLJIT_C_NOT_EQUAL, TMP2, 0, SLJIT_IMM, 0)); +OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, notempty_atstart)); +if (common->accept_label == NULL) + add_jump(compiler, &common->accept, CMP(SLJIT_C_EQUAL, TMP2, 0, SLJIT_IMM, 0)); +else + CMPTO(SLJIT_C_EQUAL, TMP2, 0, SLJIT_IMM, 0, common->accept_label); +OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, str)); +if (common->accept_label == NULL) + add_jump(compiler, &common->accept, CMP(SLJIT_C_NOT_EQUAL, TMP2, 0, STR_PTR, 0)); +else + CMPTO(SLJIT_C_NOT_EQUAL, TMP2, 0, STR_PTR, 0, common->accept_label); +add_jump(compiler, &backtrack->topbacktracks, JUMP(SLJIT_JUMP)); +return cc + 1; +} + +static SLJIT_INLINE pcre_uchar *compile_close_matchingpath(compiler_common *common, pcre_uchar *cc) +{ +DEFINE_COMPILER; +int offset = GET2(cc, 1); +BOOL optimized_cbracket = common->optimized_cbracket[offset] != 0; + +/* Data will be discarded anyway... */ +if (common->currententry != NULL) + return cc + 1 + IMM2_SIZE; + +if (!optimized_cbracket) + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR_PRIV(offset)); +offset <<= 1; +OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset + 1), STR_PTR, 0); +if (!optimized_cbracket) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset), TMP1, 0); +return cc + 1 + IMM2_SIZE; +} + +static SLJIT_INLINE pcre_uchar *compile_control_verb_matchingpath(compiler_common *common, pcre_uchar *cc, backtrack_common *parent) +{ +DEFINE_COMPILER; +backtrack_common *backtrack; +pcre_uchar opcode = *cc; +pcre_uchar *ccend = cc + 1; + +if (opcode == OP_PRUNE_ARG || opcode == OP_SKIP_ARG || opcode == OP_THEN_ARG) + ccend += 2 + cc[1]; + +PUSH_BACKTRACK(sizeof(backtrack_common), cc, NULL); + +if (opcode == OP_SKIP) + { + allocate_stack(common, 1); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); + return ccend; + } + +if (opcode == OP_PRUNE_ARG || opcode == OP_THEN_ARG) + { + OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); + OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, (sljit_sw)(cc + 2)); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->mark_ptr, TMP2, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, mark_ptr), TMP2, 0); + } + +return ccend; +} + +static pcre_uchar then_trap_opcode[1] = { OP_THEN_TRAP }; + +static SLJIT_INLINE void compile_then_trap_matchingpath(compiler_common *common, pcre_uchar *cc, pcre_uchar *ccend, backtrack_common *parent) +{ +DEFINE_COMPILER; +backtrack_common *backtrack; +BOOL needs_control_head; +int size; + +PUSH_BACKTRACK_NOVALUE(sizeof(then_trap_backtrack), cc); +common->then_trap = BACKTRACK_AS(then_trap_backtrack); +BACKTRACK_AS(then_trap_backtrack)->common.cc = then_trap_opcode; +BACKTRACK_AS(then_trap_backtrack)->start = (sljit_sw)(cc - common->start); +BACKTRACK_AS(then_trap_backtrack)->framesize = get_framesize(common, cc, ccend, FALSE, &needs_control_head); + +size = BACKTRACK_AS(then_trap_backtrack)->framesize; +size = 3 + (size < 0 ? 0 : size); + +OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr); +allocate_stack(common, size); +if (size > 3) + OP2(SLJIT_SUB, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr, STACK_TOP, 0, SLJIT_IMM, (size - 3) * sizeof(sljit_sw)); +else + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr, STACK_TOP, 0); +OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(size - 1), SLJIT_IMM, BACKTRACK_AS(then_trap_backtrack)->start); +OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(size - 2), SLJIT_IMM, type_then_trap); +OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(size - 3), TMP2, 0); + +size = BACKTRACK_AS(then_trap_backtrack)->framesize; +if (size >= 0) + init_frame(common, cc, ccend, size - 1, 0, FALSE); +} + +static void compile_matchingpath(compiler_common *common, pcre_uchar *cc, pcre_uchar *ccend, backtrack_common *parent) +{ +DEFINE_COMPILER; +backtrack_common *backtrack; +BOOL has_then_trap = FALSE; +then_trap_backtrack *save_then_trap = NULL; + +SLJIT_ASSERT(*ccend == OP_END || (*ccend >= OP_ALT && *ccend <= OP_KETRPOS)); + +if (common->has_then && common->then_offsets[cc - common->start] != 0) + { + SLJIT_ASSERT(*ccend != OP_END && common->control_head_ptr != 0); + has_then_trap = TRUE; + save_then_trap = common->then_trap; + /* Tail item on backtrack. */ + compile_then_trap_matchingpath(common, cc, ccend, parent); + } + +while (cc < ccend) + { + switch(*cc) + { + case OP_SOD: + case OP_SOM: + case OP_NOT_WORD_BOUNDARY: + case OP_WORD_BOUNDARY: + case OP_NOT_DIGIT: + case OP_DIGIT: + case OP_NOT_WHITESPACE: + case OP_WHITESPACE: + case OP_NOT_WORDCHAR: + case OP_WORDCHAR: + case OP_ANY: + case OP_ALLANY: + case OP_ANYBYTE: + case OP_NOTPROP: + case OP_PROP: + case OP_ANYNL: + case OP_NOT_HSPACE: + case OP_HSPACE: + case OP_NOT_VSPACE: + case OP_VSPACE: + case OP_EXTUNI: + case OP_EODN: + case OP_EOD: + case OP_CIRC: + case OP_CIRCM: + case OP_DOLL: + case OP_DOLLM: + case OP_NOT: + case OP_NOTI: + case OP_REVERSE: + cc = compile_char1_matchingpath(common, *cc, cc + 1, parent->top != NULL ? &parent->top->nextbacktracks : &parent->topbacktracks); + break; + + case OP_SET_SOM: + PUSH_BACKTRACK_NOVALUE(sizeof(backtrack_common), cc); + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(0)); + allocate_stack(common, 1); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(0), STR_PTR, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), TMP2, 0); + cc++; + break; + + case OP_CHAR: + case OP_CHARI: + if (common->mode == JIT_COMPILE) + cc = compile_charn_matchingpath(common, cc, ccend, parent->top != NULL ? &parent->top->nextbacktracks : &parent->topbacktracks); + else + cc = compile_char1_matchingpath(common, *cc, cc + 1, parent->top != NULL ? &parent->top->nextbacktracks : &parent->topbacktracks); + break; + + case OP_STAR: + case OP_MINSTAR: + case OP_PLUS: + case OP_MINPLUS: + case OP_QUERY: + case OP_MINQUERY: + case OP_UPTO: + case OP_MINUPTO: + case OP_EXACT: + case OP_POSSTAR: + case OP_POSPLUS: + case OP_POSQUERY: + case OP_POSUPTO: + case OP_STARI: + case OP_MINSTARI: + case OP_PLUSI: + case OP_MINPLUSI: + case OP_QUERYI: + case OP_MINQUERYI: + case OP_UPTOI: + case OP_MINUPTOI: + case OP_EXACTI: + case OP_POSSTARI: + case OP_POSPLUSI: + case OP_POSQUERYI: + case OP_POSUPTOI: + case OP_NOTSTAR: + case OP_NOTMINSTAR: + case OP_NOTPLUS: + case OP_NOTMINPLUS: + case OP_NOTQUERY: + case OP_NOTMINQUERY: + case OP_NOTUPTO: + case OP_NOTMINUPTO: + case OP_NOTEXACT: + case OP_NOTPOSSTAR: + case OP_NOTPOSPLUS: + case OP_NOTPOSQUERY: + case OP_NOTPOSUPTO: + case OP_NOTSTARI: + case OP_NOTMINSTARI: + case OP_NOTPLUSI: + case OP_NOTMINPLUSI: + case OP_NOTQUERYI: + case OP_NOTMINQUERYI: + case OP_NOTUPTOI: + case OP_NOTMINUPTOI: + case OP_NOTEXACTI: + case OP_NOTPOSSTARI: + case OP_NOTPOSPLUSI: + case OP_NOTPOSQUERYI: + case OP_NOTPOSUPTOI: + case OP_TYPESTAR: + case OP_TYPEMINSTAR: + case OP_TYPEPLUS: + case OP_TYPEMINPLUS: + case OP_TYPEQUERY: + case OP_TYPEMINQUERY: + case OP_TYPEUPTO: + case OP_TYPEMINUPTO: + case OP_TYPEEXACT: + case OP_TYPEPOSSTAR: + case OP_TYPEPOSPLUS: + case OP_TYPEPOSQUERY: + case OP_TYPEPOSUPTO: + cc = compile_iterator_matchingpath(common, cc, parent); + break; + + case OP_CLASS: + case OP_NCLASS: + if (cc[1 + (32 / sizeof(pcre_uchar))] >= OP_CRSTAR && cc[1 + (32 / sizeof(pcre_uchar))] <= OP_CRPOSRANGE) + cc = compile_iterator_matchingpath(common, cc, parent); + else + cc = compile_char1_matchingpath(common, *cc, cc + 1, parent->top != NULL ? &parent->top->nextbacktracks : &parent->topbacktracks); + break; + +#if defined SUPPORT_UTF || defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + case OP_XCLASS: + if (*(cc + GET(cc, 1)) >= OP_CRSTAR && *(cc + GET(cc, 1)) <= OP_CRPOSRANGE) + cc = compile_iterator_matchingpath(common, cc, parent); + else + cc = compile_char1_matchingpath(common, *cc, cc + 1, parent->top != NULL ? &parent->top->nextbacktracks : &parent->topbacktracks); + break; +#endif + + case OP_REF: + case OP_REFI: + if (cc[1 + IMM2_SIZE] >= OP_CRSTAR && cc[1 + IMM2_SIZE] <= OP_CRPOSRANGE) + cc = compile_ref_iterator_matchingpath(common, cc, parent); + else + { + compile_ref_matchingpath(common, cc, parent->top != NULL ? &parent->top->nextbacktracks : &parent->topbacktracks, TRUE, FALSE); + cc += 1 + IMM2_SIZE; + } + break; + + case OP_DNREF: + case OP_DNREFI: + if (cc[1 + 2 * IMM2_SIZE] >= OP_CRSTAR && cc[1 + 2 * IMM2_SIZE] <= OP_CRPOSRANGE) + cc = compile_ref_iterator_matchingpath(common, cc, parent); + else + { + compile_dnref_search(common, cc, parent->top != NULL ? &parent->top->nextbacktracks : &parent->topbacktracks); + compile_ref_matchingpath(common, cc, parent->top != NULL ? &parent->top->nextbacktracks : &parent->topbacktracks, TRUE, FALSE); + cc += 1 + 2 * IMM2_SIZE; + } + break; + + case OP_RECURSE: + cc = compile_recurse_matchingpath(common, cc, parent); + break; + + case OP_CALLOUT: + cc = compile_callout_matchingpath(common, cc, parent); + break; + + case OP_ASSERT: + case OP_ASSERT_NOT: + case OP_ASSERTBACK: + case OP_ASSERTBACK_NOT: + PUSH_BACKTRACK_NOVALUE(sizeof(assert_backtrack), cc); + cc = compile_assert_matchingpath(common, cc, BACKTRACK_AS(assert_backtrack), FALSE); + break; + + case OP_BRAMINZERO: + PUSH_BACKTRACK_NOVALUE(sizeof(braminzero_backtrack), cc); + cc = bracketend(cc + 1); + if (*(cc - 1 - LINK_SIZE) != OP_KETRMIN) + { + allocate_stack(common, 1); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); + } + else + { + allocate_stack(common, 2); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(1), STR_PTR, 0); + } + BACKTRACK_AS(braminzero_backtrack)->matchingpath = LABEL(); + if (cc[1] > OP_ASSERTBACK_NOT) + count_match(common); + break; + + case OP_ONCE: + case OP_ONCE_NC: + case OP_BRA: + case OP_CBRA: + case OP_COND: + case OP_SBRA: + case OP_SCBRA: + case OP_SCOND: + cc = compile_bracket_matchingpath(common, cc, parent); + break; + + case OP_BRAZERO: + if (cc[1] > OP_ASSERTBACK_NOT) + cc = compile_bracket_matchingpath(common, cc, parent); + else + { + PUSH_BACKTRACK_NOVALUE(sizeof(assert_backtrack), cc); + cc = compile_assert_matchingpath(common, cc, BACKTRACK_AS(assert_backtrack), FALSE); + } + break; + + case OP_BRAPOS: + case OP_CBRAPOS: + case OP_SBRAPOS: + case OP_SCBRAPOS: + case OP_BRAPOSZERO: + cc = compile_bracketpos_matchingpath(common, cc, parent); + break; + + case OP_MARK: + PUSH_BACKTRACK_NOVALUE(sizeof(backtrack_common), cc); + SLJIT_ASSERT(common->mark_ptr != 0); + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->mark_ptr); + allocate_stack(common, common->has_skip_arg ? 5 : 1); + OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(common->has_skip_arg ? 4 : 0), TMP2, 0); + OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, (sljit_sw)(cc + 2)); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->mark_ptr, TMP2, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, mark_ptr), TMP2, 0); + if (common->has_skip_arg) + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr, STACK_TOP, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(1), SLJIT_IMM, type_mark); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(2), SLJIT_IMM, (sljit_sw)(cc + 2)); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(3), STR_PTR, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), TMP1, 0); + } + cc += 1 + 2 + cc[1]; + break; + + case OP_PRUNE: + case OP_PRUNE_ARG: + case OP_SKIP: + case OP_SKIP_ARG: + case OP_THEN: + case OP_THEN_ARG: + case OP_COMMIT: + cc = compile_control_verb_matchingpath(common, cc, parent); + break; + + case OP_FAIL: + case OP_ACCEPT: + case OP_ASSERT_ACCEPT: + cc = compile_fail_accept_matchingpath(common, cc, parent); + break; + + case OP_CLOSE: + cc = compile_close_matchingpath(common, cc); + break; + + case OP_SKIPZERO: + cc = bracketend(cc + 1); + break; + + default: + SLJIT_ASSERT_STOP(); + return; + } + if (cc == NULL) + return; + } + +if (has_then_trap) + { + /* Head item on backtrack. */ + PUSH_BACKTRACK_NOVALUE(sizeof(then_trap_backtrack), cc); + BACKTRACK_AS(then_trap_backtrack)->common.cc = then_trap_opcode; + BACKTRACK_AS(then_trap_backtrack)->then_trap = common->then_trap; + common->then_trap = save_then_trap; + } +SLJIT_ASSERT(cc == ccend); +} + +#undef PUSH_BACKTRACK +#undef PUSH_BACKTRACK_NOVALUE +#undef BACKTRACK_AS + +#define COMPILE_BACKTRACKINGPATH(current) \ + do \ + { \ + compile_backtrackingpath(common, (current)); \ + if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) \ + return; \ + } \ + while (0) + +#define CURRENT_AS(type) ((type *)current) + +static void compile_iterator_backtrackingpath(compiler_common *common, struct backtrack_common *current) +{ +DEFINE_COMPILER; +pcre_uchar *cc = current->cc; +pcre_uchar opcode; +pcre_uchar type; +int max = -1, min = -1; +struct sljit_label *label = NULL; +struct sljit_jump *jump = NULL; +jump_list *jumplist = NULL; +int private_data_ptr = PRIVATE_DATA(cc); +int base = (private_data_ptr == 0) ? SLJIT_MEM1(STACK_TOP) : SLJIT_MEM1(SLJIT_LOCALS_REG); +int offset0 = (private_data_ptr == 0) ? STACK(0) : private_data_ptr; +int offset1 = (private_data_ptr == 0) ? STACK(1) : private_data_ptr + (int)sizeof(sljit_sw); + +cc = get_iterator_parameters(common, cc, &opcode, &type, &max, &min, NULL); + +switch(opcode) + { + case OP_STAR: + case OP_PLUS: + case OP_UPTO: + case OP_CRRANGE: + if (type == OP_ANYNL || type == OP_EXTUNI) + { + SLJIT_ASSERT(private_data_ptr == 0); + set_jumps(current->topbacktracks, LABEL()); + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + free_stack(common, 1); + CMPTO(SLJIT_C_NOT_EQUAL, STR_PTR, 0, SLJIT_IMM, 0, CURRENT_AS(iterator_backtrack)->matchingpath); + } + else + { + if (opcode == OP_UPTO) + min = 0; + if (opcode <= OP_PLUS) + { + OP1(SLJIT_MOV, STR_PTR, 0, base, offset0); + jump = CMP(SLJIT_C_LESS_EQUAL, STR_PTR, 0, base, offset1); + } + else + { + OP1(SLJIT_MOV, TMP1, 0, base, offset1); + OP1(SLJIT_MOV, STR_PTR, 0, base, offset0); + jump = CMP(SLJIT_C_LESS_EQUAL, TMP1, 0, SLJIT_IMM, min + 1); + OP2(SLJIT_SUB, base, offset1, TMP1, 0, SLJIT_IMM, 1); + } + skip_char_back(common); + OP1(SLJIT_MOV, base, offset0, STR_PTR, 0); + JUMPTO(SLJIT_JUMP, CURRENT_AS(iterator_backtrack)->matchingpath); + if (opcode == OP_CRRANGE) + set_jumps(current->topbacktracks, LABEL()); + JUMPHERE(jump); + if (private_data_ptr == 0) + free_stack(common, 2); + if (opcode == OP_PLUS) + set_jumps(current->topbacktracks, LABEL()); + } + break; + + case OP_MINSTAR: + case OP_MINPLUS: + OP1(SLJIT_MOV, STR_PTR, 0, base, offset0); + compile_char1_matchingpath(common, type, cc, &jumplist); + OP1(SLJIT_MOV, base, offset0, STR_PTR, 0); + JUMPTO(SLJIT_JUMP, CURRENT_AS(iterator_backtrack)->matchingpath); + set_jumps(jumplist, LABEL()); + if (private_data_ptr == 0) + free_stack(common, 1); + if (opcode == OP_MINPLUS) + set_jumps(current->topbacktracks, LABEL()); + break; + + case OP_MINUPTO: + case OP_CRMINRANGE: + if (opcode == OP_CRMINRANGE) + { + label = LABEL(); + set_jumps(current->topbacktracks, label); + } + OP1(SLJIT_MOV, STR_PTR, 0, base, offset0); + compile_char1_matchingpath(common, type, cc, &jumplist); + + OP1(SLJIT_MOV, TMP1, 0, base, offset1); + OP1(SLJIT_MOV, base, offset0, STR_PTR, 0); + OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, SLJIT_IMM, 1); + OP1(SLJIT_MOV, base, offset1, TMP1, 0); + + if (opcode == OP_CRMINRANGE) + CMPTO(SLJIT_C_LESS, TMP1, 0, SLJIT_IMM, min + 1, label); + + if (opcode == OP_CRMINRANGE && max == 0) + JUMPTO(SLJIT_JUMP, CURRENT_AS(iterator_backtrack)->matchingpath); + else + CMPTO(SLJIT_C_LESS, TMP1, 0, SLJIT_IMM, max + 2, CURRENT_AS(iterator_backtrack)->matchingpath); + + set_jumps(jumplist, LABEL()); + if (private_data_ptr == 0) + free_stack(common, 2); + break; + + case OP_QUERY: + OP1(SLJIT_MOV, STR_PTR, 0, base, offset0); + OP1(SLJIT_MOV, base, offset0, SLJIT_IMM, 0); + CMPTO(SLJIT_C_NOT_EQUAL, STR_PTR, 0, SLJIT_IMM, 0, CURRENT_AS(iterator_backtrack)->matchingpath); + jump = JUMP(SLJIT_JUMP); + set_jumps(current->topbacktracks, LABEL()); + OP1(SLJIT_MOV, STR_PTR, 0, base, offset0); + OP1(SLJIT_MOV, base, offset0, SLJIT_IMM, 0); + JUMPTO(SLJIT_JUMP, CURRENT_AS(iterator_backtrack)->matchingpath); + JUMPHERE(jump); + if (private_data_ptr == 0) + free_stack(common, 1); + break; + + case OP_MINQUERY: + OP1(SLJIT_MOV, STR_PTR, 0, base, offset0); + OP1(SLJIT_MOV, base, offset0, SLJIT_IMM, 0); + jump = CMP(SLJIT_C_EQUAL, STR_PTR, 0, SLJIT_IMM, 0); + compile_char1_matchingpath(common, type, cc, &jumplist); + JUMPTO(SLJIT_JUMP, CURRENT_AS(iterator_backtrack)->matchingpath); + set_jumps(jumplist, LABEL()); + JUMPHERE(jump); + if (private_data_ptr == 0) + free_stack(common, 1); + break; + + case OP_EXACT: + case OP_POSPLUS: + case OP_CRPOSRANGE: + set_jumps(current->topbacktracks, LABEL()); + break; + + case OP_POSSTAR: + case OP_POSQUERY: + case OP_POSUPTO: + break; + + default: + SLJIT_ASSERT_STOP(); + break; + } +} + +static SLJIT_INLINE void compile_ref_iterator_backtrackingpath(compiler_common *common, struct backtrack_common *current) +{ +DEFINE_COMPILER; +pcre_uchar *cc = current->cc; +BOOL ref = (*cc == OP_REF || *cc == OP_REFI); +pcre_uchar type; + +type = cc[ref ? 1 + IMM2_SIZE : 1 + 2 * IMM2_SIZE]; + +if ((type & 0x1) == 0) + { + /* Maximize case. */ + set_jumps(current->topbacktracks, LABEL()); + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + free_stack(common, 1); + CMPTO(SLJIT_C_NOT_EQUAL, STR_PTR, 0, SLJIT_IMM, 0, CURRENT_AS(iterator_backtrack)->matchingpath); + return; + } + +OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); +CMPTO(SLJIT_C_NOT_EQUAL, STR_PTR, 0, SLJIT_IMM, 0, CURRENT_AS(iterator_backtrack)->matchingpath); +set_jumps(current->topbacktracks, LABEL()); +free_stack(common, ref ? 2 : 3); +} + +static SLJIT_INLINE void compile_recurse_backtrackingpath(compiler_common *common, struct backtrack_common *current) +{ +DEFINE_COMPILER; + +if (CURRENT_AS(recurse_backtrack)->inlined_pattern) + compile_backtrackingpath(common, current->top); +set_jumps(current->topbacktracks, LABEL()); +if (CURRENT_AS(recurse_backtrack)->inlined_pattern) + return; + +if (common->has_set_som && common->mark_ptr != 0) + { + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(1)); + free_stack(common, 2); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(0), TMP2, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->mark_ptr, TMP1, 0); + } +else if (common->has_set_som || common->mark_ptr != 0) + { + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + free_stack(common, 1); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->has_set_som ? (int)(OVECTOR(0)) : common->mark_ptr, TMP2, 0); + } +} + +static void compile_assert_backtrackingpath(compiler_common *common, struct backtrack_common *current) +{ +DEFINE_COMPILER; +pcre_uchar *cc = current->cc; +pcre_uchar bra = OP_BRA; +struct sljit_jump *brajump = NULL; + +SLJIT_ASSERT(*cc != OP_BRAMINZERO); +if (*cc == OP_BRAZERO) + { + bra = *cc; + cc++; + } + +if (bra == OP_BRAZERO) + { + SLJIT_ASSERT(current->topbacktracks == NULL); + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + } + +if (CURRENT_AS(assert_backtrack)->framesize < 0) + { + set_jumps(current->topbacktracks, LABEL()); + + if (bra == OP_BRAZERO) + { + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); + CMPTO(SLJIT_C_NOT_EQUAL, STR_PTR, 0, SLJIT_IMM, 0, CURRENT_AS(assert_backtrack)->matchingpath); + free_stack(common, 1); + } + return; + } + +if (bra == OP_BRAZERO) + { + if (*cc == OP_ASSERT_NOT || *cc == OP_ASSERTBACK_NOT) + { + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); + CMPTO(SLJIT_C_NOT_EQUAL, STR_PTR, 0, SLJIT_IMM, 0, CURRENT_AS(assert_backtrack)->matchingpath); + free_stack(common, 1); + return; + } + free_stack(common, 1); + brajump = CMP(SLJIT_C_EQUAL, STR_PTR, 0, SLJIT_IMM, 0); + } + +if (*cc == OP_ASSERT || *cc == OP_ASSERTBACK) + { + OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), CURRENT_AS(assert_backtrack)->private_data_ptr); + add_jump(compiler, &common->revertframes, JUMP(SLJIT_FAST_CALL)); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), CURRENT_AS(assert_backtrack)->private_data_ptr, SLJIT_MEM1(STACK_TOP), CURRENT_AS(assert_backtrack)->framesize * sizeof(sljit_sw)); + + set_jumps(current->topbacktracks, LABEL()); + } +else + set_jumps(current->topbacktracks, LABEL()); + +if (bra == OP_BRAZERO) + { + /* We know there is enough place on the stack. */ + OP2(SLJIT_ADD, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, sizeof(sljit_sw)); + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); + JUMPTO(SLJIT_JUMP, CURRENT_AS(assert_backtrack)->matchingpath); + JUMPHERE(brajump); + } +} + +static void compile_bracket_backtrackingpath(compiler_common *common, struct backtrack_common *current) +{ +DEFINE_COMPILER; +int opcode, stacksize, alt_count, alt_max; +int offset = 0; +int private_data_ptr = CURRENT_AS(bracket_backtrack)->private_data_ptr; +int repeat_ptr = 0, repeat_type = 0, repeat_count = 0; +pcre_uchar *cc = current->cc; +pcre_uchar *ccbegin; +pcre_uchar *ccprev; +pcre_uchar bra = OP_BRA; +pcre_uchar ket; +assert_backtrack *assert; +BOOL has_alternatives; +BOOL needs_control_head = FALSE; +struct sljit_jump *brazero = NULL; +struct sljit_jump *alt1 = NULL; +struct sljit_jump *alt2 = NULL; +struct sljit_jump *once = NULL; +struct sljit_jump *cond = NULL; +struct sljit_label *rmin_label = NULL; +struct sljit_label *exact_label = NULL; + +if (*cc == OP_BRAZERO || *cc == OP_BRAMINZERO) + { + bra = *cc; + cc++; + } + +opcode = *cc; +ccbegin = bracketend(cc) - 1 - LINK_SIZE; +ket = *ccbegin; +if (ket == OP_KET && PRIVATE_DATA(ccbegin) != 0) + { + repeat_ptr = PRIVATE_DATA(ccbegin); + repeat_type = PRIVATE_DATA(ccbegin + 2); + repeat_count = PRIVATE_DATA(ccbegin + 3); + SLJIT_ASSERT(repeat_type != 0 && repeat_count != 0); + if (repeat_type == OP_UPTO) + ket = OP_KETRMAX; + if (repeat_type == OP_MINUPTO) + ket = OP_KETRMIN; + } +ccbegin = cc; +cc += GET(cc, 1); +has_alternatives = *cc == OP_ALT; +if (SLJIT_UNLIKELY(opcode == OP_COND) || SLJIT_UNLIKELY(opcode == OP_SCOND)) + has_alternatives = (ccbegin[1 + LINK_SIZE] >= OP_ASSERT && ccbegin[1 + LINK_SIZE] <= OP_ASSERTBACK_NOT) || CURRENT_AS(bracket_backtrack)->u.condfailed != NULL; +if (opcode == OP_CBRA || opcode == OP_SCBRA) + offset = (GET2(ccbegin, 1 + LINK_SIZE)) << 1; +if (SLJIT_UNLIKELY(opcode == OP_COND) && (*cc == OP_KETRMAX || *cc == OP_KETRMIN)) + opcode = OP_SCOND; +if (SLJIT_UNLIKELY(opcode == OP_ONCE_NC)) + opcode = OP_ONCE; + +alt_max = has_alternatives ? no_alternatives(ccbegin) : 0; + +/* Decoding the needs_control_head in framesize. */ +if (opcode == OP_ONCE) + { + needs_control_head = (CURRENT_AS(bracket_backtrack)->u.framesize & 0x1) != 0; + CURRENT_AS(bracket_backtrack)->u.framesize >>= 1; + } + +if (ket != OP_KET && repeat_type != 0) + { + /* TMP1 is used in OP_KETRMIN below. */ + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + free_stack(common, 1); + if (repeat_type == OP_UPTO) + OP2(SLJIT_ADD, SLJIT_MEM1(SLJIT_LOCALS_REG), repeat_ptr, TMP1, 0, SLJIT_IMM, 1); + else + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), repeat_ptr, TMP1, 0); + } + +if (ket == OP_KETRMAX) + { + if (bra == OP_BRAZERO) + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + free_stack(common, 1); + brazero = CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_IMM, 0); + } + } +else if (ket == OP_KETRMIN) + { + if (bra != OP_BRAMINZERO) + { + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + if (repeat_type != 0) + { + /* TMP1 was set a few lines above. */ + CMPTO(SLJIT_C_NOT_EQUAL, TMP1, 0, SLJIT_IMM, 0, CURRENT_AS(bracket_backtrack)->recursive_matchingpath); + /* Drop STR_PTR for non-greedy plus quantifier. */ + if (opcode != OP_ONCE) + free_stack(common, 1); + } + else if (opcode >= OP_SBRA || opcode == OP_ONCE) + { + /* Checking zero-length iteration. */ + if (opcode != OP_ONCE || CURRENT_AS(bracket_backtrack)->u.framesize < 0) + CMPTO(SLJIT_C_NOT_EQUAL, STR_PTR, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, CURRENT_AS(bracket_backtrack)->recursive_matchingpath); + else + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr); + CMPTO(SLJIT_C_NOT_EQUAL, STR_PTR, 0, SLJIT_MEM1(TMP1), (CURRENT_AS(bracket_backtrack)->u.framesize + 1) * sizeof(sljit_sw), CURRENT_AS(bracket_backtrack)->recursive_matchingpath); + } + /* Drop STR_PTR for non-greedy plus quantifier. */ + if (opcode != OP_ONCE) + free_stack(common, 1); + } + else + JUMPTO(SLJIT_JUMP, CURRENT_AS(bracket_backtrack)->recursive_matchingpath); + } + rmin_label = LABEL(); + if (repeat_type != 0) + OP2(SLJIT_ADD, SLJIT_MEM1(SLJIT_LOCALS_REG), repeat_ptr, SLJIT_MEM1(SLJIT_LOCALS_REG), repeat_ptr, SLJIT_IMM, 1); + } +else if (bra == OP_BRAZERO) + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + free_stack(common, 1); + brazero = CMP(SLJIT_C_NOT_EQUAL, TMP1, 0, SLJIT_IMM, 0); + } +else if (repeat_type == OP_EXACT) + { + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), repeat_ptr, SLJIT_IMM, 1); + exact_label = LABEL(); + } + +if (offset != 0) + { + if (common->capture_last_ptr != 0) + { + SLJIT_ASSERT(common->optimized_cbracket[offset >> 1] == 0); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), STACK(1)); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->capture_last_ptr, TMP1, 0); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(2)); + free_stack(common, 3); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset), TMP2, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset + 1), TMP1, 0); + } + else if (common->optimized_cbracket[offset >> 1] == 0) + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), STACK(1)); + free_stack(common, 2); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset), TMP1, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset + 1), TMP2, 0); + } + } + +if (SLJIT_UNLIKELY(opcode == OP_ONCE)) + { + if (CURRENT_AS(bracket_backtrack)->u.framesize >= 0) + { + OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr); + add_jump(compiler, &common->revertframes, JUMP(SLJIT_FAST_CALL)); + } + once = JUMP(SLJIT_JUMP); + } +else if (SLJIT_UNLIKELY(opcode == OP_COND) || SLJIT_UNLIKELY(opcode == OP_SCOND)) + { + if (has_alternatives) + { + /* Always exactly one alternative. */ + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + free_stack(common, 1); + + alt_max = 2; + alt1 = CMP(SLJIT_C_EQUAL, TMP1, 0, SLJIT_IMM, sizeof(sljit_uw)); + } + } +else if (has_alternatives) + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + free_stack(common, 1); + + if (alt_max > 4) + { + /* Table jump if alt_max is greater than 4. */ + sljit_emit_ijump(compiler, SLJIT_JUMP, SLJIT_MEM1(TMP1), (sljit_sw)common->read_only_data_ptr); + add_label_addr(common); + } + else + { + if (alt_max == 4) + alt2 = CMP(SLJIT_C_GREATER_EQUAL, TMP1, 0, SLJIT_IMM, 2 * sizeof(sljit_uw)); + alt1 = CMP(SLJIT_C_GREATER_EQUAL, TMP1, 0, SLJIT_IMM, sizeof(sljit_uw)); + } + } + +COMPILE_BACKTRACKINGPATH(current->top); +if (current->topbacktracks) + set_jumps(current->topbacktracks, LABEL()); + +if (SLJIT_UNLIKELY(opcode == OP_COND) || SLJIT_UNLIKELY(opcode == OP_SCOND)) + { + /* Conditional block always has at most one alternative. */ + if (ccbegin[1 + LINK_SIZE] >= OP_ASSERT && ccbegin[1 + LINK_SIZE] <= OP_ASSERTBACK_NOT) + { + SLJIT_ASSERT(has_alternatives); + assert = CURRENT_AS(bracket_backtrack)->u.assert; + if (assert->framesize >= 0 && (ccbegin[1 + LINK_SIZE] == OP_ASSERT || ccbegin[1 + LINK_SIZE] == OP_ASSERTBACK)) + { + OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), assert->private_data_ptr); + add_jump(compiler, &common->revertframes, JUMP(SLJIT_FAST_CALL)); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), assert->private_data_ptr, SLJIT_MEM1(STACK_TOP), assert->framesize * sizeof(sljit_sw)); + } + cond = JUMP(SLJIT_JUMP); + set_jumps(CURRENT_AS(bracket_backtrack)->u.assert->condfailed, LABEL()); + } + else if (CURRENT_AS(bracket_backtrack)->u.condfailed != NULL) + { + SLJIT_ASSERT(has_alternatives); + cond = JUMP(SLJIT_JUMP); + set_jumps(CURRENT_AS(bracket_backtrack)->u.condfailed, LABEL()); + } + else + SLJIT_ASSERT(!has_alternatives); + } + +if (has_alternatives) + { + alt_count = sizeof(sljit_uw); + do + { + current->top = NULL; + current->topbacktracks = NULL; + current->nextbacktracks = NULL; + /* Conditional blocks always have an additional alternative, even if it is empty. */ + if (*cc == OP_ALT) + { + ccprev = cc + 1 + LINK_SIZE; + cc += GET(cc, 1); + if (opcode != OP_COND && opcode != OP_SCOND) + { + if (opcode != OP_ONCE) + { + if (private_data_ptr != 0) + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr); + else + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + } + else + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(needs_control_head ? 1 : 0)); + } + compile_matchingpath(common, ccprev, cc, current); + if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) + return; + } + + /* Instructions after the current alternative is successfully matched. */ + /* There is a similar code in compile_bracket_matchingpath. */ + if (opcode == OP_ONCE) + match_once_common(common, ket, CURRENT_AS(bracket_backtrack)->u.framesize, private_data_ptr, has_alternatives, needs_control_head); + + stacksize = 0; + if (repeat_type == OP_MINUPTO) + { + /* We need to preserve the counter. TMP2 will be used below. */ + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), repeat_ptr); + stacksize++; + } + if (ket != OP_KET || bra != OP_BRA) + stacksize++; + if (offset != 0) + { + if (common->capture_last_ptr != 0) + stacksize++; + if (common->optimized_cbracket[offset >> 1] == 0) + stacksize += 2; + } + if (opcode != OP_ONCE) + stacksize++; + + if (stacksize > 0) + allocate_stack(common, stacksize); + + stacksize = 0; + if (repeat_type == OP_MINUPTO) + { + /* TMP2 was set above. */ + OP2(SLJIT_SUB, SLJIT_MEM1(STACK_TOP), STACK(stacksize), TMP2, 0, SLJIT_IMM, 1); + stacksize++; + } + + if (ket != OP_KET || bra != OP_BRA) + { + if (ket != OP_KET) + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), STR_PTR, 0); + else + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), SLJIT_IMM, 0); + stacksize++; + } + + if (offset != 0) + stacksize = match_capture_common(common, stacksize, offset, private_data_ptr); + + if (opcode != OP_ONCE) + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), SLJIT_IMM, alt_count); + + if (offset != 0 && ket == OP_KETRMAX && common->optimized_cbracket[offset >> 1] != 0) + { + /* If ket is not OP_KETRMAX, this code path is executed after the jump to alternative_matchingpath. */ + SLJIT_ASSERT(private_data_ptr == OVECTOR(offset + 0)); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset + 1), STR_PTR, 0); + } + + JUMPTO(SLJIT_JUMP, CURRENT_AS(bracket_backtrack)->alternative_matchingpath); + + if (opcode != OP_ONCE) + { + if (alt_max > 4) + add_label_addr(common); + else + { + if (alt_count != 2 * sizeof(sljit_uw)) + { + JUMPHERE(alt1); + if (alt_max == 3 && alt_count == sizeof(sljit_uw)) + alt2 = CMP(SLJIT_C_GREATER_EQUAL, TMP1, 0, SLJIT_IMM, 2 * sizeof(sljit_uw)); + } + else + { + JUMPHERE(alt2); + if (alt_max == 4) + alt1 = CMP(SLJIT_C_GREATER_EQUAL, TMP1, 0, SLJIT_IMM, 3 * sizeof(sljit_uw)); + } + } + alt_count += sizeof(sljit_uw); + } + + COMPILE_BACKTRACKINGPATH(current->top); + if (current->topbacktracks) + set_jumps(current->topbacktracks, LABEL()); + SLJIT_ASSERT(!current->nextbacktracks); + } + while (*cc == OP_ALT); + + if (cond != NULL) + { + SLJIT_ASSERT(opcode == OP_COND || opcode == OP_SCOND); + assert = CURRENT_AS(bracket_backtrack)->u.assert; + if ((ccbegin[1 + LINK_SIZE] == OP_ASSERT_NOT || ccbegin[1 + LINK_SIZE] == OP_ASSERTBACK_NOT) && assert->framesize >= 0) + { + OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), assert->private_data_ptr); + add_jump(compiler, &common->revertframes, JUMP(SLJIT_FAST_CALL)); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), assert->private_data_ptr, SLJIT_MEM1(STACK_TOP), assert->framesize * sizeof(sljit_sw)); + } + JUMPHERE(cond); + } + + /* Free the STR_PTR. */ + if (private_data_ptr == 0) + free_stack(common, 1); + } + +if (offset != 0) + { + /* Using both tmp register is better for instruction scheduling. */ + if (common->optimized_cbracket[offset >> 1] != 0) + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), STACK(1)); + free_stack(common, 2); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset), TMP1, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset + 1), TMP2, 0); + } + else + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + free_stack(common, 1); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, TMP1, 0); + } + } +else if (opcode == OP_SBRA || opcode == OP_SCOND) + { + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, SLJIT_MEM1(STACK_TOP), STACK(0)); + free_stack(common, 1); + } +else if (opcode == OP_ONCE) + { + cc = ccbegin + GET(ccbegin, 1); + stacksize = needs_control_head ? 1 : 0; + + if (CURRENT_AS(bracket_backtrack)->u.framesize >= 0) + { + /* Reset head and drop saved frame. */ + stacksize += CURRENT_AS(bracket_backtrack)->u.framesize + ((ket != OP_KET || *cc == OP_ALT) ? 2 : 1); + } + else if (ket == OP_KETRMAX || (*cc == OP_ALT && ket != OP_KETRMIN)) + { + /* The STR_PTR must be released. */ + stacksize++; + } + free_stack(common, stacksize); + + JUMPHERE(once); + /* Restore previous private_data_ptr */ + if (CURRENT_AS(bracket_backtrack)->u.framesize >= 0) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, SLJIT_MEM1(STACK_TOP), CURRENT_AS(bracket_backtrack)->u.framesize * sizeof(sljit_sw)); + else if (ket == OP_KETRMIN) + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(1)); + /* See the comment below. */ + free_stack(common, 2); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), private_data_ptr, TMP1, 0); + } + } + +if (repeat_type == OP_EXACT) + { + OP2(SLJIT_ADD, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), repeat_ptr, SLJIT_IMM, 1); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), repeat_ptr, TMP1, 0); + CMPTO(SLJIT_C_LESS_EQUAL, TMP1, 0, SLJIT_IMM, repeat_count, exact_label); + } +else if (ket == OP_KETRMAX) + { + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + if (bra != OP_BRAZERO) + free_stack(common, 1); + + CMPTO(SLJIT_C_NOT_EQUAL, STR_PTR, 0, SLJIT_IMM, 0, CURRENT_AS(bracket_backtrack)->recursive_matchingpath); + if (bra == OP_BRAZERO) + { + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(1)); + JUMPTO(SLJIT_JUMP, CURRENT_AS(bracket_backtrack)->zero_matchingpath); + JUMPHERE(brazero); + free_stack(common, 1); + } + } +else if (ket == OP_KETRMIN) + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + + /* OP_ONCE removes everything in case of a backtrack, so we don't + need to explicitly release the STR_PTR. The extra release would + affect badly the free_stack(2) above. */ + if (opcode != OP_ONCE) + free_stack(common, 1); + CMPTO(SLJIT_C_NOT_EQUAL, TMP1, 0, SLJIT_IMM, 0, rmin_label); + if (opcode == OP_ONCE) + free_stack(common, bra == OP_BRAMINZERO ? 2 : 1); + else if (bra == OP_BRAMINZERO) + free_stack(common, 1); + } +else if (bra == OP_BRAZERO) + { + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + JUMPTO(SLJIT_JUMP, CURRENT_AS(bracket_backtrack)->zero_matchingpath); + JUMPHERE(brazero); + } +} + +static SLJIT_INLINE void compile_bracketpos_backtrackingpath(compiler_common *common, struct backtrack_common *current) +{ +DEFINE_COMPILER; +int offset; +struct sljit_jump *jump; + +if (CURRENT_AS(bracketpos_backtrack)->framesize < 0) + { + if (*current->cc == OP_CBRAPOS || *current->cc == OP_SCBRAPOS) + { + offset = (GET2(current->cc, 1 + LINK_SIZE)) << 1; + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), STACK(1)); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset), TMP1, 0); + if (common->capture_last_ptr != 0) + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(2)); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(offset + 1), TMP2, 0); + if (common->capture_last_ptr != 0) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->capture_last_ptr, TMP1, 0); + } + set_jumps(current->topbacktracks, LABEL()); + free_stack(common, CURRENT_AS(bracketpos_backtrack)->stacksize); + return; + } + +OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), CURRENT_AS(bracketpos_backtrack)->private_data_ptr); +add_jump(compiler, &common->revertframes, JUMP(SLJIT_FAST_CALL)); + +if (current->topbacktracks) + { + jump = JUMP(SLJIT_JUMP); + set_jumps(current->topbacktracks, LABEL()); + /* Drop the stack frame. */ + free_stack(common, CURRENT_AS(bracketpos_backtrack)->stacksize); + JUMPHERE(jump); + } +OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), CURRENT_AS(bracketpos_backtrack)->private_data_ptr, SLJIT_MEM1(STACK_TOP), CURRENT_AS(bracketpos_backtrack)->framesize * sizeof(sljit_sw)); +} + +static SLJIT_INLINE void compile_braminzero_backtrackingpath(compiler_common *common, struct backtrack_common *current) +{ +assert_backtrack backtrack; + +current->top = NULL; +current->topbacktracks = NULL; +current->nextbacktracks = NULL; +if (current->cc[1] > OP_ASSERTBACK_NOT) + { + /* Manual call of compile_bracket_matchingpath and compile_bracket_backtrackingpath. */ + compile_bracket_matchingpath(common, current->cc, current); + compile_bracket_backtrackingpath(common, current->top); + } +else + { + memset(&backtrack, 0, sizeof(backtrack)); + backtrack.common.cc = current->cc; + backtrack.matchingpath = CURRENT_AS(braminzero_backtrack)->matchingpath; + /* Manual call of compile_assert_matchingpath. */ + compile_assert_matchingpath(common, current->cc, &backtrack, FALSE); + } +SLJIT_ASSERT(!current->nextbacktracks && !current->topbacktracks); +} + +static SLJIT_INLINE void compile_control_verb_backtrackingpath(compiler_common *common, struct backtrack_common *current) +{ +DEFINE_COMPILER; +pcre_uchar opcode = *current->cc; +struct sljit_label *loop; +struct sljit_jump *jump; + +if (opcode == OP_THEN || opcode == OP_THEN_ARG) + { + if (common->then_trap != NULL) + { + SLJIT_ASSERT(common->control_head_ptr != 0); + + OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_IMM, type_then_trap); + OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, common->then_trap->start); + jump = JUMP(SLJIT_JUMP); + + loop = LABEL(); + OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(STACK_TOP), -(int)sizeof(sljit_sw)); + JUMPHERE(jump); + CMPTO(SLJIT_C_NOT_EQUAL, SLJIT_MEM1(STACK_TOP), -(int)(2 * sizeof(sljit_sw)), TMP1, 0, loop); + CMPTO(SLJIT_C_NOT_EQUAL, SLJIT_MEM1(STACK_TOP), -(int)(3 * sizeof(sljit_sw)), TMP2, 0, loop); + add_jump(compiler, &common->then_trap->quit, JUMP(SLJIT_JUMP)); + return; + } + else if (common->positive_assert) + { + add_jump(compiler, &common->positive_assert_quit, JUMP(SLJIT_JUMP)); + return; + } + } + +if (common->local_exit) + { + if (common->quit_label == NULL) + add_jump(compiler, &common->quit, JUMP(SLJIT_JUMP)); + else + JUMPTO(SLJIT_JUMP, common->quit_label); + return; + } + +if (opcode == OP_SKIP_ARG) + { + SLJIT_ASSERT(common->control_head_ptr != 0); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS0, STACK_TOP, 0); + OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_IMM, (sljit_sw)(current->cc + 2)); + sljit_emit_ijump(compiler, SLJIT_CALL2, SLJIT_IMM, SLJIT_FUNC_OFFSET(do_search_mark)); + OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS0); + + OP1(SLJIT_MOV, STR_PTR, 0, TMP1, 0); + add_jump(compiler, &common->reset_match, CMP(SLJIT_C_NOT_EQUAL, STR_PTR, 0, SLJIT_IMM, -1)); + return; + } + +if (opcode == OP_SKIP) + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); +else + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_IMM, 0); +add_jump(compiler, &common->reset_match, JUMP(SLJIT_JUMP)); +} + +static SLJIT_INLINE void compile_then_trap_backtrackingpath(compiler_common *common, struct backtrack_common *current) +{ +DEFINE_COMPILER; +struct sljit_jump *jump; +int size; + +if (CURRENT_AS(then_trap_backtrack)->then_trap) + { + common->then_trap = CURRENT_AS(then_trap_backtrack)->then_trap; + return; + } + +size = CURRENT_AS(then_trap_backtrack)->framesize; +size = 3 + (size < 0 ? 