- added basic html conversion for receiving (maybe a bit too powerful)

- some bugfixes

git-svn-id: http://mirotr.googlecode.com/svn/trunk@12 eced67a3-f377-a0ae-92ae-d6de1850b05a

17 files changed, 1842 insertions, 0 deletions

diff --git a/ekhtml/testsuite/.deps/tester.Po b/ekhtml/testsuite/.deps/tester.Po
new file mode 100644
index 0000000..9ce06a8
--- /dev/null
+++ b/ekhtml/testsuite/.deps/tester.Po
@@ -0,0 +1 @@
+# dummy
diff --git a/ekhtml/testsuite/Makefile b/ekhtml/testsuite/Makefile
new file mode 100644
index 0000000..5c6b92b
--- /dev/null
+++ b/ekhtml/testsuite/Makefile
@@ -0,0 +1,406 @@
+# Makefile.in generated by automake 1.6.3 from Makefile.am.
+# Generated automatically from Makefile.in by configure.
+
+# Copyright 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002
+# Free Software Foundation, Inc.
+# This Makefile.in is free software; the Free Software Foundation
+# gives unlimited permission to copy and/or distribute it,
+# with or without modifications, as long as this notice is preserved.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY, to the extent permitted by law; without
+# even the implied warranty of MERCHANTABILITY or FITNESS FOR A
+# PARTICULAR PURPOSE.
+
+
+SHELL = /bin/sh
+
+srcdir = .
+top_srcdir = ..
+
+prefix = /usr/local
+exec_prefix = ${prefix}
+
+bindir = ${exec_prefix}/bin
+sbindir = ${exec_prefix}/sbin
+libexecdir = ${exec_prefix}/libexec
+datadir = ${prefix}/share
+sysconfdir = ${prefix}/etc
+sharedstatedir = ${prefix}/com
+localstatedir = ${prefix}/var
+libdir = ${exec_prefix}/lib
+infodir = ${prefix}/info
+mandir = ${prefix}/man
+includedir = ${prefix}/include
+oldincludedir = /usr/include
+pkgdatadir = $(datadir)/ekhtml
+pkglibdir = $(libdir)/ekhtml
+pkgincludedir = $(includedir)/ekhtml
+top_builddir = ..
+
+ACLOCAL = ${SHELL} /z/missing --run aclocal-1.6
+AUTOCONF = ${SHELL} /z/missing --run autoconf
+AUTOMAKE = ${SHELL} /z/missing --run automake-1.6
+AUTOHEADER = ${SHELL} /z/missing --run autoheader
+
+am__cd = CDPATH="$${ZSH_VERSION+.}$(PATH_SEPARATOR)" && cd
+INSTALL = /bin/install -c
+INSTALL_PROGRAM = ${INSTALL}
+INSTALL_DATA = ${INSTALL} -m 644
+install_sh_DATA = $(install_sh) -c -m 644
+install_sh_PROGRAM = $(install_sh) -c
+install_sh_SCRIPT = $(install_sh) -c
+INSTALL_SCRIPT = ${INSTALL}
+INSTALL_HEADER = $(INSTALL_DATA)
+transform = s,x,x,
+NORMAL_INSTALL = :
+PRE_INSTALL = :
+POST_INSTALL = :
+NORMAL_UNINSTALL = :
+PRE_UNINSTALL = :
+POST_UNINSTALL = :
+host_alias = 
+host_triplet = i686-pc-mingw32
+
+EXEEXT = .exe
+OBJEXT = o
+PATH_SEPARATOR = :
+AMTAR = ${SHELL} /z/missing --run tar
+AS = @AS@
+AWK = gawk
+CC = gcc
+DEPDIR = .deps
+DLLTOOL = @DLLTOOL@
+ECHO = echo
+INSTALL_STRIP_PROGRAM = ${SHELL} $(install_sh) -c -s
+LIBTOOL = $(SHELL) $(top_builddir)/libtool
+LN_S = ln -s
+MAINT = #
+OBJDUMP = @OBJDUMP@
+PACKAGE = ekhtml
+RANLIB = ranlib
+STRIP = strip
+VERSION = 0.3.2
+am__include = include
+am__quote = 
+install_sh = /z/install-sh
+EKHTML_LIB = $(top_srcdir)/src/libekhtml.la
+
+EXTRA_DIST = \
+	ek_sgmllib.py \
+	gen_html.py \
+	plparser.pl \
+	pyparser.py \
+	test_basic.sh \
+	test_bogus_feedsize.sh \
+	test_crazypage.sh \
+	tstpages
+
+
+noinst_PROGRAMS = tester
+
+tester_SOURCES = tester.c
+tester_LDADD = $(EKHTML_LIB) 
+tester_LDFLAGS = -static
+tester_DEPENDENCIES = $(EKHTML_LIB)
+
+TESTS = test_basic.sh test_crazypage.sh test_bogus_feedsize.sh
+subdir = testsuite
+mkinstalldirs = $(SHELL) $(top_srcdir)/mkinstalldirs
+CONFIG_HEADER = $(top_builddir)/include/ekhtml_config.h
+CONFIG_CLEAN_FILES =
+noinst_PROGRAMS = tester$(EXEEXT)
+PROGRAMS = $(noinst_PROGRAMS)
+
+am_tester_OBJECTS = tester.$(OBJEXT)
+tester_OBJECTS = $(am_tester_OBJECTS)
+
+DEFS = -DHAVE_CONFIG_H
+DEFAULT_INCLUDES =  -I. -I$(srcdir) -I$(top_builddir)/include
+CPPFLAGS = 
+LDFLAGS = 
+LIBS = 
+depcomp = $(SHELL) $(top_srcdir)/depcomp
+am__depfiles_maybe = depfiles
+DEP_FILES = ./$(DEPDIR)/tester.Po