0 : size); + +OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(size - 3)); +free_stack(common, size); +jump = JUMP(SLJIT_JUMP); + +set_jumps(CURRENT_AS(then_trap_backtrack)->quit, LABEL()); +/* STACK_TOP is set by THEN. */ +if (CURRENT_AS(then_trap_backtrack)->framesize >= 0) + add_jump(compiler, &common->revertframes, JUMP(SLJIT_FAST_CALL)); +OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); +free_stack(common, 3); + +JUMPHERE(jump); +OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr, TMP1, 0); +} + +static void compile_backtrackingpath(compiler_common *common, struct backtrack_common *current) +{ +DEFINE_COMPILER; +then_trap_backtrack *save_then_trap = common->then_trap; + +while (current) + { + if (current->nextbacktracks != NULL) + set_jumps(current->nextbacktracks, LABEL()); + switch(*current->cc) + { + case OP_SET_SOM: + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + free_stack(common, 1); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(0), TMP1, 0); + break; + + case OP_STAR: + case OP_MINSTAR: + case OP_PLUS: + case OP_MINPLUS: + case OP_QUERY: + case OP_MINQUERY: + case OP_UPTO: + case OP_MINUPTO: + case OP_EXACT: + case OP_POSSTAR: + case OP_POSPLUS: + case OP_POSQUERY: + case OP_POSUPTO: + case OP_STARI: + case OP_MINSTARI: + case OP_PLUSI: + case OP_MINPLUSI: + case OP_QUERYI: + case OP_MINQUERYI: + case OP_UPTOI: + case OP_MINUPTOI: + case OP_EXACTI: + case OP_POSSTARI: + case OP_POSPLUSI: + case OP_POSQUERYI: + case OP_POSUPTOI: + case OP_NOTSTAR: + case OP_NOTMINSTAR: + case OP_NOTPLUS: + case OP_NOTMINPLUS: + case OP_NOTQUERY: + case OP_NOTMINQUERY: + case OP_NOTUPTO: + case OP_NOTMINUPTO: + case OP_NOTEXACT: + case OP_NOTPOSSTAR: + case OP_NOTPOSPLUS: + case OP_NOTPOSQUERY: + case OP_NOTPOSUPTO: + case OP_NOTSTARI: + case OP_NOTMINSTARI: + case OP_NOTPLUSI: + case OP_NOTMINPLUSI: + case OP_NOTQUERYI: + case OP_NOTMINQUERYI: + case OP_NOTUPTOI: + case OP_NOTMINUPTOI: + case OP_NOTEXACTI: + case OP_NOTPOSSTARI: + case OP_NOTPOSPLUSI: + case OP_NOTPOSQUERYI: + case OP_NOTPOSUPTOI: + case OP_TYPESTAR: + case OP_TYPEMINSTAR: + case OP_TYPEPLUS: + case OP_TYPEMINPLUS: + case OP_TYPEQUERY: + case OP_TYPEMINQUERY: + case OP_TYPEUPTO: + case OP_TYPEMINUPTO: + case OP_TYPEEXACT: + case OP_TYPEPOSSTAR: + case OP_TYPEPOSPLUS: + case OP_TYPEPOSQUERY: + case OP_TYPEPOSUPTO: + case OP_CLASS: + case OP_NCLASS: +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + case OP_XCLASS: +#endif + compile_iterator_backtrackingpath(common, current); + break; + + case OP_REF: + case OP_REFI: + case OP_DNREF: + case OP_DNREFI: + compile_ref_iterator_backtrackingpath(common, current); + break; + + case OP_RECURSE: + compile_recurse_backtrackingpath(common, current); + break; + + case OP_ASSERT: + case OP_ASSERT_NOT: + case OP_ASSERTBACK: + case OP_ASSERTBACK_NOT: + compile_assert_backtrackingpath(common, current); + break; + + case OP_ONCE: + case OP_ONCE_NC: + case OP_BRA: + case OP_CBRA: + case OP_COND: + case OP_SBRA: + case OP_SCBRA: + case OP_SCOND: + compile_bracket_backtrackingpath(common, current); + break; + + case OP_BRAZERO: + if (current->cc[1] > OP_ASSERTBACK_NOT) + compile_bracket_backtrackingpath(common, current); + else + compile_assert_backtrackingpath(common, current); + break; + + case OP_BRAPOS: + case OP_CBRAPOS: + case OP_SBRAPOS: + case OP_SCBRAPOS: + case OP_BRAPOSZERO: + compile_bracketpos_backtrackingpath(common, current); + break; + + case OP_BRAMINZERO: + compile_braminzero_backtrackingpath(common, current); + break; + + case OP_MARK: + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(common->has_skip_arg ? 4 : 0)); + if (common->has_skip_arg) + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + free_stack(common, common->has_skip_arg ? 5 : 1); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->mark_ptr, TMP1, 0); + if (common->has_skip_arg) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr, TMP2, 0); + break; + + case OP_THEN: + case OP_THEN_ARG: + case OP_PRUNE: + case OP_PRUNE_ARG: + case OP_SKIP: + case OP_SKIP_ARG: + compile_control_verb_backtrackingpath(common, current); + break; + + case OP_COMMIT: + if (!common->local_exit) + OP1(SLJIT_MOV, SLJIT_RETURN_REG, 0, SLJIT_IMM, PCRE_ERROR_NOMATCH); + if (common->quit_label == NULL) + add_jump(compiler, &common->quit, JUMP(SLJIT_JUMP)); + else + JUMPTO(SLJIT_JUMP, common->quit_label); + break; + + case OP_CALLOUT: + case OP_FAIL: + case OP_ACCEPT: + case OP_ASSERT_ACCEPT: + set_jumps(current->topbacktracks, LABEL()); + break; + + case OP_THEN_TRAP: + /* A virtual opcode for then traps. */ + compile_then_trap_backtrackingpath(common, current); + break; + + default: + SLJIT_ASSERT_STOP(); + break; + } + current = current->prev; + } +common->then_trap = save_then_trap; +} + +static SLJIT_INLINE void compile_recurse(compiler_common *common) +{ +DEFINE_COMPILER; +pcre_uchar *cc = common->start + common->currententry->start; +pcre_uchar *ccbegin = cc + 1 + LINK_SIZE + (*cc == OP_BRA ? 0 : IMM2_SIZE); +pcre_uchar *ccend = bracketend(cc); +BOOL needs_control_head; +int framesize = get_framesize(common, cc, NULL, TRUE, &needs_control_head); +int private_data_size = get_private_data_copy_length(common, ccbegin, ccend, needs_control_head); +int alternativesize; +BOOL needs_frame; +backtrack_common altbacktrack; +struct sljit_jump *jump; + +/* Recurse captures then. */ +common->then_trap = NULL; + +SLJIT_ASSERT(*cc == OP_BRA || *cc == OP_CBRA || *cc == OP_CBRAPOS || *cc == OP_SCBRA || *cc == OP_SCBRAPOS); +needs_frame = framesize >= 0; +if (!needs_frame) + framesize = 0; +alternativesize = *(cc + GET(cc, 1)) == OP_ALT ? 1 : 0; + +SLJIT_ASSERT(common->currententry->entry == NULL && common->recursive_head_ptr != 0); +common->currententry->entry = LABEL(); +set_jumps(common->currententry->calls, common->currententry->entry); + +sljit_emit_fast_enter(compiler, TMP2, 0); +allocate_stack(common, private_data_size + framesize + alternativesize); +OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(private_data_size + framesize + alternativesize - 1), TMP2, 0); +copy_private_data(common, ccbegin, ccend, TRUE, private_data_size + framesize + alternativesize, framesize + alternativesize, needs_control_head); +if (needs_control_head) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr, SLJIT_IMM, 0); +OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->recursive_head_ptr, STACK_TOP, 0); +if (needs_frame) + init_frame(common, cc, NULL, framesize + alternativesize - 1, alternativesize, TRUE); + +if (alternativesize > 0) + OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); + +memset(&altbacktrack, 0, sizeof(backtrack_common)); +common->quit_label = NULL; +common->accept_label = NULL; +common->quit = NULL; +common->accept = NULL; +altbacktrack.cc = ccbegin; +cc += GET(cc, 1); +while (1) + { + altbacktrack.top = NULL; + altbacktrack.topbacktracks = NULL; + + if (altbacktrack.cc != ccbegin) + OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); + + compile_matchingpath(common, altbacktrack.cc, cc, &altbacktrack); + if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) + return; + + add_jump(compiler, &common->accept, JUMP(SLJIT_JUMP)); + + compile_backtrackingpath(common, altbacktrack.top); + if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) + return; + set_jumps(altbacktrack.topbacktracks, LABEL()); + + if (*cc != OP_ALT) + break; + + altbacktrack.cc = cc + 1 + LINK_SIZE; + cc += GET(cc, 1); + } + +/* None of them matched. */ +OP1(SLJIT_MOV, TMP3, 0, SLJIT_IMM, 0); +jump = JUMP(SLJIT_JUMP); + +if (common->quit != NULL) + { + set_jumps(common->quit, LABEL()); + OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->recursive_head_ptr); + if (needs_frame) + { + OP2(SLJIT_SUB, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, (framesize + alternativesize) * sizeof(sljit_sw)); + add_jump(compiler, &common->revertframes, JUMP(SLJIT_FAST_CALL)); + OP2(SLJIT_ADD, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, (framesize + alternativesize) * sizeof(sljit_sw)); + } + OP1(SLJIT_MOV, TMP3, 0, SLJIT_IMM, 0); + common->quit = NULL; + add_jump(compiler, &common->quit, JUMP(SLJIT_JUMP)); + } + +set_jumps(common->accept, LABEL()); +OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->recursive_head_ptr); +if (needs_frame) + { + OP2(SLJIT_SUB, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, (framesize + alternativesize) * sizeof(sljit_sw)); + add_jump(compiler, &common->revertframes, JUMP(SLJIT_FAST_CALL)); + OP2(SLJIT_ADD, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, (framesize + alternativesize) * sizeof(sljit_sw)); + } +OP1(SLJIT_MOV, TMP3, 0, SLJIT_IMM, 1); + +JUMPHERE(jump); +if (common->quit != NULL) + set_jumps(common->quit, LABEL()); +copy_private_data(common, ccbegin, ccend, FALSE, private_data_size + framesize + alternativesize, framesize + alternativesize, needs_control_head); +free_stack(common, private_data_size + framesize + alternativesize); +if (needs_control_head) + { + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), 2 * sizeof(sljit_sw)); + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), sizeof(sljit_sw)); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->recursive_head_ptr, TMP1, 0); + OP1(SLJIT_MOV, TMP1, 0, TMP3, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr, TMP2, 0); + } +else + { + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), sizeof(sljit_sw)); + OP1(SLJIT_MOV, TMP1, 0, TMP3, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->recursive_head_ptr, TMP2, 0); + } +sljit_emit_fast_return(compiler, SLJIT_MEM1(STACK_TOP), 0); +} + +#undef COMPILE_BACKTRACKINGPATH +#undef CURRENT_AS + +void +PRIV(jit_compile)(const REAL_PCRE *re, PUBL(extra) *extra, int mode) +{ +struct sljit_compiler *compiler; +backtrack_common rootbacktrack; +compiler_common common_data; +compiler_common *common = &common_data; +const pcre_uint8 *tables = re->tables; +pcre_study_data *study; +int private_data_size; +pcre_uchar *ccend; +executable_functions *functions; +void *executable_func; +sljit_uw executable_size; +sljit_uw total_length; +label_addr_list *label_addr; +struct sljit_label *mainloop_label = NULL; +struct sljit_label *continue_match_label; +struct sljit_label *empty_match_found_label = NULL; +struct sljit_label *empty_match_backtrack_label = NULL; +struct sljit_label *reset_match_label; +struct sljit_label *quit_label; +struct sljit_jump *jump; +struct sljit_jump *minlength_check_failed = NULL; +struct sljit_jump *reqbyte_notfound = NULL; +struct sljit_jump *empty_match = NULL; + +SLJIT_ASSERT((extra->flags & PCRE_EXTRA_STUDY_DATA) != 0); +study = extra->study_data; + +if (!tables) + tables = PRIV(default_tables); + +memset(&rootbacktrack, 0, sizeof(backtrack_common)); +memset(common, 0, sizeof(compiler_common)); +rootbacktrack.cc = (pcre_uchar *)re + re->name_table_offset + re->name_count * re->name_entry_size; + +common->start = rootbacktrack.cc; +common->read_only_data = NULL; +common->read_only_data_size = 0; +common->read_only_data_ptr = NULL; +common->fcc = tables + fcc_offset; +common->lcc = (sljit_sw)(tables + lcc_offset); +common->mode = mode; +common->might_be_empty = study->minlength == 0; +common->nltype = NLTYPE_FIXED; +switch(re->options & PCRE_NEWLINE_BITS) + { + case 0: + /* Compile-time default */ + switch(NEWLINE) + { + case -1: common->newline = (CHAR_CR << 8) | CHAR_NL; common->nltype = NLTYPE_ANY; break; + case -2: common->newline = (CHAR_CR << 8) | CHAR_NL; common->nltype = NLTYPE_ANYCRLF; break; + default: common->newline = NEWLINE; break; + } + break; + case PCRE_NEWLINE_CR: common->newline = CHAR_CR; break; + case PCRE_NEWLINE_LF: common->newline = CHAR_NL; break; + case PCRE_NEWLINE_CR+ + PCRE_NEWLINE_LF: common->newline = (CHAR_CR << 8) | CHAR_NL; break; + case PCRE_NEWLINE_ANY: common->newline = (CHAR_CR << 8) | CHAR_NL; common->nltype = NLTYPE_ANY; break; + case PCRE_NEWLINE_ANYCRLF: common->newline = (CHAR_CR << 8) | CHAR_NL; common->nltype = NLTYPE_ANYCRLF; break; + default: return; + } +common->nlmax = READ_CHAR_MAX; +common->nlmin = 0; +if ((re->options & PCRE_BSR_ANYCRLF) != 0) + common->bsr_nltype = NLTYPE_ANYCRLF; +else if ((re->options & PCRE_BSR_UNICODE) != 0) + common->bsr_nltype = NLTYPE_ANY; +else + { +#ifdef BSR_ANYCRLF + common->bsr_nltype = NLTYPE_ANYCRLF; +#else + common->bsr_nltype = NLTYPE_ANY; +#endif + } +common->bsr_nlmax = READ_CHAR_MAX; +common->bsr_nlmin = 0; +common->endonly = (re->options & PCRE_DOLLAR_ENDONLY) != 0; +common->ctypes = (sljit_sw)(tables + ctypes_offset); +common->name_table = ((pcre_uchar *)re) + re->name_table_offset; +common->name_count = re->name_count; +common->name_entry_size = re->name_entry_size; +common->jscript_compat = (re->options & PCRE_JAVASCRIPT_COMPAT) != 0; +#ifdef SUPPORT_UTF +/* PCRE_UTF[16|32] have the same value as PCRE_UTF8. */ +common->utf = (re->options & PCRE_UTF8) != 0; +#ifdef SUPPORT_UCP +common->use_ucp = (re->options & PCRE_UCP) != 0; +#endif +if (common->utf) + { + if (common->nltype == NLTYPE_ANY) + common->nlmax = 0x2029; + else if (common->nltype == NLTYPE_ANYCRLF) + common->nlmax = (CHAR_CR > CHAR_NL) ? CHAR_CR : CHAR_NL; + else + { + /* We only care about the first newline character. */ + common->nlmax = common->newline & 0xff; + } + + if (common->nltype == NLTYPE_FIXED) + common->nlmin = common->newline & 0xff; + else + common->nlmin = (CHAR_CR < CHAR_NL) ? CHAR_CR : CHAR_NL; + + if (common->bsr_nltype == NLTYPE_ANY) + common->bsr_nlmax = 0x2029; + else + common->bsr_nlmax = (CHAR_CR > CHAR_NL) ? CHAR_CR : CHAR_NL; + common->bsr_nlmin = (CHAR_CR < CHAR_NL) ? CHAR_CR : CHAR_NL; + } +#endif /* SUPPORT_UTF */ +ccend = bracketend(common->start); + +/* Calculate the local space size on the stack. */ +common->ovector_start = LIMIT_MATCH + sizeof(sljit_sw); +common->optimized_cbracket = (pcre_uint8 *)SLJIT_MALLOC(re->top_bracket + 1); +if (!common->optimized_cbracket) + return; +#if defined DEBUG_FORCE_UNOPTIMIZED_CBRAS && DEBUG_FORCE_UNOPTIMIZED_CBRAS == 1 +memset(common->optimized_cbracket, 0, re->top_bracket + 1); +#else +memset(common->optimized_cbracket, 1, re->top_bracket + 1); +#endif + +SLJIT_ASSERT(*common->start == OP_BRA && ccend[-(1 + LINK_SIZE)] == OP_KET); +#if defined DEBUG_FORCE_UNOPTIMIZED_CBRAS && DEBUG_FORCE_UNOPTIMIZED_CBRAS == 2 +common->capture_last_ptr = common->ovector_start; +common->ovector_start += sizeof(sljit_sw); +#endif +if (!check_opcode_types(common, common->start, ccend)) + { + SLJIT_FREE(common->optimized_cbracket); + return; + } + +/* Checking flags and updating ovector_start. */ +if (mode == JIT_COMPILE && (re->flags & PCRE_REQCHSET) != 0 && (re->options & PCRE_NO_START_OPTIMIZE) == 0) + { + common->req_char_ptr = common->ovector_start; + common->ovector_start += sizeof(sljit_sw); + } +if (mode != JIT_COMPILE) + { + common->start_used_ptr = common->ovector_start; + common->ovector_start += sizeof(sljit_sw); + if (mode == JIT_PARTIAL_SOFT_COMPILE) + { + common->hit_start = common->ovector_start; + common->ovector_start += 2 * sizeof(sljit_sw); + } + else + { + SLJIT_ASSERT(mode == JIT_PARTIAL_HARD_COMPILE); + common->needs_start_ptr = TRUE; + } + } +if ((re->options & PCRE_FIRSTLINE) != 0) + { + common->first_line_end = common->ovector_start; + common->ovector_start += sizeof(sljit_sw); + } +#if defined DEBUG_FORCE_CONTROL_HEAD && DEBUG_FORCE_CONTROL_HEAD +common->control_head_ptr = 1; +#endif +if (common->control_head_ptr != 0) + { + common->control_head_ptr = common->ovector_start; + common->ovector_start += sizeof(sljit_sw); + } +if (common->needs_start_ptr && common->has_set_som) + { + /* Saving the real start pointer is necessary. */ + common->start_ptr = common->ovector_start; + common->ovector_start += sizeof(sljit_sw); + } +else + common->needs_start_ptr = FALSE; + +/* Aligning ovector to even number of sljit words. */ +if ((common->ovector_start & sizeof(sljit_sw)) != 0) + common->ovector_start += sizeof(sljit_sw); + +if (common->start_ptr == 0) + common->start_ptr = OVECTOR(0); + +/* Capturing brackets cannot be optimized if callouts are allowed. */ +if (common->capture_last_ptr != 0) + memset(common->optimized_cbracket, 0, re->top_bracket + 1); + +SLJIT_ASSERT(!(common->req_char_ptr != 0 && common->start_used_ptr != 0)); +common->cbra_ptr = OVECTOR_START + (re->top_bracket + 1) * 2 * sizeof(sljit_sw); + +total_length = ccend - common->start; +common->private_data_ptrs = (sljit_si *)SLJIT_MALLOC(total_length * (sizeof(sljit_si) + (common->has_then ? 1 : 0))); +if (!common->private_data_ptrs) + { + SLJIT_FREE(common->optimized_cbracket); + return; + } +memset(common->private_data_ptrs, 0, total_length * sizeof(sljit_si)); + +private_data_size = common->cbra_ptr + (re->top_bracket + 1) * sizeof(sljit_sw); +set_private_data_ptrs(common, &private_data_size, ccend); +if (private_data_size > SLJIT_MAX_LOCAL_SIZE) + { + SLJIT_FREE(common->private_data_ptrs); + SLJIT_FREE(common->optimized_cbracket); + return; + } + +if (common->has_then) + { + common->then_offsets = (pcre_uint8 *)(common->private_data_ptrs + total_length); + memset(common->then_offsets, 0, total_length); + set_then_offsets(common, common->start, NULL); + } + +if (common->read_only_data_size > 0) + { + common->read_only_data = (sljit_uw *)SLJIT_MALLOC(common->read_only_data_size); + if (common->read_only_data == NULL) + { + SLJIT_FREE(common->optimized_cbracket); + SLJIT_FREE(common->private_data_ptrs); + return; + } + common->read_only_data_ptr = common->read_only_data; + } + +compiler = sljit_create_compiler(); +if (!compiler) + { + SLJIT_FREE(common->optimized_cbracket); + SLJIT_FREE(common->private_data_ptrs); + if (common->read_only_data) + SLJIT_FREE(common->read_only_data); + return; + } +common->compiler = compiler; + +/* Main pcre_jit_exec entry. */ +sljit_emit_enter(compiler, 1, 5, 5, private_data_size); + +/* Register init. */ +reset_ovector(common, (re->top_bracket + 1) * 2); +if (common->req_char_ptr != 0) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->req_char_ptr, SLJIT_SCRATCH_REG1, 0); + +OP1(SLJIT_MOV, ARGUMENTS, 0, SLJIT_SAVED_REG1, 0); +OP1(SLJIT_MOV, TMP1, 0, SLJIT_SAVED_REG1, 0); +OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, str)); +OP1(SLJIT_MOV, STR_END, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, end)); +OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, stack)); +OP1(SLJIT_MOV_UI, TMP1, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, limit_match)); +OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(TMP2), SLJIT_OFFSETOF(struct sljit_stack, base)); +OP1(SLJIT_MOV, STACK_LIMIT, 0, SLJIT_MEM1(TMP2), SLJIT_OFFSETOF(struct sljit_stack, limit)); +OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), LIMIT_MATCH, TMP1, 0); + +if (mode == JIT_PARTIAL_SOFT_COMPILE) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->hit_start, SLJIT_IMM, -1); +if (common->mark_ptr != 0) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->mark_ptr, SLJIT_IMM, 0); +if (common->control_head_ptr != 0) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->control_head_ptr, SLJIT_IMM, 0); + +/* Main part of the matching */ +if ((re->options & PCRE_ANCHORED) == 0) + { + mainloop_label = mainloop_entry(common, (re->flags & PCRE_HASCRORLF) != 0, (re->options & PCRE_FIRSTLINE) != 0); + continue_match_label = LABEL(); + /* Forward search if possible. */ + if ((re->options & PCRE_NO_START_OPTIMIZE) == 0) + { + if (mode == JIT_COMPILE && fast_forward_first_n_chars(common, (re->options & PCRE_FIRSTLINE) != 0)) + { + /* If read_only_data is reallocated, we might have an allocation failure. */ + if (common->read_only_data_size > 0 && common->read_only_data == NULL) + { + sljit_free_compiler(compiler); + SLJIT_FREE(common->optimized_cbracket); + SLJIT_FREE(common->private_data_ptrs); + return; + } + } + else if ((re->flags & PCRE_FIRSTSET) != 0) + fast_forward_first_char(common, (pcre_uchar)re->first_char, (re->flags & PCRE_FCH_CASELESS) != 0, (re->options & PCRE_FIRSTLINE) != 0); + else if ((re->flags & PCRE_STARTLINE) != 0) + fast_forward_newline(common, (re->options & PCRE_FIRSTLINE) != 0); + else if ((re->flags & PCRE_STARTLINE) == 0 && study != NULL && (study->flags & PCRE_STUDY_MAPPED) != 0) + fast_forward_start_bits(common, study->start_bits, (re->options & PCRE_FIRSTLINE) != 0); + } + } +else + continue_match_label = LABEL(); + +if (mode == JIT_COMPILE && study->minlength > 0 && (re->options & PCRE_NO_START_OPTIMIZE) == 0) + { + OP1(SLJIT_MOV, SLJIT_RETURN_REG, 0, SLJIT_IMM, PCRE_ERROR_NOMATCH); + OP2(SLJIT_ADD, TMP2, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(study->minlength)); + minlength_check_failed = CMP(SLJIT_C_GREATER, TMP2, 0, STR_END, 0); + } +if (common->req_char_ptr != 0) + reqbyte_notfound = search_requested_char(common, (pcre_uchar)re->req_char, (re->flags & PCRE_RCH_CASELESS) != 0, (re->flags & PCRE_FIRSTSET) != 0); + +/* Store the current STR_PTR in OVECTOR(0). */ +OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(0), STR_PTR, 0); +/* Copy the limit of allowed recursions. */ +OP1(SLJIT_MOV, COUNT_MATCH, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), LIMIT_MATCH); +if (common->capture_last_ptr != 0) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->capture_last_ptr, SLJIT_IMM, -1); + +if (common->needs_start_ptr) + { + SLJIT_ASSERT(common->start_ptr != OVECTOR(0)); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->start_ptr, STR_PTR, 0); + } +else + SLJIT_ASSERT(common->start_ptr == OVECTOR(0)); + +/* Copy the beginning of the string. */ +if (mode == JIT_PARTIAL_SOFT_COMPILE) + { + jump = CMP(SLJIT_C_NOT_EQUAL, SLJIT_MEM1(SLJIT_LOCALS_REG), common->hit_start, SLJIT_IMM, -1); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->start_used_ptr, STR_PTR, 0); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->hit_start + sizeof(sljit_sw), STR_PTR, 0); + JUMPHERE(jump); + } +else if (mode == JIT_PARTIAL_HARD_COMPILE) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->start_used_ptr, STR_PTR, 0); + +compile_matchingpath(common, common->start, ccend, &rootbacktrack); +if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) + { + sljit_free_compiler(compiler); + SLJIT_FREE(common->optimized_cbracket); + SLJIT_FREE(common->private_data_ptrs); + if (common->read_only_data) + SLJIT_FREE(common->read_only_data); + return; + } + +if (common->might_be_empty) + { + empty_match = CMP(SLJIT_C_EQUAL, STR_PTR, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), OVECTOR(0)); + empty_match_found_label = LABEL(); + } + +common->accept_label = LABEL(); +if (common->accept != NULL) + set_jumps(common->accept, common->accept_label); + +/* This means we have a match. Update the ovector. */ +copy_ovector(common, re->top_bracket + 1); +common->quit_label = common->forced_quit_label = LABEL(); +if (common->quit != NULL) + set_jumps(common->quit, common->quit_label); +if (common->forced_quit != NULL) + set_jumps(common->forced_quit, common->forced_quit_label); +if (minlength_check_failed != NULL) + SET_LABEL(minlength_check_failed, common->forced_quit_label); +sljit_emit_return(compiler, SLJIT_MOV, SLJIT_RETURN_REG, 0); + +if (mode != JIT_COMPILE) + { + common->partialmatchlabel = LABEL(); + set_jumps(common->partialmatch, common->partialmatchlabel); + return_with_partial_match(common, common->quit_label); + } + +if (common->might_be_empty) + empty_match_backtrack_label = LABEL(); +compile_backtrackingpath(common, rootbacktrack.top); +if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) + { + sljit_free_compiler(compiler); + SLJIT_FREE(common->optimized_cbracket); + SLJIT_FREE(common->private_data_ptrs); + if (common->read_only_data) + SLJIT_FREE(common->read_only_data); + return; + } + +SLJIT_ASSERT(rootbacktrack.prev == NULL); +reset_match_label = LABEL(); + +if (mode == JIT_PARTIAL_SOFT_COMPILE) + { + /* Update hit_start only in the first time. */ + jump = CMP(SLJIT_C_NOT_EQUAL, SLJIT_MEM1(SLJIT_LOCALS_REG), common->hit_start, SLJIT_IMM, 0); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->start_used_ptr); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->start_used_ptr, SLJIT_IMM, -1); + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), common->hit_start, TMP1, 0); + JUMPHERE(jump); + } + +/* Check we have remaining characters. */ +if ((re->options & PCRE_ANCHORED) == 0 && (re->options & PCRE_FIRSTLINE) != 0) + { + SLJIT_ASSERT(common->first_line_end != 0); + OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->first_line_end); + } + +OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), common->start_ptr); + +if ((re->options & PCRE_ANCHORED) == 0) + { + if (common->ff_newline_shortcut != NULL) + { + if ((re->options & PCRE_FIRSTLINE) == 0) + CMPTO(SLJIT_C_LESS, STR_PTR, 0, STR_END, 0, common->ff_newline_shortcut); + /* There cannot be more newlines here. */ + } + else + { + if ((re->options & PCRE_FIRSTLINE) == 0) + CMPTO(SLJIT_C_LESS, STR_PTR, 0, STR_END, 0, mainloop_label); + else + CMPTO(SLJIT_C_LESS, STR_PTR, 0, TMP1, 0, mainloop_label); + } + } + +/* No more remaining characters. */ +if (reqbyte_notfound != NULL) + JUMPHERE(reqbyte_notfound); + +if (mode == JIT_PARTIAL_SOFT_COMPILE) + CMPTO(SLJIT_C_NOT_EQUAL, SLJIT_MEM1(SLJIT_LOCALS_REG), common->hit_start, SLJIT_IMM, -1, common->partialmatchlabel); + +OP1(SLJIT_MOV, SLJIT_RETURN_REG, 0, SLJIT_IMM, PCRE_ERROR_NOMATCH); +JUMPTO(SLJIT_JUMP, common->quit_label); + +flush_stubs(common); + +if (common->might_be_empty) + { + JUMPHERE(empty_match); + OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); + OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, notempty)); + CMPTO(SLJIT_C_NOT_EQUAL, TMP2, 0, SLJIT_IMM, 0, empty_match_backtrack_label); + OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, notempty_atstart)); + CMPTO(SLJIT_C_EQUAL, TMP2, 0, SLJIT_IMM, 0, empty_match_found_label); + OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, str)); + CMPTO(SLJIT_C_NOT_EQUAL, TMP2, 0, STR_PTR, 0, empty_match_found_label); + JUMPTO(SLJIT_JUMP, empty_match_backtrack_label); + } + +common->currententry = common->entries; +common->local_exit = TRUE; +quit_label = common->quit_label; +while (common->currententry != NULL) + { + /* Might add new entries. */ + compile_recurse(common); + if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) + { + sljit_free_compiler(compiler); + SLJIT_FREE(common->optimized_cbracket); + SLJIT_FREE(common->private_data_ptrs); + if (common->read_only_data) + SLJIT_FREE(common->read_only_data); + return; + } + flush_stubs(common); + common->currententry = common->currententry->next; + } +common->local_exit = FALSE; +common->quit_label = quit_label; + +/* Allocating stack, returns with PCRE_ERROR_JIT_STACKLIMIT if fails. */ +/* This is a (really) rare case. */ +set_jumps(common->stackalloc, LABEL()); +/* RETURN_ADDR is not a saved register. */ +sljit_emit_fast_enter(compiler, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS0); +OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS1, TMP2, 0); +OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); +OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, stack)); +OP1(SLJIT_MOV, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(struct sljit_stack, top), STACK_TOP, 0); +OP2(SLJIT_ADD, TMP2, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(struct sljit_stack, limit), SLJIT_IMM, STACK_GROWTH_RATE); + +sljit_emit_ijump(compiler, SLJIT_CALL2, SLJIT_IMM, SLJIT_FUNC_OFFSET(sljit_stack_resize)); +jump = CMP(SLJIT_C_NOT_EQUAL, SLJIT_RETURN_REG, 0, SLJIT_IMM, 0); +OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); +OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, stack)); +OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(struct sljit_stack, top)); +OP1(SLJIT_MOV, STACK_LIMIT, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(struct sljit_stack, limit)); +OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS1); +sljit_emit_fast_return(compiler, SLJIT_MEM1(SLJIT_LOCALS_REG), LOCALS0); + +/* Allocation failed. */ +JUMPHERE(jump); +/* We break the return address cache here, but this is a really rare case. */ +OP1(SLJIT_MOV, SLJIT_RETURN_REG, 0, SLJIT_IMM, PCRE_ERROR_JIT_STACKLIMIT); +JUMPTO(SLJIT_JUMP, common->quit_label); + +/* Call limit reached. */ +set_jumps(common->calllimit, LABEL()); +OP1(SLJIT_MOV, SLJIT_RETURN_REG, 0, SLJIT_IMM, PCRE_ERROR_MATCHLIMIT); +JUMPTO(SLJIT_JUMP, common->quit_label); + +if (common->revertframes != NULL) + { + set_jumps(common->revertframes, LABEL()); + do_revertframes(common); + } +if (common->wordboundary != NULL) + { + set_jumps(common->wordboundary, LABEL()); + check_wordboundary(common); + } +if (common->anynewline != NULL) + { + set_jumps(common->anynewline, LABEL()); + check_anynewline(common); + } +if (common->hspace != NULL) + { + set_jumps(common->hspace, LABEL()); + check_hspace(common); + } +if (common->vspace != NULL) + { + set_jumps(common->vspace, LABEL()); + check_vspace(common); + } +if (common->casefulcmp != NULL) + { + set_jumps(common->casefulcmp, LABEL()); + do_casefulcmp(common); + } +if (common->caselesscmp != NULL) + { + set_jumps(common->caselesscmp, LABEL()); + do_caselesscmp(common); + } +if (common->reset_match != NULL) + { + set_jumps(common->reset_match, LABEL()); + do_reset_match(common, (re->top_bracket + 1) * 2); + CMPTO(SLJIT_C_GREATER, STR_PTR, 0, TMP1, 0, continue_match_label); + OP1(SLJIT_MOV, STR_PTR, 0, TMP1, 0); + JUMPTO(SLJIT_JUMP, reset_match_label); + } +#ifdef SUPPORT_UTF +#ifdef COMPILE_PCRE8 +if (common->utfreadchar != NULL) + { + set_jumps(common->utfreadchar, LABEL()); + do_utfreadchar(common); + } +if (common->utfreadchar16 != NULL) + { + set_jumps(common->utfreadchar16, LABEL()); + do_utfreadchar16(common); + } +if (common->utfreadtype8 != NULL) + { + set_jumps(common->utfreadtype8, LABEL()); + do_utfreadtype8(common); + } +#endif /* COMPILE_PCRE8 */ +#endif /* SUPPORT_UTF */ +#ifdef SUPPORT_UCP +if (common->getucd != NULL) + { + set_jumps(common->getucd, LABEL()); + do_getucd(common); + } +#endif + +SLJIT_ASSERT(common->read_only_data + (common->read_only_data_size >> SLJIT_WORD_SHIFT) == common->read_only_data_ptr); +SLJIT_FREE(common->optimized_cbracket); +SLJIT_FREE(common->private_data_ptrs); + +executable_func = sljit_generate_code(compiler); +executable_size = sljit_get_generated_code_size(compiler); +label_addr = common->label_addrs; +while (label_addr != NULL) + { + *label_addr->addr = sljit_get_label_addr(label_addr->label); + label_addr = label_addr->next; + } +sljit_free_compiler(compiler); +if (executable_func == NULL) + { + if (common->read_only_data) + SLJIT_FREE(common->read_only_data); + return; + } + +/* Reuse the function descriptor if possible. */ +if ((extra->flags & PCRE_EXTRA_EXECUTABLE_JIT) != 0 && extra->executable_jit != NULL) + functions = (executable_functions *)extra->executable_jit; +else + { + /* Note: If your memory-checker has flagged the allocation below as a + * memory leak, it is probably because you either forgot to call + * pcre_free_study() (or pcre16_free_study()) on the pcre_extra (or + * pcre16_extra) object, or you called said function after having + * cleared the PCRE_EXTRA_EXECUTABLE_JIT bit from the "flags" field + * of the object. (The function will only free the JIT data if the + * bit remains set, as the bit indicates that the pointer to the data + * is valid.) + */ + functions = SLJIT_MALLOC(sizeof(executable_functions)); + if (functions == NULL) + { + /* This case is highly unlikely since we just recently + freed a lot of memory. Not impossible though. */ + sljit_free_code(executable_func); + if (common->read_only_data) + SLJIT_FREE(common->read_only_data); + return; + } + memset(functions, 0, sizeof(executable_functions)); + functions->top_bracket = (re->top_bracket + 1) * 2; + functions->limit_match = (re->flags & PCRE_MLSET) != 0 ? re->limit_match : 0; + extra->executable_jit = functions; + extra->flags |= PCRE_EXTRA_EXECUTABLE_JIT; + } + +functions->executable_funcs[mode] = executable_func; +functions->read_only_data[mode] = common->read_only_data; +functions->executable_sizes[mode] = executable_size; +} + +static int jit_machine_stack_exec(jit_arguments *arguments, void* executable_func) +{ +union { + void* executable_func; + jit_function call_executable_func; +} convert_executable_func; +pcre_uint8 local_space[MACHINE_STACK_SIZE]; +struct sljit_stack local_stack; + +local_stack.top = (sljit_sw)&local_space; +local_stack.base = local_stack.top; +local_stack.limit = local_stack.base + MACHINE_STACK_SIZE; +local_stack.max_limit = local_stack.limit; +arguments->stack = &local_stack; +convert_executable_func.executable_func = executable_func; +return convert_executable_func.call_executable_func(arguments); +} + +int +PRIV(jit_exec)(const PUBL(extra) *extra_data, const pcre_uchar *subject, + int length, int start_offset, int options, int *offsets, int offset_count) +{ +executable_functions *functions = (executable_functions *)extra_data->executable_jit; +union { + void* executable_func; + jit_function call_executable_func; +} convert_executable_func; +jit_arguments arguments; +int max_offset_count; +int retval; +int mode = JIT_COMPILE; + +if ((options & PCRE_PARTIAL_HARD) != 0) + mode = JIT_PARTIAL_HARD_COMPILE; +else if ((options & PCRE_PARTIAL_SOFT) != 0) + mode = JIT_PARTIAL_SOFT_COMPILE; + +if (functions->executable_funcs[mode] == NULL) + return PCRE_ERROR_JIT_BADOPTION; + +/* Sanity checks should be handled by pcre_exec. */ +arguments.str = subject + start_offset; +arguments.begin = subject; +arguments.end = subject + length; +arguments.mark_ptr = NULL; +/* JIT decreases this value less frequently than the interpreter. */ +arguments.limit_match = ((extra_data->flags & PCRE_EXTRA_MATCH_LIMIT) == 0) ? MATCH_LIMIT : (pcre_uint32)(extra_data->match_limit); +if (functions->limit_match != 0 && functions->limit_match < arguments.limit_match) + arguments.limit_match = functions->limit_match; +arguments.notbol = (options & PCRE_NOTBOL) != 0; +arguments.noteol = (options & PCRE_NOTEOL) != 0; +arguments.notempty = (options & PCRE_NOTEMPTY) != 0; +arguments.notempty_atstart = (options & PCRE_NOTEMPTY_ATSTART) != 0; +arguments.offsets = offsets; +arguments.callout_data = (extra_data->flags & PCRE_EXTRA_CALLOUT_DATA) != 0 ? extra_data->callout_data : NULL; +arguments.real_offset_count = offset_count; + +/* pcre_exec() rounds offset_count to a multiple of 3, and then uses only 2/3 of +the output vector for storing captured strings, with the remainder used as +workspace. We don't need the workspace here. For compatibility, we limit the +number of captured strings in the same way as pcre_exec(), so that the user +gets the same result with and without JIT. */ + +if (offset_count != 2) + offset_count = ((offset_count - (offset_count % 3)) * 2) / 3; +max_offset_count = functions->top_bracket; +if (offset_count > max_offset_count) + offset_count = max_offset_count; +arguments.offset_count = offset_count; + +if (functions->callback) + arguments.stack = (struct sljit_stack *)functions->callback(functions->userdata); +else + arguments.stack = (struct sljit_stack *)functions->userdata; + +if (arguments.stack == NULL) + retval = jit_machine_stack_exec(&arguments, functions->executable_funcs[mode]); +else + { + convert_executable_func.executable_func = functions->executable_funcs[mode]; + retval = convert_executable_func.call_executable_func(&arguments); + } + +if (retval * 2 > offset_count) + retval = 0; +if ((extra_data->flags & PCRE_EXTRA_MARK) != 0) + *(extra_data->mark) = arguments.mark_ptr; + +return retval; +} + +#if defined COMPILE_PCRE8 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre_jit_exec(const pcre *argument_re, const pcre_extra *extra_data, + PCRE_SPTR subject, int length, int start_offset, int options, + int *offsets, int offset_count, pcre_jit_stack *stack) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre16_jit_exec(const pcre16 *argument_re, const pcre16_extra *extra_data, + PCRE_SPTR16 subject, int length, int start_offset, int options, + int *offsets, int offset_count, pcre16_jit_stack *stack) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre32_jit_exec(const pcre32 *argument_re, const pcre32_extra *extra_data, + PCRE_SPTR32 subject, int length, int start_offset, int options, + int *offsets, int offset_count, pcre32_jit_stack *stack) +#endif +{ +pcre_uchar *subject_ptr = (pcre_uchar *)subject; +executable_functions *functions = (executable_functions *)extra_data->executable_jit; +union { + void* executable_func; + jit_function call_executable_func; +} convert_executable_func; +jit_arguments arguments; +int max_offset_count; +int retval; +int mode = JIT_COMPILE; + +SLJIT_UNUSED_ARG(argument_re); + +/* Plausibility checks */ +if ((options & ~PUBLIC_JIT_EXEC_OPTIONS) != 0) return PCRE_ERROR_JIT_BADOPTION; + +if ((options & PCRE_PARTIAL_HARD) != 0) + mode = JIT_PARTIAL_HARD_COMPILE; +else if ((options & PCRE_PARTIAL_SOFT) != 0) + mode = JIT_PARTIAL_SOFT_COMPILE; + +if (functions->executable_funcs[mode] == NULL) + return PCRE_ERROR_JIT_BADOPTION; + +/* Sanity checks should be handled by pcre_exec. */ +arguments.stack = (struct sljit_stack *)stack; +arguments.str = subject_ptr + start_offset; +arguments.begin = subject_ptr; +arguments.end = subject_ptr + length; +arguments.mark_ptr = NULL; +/* JIT decreases this value less frequently than the interpreter. */ +arguments.limit_match = ((extra_data->flags & PCRE_EXTRA_MATCH_LIMIT) == 0) ? MATCH_LIMIT : (pcre_uint32)(extra_data->match_limit); +if (functions->limit_match != 0 && functions->limit_match < arguments.limit_match) + arguments.limit_match = functions->limit_match; +arguments.notbol = (options & PCRE_NOTBOL) != 0; +arguments.noteol = (options & PCRE_NOTEOL) != 0; +arguments.notempty = (options & PCRE_NOTEMPTY) != 0; +arguments.notempty_atstart = (options & PCRE_NOTEMPTY_ATSTART) != 0; +arguments.offsets = offsets; +arguments.callout_data = (extra_data->flags & PCRE_EXTRA_CALLOUT_DATA) != 0 ? extra_data->callout_data : NULL; +arguments.real_offset_count = offset_count; + +/* pcre_exec() rounds offset_count to a multiple of 3, and then uses only 2/3 of +the output vector for storing captured strings, with the remainder used as +workspace. We don't need the workspace here. For compatibility, we limit the +number of captured strings in the same way as pcre_exec(), so that the user +gets the same result with and without JIT. */ + +if (offset_count != 2) + offset_count = ((offset_count - (offset_count % 3)) * 2) / 3; +max_offset_count = functions->top_bracket; +if (offset_count > max_offset_count) + offset_count = max_offset_count; +arguments.offset_count = offset_count; + +convert_executable_func.executable_func = functions->executable_funcs[mode]; +retval = convert_executable_func.call_executable_func(&arguments); + +if (retval * 2 > offset_count) + retval = 0; +if ((extra_data->flags & PCRE_EXTRA_MARK) != 0) + *(extra_data->mark) = arguments.mark_ptr; + +return retval; +} + +void +PRIV(jit_free)(void *executable_funcs) +{ +int i; +executable_functions *functions = (executable_functions *)executable_funcs; +for (i = 0; i < JIT_NUMBER_OF_COMPILE_MODES; i++) + { + if (functions->executable_funcs[i] != NULL) + sljit_free_code(functions->executable_funcs[i]); + if (functions->read_only_data[i] != NULL) + SLJIT_FREE(functions->read_only_data[i]); + } +SLJIT_FREE(functions); +} + +int +PRIV(jit_get_size)(void *executable_funcs) +{ +int i; +sljit_uw size = 0; +sljit_uw *executable_sizes = ((executable_functions *)executable_funcs)->executable_sizes; +for (i = 0; i < JIT_NUMBER_OF_COMPILE_MODES; i++) + size += executable_sizes[i]; +return (int)size; +} + +const char* +PRIV(jit_get_target)(void) +{ +return sljit_get_platform_name(); +} + +#if defined COMPILE_PCRE8 +PCRE_EXP_DECL pcre_jit_stack * +pcre_jit_stack_alloc(int startsize, int maxsize) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DECL pcre16_jit_stack * +pcre16_jit_stack_alloc(int startsize, int maxsize) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DECL pcre32_jit_stack * +pcre32_jit_stack_alloc(int startsize, int maxsize) +#endif +{ +if (startsize < 1 || maxsize < 1) + return NULL; +if (startsize > maxsize) + startsize = maxsize; +startsize = (startsize + STACK_GROWTH_RATE - 1) & ~(STACK_GROWTH_RATE - 1); +maxsize = (maxsize + STACK_GROWTH_RATE - 1) & ~(STACK_GROWTH_RATE - 1); +return (PUBL(jit_stack)*)sljit_allocate_stack(startsize, maxsize); +} + +#if defined COMPILE_PCRE8 +PCRE_EXP_DECL void +pcre_jit_stack_free(pcre_jit_stack *stack) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DECL void +pcre16_jit_stack_free(pcre16_jit_stack *stack) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DECL void +pcre32_jit_stack_free(pcre32_jit_stack *stack) +#endif +{ +sljit_free_stack((struct sljit_stack *)stack); +} + +#if defined COMPILE_PCRE8 +PCRE_EXP_DECL void +pcre_assign_jit_stack(pcre_extra *extra, pcre_jit_callback callback, void *userdata) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DECL void +pcre16_assign_jit_stack(pcre16_extra *extra, pcre16_jit_callback callback, void *userdata) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DECL void +pcre32_assign_jit_stack(pcre32_extra *extra, pcre32_jit_callback callback, void *userdata) +#endif +{ +executable_functions *functions; +if (extra != NULL && + (extra->flags & PCRE_EXTRA_EXECUTABLE_JIT) != 0 && + extra->executable_jit != NULL) + { + functions = (executable_functions *)extra->executable_jit; + functions->callback = callback; + functions->userdata = userdata; + } +} + +#if defined COMPILE_PCRE8 +PCRE_EXP_DECL void +pcre_jit_free_unused_memory(void) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DECL void +pcre16_jit_free_unused_memory(void) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DECL void +pcre32_jit_free_unused_memory(void) +#endif +{ +sljit_free_unused_memory_exec(); +} + +#else /* SUPPORT_JIT */ + +/* These are dummy functions to avoid linking errors when JIT support is not +being compiled. */ + +#if defined COMPILE_PCRE8 +PCRE_EXP_DECL pcre_jit_stack * +pcre_jit_stack_alloc(int startsize, int maxsize) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DECL pcre16_jit_stack * +pcre16_jit_stack_alloc(int startsize, int maxsize) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DECL pcre32_jit_stack * +pcre32_jit_stack_alloc(int startsize, int maxsize) +#endif +{ +(void)startsize; +(void)maxsize; +return NULL; +} + +#if defined COMPILE_PCRE8 +PCRE_EXP_DECL void +pcre_jit_stack_free(pcre_jit_stack *stack) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DECL void +pcre16_jit_stack_free(pcre16_jit_stack *stack) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DECL void +pcre32_jit_stack_free(pcre32_jit_stack *stack) +#endif +{ +(void)stack; +} + +#if defined COMPILE_PCRE8 +PCRE_EXP_DECL void +pcre_assign_jit_stack(pcre_extra *extra, pcre_jit_callback callback, void *userdata) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DECL void +pcre16_assign_jit_stack(pcre16_extra *extra, pcre16_jit_callback callback, void *userdata) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DECL void +pcre32_assign_jit_stack(pcre32_extra *extra, pcre32_jit_callback callback, void *userdata) +#endif +{ +(void)extra; +(void)callback; +(void)userdata; +} + +#if defined COMPILE_PCRE8 +PCRE_EXP_DECL void +pcre_jit_free_unused_memory(void) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DECL void +pcre16_jit_free_unused_memory(void) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DECL void +pcre32_jit_free_unused_memory(void) +#endif +{ +} + +#endif + +/* End of pcre_jit_compile.c */ diff --git a/plugins/Pcre16/src/pcre_maketables.c b/plugins/Pcre16/src/pcre_maketables.c new file mode 100644 index 0000000000..a44a6eaa90 --- /dev/null +++ b/plugins/Pcre16/src/pcre_maketables.c @@ -0,0 +1,156 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains the external function pcre_maketables(), which builds +character tables for PCRE in the current locale. The file is compiled on its +own as part of the PCRE library. However, it is also included in the +compilation of dftables.c, in which case the macro DFTABLES is defined. */ + + +#ifndef DFTABLES +# ifdef HAVE_CONFIG_H +# include "config.h" +# endif +# include "pcre_internal.h" +#endif + + +/************************************************* +* Create PCRE character tables * +*************************************************/ + +/* This function builds a set of character tables for use by PCRE and returns +a pointer to them. They are build using the ctype functions, and consequently +their contents will depend upon the current locale setting. When compiled as +part of the library, the store is obtained via PUBL(malloc)(), but when +compiled inside dftables, use malloc(). + +Arguments: none +Returns: pointer to the contiguous block of data +*/ + +#if defined COMPILE_PCRE8 +const unsigned char * +pcre_maketables(void) +#elif defined COMPILE_PCRE16 +const unsigned char * +pcre16_maketables(void) +#elif defined COMPILE_PCRE32 +const unsigned char * +pcre32_maketables(void) +#endif +{ +unsigned char *yield, *p; +int i; + +#ifndef DFTABLES +yield = (unsigned char*)(PUBL(malloc))(tables_length); +#else +yield = (unsigned char*)malloc(tables_length); +#endif + +if (yield == NULL) return NULL; +p = yield; + +/* First comes the lower casing table */ + +for (i = 0; i < 256; i++) *p++ = tolower(i); + +/* Next the case-flipping table */ + +for (i = 0; i < 256; i++) *p++ = islower(i)? toupper(i) : tolower(i); + +/* Then the character class tables. Don't try to be clever and save effort on +exclusive ones - in some locales things may be different. + +Note that the table for "space" includes everything "isspace" gives, including +VT in the default locale. This makes it work for the POSIX class [:space:]. +From release 8.34 is is also correct for Perl space, because Perl added VT at +release 5.18. + +Note also that it is possible for a character to be alnum or alpha without +being lower or upper, such as "male and female ordinals" (\xAA and \xBA) in the +fr_FR locale (at least under Debian Linux's locales as of 12/2005). So we must +test for alnum specially. */ + +memset(p, 0, cbit_length); +for (i = 0; i < 256; i++) + { + if (isdigit(i)) p[cbit_digit + i/8] |= 1 << (i&7); + if (isupper(i)) p[cbit_upper + i/8] |= 1 << (i&7); + if (islower(i)) p[cbit_lower + i/8] |= 1 << (i&7); + if (isalnum(i)) p[cbit_word + i/8] |= 1 << (i&7); + if (i == '_') p[cbit_word + i/8] |= 1 << (i&7); + if (isspace(i)) p[cbit_space + i/8] |= 1 << (i&7); + if (isxdigit(i))p[cbit_xdigit + i/8] |= 1 << (i&7); + if (isgraph(i)) p[cbit_graph + i/8] |= 1 << (i&7); + if (isprint(i)) p[cbit_print + i/8] |= 1 << (i&7); + if (ispunct(i)) p[cbit_punct + i/8] |= 1 << (i&7); + if (iscntrl(i)) p[cbit_cntrl + i/8] |= 1 << (i&7); + } +p += cbit_length; + +/* Finally, the character type table. In this, we used to exclude VT from the +white space chars, because Perl didn't recognize it as such for \s and for +comments within regexes. However, Perl changed at release 5.18, so PCRE changed +at release 8.34. */ + +for (i = 0; i < 256; i++) + { + int x = 0; + if (isspace(i)) x += ctype_space; + if (isalpha(i)) x += ctype_letter; + if (isdigit(i)) x += ctype_digit; + if (isxdigit(i)) x += ctype_xdigit; + if (isalnum(i) || i == '_') x += ctype_word; + + /* Note: strchr includes the terminating zero in the characters it considers. + In this instance, that is ok because we want binary zero to be flagged as a + meta-character, which in this sense is any character that terminates a run + of data characters. */ + + if (strchr("\\*+?{^.$|()[", i) != 0) x += ctype_meta; + *p++ = x; + } + +return yield; +} + +/* End of pcre_maketables.c */ diff --git a/plugins/Pcre16/src/pcre_newline.c b/plugins/Pcre16/src/pcre_newline.c new file mode 100644 index 0000000000..b8f5a4de19 --- /dev/null +++ b/plugins/Pcre16/src/pcre_newline.c @@ -0,0 +1,210 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains internal functions for testing newlines when more than +one kind of newline is to be recognized. When a newline is found, its length is +returned. In principle, we could implement several newline "types", each +referring to a different set of newline characters. At present, PCRE supports +only NLTYPE_FIXED, which gets handled without these functions, NLTYPE_ANYCRLF, +and NLTYPE_ANY. The full list of Unicode newline characters is taken from +http://unicode.org/unicode/reports/tr18/. */ + + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#include "pcre_internal.h" + + + +/************************************************* +* Check for newline at given position * +*************************************************/ + +/* It is guaranteed that the initial value of ptr is less than the end of the +string that is being processed. + +Arguments: + ptr pointer to possible newline + type the newline type + endptr pointer to the end of the string + lenptr where to return the length + utf TRUE if in utf mode + +Returns: TRUE or FALSE +*/ + +BOOL +PRIV(is_newline)(PCRE_PUCHAR ptr, int type, PCRE_PUCHAR endptr, int *lenptr, + BOOL utf) +{ +pcre_uint32 c; +(void)utf; +#ifdef SUPPORT_UTF +if (utf) + { + GETCHAR(c, ptr); + } +else +#endif /* SUPPORT_UTF */ + c = *ptr; + +/* Note that this function is called only for ANY or ANYCRLF. */ + +if (type == NLTYPE_ANYCRLF) switch(c) + { + case CHAR_LF: *lenptr = 1; return TRUE; + case CHAR_CR: *lenptr = (ptr < endptr - 1 && ptr[1] == CHAR_LF)? 2 : 1; + return TRUE; + default: return FALSE; + } + +/* NLTYPE_ANY */ + +else switch(c) + { +#ifdef EBCDIC + case CHAR_NEL: +#endif + case CHAR_LF: + case CHAR_VT: + case CHAR_FF: *lenptr = 1; return TRUE; + + case CHAR_CR: + *lenptr = (ptr < endptr - 1 && ptr[1] == CHAR_LF)? 2 : 1; + return TRUE; + +#ifndef EBCDIC +#ifdef COMPILE_PCRE8 + case CHAR_NEL: *lenptr = utf? 2 : 1; return TRUE; + case 0x2028: /* LS */ + case 0x2029: *lenptr = 3; return TRUE; /* PS */ +#else /* COMPILE_PCRE16 || COMPILE_PCRE32 */ + case CHAR_NEL: + case 0x2028: /* LS */ + case 0x2029: *lenptr = 1; return TRUE; /* PS */ +#endif /* COMPILE_PCRE8 */ +#endif /* Not EBCDIC */ + + default: return FALSE; + } +} + + + +/************************************************* +* Check for newline at previous position * +*************************************************/ + +/* It is guaranteed that the initial value of ptr is greater than the start of +the string that is being processed. + +Arguments: + ptr pointer to possible newline + type the newline type + startptr pointer to the start of the string + lenptr where to return the length + utf TRUE if in utf mode + +Returns: TRUE or FALSE +*/ + +BOOL +PRIV(was_newline)(PCRE_PUCHAR ptr, int type, PCRE_PUCHAR startptr, int *lenptr, + BOOL utf) +{ +pcre_uint32 c; +(void)utf; +ptr--; +#ifdef SUPPORT_UTF +if (utf) + { + BACKCHAR(ptr); + GETCHAR(c, ptr); + } +else +#endif /* SUPPORT_UTF */ + c = *ptr; + +/* Note that this function is called only for ANY or ANYCRLF. */ + +if (type == NLTYPE_ANYCRLF) switch(c) + { + case CHAR_LF: + *lenptr = (ptr > startptr && ptr[-1] == CHAR_CR)? 2 : 1; + return TRUE; + + case CHAR_CR: *lenptr = 1; return TRUE; + default: return FALSE; + } + +/* NLTYPE_ANY */ + +else switch(c) + { + case CHAR_LF: + *lenptr = (ptr > startptr && ptr[-1] == CHAR_CR)? 2 : 1; + return TRUE; + +#ifdef EBCDIC + case CHAR_NEL: +#endif + case CHAR_VT: + case CHAR_FF: + case CHAR_CR: *lenptr = 1; return TRUE; + +#ifndef EBCDIC +#ifdef COMPILE_PCRE8 + case CHAR_NEL: *lenptr = utf? 2 : 1; return TRUE; + case 0x2028: /* LS */ + case 0x2029: *lenptr = 3; return TRUE; /* PS */ +#else /* COMPILE_PCRE16 || COMPILE_PCRE32 */ + case CHAR_NEL: + case 0x2028: /* LS */ + case 0x2029: *lenptr = 1; return TRUE; /* PS */ +#endif /* COMPILE_PCRE8 */ +#endif /* NotEBCDIC */ + + default: return FALSE; + } +} + +/* End of pcre_newline.c */ diff --git a/plugins/Pcre16/src/pcre_refcount.c b/plugins/Pcre16/src/pcre_refcount.c new file mode 100644 index 0000000000..79efa90f21 --- /dev/null +++ b/plugins/Pcre16/src/pcre_refcount.c @@ -0,0 +1,92 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains the external function pcre_refcount(), which is an +auxiliary function that can be used to maintain a reference count in a compiled +pattern data block. This might be helpful in applications where the block is +shared by different users. */ + + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#include "pcre_internal.h" + + +/************************************************* +* Maintain reference count * +*************************************************/ + +/* The reference count is a 16-bit field, initialized to zero. It is not +possible to transfer a non-zero count from one host to a different host that +has a different byte order - though I can't see why anyone in their right mind +would ever want to do that! + +Arguments: + argument_re points to compiled code + adjust value to add to the count + +Returns: the (possibly updated) count value (a non-negative number), or + a negative error number +*/ + +#if defined COMPILE_PCRE8 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre_refcount(pcre *argument_re, int adjust) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre16_refcount(pcre16 *argument_re, int adjust) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DEFN int PCRE_CALL_CONVENTION +pcre32_refcount(pcre32 *argument_re, int adjust) +#endif +{ +REAL_PCRE *re = (REAL_PCRE *)argument_re; +if (re == NULL) return PCRE_ERROR_NULL; +if (re->magic_number != MAGIC_NUMBER) return PCRE_ERROR_BADMAGIC; +if ((re->flags & PCRE_MODE) == 0) return PCRE_ERROR_BADMODE; +re->ref_count = (-adjust > re->ref_count)? 0 : + (adjust + re->ref_count > 65535)? 65535 : + re->ref_count + adjust; +return re->ref_count; +} + +/* End of pcre_refcount.c */ diff --git a/plugins/Pcre16/src/pcre_string_utils.c b/plugins/Pcre16/src/pcre_string_utils.c new file mode 100644 index 0000000000..25eacc8507 --- /dev/null +++ b/plugins/Pcre16/src/pcre_string_utils.c @@ -0,0 +1,211 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2014 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains internal functions for comparing and finding the length +of strings for different data item sizes. */ + + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#include "pcre_internal.h" + +#ifndef COMPILE_PCRE8 + +/************************************************* +* Compare string utilities * +*************************************************/ + +/* The following two functions compares two strings. Basically a strcmp +for non 8 bit characters. + +Arguments: + str1 first string + str2 second string + +Returns: 0 if both string are equal (like strcmp), 1 otherwise +*/ + +int +PRIV(strcmp_uc_uc)(const pcre_uchar *str1, const pcre_uchar *str2) +{ +pcre_uchar c1; +pcre_uchar c2; + +while (*str1 != '\0' || *str2 != '\0') + { + c1 = *str1++; + c2 = *str2++; + if (c1 != c2) + return ((c1 > c2) << 1) - 1; + } +/* Both length and characters must be equal. */ +return 0; +} + +#ifdef COMPILE_PCRE32 + +int +PRIV(strcmp_uc_uc_utf)(const pcre_uchar *str1, const pcre_uchar *str2) +{ +pcre_uchar c1; +pcre_uchar c2; + +while (*str1 != '\0' || *str2 != '\0') + { + c1 = UCHAR21INC(str1); + c2 = UCHAR21INC(str2); + if (c1 != c2) + return ((c1 > c2) << 1) - 1; + } +/* Both length and characters must be equal. */ +return 0; +} + +#endif /* COMPILE_PCRE32 */ + +int +PRIV(strcmp_uc_c8)(const pcre_uchar *str1, const char *str2) +{ +const pcre_uint8 *ustr2 = (pcre_uint8 *)str2; +pcre_uchar c1; +pcre_uchar c2; + +while (*str1 != '\0' || *ustr2 != '\0') + { + c1 = *str1++; + c2 = (pcre_uchar)*ustr2++; + if (c1 != c2) + return ((c1 > c2) << 1) - 1; + } +/* Both length and characters must be equal. */ +return 0; +} + +#ifdef COMPILE_PCRE32 + +int +PRIV(strcmp_uc_c8_utf)(const pcre_uchar *str1, const char *str2) +{ +const pcre_uint8 *ustr2 = (pcre_uint8 *)str2; +pcre_uchar c1; +pcre_uchar c2; + +while (*str1 != '\0' || *ustr2 != '\0') + { + c1 = UCHAR21INC(str1); + c2 = (pcre_uchar)*ustr2++; + if (c1 != c2) + return ((c1 > c2) << 1) - 1; + } +/* Both length and characters must be equal. */ +return 0; +} + +#endif /* COMPILE_PCRE32 */ + +/* The following two functions compares two, fixed length +strings. Basically an strncmp for non 8 bit characters. + +Arguments: + str1 first string + str2 second string + num size of the string + +Returns: 0 if both string are equal (like strcmp), 1 otherwise +*/ + +int +PRIV(strncmp_uc_uc)(const pcre_uchar *str1, const pcre_uchar *str2, unsigned int num) +{ +pcre_uchar c1; +pcre_uchar c2; + +while (num-- > 0) + { + c1 = *str1++; + c2 = *str2++; + if (c1 != c2) + return ((c1 > c2) << 1) - 1; + } +/* Both length and characters must be equal. */ +return 0; +} + +int +PRIV(strncmp_uc_c8)(const pcre_uchar *str1, const char *str2, unsigned int num) +{ +const pcre_uint8 *ustr2 = (pcre_uint8 *)str2; +pcre_uchar c1; +pcre_uchar c2; + +while (num-- > 0) + { + c1 = *str1++; + c2 = (pcre_uchar)*ustr2++; + if (c1 != c2) + return ((c1 > c2) << 1) - 1; + } +/* Both length and characters must be equal. */ +return 0; +} + +/* The following function returns with the length of +a zero terminated string. Basically an strlen for non 8 bit characters. + +Arguments: + str string + +Returns: length of the string +*/ + +unsigned int +PRIV(strlen_uc)(const pcre_uchar *str) +{ +unsigned int len = 0; +while (*str++ != 0) + len++; +return len; +} + +#endif /* !COMPILE_PCRE8 */ + +/* End of pcre_string_utils.c */ diff --git a/plugins/Pcre16/src/pcre_study.c b/plugins/Pcre16/src/pcre_study.c new file mode 100644 index 0000000000..ab9510e20e --- /dev/null +++ b/plugins/Pcre16/src/pcre_study.c @@ -0,0 +1,1626 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains the external function pcre_study(), along with local +supporting functions. */ + + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#include "pcre_internal.h" + +#define SET_BIT(c) start_bits[c/8] |= (1 << (c&7)) + +/* Returns from set_start_bits() */ + +enum { SSB_FAIL, SSB_DONE, SSB_CONTINUE, SSB_UNKNOWN }; + + + +/************************************************* +* Find the minimum subject length for a group * +*************************************************/ + +/* Scan a parenthesized group and compute the minimum length of subject that +is needed to match it. This is a lower bound; it does not mean there is a +string of that length that matches. In UTF8 mode, the result is in characters +rather than bytes. + +Arguments: + re compiled pattern block + code pointer to start of group (the bracket) + startcode pointer to start of the whole pattern's code + options the compiling options + int RECURSE depth + +Returns: the minimum length + -1 if \C in UTF-8 mode or (*ACCEPT) was encountered + -2 internal error (missing capturing bracket) + -3 internal error (opcode not listed) +*/ + +static int +find_minlength(const REAL_PCRE *re, const pcre_uchar *code, + const pcre_uchar *startcode, int options, int recurse_depth) +{ +int length = -1; +/* PCRE_UTF16 has the same value as PCRE_UTF8. */ +BOOL utf = (options & PCRE_UTF8) != 0; +BOOL had_recurse = FALSE; +register int branchlength = 0; +register pcre_uchar *cc = (pcre_uchar *)code + 1 + LINK_SIZE; + +if (*code == OP_CBRA || *code == OP_SCBRA || + *code == OP_CBRAPOS || *code == OP_SCBRAPOS) cc += IMM2_SIZE; + +/* Scan along the opcodes for this branch. If we get to the end of the +branch, check the length against that of the other branches. */ + +for (;;) + { + int d, min; + pcre_uchar *cs, *ce; + register pcre_uchar op = *cc; + + switch (op) + { + case OP_COND: + case OP_SCOND: + + /* If there is only one branch in a condition, the implied branch has zero + length, so we don't add anything. This covers the DEFINE "condition" + automatically. */ + + cs = cc + GET(cc, 1); + if (*cs != OP_ALT) + { + cc = cs + 1 + LINK_SIZE; + break; + } + + /* Otherwise we can fall through and treat it the same as any other + subpattern. */ + + case OP_CBRA: + case OP_SCBRA: + case OP_BRA: + case OP_SBRA: + case OP_CBRAPOS: + case OP_SCBRAPOS: + case OP_BRAPOS: + case OP_SBRAPOS: + case OP_ONCE: + case OP_ONCE_NC: + d = find_minlength(re, cc, startcode, options, recurse_depth); + if (d < 0) return d; + branchlength += d; + do cc += GET(cc, 1); while (*cc == OP_ALT); + cc += 1 + LINK_SIZE; + break; + + /* ACCEPT makes things far too complicated; we have to give up. */ + + case OP_ACCEPT: + case OP_ASSERT_ACCEPT: + return -1; + + /* Reached end of a branch; if it's a ket it is the end of a nested + call. If it's ALT it is an alternation in a nested call. If it is END it's + the end of the outer call. All can be handled by the same code. If an + ACCEPT was previously encountered, use the length that was in force at that + time, and pass back the shortest ACCEPT length. */ + + case OP_ALT: + case OP_KET: + case OP_KETRMAX: + case OP_KETRMIN: + case OP_KETRPOS: + case OP_END: + if (length < 0 || (!had_recurse && branchlength < length)) + length = branchlength; + if (op != OP_ALT) return length; + cc += 1 + LINK_SIZE; + branchlength = 0; + had_recurse = FALSE; + break; + + /* Skip over assertive subpatterns */ + + case OP_ASSERT: + case OP_ASSERT_NOT: + case OP_ASSERTBACK: + case OP_ASSERTBACK_NOT: + do cc += GET(cc, 1); while (*cc == OP_ALT); + /* Fall through */ + + /* Skip over things that don't match chars */ + + case OP_REVERSE: + case OP_CREF: + case OP_DNCREF: + case OP_RREF: + case OP_DNRREF: + case OP_DEF: + case OP_CALLOUT: + case OP_SOD: + case OP_SOM: + case OP_EOD: + case OP_EODN: + case OP_CIRC: + case OP_CIRCM: + case OP_DOLL: + case OP_DOLLM: + case OP_NOT_WORD_BOUNDARY: + case OP_WORD_BOUNDARY: + cc += PRIV(OP_lengths)[*cc]; + break; + + /* Skip over a subpattern that has a {0} or {0,x} quantifier */ + + case OP_BRAZERO: + case OP_BRAMINZERO: + case OP_BRAPOSZERO: + case OP_SKIPZERO: + cc += PRIV(OP_lengths)[*cc]; + do cc += GET(cc, 1); while (*cc == OP_ALT); + cc += 1 + LINK_SIZE; + break; + + /* Handle literal characters and + repetitions */ + + case OP_CHAR: + case OP_CHARI: + case OP_NOT: + case OP_NOTI: + case OP_PLUS: + case OP_PLUSI: + case OP_MINPLUS: + case OP_MINPLUSI: + case OP_POSPLUS: + case OP_POSPLUSI: + case OP_NOTPLUS: + case OP_NOTPLUSI: + case OP_NOTMINPLUS: + case OP_NOTMINPLUSI: + case OP_NOTPOSPLUS: + case OP_NOTPOSPLUSI: + branchlength++; + cc += 2; +#ifdef SUPPORT_UTF + if (utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); +#endif + break; + + case OP_TYPEPLUS: + case OP_TYPEMINPLUS: + case OP_TYPEPOSPLUS: + branchlength++; + cc += (cc[1] == OP_PROP || cc[1] == OP_NOTPROP)? 4 : 2; + break; + + /* Handle exact repetitions. The count is already in characters, but we + need to skip over a multibyte character in UTF8 mode. */ + + case OP_EXACT: + case OP_EXACTI: + case OP_NOTEXACT: + case OP_NOTEXACTI: + branchlength += GET2(cc,1); + cc += 2 + IMM2_SIZE; +#ifdef SUPPORT_UTF + if (utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); +#endif + break; + + case OP_TYPEEXACT: + branchlength += GET2(cc,1); + cc += 2 + IMM2_SIZE + ((cc[1 + IMM2_SIZE] == OP_PROP + || cc[1 + IMM2_SIZE] == OP_NOTPROP)? 2 : 0); + break; + + /* Handle single-char non-literal matchers */ + + case OP_PROP: + case OP_NOTPROP: + cc += 2; + /* Fall through */ + + case OP_NOT_DIGIT: + case OP_DIGIT: + case OP_NOT_WHITESPACE: + case OP_WHITESPACE: + case OP_NOT_WORDCHAR: + case OP_WORDCHAR: + case OP_ANY: + case OP_ALLANY: + case OP_EXTUNI: + case OP_HSPACE: + case OP_NOT_HSPACE: + case OP_VSPACE: + case OP_NOT_VSPACE: + branchlength++; + cc++; + break; + + /* "Any newline" might match two characters, but it also might match just + one. */ + + case OP_ANYNL: + branchlength += 1; + cc++; + break; + + /* The single-byte matcher means we can't proceed in UTF-8 mode. (In + non-UTF-8 mode \C will actually be turned into OP_ALLANY, so won't ever + appear, but leave the code, just in case.) */ + + case OP_ANYBYTE: +#ifdef SUPPORT_UTF + if (utf) return -1; +#endif + branchlength++; + cc++; + break; + + /* For repeated character types, we have to test for \p and \P, which have + an extra two bytes of parameters. */ + + case OP_TYPESTAR: + case OP_TYPEMINSTAR: + case OP_TYPEQUERY: + case OP_TYPEMINQUERY: + case OP_TYPEPOSSTAR: + case OP_TYPEPOSQUERY: + if (cc[1] == OP_PROP || cc[1] == OP_NOTPROP) cc += 2; + cc += PRIV(OP_lengths)[op]; + break; + + case OP_TYPEUPTO: + case OP_TYPEMINUPTO: + case OP_TYPEPOSUPTO: + if (cc[1 + IMM2_SIZE] == OP_PROP + || cc[1 + IMM2_SIZE] == OP_NOTPROP) cc += 2; + cc += PRIV(OP_lengths)[op]; + break; + + /* Check a class for variable quantification */ + + case OP_CLASS: + case OP_NCLASS: +#if defined SUPPORT_UTF || defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + case OP_XCLASS: + /* The original code caused an unsigned overflow in 64 bit systems, + so now we use a conditional statement. */ + if (op == OP_XCLASS) + cc += GET(cc, 1); + else + cc += PRIV(OP_lengths)[OP_CLASS]; +#else + cc += PRIV(OP_lengths)[OP_CLASS]; +#endif + + switch (*cc) + { + case OP_CRPLUS: + case OP_CRMINPLUS: + case OP_CRPOSPLUS: + branchlength++; + /* Fall through */ + + case OP_CRSTAR: + case OP_CRMINSTAR: + case OP_CRQUERY: + case OP_CRMINQUERY: + case OP_CRPOSSTAR: + case OP_CRPOSQUERY: + cc++; + break; + + case OP_CRRANGE: + case OP_CRMINRANGE: + case OP_CRPOSRANGE: + branchlength += GET2(cc,1); + cc += 1 + 2 * IMM2_SIZE; + break; + + default: + branchlength++; + break; + } + break; + + /* Backreferences and subroutine calls are treated in the same way: we find + the minimum length for the subpattern. A recursion, however, causes an + a flag to be set that causes the length of this branch to be ignored. The + logic is that a recursion can only make sense if there is another + alternation that stops the recursing. That will provide the minimum length + (when no recursion happens). A backreference within the group that it is + referencing behaves in the same way. + + If PCRE_JAVASCRIPT_COMPAT is set, a backreference to an unset bracket + matches an empty string (by default it causes a matching failure), so in + that case we must set the minimum length to zero. */ + + case OP_DNREF: /* Duplicate named pattern back reference */ + case OP_DNREFI: + if ((options & PCRE_JAVASCRIPT_COMPAT) == 0) + { + int count = GET2(cc, 1+IMM2_SIZE); + pcre_uchar *slot = (pcre_uchar *)re + + re->name_table_offset + GET2(cc, 1) * re->name_entry_size; + d = INT_MAX; + while (count-- > 0) + { + ce = cs = (pcre_uchar *)PRIV(find_bracket)(startcode, utf, GET2(slot, 0)); + if (cs == NULL) return -2; + do ce += GET(ce, 1); while (*ce == OP_ALT); + if (cc > cs && cc < ce) + { + d = 0; + had_recurse = TRUE; + break; + } + else + { + int dd = find_minlength(re, cs, startcode, options, recurse_depth); + if (dd < d) d = dd; + } + slot += re->name_entry_size; + } + } + else d = 0; + cc += 1 + 2*IMM2_SIZE; + goto REPEAT_BACK_REFERENCE; + + case OP_REF: /* Single back reference */ + case OP_REFI: + if ((options & PCRE_JAVASCRIPT_COMPAT) == 0) + { + ce = cs = (pcre_uchar *)PRIV(find_bracket)(startcode, utf, GET2(cc, 1)); + if (cs == NULL) return -2; + do ce += GET(ce, 1); while (*ce == OP_ALT); + if (cc > cs && cc < ce) + { + d = 0; + had_recurse = TRUE; + } + else + { + d = find_minlength(re, cs, startcode, options, recurse_depth); + } + } + else d = 0; + cc += 1 + IMM2_SIZE; + + /* Handle repeated back references */ + + REPEAT_BACK_REFERENCE: + switch (*cc) + { + case OP_CRSTAR: + case OP_CRMINSTAR: + case OP_CRQUERY: + case OP_CRMINQUERY: + case OP_CRPOSSTAR: + case OP_CRPOSQUERY: + min = 0; + cc++; + break; + + case OP_CRPLUS: + case OP_CRMINPLUS: + case OP_CRPOSPLUS: + min = 1; + cc++; + break; + + case OP_CRRANGE: + case OP_CRMINRANGE: + case OP_CRPOSRANGE: + min = GET2(cc, 1); + cc += 1 + 2 * IMM2_SIZE; + break; + + default: + min = 1; + break; + } + + branchlength += min * d; + break; + + /* We can easily detect direct recursion, but not mutual recursion. This is + caught by a recursion depth count. */ + + case OP_RECURSE: + cs = ce = (pcre_uchar *)startcode + GET(cc, 1); + do ce += GET(ce, 1); while (*ce == OP_ALT); + if ((cc > cs && cc < ce) || recurse_depth > 10) + had_recurse = TRUE; + else + { + branchlength += find_minlength(re, cs, startcode, options, + recurse_depth + 1); + } + cc += 1 + LINK_SIZE; + break; + + /* Anything else does not or need not match a character. We can get the + item's length from the table, but for those that can match zero occurrences + of a character, we must take special action for UTF-8 characters. As it + happens, the "NOT" versions of these opcodes are used at present only for + ASCII characters, so they could be omitted from this list. However, in + future that may change, so we include them here so as not to leave a + gotcha for a future maintainer. */ + + case OP_UPTO: + case OP_UPTOI: + case OP_NOTUPTO: + case OP_NOTUPTOI: + case OP_MINUPTO: + case OP_MINUPTOI: + case OP_NOTMINUPTO: + case OP_NOTMINUPTOI: + case OP_POSUPTO: + case OP_POSUPTOI: + case OP_NOTPOSUPTO: + case OP_NOTPOSUPTOI: + + case OP_STAR: + case OP_STARI: + case OP_NOTSTAR: + case OP_NOTSTARI: + case OP_MINSTAR: + case OP_MINSTARI: + case OP_NOTMINSTAR: + case OP_NOTMINSTARI: + case OP_POSSTAR: + case OP_POSSTARI: + case OP_NOTPOSSTAR: + case OP_NOTPOSSTARI: + + case OP_QUERY: + case OP_QUERYI: + case OP_NOTQUERY: + case OP_NOTQUERYI: + case OP_MINQUERY: + case OP_MINQUERYI: + case OP_NOTMINQUERY: + case OP_NOTMINQUERYI: + case OP_POSQUERY: + case OP_POSQUERYI: + case OP_NOTPOSQUERY: + case OP_NOTPOSQUERYI: + + cc += PRIV(OP_lengths)[op]; +#ifdef SUPPORT_UTF + if (utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); +#endif + break; + + /* Skip these, but we need to add in the name length. */ + + case OP_MARK: + case OP_PRUNE_ARG: + case OP_SKIP_ARG: + case OP_THEN_ARG: + cc += PRIV(OP_lengths)[op] + cc[1]; + break; + + /* The remaining opcodes are just skipped over. */ + + case OP_CLOSE: + case OP_COMMIT: + case OP_FAIL: + case OP_PRUNE: + case OP_SET_SOM: + case OP_SKIP: + case OP_THEN: + cc += PRIV(OP_lengths)[op]; + break; + + /* This should not occur: we list all opcodes explicitly so that when + new ones get added they are properly considered. */ + + default: + return -3; + } + } +/* Control never gets here */ +} + + + +/************************************************* +* Set a bit and maybe its alternate case * +*************************************************/ + +/* Given a character, set its first byte's bit in the table, and also the +corresponding bit for the other version of a letter if we are caseless. In +UTF-8 mode, for characters greater than 127, we can only do the caseless thing +when Unicode property support is available. + +Arguments: + start_bits points to the bit map + p points to the character + caseless the caseless flag + cd the block with char table pointers + utf TRUE for UTF-8 / UTF-16 / UTF-32 mode + +Returns: pointer after the character +*/ + +static const pcre_uchar * +set_table_bit(pcre_uint8 *start_bits, const pcre_uchar *p, BOOL caseless, + compile_data *cd, BOOL utf) +{ +pcre_uint32 c = *p; + +#ifdef COMPILE_PCRE8 +SET_BIT(c); + +#ifdef SUPPORT_UTF +if (utf && c > 127) + { + GETCHARINC(c, p); +#ifdef SUPPORT_UCP + if (caseless) + { + pcre_uchar buff[6]; + c = UCD_OTHERCASE(c); + (void)PRIV(ord2utf)(c, buff); + SET_BIT(buff[0]); + } +#endif /* Not SUPPORT_UCP */ + return p; + } +#else /* Not SUPPORT_UTF */ +(void)(utf); /* Stops warning for unused parameter */ +#endif /* SUPPORT_UTF */ + +/* Not UTF-8 mode, or character is less than 127. */ + +if (caseless && (cd->ctypes[c] & ctype_letter) != 0) SET_BIT(cd->fcc[c]); +return p + 1; +#endif /* COMPILE_PCRE8 */ + +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 +if (c > 0xff) + { + c = 0xff; + caseless = FALSE; + } +SET_BIT(c); + +#ifdef SUPPORT_UTF +if (utf && c > 127) + { + GETCHARINC(c, p); +#ifdef SUPPORT_UCP + if (caseless) + { + c = UCD_OTHERCASE(c); + if (c > 0xff) + c = 0xff; + SET_BIT(c); + } +#endif /* SUPPORT_UCP */ + return p; + } +#else /* Not SUPPORT_UTF */ +(void)(utf); /* Stops warning for unused parameter */ +#endif /* SUPPORT_UTF */ + +if (caseless && (cd->ctypes[c] & ctype_letter) != 0) SET_BIT(cd->fcc[c]); +return p + 1; +#endif +} + + + +/************************************************* +* Set bits for a positive character type * +*************************************************/ + +/* This function sets starting bits for a character type. In UTF-8 mode, we can +only do a direct setting for bytes less than 128, as otherwise there can be +confusion with bytes in the middle of UTF-8 characters. In a "traditional" +environment, the tables will only recognize ASCII characters anyway, but in at +least one Windows environment, some higher bytes bits were set in the tables. +So we deal with that case by considering the UTF-8 encoding. + +Arguments: + start_bits the starting bitmap + cbit type the type of character wanted + table_limit 32 for non-UTF-8; 16 for UTF-8 + cd the block with char table pointers + +Returns: nothing +*/ + +static void +set_type_bits(pcre_uint8 *start_bits, int cbit_type, unsigned int table_limit, + compile_data *cd) +{ +register pcre_uint32 c; +for (c = 0; c < table_limit; c++) start_bits[c] |= cd->cbits[c+cbit_type]; +#if defined SUPPORT_UTF && defined COMPILE_PCRE8 +if (table_limit == 32) return; +for (c = 128; c < 256; c++) + { + if ((cd->cbits[c/8] & (1 << (c&7))) != 0) + { + pcre_uchar buff[6]; + (void)PRIV(ord2utf)(c, buff); + SET_BIT(buff[0]); + } + } +#endif +} + + +/************************************************* +* Set bits for a negative character type * +*************************************************/ + +/* This function sets starting bits for a negative character type such as \D. +In UTF-8 mode, we can only do a direct setting for bytes less than 128, as +otherwise there can be confusion with bytes in the middle of UTF-8 characters. +Unlike in the positive case, where we can set appropriate starting bits for +specific high-valued UTF-8 characters, in this case we have to set the bits for +all high-valued characters. The lowest is 0xc2, but we overkill by starting at +0xc0 (192) for simplicity. + +Arguments: + start_bits the starting bitmap + cbit type the type of character wanted + table_limit 32 for non-UTF-8; 16 for UTF-8 + cd the block with char table pointers + +Returns: nothing +*/ + +static void +set_nottype_bits(pcre_uint8 *start_bits, int cbit_type, unsigned int table_limit, + compile_data *cd) +{ +register pcre_uint32 c; +for (c = 0; c < table_limit; c++) start_bits[c] |= ~cd->cbits[c+cbit_type]; +#if defined SUPPORT_UTF && defined COMPILE_PCRE8 +if (table_limit != 32) for (c = 24; c < 32; c++) start_bits[c] = 0xff; +#endif +} + + + +/************************************************* +* Create bitmap of starting bytes * +*************************************************/ + +/* This function scans a compiled unanchored expression recursively and +attempts to build a bitmap of the set of possible starting bytes. As time goes +by, we may be able to get more clever at doing this. The SSB_CONTINUE return is +useful for parenthesized groups in patterns such as (a*)b where the group +provides some optional starting bytes but scanning must continue at the outer +level to find at least one mandatory byte. At the outermost level, this +function fails unless the result is SSB_DONE. + +Arguments: + code points to an expression + start_bits points to a 32-byte table, initialized to 0 + utf TRUE if in UTF-8 / UTF-16 / UTF-32 mode + cd the block with char table pointers + +Returns: SSB_FAIL => Failed to find any starting bytes + SSB_DONE => Found mandatory starting bytes + SSB_CONTINUE => Found optional starting bytes + SSB_UNKNOWN => Hit an unrecognized opcode +*/ + +static int +set_start_bits(const pcre_uchar *code, pcre_uint8 *start_bits, BOOL utf, + compile_data *cd) +{ +register pcre_uint32 c; +int yield = SSB_DONE; +#if defined SUPPORT_UTF && defined COMPILE_PCRE8 +int table_limit = utf? 16:32; +#else +int table_limit = 32; +#endif + +#if 0 +/* ========================================================================= */ +/* The following comment and code was inserted in January 1999. In May 2006, +when it was observed to cause compiler warnings about unused values, I took it +out again. If anybody is still using OS/2, they will have to put it back +manually. */ + +/* This next statement and the later reference to dummy are here in order to +trick the optimizer of the IBM C compiler for OS/2 into generating correct +code. Apparently IBM isn't going to fix the problem, and we would rather not +disable optimization (in this module it actually makes a big difference, and +the pcre module can use all the optimization it can get). */ + +volatile int dummy; +/* ========================================================================= */ +#endif + +do + { + BOOL try_next = TRUE; + const pcre_uchar *tcode = code + 1 + LINK_SIZE; + + if (*code == OP_CBRA || *code == OP_SCBRA || + *code == OP_CBRAPOS || *code == OP_SCBRAPOS) tcode += IMM2_SIZE; + + while (try_next) /* Loop for items in this branch */ + { + int rc; + + switch(*tcode) + { + /* If we reach something we don't understand, it means a new opcode has + been created that hasn't been added to this code. Hopefully this problem + will be discovered during testing. */ + + default: + return SSB_UNKNOWN; + + /* Fail for a valid opcode that implies no starting bits. */ + + case OP_ACCEPT: + case OP_ASSERT_ACCEPT: + case OP_ALLANY: + case OP_ANY: + case OP_ANYBYTE: + case OP_CIRC: + case OP_CIRCM: + case OP_CLOSE: + case OP_COMMIT: + case OP_COND: + case OP_CREF: + case OP_DEF: + case OP_DNCREF: + case OP_DNREF: + case OP_DNREFI: + case OP_DNRREF: + case OP_DOLL: + case OP_DOLLM: + case OP_END: + case OP_EOD: + case OP_EODN: + case OP_EXTUNI: + case OP_FAIL: + case OP_MARK: + case OP_NOT: + case OP_NOTEXACT: + case OP_NOTEXACTI: + case OP_NOTI: + case OP_NOTMINPLUS: + case OP_NOTMINPLUSI: + case OP_NOTMINQUERY: + case OP_NOTMINQUERYI: + case OP_NOTMINSTAR: + case OP_NOTMINSTARI: + case OP_NOTMINUPTO: + case OP_NOTMINUPTOI: + case OP_NOTPLUS: + case OP_NOTPLUSI: + case OP_NOTPOSPLUS: + case OP_NOTPOSPLUSI: + case OP_NOTPOSQUERY: + case OP_NOTPOSQUERYI: + case OP_NOTPOSSTAR: + case OP_NOTPOSSTARI: + case OP_NOTPOSUPTO: + case OP_NOTPOSUPTOI: + case OP_NOTPROP: + case OP_NOTQUERY: + case OP_NOTQUERYI: + case OP_NOTSTAR: + case OP_NOTSTARI: + case OP_NOTUPTO: + case OP_NOTUPTOI: + case OP_NOT_HSPACE: + case OP_NOT_VSPACE: + case OP_PROP: + case OP_PRUNE: + case OP_PRUNE_ARG: + case OP_RECURSE: + case OP_REF: + case OP_REFI: + case OP_REVERSE: + case OP_RREF: + case OP_SCOND: + case OP_SET_SOM: + case OP_SKIP: + case OP_SKIP_ARG: + case OP_SOD: + case OP_SOM: + case OP_THEN: + case OP_THEN_ARG: + return SSB_FAIL; + + /* We can ignore word boundary tests. */ + + case OP_WORD_BOUNDARY: + case OP_NOT_WORD_BOUNDARY: + tcode++; + break; + + /* If we hit a bracket or a positive lookahead assertion, recurse to set + bits from within the subpattern. If it can't find anything, we have to + give up. If it finds some mandatory character(s), we are done for this + branch. Otherwise, carry on scanning after the subpattern. */ + + case OP_BRA: + case OP_SBRA: + case OP_CBRA: + case OP_SCBRA: + case OP_BRAPOS: + case OP_SBRAPOS: + case OP_CBRAPOS: + case OP_SCBRAPOS: + case OP_ONCE: + case OP_ONCE_NC: + case OP_ASSERT: + rc = set_start_bits(tcode, start_bits, utf, cd); + if (rc == SSB_FAIL || rc == SSB_UNKNOWN) return rc; + if (rc == SSB_DONE) try_next = FALSE; else + { + do tcode += GET(tcode, 1); while (*tcode == OP_ALT); + tcode += 1 + LINK_SIZE; + } + break; + + /* If we hit ALT or KET, it means we haven't found anything mandatory in + this branch, though we might have found something optional. For ALT, we + continue with the next alternative, but we have to arrange that the final + result from subpattern is SSB_CONTINUE rather than SSB_DONE. For KET, + return SSB_CONTINUE: if this is the top level, that indicates failure, + but after a nested subpattern, it causes scanning to continue. */ + + case OP_ALT: + yield = SSB_CONTINUE; + try_next = FALSE; + break; + + case OP_KET: + case OP_KETRMAX: + case OP_KETRMIN: + case OP_KETRPOS: + return SSB_CONTINUE; + + /* Skip over callout */ + + case OP_CALLOUT: + tcode += 2 + 2*LINK_SIZE; + break; + + /* Skip over lookbehind and negative lookahead assertions */ + + case OP_ASSERT_NOT: + case OP_ASSERTBACK: + case OP_ASSERTBACK_NOT: + do tcode += GET(tcode, 1); while (*tcode == OP_ALT); + tcode += 1 + LINK_SIZE; + break; + + /* BRAZERO does the bracket, but carries on. */ + + case OP_BRAZERO: + case OP_BRAMINZERO: + case OP_BRAPOSZERO: + rc = set_start_bits(++tcode, start_bits, utf, cd); + if (rc == SSB_FAIL || rc == SSB_UNKNOWN) return rc; +/* ========================================================================= + See the comment at the head of this function concerning the next line, + which was an old fudge for the benefit of OS/2. + dummy = 1; + ========================================================================= */ + do tcode += GET(tcode,1); while (*tcode == OP_ALT); + tcode += 1 + LINK_SIZE; + break; + + /* SKIPZERO skips the bracket. */ + + case OP_SKIPZERO: + tcode++; + do tcode += GET(tcode,1); while (*tcode == OP_ALT); + tcode += 1 + LINK_SIZE; + break; + + /* Single-char * or ? sets the bit and tries the next item */ + + case OP_STAR: + case OP_MINSTAR: + case OP_POSSTAR: + case OP_QUERY: + case OP_MINQUERY: + case OP_POSQUERY: + tcode = set_table_bit(start_bits, tcode + 1, FALSE, cd, utf); + break; + + case OP_STARI: + case OP_MINSTARI: + case OP_POSSTARI: + case OP_QUERYI: + case OP_MINQUERYI: + case OP_POSQUERYI: + tcode = set_table_bit(start_bits, tcode + 1, TRUE, cd, utf); + break; + + /* Single-char upto sets the bit and tries the next */ + + case OP_UPTO: + case OP_MINUPTO: + case OP_POSUPTO: + tcode = set_table_bit(start_bits, tcode + 1 + IMM2_SIZE, FALSE, cd, utf); + break; + + case OP_UPTOI: + case OP_MINUPTOI: + case OP_POSUPTOI: + tcode = set_table_bit(start_bits, tcode + 1 + IMM2_SIZE, TRUE, cd, utf); + break; + + /* At least one single char sets the bit and stops */ + + case OP_EXACT: + tcode += IMM2_SIZE; + /* Fall through */ + case OP_CHAR: + case OP_PLUS: + case OP_MINPLUS: + case OP_POSPLUS: + (void)set_table_bit(start_bits, tcode + 1, FALSE, cd, utf); + try_next = FALSE; + break; + + case OP_EXACTI: + tcode += IMM2_SIZE; + /* Fall through */ + case OP_CHARI: + case OP_PLUSI: + case OP_MINPLUSI: + case OP_POSPLUSI: + (void)set_table_bit(start_bits, tcode + 1, TRUE, cd, utf); + try_next = FALSE; + break; + + /* Special spacing and line-terminating items. These recognize specific + lists of characters. The difference between VSPACE and ANYNL is that the + latter can match the two-character CRLF sequence, but that is not + relevant for finding the first character, so their code here is + identical. */ + + case OP_HSPACE: + SET_BIT(CHAR_HT); + SET_BIT(CHAR_SPACE); +#ifdef SUPPORT_UTF + if (utf) + { +#ifdef COMPILE_PCRE8 + SET_BIT(0xC2); /* For U+00A0 */ + SET_BIT(0xE1); /* For U+1680, U+180E */ + SET_BIT(0xE2); /* For U+2000 - U+200A, U+202F, U+205F */ + SET_BIT(0xE3); /* For U+3000 */ +#elif defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + SET_BIT(0xA0); + SET_BIT(0xFF); /* For characters > 255 */ +#endif /* COMPILE_PCRE[8|16|32] */ + } + else +#endif /* SUPPORT_UTF */ + { +#ifndef EBCDIC + SET_BIT(0xA0); +#endif /* Not EBCDIC */ +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + SET_BIT(0xFF); /* For characters > 255 */ +#endif /* COMPILE_PCRE[16|32] */ + } + try_next = FALSE; + break; + + case OP_ANYNL: + case OP_VSPACE: + SET_BIT(CHAR_LF); + SET_BIT(CHAR_VT); + SET_BIT(CHAR_FF); + SET_BIT(CHAR_CR); +#ifdef SUPPORT_UTF + if (utf) + { +#ifdef COMPILE_PCRE8 + SET_BIT(0xC2); /* For U+0085 */ + SET_BIT(0xE2); /* For U+2028, U+2029 */ +#elif defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + SET_BIT(CHAR_NEL); + SET_BIT(0xFF); /* For characters > 255 */ +#endif /* COMPILE_PCRE[8|16|32] */ + } + else +#endif /* SUPPORT_UTF */ + { + SET_BIT(CHAR_NEL); +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + SET_BIT(0xFF); /* For characters > 255 */ +#endif + } + try_next = FALSE; + break; + + /* Single character types set the bits and stop. Note that if PCRE_UCP + is set, we do not see these op codes because \d etc are converted to + properties. Therefore, these apply in the case when only characters less + than 256 are recognized to match the types. */ + + case OP_NOT_DIGIT: + set_nottype_bits(start_bits, cbit_digit, table_limit, cd); + try_next = FALSE; + break; + + case OP_DIGIT: + set_type_bits(start_bits, cbit_digit, table_limit, cd); + try_next = FALSE; + break; + + /* The cbit_space table has vertical tab as whitespace; we have to + ensure it is set as not whitespace. Luckily, the code value is the same + (0x0b) in ASCII and EBCDIC, so we can just adjust the appropriate bit. */ + + case OP_NOT_WHITESPACE: + set_nottype_bits(start_bits, cbit_space, table_limit, cd); + start_bits[1] |= 0x08; + try_next = FALSE; + break; + + /* The cbit_space table has vertical tab as whitespace; we have to not + set it from the table. Luckily, the code value is the same (0x0b) in + ASCII and EBCDIC, so we can just adjust the appropriate bit. */ + + case OP_WHITESPACE: + c = start_bits[1]; /* Save in case it was already set */ + set_type_bits(start_bits, cbit_space, table_limit, cd); + start_bits[1] = (start_bits[1] & ~0x08) | c; + try_next = FALSE; + break; + + case OP_NOT_WORDCHAR: + set_nottype_bits(start_bits, cbit_word, table_limit, cd); + try_next = FALSE; + break; + + case OP_WORDCHAR: + set_type_bits(start_bits, cbit_word, table_limit, cd); + try_next = FALSE; + break; + + /* One or more character type fudges the pointer and restarts, knowing + it will hit a single character type and stop there. */ + + case OP_TYPEPLUS: + case OP_TYPEMINPLUS: + case OP_TYPEPOSPLUS: + tcode++; + break; + + case OP_TYPEEXACT: + tcode += 1 + IMM2_SIZE; + break; + + /* Zero or more repeats of character types set the bits and then + try again. */ + + case OP_TYPEUPTO: + case OP_TYPEMINUPTO: + case OP_TYPEPOSUPTO: + tcode += IMM2_SIZE; /* Fall through */ + + case OP_TYPESTAR: + case OP_TYPEMINSTAR: + case OP_TYPEPOSSTAR: + case OP_TYPEQUERY: + case OP_TYPEMINQUERY: + case OP_TYPEPOSQUERY: + switch(tcode[1]) + { + default: + case OP_ANY: + case OP_ALLANY: + return SSB_FAIL; + + case OP_HSPACE: + SET_BIT(CHAR_HT); + SET_BIT(CHAR_SPACE); +#ifdef SUPPORT_UTF + if (utf) + { +#ifdef COMPILE_PCRE8 + SET_BIT(0xC2); /* For U+00A0 */ + SET_BIT(0xE1); /* For U+1680, U+180E */ + SET_BIT(0xE2); /* For U+2000 - U+200A, U+202F, U+205F */ + SET_BIT(0xE3); /* For U+3000 */ +#elif defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + SET_BIT(0xA0); + SET_BIT(0xFF); /* For characters > 255 */ +#endif /* COMPILE_PCRE[8|16|32] */ + } + else +#endif /* SUPPORT_UTF */ +#ifndef EBCDIC + SET_BIT(0xA0); +#endif /* Not EBCDIC */ + break; + + case OP_ANYNL: + case OP_VSPACE: + SET_BIT(CHAR_LF); + SET_BIT(CHAR_VT); + SET_BIT(CHAR_FF); + SET_BIT(CHAR_CR); +#ifdef SUPPORT_UTF + if (utf) + { +#ifdef COMPILE_PCRE8 + SET_BIT(0xC2); /* For U+0085 */ + SET_BIT(0xE2); /* For U+2028, U+2029 */ +#elif defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + SET_BIT(CHAR_NEL); + SET_BIT(0xFF); /* For characters > 255 */ +#endif /* COMPILE_PCRE16 */ + } + else +#endif /* SUPPORT_UTF */ + SET_BIT(CHAR_NEL); + break; + + case OP_NOT_DIGIT: + set_nottype_bits(start_bits, cbit_digit, table_limit, cd); + break; + + case OP_DIGIT: + set_type_bits(start_bits, cbit_digit, table_limit, cd); + break; + + /* The cbit_space table has vertical tab as whitespace; we no longer + have to play fancy tricks because Perl added VT to its whitespace at + release 5.18. PCRE added it at release 8.34. */ + + case OP_NOT_WHITESPACE: + set_nottype_bits(start_bits, cbit_space, table_limit, cd); + break; + + case OP_WHITESPACE: + set_type_bits(start_bits, cbit_space, table_limit, cd); + break; + + case OP_NOT_WORDCHAR: + set_nottype_bits(start_bits, cbit_word, table_limit, cd); + break; + + case OP_WORDCHAR: + set_type_bits(start_bits, cbit_word, table_limit, cd); + break; + } + + tcode += 2; + break; + + /* Character class where all the information is in a bit map: set the + bits and either carry on or not, according to the repeat count. If it was + a negative class, and we are operating with UTF-8 characters, any byte + with a value >= 0xc4 is a potentially valid starter because it starts a + character with a value > 255. */ + +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + case OP_XCLASS: + if ((tcode[1 + LINK_SIZE] & XCL_HASPROP) != 0) + return SSB_FAIL; + /* All bits are set. */ + if ((tcode[1 + LINK_SIZE] & XCL_MAP) == 0 && (tcode[1 + LINK_SIZE] & XCL_NOT) != 0) + return SSB_FAIL; +#endif + /* Fall through */ + + case OP_NCLASS: +#if defined SUPPORT_UTF && defined COMPILE_PCRE8 + if (utf) + { + start_bits[24] |= 0xf0; /* Bits for 0xc4 - 0xc8 */ + memset(start_bits+25, 0xff, 7); /* Bits for 0xc9 - 0xff */ + } +#endif +#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 + SET_BIT(0xFF); /* For characters > 255 */ +#endif + /* Fall through */ + + case OP_CLASS: + { + pcre_uint8 *map; +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + map = NULL; + if (*tcode == OP_XCLASS) + { + if ((tcode[1 + LINK_SIZE] & XCL_MAP) != 0) + map = (pcre_uint8 *)(tcode + 1 + LINK_SIZE + 1); + tcode += GET(tcode, 1); + } + else +#endif + { + tcode++; + map = (pcre_uint8 *)tcode; + tcode += 32 / sizeof(pcre_uchar); + } + + /* In UTF-8 mode, the bits in a bit map correspond to character + values, not to byte values. However, the bit map we are constructing is + for byte values. So we have to do a conversion for characters whose + value is > 127. In fact, there are only two possible starting bytes for + characters in the range 128 - 255. */ + +#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 + if (map != NULL) +#endif + { +#if defined SUPPORT_UTF && defined COMPILE_PCRE8 + if (utf) + { + for (c = 0; c < 16; c++) start_bits[c] |= map[c]; + for (c = 128; c < 256; c++) + { + if ((map[c/8] && (1 << (c&7))) != 0) + { + int d = (c >> 6) | 0xc0; /* Set bit for this starter */ + start_bits[d/8] |= (1 << (d&7)); /* and then skip on to the */ + c = (c & 0xc0) + 0x40 - 1; /* next relevant character. */ + } + } + } + else +#endif + { + /* In non-UTF-8 mode, the two bit maps are completely compatible. */ + for (c = 0; c < 32; c++) start_bits[c] |= map[c]; + } + } + + /* Advance past the bit map, and act on what follows. For a zero + minimum repeat, continue; otherwise stop processing. */ + + switch (*tcode) + { + case OP_CRSTAR: + case OP_CRMINSTAR: + case OP_CRQUERY: + case OP_CRMINQUERY: + case OP_CRPOSSTAR: + case OP_CRPOSQUERY: + tcode++; + break; + + case OP_CRRANGE: + case OP_CRMINRANGE: + case OP_CRPOSRANGE: + if (GET2(tcode, 1) == 0) tcode += 1 + 2 * IMM2_SIZE; + else try_next = FALSE; + break; + + default: + try_next = FALSE; + break; + } + } + break; /* End of bitmap class handling */ + + } /* End of switch */ + } /* End of try_next loop */ + + code += GET(code, 1); /* Advance to next branch */ + } +while (*code == OP_ALT); +return yield; +} + + + + + +/************************************************* +* Study a compiled expression * +*************************************************/ + +/* This function is handed a compiled expression that it must study to produce +information that will speed up the matching. It returns a pcre[16]_extra block +which then gets handed back to pcre_exec(). + +Arguments: + re points to the compiled expression + options contains option bits + errorptr points to where to place error messages; + set NULL unless error + +Returns: pointer to a pcre[16]_extra block, with study_data filled in and + the appropriate flags set; + NULL on error or if no optimization possible +*/ + +#if defined COMPILE_PCRE8 +PCRE_EXP_DEFN pcre_extra * PCRE_CALL_CONVENTION +pcre_study(const pcre *external_re, int options, const char **errorptr) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DEFN pcre16_extra * PCRE_CALL_CONVENTION +pcre16_study(const pcre16 *external_re, int options, const char **errorptr) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DEFN pcre32_extra * PCRE_CALL_CONVENTION +pcre32_study(const pcre32 *external_re, int options, const char **errorptr) +#endif +{ +int min; +BOOL bits_set = FALSE; +pcre_uint8 start_bits[32]; +PUBL(extra) *extra = NULL; +pcre_study_data *study; +const pcre_uint8 *tables; +pcre_uchar *code; +compile_data compile_block; +const REAL_PCRE *re = (const REAL_PCRE *)external_re; + + +*errorptr = NULL; + +if (re == NULL || re->magic_number != MAGIC_NUMBER) + { + *errorptr = "argument is not a compiled regular expression"; + return NULL; + } + +if ((re->flags & PCRE_MODE) == 0) + { +#if defined COMPILE_PCRE8 + *errorptr = "argument not compiled in 8 bit mode"; +#elif defined COMPILE_PCRE16 + *errorptr = "argument not compiled in 16 bit mode"; +#elif defined COMPILE_PCRE32 + *errorptr = "argument not compiled in 32 bit mode"; +#endif + return NULL; + } + +if ((options & ~PUBLIC_STUDY_OPTIONS) != 0) + { + *errorptr = "unknown or incorrect option bit(s) set"; + return NULL; + } + +code = (pcre_uchar *)re + re->name_table_offset + + (re->name_count * re->name_entry_size); + +/* For an anchored pattern, or an unanchored pattern that has a first char, or +a multiline pattern that matches only at "line starts", there is no point in +seeking a list of starting bytes. */ + +if ((re->options & PCRE_ANCHORED) == 0 && + (re->flags & (PCRE_FIRSTSET|PCRE_STARTLINE)) == 0) + { + int rc; + + /* Set the character tables in the block that is passed around */ + + tables = re->tables; + +#if defined COMPILE_PCRE8 + if (tables == NULL) + (void)pcre_fullinfo(external_re, NULL, PCRE_INFO_DEFAULT_TABLES, + (void *)(&tables)); +#elif defined COMPILE_PCRE16 + if (tables == NULL) + (void)pcre16_fullinfo(external_re, NULL, PCRE_INFO_DEFAULT_TABLES, + (void *)(&tables)); +#elif defined COMPILE_PCRE32 + if (tables == NULL) + (void)pcre32_fullinfo(external_re, NULL, PCRE_INFO_DEFAULT_TABLES, + (void *)(&tables)); +#endif + + compile_block.lcc = tables + lcc_offset; + compile_block.fcc = tables + fcc_offset; + compile_block.cbits = tables + cbits_offset; + compile_block.ctypes = tables + ctypes_offset; + + /* See if we can find a fixed set of initial characters for the pattern. */ + + memset(start_bits, 0, 32 * sizeof(pcre_uint8)); + rc = set_start_bits(code, start_bits, (re->options & PCRE_UTF8) != 0, + &compile_block); + bits_set = rc == SSB_DONE; + if (rc == SSB_UNKNOWN) + { + *errorptr = "internal error: opcode not recognized"; + return NULL; + } + } + +/* Find the minimum length of subject string. */ + +switch(min = find_minlength(re, code, code, re->options, 0)) + { + case -2: *errorptr = "internal error: missing capturing bracket"; return NULL; + case -3: *errorptr = "internal error: opcode not recognized"; return NULL; + default: break; + } + +/* If a set of starting bytes has been identified, or if the minimum length is +greater than zero, or if JIT optimization has been requested, or if +PCRE_STUDY_EXTRA_NEEDED is set, get a pcre[16]_extra block and a +pcre_study_data block. The study data is put in the latter, which is pointed to +by the former, which may also get additional data set later by the calling +program. At the moment, the size of pcre_study_data is fixed. We nevertheless +save it in a field for returning via the pcre_fullinfo() function so that if it +becomes variable in the future, we don't have to change that code. */ + +if (bits_set || min > 0 || (options & ( +#ifdef SUPPORT_JIT + PCRE_STUDY_JIT_COMPILE | PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE | + PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE | +#endif + PCRE_STUDY_EXTRA_NEEDED)) != 0) + { + extra = (PUBL(extra) *)(PUBL(malloc)) + (sizeof(PUBL(extra)) + sizeof(pcre_study_data)); + if (extra == NULL) + { + *errorptr = "failed to get memory"; + return NULL; + } + + study = (pcre_study_data *)((char *)extra + sizeof(PUBL(extra))); + extra->flags = PCRE_EXTRA_STUDY_DATA; + extra->study_data = study; + + study->size = sizeof(pcre_study_data); + study->flags = 0; + + /* Set the start bits always, to avoid unset memory errors if the + study data is written to a file, but set the flag only if any of the bits + are set, to save time looking when none are. */ + + if (bits_set) + { + study->flags |= PCRE_STUDY_MAPPED; + memcpy(study->start_bits, start_bits, sizeof(start_bits)); + } + else memset(study->start_bits, 0, 32 * sizeof(pcre_uint8)); + +#ifdef PCRE_DEBUG + if (bits_set) + { + pcre_uint8 *ptr = start_bits; + int i; + + printf("Start bits:\n"); + for (i = 0; i < 32; i++) + printf("%3d: %02x%s", i * 8, *ptr++, ((i + 1) & 0x7) != 0? " " : "\n"); + } +#endif + + /* Always set the minlength value in the block, because the JIT compiler + makes use of it. However, don't set the bit unless the length is greater than + zero - the interpretive pcre_exec() and pcre_dfa_exec() needn't waste time + checking the zero case. */ + + if (min > 0) + { + study->flags |= PCRE_STUDY_MINLEN; + study->minlength = min; + } + else study->minlength = 0; + + /* If JIT support was compiled and requested, attempt the JIT compilation. + If no starting bytes were found, and the minimum length is zero, and JIT + compilation fails, abandon the extra block and return NULL, unless + PCRE_STUDY_EXTRA_NEEDED is set. */ + +#ifdef SUPPORT_JIT + extra->executable_jit = NULL; + if ((options & PCRE_STUDY_JIT_COMPILE) != 0) + PRIV(jit_compile)(re, extra, JIT_COMPILE); + if ((options & PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE) != 0) + PRIV(jit_compile)(re, extra, JIT_PARTIAL_SOFT_COMPILE); + if ((options & PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE) != 0) + PRIV(jit_compile)(re, extra, JIT_PARTIAL_HARD_COMPILE); + + if (study->flags == 0 && (extra->flags & PCRE_EXTRA_EXECUTABLE_JIT) == 0 && + (options & PCRE_STUDY_EXTRA_NEEDED) == 0) + { +#if defined COMPILE_PCRE8 + pcre_free_study(extra); +#elif defined COMPILE_PCRE16 + pcre16_free_study(extra); +#elif defined COMPILE_PCRE32 + pcre32_free_study(extra); +#endif + extra = NULL; + } +#endif + } + +return extra; +} + + +/************************************************* +* Free the study data * +*************************************************/ + +/* This function frees the memory that was obtained by pcre_study(). + +Argument: a pointer to the pcre[16]_extra block +Returns: nothing +*/ + +#if defined COMPILE_PCRE8 +PCRE_EXP_DEFN void +pcre_free_study(pcre_extra *extra) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DEFN void +pcre16_free_study(pcre16_extra *extra) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DEFN void +pcre32_free_study(pcre32_extra *extra) +#endif +{ +if (extra == NULL) + return; +#ifdef SUPPORT_JIT +if ((extra->flags & PCRE_EXTRA_EXECUTABLE_JIT) != 0 && + extra->executable_jit != NULL) + PRIV(jit_free)(extra->executable_jit); +#endif +PUBL(free)(extra); +} + +/* End of pcre_study.c */ diff --git a/plugins/Pcre16/src/pcre_tables.c b/plugins/Pcre16/src/pcre_tables.c new file mode 100644 index 0000000000..f38ab52cbb --- /dev/null +++ b/plugins/Pcre16/src/pcre_tables.c @@ -0,0 +1,658 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +#ifndef PCRE_INCLUDED + +/* This module contains some fixed tables that are used by more than one of the +PCRE code modules. The tables are also #included by the pcretest program, which +uses macros to change their names from _pcre_xxx to xxxx, thereby avoiding name +clashes with the library. */ + + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#include "pcre_internal.h" + +#endif /* PCRE_INCLUDED */ + +/* Table of sizes for the fixed-length opcodes. It's defined in a macro so that +the definition is next to the definition of the opcodes in pcre_internal.h. */ + +const pcre_uint8 PRIV(OP_lengths)[] = { OP_LENGTHS }; + +/* Tables of horizontal and vertical whitespace characters, suitable for +adding to classes. */ + +const pcre_uint32 PRIV(hspace_list)[] = { HSPACE_LIST }; +const pcre_uint32 PRIV(vspace_list)[] = { VSPACE_LIST }; + + + +/************************************************* +* Tables for UTF-8 support * +*************************************************/ + +/* These are the breakpoints for different numbers of bytes in a UTF-8 +character. */ + +#if (defined SUPPORT_UTF && defined COMPILE_PCRE8) \ + || (defined PCRE_INCLUDED && (defined SUPPORT_PCRE16 || defined SUPPORT_PCRE32)) + +/* These tables are also required by pcretest in 16- or 32-bit mode. */ + +const int PRIV(utf8_table1)[] = + { 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff}; + +const int PRIV(utf8_table1_size) = sizeof(PRIV(utf8_table1)) / sizeof(int); + +/* These are the indicator bits and the mask for the data bits to set in the +first byte of a character, indexed by the number of additional bytes. */ + +const int PRIV(utf8_table2)[] = { 0, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc}; +const int PRIV(utf8_table3)[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01}; + +/* Table of the number of extra bytes, indexed by the first byte masked with +0x3f. The highest number for a valid UTF-8 first byte is in fact 0x3d. */ + +const pcre_uint8 PRIV(utf8_table4)[] = { + 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, + 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, + 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, + 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 }; + +#endif /* (SUPPORT_UTF && COMPILE_PCRE8) || (PCRE_INCLUDED && SUPPORT_PCRE[16|32])*/ + +#ifdef SUPPORT_UTF + +/* Table to translate from particular type value to the general value. */ + +const pcre_uint32 PRIV(ucp_gentype)[] = { + ucp_C, ucp_C, ucp_C, ucp_C, ucp_C, /* Cc, Cf, Cn, Co, Cs */ + ucp_L, ucp_L, ucp_L, ucp_L, ucp_L, /* Ll, Lu, Lm, Lo, Lt */ + ucp_M, ucp_M, ucp_M, /* Mc, Me, Mn */ + ucp_N, ucp_N, ucp_N, /* Nd, Nl, No */ + ucp_P, ucp_P, ucp_P, ucp_P, ucp_P, /* Pc, Pd, Pe, Pf, Pi */ + ucp_P, ucp_P, /* Ps, Po */ + ucp_S, ucp_S, ucp_S, ucp_S, /* Sc, Sk, Sm, So */ + ucp_Z, ucp_Z, ucp_Z /* Zl, Zp, Zs */ +}; + +/* This table encodes the rules for finding the end of an extended grapheme +cluster. Every code point has a grapheme break property which is one of the +ucp_gbXX values defined in ucp.h. The 2-dimensional table is indexed by the +properties of two adjacent code points. The left property selects a word from +the table, and the right property selects a bit from that word like this: + + ucp_gbtable[left-property] & (1 << right-property) + +The value is non-zero if a grapheme break is NOT permitted between the relevant +two code points. The breaking rules are as follows: + +1. Break at the start and end of text (pretty obviously). + +2. Do not break between a CR and LF; otherwise, break before and after + controls. + +3. Do not break Hangul syllable sequences, the rules for which are: + + L may be followed by L, V, LV or LVT + LV or V may be followed by V or T + LVT or T may be followed by T + +4. Do not break before extending characters. + +The next two rules are only for extended grapheme clusters (but that's what we +are implementing). + +5. Do not break before SpacingMarks. + +6. Do not break after Prepend characters. + +7. Otherwise, break everywhere. +*/ + +const pcre_uint32 PRIV(ucp_gbtable[]) = { + (1<<ucp_gbLF), /* 0 CR */ + 0, /* 1 LF */ + 0, /* 2 Control */ + (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark), /* 3 Extend */ + (1<<ucp_gbExtend)|(1<<ucp_gbPrepend)| /* 4 Prepend */ + (1<<ucp_gbSpacingMark)|(1<<ucp_gbL)| + (1<<ucp_gbV)|(1<<ucp_gbT)|(1<<ucp_gbLV)| + (1<<ucp_gbLVT)|(1<<ucp_gbOther), + + (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark), /* 5 SpacingMark */ + (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbL)| /* 6 L */ + (1<<ucp_gbL)|(1<<ucp_gbV)|(1<<ucp_gbLV)|(1<<ucp_gbLVT), + + (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbV)| /* 7 V */ + (1<<ucp_gbT), + + (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbT), /* 8 T */ + (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbV)| /* 9 LV */ + (1<<ucp_gbT), + + (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbT), /* 10 LVT */ + (1<<ucp_gbRegionalIndicator), /* 11 RegionalIndicator */ + (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark) /* 12 Other */ +}; + +#ifdef SUPPORT_JIT +/* This table reverses PRIV(ucp_gentype). We can save the cost +of a memory load. */ + +const int PRIV(ucp_typerange)[] = { + ucp_Cc, ucp_Cs, + ucp_Ll, ucp_Lu, + ucp_Mc, ucp_Mn, + ucp_Nd, ucp_No, + ucp_Pc, ucp_Ps, + ucp_Sc, ucp_So, + ucp_Zl, ucp_Zs, +}; +#endif /* SUPPORT_JIT */ + +/* The pcre_utt[] table below translates Unicode property names into type and +code values. It is searched by binary chop, so must be in collating sequence of +name. Originally, the table contained pointers to the name strings in the first +field of each entry. However, that leads to a large number of relocations when +a shared library is dynamically loaded. A significant reduction is made by +putting all the names into a single, large string and then using offsets in the +table itself. Maintenance is more error-prone, but frequent changes to this +data are unlikely. + +July 2008: There is now a script called maint/GenerateUtt.py that can be used +to generate this data automatically instead of maintaining it by hand. + +The script was updated in March 2009 to generate a new EBCDIC-compliant +version. Like all other character and string literals that are compared against +the regular expression pattern, we must use STR_ macros instead of literal +strings to make sure that UTF-8 support works on EBCDIC platforms. */ + +#define STRING_Any0 STR_A STR_n STR_y "\0" +#define STRING_Arabic0 STR_A STR_r STR_a STR_b STR_i STR_c "\0" +#define STRING_Armenian0 STR_A STR_r STR_m STR_e STR_n STR_i STR_a STR_n "\0" +#define STRING_Avestan0 STR_A STR_v STR_e STR_s STR_t STR_a STR_n "\0" +#define STRING_Balinese0 STR_B STR_a STR_l STR_i STR_n STR_e STR_s STR_e "\0" +#define STRING_Bamum0 STR_B STR_a STR_m STR_u STR_m "\0" +#define STRING_Batak0 STR_B STR_a STR_t STR_a STR_k "\0" +#define STRING_Bengali0 STR_B STR_e STR_n STR_g STR_a STR_l STR_i "\0" +#define STRING_Bopomofo0 STR_B STR_o STR_p STR_o STR_m STR_o STR_f STR_o "\0" +#define STRING_Brahmi0 STR_B STR_r STR_a STR_h STR_m STR_i "\0" +#define STRING_Braille0 STR_B STR_r STR_a STR_i STR_l STR_l STR_e "\0" +#define STRING_Buginese0 STR_B STR_u STR_g STR_i STR_n STR_e STR_s STR_e "\0" +#define STRING_Buhid0 STR_B STR_u STR_h STR_i STR_d "\0" +#define STRING_C0 STR_C "\0" +#define STRING_Canadian_Aboriginal0 STR_C STR_a STR_n STR_a STR_d STR_i STR_a STR_n STR_UNDERSCORE STR_A STR_b STR_o STR_r STR_i STR_g STR_i STR_n STR_a STR_l "\0" +#define STRING_Carian0 STR_C STR_a STR_r STR_i STR_a STR_n "\0" +#define STRING_Cc0 STR_C STR_c "\0" +#define STRING_Cf0 STR_C STR_f "\0" +#define STRING_Chakma0 STR_C STR_h STR_a STR_k STR_m STR_a "\0" +#define STRING_Cham0 STR_C STR_h STR_a STR_m "\0" +#define STRING_Cherokee0 STR_C STR_h STR_e STR_r STR_o STR_k STR_e STR_e "\0" +#define STRING_Cn0 STR_C STR_n "\0" +#define STRING_Co0 STR_C STR_o "\0" +#define STRING_Common0 STR_C STR_o STR_m STR_m STR_o STR_n "\0" +#define STRING_Coptic0 STR_C STR_o STR_p STR_t STR_i STR_c "\0" +#define STRING_Cs0 STR_C STR_s "\0" +#define STRING_Cuneiform0 STR_C STR_u STR_n STR_e STR_i STR_f STR_o STR_r STR_m "\0" +#define STRING_Cypriot0 STR_C STR_y STR_p STR_r STR_i STR_o STR_t "\0" +#define STRING_Cyrillic0 STR_C STR_y STR_r STR_i STR_l STR_l STR_i STR_c "\0" +#define STRING_Deseret0 STR_D STR_e STR_s STR_e STR_r STR_e STR_t "\0" +#define STRING_Devanagari0 STR_D STR_e STR_v STR_a STR_n STR_a STR_g STR_a STR_r STR_i "\0" +#define STRING_Egyptian_Hieroglyphs0 STR_E STR_g STR_y STR_p STR_t STR_i STR_a STR_n STR_UNDERSCORE STR_H STR_i STR_e STR_r STR_o STR_g STR_l STR_y STR_p STR_h STR_s "\0" +#define STRING_Ethiopic0 STR_E STR_t STR_h STR_i STR_o STR_p STR_i STR_c "\0" +#define STRING_Georgian0 STR_G STR_e STR_o STR_r STR_g STR_i STR_a STR_n "\0" +#define STRING_Glagolitic0 STR_G STR_l STR_a STR_g STR_o STR_l STR_i STR_t STR_i STR_c "\0" +#define STRING_Gothic0 STR_G STR_o STR_t STR_h STR_i STR_c "\0" +#define STRING_Greek0 STR_G STR_r STR_e STR_e STR_k "\0" +#define STRING_Gujarati0 STR_G STR_u STR_j STR_a STR_r STR_a STR_t STR_i "\0" +#define STRING_Gurmukhi0 STR_G STR_u STR_r STR_m STR_u STR_k STR_h STR_i "\0" +#define STRING_Han0 STR_H STR_a STR_n "\0" +#define STRING_Hangul0 STR_H STR_a STR_n STR_g STR_u STR_l "\0" +#define STRING_Hanunoo0 STR_H STR_a STR_n STR_u STR_n STR_o STR_o "\0" +#define STRING_Hebrew0 STR_H STR_e STR_b STR_r STR_e STR_w "\0" +#define STRING_Hiragana0 STR_H STR_i STR_r STR_a STR_g STR_a STR_n STR_a "\0" +#define STRING_Imperial_Aramaic0 STR_I STR_m STR_p STR_e STR_r STR_i STR_a STR_l STR_UNDERSCORE STR_A STR_r STR_a STR_m STR_a STR_i STR_c "\0" +#define STRING_Inherited0 STR_I STR_n STR_h STR_e STR_r STR_i STR_t STR_e STR_d "\0" +#define STRING_Inscriptional_Pahlavi0 STR_I STR_n STR_s STR_c STR_r STR_i STR_p STR_t STR_i STR_o STR_n STR_a STR_l STR_UNDERSCORE STR_P STR_a STR_h STR_l STR_a STR_v STR_i "\0" +#define STRING_Inscriptional_Parthian0 STR_I STR_n STR_s STR_c STR_r STR_i STR_p STR_t STR_i STR_o STR_n STR_a STR_l STR_UNDERSCORE STR_P STR_a STR_r STR_t STR_h STR_i STR_a STR_n "\0" +#define STRING_Javanese0 STR_J STR_a STR_v STR_a STR_n STR_e STR_s STR_e "\0" +#define STRING_Kaithi0 STR_K STR_a STR_i STR_t STR_h STR_i "\0" +#define STRING_Kannada0 STR_K STR_a STR_n STR_n STR_a STR_d STR_a "\0" +#define STRING_Katakana0 STR_K STR_a STR_t STR_a STR_k STR_a STR_n STR_a "\0" +#define STRING_Kayah_Li0 STR_K STR_a STR_y STR_a STR_h STR_UNDERSCORE STR_L STR_i "\0" +#define STRING_Kharoshthi0 STR_K STR_h STR_a STR_r STR_o STR_s STR_h STR_t STR_h STR_i "\0" +#define STRING_Khmer0 STR_K STR_h STR_m STR_e STR_r "\0" +#define STRING_L0 STR_L "\0" +#define STRING_L_AMPERSAND0 STR_L STR_AMPERSAND "\0" +#define STRING_Lao0 STR_L STR_a STR_o "\0" +#define STRING_Latin0 STR_L STR_a STR_t STR_i STR_n "\0" +#define STRING_Lepcha0 STR_L STR_e STR_p STR_c STR_h STR_a "\0" +#define STRING_Limbu0 STR_L STR_i STR_m STR_b STR_u "\0" +#define STRING_Linear_B0 STR_L STR_i STR_n STR_e STR_a STR_r STR_UNDERSCORE STR_B "\0" +#define STRING_Lisu0 STR_L STR_i STR_s STR_u "\0" +#define STRING_Ll0 STR_L STR_l "\0" +#define STRING_Lm0 STR_L STR_m "\0" +#define STRING_Lo0 STR_L STR_o "\0" +#define STRING_Lt0 STR_L STR_t "\0" +#define STRING_Lu0 STR_L STR_u "\0" +#define STRING_Lycian0 STR_L STR_y STR_c STR_i STR_a STR_n "\0" +#define STRING_Lydian0 STR_L STR_y STR_d STR_i STR_a STR_n "\0" +#define STRING_M0 STR_M "\0" +#define STRING_Malayalam0 STR_M STR_a STR_l STR_a STR_y STR_a STR_l STR_a STR_m "\0" +#define STRING_Mandaic0 STR_M STR_a STR_n STR_d STR_a STR_i STR_c "\0" +#define STRING_Mc0 STR_M STR_c "\0" +#define STRING_Me0 STR_M STR_e "\0" +#define STRING_Meetei_Mayek0 STR_M STR_e STR_e STR_t STR_e STR_i STR_UNDERSCORE STR_M STR_a STR_y STR_e STR_k "\0" +#define STRING_Meroitic_Cursive0 STR_M STR_e STR_r STR_o STR_i STR_t STR_i STR_c STR_UNDERSCORE STR_C STR_u STR_r STR_s STR_i STR_v STR_e "\0" +#define STRING_Meroitic_Hieroglyphs0 STR_M STR_e STR_r STR_o STR_i STR_t STR_i STR_c STR_UNDERSCORE STR_H STR_i STR_e STR_r STR_o STR_g STR_l STR_y STR_p STR_h STR_s "\0" +#define STRING_Miao0 STR_M STR_i STR_a STR_o "\0" +#define STRING_Mn0 STR_M STR_n "\0" +#define STRING_Mongolian0 STR_M STR_o STR_n STR_g STR_o STR_l STR_i STR_a STR_n "\0" +#define STRING_Myanmar0 STR_M STR_y STR_a STR_n STR_m STR_a STR_r "\0" +#define STRING_N0 STR_N "\0" +#define STRING_Nd0 STR_N STR_d "\0" +#define STRING_New_Tai_Lue0 STR_N STR_e STR_w STR_UNDERSCORE STR_T STR_a STR_i STR_UNDERSCORE STR_L STR_u STR_e "\0" +#define STRING_Nko0 STR_N STR_k STR_o "\0" +#define STRING_Nl0 STR_N STR_l "\0" +#define STRING_No0 STR_N STR_o "\0" +#define STRING_Ogham0 STR_O STR_g STR_h STR_a STR_m "\0" +#define STRING_Ol_Chiki0 STR_O STR_l STR_UNDERSCORE STR_C STR_h STR_i STR_k STR_i "\0" +#define STRING_Old_Italic0 STR_O STR_l STR_d STR_UNDERSCORE STR_I STR_t STR_a STR_l STR_i STR_c "\0" +#define STRING_Old_Persian0 STR_O STR_l STR_d STR_UNDERSCORE STR_P STR_e STR_r STR_s STR_i STR_a STR_n "\0" +#define STRING_Old_South_Arabian0 STR_O STR_l STR_d STR_UNDERSCORE STR_S STR_o STR_u STR_t STR_h STR_UNDERSCORE STR_A STR_r STR_a STR_b STR_i STR_a STR_n "\0" +#define STRING_Old_Turkic0 STR_O STR_l STR_d STR_UNDERSCORE STR_T STR_u STR_r STR_k STR_i STR_c "\0" +#define STRING_Oriya0 STR_O STR_r STR_i STR_y STR_a "\0" +#define STRING_Osmanya0 STR_O STR_s STR_m STR_a STR_n STR_y STR_a "\0" +#define STRING_P0 STR_P "\0" +#define STRING_Pc0 STR_P STR_c "\0" +#define STRING_Pd0 STR_P STR_d "\0" +#define STRING_Pe0 STR_P STR_e "\0" +#define STRING_Pf0 STR_P STR_f "\0" +#define STRING_Phags_Pa0 STR_P STR_h STR_a STR_g STR_s STR_UNDERSCORE STR_P STR_a "\0" +#define STRING_Phoenician0 STR_P STR_h STR_o STR_e STR_n STR_i STR_c STR_i STR_a STR_n "\0" +#define STRING_Pi0 STR_P STR_i "\0" +#define STRING_Po0 STR_P STR_o "\0" +#define STRING_Ps0 STR_P STR_s "\0" +#define STRING_Rejang0 STR_R STR_e STR_j STR_a STR_n STR_g "\0" +#define STRING_Runic0 STR_R STR_u STR_n STR_i STR_c "\0" +#define STRING_S0 STR_S "\0" +#define STRING_Samaritan0 STR_S STR_a STR_m STR_a STR_r STR_i STR_t STR_a STR_n "\0" +#define STRING_Saurashtra0 STR_S STR_a STR_u STR_r STR_a STR_s STR_h STR_t STR_r STR_a "\0" +#define STRING_Sc0 STR_S STR_c "\0" +#define STRING_Sharada0 STR_S STR_h STR_a STR_r STR_a STR_d STR_a "\0" +#define STRING_Shavian0 STR_S STR_h STR_a STR_v STR_i STR_a STR_n "\0" +#define STRING_Sinhala0 STR_S STR_i STR_n STR_h STR_a STR_l STR_a "\0" +#define STRING_Sk0 STR_S STR_k "\0" +#define STRING_Sm0 STR_S STR_m "\0" +#define STRING_So0 STR_S STR_o "\0" +#define STRING_Sora_Sompeng0 STR_S STR_o STR_r STR_a STR_UNDERSCORE STR_S STR_o STR_m STR_p STR_e STR_n STR_g "\0" +#define STRING_Sundanese0 STR_S STR_u STR_n STR_d STR_a STR_n STR_e STR_s STR_e "\0" +#define STRING_Syloti_Nagri0 STR_S STR_y STR_l STR_o STR_t STR_i STR_UNDERSCORE STR_N STR_a STR_g STR_r STR_i "\0" +#define STRING_Syriac0 STR_S STR_y STR_r STR_i STR_a STR_c "\0" +#define STRING_Tagalog0 STR_T STR_a STR_g STR_a STR_l STR_o STR_g "\0" +#define STRING_Tagbanwa0 STR_T STR_a STR_g STR_b STR_a STR_n STR_w STR_a "\0" +#define STRING_Tai_Le0 STR_T STR_a STR_i STR_UNDERSCORE STR_L STR_e "\0" +#define STRING_Tai_Tham0 STR_T STR_a STR_i STR_UNDERSCORE STR_T STR_h STR_a STR_m "\0" +#define STRING_Tai_Viet0 STR_T STR_a STR_i STR_UNDERSCORE STR_V STR_i STR_e STR_t "\0" +#define STRING_Takri0 STR_T STR_a STR_k STR_r STR_i "\0" +#define STRING_Tamil0 STR_T STR_a STR_m STR_i STR_l "\0" +#define STRING_Telugu0 STR_T STR_e STR_l STR_u STR_g STR_u "\0" +#define STRING_Thaana0 STR_T STR_h STR_a STR_a STR_n STR_a "\0" +#define STRING_Thai0 STR_T STR_h STR_a STR_i "\0" +#define STRING_Tibetan0 STR_T STR_i STR_b STR_e STR_t STR_a STR_n "\0" +#define STRING_Tifinagh0 STR_T STR_i STR_f STR_i STR_n STR_a STR_g STR_h "\0" +#define STRING_Ugaritic0 STR_U STR_g STR_a STR_r STR_i STR_t STR_i STR_c "\0" +#define STRING_Vai0 STR_V STR_a STR_i "\0" +#define STRING_Xan0 STR_X STR_a STR_n "\0" +#define STRING_Xps0 STR_X STR_p STR_s "\0" +#define STRING_Xsp0 STR_X STR_s STR_p "\0" +#define STRING_Xuc0 STR_X STR_u STR_c "\0" +#define STRING_Xwd0 STR_X STR_w STR_d "\0" +#define STRING_Yi0 STR_Y STR_i "\0" +#define STRING_Z0 STR_Z "\0" +#define STRING_Zl0 STR_Z STR_l "\0" +#define STRING_Zp0 STR_Z STR_p "\0" +#define STRING_Zs0 STR_Z STR_s "\0" + +const char PRIV(utt_names)[] = + STRING_Any0 + STRING_Arabic0 + STRING_Armenian0 + STRING_Avestan0 + STRING_Balinese0 + STRING_Bamum0 + STRING_Batak0 + STRING_Bengali0 + STRING_Bopomofo0 + STRING_Brahmi0 + STRING_Braille0 + STRING_Buginese0 + STRING_Buhid0 + STRING_C0 + STRING_Canadian_Aboriginal0 + STRING_Carian0 + STRING_Cc0 + STRING_Cf0 + STRING_Chakma0 + STRING_Cham0 + STRING_Cherokee0 + STRING_Cn0 + STRING_Co0 + STRING_Common0 + STRING_Coptic0 + STRING_Cs0 + STRING_Cuneiform0 + STRING_Cypriot0 + STRING_Cyrillic0 + STRING_Deseret0 + STRING_Devanagari0 + STRING_Egyptian_Hieroglyphs0 + STRING_Ethiopic0 + STRING_Georgian0 + STRING_Glagolitic0 + STRING_Gothic0 + STRING_Greek0 + STRING_Gujarati0 + STRING_Gurmukhi0 + STRING_Han0 + STRING_Hangul0 + STRING_Hanunoo0 + STRING_Hebrew0 + STRING_Hiragana0 + STRING_Imperial_Aramaic0 + STRING_Inherited0 + STRING_Inscriptional_Pahlavi0 + STRING_Inscriptional_Parthian0 + STRING_Javanese0 + STRING_Kaithi0 + STRING_Kannada0 + STRING_Katakana0 + STRING_Kayah_Li0 + STRING_Kharoshthi0 + STRING_Khmer0 + STRING_L0 + STRING_L_AMPERSAND0 + STRING_Lao0 + STRING_Latin0 + STRING_Lepcha0 + STRING_Limbu0 + STRING_Linear_B0 + STRING_Lisu0 + STRING_Ll0 + STRING_Lm0 + STRING_Lo0 + STRING_Lt0 + STRING_Lu0 + STRING_Lycian0 + STRING_Lydian0 + STRING_M0 + STRING_Malayalam0 + STRING_Mandaic0 + STRING_Mc0 + STRING_Me0 + STRING_Meetei_Mayek0 + STRING_Meroitic_Cursive0 + STRING_Meroitic_Hieroglyphs0 + STRING_Miao0 + STRING_Mn0 + STRING_Mongolian0 + STRING_Myanmar0 + STRING_N0 + STRING_Nd0 + STRING_New_Tai_Lue0 + STRING_Nko0 + STRING_Nl0 + STRING_No0 + STRING_Ogham0 + STRING_Ol_Chiki0 + STRING_Old_Italic0 + STRING_Old_Persian0 + STRING_Old_South_Arabian0 + STRING_Old_Turkic0 + STRING_Oriya0 + STRING_Osmanya0 + STRING_P0 + STRING_Pc0 + STRING_Pd0 + STRING_Pe0 + STRING_Pf0 + STRING_Phags_Pa0 + STRING_Phoenician0 + STRING_Pi0 + STRING_Po0 + STRING_Ps0 + STRING_Rejang0 + STRING_Runic0 + STRING_S0 + STRING_Samaritan0 + STRING_Saurashtra0 + STRING_Sc0 + STRING_Sharada0 + STRING_Shavian0 + STRING_Sinhala0 + STRING_Sk0 + STRING_Sm0 + STRING_So0 + STRING_Sora_Sompeng0 + STRING_Sundanese0 + STRING_Syloti_Nagri0 + STRING_Syriac0 + STRING_Tagalog0 + STRING_Tagbanwa0 + STRING_Tai_Le0 + STRING_Tai_Tham0 + STRING_Tai_Viet0 + STRING_Takri0 + STRING_Tamil0 + STRING_Telugu0 + STRING_Thaana0 + STRING_Thai0 + STRING_Tibetan0 + STRING_Tifinagh0 + STRING_Ugaritic0 + STRING_Vai0 + STRING_Xan0 + STRING_Xps0 + STRING_Xsp0 + STRING_Xuc0 + STRING_Xwd0 + STRING_Yi0 + STRING_Z0 + STRING_Zl0 + STRING_Zp0 + STRING_Zs0; + +const ucp_type_table PRIV(utt)[] = { + { 0, PT_ANY, 0 }, + { 4, PT_SC, ucp_Arabic }, + { 11, PT_SC, ucp_Armenian }, + { 20, PT_SC, ucp_Avestan }, + { 28, PT_SC, ucp_Balinese }, + { 37, PT_SC, ucp_Bamum }, + { 43, PT_SC, ucp_Batak }, + { 49, PT_SC, ucp_Bengali }, + { 57, PT_SC, ucp_Bopomofo }, + { 66, PT_SC, ucp_Brahmi }, + { 73, PT_SC, ucp_Braille }, + { 81, PT_SC, ucp_Buginese }, + { 90, PT_SC, ucp_Buhid }, + { 96, PT_GC, ucp_C }, + { 98, PT_SC, ucp_Canadian_Aboriginal }, + { 118, PT_SC, ucp_Carian }, + { 125, PT_PC, ucp_Cc }, + { 128, PT_PC, ucp_Cf }, + { 131, PT_SC, ucp_Chakma }, + { 138, PT_SC, ucp_Cham }, + { 143, PT_SC, ucp_Cherokee }, + { 152, PT_PC, ucp_Cn }, + { 155, PT_PC, ucp_Co }, + { 158, PT_SC, ucp_Common }, + { 165, PT_SC, ucp_Coptic }, + { 172, PT_PC, ucp_Cs }, + { 175, PT_SC, ucp_Cuneiform }, + { 185, PT_SC, ucp_Cypriot }, + { 193, PT_SC, ucp_Cyrillic }, + { 202, PT_SC, ucp_Deseret }, + { 210, PT_SC, ucp_Devanagari }, + { 221, PT_SC, ucp_Egyptian_Hieroglyphs }, + { 242, PT_SC, ucp_Ethiopic }, + { 251, PT_SC, ucp_Georgian }, + { 260, PT_SC, ucp_Glagolitic }, + { 271, PT_SC, ucp_Gothic }, + { 278, PT_SC, ucp_Greek }, + { 284, PT_SC, ucp_Gujarati }, + { 293, PT_SC, ucp_Gurmukhi }, + { 302, PT_SC, ucp_Han }, + { 306, PT_SC, ucp_Hangul }, + { 313, PT_SC, ucp_Hanunoo }, + { 321, PT_SC, ucp_Hebrew }, + { 328, PT_SC, ucp_Hiragana }, + { 337, PT_SC, ucp_Imperial_Aramaic }, + { 354, PT_SC, ucp_Inherited }, + { 364, PT_SC, ucp_Inscriptional_Pahlavi }, + { 386, PT_SC, ucp_Inscriptional_Parthian }, + { 409, PT_SC, ucp_Javanese }, + { 418, PT_SC, ucp_Kaithi }, + { 425, PT_SC, ucp_Kannada }, + { 433, PT_SC, ucp_Katakana }, + { 442, PT_SC, ucp_Kayah_Li }, + { 451, PT_SC, ucp_Kharoshthi }, + { 462, PT_SC, ucp_Khmer }, + { 468, PT_GC, ucp_L }, + { 470, PT_LAMP, 0 }, + { 473, PT_SC, ucp_Lao }, + { 477, PT_SC, ucp_Latin }, + { 483, PT_SC, ucp_Lepcha }, + { 490, PT_SC, ucp_Limbu }, + { 496, PT_SC, ucp_Linear_B }, + { 505, PT_SC, ucp_Lisu }, + { 510, PT_PC, ucp_Ll }, + { 513, PT_PC, ucp_Lm }, + { 516, PT_PC, ucp_Lo }, + { 519, PT_PC, ucp_Lt }, + { 522, PT_PC, ucp_Lu }, + { 525, PT_SC, ucp_Lycian }, + { 532, PT_SC, ucp_Lydian }, + { 539, PT_GC, ucp_M }, + { 541, PT_SC, ucp_Malayalam }, + { 551, PT_SC, ucp_Mandaic }, + { 559, PT_PC, ucp_Mc }, + { 562, PT_PC, ucp_Me }, + { 565, PT_SC, ucp_Meetei_Mayek }, + { 578, PT_SC, ucp_Meroitic_Cursive }, + { 595, PT_SC, ucp_Meroitic_Hieroglyphs }, + { 616, PT_SC, ucp_Miao }, + { 621, PT_PC, ucp_Mn }, + { 624, PT_SC, ucp_Mongolian }, + { 634, PT_SC, ucp_Myanmar }, + { 642, PT_GC, ucp_N }, + { 644, PT_PC, ucp_Nd }, + { 647, PT_SC, ucp_New_Tai_Lue }, + { 659, PT_SC, ucp_Nko }, + { 663, PT_PC, ucp_Nl }, + { 666, PT_PC, ucp_No }, + { 669, PT_SC, ucp_Ogham }, + { 675, PT_SC, ucp_Ol_Chiki }, + { 684, PT_SC, ucp_Old_Italic }, + { 695, PT_SC, ucp_Old_Persian }, + { 707, PT_SC, ucp_Old_South_Arabian }, + { 725, PT_SC, ucp_Old_Turkic }, + { 736, PT_SC, ucp_Oriya }, + { 742, PT_SC, ucp_Osmanya }, + { 750, PT_GC, ucp_P }, + { 752, PT_PC, ucp_Pc }, + { 755, PT_PC, ucp_Pd }, + { 758, PT_PC, ucp_Pe }, + { 761, PT_PC, ucp_Pf }, + { 764, PT_SC, ucp_Phags_Pa }, + { 773, PT_SC, ucp_Phoenician }, + { 784, PT_PC, ucp_Pi }, + { 787, PT_PC, ucp_Po }, + { 790, PT_PC, ucp_Ps }, + { 793, PT_SC, ucp_Rejang }, + { 800, PT_SC, ucp_Runic }, + { 806, PT_GC, ucp_S }, + { 808, PT_SC, ucp_Samaritan }, + { 818, PT_SC, ucp_Saurashtra }, + { 829, PT_PC, ucp_Sc }, + { 832, PT_SC, ucp_Sharada }, + { 840, PT_SC, ucp_Shavian }, + { 848, PT_SC, ucp_Sinhala }, + { 856, PT_PC, ucp_Sk }, + { 859, PT_PC, ucp_Sm }, + { 862, PT_PC, ucp_So }, + { 865, PT_SC, ucp_Sora_Sompeng }, + { 878, PT_SC, ucp_Sundanese }, + { 888, PT_SC, ucp_Syloti_Nagri }, + { 901, PT_SC, ucp_Syriac }, + { 908, PT_SC, ucp_Tagalog }, + { 916, PT_SC, ucp_Tagbanwa }, + { 925, PT_SC, ucp_Tai_Le }, + { 932, PT_SC, ucp_Tai_Tham }, + { 941, PT_SC, ucp_Tai_Viet }, + { 950, PT_SC, ucp_Takri }, + { 956, PT_SC, ucp_Tamil }, + { 962, PT_SC, ucp_Telugu }, + { 969, PT_SC, ucp_Thaana }, + { 976, PT_SC, ucp_Thai }, + { 981, PT_SC, ucp_Tibetan }, + { 989, PT_SC, ucp_Tifinagh }, + { 998, PT_SC, ucp_Ugaritic }, + { 1007, PT_SC, ucp_Vai }, + { 1011, PT_ALNUM, 0 }, + { 1015, PT_PXSPACE, 0 }, + { 1019, PT_SPACE, 0 }, + { 1023, PT_UCNC, 0 }, + { 1027, PT_WORD, 0 }, + { 1031, PT_SC, ucp_Yi }, + { 1034, PT_GC, ucp_Z }, + { 1036, PT_PC, ucp_Zl }, + { 1039, PT_PC, ucp_Zp }, + { 1042, PT_PC, ucp_Zs } +}; + +const int PRIV(utt_size) = sizeof(PRIV(utt)) / sizeof(ucp_type_table); + +#endif /* SUPPORT_UTF */ + +/* End of pcre_tables.c */ diff --git a/plugins/Pcre16/src/pcre_ucd.c b/plugins/Pcre16/src/pcre_ucd.c new file mode 100644 index 0000000000..46ea70c44c --- /dev/null +++ b/plugins/Pcre16/src/pcre_ucd.c @@ -0,0 +1,3297 @@ +/* This module is generated by the maint/MultiStage2.py script. +Do not modify it by hand. Instead modify the script and run it +to regenerate this code. + +As well as being part of the PCRE library, this module is #included +by the pcretest program, which redefines the PRIV macro to change +table names from _pcre_xxx to xxxx, thereby avoiding name clashes +with the library. At present, just one of these tables is actually +needed. */ + +#ifndef PCRE_INCLUDED + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#include "pcre_internal.h" + +#endif /* PCRE_INCLUDED */ + +/* Unicode character database. */ +/* This file was autogenerated by the MultiStage2.py script. */ +/* Total size: 65688 bytes, block size: 128. */ + +/* The tables herein are needed only when UCP support is built +into PCRE. This module should not be referenced otherwise, so +it should not matter whether it is compiled or not. However +a comment was received about space saving - maybe the guy linked +all the modules rather than using a library - so we include a +condition to cut out the tables when not needed. But don't leave +a totally empty module because some compilers barf at that. +Instead, just supply small dummy tables. */ + +#ifndef SUPPORT_UCP +const ucd_record PRIV(ucd_records)[] = {{0,0,0,0,0 }}; +const pcre_uint8 PRIV(ucd_stage1)[] = {0}; +const pcre_uint16 PRIV(ucd_stage2)[] = {0}; +const pcre_uint32 PRIV(ucd_caseless_sets)[] = {0}; +#else + +/* When recompiling tables with a new Unicode version, please check the +types in this structure definition from pcre_internal.h (the actual +field names will be different): + +typedef struct { +pcre_uint8 property_0; +pcre_uint8 property_1; +pcre_uint8 property_2; +pcre_uint8 property_3; +pcre_int32 property_4; +} ucd_record; +*/ + + +const pcre_uint32 PRIV(ucd_caseless_sets)[] = { + NOTACHAR, + 0x0053, 0x0073, 0x017f, NOTACHAR, + 0x01c4, 0x01c5, 0x01c6, NOTACHAR, + 0x01c7, 0x01c8, 0x01c9, NOTACHAR, + 0x01ca, 0x01cb, 0x01cc, NOTACHAR, + 0x01f1, 0x01f2, 0x01f3, NOTACHAR, + 0x0345, 0x0399, 0x03b9, 0x1fbe, NOTACHAR, + 0x00b5, 0x039c, 0x03bc, NOTACHAR, + 0x03a3, 0x03c2, 0x03c3, NOTACHAR, + 0x0392, 0x03b2, 0x03d0, NOTACHAR, + 0x0398, 0x03b8, 0x03d1, 0x03f4, NOTACHAR, + 0x03a6, 0x03c6, 0x03d5, NOTACHAR, + 0x03a0, 0x03c0, 0x03d6, NOTACHAR, + 0x039a, 0x03ba, 0x03f0, NOTACHAR, + 0x03a1, 0x03c1, 0x03f1, NOTACHAR, + 0x0395, 0x03b5, 0x03f5, NOTACHAR, + 0x1e60, 0x1e61, 0x1e9b, NOTACHAR, + 0x03a9, 0x03c9, 0x2126, NOTACHAR, + 0x004b, 0x006b, 0x212a, NOTACHAR, + 0x00c5, 0x00e5, 0x212b, NOTACHAR, +}; + +/* When #included in pcretest, we don't need this large table. */ + +#ifndef PCRE_INCLUDED + +const ucd_record PRIV(ucd_records)[] = { /* 5016 bytes, record size 8 */ + { 9, 0, 2, 0, 0, }, /* 0 */ + { 9, 0, 1, 0, 0, }, /* 1 */ + { 9, 0, 0, 0, 0, }, /* 2 */ + { 9, 29, 12, 0, 0, }, /* 3 */ + { 9, 21, 12, 0, 0, }, /* 4 */ + { 9, 23, 12, 0, 0, }, /* 5 */ + { 9, 22, 12, 0, 0, }, /* 6 */ + { 9, 18, 12, 0, 0, }, /* 7 */ + { 9, 25, 12, 0, 0, }, /* 8 */ + { 9, 17, 12, 0, 0, }, /* 9 */ + { 9, 13, 12, 0, 0, }, /* 10 */ + { 33, 9, 12, 0, 32, }, /* 11 */ + { 33, 9, 12, 71, 32, }, /* 12 */ + { 33, 9, 12, 1, 32, }, /* 13 */ + { 9, 24, 12, 0, 0, }, /* 14 */ + { 9, 16, 12, 0, 0, }, /* 15 */ + { 33, 5, 12, 0, -32, }, /* 16 */ + { 33, 5, 12, 71, -32, }, /* 17 */ + { 33, 5, 12, 1, -32, }, /* 18 */ + { 9, 26, 12, 0, 0, }, /* 19 */ + { 33, 7, 12, 0, 0, }, /* 20 */ + { 9, 20, 12, 0, 0, }, /* 21 */ + { 9, 1, 2, 0, 0, }, /* 22 */ + { 9, 15, 12, 0, 0, }, /* 23 */ + { 9, 5, 12, 26, 775, }, /* 24 */ + { 9, 19, 12, 0, 0, }, /* 25 */ + { 33, 9, 12, 75, 32, }, /* 26 */ + { 33, 5, 12, 0, 7615, }, /* 27 */ + { 33, 5, 12, 75, -32, }, /* 28 */ + { 33, 5, 12, 0, 121, }, /* 29 */ + { 33, 9, 12, 0, 1, }, /* 30 */ + { 33, 5, 12, 0, -1, }, /* 31 */ + { 33, 9, 12, 0, 0, }, /* 32 */ + { 33, 5, 12, 0, 0, }, /* 33 */ + { 33, 9, 12, 0, -121, }, /* 34 */ + { 33, 5, 12, 1, -268, }, /* 35 */ + { 33, 5, 12, 0, 195, }, /* 36 */ + { 33, 9, 12, 0, 210, }, /* 37 */ + { 33, 9, 12, 0, 206, }, /* 38 */ + { 33, 9, 12, 0, 205, }, /* 39 */ + { 33, 9, 12, 0, 79, }, /* 40 */ + { 33, 9, 12, 0, 202, }, /* 41 */ + { 33, 9, 12, 0, 203, }, /* 42 */ + { 33, 9, 12, 0, 207, }, /* 43 */ + { 33, 5, 12, 0, 97, }, /* 44 */ + { 33, 9, 12, 0, 211, }, /* 45 */ + { 33, 9, 12, 0, 209, }, /* 46 */ + { 33, 5, 12, 0, 163, }, /* 47 */ + { 33, 9, 12, 0, 213, }, /* 48 */ + { 33, 5, 12, 0, 130, }, /* 49 */ + { 33, 9, 12, 0, 214, }, /* 50 */ + { 33, 9, 12, 0, 218, }, /* 51 */ + { 33, 9, 12, 0, 217, }, /* 52 */ + { 33, 9, 12, 0, 219, }, /* 53 */ + { 33, 5, 12, 0, 56, }, /* 54 */ + { 33, 9, 12, 5, 2, }, /* 55 */ + { 33, 8, 12, 5, 1, }, /* 56 */ + { 33, 5, 12, 5, -2, }, /* 57 */ + { 33, 9, 12, 9, 2, }, /* 58 */ + { 33, 8, 12, 9, 1, }, /* 59 */ + { 33, 5, 12, 9, -2, }, /* 60 */ + { 33, 9, 12, 13, 2, }, /* 61 */ + { 33, 8, 12, 13, 1, }, /* 62 */ + { 33, 5, 12, 13, -2, }, /* 63 */ + { 33, 5, 12, 0, -79, }, /* 64 */ + { 33, 9, 12, 17, 2, }, /* 65 */ + { 33, 8, 12, 17, 1, }, /* 66 */ + { 33, 5, 12, 17, -2, }, /* 67 */ + { 33, 9, 12, 0, -97, }, /* 68 */ + { 33, 9, 12, 0, -56, }, /* 69 */ + { 33, 9, 12, 0, -130, }, /* 70 */ + { 33, 9, 12, 0, 10795, }, /* 71 */ + { 33, 9, 12, 0, -163, }, /* 72 */ + { 33, 9, 12, 0, 10792, }, /* 73 */ + { 33, 5, 12, 0, 10815, }, /* 74 */ + { 33, 9, 12, 0, -195, }, /* 75 */ + { 33, 9, 12, 0, 69, }, /* 76 */ + { 33, 9, 12, 0, 71, }, /* 77 */ + { 33, 5, 12, 0, 10783, }, /* 78 */ + { 33, 5, 12, 0, 10780, }, /* 79 */ + { 33, 5, 12, 0, 10782, }, /* 80 */ + { 33, 5, 12, 0, -210, }, /* 81 */ + { 33, 5, 12, 0, -206, }, /* 82 */ + { 33, 5, 12, 0, -205, }, /* 83 */ + { 33, 5, 12, 0, -202, }, /* 84 */ + { 33, 5, 12, 0, -203, }, /* 85 */ + { 33, 5, 12, 0, -207, }, /* 86 */ + { 33, 5, 12, 0, 42280, }, /* 87 */ + { 33, 5, 12, 0, 42308, }, /* 88 */ + { 33, 5, 12, 0, -209, }, /* 89 */ + { 33, 5, 12, 0, -211, }, /* 90 */ + { 33, 5, 12, 0, 10743, }, /* 91 */ + { 33, 5, 12, 0, 10749, }, /* 92 */ + { 33, 5, 12, 0, -213, }, /* 93 */ + { 33, 5, 12, 0, -214, }, /* 94 */ + { 33, 5, 12, 0, 10727, }, /* 95 */ + { 33, 5, 12, 0, -218, }, /* 96 */ + { 33, 5, 12, 0, -69, }, /* 97 */ + { 33, 5, 12, 0, -217, }, /* 98 */ + { 33, 5, 12, 0, -71, }, /* 99 */ + { 33, 5, 12, 0, -219, }, /* 100 */ + { 33, 6, 12, 0, 0, }, /* 101 */ + { 9, 6, 12, 0, 0, }, /* 102 */ + { 3, 24, 12, 0, 0, }, /* 103 */ + { 27, 12, 3, 0, 0, }, /* 104 */ + { 27, 12, 3, 21, 116, }, /* 105 */ + { 19, 9, 12, 0, 1, }, /* 106 */ + { 19, 5, 12, 0, -1, }, /* 107 */ + { 19, 24, 12, 0, 0, }, /* 108 */ + { 9, 2, 12, 0, 0, }, /* 109 */ + { 19, 6, 12, 0, 0, }, /* 110 */ + { 19, 5, 12, 0, 130, }, /* 111 */ + { 19, 9, 12, 0, 38, }, /* 112 */ + { 19, 9, 12, 0, 37, }, /* 113 */ + { 19, 9, 12, 0, 64, }, /* 114 */ + { 19, 9, 12, 0, 63, }, /* 115 */ + { 19, 5, 12, 0, 0, }, /* 116 */ + { 19, 9, 12, 0, 32, }, /* 117 */ + { 19, 9, 12, 34, 32, }, /* 118 */ + { 19, 9, 12, 59, 32, }, /* 119 */ + { 19, 9, 12, 38, 32, }, /* 120 */ + { 19, 9, 12, 21, 32, }, /* 121 */ + { 19, 9, 12, 51, 32, }, /* 122 */ + { 19, 9, 12, 26, 32, }, /* 123 */ + { 19, 9, 12, 47, 32, }, /* 124 */ + { 19, 9, 12, 55, 32, }, /* 125 */ + { 19, 9, 12, 30, 32, }, /* 126 */ + { 19, 9, 12, 43, 32, }, /* 127 */ + { 19, 9, 12, 67, 32, }, /* 128 */ + { 19, 5, 12, 0, -38, }, /* 129 */ + { 19, 5, 12, 0, -37, }, /* 130 */ + { 19, 5, 12, 0, -32, }, /* 131 */ + { 19, 5, 12, 34, -32, }, /* 132 */ + { 19, 5, 12, 59, -32, }, /* 133 */ + { 19, 5, 12, 38, -32, }, /* 134 */ + { 19, 5, 12, 21, -116, }, /* 135 */ + { 19, 5, 12, 51, -32, }, /* 136 */ + { 19, 5, 12, 26, -775, }, /* 137 */ + { 19, 5, 12, 47, -32, }, /* 138 */ + { 19, 5, 12, 55, -32, }, /* 139 */ + { 19, 5, 12, 30, 1, }, /* 140 */ + { 19, 5, 12, 30, -32, }, /* 141 */ + { 19, 5, 12, 43, -32, }, /* 142 */ + { 19, 5, 12, 67, -32, }, /* 143 */ + { 19, 5, 12, 0, -64, }, /* 144 */ + { 19, 5, 12, 0, -63, }, /* 145 */ + { 19, 9, 12, 0, 8, }, /* 146 */ + { 19, 5, 12, 34, -30, }, /* 147 */ + { 19, 5, 12, 38, -25, }, /* 148 */ + { 19, 9, 12, 0, 0, }, /* 149 */ + { 19, 5, 12, 43, -15, }, /* 150 */ + { 19, 5, 12, 47, -22, }, /* 151 */ + { 19, 5, 12, 0, -8, }, /* 152 */ + { 10, 9, 12, 0, 1, }, /* 153 */ + { 10, 5, 12, 0, -1, }, /* 154 */ + { 19, 5, 12, 51, -54, }, /* 155 */ + { 19, 5, 12, 55, -48, }, /* 156 */ + { 19, 5, 12, 0, 7, }, /* 157 */ + { 19, 9, 12, 38, -60, }, /* 158 */ + { 19, 5, 12, 59, -64, }, /* 159 */ + { 19, 25, 12, 0, 0, }, /* 160 */ + { 19, 9, 12, 0, -7, }, /* 161 */ + { 19, 9, 12, 0, -130, }, /* 162 */ + { 12, 9, 12, 0, 80, }, /* 163 */ + { 12, 9, 12, 0, 32, }, /* 164 */ + { 12, 5, 12, 0, -32, }, /* 165 */ + { 12, 5, 12, 0, -80, }, /* 166 */ + { 12, 9, 12, 0, 1, }, /* 167 */ + { 12, 5, 12, 0, -1, }, /* 168 */ + { 12, 26, 12, 0, 0, }, /* 169 */ + { 12, 12, 3, 0, 0, }, /* 170 */ + { 12, 11, 3, 0, 0, }, /* 171 */ + { 12, 9, 12, 0, 15, }, /* 172 */ + { 12, 5, 12, 0, -15, }, /* 173 */ + { 1, 9, 12, 0, 48, }, /* 174 */ + { 1, 6, 12, 0, 0, }, /* 175 */ + { 1, 21, 12, 0, 0, }, /* 176 */ + { 1, 5, 12, 0, -48, }, /* 177 */ + { 1, 5, 12, 0, 0, }, /* 178 */ + { 1, 17, 12, 0, 0, }, /* 179 */ + { 1, 23, 12, 0, 0, }, /* 180 */ + { 25, 12, 3, 0, 0, }, /* 181 */ + { 25, 17, 12, 0, 0, }, /* 182 */ + { 25, 21, 12, 0, 0, }, /* 183 */ + { 25, 7, 12, 0, 0, }, /* 184 */ + { 0, 1, 2, 0, 0, }, /* 185 */ + { 0, 25, 12, 0, 0, }, /* 186 */ + { 0, 21, 12, 0, 0, }, /* 187 */ + { 0, 23, 12, 0, 0, }, /* 188 */ + { 0, 26, 12, 0, 0, }, /* 189 */ + { 0, 12, 3, 0, 0, }, /* 190 */ + { 0, 7, 12, 0, 0, }, /* 191 */ + { 0, 6, 12, 0, 0, }, /* 192 */ + { 0, 13, 12, 0, 0, }, /* 193 */ + { 49, 21, 12, 0, 0, }, /* 194 */ + { 49, 1, 2, 0, 0, }, /* 195 */ + { 49, 7, 12, 0, 0, }, /* 196 */ + { 49, 12, 3, 0, 0, }, /* 197 */ + { 55, 7, 12, 0, 0, }, /* 198 */ + { 55, 12, 3, 0, 0, }, /* 199 */ + { 63, 13, 12, 0, 0, }, /* 200 */ + { 63, 7, 12, 0, 0, }, /* 201 */ + { 63, 12, 3, 0, 0, }, /* 202 */ + { 63, 6, 12, 0, 0, }, /* 203 */ + { 63, 26, 12, 0, 0, }, /* 204 */ + { 63, 21, 12, 0, 0, }, /* 205 */ + { 89, 7, 12, 0, 0, }, /* 206 */ + { 89, 12, 3, 0, 0, }, /* 207 */ + { 89, 6, 12, 0, 0, }, /* 208 */ + { 89, 21, 12, 0, 0, }, /* 209 */ + { 94, 7, 12, 0, 0, }, /* 210 */ + { 94, 12, 3, 0, 0, }, /* 211 */ + { 94, 21, 12, 0, 0, }, /* 212 */ + { 14, 12, 3, 0, 0, }, /* 213 */ + { 14, 10, 5, 0, 0, }, /* 214 */ + { 14, 7, 12, 0, 0, }, /* 215 */ + { 14, 13, 12, 0, 0, }, /* 216 */ + { 14, 21, 12, 0, 0, }, /* 217 */ + { 14, 6, 12, 0, 0, }, /* 218 */ + { 2, 12, 3, 0, 0, }, /* 219 */ + { 2, 10, 5, 0, 0, }, /* 220 */ + { 2, 7, 12, 0, 0, }, /* 221 */ + { 2, 10, 3, 0, 0, }, /* 222 */ + { 2, 13, 12, 0, 0, }, /* 223 */ + { 2, 23, 12, 0, 0, }, /* 224 */ + { 2, 15, 12, 0, 0, }, /* 225 */ + { 2, 26, 12, 0, 0, }, /* 226 */ + { 21, 12, 3, 0, 0, }, /* 227 */ + { 21, 10, 5, 0, 0, }, /* 228 */ + { 21, 7, 12, 0, 0, }, /* 229 */ + { 21, 13, 12, 0, 0, }, /* 230 */ + { 20, 12, 3, 0, 0, }, /* 231 */ + { 20, 10, 5, 0, 0, }, /* 232 */ + { 20, 7, 12, 0, 0, }, /* 233 */ + { 20, 13, 12, 0, 0, }, /* 234 */ + { 20, 21, 12, 0, 0, }, /* 235 */ + { 20, 23, 12, 0, 0, }, /* 236 */ + { 43, 12, 3, 0, 0, }, /* 237 */ + { 43, 10, 5, 0, 0, }, /* 238 */ + { 43, 7, 12, 0, 0, }, /* 239 */ + { 43, 10, 3, 0, 0, }, /* 240 */ + { 43, 13, 12, 0, 0, }, /* 241 */ + { 43, 26, 12, 0, 0, }, /* 242 */ + { 43, 15, 12, 0, 0, }, /* 243 */ + { 53, 12, 3, 0, 0, }, /* 244 */ + { 53, 7, 12, 0, 0, }, /* 245 */ + { 53, 10, 3, 0, 0, }, /* 246 */ + { 53, 10, 5, 0, 0, }, /* 247 */ + { 53, 13, 12, 0, 0, }, /* 248 */ + { 53, 15, 12, 0, 0, }, /* 249 */ + { 53, 26, 12, 0, 0, }, /* 250 */ + { 53, 23, 12, 0, 0, }, /* 251 */ + { 54, 10, 5, 0, 0, }, /* 252 */ + { 54, 7, 12, 0, 0, }, /* 253 */ + { 54, 12, 3, 0, 0, }, /* 254 */ + { 54, 13, 12, 0, 0, }, /* 255 */ + { 54, 15, 12, 0, 0, }, /* 256 */ + { 54, 26, 12, 0, 0, }, /* 257 */ + { 28, 10, 5, 0, 0, }, /* 258 */ + { 28, 7, 12, 0, 0, }, /* 259 */ + { 28, 12, 3, 0, 0, }, /* 260 */ + { 28, 10, 3, 0, 0, }, /* 261 */ + { 28, 13, 12, 0, 0, }, /* 262 */ + { 36, 10, 5, 0, 0, }, /* 263 */ + { 36, 7, 12, 0, 0, }, /* 264 */ + { 36, 10, 3, 0, 0, }, /* 265 */ + { 36, 12, 3, 0, 0, }, /* 266 */ + { 36, 13, 12, 0, 0, }, /* 267 */ + { 36, 15, 12, 0, 0, }, /* 268 */ + { 36, 26, 12, 0, 0, }, /* 269 */ + { 47, 10, 5, 0, 0, }, /* 270 */ + { 47, 7, 12, 0, 0, }, /* 271 */ + { 47, 12, 3, 0, 0, }, /* 272 */ + { 47, 10, 3, 0, 0, }, /* 273 */ + { 47, 21, 12, 0, 0, }, /* 274 */ + { 56, 7, 12, 0, 0, }, /* 275 */ + { 56, 12, 3, 0, 0, }, /* 276 */ + { 56, 7, 5, 0, 0, }, /* 277 */ + { 56, 6, 12, 0, 0, }, /* 278 */ + { 56, 21, 12, 0, 0, }, /* 279 */ + { 56, 13, 12, 0, 0, }, /* 280 */ + { 32, 7, 12, 0, 0, }, /* 281 */ + { 32, 12, 3, 0, 0, }, /* 282 */ + { 32, 7, 5, 0, 0, }, /* 283 */ + { 32, 6, 12, 0, 0, }, /* 284 */ + { 32, 13, 12, 0, 0, }, /* 285 */ + { 57, 7, 12, 0, 0, }, /* 286 */ + { 57, 26, 12, 0, 0, }, /* 287 */ + { 57, 21, 12, 0, 0, }, /* 288 */ + { 57, 12, 3, 0, 0, }, /* 289 */ + { 57, 13, 12, 0, 0, }, /* 290 */ + { 57, 15, 12, 0, 0, }, /* 291 */ + { 57, 22, 12, 0, 0, }, /* 292 */ + { 57, 18, 12, 0, 0, }, /* 293 */ + { 57, 10, 5, 0, 0, }, /* 294 */ + { 38, 7, 12, 0, 0, }, /* 295 */ + { 38, 10, 12, 0, 0, }, /* 296 */ + { 38, 12, 3, 0, 0, }, /* 297 */ + { 38, 10, 5, 0, 0, }, /* 298 */ + { 38, 13, 12, 0, 0, }, /* 299 */ + { 38, 21, 12, 0, 0, }, /* 300 */ + { 38, 26, 12, 0, 0, }, /* 301 */ + { 16, 9, 12, 0, 7264, }, /* 302 */ + { 16, 7, 12, 0, 0, }, /* 303 */ + { 16, 6, 12, 0, 0, }, /* 304 */ + { 23, 7, 6, 0, 0, }, /* 305 */ + { 23, 7, 7, 0, 0, }, /* 306 */ + { 23, 7, 8, 0, 0, }, /* 307 */ + { 15, 7, 12, 0, 0, }, /* 308 */ + { 15, 12, 3, 0, 0, }, /* 309 */ + { 15, 21, 12, 0, 0, }, /* 310 */ + { 15, 15, 12, 0, 0, }, /* 311 */ + { 15, 26, 12, 0, 0, }, /* 312 */ + { 8, 7, 12, 0, 0, }, /* 313 */ + { 7, 17, 12, 0, 0, }, /* 314 */ + { 7, 7, 12, 0, 0, }, /* 315 */ + { 7, 21, 12, 0, 0, }, /* 316 */ + { 40, 29, 12, 0, 0, }, /* 317 */ + { 40, 7, 12, 0, 0, }, /* 318 */ + { 40, 22, 12, 0, 0, }, /* 319 */ + { 40, 18, 12, 0, 0, }, /* 320 */ + { 45, 7, 12, 0, 0, }, /* 321 */ + { 45, 14, 12, 0, 0, }, /* 322 */ + { 50, 7, 12, 0, 0, }, /* 323 */ + { 50, 12, 3, 0, 0, }, /* 324 */ + { 24, 7, 12, 0, 0, }, /* 325 */ + { 24, 12, 3, 0, 0, }, /* 326 */ + { 6, 7, 12, 0, 0, }, /* 327 */ + { 6, 12, 3, 0, 0, }, /* 328 */ + { 51, 7, 12, 0, 0, }, /* 329 */ + { 51, 12, 3, 0, 0, }, /* 330 */ + { 31, 7, 12, 0, 0, }, /* 331 */ + { 31, 12, 3, 0, 0, }, /* 332 */ + { 31, 10, 5, 0, 0, }, /* 333 */ + { 31, 21, 12, 0, 0, }, /* 334 */ + { 31, 6, 12, 0, 0, }, /* 335 */ + { 31, 23, 12, 0, 0, }, /* 336 */ + { 31, 13, 12, 0, 0, }, /* 337 */ + { 31, 15, 12, 0, 0, }, /* 338 */ + { 37, 21, 12, 0, 0, }, /* 339 */ + { 37, 17, 12, 0, 0, }, /* 340 */ + { 37, 12, 3, 0, 0, }, /* 341 */ + { 37, 1, 2, 0, 0, }, /* 342 */ + { 37, 13, 12, 0, 0, }, /* 343 */ + { 37, 7, 12, 0, 0, }, /* 344 */ + { 37, 6, 12, 0, 0, }, /* 345 */ + { 34, 7, 12, 0, 0, }, /* 346 */ + { 34, 12, 3, 0, 0, }, /* 347 */ + { 34, 10, 5, 0, 0, }, /* 348 */ + { 34, 26, 12, 0, 0, }, /* 349 */ + { 34, 21, 12, 0, 0, }, /* 350 */ + { 34, 13, 12, 0, 0, }, /* 351 */ + { 52, 7, 12, 0, 0, }, /* 352 */ + { 39, 7, 12, 0, 0, }, /* 353 */ + { 39, 10, 12, 0, 0, }, /* 354 */ + { 39, 10, 5, 0, 0, }, /* 355 */ + { 39, 13, 12, 0, 0, }, /* 356 */ + { 39, 15, 12, 0, 0, }, /* 357 */ + { 39, 26, 12, 0, 0, }, /* 358 */ + { 31, 26, 12, 0, 0, }, /* 359 */ + { 5, 7, 12, 0, 0, }, /* 360 */ + { 5, 12, 3, 0, 0, }, /* 361 */ + { 5, 10, 5, 0, 0, }, /* 362 */ + { 5, 21, 12, 0, 0, }, /* 363 */ + { 90, 7, 12, 0, 0, }, /* 364 */ + { 90, 10, 5, 0, 0, }, /* 365 */ + { 90, 12, 3, 0, 0, }, /* 366 */ + { 90, 10, 12, 0, 0, }, /* 367 */ + { 90, 13, 12, 0, 0, }, /* 368 */ + { 90, 21, 12, 0, 0, }, /* 369 */ + { 90, 6, 12, 0, 0, }, /* 370 */ + { 61, 12, 3, 0, 0, }, /* 371 */ + { 61, 10, 5, 0, 0, }, /* 372 */ + { 61, 7, 12, 0, 0, }, /* 373 */ + { 61, 13, 12, 0, 0, }, /* 374 */ + { 61, 21, 12, 0, 0, }, /* 375 */ + { 61, 26, 12, 0, 0, }, /* 376 */ + { 75, 12, 3, 0, 0, }, /* 377 */ + { 75, 10, 5, 0, 0, }, /* 378 */ + { 75, 7, 12, 0, 0, }, /* 379 */ + { 75, 13, 12, 0, 0, }, /* 380 */ + { 92, 7, 12, 0, 0, }, /* 381 */ + { 92, 12, 3, 0, 0, }, /* 382 */ + { 92, 10, 5, 0, 0, }, /* 383 */ + { 92, 21, 12, 0, 0, }, /* 384 */ + { 69, 7, 12, 0, 0, }, /* 385 */ + { 69, 10, 5, 0, 0, }, /* 386 */ + { 69, 12, 3, 0, 0, }, /* 387 */ + { 69, 21, 12, 0, 0, }, /* 388 */ + { 69, 13, 12, 0, 0, }, /* 389 */ + { 72, 13, 12, 0, 0, }, /* 390 */ + { 72, 7, 12, 0, 0, }, /* 391 */ + { 72, 6, 12, 0, 0, }, /* 392 */ + { 72, 21, 12, 0, 0, }, /* 393 */ + { 75, 21, 12, 0, 0, }, /* 394 */ + { 9, 10, 5, 0, 0, }, /* 395 */ + { 9, 7, 12, 0, 0, }, /* 396 */ + { 12, 5, 12, 0, 0, }, /* 397 */ + { 12, 6, 12, 0, 0, }, /* 398 */ + { 33, 5, 12, 0, 35332, }, /* 399 */ + { 33, 5, 12, 0, 3814, }, /* 400 */ + { 33, 9, 12, 63, 1, }, /* 401 */ + { 33, 5, 12, 63, -1, }, /* 402 */ + { 33, 5, 12, 63, -58, }, /* 403 */ + { 33, 9, 12, 0, -7615, }, /* 404 */ + { 19, 5, 12, 0, 8, }, /* 405 */ + { 19, 9, 12, 0, -8, }, /* 406 */ + { 19, 5, 12, 0, 74, }, /* 407 */ + { 19, 5, 12, 0, 86, }, /* 408 */ + { 19, 5, 12, 0, 100, }, /* 409 */ + { 19, 5, 12, 0, 128, }, /* 410 */ + { 19, 5, 12, 0, 112, }, /* 411 */ + { 19, 5, 12, 0, 126, }, /* 412 */ + { 19, 8, 12, 0, -8, }, /* 413 */ + { 19, 5, 12, 0, 9, }, /* 414 */ + { 19, 9, 12, 0, -74, }, /* 415 */ + { 19, 8, 12, 0, -9, }, /* 416 */ + { 19, 5, 12, 21, -7173, }, /* 417 */ + { 19, 9, 12, 0, -86, }, /* 418 */ + { 19, 9, 12, 0, -100, }, /* 419 */ + { 19, 9, 12, 0, -112, }, /* 420 */ + { 19, 9, 12, 0, -128, }, /* 421 */ + { 19, 9, 12, 0, -126, }, /* 422 */ + { 27, 1, 3, 0, 0, }, /* 423 */ + { 9, 27, 2, 0, 0, }, /* 424 */ + { 9, 28, 2, 0, 0, }, /* 425 */ + { 9, 2, 2, 0, 0, }, /* 426 */ + { 27, 11, 3, 0, 0, }, /* 427 */ + { 9, 9, 12, 0, 0, }, /* 428 */ + { 9, 5, 12, 0, 0, }, /* 429 */ + { 19, 9, 12, 67, -7517, }, /* 430 */ + { 33, 9, 12, 71, -8383, }, /* 431 */ + { 33, 9, 12, 75, -8262, }, /* 432 */ + { 33, 9, 12, 0, 28, }, /* 433 */ + { 33, 5, 12, 0, -28, }, /* 434 */ + { 33, 14, 12, 0, 16, }, /* 435 */ + { 33, 14, 12, 0, -16, }, /* 436 */ + { 33, 14, 12, 0, 0, }, /* 437 */ + { 9, 26, 12, 0, 26, }, /* 438 */ + { 9, 26, 12, 0, -26, }, /* 439 */ + { 4, 26, 12, 0, 0, }, /* 440 */ + { 17, 9, 12, 0, 48, }, /* 441 */ + { 17, 5, 12, 0, -48, }, /* 442 */ + { 33, 9, 12, 0, -10743, }, /* 443 */ + { 33, 9, 12, 0, -3814, }, /* 444 */ + { 33, 9, 12, 0, -10727, }, /* 445 */ + { 33, 5, 12, 0, -10795, }, /* 446 */ + { 33, 5, 12, 0, -10792, }, /* 447 */ + { 33, 9, 12, 0, -10780, }, /* 448 */ + { 33, 9, 12, 0, -10749, }, /* 449 */ + { 33, 9, 12, 0, -10783, }, /* 450 */ + { 33, 9, 12, 0, -10782, }, /* 451 */ + { 33, 9, 12, 0, -10815, }, /* 452 */ + { 10, 5, 12, 0, 0, }, /* 453 */ + { 10, 26, 12, 0, 0, }, /* 454 */ + { 10, 12, 3, 0, 0, }, /* 455 */ + { 10, 21, 12, 0, 0, }, /* 456 */ + { 10, 15, 12, 0, 0, }, /* 457 */ + { 16, 5, 12, 0, -7264, }, /* 458 */ + { 58, 7, 12, 0, 0, }, /* 459 */ + { 58, 6, 12, 0, 0, }, /* 460 */ + { 58, 21, 12, 0, 0, }, /* 461 */ + { 58, 12, 3, 0, 0, }, /* 462 */ + { 22, 26, 12, 0, 0, }, /* 463 */ + { 22, 6, 12, 0, 0, }, /* 464 */ + { 22, 14, 12, 0, 0, }, /* 465 */ + { 23, 10, 3, 0, 0, }, /* 466 */ + { 26, 7, 12, 0, 0, }, /* 467 */ + { 26, 6, 12, 0, 0, }, /* 468 */ + { 29, 7, 12, 0, 0, }, /* 469 */ + { 29, 6, 12, 0, 0, }, /* 470 */ + { 3, 7, 12, 0, 0, }, /* 471 */ + { 23, 7, 12, 0, 0, }, /* 472 */ + { 23, 26, 12, 0, 0, }, /* 473 */ + { 29, 26, 12, 0, 0, }, /* 474 */ + { 22, 7, 12, 0, 0, }, /* 475 */ + { 60, 7, 12, 0, 0, }, /* 476 */ + { 60, 6, 12, 0, 0, }, /* 477 */ + { 60, 26, 12, 0, 0, }, /* 478 */ + { 85, 7, 12, 0, 0, }, /* 479 */ + { 85, 6, 12, 0, 0, }, /* 480 */ + { 85, 21, 12, 0, 0, }, /* 481 */ + { 76, 7, 12, 0, 0, }, /* 482 */ + { 76, 6, 12, 0, 0, }, /* 483 */ + { 76, 21, 12, 0, 0, }, /* 484 */ + { 76, 13, 12, 0, 0, }, /* 485 */ + { 12, 7, 12, 0, 0, }, /* 486 */ + { 12, 21, 12, 0, 0, }, /* 487 */ + { 78, 7, 12, 0, 0, }, /* 488 */ + { 78, 14, 12, 0, 0, }, /* 489 */ + { 78, 12, 3, 0, 0, }, /* 490 */ + { 78, 21, 12, 0, 0, }, /* 491 */ + { 33, 9, 12, 0, -35332, }, /* 492 */ + { 33, 9, 12, 0, -42280, }, /* 493 */ + { 33, 9, 12, 0, -42308, }, /* 494 */ + { 48, 7, 12, 0, 0, }, /* 495 */ + { 48, 12, 3, 0, 0, }, /* 496 */ + { 48, 10, 5, 0, 0, }, /* 497 */ + { 48, 26, 12, 0, 0, }, /* 498 */ + { 64, 7, 12, 0, 0, }, /* 499 */ + { 64, 21, 12, 0, 0, }, /* 500 */ + { 74, 10, 5, 0, 0, }, /* 501 */ + { 74, 7, 12, 0, 0, }, /* 502 */ + { 74, 12, 3, 0, 0, }, /* 503 */ + { 74, 21, 12, 0, 0, }, /* 504 */ + { 74, 13, 12, 0, 0, }, /* 505 */ + { 68, 13, 12, 0, 0, }, /* 506 */ + { 68, 7, 12, 0, 0, }, /* 507 */ + { 68, 12, 3, 0, 0, }, /* 508 */ + { 68, 21, 12, 0, 0, }, /* 509 */ + { 73, 7, 12, 0, 0, }, /* 510 */ + { 73, 12, 3, 0, 0, }, /* 511 */ + { 73, 10, 5, 0, 0, }, /* 512 */ + { 73, 21, 12, 0, 0, }, /* 513 */ + { 83, 12, 3, 0, 0, }, /* 514 */ + { 83, 10, 5, 0, 0, }, /* 515 */ + { 83, 7, 12, 0, 0, }, /* 516 */ + { 83, 21, 12, 0, 0, }, /* 517 */ + { 83, 13, 12, 0, 0, }, /* 518 */ + { 67, 7, 12, 0, 0, }, /* 519 */ + { 67, 12, 3, 0, 0, }, /* 520 */ + { 67, 10, 5, 0, 0, }, /* 521 */ + { 67, 13, 12, 0, 0, }, /* 522 */ + { 67, 21, 12, 0, 0, }, /* 523 */ + { 38, 6, 12, 0, 0, }, /* 524 */ + { 91, 7, 12, 0, 0, }, /* 525 */ + { 91, 12, 3, 0, 0, }, /* 526 */ + { 91, 6, 12, 0, 0, }, /* 527 */ + { 91, 21, 12, 0, 0, }, /* 528 */ + { 86, 7, 12, 0, 0, }, /* 529 */ + { 86, 10, 5, 0, 0, }, /* 530 */ + { 86, 12, 3, 0, 0, }, /* 531 */ + { 86, 21, 12, 0, 0, }, /* 532 */ + { 86, 6, 12, 0, 0, }, /* 533 */ + { 86, 13, 12, 0, 0, }, /* 534 */ + { 23, 7, 9, 0, 0, }, /* 535 */ + { 23, 7, 10, 0, 0, }, /* 536 */ + { 9, 4, 2, 0, 0, }, /* 537 */ + { 9, 3, 12, 0, 0, }, /* 538 */ + { 25, 25, 12, 0, 0, }, /* 539 */ + { 0, 24, 12, 0, 0, }, /* 540 */ + { 9, 6, 3, 0, 0, }, /* 541 */ + { 35, 7, 12, 0, 0, }, /* 542 */ + { 19, 14, 12, 0, 0, }, /* 543 */ + { 19, 15, 12, 0, 0, }, /* 544 */ + { 19, 26, 12, 0, 0, }, /* 545 */ + { 70, 7, 12, 0, 0, }, /* 546 */ + { 66, 7, 12, 0, 0, }, /* 547 */ + { 41, 7, 12, 0, 0, }, /* 548 */ + { 41, 15, 12, 0, 0, }, /* 549 */ + { 18, 7, 12, 0, 0, }, /* 550 */ + { 18, 14, 12, 0, 0, }, /* 551 */ + { 59, 7, 12, 0, 0, }, /* 552 */ + { 59, 21, 12, 0, 0, }, /* 553 */ + { 42, 7, 12, 0, 0, }, /* 554 */ + { 42, 21, 12, 0, 0, }, /* 555 */ + { 42, 14, 12, 0, 0, }, /* 556 */ + { 13, 9, 12, 0, 40, }, /* 557 */ + { 13, 5, 12, 0, -40, }, /* 558 */ + { 46, 7, 12, 0, 0, }, /* 559 */ + { 44, 7, 12, 0, 0, }, /* 560 */ + { 44, 13, 12, 0, 0, }, /* 561 */ + { 11, 7, 12, 0, 0, }, /* 562 */ + { 80, 7, 12, 0, 0, }, /* 563 */ + { 80, 21, 12, 0, 0, }, /* 564 */ + { 80, 15, 12, 0, 0, }, /* 565 */ + { 65, 7, 12, 0, 0, }, /* 566 */ + { 65, 15, 12, 0, 0, }, /* 567 */ + { 65, 21, 12, 0, 0, }, /* 568 */ + { 71, 7, 12, 0, 0, }, /* 569 */ + { 71, 21, 12, 0, 0, }, /* 570 */ + { 97, 7, 12, 0, 0, }, /* 571 */ + { 96, 7, 12, 0, 0, }, /* 572 */ + { 30, 7, 12, 0, 0, }, /* 573 */ + { 30, 12, 3, 0, 0, }, /* 574 */ + { 30, 15, 12, 0, 0, }, /* 575 */ + { 30, 21, 12, 0, 0, }, /* 576 */ + { 87, 7, 12, 0, 0, }, /* 577 */ + { 87, 15, 12, 0, 0, }, /* 578 */ + { 87, 21, 12, 0, 0, }, /* 579 */ + { 77, 7, 12, 0, 0, }, /* 580 */ + { 77, 21, 12, 0, 0, }, /* 581 */ + { 82, 7, 12, 0, 0, }, /* 582 */ + { 82, 15, 12, 0, 0, }, /* 583 */ + { 81, 7, 12, 0, 0, }, /* 584 */ + { 81, 15, 12, 0, 0, }, /* 585 */ + { 88, 7, 12, 0, 0, }, /* 586 */ + { 0, 15, 12, 0, 0, }, /* 587 */ + { 93, 10, 5, 0, 0, }, /* 588 */ + { 93, 12, 3, 0, 0, }, /* 589 */ + { 93, 7, 12, 0, 0, }, /* 590 */ + { 93, 21, 12, 0, 0, }, /* 591 */ + { 93, 15, 12, 0, 0, }, /* 592 */ + { 93, 13, 12, 0, 0, }, /* 593 */ + { 84, 12, 3, 0, 0, }, /* 594 */ + { 84, 10, 5, 0, 0, }, /* 595 */ + { 84, 7, 12, 0, 0, }, /* 596 */ + { 84, 21, 12, 0, 0, }, /* 597 */ + { 84, 1, 2, 0, 0, }, /* 598 */ + { 100, 7, 12, 0, 0, }, /* 599 */ + { 100, 13, 12, 0, 0, }, /* 600 */ + { 95, 12, 3, 0, 0, }, /* 601 */ + { 95, 7, 12, 0, 0, }, /* 602 */ + { 95, 10, 5, 0, 0, }, /* 603 */ + { 95, 13, 12, 0, 0, }, /* 604 */ + { 95, 21, 12, 0, 0, }, /* 605 */ + { 99, 12, 3, 0, 0, }, /* 606 */ + { 99, 10, 5, 0, 0, }, /* 607 */ + { 99, 7, 12, 0, 0, }, /* 608 */ + { 99, 21, 12, 0, 0, }, /* 609 */ + { 99, 13, 12, 0, 0, }, /* 610 */ + { 101, 7, 12, 0, 0, }, /* 611 */ + { 101, 12, 3, 0, 0, }, /* 612 */ + { 101, 10, 5, 0, 0, }, /* 613 */ + { 101, 13, 12, 0, 0, }, /* 614 */ + { 62, 7, 12, 0, 0, }, /* 615 */ + { 62, 14, 12, 0, 0, }, /* 616 */ + { 62, 21, 12, 0, 0, }, /* 617 */ + { 79, 7, 12, 0, 0, }, /* 618 */ + { 98, 7, 12, 0, 0, }, /* 619 */ + { 98, 10, 5, 0, 0, }, /* 620 */ + { 98, 12, 3, 0, 0, }, /* 621 */ + { 98, 6, 12, 0, 0, }, /* 622 */ + { 9, 10, 3, 0, 0, }, /* 623 */ + { 19, 12, 3, 0, 0, }, /* 624 */ + { 9, 26, 11, 0, 0, }, /* 625 */ + { 26, 26, 12, 0, 0, }, /* 626 */ +}; + +const pcre_uint8 PRIV(ucd_stage1)[] = { /* 8704 bytes */ + 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, /* U+0000 */ + 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, /* U+0800 */ + 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 41, 41, 42, 43, 44, 45, /* U+1000 */ + 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, /* U+1800 */ + 62, 63, 64, 65, 66, 66, 67, 68, 69, 70, 71, 72, 73, 71, 74, 75, /* U+2000 */ + 76, 76, 66, 77, 66, 66, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, /* U+2800 */ + 88, 89, 90, 91, 92, 93, 94, 71, 95, 95, 95, 95, 95, 95, 95, 95, /* U+3000 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+3800 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+4000 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 96, 95, 95, 95, 95, /* U+4800 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+5000 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+5800 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+6000 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+6800 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+7000 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+7800 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+8000 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+8800 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+9000 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 97, /* U+9800 */ + 98, 99, 99, 99, 99, 99, 99, 99, 99,100,101,101,102,103,104,105, /* U+A000 */ +106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,114, /* U+A800 */ +115,116,117,118,119,120,114,115,116,117,118,119,120,114,115,116, /* U+B000 */ +117,118,119,120,114,115,116,117,118,119,120,114,115,116,117,118, /* U+B800 */ +119,120,114,115,116,117,118,119,120,114,115,116,117,118,119,120, /* U+C000 */ +114,115,116,117,118,119,120,114,115,116,117,118,119,120,114,115, /* U+C800 */ +116,117,118,119,120,114,115,116,117,118,119,120,114,115,116,121, /* U+D000 */ +122,122,122,122,122,122,122,122,122,122,122,122,122,122,122,122, /* U+D800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+E000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+E800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F000 */ +123,123, 95, 95,124,125,126,127,128,128,129,130,131,132,133,134, /* U+F800 */ +135,136,137,138, 79,139,140,141,142,143, 79, 79, 79, 79, 79, 79, /* U+10000 */ +144, 79,145,146,147, 79,148, 79,149, 79, 79, 79,150, 79, 79, 79, /* U+10800 */ +151,152,153,154, 79, 79, 79, 79, 79, 79, 79, 79, 79,155, 79, 79, /* U+11000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+11800 */ +156,156,156,156,156,156,157, 79,158, 79, 79, 79, 79, 79, 79, 79, /* U+12000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+12800 */ +159,159,159,159,159,159,159,159,160, 79, 79, 79, 79, 79, 79, 79, /* U+13000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+13800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+14000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+14800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+15000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+15800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+16000 */ +161,161,161,161,162, 79, 79, 79, 79, 79, 79, 79, 79, 79,163,164, /* U+16800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+17000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+17800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+18000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+18800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+19000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+19800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+1A000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+1A800 */ +165, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+1B000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+1B800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+1C000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+1C800 */ + 71,166,167,168,169, 79,170, 79,171,172,173,174,175,176,177,178, /* U+1D000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+1D800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+1E000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79,179,180, 79, 79, /* U+1E800 */ +181,182,183,184,185, 79,186,187,188,189,190,191,192,193,194, 79, /* U+1F000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+1F800 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+20000 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+20800 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+21000 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+21800 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+22000 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+22800 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+23000 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+23800 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+24000 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+24800 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+25000 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+25800 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+26000 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+26800 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+27000 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+27800 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+28000 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+28800 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+29000 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+29800 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95,195, 95, 95, /* U+2A000 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+2A800 */ + 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95,196, 95, /* U+2B000 */ +197, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+2B800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+2C000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+2C800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+2D000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+2D800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+2E000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+2E800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+2F000 */ + 95, 95, 95, 