+COMPILE = $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) \
+	$(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS)
+LTCOMPILE = $(LIBTOOL) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) \
+	$(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS)
+CCLD = $(CC)
+LINK = $(LIBTOOL) --mode=link $(CCLD) $(AM_CFLAGS) $(CFLAGS) \
+	$(AM_LDFLAGS) $(LDFLAGS) -o $@
+CFLAGS = -g -O2
+DIST_SOURCES = $(tester_SOURCES)
+DIST_COMMON = Makefile.am Makefile.in
+SOURCES = $(tester_SOURCES)
+
+all: all-am
+
+.SUFFIXES:
+.SUFFIXES: .c .lo .o .obj
+$(srcdir)/Makefile.in: # Makefile.am  $(top_srcdir)/configure.in $(ACLOCAL_M4)
+	cd $(top_srcdir) && \
+	  $(AUTOMAKE) --gnu  testsuite/Makefile
+Makefile: # $(srcdir)/Makefile.in  $(top_builddir)/config.status
+	cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe)
+
+clean-noinstPROGRAMS:
+	@list='$(noinst_PROGRAMS)'; for p in $$list; do \
+	  f=`echo $$p|sed 's/$(EXEEXT)$$//'`; \
+	  echo " rm -f $$p $$f"; \
+	  rm -f $$p $$f ; \
+	done
+tester$(EXEEXT): $(tester_OBJECTS) $(tester_DEPENDENCIES) 
+	@rm -f tester$(EXEEXT)
+	$(LINK) $(tester_LDFLAGS) $(tester_OBJECTS) $(tester_LDADD) $(LIBS)
+
+mostlyclean-compile:
+	-rm -f *.$(OBJEXT) core *.core
+
+distclean-compile:
+	-rm -f *.tab.c
+
+include ./$(DEPDIR)/tester.Po
+
+distclean-depend:
+	-rm -rf ./$(DEPDIR)
+
+.c.o:
+	source='$<' object='$@' libtool=no \
+	depfile='$(DEPDIR)/$*.Po' tmpdepfile='$(DEPDIR)/$*.TPo' \
+	$(CCDEPMODE) $(depcomp) \
+	$(COMPILE) -c `test -f '$<' || echo '$(srcdir)/'`$<
+
+.c.obj:
+	source='$<' object='$@' libtool=no \
+	depfile='$(DEPDIR)/$*.Po' tmpdepfile='$(DEPDIR)/$*.TPo' \
+	$(CCDEPMODE) $(depcomp) \
+	$(COMPILE) -c `cygpath -w $<`
+
+.c.lo:
+	source='$<' object='$@' libtool=yes \
+	depfile='$(DEPDIR)/$*.Plo' tmpdepfile='$(DEPDIR)/$*.TPlo' \
+	$(CCDEPMODE) $(depcomp) \
+	$(LTCOMPILE) -c -o $@ `test -f '$<' || echo '$(srcdir)/'`$<
+CCDEPMODE = depmode=gcc3
+
+mostlyclean-libtool:
+	-rm -f *.lo
+
+clean-libtool:
+	-rm -rf .libs _libs
+
+distclean-libtool:
+	-rm -f libtool
+uninstall-info-am:
+
+ETAGS = etags
+ETAGSFLAGS =
+
+tags: TAGS
+
+ID: $(HEADERS) $(SOURCES) $(LISP) $(TAGS_FILES)
+	list='$(SOURCES) $(HEADERS) $(LISP) $(TAGS_FILES)'; \
+	unique=`for i in $$list; do \
+	    if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \
+	  done | \
+	  $(AWK) '    { files[$$0] = 1; } \
+	       END { for (i in files) print i; }'`; \
+	mkid -fID $$unique
+
+TAGS:  $(HEADERS) $(SOURCES)  $(TAGS_DEPENDENCIES) \
+		$(TAGS_FILES) $(LISP)
+	tags=; \
+	here=`pwd`; \
+	list='$(SOURCES) $(HEADERS)  $(LISP) $(TAGS_FILES)'; \
+	unique=`for i in $$list; do \
+	    if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \
+	  done | \
+	  $(AWK) '    { files[$$0] = 1; } \
+	       END { for (i in files) print i; }'`; \
+	test -z "$(ETAGS_ARGS)$$tags$$unique" \
+	  || $(ETAGS) $(ETAGSFLAGS) $(AM_ETAGSFLAGS) $(ETAGS_ARGS) \
+	     $$tags $$unique
+
+GTAGS:
+	here=`$(am__cd) $(top_builddir) && pwd` \
+	  && cd $(top_srcdir) \
+	  && gtags -i $(GTAGS_ARGS) $$here
+
+distclean-tags:
+	-rm -f TAGS ID GTAGS GRTAGS GSYMS GPATH
+
+check-TESTS: $(TESTS)
+	@failed=0; all=0; xfail=0; xpass=0; \
+	srcdir=$(srcdir); export srcdir; \
+	list='$(TESTS)'; \
+	if test -n "$$list"; then \
+	  for tst in $$list; do \
+	    if test -f ./$$tst; then dir=./; \
+	    elif test -f $$tst; then dir=; \
+	    else dir="$(srcdir)/"; fi; \
+	    if $(TESTS_ENVIRONMENT) $${dir}$$tst; then \
+	      all=`expr $$all + 1`; \
+	      case " $(XFAIL_TESTS) " in \
+	      *" $$tst "*) \
+	        xpass=`expr $$xpass + 1`; \
+	        failed=`expr $$failed + 1`; \
+	        echo "XPASS: $$tst"; \
+	      ;; \
+	      *) \
+	        echo "PASS: $$tst"; \
+	      ;; \
+	      esac; \
+	    elif test $$? -ne 77; then \
+	      all=`expr $$all + 1`; \
+	      case " $(XFAIL_TESTS) " in \
+	      *" $$tst "*) \
+	        xfail=`expr $$xfail + 1`; \
+	        echo "XFAIL: $$tst"; \
+	      ;; \
+	      *) \