95,197, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+2F800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+30000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+30800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+31000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+31800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+32000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+32800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+33000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+33800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+34000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+34800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+35000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+35800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+36000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+36800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+37000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+37800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+38000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+38800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+39000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+39800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+3A000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+3A800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+3B000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+3B800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+3C000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+3C800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+3D000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+3D800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+3E000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+3E800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+3F000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+3F800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+40000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+40800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+41000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+41800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+42000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+42800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+43000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+43800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+44000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+44800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+45000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+45800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+46000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+46800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+47000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+47800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+48000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+48800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+49000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+49800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+4A000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+4A800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+4B000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+4B800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+4C000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+4C800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+4D000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+4D800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+4E000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+4E800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+4F000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+4F800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+50000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+50800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+51000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+51800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+52000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+52800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+53000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+53800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+54000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+54800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+55000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+55800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+56000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+56800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+57000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+57800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+58000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+58800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+59000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+59800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+5A000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+5A800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+5B000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+5B800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+5C000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+5C800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+5D000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+5D800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+5E000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+5E800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+5F000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+5F800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+60000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+60800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+61000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+61800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+62000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+62800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+63000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+63800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+64000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+64800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+65000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+65800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+66000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+66800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+67000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+67800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+68000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+68800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+69000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+69800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+6A000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+6A800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+6B000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+6B800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+6C000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+6C800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+6D000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+6D800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+6E000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+6E800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+6F000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+6F800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+70000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+70800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+71000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+71800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+72000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+72800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+73000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+73800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+74000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+74800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+75000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+75800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+76000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+76800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+77000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+77800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+78000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+78800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+79000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+79800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+7A000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+7A800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+7B000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+7B800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+7C000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+7C800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+7D000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+7D800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+7E000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+7E800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+7F000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+7F800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+80000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+80800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+81000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+81800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+82000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+82800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+83000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+83800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+84000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+84800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+85000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+85800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+86000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+86800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+87000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+87800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+88000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+88800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+89000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+89800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+8A000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+8A800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+8B000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+8B800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+8C000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+8C800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+8D000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+8D800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+8E000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+8E800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+8F000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+8F800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+90000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+90800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+91000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+91800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+92000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+92800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+93000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+93800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+94000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+94800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+95000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+95800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+96000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+96800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+97000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+97800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+98000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+98800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+99000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+99800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+9A000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+9A800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+9B000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+9B800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+9C000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+9C800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+9D000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+9D800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+9E000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+9E800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+9F000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+9F800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+A0000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+A0800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+A1000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+A1800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+A2000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+A2800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+A3000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+A3800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+A4000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+A4800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+A5000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+A5800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+A6000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+A6800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+A7000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+A7800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+A8000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+A8800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+A9000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+A9800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+AA000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+AA800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+AB000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+AB800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+AC000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+AC800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+AD000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+AD800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+AE000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+AE800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+AF000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+AF800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+B0000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+B0800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+B1000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+B1800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+B2000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+B2800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+B3000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+B3800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+B4000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+B4800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+B5000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+B5800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+B6000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+B6800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+B7000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+B7800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+B8000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+B8800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+B9000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+B9800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+BA000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+BA800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+BB000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+BB800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+BC000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+BC800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+BD000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+BD800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+BE000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+BE800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+BF000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+BF800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+C0000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+C0800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+C1000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+C1800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+C2000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+C2800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+C3000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+C3800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+C4000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+C4800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+C5000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+C5800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+C6000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+C6800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+C7000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+C7800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+C8000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+C8800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+C9000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+C9800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+CA000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+CA800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+CB000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+CB800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+CC000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+CC800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+CD000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+CD800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+CE000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+CE800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+CF000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+CF800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+D0000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+D0800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+D1000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+D1800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+D2000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+D2800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+D3000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+D3800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+D4000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+D4800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+D5000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+D5800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+D6000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+D6800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+D7000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+D7800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+D8000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+D8800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+D9000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+D9800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+DA000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+DA800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+DB000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+DB800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+DC000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+DC800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+DD000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+DD800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+DE000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+DE800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+DF000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+DF800 */ +198,199,200,201,199,199,199,199,199,199,199,199,199,199,199,199, /* U+E0000 */ +199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, /* U+E0800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+E1000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+E1800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+E2000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+E2800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+E3000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+E3800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+E4000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+E4800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+E5000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+E5800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+E6000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+E6800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+E7000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+E7800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+E8000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+E8800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+E9000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+E9800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+EA000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+EA800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+EB000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+EB800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+EC000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+EC800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+ED000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+ED800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+EE000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+EE800 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+EF000 */ + 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, 79, /* U+EF800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F0000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F0800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F1000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F1800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F2000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F2800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F3000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F3800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F4000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F4800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F5000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F5800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F6000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F6800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F7000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F7800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F8000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F8800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F9000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F9800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+FA000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+FA800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+FB000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+FB800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+FC000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+FC800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+FD000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+FD800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+FE000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+FE800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+FF000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,202, /* U+FF800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+100000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+100800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+101000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+101800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+102000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+102800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+103000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+103800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+104000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+104800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+105000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+105800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+106000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+106800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+107000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+107800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+108000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+108800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+109000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+109800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+10A000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+10A800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+10B000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+10B800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+10C000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+10C800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+10D000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+10D800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+10E000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+10E800 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+10F000 */ +123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,202, /* U+10F800 */ +}; + +const pcre_uint16 PRIV(ucd_stage2)[] = { /* 51968 bytes, block = 128 */ +/* block 0 */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 2, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 3, 4, 4, 4, 5, 4, 4, 4, 6, 7, 4, 8, 4, 9, 4, 4, + 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 4, 4, 8, 8, 8, 4, + 4, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 12, 11, 11, 11, 11, + 11, 11, 11, 13, 11, 11, 11, 11, 11, 11, 11, 6, 4, 7, 14, 15, + 14, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 17, 16, 16, 16, 16, + 16, 16, 16, 18, 16, 16, 16, 16, 16, 16, 16, 6, 8, 7, 8, 0, + +/* block 1 */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 3, 4, 5, 5, 5, 5, 19, 4, 14, 19, 20, 21, 8, 22, 19, 14, + 19, 8, 23, 23, 14, 24, 4, 4, 14, 23, 20, 25, 23, 23, 23, 4, + 11, 11, 11, 11, 11, 26, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, + 11, 11, 11, 11, 11, 11, 11, 8, 11, 11, 11, 11, 11, 11, 11, 27, + 16, 16, 16, 16, 16, 28, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, + 16, 16, 16, 16, 16, 16, 16, 8, 16, 16, 16, 16, 16, 16, 16, 29, + +/* block 2 */ + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 32, 33, 30, 31, 30, 31, 30, 31, 33, 30, 31, 30, 31, 30, 31, 30, + 31, 30, 31, 30, 31, 30, 31, 30, 31, 33, 30, 31, 30, 31, 30, 31, + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 30, 31, 30, 31, 30, 31, 30, 31, 34, 30, 31, 30, 31, 30, 31, 35, + +/* block 3 */ + 36, 37, 30, 31, 30, 31, 38, 30, 31, 39, 39, 30, 31, 33, 40, 41, + 42, 30, 31, 39, 43, 44, 45, 46, 30, 31, 47, 33, 45, 48, 49, 50, + 30, 31, 30, 31, 30, 31, 51, 30, 31, 51, 33, 33, 30, 31, 51, 30, + 31, 52, 52, 30, 31, 30, 31, 53, 30, 31, 33, 20, 30, 31, 33, 54, + 20, 20, 20, 20, 55, 56, 57, 58, 59, 60, 61, 62, 63, 30, 31, 30, + 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 64, 30, 31, + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 33, 65, 66, 67, 30, 31, 68, 69, 30, 31, 30, 31, 30, 31, 30, 31, + +/* block 4 */ + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 70, 33, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 30, 31, 30, 31, 33, 33, 33, 33, 33, 33, 71, 30, 31, 72, 73, 74, + 74, 30, 31, 75, 76, 77, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 78, 79, 80, 81, 82, 33, 83, 83, 33, 84, 33, 85, 33, 33, 33, 33, + 83, 33, 33, 86, 33, 87, 88, 33, 89, 90, 33, 91, 33, 33, 33, 90, + 33, 92, 93, 33, 33, 94, 33, 33, 33, 33, 33, 33, 33, 95, 33, 33, + +/* block 5 */ + 96, 33, 33, 96, 33, 33, 33, 33, 96, 97, 98, 98, 99, 33, 33, 33, + 33, 33,100, 33, 20, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, + 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, +101,101,101,101,101,101,101,101,101,102,102,102,102,102,102,102, +102,102, 14, 14, 14, 14,102,102,102,102,102,102,102,102,102,102, +102,102, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, +101,101,101,101,101, 14, 14, 14, 14, 14,103,103,102, 14,102, 14, + 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, + +/* block 6 */ +104,104,104,104,104,104,104,104,104,104,104,104,104,104,104,104, +104,104,104,104,104,104,104,104,104,104,104,104,104,104,104,104, +104,104,104,104,104,104,104,104,104,104,104,104,104,104,104,104, +104,104,104,104,104,104,104,104,104,104,104,104,104,104,104,104, +104,104,104,104,104,105,104,104,104,104,104,104,104,104,104,104, +104,104,104,104,104,104,104,104,104,104,104,104,104,104,104,104, +104,104,104,104,104,104,104,104,104,104,104,104,104,104,104,104, +106,107,106,107,102,108,106,107,109,109,110,111,111,111, 4,109, + +/* block 7 */ +109,109,109,109,108, 14,112, 4,113,113,113,109,114,109,115,115, +116,117,118,117,117,119,117,117,120,121,122,117,123,117,117,117, +124,125,109,126,117,117,127,117,117,128,117,117,129,130,130,130, +116,131,132,131,131,133,131,131,134,135,136,131,137,131,131,131, +138,139,140,141,131,131,142,131,131,143,131,131,144,145,145,146, +147,148,149,149,149,150,151,152,106,107,106,107,106,107,106,107, +106,107,153,154,153,154,153,154,153,154,153,154,153,154,153,154, +155,156,157,116,158,159,160,106,107,161,106,107,116,162,162,162, + +/* block 8 */ +163,163,163,163,163,163,163,163,163,163,163,163,163,163,163,163, +164,164,164,164,164,164,164,164,164,164,164,164,164,164,164,164, +164,164,164,164,164,164,164,164,164,164,164,164,164,164,164,164, +165,165,165,165,165,165,165,165,165,165,165,165,165,165,165,165, +165,165,165,165,165,165,165,165,165,165,165,165,165,165,165,165, +166,166,166,166,166,166,166,166,166,166,166,166,166,166,166,166, +167,168,167,168,167,168,167,168,167,168,167,168,167,168,167,168, +167,168,167,168,167,168,167,168,167,168,167,168,167,168,167,168, + +/* block 9 */ +167,168,169,170,170,104,104,170,171,171,167,168,167,168,167,168, +167,168,167,168,167,168,167,168,167,168,167,168,167,168,167,168, +167,168,167,168,167,168,167,168,167,168,167,168,167,168,167,168, +167,168,167,168,167,168,167,168,167,168,167,168,167,168,167,168, +172,167,168,167,168,167,168,167,168,167,168,167,168,167,168,173, +167,168,167,168,167,168,167,168,167,168,167,168,167,168,167,168, +167,168,167,168,167,168,167,168,167,168,167,168,167,168,167,168, +167,168,167,168,167,168,167,168,167,168,167,168,167,168,167,168, + +/* block 10 */ +167,168,167,168,167,168,167,168,167,168,167,168,167,168,167,168, +167,168,167,168,167,168,167,168,167,168,167,168,167,168,167,168, +167,168,167,168,167,168,167,168,109,109,109,109,109,109,109,109, +109,174,174,174,174,174,174,174,174,174,174,174,174,174,174,174, +174,174,174,174,174,174,174,174,174,174,174,174,174,174,174,174, +174,174,174,174,174,174,174,109,109,175,176,176,176,176,176,176, +109,177,177,177,177,177,177,177,177,177,177,177,177,177,177,177, +177,177,177,177,177,177,177,177,177,177,177,177,177,177,177,177, + +/* block 11 */ +177,177,177,177,177,177,177,178,109, 4,179,109,109,109,109,180, +109,181,181,181,181,181,181,181,181,181,181,181,181,181,181,181, +181,181,181,181,181,181,181,181,181,181,181,181,181,181,181,181, +181,181,181,181,181,181,181,181,181,181,181,181,181,181,182,181, +183,181,181,183,181,181,183,181,109,109,109,109,109,109,109,109, +184,184,184,184,184,184,184,184,184,184,184,184,184,184,184,184, +184,184,184,184,184,184,184,184,184,184,184,109,109,109,109,109, +184,184,184,183,183,109,109,109,109,109,109,109,109,109,109,109, + +/* block 12 */ +185,185,185,185,185,109,186,186,186,187,187,188, 4,187,189,189, +190,190,190,190,190,190,190,190,190,190,190, 4,185,109,187, 4, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +102,191,191,191,191,191,191,191,191,191,191,104,104,104,104,104, +104,104,104,104,104,104,190,190,190,190,190,190,190,190,190,190, + 10, 10, 10, 10, 10, 10, 10, 10, 10, 10,187,187,187,187,191,191, +104,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, + +/* block 13 */ +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,187,191,190,190,190,190,190,190,190, 22,189,190, +190,190,190,190,190,192,192,190,190,189,190,190,190,190,191,191, +193,193,193,193,193,193,193,193,193,193,191,191,191,189,189,191, + +/* block 14 */ +194,194,194,194,194,194,194,194,194,194,194,194,194,194,109,195, +196,197,196,196,196,196,196,196,196,196,196,196,196,196,196,196, +196,196,196,196,196,196,196,196,196,196,196,196,196,196,196,196, +197,197,197,197,197,197,197,197,197,197,197,197,197,197,197,197, +197,197,197,197,197,197,197,197,197,197,197,109,109,196,196,196, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, + +/* block 15 */ +198,198,198,198,198,198,198,198,198,198,198,198,198,198,198,198, +198,198,198,198,198,198,198,198,198,198,198,198,198,198,198,198, +198,198,198,198,198,198,199,199,199,199,199,199,199,199,199,199, +199,198,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +200,200,200,200,200,200,200,200,200,200,201,201,201,201,201,201, +201,201,201,201,201,201,201,201,201,201,201,201,201,201,201,201, +201,201,201,201,201,201,201,201,201,201,201,202,202,202,202,202, +202,202,202,202,203,203,204,205,205,205,203,109,109,109,109,109, + +/* block 16 */ +206,206,206,206,206,206,206,206,206,206,206,206,206,206,206,206, +206,206,206,206,206,206,207,207,207,207,208,207,207,207,207,207, +207,207,207,207,208,207,207,207,208,207,207,207,207,207,109,109, +209,209,209,209,209,209,209,209,209,209,209,209,209,209,209,109, +210,210,210,210,210,210,210,210,210,210,210,210,210,210,210,210, +210,210,210,210,210,210,210,210,210,211,211,211,109,109,212,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 17 */ +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +191,109,191,191,191,191,191,191,191,191,191,191,191,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,190,190,190,190,190,190,190,190,190,190,190,190, +190,190,190,190,190,190,190,190,190,190,190,190,190,190,190,109, + +/* block 18 */ +213,213,213,214,215,215,215,215,215,215,215,215,215,215,215,215, +215,215,215,215,215,215,215,215,215,215,215,215,215,215,215,215, +215,215,215,215,215,215,215,215,215,215,215,215,215,215,215,215, +215,215,215,215,215,215,215,215,215,215,213,214,213,215,214,214, +214,213,213,213,213,213,213,213,213,214,214,214,214,213,214,214, +215,104,104,213,213,213,213,213,215,215,215,215,215,215,215,215, +215,215,213,213, 4, 4,216,216,216,216,216,216,216,216,216,216, +217,218,215,215,215,215,215,215,109,215,215,215,215,215,215,215, + +/* block 19 */ +109,219,220,220,109,221,221,221,221,221,221,221,221,109,109,221, +221,109,109,221,221,221,221,221,221,221,221,221,221,221,221,221, +221,221,221,221,221,221,221,221,221,109,221,221,221,221,221,221, +221,109,221,109,109,109,221,221,221,221,109,109,219,221,222,220, +220,219,219,219,219,109,109,220,220,109,109,220,220,219,221,109, +109,109,109,109,109,109,109,222,109,109,109,109,221,221,109,221, +221,221,219,219,109,109,223,223,223,223,223,223,223,223,223,223, +221,221,224,224,225,225,225,225,225,225,226,224,109,109,109,109, + +/* block 20 */ +109,227,227,228,109,229,229,229,229,229,229,109,109,109,109,229, +229,109,109,229,229,229,229,229,229,229,229,229,229,229,229,229, +229,229,229,229,229,229,229,229,229,109,229,229,229,229,229,229, +229,109,229,229,109,229,229,109,229,229,109,109,227,109,228,228, +228,227,227,109,109,109,109,227,227,109,109,227,227,227,109,109, +109,227,109,109,109,109,109,109,109,229,229,229,229,109,229,109, +109,109,109,109,109,109,230,230,230,230,230,230,230,230,230,230, +227,227,229,229,229,227,109,109,109,109,109,109,109,109,109,109, + +/* block 21 */ +109,231,231,232,109,233,233,233,233,233,233,233,233,233,109,233, +233,233,109,233,233,233,233,233,233,233,233,233,233,233,233,233, +233,233,233,233,233,233,233,233,233,109,233,233,233,233,233,233, +233,109,233,233,109,233,233,233,233,233,109,109,231,233,232,232, +232,231,231,231,231,231,109,231,231,232,109,232,232,231,109,109, +233,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +233,233,231,231,109,109,234,234,234,234,234,234,234,234,234,234, +235,236,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 22 */ +109,237,238,238,109,239,239,239,239,239,239,239,239,109,109,239, +239,109,109,239,239,239,239,239,239,239,239,239,239,239,239,239, +239,239,239,239,239,239,239,239,239,109,239,239,239,239,239,239, +239,109,239,239,109,239,239,239,239,239,109,109,237,239,240,237, +238,237,237,237,237,109,109,238,238,109,109,238,238,237,109,109, +109,109,109,109,109,109,237,240,109,109,109,109,239,239,109,239, +239,239,237,237,109,109,241,241,241,241,241,241,241,241,241,241, +242,239,243,243,243,243,243,243,109,109,109,109,109,109,109,109, + +/* block 23 */ +109,109,244,245,109,245,245,245,245,245,245,109,109,109,245,245, +245,109,245,245,245,245,109,109,109,245,245,109,245,109,245,245, +109,109,109,245,245,109,109,109,245,245,245,109,109,109,245,245, +245,245,245,245,245,245,245,245,245,245,109,109,109,109,246,247, +244,247,247,109,109,109,247,247,247,109,247,247,247,244,109,109, +245,109,109,109,109,109,109,246,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,248,248,248,248,248,248,248,248,248,248, +249,249,249,250,250,250,250,250,250,251,250,109,109,109,109,109, + +/* block 24 */ +109,252,252,252,109,253,253,253,253,253,253,253,253,109,253,253, +253,109,253,253,253,253,253,253,253,253,253,253,253,253,253,253, +253,253,253,253,253,253,253,253,253,109,253,253,253,253,253,253, +253,253,253,253,109,253,253,253,253,253,109,109,109,253,254,254, +254,252,252,252,252,109,254,254,254,109,254,254,254,254,109,109, +109,109,109,109,109,254,254,109,253,253,109,109,109,109,109,109, +253,253,254,254,109,109,255,255,255,255,255,255,255,255,255,255, +109,109,109,109,109,109,109,109,256,256,256,256,256,256,256,257, + +/* block 25 */ +109,109,258,258,109,259,259,259,259,259,259,259,259,109,259,259, +259,109,259,259,259,259,259,259,259,259,259,259,259,259,259,259, +259,259,259,259,259,259,259,259,259,109,259,259,259,259,259,259, +259,259,259,259,109,259,259,259,259,259,109,109,260,259,258,260, +258,258,261,258,258,109,260,258,258,109,258,258,260,260,109,109, +109,109,109,109,109,261,261,109,109,109,109,109,109,109,259,109, +259,259,260,260,109,109,262,262,262,262,262,262,262,262,262,262, +109,259,259,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 26 */ +109,109,263,263,109,264,264,264,264,264,264,264,264,109,264,264, +264,109,264,264,264,264,264,264,264,264,264,264,264,264,264,264, +264,264,264,264,264,264,264,264,264,264,264,264,264,264,264,264, +264,264,264,264,264,264,264,264,264,264,264,109,109,264,265,263, +263,266,266,266,266,109,263,263,263,109,263,263,263,266,264,109, +109,109,109,109,109,109,109,265,109,109,109,109,109,109,109,109, +264,264,266,266,109,109,267,267,267,267,267,267,267,267,267,267, +268,268,268,268,268,268,109,109,109,269,264,264,264,264,264,264, + +/* block 27 */ +109,109,270,270,109,271,271,271,271,271,271,271,271,271,271,271, +271,271,271,271,271,271,271,109,109,109,271,271,271,271,271,271, +271,271,271,271,271,271,271,271,271,271,271,271,271,271,271,271, +271,271,109,271,271,271,271,271,271,271,271,271,109,271,109,109, +271,271,271,271,271,271,271,109,109,109,272,109,109,109,109,273, +270,270,272,272,272,109,272,109,270,270,270,270,270,270,270,273, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,270,270,274,109,109,109,109,109,109,109,109,109,109,109, + +/* block 28 */ +109,275,275,275,275,275,275,275,275,275,275,275,275,275,275,275, +275,275,275,275,275,275,275,275,275,275,275,275,275,275,275,275, +275,275,275,275,275,275,275,275,275,275,275,275,275,275,275,275, +275,276,275,277,276,276,276,276,276,276,276,109,109,109,109, 5, +275,275,275,275,275,275,278,276,276,276,276,276,276,276,276,279, +280,280,280,280,280,280,280,280,280,280,279,279,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 29 */ +109,281,281,109,281,109,109,281,281,109,281,109,109,281,109,109, +109,109,109,109,281,281,281,281,109,281,281,281,281,281,281,281, +109,281,281,281,109,281,109,281,109,109,281,281,109,281,281,281, +281,282,281,283,282,282,282,282,282,282,109,282,282,281,109,109, +281,281,281,281,281,109,284,109,282,282,282,282,282,282,109,109, +285,285,285,285,285,285,285,285,285,285,109,109,281,281,281,281, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 30 */ +286,287,287,287,288,288,288,288,288,288,288,288,288,288,288,288, +288,288,288,287,288,287,287,287,289,289,287,287,287,287,287,287, +290,290,290,290,290,290,290,290,290,290,291,291,291,291,291,291, +291,291,291,291,287,289,287,289,287,289,292,293,292,293,294,294, +286,286,286,286,286,286,286,286,109,286,286,286,286,286,286,286, +286,286,286,286,286,286,286,286,286,286,286,286,286,286,286,286, +286,286,286,286,286,286,286,286,286,286,286,286,286,109,109,109, +109,289,289,289,289,289,289,289,289,289,289,289,289,289,289,294, + +/* block 