+	        failed=`expr $$failed + 1`; \
+	        echo "FAIL: $$tst"; \
+	      ;; \
+	      esac; \
+	    fi; \
+	  done; \
+	  if test "$$failed" -eq 0; then \
+	    if test "$$xfail" -eq 0; then \
+	      banner="All $$all tests passed"; \
+	    else \
+	      banner="All $$all tests behaved as expected ($$xfail expected failures)"; \
+	    fi; \
+	  else \
+	    if test "$$xpass" -eq 0; then \
+	      banner="$$failed of $$all tests failed"; \
+	    else \
+	      banner="$$failed of $$all tests did not behave as expected ($$xpass unexpected passes)"; \
+	    fi; \
+	  fi; \
+	  dashes=`echo "$$banner" | sed s/./=/g`; \
+	  echo "$$dashes"; \
+	  echo "$$banner"; \
+	  echo "$$dashes"; \
+	  test "$$failed" -eq 0; \
+	else :; fi
+DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST)
+
+top_distdir = ..
+distdir = $(top_distdir)/$(PACKAGE)-$(VERSION)
+
+distdir: $(DISTFILES)
+	@list='$(DISTFILES)'; for file in $$list; do \
+	  if test -f $$file || test -d $$file; then d=.; else d=$(srcdir); fi; \
+	  dir=`echo "$$file" | sed -e 's,/[^/]*$$,,'`; \
+	  if test "$$dir" != "$$file" && test "$$dir" != "."; then \
+	    dir="/$$dir"; \
+	    $(mkinstalldirs) "$(distdir)$$dir"; \
+	  else \
+	    dir=''; \
+	  fi; \
+	  if test -d $$d/$$file; then \
+	    if test -d $(srcdir)/$$file && test $$d != $(srcdir); then \
+	      cp -pR $(srcdir)/$$file $(distdir)$$dir || exit 1; \
+	    fi; \
+	    cp -pR $$d/$$file $(distdir)$$dir || exit 1; \
+	  else \
+	    test -f $(distdir)/$$file \
+	    || cp -p $$d/$$file $(distdir)/$$file \
+	    || exit 1; \
+	  fi; \
+	done
+	$(MAKE) $(AM_MAKEFLAGS) \
+	  top_distdir="${top_distdir}" distdir="$(distdir)" \
+	  dist-hook
+check-am: all-am
+	$(MAKE) $(AM_MAKEFLAGS) check-TESTS
+check: check-am
+all-am: Makefile $(PROGRAMS)
+
+installdirs:
+
+install: install-am
+install-exec: install-exec-am
+install-data: install-data-am
+uninstall: uninstall-am
+
+install-am: all-am
+	@$(MAKE) $(AM_MAKEFLAGS) install-exec-am install-data-am
+
+installcheck: installcheck-am
+install-strip:
+	$(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \
+	  INSTALL_STRIP_FLAG=-s \
+	  `test -z '$(STRIP)' || \
+	    echo "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'"` install
+mostlyclean-generic:
+
+clean-generic:
+
+distclean-generic:
+	-rm -f Makefile $(CONFIG_CLEAN_FILES)
+
+maintainer-clean-generic:
+	@echo "This command is intended for maintainers to use"
+	@echo "it deletes files that may require special tools to rebuild."
+clean: clean-am
+
+clean-am: clean-generic clean-libtool clean-noinstPROGRAMS \
+	mostlyclean-am
+
+distclean: distclean-am
+
+distclean-am: clean-am distclean-compile distclean-depend \
+	distclean-generic distclean-libtool distclean-tags
+
+dvi: dvi-am
+
+dvi-am:
+
+info: info-am
+
+info-am:
+
+install-data-am:
+
+install-exec-am:
+
+install-info: install-info-am
+
+install-man:
+
+installcheck-am:
+
+maintainer-clean: maintainer-clean-am
+
+maintainer-clean-am: distclean-am maintainer-clean-generic
+
+mostlyclean: mostlyclean-am
+
+mostlyclean-am: mostlyclean-compile mostlyclean-generic \
+	mostlyclean-libtool
+
+uninstall-am: uninstall-info-am
+
+.PHONY: GTAGS all all-am check check-TESTS check-am clean clean-generic \
+	clean-libtool clean-noinstPROGRAMS distclean distclean-compile \
+	distclean-depend distclean-generic distclean-libtool \
+	distclean-tags distdir dvi dvi-am info info-am install \
+	install-am install-data install-data-am install-exec \
+	install-exec-am install-info install-info-am install-man \
+	install-strip installcheck installcheck-am installdirs \
+	maintainer-clean maintainer-clean-generic mostlyclean \
+	mostlyclean-compile mostlyclean-generic mostlyclean-libtool \
+	tags uninstall uninstall-am uninstall-info-am
+
+
+$(EKHTML_LIB):
+	cd $(top_srcdir)/src && $(MAKE)
+
+dist-hook:
+	rm -rf `find $(distdir)/tstpages -name CVS`
+# Tell versions [3.59,3.63) of GNU make to not export all variables.