31 */ +289,289,289,289,289,288,289,289,286,286,286,286,286,289,289,289, +289,289,289,289,289,289,289,289,109,289,289,289,289,289,289,289, +289,289,289,289,289,289,289,289,289,289,289,289,289,289,289,289, +289,289,289,289,289,289,289,289,289,289,289,289,289,109,287,287, +287,287,287,287,287,287,289,287,287,287,287,287,287,109,287,287, +288,288,288,288,288, 19, 19, 19, 19,288,288,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 32 */ +295,295,295,295,295,295,295,295,295,295,295,295,295,295,295,295, +295,295,295,295,295,295,295,295,295,295,295,295,295,295,295,295, +295,295,295,295,295,295,295,295,295,295,295,296,296,297,297,297, +297,298,297,297,297,297,297,297,296,297,297,298,298,297,297,295, +299,299,299,299,299,299,299,299,299,299,300,300,300,300,300,300, +295,295,295,295,295,295,298,298,297,297,295,295,295,295,297,297, +297,295,296,296,296,295,295,296,296,296,296,296,296,296,295,295, +295,297,297,297,297,295,295,295,295,295,295,295,295,295,295,295, + +/* block 33 */ +295,295,297,296,298,297,297,296,296,296,296,296,296,297,295,296, +299,299,299,299,299,299,299,299,299,299,296,296,296,297,301,301, +302,302,302,302,302,302,302,302,302,302,302,302,302,302,302,302, +302,302,302,302,302,302,302,302,302,302,302,302,302,302,302,302, +302,302,302,302,302,302,109,302,109,109,109,109,109,302,109,109, +303,303,303,303,303,303,303,303,303,303,303,303,303,303,303,303, +303,303,303,303,303,303,303,303,303,303,303,303,303,303,303,303, +303,303,303,303,303,303,303,303,303,303,303, 4,304,303,303,303, + +/* block 34 */ +305,305,305,305,305,305,305,305,305,305,305,305,305,305,305,305, +305,305,305,305,305,305,305,305,305,305,305,305,305,305,305,305, +305,305,305,305,305,305,305,305,305,305,305,305,305,305,305,305, +305,305,305,305,305,305,305,305,305,305,305,305,305,305,305,305, +305,305,305,305,305,305,305,305,305,305,305,305,305,305,305,305, +305,305,305,305,305,305,305,305,305,305,305,305,305,305,305,305, +306,306,306,306,306,306,306,306,306,306,306,306,306,306,306,306, +306,306,306,306,306,306,306,306,306,306,306,306,306,306,306,306, + +/* block 35 */ +306,306,306,306,306,306,306,306,306,306,306,306,306,306,306,306, +306,306,306,306,306,306,306,306,306,306,306,306,306,306,306,306, +306,306,306,306,306,306,306,306,307,307,307,307,307,307,307,307, +307,307,307,307,307,307,307,307,307,307,307,307,307,307,307,307, +307,307,307,307,307,307,307,307,307,307,307,307,307,307,307,307, +307,307,307,307,307,307,307,307,307,307,307,307,307,307,307,307, +307,307,307,307,307,307,307,307,307,307,307,307,307,307,307,307, +307,307,307,307,307,307,307,307,307,307,307,307,307,307,307,307, + +/* block 36 */ +308,308,308,308,308,308,308,308,308,308,308,308,308,308,308,308, +308,308,308,308,308,308,308,308,308,308,308,308,308,308,308,308, +308,308,308,308,308,308,308,308,308,308,308,308,308,308,308,308, +308,308,308,308,308,308,308,308,308,308,308,308,308,308,308,308, +308,308,308,308,308,308,308,308,308,109,308,308,308,308,109,109, +308,308,308,308,308,308,308,109,308,109,308,308,308,308,109,109, +308,308,308,308,308,308,308,308,308,308,308,308,308,308,308,308, +308,308,308,308,308,308,308,308,308,308,308,308,308,308,308,308, + +/* block 37 */ +308,308,308,308,308,308,308,308,308,109,308,308,308,308,109,109, +308,308,308,308,308,308,308,308,308,308,308,308,308,308,308,308, +308,308,308,308,308,308,308,308,308,308,308,308,308,308,308,308, +308,109,308,308,308,308,109,109,308,308,308,308,308,308,308,109, +308,109,308,308,308,308,109,109,308,308,308,308,308,308,308,308, +308,308,308,308,308,308,308,109,308,308,308,308,308,308,308,308, +308,308,308,308,308,308,308,308,308,308,308,308,308,308,308,308, +308,308,308,308,308,308,308,308,308,308,308,308,308,308,308,308, + +/* block 38 */ +308,308,308,308,308,308,308,308,308,308,308,308,308,308,308,308, +308,109,308,308,308,308,109,109,308,308,308,308,308,308,308,308, +308,308,308,308,308,308,308,308,308,308,308,308,308,308,308,308, +308,308,308,308,308,308,308,308,308,308,308,308,308,308,308,308, +308,308,308,308,308,308,308,308,308,308,308,308,308,308,308,308, +308,308,308,308,308,308,308,308,308,308,308,109,109,309,309,309, +310,310,310,310,310,310,310,310,310,311,311,311,311,311,311,311, +311,311,311,311,311,311,311,311,311,311,311,311,311,109,109,109, + +/* block 39 */ +308,308,308,308,308,308,308,308,308,308,308,308,308,308,308,308, +312,312,312,312,312,312,312,312,312,312,109,109,109,109,109,109, +313,313,313,313,313,313,313,313,313,313,313,313,313,313,313,313, +313,313,313,313,313,313,313,313,313,313,313,313,313,313,313,313, +313,313,313,313,313,313,313,313,313,313,313,313,313,313,313,313, +313,313,313,313,313,313,313,313,313,313,313,313,313,313,313,313, +313,313,313,313,313,313,313,313,313,313,313,313,313,313,313,313, +313,313,313,313,313,109,109,109,109,109,109,109,109,109,109,109, + +/* block 40 */ +314,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, + +/* block 41 */ +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, + +/* block 42 */ +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, +315,315,315,315,315,315,315,315,315,315,315,315,315,316,316,315, +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, + +/* block 43 */ +317,318,318,318,318,318,318,318,318,318,318,318,318,318,318,318, +318,318,318,318,318,318,318,318,318,318,318,319,320,109,109,109, +321,321,321,321,321,321,321,321,321,321,321,321,321,321,321,321, +321,321,321,321,321,321,321,321,321,321,321,321,321,321,321,321, +321,321,321,321,321,321,321,321,321,321,321,321,321,321,321,321, +321,321,321,321,321,321,321,321,321,321,321,321,321,321,321,321, +321,321,321,321,321,321,321,321,321,321,321, 4, 4, 4,322,322, +322,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 44 */ +323,323,323,323,323,323,323,323,323,323,323,323,323,109,323,323, +323,323,324,324,324,109,109,109,109,109,109,109,109,109,109,109, +325,325,325,325,325,325,325,325,325,325,325,325,325,325,325,325, +325,325,326,326,326, 4, 4,109,109,109,109,109,109,109,109,109, +327,327,327,327,327,327,327,327,327,327,327,327,327,327,327,327, +327,327,328,328,109,109,109,109,109,109,109,109,109,109,109,109, +329,329,329,329,329,329,329,329,329,329,329,329,329,109,329,329, +329,109,330,330,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 45 */ +331,331,331,331,331,331,331,331,331,331,331,331,331,331,331,331, +331,331,331,331,331,331,331,331,331,331,331,331,331,331,331,331, +331,331,331,331,331,331,331,331,331,331,331,331,331,331,331,331, +331,331,331,331,332,332,333,332,332,332,332,332,332,332,333,333, +333,333,333,333,333,333,332,333,333,332,332,332,332,332,332,332, +332,332,332,332,334,334,334,335,334,334,334,336,331,332,109,109, +337,337,337,337,337,337,337,337,337,337,109,109,109,109,109,109, +338,338,338,338,338,338,338,338,338,338,109,109,109,109,109,109, + +/* block 46 */ +339,339, 4, 4,339, 4,340,339,339,339,339,341,341,341,342,109, +343,343,343,343,343,343,343,343,343,343,109,109,109,109,109,109, +344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, +344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, +344,344,344,345,344,344,344,344,344,344,344,344,344,344,344,344, +344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, +344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, +344,344,344,344,344,344,344,344,109,109,109,109,109,109,109,109, + +/* block 47 */ +344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, +344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, +344,344,344,344,344,344,344,344,344,341,344,109,109,109,109,109, +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, +315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, +315,315,315,315,315,315,109,109,109,109,109,109,109,109,109,109, + +/* block 48 */ +346,346,346,346,346,346,346,346,346,346,346,346,346,346,346,346, +346,346,346,346,346,346,346,346,346,346,346,346,346,109,109,109, +347,347,347,348,348,348,348,347,347,348,348,348,109,109,109,109, +348,348,347,348,348,348,348,348,348,347,347,347,109,109,109,109, +349,109,109,109,350,350,351,351,351,351,351,351,351,351,351,351, +352,352,352,352,352,352,352,352,352,352,352,352,352,352,352,352, +352,352,352,352,352,352,352,352,352,352,352,352,352,352,109,109, +352,352,352,352,352,109,109,109,109,109,109,109,109,109,109,109, + +/* block 49 */ +353,353,353,353,353,353,353,353,353,353,353,353,353,353,353,353, +353,353,353,353,353,353,353,353,353,353,353,353,353,353,353,353, +353,353,353,353,353,353,353,353,353,353,353,353,109,109,109,109, +354,354,354,354,354,355,355,355,354,354,355,354,354,354,354,354, +354,353,353,353,353,353,353,353,354,354,109,109,109,109,109,109, +356,356,356,356,356,356,356,356,356,356,357,109,109,109,358,358, +359,359,359,359,359,359,359,359,359,359,359,359,359,359,359,359, +359,359,359,359,359,359,359,359,359,359,359,359,359,359,359,359, + +/* block 50 */ +360,360,360,360,360,360,360,360,360,360,360,360,360,360,360,360, +360,360,360,360,360,360,360,361,361,362,362,361,109,109,363,363, +364,364,364,364,364,364,364,364,364,364,364,364,364,364,364,364, +364,364,364,364,364,364,364,364,364,364,364,364,364,364,364,364, +364,364,364,364,364,364,364,364,364,364,364,364,364,364,364,364, +364,364,364,364,364,365,366,365,366,366,366,366,366,366,366,109, +366,367,366,367,367,366,366,366,366,366,366,366,366,365,365,365, +365,365,365,366,366,366,366,366,366,366,366,366,366,109,109,366, + +/* block 51 */ +368,368,368,368,368,368,368,368,368,368,109,109,109,109,109,109, +368,368,368,368,368,368,368,368,368,368,109,109,109,109,109,109, +369,369,369,369,369,369,369,370,369,369,369,369,369,369,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 52 */ +371,371,371,371,372,373,373,373,373,373,373,373,373,373,373,373, +373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,373, +373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,373, +373,373,373,373,371,372,371,371,371,371,371,372,371,372,372,372, +372,372,371,372,372,373,373,373,373,373,373,373,109,109,109,109, +374,374,374,374,374,374,374,374,374,374,375,375,375,375,375,375, +375,376,376,376,376,376,376,376,376,376,376,371,371,371,371,371, +371,371,371,371,376,376,376,376,376,376,376,376,376,109,109,109, + +/* block 53 */ +377,377,378,379,379,379,379,379,379,379,379,379,379,379,379,379, +379,379,379,379,379,379,379,379,379,379,379,379,379,379,379,379, +379,378,377,377,377,377,378,378,377,377,378,377,378,378,379,379, +380,380,380,380,380,380,380,380,380,380,379,379,379,379,379,379, +381,381,381,381,381,381,381,381,381,381,381,381,381,381,381,381, +381,381,381,381,381,381,381,381,381,381,381,381,381,381,381,381, +381,381,381,381,381,381,382,383,382,382,383,383,383,382,383,382, +382,382,383,383,109,109,109,109,109,109,109,109,384,384,384,384, + +/* block 54 */ +385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, +385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, +385,385,385,385,386,386,386,386,386,386,386,386,387,387,387,387, +387,387,387,387,386,386,387,387,109,109,109,388,388,388,388,388, +389,389,389,389,389,389,389,389,389,389,109,109,109,385,385,385, +390,390,390,390,390,390,390,390,390,390,391,391,391,391,391,391, +391,391,391,391,391,391,391,391,391,391,391,391,391,391,391,391, +391,391,391,391,391,391,391,391,392,392,392,392,392,392,393,393, + +/* block 55 */ +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +394,394,394,394,394,394,394,394,109,109,109,109,109,109,109,109, +104,104,104, 4,104,104,104,104,104,104,104,104,104,104,104,104, +104,395,104,104,104,104,104,104,104,396,396,396,396,104,396,396, +396,396,395,395,104,396,396,109,109,109,109,109,109,109,109,109, + +/* block 56 */ + 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, + 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, + 33, 33, 33, 33, 33, 33,116,116,116,116,116,397,101,101,101,101, +101,101,101,101,101,101,101,101,101,101,101,101,101,101,101,101, +101,101,101,101,101,101,101,101,101,101,101,101,101,101,101,101, +101,101,101,101,101,101,101,101,101,101,101,101,101,110,110,110, +110,110,101,101,101,101,110,110,110,110,110, 33, 33, 33, 33, 33, + 33, 33, 33, 33, 33, 33, 33, 33,398,399, 33, 33, 33,400, 33, 33, + +/* block 57 */ + 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, + 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,101,101,101,101,101, +101,101,101,101,101,101,101,101,101,101,101,101,101,101,101,101, +101,101,101,101,101,101,101,101,101,101,101,101,101,101,101,110, +104,104,104,104,104,104,104,104,104,104,104,104,104,104,104,104, +104,104,104,104,104,104,104,104,104,104,104,104,104,104,104,104, +104,104,104,104,104,104,104,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,104,104,104,104, + +/* block 58 */ + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, +401,402, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + +/* block 59 */ + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 30, 31, 30, 31, 30, 31, 33, 33, 33, 33, 33,403, 33, 33,404, 33, + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + +/* block 60 */ +405,405,405,405,405,405,405,405,406,406,406,406,406,406,406,406, +405,405,405,405,405,405,109,109,406,406,406,406,406,406,109,109, +405,405,405,405,405,405,405,405,406,406,406,406,406,406,406,406, +405,405,405,405,405,405,405,405,406,406,406,406,406,406,406,406, +405,405,405,405,405,405,109,109,406,406,406,406,406,406,109,109, +116,405,116,405,116,405,116,405,109,406,109,406,109,406,109,406, +405,405,405,405,405,405,405,405,406,406,406,406,406,406,406,406, +407,407,408,408,408,408,409,409,410,410,411,411,412,412,109,109, + +/* block 61 */ +405,405,405,405,405,405,405,405,413,413,413,413,413,413,413,413, +405,405,405,405,405,405,405,405,413,413,413,413,413,413,413,413, +405,405,405,405,405,405,405,405,413,413,413,413,413,413,413,413, +405,405,116,414,116,109,116,116,406,406,415,415,416,108,417,108, +108,108,116,414,116,109,116,116,418,418,418,418,416,108,108,108, +405,405,116,116,109,109,116,116,406,406,419,419,109,108,108,108, +405,405,116,116,116,157,116,116,406,406,420,420,161,108,108,108, +109,109,116,414,116,109,116,116,421,421,422,422,416,108,108,109, + +/* block 62 */ + 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 22,423,423, 22, 22, + 9, 9, 9, 9, 9, 9, 4, 4, 21, 25, 6, 21, 21, 25, 6, 21, + 4, 4, 4, 4, 4, 4, 4, 4,424,425, 22, 22, 22, 22, 22, 3, + 4, 4, 4, 4, 4, 4, 4, 4, 4, 21, 25, 4, 4, 4, 4, 15, + 15, 4, 4, 4, 8, 6, 7, 4, 4, 4, 4, 4, 4, 4, 4, 4, + 4, 4, 8, 4, 15, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 3, + 22, 22, 22, 22, 22,426, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, + 23,101,109,109, 23, 23, 23, 23, 23, 23, 8, 8, 8, 6, 7,101, + +/* block 63 */ + 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 8, 8, 8, 6, 7,109, +101,101,101,101,101,101,101,101,101,101,101,101,101,109,109,109, + 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, + 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +104,104,104,104,104,104,104,104,104,104,104,104,104,427,427,427, +427,104,427,427,427,104,104,104,104,104,104,104,104,104,104,104, +104,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 64 */ + 19, 19,428, 19, 19, 19, 19,428, 19, 19,429,428,428,428,429,429, +428,428,428,429, 19,428, 19, 19, 8,428,428,428,428,428, 19, 19, + 19, 19, 19, 19,428, 19,430, 19,428, 19,431,432,428,428, 19,429, +428,428,433,428,429,396,396,396,396,429, 19, 19,429,429,428,428, + 8, 8, 8, 8, 8,428,429,429,429,429, 19, 8, 19, 19,434, 19, + 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, +435,435,435,435,435,435,435,435,435,435,435,435,435,435,435,435, +436,436,436,436,436,436,436,436,436,436,436,436,436,436,436,436, + +/* block 65 */ +437,437,437, 30, 31,437,437,437,437, 23,109,109,109,109,109,109, + 8, 8, 8, 8, 8, 19, 19, 19, 19, 19, 8, 8, 19, 19, 19, 19, + 8, 19, 19, 8, 19, 19, 8, 19, 19, 19, 19, 19, 19, 19, 8, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 8, 8, + 19, 19, 8, 19, 8, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, + +/* block 66 */ + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, + +/* block 67 */ + 19, 19, 19, 19, 19, 19, 19, 19, 6, 7, 6, 7, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 8, 8, 19, 19, 19, 19, 19, 19, 19, 6, 7, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 8, 19, 19, 19, + +/* block 68 */ + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 8, 8, 8, 8, + 8, 8, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 69 */ + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, + 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, + +/* block 70 */ + 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, + 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19,438,438,438,438,438,438,438,438,438,438, +438,438,438,438,438,438,438,438,438,438,438,438,438,438,438,438, +439,439,439,439,439,439,439,439,439,439,439,439,439,439,439,439, +439,439,439,439,439,439,439,439,439,439, 23, 23, 23, 23, 23, 23, + 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, + +/* block 71 */ + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + +/* block 72 */ + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 8, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 8, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 8, 8, 8, 8, 8, 8, 8, 8, + +/* block 73 */ + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 8, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + +/* block 74 */ +109, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 6, 7, 6, 7, 6, 7, 6, 7, + 6, 7, 6, 7, 6, 7, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, + +/* block 75 */ + 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, + 23, 23, 23, 23, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 8, 8, 8, 8, 8, 6, 7, 8, 8, 8, 8, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 8, 6, 7, 6, 7, 6, 7, 6, 7, 6, 7, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, + +/* block 76 */ +440,440,440,440,440,440,440,440,440,440,440,440,440,440,440,440, +440,440,440,440,440,440,440,440,440,440,440,440,440,440,440,440, +440,440,440,440,440,440,440,440,440,440,440,440,440,440,440,440, +440,440,440,440,440,440,440,440,440,440,440,440,440,440,440,440, +440,440,440,440,440,440,440,440,440,440,440,440,440,440,440,440, +440,440,440,440,440,440,440,440,440,440,440,440,440,440,440,440, +440,440,440,440,440,440,440,440,440,440,440,440,440,440,440,440, +440,440,440,440,440,440,440,440,440,440,440,440,440,440,440,440, + +/* block 77 */ + 8, 8, 8, 6, 7, 6, 7, 6, 7, 6, 7, 6, 7, 6, 7, 6, + 7, 6, 7, 6, 7, 6, 7, 6, 7, 8, 8, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 8, 8, 8, 6, 7, 6, 7, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 6, 7, 8, 8, + +/* block 78 */ + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 19, 19, 8, 8, 8, 8, 8, 8,109,109,109, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 79 */ +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 80 */ +441,441,441,441,441,441,441,441,441,441,441,441,441,441,441,441, +441,441,441,441,441,441,441,441,441,441,441,441,441,441,441,441, +441,441,441,441,441,441,441,441,441,441,441,441,441,441,441,109, +442,442,442,442,442,442,442,442,442,442,442,442,442,442,442,442, +442,442,442,442,442,442,442,442,442,442,442,442,442,442,442,442, +442,442,442,442,442,442,442,442,442,442,442,442,442,442,442,109, + 30, 31,443,444,445,446,447, 30, 31, 30, 31, 30, 31,448,449,450, +451, 33, 30, 31, 33, 30, 31, 33, 33, 33, 33, 33,101,101,452,452, + +/* block 81 */ +153,154,153,154,153,154,153,154,153,154,153,154,153,154,153,154, +153,154,153,154,153,154,153,154,153,154,153,154,153,154,153,154, +153,154,153,154,153,154,153,154,153,154,153,154,153,154,153,154, +153,154,153,154,153,154,153,154,153,154,153,154,153,154,153,154, +153,154,153,154,153,154,153,154,153,154,153,154,153,154,153,154, +153,154,153,154,153,154,153,154,153,154,153,154,153,154,153,154, +153,154,153,154,453,454,454,454,454,454,454,153,154,153,154,455, +455,455,153,154,109,109,109,109,109,456,456,456,456,457,456,456, + +/* block 82 */ +458,458,458,458,458,458,458,458,458,458,458,458,458,458,458,458, +458,458,458,458,458,458,458,458,458,458,458,458,458,458,458,458, +458,458,458,458,458,458,109,458,109,109,109,109,109,458,109,109, +459,459,459,459,459,459,459,459,459,459,459,459,459,459,459,459, +459,459,459,459,459,459,459,459,459,459,459,459,459,459,459,459, +459,459,459,459,459,459,459,459,459,459,459,459,459,459,459,459, +459,459,459,459,459,459,459,459,109,109,109,109,109,109,109,460, +461,109,109,109,109,109,109,109,109,109,109,109,109,109,109,462, + +/* block 83 */ +308,308,308,308,308,308,308,308,308,308,308,308,308,308,308,308, +308,308,308,308,308,308,308,109,109,109,109,109,109,109,109,109, +308,308,308,308,308,308,308,109,308,308,308,308,308,308,308,109, +308,308,308,308,308,308,308,109,308,308,308,308,308,308,308,109, +308,308,308,308,308,308,308,109,308,308,308,308,308,308,308,109, +308,308,308,308,308,308,308,109,308,308,308,308,308,308,308,109, +170,170,170,170,170,170,170,170,170,170,170,170,170,170,170,170, +170,170,170,170,170,170,170,170,170,170,170,170,170,170,170,170, + +/* block 84 */ + 4, 4, 21, 25, 21, 25, 4, 4, 4, 21, 25, 4, 21, 25, 4, 4, + 4, 4, 4, 4, 4, 4, 4, 9, 4, 4, 9, 4, 21, 25, 4, 4, + 21, 25, 6, 7, 6, 7, 6, 7, 6, 7, 4, 4, 4, 4, 4,102, + 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 9, 9,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 85 */ +463,463,463,463,463,463,463,463,463,463,463,463,463,463,463,463, +463,463,463,463,463,463,463,463,463,463,109,463,463,463,463,463, +463,463,463,463,463,463,463,463,463,463,463,463,463,463,463,463, +463,463,463,463,463,463,463,463,463,463,463,463,463,463,463,463, +463,463,463,463,463,463,463,463,463,463,463,463,463,463,463,463, +463,463,463,463,463,463,463,463,463,463,463,463,463,463,463,463, +463,463,463,463,463,463,463,463,463,463,463,463,463,463,463,463, +463,463,463,463,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 86 */ +463,463,463,463,463,463,463,463,463,463,463,463,463,463,463,463, +463,463,463,463,463,463,463,463,463,463,463,463,463,463,463,463, +463,463,463,463,463,463,463,463,463,463,463,463,463,463,463,463, +463,463,463,463,463,463,463,463,463,463,463,463,463,463,463,463, +463,463,463,463,463,463,463,463,463,463,463,463,463,463,463,463, +463,463,463,463,463,463,463,463,463,463,463,463,463,463,463,463, +463,463,463,463,463,463,463,463,463,463,463,463,463,463,463,463, +463,463,463,463,463,463,463,463,463,463,463,463,463,463,463,463, + +/* block 87 */ +463,463,463,463,463,463,463,463,463,463,463,463,463,463,463,463, +463,463,463,463,463,463,463,463,463,463,463,463,463,463,463,463, +463,463,463,463,463,463,463,463,463,463,463,463,463,463,463,463, +463,463,463,463,463,463,463,463,463,463,463,463,463,463,463,463, +463,463,463,463,463,463,463,463,463,463,463,463,463,463,463,463, +463,463,463,463,463,463,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,109,109,109,109, + +/* block 88 */ + 3, 4, 4, 4, 19,464,396,465, 6, 7, 6, 7, 6, 7, 6, 7, + 6, 7, 19, 19, 6, 7, 6, 7, 6, 7, 6, 7, 9, 6, 7, 7, + 19,465,465,465,465,465,465,465,465,465,104,104,104,104,466,466, + 9,102,102,102,102,102, 19, 19,465,465,465,464,396, 4, 19, 19, +109,467,467,467,467,467,467,467,467,467,467,467,467,467,467,467, +467,467,467,467,467,467,467,467,467,467,467,467,467,467,467,467, +467,467,467,467,467,467,467,467,467,467,467,467,467,467,467,467, +467,467,467,467,467,467,467,467,467,467,467,467,467,467,467,467, + +/* block 89 */ +467,467,467,467,467,467,467,467,467,467,467,467,467,467,467,467, +467,467,467,467,467,467,467,109,109,104,104, 14, 14,468,468,467, + 9,469,469,469,469,469,469,469,469,469,469,469,469,469,469,469, +469,469,469,469,469,469,469,469,469,469,469,469,469,469,469,469, +469,469,469,469,469,469,469,469,469,469,469,469,469,469,469,469, +469,469,469,469,469,469,469,469,469,469,469,469,469,469,469,469, +469,469,469,469,469,469,469,469,469,469,469,469,469,469,469,469, +469,469,469,469,469,469,469,469,469,469,469, 4,102,470,470,469, + +/* block 90 */ +109,109,109,109,109,471,471,471,471,471,471,471,471,471,471,471, +471,471,471,471,471,471,471,471,471,471,471,471,471,471,471,471, +471,471,471,471,471,471,471,471,471,471,471,471,471,471,109,109, +109,472,472,472,472,472,472,472,472,472,472,472,472,472,472,472, +472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,472, +472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,472, +472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,472, +472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,472, + +/* block 91 */ +472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,109, + 19, 19, 23, 23, 23, 23, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, +471,471,471,471,471,471,471,471,471,471,471,471,471,471,471,471, +471,471,471,471,471,471,471,471,471,471,471,109,109,109,109,109, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19,109,109,109,109,109,109,109,109,109,109,109,109, +469,469,469,469,469,469,469,469,469,469,469,469,469,469,469,469, + +/* block 92 */ +473,473,473,473,473,473,473,473,473,473,473,473,473,473,473,473, +473,473,473,473,473,473,473,473,473,473,473,473,473,473,473,109, + 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 23, 23, 23, 23, 23, 23, 23, 23, + 19, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, +473,473,473,473,473,473,473,473,473,473,473,473,473,473,473,473, +473,473,473,473,473,473,473,473,473,473,473,473,473,473,473, 19, + +/* block 93 */ + 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, +474,474,474,474,474,474,474,474,474,474,474,474,474,474,474,474, +474,474,474,474,474,474,474,474,474,474,474,474,474,474,474,474, +474,474,474,474,474,474,474,474,474,474,474,474,474,474,474,109, + +/* block 94 */ +474,474,474,474,474,474,474,474,474,474,474,474,474,474,474,474, +474,474,474,474,474,474,474,474,474,474,474,474,474,474,474,474, +474,474,474,474,474,474,474,474,474,474,474,474,474,474,474,474, +474,474,474,474,474,474,474,474,474,474,474,474,474,474,474,474, +474,474,474,474,474,474,474,474,474,474,474,474,474,474,474,474, +474,474,474,474,474,474,474,474, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + +/* block 95 */ +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, + +/* block 96 */ +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,109,109,109,109,109,109,109,109,109,109, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + +/* block 97 */ +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 98 */ +476,476,476,476,476,476,476,476,476,476,476,476,476,476,476,476, +476,476,476,476,476,477,476,476,476,476,476,476,476,476,476,476, +476,476,476,476,476,476,476,476,476,476,476,476,476,476,476,476, +476,476,476,476,476,476,476,476,476,476,476,476,476,476,476,476, +476,476,476,476,476,476,476,476,476,476,476,476,476,476,476,476, +476,476,476,476,476,476,476,476,476,476,476,476,476,476,476,476, +476,476,476,476,476,476,476,476,476,476,476,476,476,476,476,476, +476,476,476,476,476,476,476,476,476,476,476,476,476,476,476,476, + +/* block 99 */ +476,476,476,476,476,476,476,476,476,476,476,476,476,476,476,476, +476,476,476,476,476,476,476,476,476,476,476,476,476,476,476,476, +476,476,476,476,476,476,476,476,476,476,476,476,476,476,476,476, +476,476,476,476,476,476,476,476,476,476,476,476,476,476,476,476, +476,476,476,476,476,476,476,476,476,476,476,476,476,476,476,476, +476,476,476,476,476,476,476,476,476,476,476,476,476,476,476,476, +476,476,476,476,476,476,476,476,476,476,476,476,476,476,476,476, +476,476,476,476,476,476,476,476,476,476,476,476,476,476,476,476, + +/* block 100 */ +476,476,476,476,476,476,476,476,476,476,476,476,476,109,109,109, +478,478,478,478,478,478,478,478,478,478,478,478,478,478,478,478, +478,478,478,478,478,478,478,478,478,478,478,478,478,478,478,478, +478,478,478,478,478,478,478,478,478,478,478,478,478,478,478,478, +478,478,478,478,478,478,478,109,109,109,109,109,109,109,109,109, +479,479,479,479,479,479,479,479,479,479,479,479,479,479,479,479, +479,479,479,479,479,479,479,479,479,479,479,479,479,479,479,479, +479,479,479,479,479,479,479,479,480,480,480,480,480,480,481,481, + +/* block 101 */ +482,482,482,482,482,482,482,482,482,482,482,482,482,482,482,482, +482,482,482,482,482,482,482,482,482,482,482,482,482,482,482,482, +482,482,482,482,482,482,482,482,482,482,482,482,482,482,482,482, +482,482,482,482,482,482,482,482,482,482,482,482,482,482,482,482, +482,482,482,482,482,482,482,482,482,482,482,482,482,482,482,482, +482,482,482,482,482,482,482,482,482,482,482,482,482,482,482,482, +482,482,482,482,482,482,482,482,482,482,482,482,482,482,482,482, +482,482,482,482,482,482,482,482,482,482,482,482,482,482,482,482, + +/* block 102 */ +482,482,482,482,482,482,482,482,482,482,482,482,483,484,484,484, +482,482,482,482,482,482,482,482,482,482,482,482,482,482,482,482, +485,485,485,485,485,485,485,485,485,485,482,482,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +167,168,167,168,167,168,167,168,167,168,167,168,167,168,167,168, +167,168,167,168,167,168,167,168,167,168,167,168,167,168,167,168, +167,168,167,168,167,168,167,168,167,168,167,168,167,168,486,170, +171,171,171,487,170,170,170,170,170,170,170,170,170,170,487,398, + +/* block 103 */ +167,168,167,168,167,168,167,168,167,168,167,168,167,168,167,168, +167,168,167,168,167,168,167,168,109,109,109,109,109,109,109,170, +488,488,488,488,488,488,488,488,488,488,488,488,488,488,488,488, +488,488,488,488,488,488,488,488,488,488,488,488,488,488,488,488, +488,488,488,488,488,488,488,488,488,488,488,488,488,488,488,488, +488,488,488,488,488,488,488,488,488,488,488,488,488,488,488,488, +488,488,488,488,488,488,489,489,489,489,489,489,489,489,489,489, +490,490,491,491,491,491,491,491,109,109,109,109,109,109,109,109, + +/* block 104 */ + 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, + 14, 14, 14, 14, 14, 14, 14,102,102,102,102,102,102,102,102,102, + 14, 14, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 33, 33, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, +101, 33, 33, 33, 33, 33, 33, 33, 33, 30, 31, 30, 31,492, 30, 31, + +/* block 105 */ + 30, 31, 30, 31, 30, 31, 30, 31,102, 14, 14, 30, 31,493, 33,109, + 30, 31, 30, 31,109,109,109,109,109,109,109,109,109,109,109,109, + 30, 31, 30, 31, 30, 31, 30, 31, 30, 31,494,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,101,101, 33, 20, 20, 20, 20, 20, + +/* block 106 */ +495,495,496,495,495,495,496,495,495,495,495,496,495,495,495,495, +495,495,495,495,495,495,495,495,495,495,495,495,495,495,495,495, +495,495,495,497,497,496,496,497,498,498,498,498,109,109,109,109, + 23, 23, 23, 23, 23, 23, 19, 19, 5, 19,109,109,109,109,109,109, +499,499,499,499,499,499,499,499,499,499,499,499,499,499,499,499, +499,499,499,499,499,499,499,499,499,499,499,499,499,499,499,499, +499,499,499,499,499,499,499,499,499,499,499,499,499,499,499,499, +499,499,499,499,500,500,500,500,109,109,109,109,109,109,109,109, + +/* block 107 */ +501,501,502,502,502,502,502,502,502,502,502,502,502,502,502,502, +502,502,502,502,502,502,502,502,502,502,502,502,502,502,502,502, +502,502,502,502,502,502,502,502,502,502,502,502,502,502,502,502, +502,502,502,502,501,501,501,501,501,501,501,501,501,501,501,501, +501,501,501,501,503,109,109,109,109,109,109,109,109,109,504,504, +505,505,505,505,505,505,505,505,505,505,109,109,109,109,109,109, +213,213,213,213,213,213,213,213,213,213,213,213,213,213,213,213, +213,213,215,215,215,215,215,215,217,217,217,215,109,109,109,109, + +/* block 108 */ +506,506,506,506,506,506,506,506,506,506,507,507,507,507,507,507, +507,507,507,507,507,507,507,507,507,507,507,507,507,507,507,507, +507,507,507,507,507,507,508,508,508,508,508,508,508,508,509,509, +510,510,510,510,510,510,510,510,510,510,510,510,510,510,510,510, +510,510,510,510,510,510,510,511,511,511,511,511,511,511,511,511, +511,511,512,512,109,109,109,109,109,109,109,109,109,109,109,513, +305,305,305,305,305,305,305,305,305,305,305,305,305,305,305,305, +305,305,305,305,305,305,305,305,305,305,305,305,305,109,109,109, + +/* block 109 */ +514,514,514,515,516,516,516,516,516,516,516,516,516,516,516,516, +516,516,516,516,516,516,516,516,516,516,516,516,516,516,516,516, +516,516,516,516,516,516,516,516,516,516,516,516,516,516,516,516, +516,516,516,514,515,515,514,514,514,514,515,515,514,515,515,515, +515,517,517,517,517,517,517,517,517,517,517,517,517,517,109,102, +518,518,518,518,518,518,518,518,518,518,109,109,109,109,517,517, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 110 */ +519,519,519,519,519,519,519,519,519,519,519,519,519,519,519,519, +519,519,519,519,519,519,519,519,519,519,519,519,519,519,519,519, +519,519,519,519,519,519,519,519,519,520,520,520,520,520,520,521, +521,520,520,521,521,520,520,109,109,109,109,109,109,109,109,109, +519,519,519,520,519,519,519,519,519,519,519,519,520,521,109,109, +522,522,522,522,522,522,522,522,522,522,109,109,523,523,523,523, +295,295,295,295,295,295,295,295,295,295,295,295,295,295,295,295, +524,295,295,295,295,295,295,301,301,301,295,296,109,109,109,109, + +/* block 111 */ +525,525,525,525,525,525,525,525,525,525,525,525,525,525,525,525, +525,525,525,525,525,525,525,525,525,525,525,525,525,525,525,525, +525,525,525,525,525,525,525,525,525,525,525,525,525,525,525,525, +526,525,526,526,526,525,525,526,526,525,525,525,525,525,526,526, +525,526,525,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,525,525,527,528,528, +529,529,529,529,529,529,529,529,529,529,529,530,531,531,530,530, +532,532,529,533,533,530,531,109,109,109,109,109,109,109,109,109, + +/* block 112 */ +109,308,308,308,308,308,308,109,109,308,308,308,308,308,308,109, +109,308,308,308,308,308,308,109,109,109,109,109,109,109,109,109, +308,308,308,308,308,308,308,109,308,308,308,308,308,308,308,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 113 */ +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +529,529,529,529,529,529,529,529,529,529,529,529,529,529,529,529, +529,529,529,529,529,529,529,529,529,529,529,529,529,529,529,529, +529,529,529,530,530,531,530,530,531,530,530,532,530,531,109,109, +534,534,534,534,534,534,534,534,534,534,109,109,109,109,109,109, + +/* block 114 */ +535,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,535,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,535,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,535,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +535,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, + +/* block 115 */ +536,536,536,536,536,536,536,536,536,536,536,536,535,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,535,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,535,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +535,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,535,536,536,536, + +/* block 116 */ +536,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,535,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,535,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +535,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,535,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, + +/* block 117 */ +536,536,536,536,536,536,536,536,535,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,535,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +535,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,535,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,535,536,536,536,536,536,536,536, + +/* block 118 */ +536,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,535,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +535,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,535,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,535,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, + +/* block 119 */ +536,536,536,536,535,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +535,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,535,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,535,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,535,536,536,536,536,536,536,536,536,536,536,536, + +/* block 120 */ +536,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +535,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,535,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,535,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,535,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, + +/* block 121 */ +536,536,536,536,536,536,536,536,535,536,536,536,536,536,536,536, +536,536,536,536,536,536,536,536,536,536,536,536,536,536,536,536, +536,536,536,536,109,109,109,109,109,109,109,109,109,109,109,109, +306,306,306,306,306,306,306,306,306,306,306,306,306,306,306,306, +306,306,306,306,306,306,306,109,109,109,109,307,307,307,307,307, +307,307,307,307,307,307,307,307,307,307,307,307,307,307,307,307, +307,307,307,307,307,307,307,307,307,307,307,307,307,307,307,307, +307,307,307,307,307,307,307,307,307,307,307,307,109,109,109,109, + +/* block 122 */ +537,537,537,537,537,537,537,537,537,537,537,537,537,537,537,537, +537,537,537,537,537,537,537,537,537,537,537,537,537,537,537,537, +537,537,537,537,537,537,537,537,537,537,537,537,537,537,537,537, +537,537,537,537,537,537,537,537,537,537,537,537,537,537,537,537, +537,537,537,537,537,537,537,537,537,537,537,537,537,537,537,537, +537,537,537,537,537,537,537,537,537,537,537,537,537,537,537,537, +537,537,537,537,537,537,537,537,537,537,537,537,537,537,537,537, +537,537,537,537,537,537,537,537,537,537,537,537,537,537,537,537, + +/* block 123 */ +538,538,538,538,538,538,538,538,538,538,538,538,538,538,538,538, +538,538,538,538,538,538,538,538,538,538,538,538,538,538,538,538, +538,538,538,538,538,538,538,538,538,538,538,538,538,538,538,538, +538,538,538,538,538,538,538,538,538,538,538,538,538,538,538,538, +538,538,538,538,538,538,538,538,538,538,538,538,538,538,538,538, +538,538,538,538,538,538,538,538,538,538,538,538,538,538,538,538, +538,538,538,538,538,538,538,538,538,538,538,538,538,538,538,538, +538,538,538,538,538,538,538,538,538,538,538,538,538,538,538,538, + +/* block 124 */ +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,109,109, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, + +/* block 125 */ +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 126 */ + 33, 33, 33, 33, 33, 33, 33,109,109,109,109,109,109,109,109,109, +109,109,109,178,178,178,178,178,109,109,109,109,109,184,181,184, +184,184,184,184,184,184,184,184,184,539,184,184,184,184,184,184, +184,184,184,184,184,184,184,109,184,184,184,184,184,109,184,109, +184,184,109,184,184,109,184,184,184,184,184,184,184,184,184,184, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, + +/* block 127 */ +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,540,540,540,540,540,540,540,540,540,540,540,540,540,540, +540,540,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, + +/* block 128 */ +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, + +/* block 129 */ +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191, 6, 7, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, + +/* block 130 */ +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +109,109,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +191,191,191,191,191,191,191,191,191,191,191,191,188, 19,109,109, + +/* block 131 */ +104,104,104,104,104,104,104,104,104,104,104,104,104,104,104,104, + 4, 4, 4, 4, 4, 4, 4, 6, 7, 4,109,109,109,109,109,109, +104,104,104,104,104,104,104,109,109,109,109,109,109,109,109,109, + 4, 9, 9, 