+# Otherwise a system limit (for SysV at least) may be exceeded.
+.NOEXPORT:
diff --git a/ekhtml/testsuite/Makefile.am b/ekhtml/testsuite/Makefile.am
new file mode 100644
index 0000000..adbda98
--- /dev/null
+++ b/ekhtml/testsuite/Makefile.am
@@ -0,0 +1,26 @@
+EKHTML_LIB = $(top_srcdir)/src/libekhtml.la
+
+EXTRA_DIST = \
+	ek_sgmllib.py \
+	gen_html.py \
+	plparser.pl \
+	pyparser.py \
+	test_basic.sh \
+	test_bogus_feedsize.sh \
+	test_crazypage.sh \
+	tstpages
+
+noinst_PROGRAMS = tester
+
+tester_SOURCES      = tester.c
+tester_LDADD        = $(EKHTML_LIB) 
+tester_LDFLAGS      = -static
+tester_DEPENDENCIES = $(EKHTML_LIB)
+
+$(EKHTML_LIB):
+	cd $(top_srcdir)/src && $(MAKE)
+
+TESTS = test_basic.sh test_crazypage.sh test_bogus_feedsize.sh
+
+dist-hook:
+	rm -rf `find $(distdir)/tstpages -name CVS`
diff --git a/ekhtml/testsuite/Makefile.in b/ekhtml/testsuite/Makefile.in
new file mode 100644
index 0000000..0cb60d3
--- /dev/null
+++ b/ekhtml/testsuite/Makefile.in
@@ -0,0 +1,406 @@
+# Makefile.in generated by automake 1.6.3 from Makefile.am.
+# @configure_input@
+
+# Copyright 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002
+# Free Software Foundation, Inc.
+# This Makefile.in is free software; the Free Software Foundation
+# gives unlimited permission to copy and/or distribute it,
+# with or without modifications, as long as this notice is preserved.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY, to the extent permitted by law; without
+# even the implied warranty of MERCHANTABILITY or FITNESS FOR A
+# PARTICULAR PURPOSE.
+
+@SET_MAKE@
+SHELL = @SHELL@
+
+srcdir = @srcdir@
+top_srcdir = @top_srcdir@
+VPATH = @srcdir@
+prefix = @prefix@
+exec_prefix = @exec_prefix@
+
+bindir = @bindir@
+sbindir = @sbindir@
+libexecdir = @libexecdir@
+datadir = @datadir@
+sysconfdir = @sysconfdir@
+sharedstatedir = @sharedstatedir@
+localstatedir = @localstatedir@
+libdir = @libdir@
+infodir = @infodir@
+mandir = @mandir@
+includedir = @includedir@
+oldincludedir = /usr/include
+pkgdatadir = $(datadir)/@PACKAGE@
+pkglibdir = $(libdir)/@PACKAGE@
+pkgincludedir = $(includedir)/@PACKAGE@
+top_builddir = ..
+
+ACLOCAL = @ACLOCAL@
+AUTOCONF = @AUTOCONF@
+AUTOMAKE = @AUTOMAKE@
+AUTOHEADER = @AUTOHEADER@
+
+am__cd = CDPATH="$${ZSH_VERSION+.}$(PATH_SEPARATOR)" && cd
+INSTALL = @INSTALL@
+INSTALL_PROGRAM = @INSTALL_PROGRAM@
+INSTALL_DATA = @INSTALL_DATA@
+install_sh_DATA = $(install_sh) -c -m 644
+install_sh_PROGRAM = $(install_sh) -c
+install_sh_SCRIPT = $(install_sh) -c
+INSTALL_SCRIPT = @INSTALL_SCRIPT@
+INSTALL_HEADER = $(INSTALL_DATA)
+transform = @program_transform_name@
+NORMAL_INSTALL = :
+PRE_INSTALL = :
+POST_INSTALL = :
+NORMAL_UNINSTALL = :
+PRE_UNINSTALL = :
+POST_UNINSTALL = :
+host_alias = @host_alias@
+host_triplet = @host@
+
+EXEEXT = @EXEEXT@
+OBJEXT = @OBJEXT@
+PATH_SEPARATOR = @PATH_SEPARATOR@
+AMTAR = @AMTAR@
+AS = @AS@
+AWK = @AWK@
+CC = @CC@
+DEPDIR = @DEPDIR@
+DLLTOOL = @DLLTOOL@
+ECHO = @ECHO@
+INSTALL_STRIP_PROGRAM = @INSTALL_STRIP_PROGRAM@
+LIBTOOL = @LIBTOOL@
+LN_S = @LN_S@
+MAINT = @MAINT@
+OBJDUMP = @OBJDUMP@
+PACKAGE = @PACKAGE@
+RANLIB = @RANLIB@
+STRIP = @STRIP@
+VERSION = @VERSION@
+am__include = @am__include@
+am__quote = @am__quote@
+install_sh = @install_sh@
+EKHTML_LIB = $(top_srcdir)/src/libekhtml.la
+
+EXTRA_DIST = \
+	ek_sgmllib.py \
+	gen_html.py \
+	plparser.pl \
+	pyparser.py \
+	test_basic.sh \
+	test_bogus_feedsize.sh \
+	test_crazypage.sh \
+	tstpages
+
+
+noinst_PROGRAMS = tester
+
+tester_SOURCES = tester.c
+tester_LDADD = $(EKHTML_LIB) 
+tester_LDFLAGS = -static
+tester_DEPENDENCIES = $(EKHTML_LIB)
+
+TESTS = test_basic.sh test_crazypage.sh test_bogus_feedsize.sh
+subdir = testsuite
+mkinstalldirs = $(SHELL) $(top_srcdir)/mkinstalldirs
+CONFIG_HEADER = $(top_builddir)/include/ekhtml_config.h
+CONFIG_CLEAN_FILES =
+noinst_PROGRAMS = tester$(EXEEXT)
+PROGRAMS = $(noinst_PROGRAMS)
+
+am_tester_OBJECTS = tester.$(OBJEXT)
+tester_OBJECTS = $(am_tester_OBJECTS)
+
+DEFS = @DEFS@
+DEFAULT_INCLUDES =  -I. -I$(srcdir) -I$(top_builddir)/include
+CPPFLAGS = @CPPFLAGS@
+LDFLAGS = @LDFLAGS@
+LIBS = @LIBS@
+depcomp = $(SHELL) $(top_srcdir)/depcomp
+am__depfiles_maybe = depfiles
+@AMDEP_TRUE@DEP_FILES = ./$(DEPDIR)/tester.Po
+COMPILE = $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) \
+	$(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS)
+LTCOMPILE = $(LIBTOOL) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) \
+	$(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS)
+CCLD = $(CC)
+LINK = $(LIBTOOL) --mode=link $(CCLD) $(AM_CFLAGS) $(CFLAGS) \
+	$(AM_LDFLAGS) $(LDFLAGS) -o $@
+CFLAGS = @CFLAGS@
+DIST_SOURCES = $(tester_SOURCES)
+DIST_COMMON = Makefile.am Makefile.in
+SOURCES = $(tester_SOURCES)
+
+all: all-am
+
+.SUFFIXES:
+.SUFFIXES: .c .lo .o .obj
+$(srcdir)/Makefile.in: @MAINTAINER_MODE_TRUE@ Makefile.am  $(top_srcdir)/configure.in $(ACLOCAL_M4)
+	cd $(top_srcdir) && \
+	  $(AUTOMAKE) --gnu  testsuite/Makefile
+Makefile: @MAINTAINER_MODE_TRUE@ $(srcdir)/Makefile.in  $(top_builddir)/config.status
+	cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe)
+
+clean-noinstPROGRAMS:
+	@list='$(noinst_PROGRAMS)'; for p in $$list; do \
+	  f=`echo $$p|sed 's/$(EXEEXT)$$//'`; \
+	  echo " rm -f $$p $$f"; \
+	  rm -f $$p $$f ; \
+	done
+tester$(EXEEXT): $(tester_OBJECTS) $(tester_DEPENDENCIES) 
+	@rm -f tester$(EXEEXT)
+	$(LINK) $(tester_LDFLAGS) $(tester_OBJECTS) $(tester_LDADD) $(LIBS)
+
+mostlyclean-compile:
+	-rm -f *.$(OBJEXT) core *.core
+
+distclean-compile:
+	-rm -f *.tab.c
+
+@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/tester.Po@am__quote@
+
+distclean-depend:
+	-rm -rf ./$(DEPDIR)
+
+.c.o:
+@AMDEP_TRUE@	source='$<' object='$@' libtool=no @AMDEPBACKSLASH@
+@AMDEP_TRUE@	depfile='$(DEPDIR)/$*.Po' tmpdepfile='$(DEPDIR)/$*.TPo' @AMDEPBACKSLASH@
+@AMDEP_TRUE@	$(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@
+	$(COMPILE) -c `test -f '$<' || echo '$(srcdir)/'`$<
+
+.c.obj:
+@AMDEP_TRUE@	source='$<' object='$@' libtool=no @AMDEPBACKSLASH@
+@AMDEP_TRUE@	depfile='$(DEPDIR)/$*.Po' tmpdepfile='$(DEPDIR)/$*.TPo' @AMDEPBACKSLASH@
+@AMDEP_TRUE@	$(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@
+	$(COMPILE) -c `cygpath -w $<`
+
+.c.lo:
+@AMDEP_TRUE@	source='$<' object='$@' libtool=yes @AMDEPBACKSLASH@
+@AMDEP_TRUE@	depfile='$(DEPDIR)/$*.Plo' tmpdepfile='$(DEPDIR)/$*.TPlo' @AMDEPBACKSLASH@
+@AMDEP_TRUE@	$(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@
+	$(LTCOMPILE) -c -o $@ `test -f '$<' || echo '$(srcdir)/'`$<
+CCDEPMODE = @CCDEPMODE@
+
+mostlyclean-libtool:
+	-rm -f *.lo
+
+clean-libtool:
+	-rm -rf .libs _libs
+
+distclean-libtool:
+	-rm -f libtool
+uninstall-info-am:
+
+ETAGS = etags
+ETAGSFLAGS =
+
+tags: TAGS
+
+ID: $(HEADERS) $(SOURCES) $(LISP) $(TAGS_FILES)
+	list='$(SOURCES) $(HEADERS) $(LISP) $(TAGS_FILES)'; \
+	unique=`for i in $$list; do \
+	    if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \
+	  done | \
+	  $(AWK) '    { files[$$0] = 1; } \
+	       END { for (i in files) print i; }'`; \
+	mkid -fID $$unique
+
+TAGS:  $(HEADERS) $(SOURCES)  $(TAGS_DEPENDENCIES) \
+		$(TAGS_FILES) $(LISP)
+	tags=; \
+	here=`pwd`; \
+	list='$(SOURCES) $(HEADERS)  $(LISP) $(TAGS_FILES)'; \
+	unique=`for i in $$list; do \
+	    if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \
+	  done | \
+	  $(AWK) '    { files[$$0] = 1; } \
+	       END { for (i in files) print i; }'`; \