15, 15, 6, 7, 6, 7, 6, 7, 6, 7, 6, 7, 6, + 7, 6, 7, 6, 7, 4, 4, 6, 7, 4, 4, 4, 4, 15, 15, 15, + 4, 4, 4,109, 4, 4, 4, 4, 9, 6, 7, 6, 7, 6, 7, 4, + 4, 4, 8, 9, 8, 8, 8,109, 4, 5, 4, 4,109,109,109,109, +191,191,191,191,191,109,191,191,191,191,191,191,191,191,191,191, + +/* block 132 */ +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,109,109, 22, + +/* block 133 */ +109, 4, 4, 4, 5, 4, 4, 4, 6, 7, 4, 8, 4, 9, 4, 4, + 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 4, 4, 8, 8, 8, 4, + 4, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, + 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 6, 4, 7, 14, 15, + 14, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, + 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 6, 8, 7, 8, 6, + 7, 4, 6, 7, 4, 4,469,469,469,469,469,469,469,469,469,469, +102,469,469,469,469,469,469,469,469,469,469,469,469,469,469,469, + +/* block 134 */ +469,469,469,469,469,469,469,469,469,469,469,469,469,469,469,469, +469,469,469,469,469,469,469,469,469,469,469,469,469,469,541,541, +472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,472, +472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,109, +109,109,472,472,472,472,472,472,109,109,472,472,472,472,472,472, +109,109,472,472,472,472,472,472,109,109,472,472,472,109,109,109, + 5, 5, 8, 14, 19, 5, 5,109, 19, 8, 8, 8, 8, 19, 19,109, +426,426,426,426,426,426,426,426,426, 22, 22, 22, 19, 19,109,109, + +/* block 135 */ +542,542,542,542,542,542,542,542,542,542,542,542,109,542,542,542, +542,542,542,542,542,542,542,542,542,542,542,542,542,542,542,542, +542,542,542,542,542,542,542,109,542,542,542,542,542,542,542,542, +542,542,542,542,542,542,542,542,542,542,542,109,542,542,109,542, +542,542,542,542,542,542,542,542,542,542,542,542,542,542,109,109, +542,542,542,542,542,542,542,542,542,542,542,542,542,542,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 136 */ +542,542,542,542,542,542,542,542,542,542,542,542,542,542,542,542, +542,542,542,542,542,542,542,542,542,542,542,542,542,542,542,542, +542,542,542,542,542,542,542,542,542,542,542,542,542,542,542,542, +542,542,542,542,542,542,542,542,542,542,542,542,542,542,542,542, +542,542,542,542,542,542,542,542,542,542,542,542,542,542,542,542, +542,542,542,542,542,542,542,542,542,542,542,542,542,542,542,542, +542,542,542,542,542,542,542,542,542,542,542,542,542,542,542,542, +542,542,542,542,542,542,542,542,542,542,542,109,109,109,109,109, + +/* block 137 */ + 4, 4, 4,109,109,109,109, 23, 23, 23, 23, 23, 23, 23, 23, 23, + 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, + 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, + 23, 23, 23, 23,109,109,109, 19, 19, 19, 19, 19, 19, 19, 19, 19, +543,543,543,543,543,543,543,543,543,543,543,543,543,543,543,543, +543,543,543,543,543,543,543,543,543,543,543,543,543,543,543,543, +543,543,543,543,543,543,543,543,543,543,543,543,543,543,543,543, +543,543,543,543,543,544,544,544,544,545,545,545,545,545,545,545, + +/* block 138 */ +545,545,545,545,545,545,545,545,545,545,544,109,109,109,109,109, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,104,109,109, + +/* block 139 */ +546,546,546,546,546,546,546,546,546,546,546,546,546,546,546,546, +546,546,546,546,546,546,546,546,546,546,546,546,546,109,109,109, +547,547,547,547,547,547,547,547,547,547,547,547,547,547,547,547, +547,547,547,547,547,547,547,547,547,547,547,547,547,547,547,547, +547,547,547,547,547,547,547,547,547,547,547,547,547,547,547,547, +547,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 140 */ +548,548,548,548,548,548,548,548,548,548,548,548,548,548,548,548, +548,548,548,548,548,548,548,548,548,548,548,548,548,548,548,109, +549,549,549,549,109,109,109,109,109,109,109,109,109,109,109,109, +550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, +550,551,550,550,550,550,550,550,550,550,551,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 141 */ +552,552,552,552,552,552,552,552,552,552,552,552,552,552,552,552, +552,552,552,552,552,552,552,552,552,552,552,552,552,552,109,553, +554,554,554,554,554,554,554,554,554,554,554,554,554,554,554,554, +554,554,554,554,554,554,554,554,554,554,554,554,554,554,554,554, +554,554,554,554,109,109,109,109,554,554,554,554,554,554,554,554, +555,556,556,556,556,556,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 142 */ +557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,557, +557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,557, +557,557,557,557,557,557,557,557,558,558,558,558,558,558,558,558, +558,558,558,558,558,558,558,558,558,558,558,558,558,558,558,558, +558,558,558,558,558,558,558,558,558,558,558,558,558,558,558,558, +559,559,559,559,559,559,559,559,559,559,559,559,559,559,559,559, +559,559,559,559,559,559,559,559,559,559,559,559,559,559,559,559, +559,559,559,559,559,559,559,559,559,559,559,559,559,559,559,559, + +/* block 143 */ +560,560,560,560,560,560,560,560,560,560,560,560,560,560,560,560, +560,560,560,560,560,560,560,560,560,560,560,560,560,560,109,109, +561,561,561,561,561,561,561,561,561,561,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 144 */ +562,562,562,562,562,562,109,109,562,109,562,562,562,562,562,562, +562,562,562,562,562,562,562,562,562,562,562,562,562,562,562,562, +562,562,562,562,562,562,562,562,562,562,562,562,562,562,562,562, +562,562,562,562,562,562,109,562,562,109,109,109,562,109,109,562, +563,563,563,563,563,563,563,563,563,563,563,563,563,563,563,563, +563,563,563,563,563,563,109,564,565,565,565,565,565,565,565,565, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 145 */ +566,566,566,566,566,566,566,566,566,566,566,566,566,566,566,566, +566,566,566,566,566,566,567,567,567,567,567,567,109,109,109,568, +569,569,569,569,569,569,569,569,569,569,569,569,569,569,569,569, +569,569,569,569,569,569,569,569,569,569,109,109,109,109,109,570, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 146 */ +571,571,571,571,571,571,571,571,571,571,571,571,571,571,571,571, +571,571,571,571,571,571,571,571,571,571,571,571,571,571,571,571, +572,572,572,572,572,572,572,572,572,572,572,572,572,572,572,572, +572,572,572,572,572,572,572,572,109,109,109,109,109,109,572,572, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 147 */ +573,574,574,574,109,574,574,109,109,109,109,109,574,574,574,574, +573,573,573,573,109,573,573,573,109,573,573,573,573,573,573,573, +573,573,573,573,573,573,573,573,573,573,573,573,573,573,573,573, +573,573,573,573,109,109,109,109,574,574,574,109,109,109,109,574, +575,575,575,575,575,575,575,575,109,109,109,109,109,109,109,109, +576,576,576,576,576,576,576,576,576,109,109,109,109,109,109,109, +577,577,577,577,577,577,577,577,577,577,577,577,577,577,577,577, +577,577,577,577,577,577,577,577,577,577,577,577,577,578,578,579, + +/* block 148 */ +580,580,580,580,580,580,580,580,580,580,580,580,580,580,580,580, +580,580,580,580,580,580,580,580,580,580,580,580,580,580,580,580, +580,580,580,580,580,580,580,580,580,580,580,580,580,580,580,580, +580,580,580,580,580,580,109,109,109,581,581,581,581,581,581,581, +582,582,582,582,582,582,582,582,582,582,582,582,582,582,582,582, +582,582,582,582,582,582,109,109,583,583,583,583,583,583,583,583, +584,584,584,584,584,584,584,584,584,584,584,584,584,584,584,584, +584,584,584,109,109,109,109,109,585,585,585,585,585,585,585,585, + +/* block 149 */ +586,586,586,586,586,586,586,586,586,586,586,586,586,586,586,586, +586,586,586,586,586,586,586,586,586,586,586,586,586,586,586,586, +586,586,586,586,586,586,586,586,586,586,586,586,586,586,586,586, +586,586,586,586,586,586,586,586,586,586,586,586,586,586,586,586, +586,586,586,586,586,586,586,586,586,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 150 */ +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +587,587,587,587,587,587,587,587,587,587,587,587,587,587,587,587, +587,587,587,587,587,587,587,587,587,587,587,587,587,587,587,109, + +/* block 151 */ +588,589,588,590,590,590,590,590,590,590,590,590,590,590,590,590, +590,590,590,590,590,590,590,590,590,590,590,590,590,590,590,590, +590,590,590,590,590,590,590,590,590,590,590,590,590,590,590,590, +590,590,590,590,590,590,590,590,589,589,589,589,589,589,589,589, +589,589,589,589,589,589,589,591,591,591,591,591,591,591,109,109, +109,109,592,592,592,592,592,592,592,592,592,592,592,592,592,592, +592,592,592,592,592,592,593,593,593,593,593,593,593,593,593,593, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 152 */ +594,594,595,596,596,596,596,596,596,596,596,596,596,596,596,596, +596,596,596,596,596,596,596,596,596,596,596,596,596,596,596,596, +596,596,596,596,596,596,596,596,596,596,596,596,596,596,596,596, +595,595,595,594,594,594,594,595,595,594,594,597,597,598,597,597, +597,597,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +599,599,599,599,599,599,599,599,599,599,599,599,599,599,599,599, +599,599,599,599,599,599,599,599,599,109,109,109,109,109,109,109, +600,600,600,600,600,600,600,600,600,600,109,109,109,109,109,109, + +/* block 153 */ +601,601,601,602,602,602,602,602,602,602,602,602,602,602,602,602, +602,602,602,602,602,602,602,602,602,602,602,602,602,602,602,602, +602,602,602,602,602,602,602,601,601,601,601,601,603,601,601,601, +601,601,601,601,601,109,604,604,604,604,604,604,604,604,604,604, +605,605,605,605,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 154 */ +606,606,607,608,608,608,608,608,608,608,608,608,608,608,608,608, +608,608,608,608,608,608,608,608,608,608,608,608,608,608,608,608, +608,608,608,608,608,608,608,608,608,608,608,608,608,608,608,608, +608,608,608,607,607,607,606,606,606,606,606,606,606,606,606,607, +607,608,608,608,608,609,609,609,609,109,109,109,109,109,109,109, +610,610,610,610,610,610,610,610,610,610,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 155 */ +611,611,611,611,611,611,611,611,611,611,611,611,611,611,611,611, +611,611,611,611,611,611,611,611,611,611,611,611,611,611,611,611, +611,611,611,611,611,611,611,611,611,611,611,612,613,612,613,613, +612,612,612,612,612,612,613,612,109,109,109,109,109,109,109,109, +614,614,614,614,614,614,614,614,614,614,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 156 */ +615,615,615,615,615,615,615,615,615,615,615,615,615,615,615,615, +615,615,615,615,615,615,615,615,615,615,615,615,615,615,615,615, +615,615,615,615,615,615,615,615,615,615,615,615,615,615,615,615, +615,615,615,615,615,615,615,615,615,615,615,615,615,615,615,615, +615,615,615,615,615,615,615,615,615,615,615,615,615,615,615,615, +615,615,615,615,615,615,615,615,615,615,615,615,615,615,615,615, +615,615,615,615,615,615,615,615,615,615,615,615,615,615,615,615, +615,615,615,615,615,615,615,615,615,615,615,615,615,615,615,615, + +/* block 157 */ +615,615,615,615,615,615,615,615,615,615,615,615,615,615,615,615, +615,615,615,615,615,615,615,615,615,615,615,615,615,615,615,615, +615,615,615,615,615,615,615,615,615,615,615,615,615,615,615,615, +615,615,615,615,615,615,615,615,615,615,615,615,615,615,615,615, +615,615,615,615,615,615,615,615,615,615,615,615,615,615,615,615, +615,615,615,615,615,615,615,615,615,615,615,615,615,615,615,615, +615,615,615,615,615,615,615,615,615,615,615,615,615,615,615,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 158 */ +616,616,616,616,616,616,616,616,616,616,616,616,616,616,616,616, +616,616,616,616,616,616,616,616,616,616,616,616,616,616,616,616, +616,616,616,616,616,616,616,616,616,616,616,616,616,616,616,616, +616,616,616,616,616,616,616,616,616,616,616,616,616,616,616,616, +616,616,616,616,616,616,616,616,616,616,616,616,616,616,616,616, +616,616,616,616,616,616,616,616,616,616,616,616,616,616,616,616, +616,616,616,109,109,109,109,109,109,109,109,109,109,109,109,109, +617,617,617,617,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 159 */ +618,618,618,618,618,618,618,618,618,618,618,618,618,618,618,618, +618,618,618,618,618,618,618,618,618,618,618,618,618,618,618,618, +618,618,618,618,618,618,618,618,618,618,618,618,618,618,618,618, +618,618,618,618,618,618,618,618,618,618,618,618,618,618,618,618, +618,618,618,618,618,618,618,618,618,618,618,618,618,618,618,618, +618,618,618,618,618,618,618,618,618,618,618,618,618,618,618,618, +618,618,618,618,618,618,618,618,618,618,618,618,618,618,618,618, +618,618,618,618,618,618,618,618,618,618,618,618,618,618,618,618, + +/* block 160 */ +618,618,618,618,618,618,618,618,618,618,618,618,618,618,618,618, +618,618,618,618,618,618,618,618,618,618,618,618,618,618,618,618, +618,618,618,618,618,618,618,618,618,618,618,618,618,618,618,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 161 */ +488,488,488,488,488,488,488,488,488,488,488,488,488,488,488,488, +488,488,488,488,488,488,488,488,488,488,488,488,488,488,488,488, +488,488,488,488,488,488,488,488,488,488,488,488,488,488,488,488, +488,488,488,488,488,488,488,488,488,488,488,488,488,488,488,488, +488,488,488,488,488,488,488,488,488,488,488,488,488,488,488,488, +488,488,488,488,488,488,488,488,488,488,488,488,488,488,488,488, +488,488,488,488,488,488,488,488,488,488,488,488,488,488,488,488, +488,488,488,488,488,488,488,488,488,488,488,488,488,488,488,488, + +/* block 162 */ +488,488,488,488,488,488,488,488,488,488,488,488,488,488,488,488, +488,488,488,488,488,488,488,488,488,488,488,488,488,488,488,488, +488,488,488,488,488,488,488,488,488,488,488,488,488,488,488,488, +488,488,488,488,488,488,488,488,488,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 163 */ +619,619,619,619,619,619,619,619,619,619,619,619,619,619,619,619, +619,619,619,619,619,619,619,619,619,619,619,619,619,619,619,619, +619,619,619,619,619,619,619,619,619,619,619,619,619,619,619,619, +619,619,619,619,619,619,619,619,619,619,619,619,619,619,619,619, +619,619,619,619,619,109,109,109,109,109,109,109,109,109,109,109, +619,620,620,620,620,620,620,620,620,620,620,620,620,620,620,620, +620,620,620,620,620,620,620,620,620,620,620,620,620,620,620,620, +620,620,620,620,620,620,620,620,620,620,620,620,620,620,620,109, + +/* block 164 */ +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,621, +621,621,621,622,622,622,622,622,622,622,622,622,622,622,622,622, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 165 */ +469,467,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 166 */ + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19,109,109,109,109,109,109,109,109,109,109, + +/* block 167 */ + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19,109,109, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19,623,395,104,104,104, 19, 19, 19,395,623,623, +623,623,623, 22, 22, 22, 22, 22, 22, 22, 22,104,104,104,104,104, + +/* block 168 */ +104,104,104, 19, 19,104,104,104,104,104,104,104, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,104,104,104,104, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 169 */ +545,545,545,545,545,545,545,545,545,545,545,545,545,545,545,545, +545,545,545,545,545,545,545,545,545,545,545,545,545,545,545,545, +545,545,545,545,545,545,545,545,545,545,545,545,545,545,545,545, +545,545,545,545,545,545,545,545,545,545,545,545,545,545,545,545, +545,545,624,624,624,545,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 170 */ + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19,109,109,109,109,109,109,109,109,109, + 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, + 23, 23,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 171 */ +428,428,428,428,428,428,428,428,428,428,428,428,428,428,428,428, +428,428,428,428,428,428,428,428,428,428,429,429,429,429,429,429, +429,429,429,429,429,429,429,429,429,429,429,429,429,429,429,429, +429,429,429,429,428,428,428,428,428,428,428,428,428,428,428,428, +428,428,428,428,428,428,428,428,428,428,428,428,428,428,429,429, +429,429,429,429,429,109,429,429,429,429,429,429,429,429,429,429, +429,429,429,429,429,429,429,429,428,428,428,428,428,428,428,428, +428,428,428,428,428,428,428,428,428,428,428,428,428,428,428,428, + +/* block 172 */ +428,428,429,429,429,429,429,429,429,429,429,429,429,429,429,429, +429,429,429,429,429,429,429,429,429,429,429,429,428,109,428,428, +109,109,428,109,109,428,428,109,109,428,428,428,428,109,428,428, +428,428,428,428,428,428,429,429,429,429,109,429,109,429,429,429, +429,429,429,429,109,429,429,429,429,429,429,429,429,429,429,429, +428,428,428,428,428,428,428,428,428,428,428,428,428,428,428,428, +428,428,428,428,428,428,428,428,428,428,429,429,429,429,429,429, +429,429,429,429,429,429,429,429,429,429,429,429,429,429,429,429, + +/* block 173 */ +429,429,429,429,428,428,109,428,428,428,428,109,109,428,428,428, +428,428,428,428,428,109,428,428,428,428,428,428,428,109,429,429, +429,429,429,429,429,429,429,429,429,429,429,429,429,429,429,429, +429,429,429,429,429,429,429,429,428,428,109,428,428,428,428,109, +428,428,428,428,428,109,428,109,109,109,428,428,428,428,428,428, +428,109,429,429,429,429,429,429,429,429,429,429,429,429,429,429, +429,429,429,429,429,429,429,429,429,429,429,429,428,428,428,428, +428,428,428,428,428,428,428,428,428,428,428,428,428,428,428,428, + +/* block 174 */ +428,428,428,428,428,428,429,429,429,429,429,429,429,429,429,429, +429,429,429,429,429,429,429,429,429,429,429,429,429,429,429,429, +428,428,428,428,428,428,428,428,428,428,428,428,428,428,428,428, +428,428,428,428,428,428,428,428,428,428,429,429,429,429,429,429, +429,429,429,429,429,429,429,429,429,429,429,429,429,429,429,429, +429,429,429,429,428,428,428,428,428,428,428,428,428,428,428,428, +428,428,428,428,428,428,428,428,428,428,428,428,428,428,429,429, +429,429,429,429,429,429,429,429,429,429,429,429,429,429,429,429, + +/* block 175 */ +429,429,429,429,429,429,429,429,428,428,428,428,428,428,428,428, +428,428,428,428,428,428,428,428,428,428,428,428,428,428,428,428, +428,428,429,429,429,429,429,429,429,429,429,429,429,429,429,429, +429,429,429,429,429,429,429,429,429,429,429,429,428,428,428,428, +428,428,428,428,428,428,428,428,428,428,428,428,428,428,428,428, +428,428,428,428,428,428,429,429,429,429,429,429,429,429,429,429, +429,429,429,429,429,429,429,429,429,429,429,429,429,429,429,429, +428,428,428,428,428,428,428,428,428,428,428,428,428,428,428,428, + +/* block 176 */ +428,428,428,428,428,428,428,428,428,428,429,429,429,429,429,429, +429,429,429,429,429,429,429,429,429,429,429,429,429,429,429,429, +429,429,429,429,429,429,109,109,428,428,428,428,428,428,428,428, +428,428,428,428,428,428,428,428,428,428,428,428,428,428,428,428, +428, 8,429,429,429,429,429,429,429,429,429,429,429,429,429,429, +429,429,429,429,429,429,429,429,429,429,429, 8,429,429,429,429, +429,429,428,428,428,428,428,428,428,428,428,428,428,428,428,428, +428,428,428,428,428,428,428,428,428,428,428, 8,429,429,429,429, + +/* block 177 */ +429,429,429,429,429,429,429,429,429,429,429,429,429,429,429,429, +429,429,429,429,429, 8,429,429,429,429,429,429,428,428,428,428, +428,428,428,428,428,428,428,428,428,428,428,428,428,428,428,428, +428,428,428,428,428, 8,429,429,429,429,429,429,429,429,429,429, +429,429,429,429,429,429,429,429,429,429,429,429,429,429,429, 8, +429,429,429,429,429,429,428,428,428,428,428,428,428,428,428,428, +428,428,428,428,428,428,428,428,428,428,428,428,428,428,428, 8, +429,429,429,429,429,429,429,429,429,429,429,429,429,429,429,429, + +/* block 178 */ +429,429,429,429,429,429,429,429,429, 8,429,429,429,429,429,429, +428,428,428,428,428,428,428,428,428,428,428,428,428,428,428,428, +428,428,428,428,428,428,428,428,428, 8,429,429,429,429,429,429, +429,429,429,429,429,429,429,429,429,429,429,429,429,429,429,429, +429,429,429, 8,429,429,429,429,429,429,428,429,109,109, 10, 10, + 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, + 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, + 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, + +/* block 179 */ +191,191,191,191,109,191,191,191,191,191,191,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,191,191,191,191, +109,191,191,109,191,109,109,191,109,191,191,191,191,191,191,191, +191,191,191,109,191,191,191,191,109,191,109,191,109,109,109,109, +109,109,191,109,109,109,109,191,109,191,109,191,109,191,191,191, +109,191,191,109,191,109,109,191,109,191,109,191,109,191,109,191, +109,191,191,109,191,109,109,191,191,191,191,109,191,191,191,191, +191,191,191,109,191,191,191,191,109,191,191,191,191,109,191,109, + +/* block 180 */ +191,191,191,191,191,191,191,191,191,191,109,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,109,109,109,109, +109,191,191,191,109,191,191,191,191,191,109,191,191,191,191,191, +191,191,191,191,191,191,191,191,191,191,191,191,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +186,186,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 181 */ + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,109,109,109,109, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + +/* block 182 */ + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19,109,109,109,109,109,109,109,109,109,109,109,109, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,109, +109, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,109, +109, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, +109, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 183 */ + 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23,109,109,109,109,109, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,109, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,109,109,109,109, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + +/* block 184 */ + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,625,625,625,625,625,625,625,625,625,625, +625,625,625,625,625,625,625,625,625,625,625,625,625,625,625,625, + +/* block 185 */ +626, 19, 19,109,109,109,109,109,109,109,109,109,109,109,109,109, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,109,109,109,109,109, + 19, 19, 19, 19, 19, 19, 19, 19, 19,109,109,109,109,109,109,109, + 19, 19,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 186 */ + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + 19, 19, 19, 19, 19, 19,109, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,109,109,109, + +/* block 187 */ + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19,109,109,109,109,109,109,109,109,109,109,109,109, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19,109, 19, 19, 19, 19, 19,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 188 */ + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,109, + 19,109, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + +/* block 189 */ + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19,109, 19, 19, 19, 19,109,109,109, + +/* block 190 */ + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,109,109, + 19, 19, 19, 19,109,109,109,109,109,109,109,109,109,109,109,109, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 191 */ +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109, 19, 19, 19, 19, 19, + +/* block 192 */ + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19,109,109,109,109, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 193 */ + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 194 */ + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, + 19, 19, 19, 19,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 195 */ +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 196 */ +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,109,109,109,109,109,109,109,109,109,109,109, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, + +/* block 197 */ +475,475,475,475,475,475,475,475,475,475,475,475,475,475,475,475, +475,475,475,475,475,475,475,475,475,475,475,475,475,475,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, +109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, + +/* block 198 */ +426, 22,426,426,426,426,426,426,426,426,426,426,426,426,426,426, +426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,426, + 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, + 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, + 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, + 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, + 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, + 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, + +/* block 199 */ +426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,426, +426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,426, +426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,426, +426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,426, +426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,426, +426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,426, +426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,426, +426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,426, + +/* block 200 */ +104,104,104,104,104,104,104,104,104,104,104,104,104,104,104,104, +104,104,104,104,104,104,104,104,104,104,104,104,104,104,104,104, +104,104,104,104,104,104,104,104,104,104,104,104,104,104,104,104, +104,104,104,104,104,104,104,104,104,104,104,104,104,104,104,104, +104,104,104,104,104,104,104,104,104,104,104,104,104,104,104,104, +104,104,104,104,104,104,104,104,104,104,104,104,104,104,104,104, +104,104,104,104,104,104,104,104,104,104,104,104,104,104,104,104, +104,104,104,104,104,104,104,104,104,104,104,104,104,104,104,104, + +/* block 201 */ +104,104,104,104,104,104,104,104,104,104,104,104,104,104,104,104, +104,104,104,104,104,104,104,104,104,104,104,104,104,104,104,104, +104,104,104,104,104,104,104,104,104,104,104,104,104,104,104,104, +104,104,104,104,104,104,104,104,104,104,104,104,104,104,104,104, +104,104,104,104,104,104,104,104,104,104,104,104,104,104,104,104, +104,104,104,104,104,104,104,104,104,104,104,104,104,104,104,104, +104,104,104,104,104,104,104,104,104,104,104,104,104,104,104,104, +426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,426, + +/* block 202 */ +538,538,538,538,538,538,538,538,538,538,538,538,538,538,538,538, +538,538,538,538,538,538,538,538,538,538,538,538,538,538,538,538, +538,538,538,538,538,538,538,538,538,538,538,538,538,538,538,538, +538,538,538,538,538,538,538,538,538,538,538,538,538,538,538,538, +538,538,538,538,538,538,538,538,538,538,538,538,538,538,538,538, +538,538,538,538,538,538,538,538,538,538,538,538,538,538,538,538, +538,538,538,538,538,538,538,538,538,538,538,538,538,538,538,538, +538,538,538,538,538,538,538,538,538,538,538,538,538,538,109,109, + +}; + +#if UCD_BLOCK_SIZE != 128 +#error Please correct UCD_BLOCK_SIZE in pcre_internal.h +#endif +#endif /* SUPPORT_UCP */ + +#endif /* PCRE_INCLUDED */ diff --git a/plugins/Pcre16/src/pcre_version.c b/plugins/Pcre16/src/pcre_version.c new file mode 100644 index 0000000000..ae86ff28bc --- /dev/null +++ b/plugins/Pcre16/src/pcre_version.c @@ -0,0 +1,98 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2012 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains the external function pcre_version(), which returns a +string that identifies the PCRE version that is in use. */ + + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#include "pcre_internal.h" + + +/************************************************* +* Return version string * +*************************************************/ + +/* These macros are the standard way of turning unquoted text into C strings. +They allow macros like PCRE_MAJOR to be defined without quotes, which is +convenient for user programs that want to test its value. */ + +#define STRING(a) # a +#define XSTRING(s) STRING(s) + +/* A problem turned up with PCRE_PRERELEASE, which is defined empty for +production releases. Originally, it was used naively in this code: + + return XSTRING(PCRE_MAJOR) + "." XSTRING(PCRE_MINOR) + XSTRING(PCRE_PRERELEASE) + " " XSTRING(PCRE_DATE); + +However, when PCRE_PRERELEASE is empty, this leads to an attempted expansion of +STRING(). The C standard states: "If (before argument substitution) any +argument consists of no preprocessing tokens, the behavior is undefined." It +turns out the gcc treats this case as a single empty string - which is what we +really want - but Visual C grumbles about the lack of an argument for the +macro. Unfortunately, both are within their rights. To cope with both ways of +handling this, I had resort to some messy hackery that does a test at run time. +I could find no way of detecting that a macro is defined as an empty string at +pre-processor time. This hack uses a standard trick for avoiding calling +the STRING macro with an empty argument when doing the test. */ + +#if defined COMPILE_PCRE8 +PCRE_EXP_DEFN const char * PCRE_CALL_CONVENTION +pcre_version(void) +#elif defined COMPILE_PCRE16 +PCRE_EXP_DEFN const char * PCRE_CALL_CONVENTION +pcre16_version(void) +#elif defined COMPILE_PCRE32 +PCRE_EXP_DEFN const char * PCRE_CALL_CONVENTION +pcre32_version(void) +#endif +{ +return (XSTRING(Z PCRE_PRERELEASE)[1] == 0)? + XSTRING(PCRE_MAJOR.PCRE_MINOR PCRE_DATE) : + XSTRING(PCRE_MAJOR.PCRE_MINOR) XSTRING(PCRE_PRERELEASE PCRE_DATE); +} + +/* End of pcre_version.c */ diff --git a/plugins/Pcre16/src/pcre_xclass.c b/plugins/Pcre16/src/pcre_xclass.c new file mode 100644 index 0000000000..c2b61f0f92 --- /dev/null +++ b/plugins/Pcre16/src/pcre_xclass.c @@ -0,0 +1,268 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2013 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains an internal function that is used to match an extended +class. It is used by both pcre_exec() and pcre_def_exec(). */ + + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#include "pcre_internal.h" + + +/************************************************* +* Match character against an XCLASS * +*************************************************/ + +/* This function is called to match a character against an extended class that +might contain values > 255 and/or Unicode properties. + +Arguments: + c the character + data points to the flag byte of the XCLASS data + +Returns: TRUE if character matches, else FALSE +*/ + +BOOL +PRIV(xclass)(pcre_uint32 c, const pcre_uchar *data, BOOL utf) +{ +pcre_uchar t; +BOOL negated = (*data & XCL_NOT) != 0; + +(void)utf; +#ifdef COMPILE_PCRE8 +/* In 8 bit mode, this must always be TRUE. Help the compiler to know that. */ +utf = TRUE; +#endif + +/* Character values < 256 are matched against a bitmap, if one is present. If +not, we still carry on, because there may be ranges that start below 256 in the +additional data. */ + +if (c < 256) + { + if ((*data & XCL_HASPROP) == 0) + { + if ((*data & XCL_MAP) == 0) return negated; + return (((pcre_uint8 *)(data + 1))[c/8] & (1 << (c&7))) != 0; + } + if ((*data & XCL_MAP) != 0 && + (((pcre_uint8 *)(data + 1))[c/8] & (1 << (c&7))) != 0) + return !negated; /* char found */ + } + +/* First skip the bit map if present. Then match against the list of Unicode +properties or large chars or ranges that end with a large char. We won't ever +encounter XCL_PROP or XCL_NOTPROP when UCP support is not compiled. */ + +if ((*data++ & XCL_MAP) != 0) data += 32 / sizeof(pcre_uchar); + +while ((t = *data++) != XCL_END) + { + pcre_uint32 x, y; + if (t == XCL_SINGLE) + { +#ifdef SUPPORT_UTF + if (utf) + { + GETCHARINC(x, data); /* macro generates multiple statements */ + } + else +#endif + x = *data++; + if (c == x) return !negated; + } + else if (t == XCL_RANGE) + { +#ifdef SUPPORT_UTF + if (utf) + { + GETCHARINC(x, data); /* macro generates multiple statements */ + GETCHARINC(y, data); /* macro generates multiple statements */ + } + else +#endif + { + x = *data++; + y = *data++; + } + if (c >= x && c <= y) return !negated; + } + +#ifdef SUPPORT_UCP + else /* XCL_PROP & XCL_NOTPROP */ + { + const ucd_record *prop = GET_UCD(c); + BOOL isprop = t == XCL_PROP; + + switch(*data) + { + case PT_ANY: + if (isprop) return !negated; + break; + + case PT_LAMP: + if ((prop->chartype == ucp_Lu || prop->chartype == ucp_Ll || + prop->chartype == ucp_Lt) == isprop) return !negated; + break; + + case PT_GC: + if ((data[1] == PRIV(ucp_gentype)[prop->chartype]) == isprop) + return !negated; + break; + + case PT_PC: + if ((data[1] == prop->chartype) == isprop) return !negated; + break; + + case PT_SC: + if ((data[1] == prop->script) == isprop) return !negated; + break; + + case PT_ALNUM: + if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L || + PRIV(ucp_gentype)[prop->chartype] == ucp_N) == isprop) + return !negated; + break; + + /* Perl space used to exclude VT, but from Perl 5.18 it is included, + which means that Perl space and POSIX space are now identical. PCRE + was changed at release 8.34. */ + + case PT_SPACE: /* Perl space */ + case PT_PXSPACE: /* POSIX space */ + switch(c) + { + HSPACE_CASES: + VSPACE_CASES: + if (isprop) return !negated; + break; + + default: + if ((PRIV(ucp_gentype)[prop->chartype] == ucp_Z) == isprop) + return !negated; + break; + } + break; + + case PT_WORD: + if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L || + PRIV(ucp_gentype)[prop->chartype] == ucp_N || c == CHAR_UNDERSCORE) + == isprop) + return !negated; + break; + + case PT_UCNC: + if (c < 0xa0) + { + if ((c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT || + c == CHAR_GRAVE_ACCENT) == isprop) + return !negated; + } + else + { + if ((c < 0xd800 || c > 0xdfff) == isprop) + return !negated; + } + break; + + /* The following three properties can occur only in an XCLASS, as there + is no \p or \P coding for them. */ + + /* Graphic character. Implement this as not Z (space or separator) and + not C (other), except for Cf (format) with a few exceptions. This seems + to be what Perl does. The exceptional characters are: + + U+061C Arabic Letter Mark + U+180E Mongolian Vowel Separator + U+2066 - U+2069 Various "isolate"s + */ + + case PT_PXGRAPH: + if ((PRIV(ucp_gentype)[prop->chartype] != ucp_Z && + (PRIV(ucp_gentype)[prop->chartype] != ucp_C || + (prop->chartype == ucp_Cf && + c != 0x061c && c != 0x180e && (c < 0x2066 || c > 0x2069)) + )) == isprop) + return !negated; + break; + + /* Printable character: same as graphic, with the addition of Zs, i.e. + not Zl and not Zp, and U+180E. */ + + case PT_PXPRINT: + if ((prop->chartype != ucp_Zl && + prop->chartype != ucp_Zp && + (PRIV(ucp_gentype)[prop->chartype] != ucp_C || + (prop->chartype == ucp_Cf && + c != 0x061c && (c < 0x2066 || c > 0x2069)) + )) == isprop) + return !negated; + break; + + /* Punctuation: all Unicode punctuation, plus ASCII characters that + Unicode treats as symbols rather than punctuation, for Perl + compatibility (these are $+<=>^`|~). */ + + case PT_PXPUNCT: + if ((PRIV(ucp_gentype)[prop->chartype] == ucp_P || + (c < 256 && PRIV(ucp_gentype)[prop->chartype] == ucp_S)) == isprop) + return !negated; + break; + + /* This should never occur, but compilers may mutter if there is no + default. */ + + default: + return FALSE; + } + + data += 2; + } +#endif /* SUPPORT_UCP */ + } + +return negated; /* char did not match */ +} + +/* End of pcre_xclass.c */ diff --git a/plugins/Pcre16/src/ucp.h b/plugins/Pcre16/src/ucp.h new file mode 100644 index 0000000000..d8b34bfcc5 --- /dev/null +++ b/plugins/Pcre16/src/ucp.h @@ -0,0 +1,200 @@ +/************************************************* +* Unicode Property Table handler * +*************************************************/ + +#ifndef _UCP_H +#define _UCP_H + +/* This file contains definitions of the property values that are returned by +the UCD access macros. New values that are added for new releases of Unicode +should always be at the end of each enum, for backwards compatibility. + +IMPORTANT: Note also that the specific numeric values of the enums have to be +the same as the values that are generated by the maint/MultiStage2.py script, +where the equivalent property descriptive names are listed in vectors. + +ALSO: The specific values of the first two enums are assumed for the table +called catposstab in pcre_compile.c. */ + +/* These are the general character categories. */ + +enum { + ucp_C, /* Other */ + ucp_L, /* Letter */ + ucp_M, /* Mark */ + ucp_N, /* Number */ + ucp_P, /* Punctuation */ + ucp_S, /* Symbol */ + ucp_Z /* Separator */ +}; + +/* These are the particular character categories. */ + +enum { + ucp_Cc, /* Control */ + ucp_Cf, /* Format */ + ucp_Cn, /* Unassigned */ + ucp_Co, /* Private use */ + ucp_Cs, /* Surrogate */ + ucp_Ll, /* Lower case letter */ + ucp_Lm, /* Modifier letter */ + ucp_Lo, /* Other letter */ + ucp_Lt, /* Title case letter */ + ucp_Lu, /* Upper case letter */ + ucp_Mc, /* Spacing mark */ + ucp_Me, /* Enclosing mark */ + ucp_Mn, /* Non-spacing mark */ + ucp_Nd, /* Decimal number */ + ucp_Nl, /* Letter number */ + ucp_No, /* Other number */ + ucp_Pc, /* Connector punctuation */ + ucp_Pd, /* Dash punctuation */ + ucp_Pe, /* Close punctuation */ + ucp_Pf, /* Final punctuation */ + ucp_Pi, /* Initial punctuation */ + ucp_Po, /* Other punctuation */ + ucp_Ps, /* Open punctuation */ + ucp_Sc, /* Currency symbol */ + ucp_Sk, /* Modifier symbol */ + ucp_Sm, /* Mathematical symbol */ + ucp_So, /* Other symbol */ + ucp_Zl, /* Line separator */ + ucp_Zp, /* Paragraph separator */ + ucp_Zs /* Space separator */ +}; + +/* These are grapheme break properties. Note that the code for processing them +assumes that the values are less than 16. If more values are added that take +the number to 16 or more, the code will have to be rewritten. */ + +enum { + ucp_gbCR, /* 0 */ + ucp_gbLF, /* 1 */ + ucp_gbControl, /* 2 */ + ucp_gbExtend, /* 3 */ + ucp_gbPrepend, /* 4 */ + ucp_gbSpacingMark, /* 5 */ + ucp_gbL, /* 6 Hangul syllable type L */ + ucp_gbV, /* 7 Hangul syllable type V */ + ucp_gbT, /* 8 Hangul syllable type T */ + ucp_gbLV, /* 9 Hangul syllable type LV */ + ucp_gbLVT, /* 10 Hangul syllable type LVT */ + ucp_gbRegionalIndicator, /* 11 */ + ucp_gbOther /* 12 */ +}; + +/* These are the script identifications. */ + +enum { + ucp_Arabic, + ucp_Armenian, + ucp_Bengali, + ucp_Bopomofo, + ucp_Braille, + ucp_Buginese, + ucp_Buhid, + ucp_Canadian_Aboriginal, + ucp_Cherokee, + ucp_Common, + ucp_Coptic, + ucp_Cypriot, + ucp_Cyrillic, + ucp_Deseret, + ucp_Devanagari, + ucp_Ethiopic, + ucp_Georgian, + ucp_Glagolitic, + ucp_Gothic, + ucp_Greek, + ucp_Gujarati, + ucp_Gurmukhi, + ucp_Han, + ucp_Hangul, + ucp_Hanunoo, + ucp_Hebrew, + ucp_Hiragana, + ucp_Inherited, + ucp_Kannada, + ucp_Katakana, + ucp_Kharoshthi, + ucp_Khmer, + ucp_Lao, + ucp_Latin, + ucp_Limbu, + ucp_Linear_B, + ucp_Malayalam, + ucp_Mongolian, + ucp_Myanmar, + ucp_New_Tai_Lue, + ucp_Ogham, + ucp_Old_Italic, + ucp_Old_Persian, + ucp_Oriya, + ucp_Osmanya, + ucp_Runic, + ucp_Shavian, + ucp_Sinhala, + ucp_Syloti_Nagri, + ucp_Syriac, + ucp_Tagalog, + ucp_Tagbanwa, + ucp_Tai_Le, + ucp_Tamil, + ucp_Telugu, + ucp_Thaana, + ucp_Thai, + ucp_Tibetan, + ucp_Tifinagh, + ucp_Ugaritic, + ucp_Yi, + /* New for Unicode 5.0: */ + ucp_Balinese, + ucp_Cuneiform, + ucp_Nko, + ucp_Phags_Pa, + ucp_Phoenician, + /* New for Unicode 5.1: */ + ucp_Carian, + ucp_Cham, + ucp_Kayah_Li, + ucp_Lepcha, + ucp_Lycian, + ucp_Lydian, + ucp_Ol_Chiki, + ucp_Rejang, + ucp_Saurashtra, + ucp_Sundanese, + ucp_Vai, + /* New for Unicode 5.2: */ + ucp_Avestan, + ucp_Bamum, + ucp_Egyptian_Hieroglyphs, + ucp_Imperial_Aramaic, + ucp_Inscriptional_Pahlavi, + ucp_Inscriptional_Parthian, + ucp_Javanese, + ucp_Kaithi, + ucp_Lisu, + ucp_Meetei_Mayek, + ucp_Old_South_Arabian, + ucp_Old_Turkic, + ucp_Samaritan, + ucp_Tai_Tham, + ucp_Tai_Viet, + /* New for Unicode 6.0.0: */ + ucp_Batak, + ucp_Brahmi, + ucp_Mandaic, + /* New for Unicode 6.1.0: */ + ucp_Chakma, + ucp_Meroitic_Cursive, + ucp_Meroitic_Hieroglyphs, + ucp_Miao, + ucp_Sharada, + ucp_Sora_Sompeng, + ucp_Takri +}; + +#endif + +/* End of ucp.h */ |