+	test -z "$(ETAGS_ARGS)$$tags$$unique" \
+	  || $(ETAGS) $(ETAGSFLAGS) $(AM_ETAGSFLAGS) $(ETAGS_ARGS) \
+	     $$tags $$unique
+
+GTAGS:
+	here=`$(am__cd) $(top_builddir) && pwd` \
+	  && cd $(top_srcdir) \
+	  && gtags -i $(GTAGS_ARGS) $$here
+
+distclean-tags:
+	-rm -f TAGS ID GTAGS GRTAGS GSYMS GPATH
+
+check-TESTS: $(TESTS)
+	@failed=0; all=0; xfail=0; xpass=0; \
+	srcdir=$(srcdir); export srcdir; \
+	list='$(TESTS)'; \
+	if test -n "$$list"; then \
+	  for tst in $$list; do \
+	    if test -f ./$$tst; then dir=./; \
+	    elif test -f $$tst; then dir=; \
+	    else dir="$(srcdir)/"; fi; \
+	    if $(TESTS_ENVIRONMENT) $${dir}$$tst; then \
+	      all=`expr $$all + 1`; \
+	      case " $(XFAIL_TESTS) " in \
+	      *" $$tst "*) \
+	        xpass=`expr $$xpass + 1`; \
+	        failed=`expr $$failed + 1`; \
+	        echo "XPASS: $$tst"; \
+	      ;; \
+	      *) \
+	        echo "PASS: $$tst"; \
+	      ;; \
+	      esac; \
+	    elif test $$? -ne 77; then \
+	      all=`expr $$all + 1`; \
+	      case " $(XFAIL_TESTS) " in \
+	      *" $$tst "*) \
+	        xfail=`expr $$xfail + 1`; \
+	        echo "XFAIL: $$tst"; \
+	      ;; \
+	      *) \
+	        failed=`expr $$failed + 1`; \
+	        echo "FAIL: $$tst"; \
+	      ;; \
+	      esac; \
+	    fi; \
+	  done; \
+	  if test "$$failed" -eq 0; then \
+	    if test "$$xfail" -eq 0; then \
+	      banner="All $$all tests passed"; \
+	    else \
+	      banner="All $$all tests behaved as expected ($$xfail expected failures)"; \
+	    fi; \
+	  else \
+	    if test "$$xpass" -eq 0; then \
+	      banner="$$failed of $$all tests failed"; \
+	    else \
+	      banner="$$failed of $$all tests did not behave as expected ($$xpass unexpected passes)"; \
+	    fi; \
+	  fi; \
+	  dashes=`echo "$$banner" | sed s/./=/g`; \
+	  echo "$$dashes"; \
+	  echo "$$banner"; \
+	  echo "$$dashes"; \
+	  test "$$failed" -eq 0; \
+	else :; fi
+DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST)
+
+top_distdir = ..
+distdir = $(top_distdir)/$(PACKAGE)-$(VERSION)
+
+distdir: $(DISTFILES)
+	@list='$(DISTFILES)'; for file in $$list; do \
+	  if test -f $$file || test -d $$file; then d=.; else d=$(srcdir); fi; \
+	  dir=`echo "$$file" | sed -e 's,/[^/]*$$,,'`; \
+	  if test "$$dir" != "$$file" && test "$$dir" != "."; then \
+	    dir="/$$dir"; \
+	    $(mkinstalldirs) "$(distdir)$$dir"; \
+	  else \
+	    dir=''; \
+	  fi; \
+	  if test -d $$d/$$file; then \
+	    if test -d $(srcdir)/$$file && test $$d != $(srcdir); then \
+	      cp -pR $(srcdir)/$$file $(distdir)$$dir || exit 1; \
+	    fi; \
+	    cp -pR $$d/$$file $(distdir)$$dir || exit 1; \
+	  else \
+	    test -f $(distdir)/$$file \
+	    || cp -p $$d/$$file $(distdir)/$$file \
+	    || exit 1; \
+	  fi; \
+	done
+	$(MAKE) $(AM_MAKEFLAGS) \
+	  top_distdir="${top_distdir}" distdir="$(distdir)" \
+	  dist-hook
+check-am: all-am
+	$(MAKE) $(AM_MAKEFLAGS) check-TESTS
+check: check-am
+all-am: Makefile $(PROGRAMS)
+
+installdirs:
+
+install: install-am
+install-exec: install-exec-am
+install-data: install-data-am
+uninstall: uninstall-am
+
+install-am: all-am
+	@$(MAKE) $(AM_MAKEFLAGS) install-exec-am install-data-am
+
+installcheck: installcheck-am
+install-strip:
+	$(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \
+	  INSTALL_STRIP_FLAG=-s \
+	  `test -z '$(STRIP)' || \
+	    echo "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'"` install
+mostlyclean-generic:
+
+clean-generic:
+
+distclean-generic:
+	-rm -f Makefile $(CONFIG_CLEAN_FILES)
+
+maintainer-clean-generic:
+	@echo "This command is intended for maintainers to use"
+	@echo "it deletes files that may require special tools to rebuild."
+clean: clean-am
+
+clean-am: clean-generic clean-libtool clean-noinstPROGRAMS \
+	mostlyclean-am
+
+distclean: distclean-am
+
+distclean-am: clean-am distclean-compile distclean-depend \
+	distclean-generic distclean-libtool distclean-tags
+
+dvi: dvi-am
+
+dvi-am:
+
+info: info-am
+
+info-am:
+
+install-data-am:
+
+install-exec-am:
+
+install-info: install-info-am
+
+install-man:
+
+installcheck-am:
+
+maintainer-clean: maintainer-clean-am
+
+maintainer-clean-am: distclean-am maintainer-clean-generic
+
+mostlyclean: mostlyclean-am
+
+mostlyclean-am: mostlyclean-compile mostlyclean-generic \
+	mostlyclean-libtool
+
+uninstall-am: uninstall-info-am
+
+.PHONY: GTAGS all all-am check check-TESTS check-am clean clean-generic \
+	clean-libtool clean-noinstPROGRAMS distclean distclean-compile \
+	distclean-depend distclean-generic distclean-libtool \
+	distclean-tags distdir dvi dvi-am info info-am install \
+	install-am install-data install-data-am install-exec \
+	install-exec-am install-info install-info-am install-man \
+	install-strip installcheck installcheck-am installdirs \
+	maintainer-clean maintainer-clean-generic mostlyclean \
+	mostlyclean-compile mostlyclean-generic mostlyclean-libtool \
+	tags uninstall uninstall-am uninstall-info-am
+
+
+$(EKHTML_LIB):
+	cd $(top_srcdir)/src && $(MAKE)
+
+dist-hook:
+	rm -rf `find $(distdir)/tstpages -name CVS`
+# Tell versions [3.59,3.63) of GNU make to not export all variables.
+# Otherwise a system limit (for SysV at least) may be exceeded.
+.NOEXPORT:
diff --git a/ekhtml/testsuite/ek_sgmllib.py b/ekhtml/testsuite/ek_sgmllib.py
new file mode 100644
index 0000000..f71496d
--- /dev/null
+++ b/ekhtml/testsuite/ek_sgmllib.py
@@ -0,0 +1,489 @@
+"""A parser for SGML, using the derived class as a static DTD."""
+
+# Stolen from the Python 2.0 distribution and tweaked by JMT
+
+# XXX This only supports those SGML features used by HTML.
+
+# XXX There should be a way to distinguish between PCDATA (parsed
+# character data -- the normal case), RCDATA (replaceable character
+# data -- only char and entity references and end tags are special)
+# and CDATA (character data -- only end tags are special).
+
+
+import re
+import string
+
+
+# Regular expressions used for parsing
+
+interesting = re.compile('[&<]')
+incomplete = re.compile('&([a-zA-Z][a-zA-Z0-9]*|#[0-9]*)?|'
+                           '<([a-zA-Z][^<>]*|'
+                              '/([a-zA-Z][^<>]*)?|'
+                              '![^<>]*)?')
+
+entityref = re.compile('&([a-zA-Z][-.a-zA-Z0-9]*);')
+charref = re.compile('&#([0-9]+)[^0-9];')
+
+starttagopen = re.compile('<[>a-zA-Z]')
+shorttagopen = re.compile('<[a-zA-Z][-.a-zA-Z0-9]*/')
+shorttag = re.compile('<([a-zA-Z][-.a-zA-Z0-9]*)/([^/]*)/')
+piopen = re.compile('<\?')
+piclose = re.compile('>')
+endtagopen = re.compile('</[<>a-zA-Z]')
+endbracket = re.compile('[<>]')
+special = re.compile('<![^<>]*>')
+commentopen = re.compile('<!--')
+commentclose = re.compile('--[%s]*>' % string.whitespace)
+tagfind = re.compile('[a-zA-Z][-.a-zA-Z0-9]*')
+attrfind = re.compile(
+    '[%s]*([a-zA-Z_][-.a-zA-Z_0-9]*)' % string.whitespace
+    + ('([%s]*=[%s]*' % (string.whitespace, string.whitespace))
+    + r'(\'[^\'<>]*[\'<>]|"[^"<>]*["<>]|[-a-zA-Z0-9@./:+*%?!&$\(\)_#=~]*))?')
+
+
+# SGML parser base class -- find tags and call handler functions.
+# Usage: p = SGMLParser(); p.feed(data); ...; p.close().
+# The dtd is defined by deriving a class which defines methods
+# with special names to handle tags: start_foo and end_foo to handle
+# <foo> and </foo>, respectively, or do_foo to handle <foo> by itself.
+# (Tags are converted to lower case for this purpose.)  The data
+# between tags is passed to the parser by calling self.handle_data()
+# with some data as argument (the data may be split up in arbitrary
+# chunks).  Entity references are passed by calling
+# self.handle_entityref() with the entity reference as argument.
+
+class SGMLParser:
+
+    # Interface -- initialize and reset this instance
+    def __init__(self, verbose=0):
+        self.verbose = verbose
+        self.reset()
+
+    # Interface -- reset this instance.  Loses all unprocessed data
+    def reset(self):
+        self.rawdata = ''
+        self.stack = []
+        self.lasttag = '???'
+        self.nomoretags = 0
+        self.literal = 0
+
+    # For derived classes only -- enter literal mode (CDATA) till EOF
+    def setnomoretags(self):
+        self.nomoretags = self.literal = 1
+
+    # For derived classes only -- enter literal mode (CDATA)
+    def setliteral(self, *args):
+        self.literal = 1
+
+    # Interface -- feed some data to the parser.  Call this as
+    # often as you want, with as little or as much text as you
+    # want (may include '\n').  (This just saves the text, all the
+    # processing is done by goahead().)
+    def feed(self, data):
+        self.rawdata = self.rawdata + data
+        self.goahead(0)
+
+    # Interface -- handle the remaining data
+    def close(self):
+        self.goahead(1)
+
+    # Internal -- handle data as far as reasonable.  May leave state
+    # and data to be processed by a subsequent call.  If 'end' is
+    # true, force handling all data as if followed by EOF marker.
+    def goahead(self, end):
+        rawdata = self.rawdata
+        i = 0
+        n = len(rawdata)
+        while i < n:
+            if self.nomoretags:
+                self.handle_data(rawdata[i:n])
+                i = n
+                break
+            match = interesting.search(rawdata, i)
+            if match: j = match.start(0)
+            else: j = n
+            if i < j: self.handle_data(rawdata[i:j])
+            i = j
+            if i == n: break
+            if rawdata[i] == '<':
+                if starttagopen.match(rawdata, i):
+                    if self.literal:
+                        self.handle_data(rawdata[i])
+                        i = i+1
+                        continue
+                    k = self.parse_starttag(i)
+                    if k < 0: break
+                    i = k
+                    continue
+                if endtagopen.match(rawdata, i):
+                    k = self.parse_endtag(i)
+                    if k < 0: break
+                    i =  k
+                    self.literal = 0
+                    continue
+                if commentopen.match(rawdata, i):
+                    if self.literal:
+                        self.handle_data(rawdata[i])
+                        i = i+1
+                        continue
+                    k = self.parse_comment(i)
+                    if k < 0: break
+                    i = i+k
+                    continue
+                if piopen.match(rawdata, i):
+                    if self.literal:
+                        self.handle_data(rawdata[i])
+                        i = i+1
+                        continue
+                    k = self.parse_pi(i)
+                    if k < 0: break
+                    i = i+k
+                    continue                    
+                match = special.match(rawdata, i)
+                if match:
+                    if self.literal:
+                        self.handle_data(rawdata[i])
+                        i = i+1
+                        continue
+                    start = i
+                    i = match.end(0)
+                    self.handle_data(rawdata[start:i])
+                    continue
+            elif rawdata[i] == '&':
+                match = charref.match(rawdata, i)
+                if match:
+                    name = match.group(1)
+                    self.handle_charref(name)
+                    i = match.end(0)
+                    if rawdata[i-1] != ';': i = i-1
+                    continue
+                match = entityref.match(rawdata, i)
+                if match:
+                    name = match.group(1)
+                    self.handle_entityref(name)
+                    i = match.end(0)
+                    if rawdata[i-1] != ';': i = i-1
+                    continue
+            else:
+                raise RuntimeError, 'neither < nor & ??'
+            # We get here only if incomplete matches but
+            # nothing else
+            match = incomplete.match(rawdata, i)
+            if not match:
+                self.handle_data(rawdata[i])
+                i = i+1
+                continue
+            j = match.end(0)
+            if j == n:
+                break # Really incomplete
+            self.handle_data(rawdata[i:j])
+            i = j
+        # end while
+        if end and i < n:
+            self.handle_data(rawdata[i:n])
+            i = n
+        self.rawdata = rawdata[i:]
+        # XXX if end: check for empty stack
+
+    # Internal -- parse comment, return length or -1 if not terminated
+    def parse_comment(self, i):
+        rawdata = self.rawdata
+        if rawdata[i:i+4] <> '<!--':
+            raise RuntimeError, 'unexpected call to handle_comment'
+        match = commentclose.search(rawdata, i+4)
+        if not match:
+            return -1
+        j = match.start(0)
+        self.handle_comment(rawdata[i+4: j])
+        j = match.end(0)
+        return j-i
+
+    # Internal -- parse processing instr, return length or -1 if not terminated
+    def parse_pi(self, i):
+        rawdata = self.rawdata
+        if rawdata[i:i+2] <> '<?':
+            raise RuntimeError, 'unexpected call to handle_pi'
+        match = piclose.search(rawdata, i+2)
+        if not match:
+            return -1
+        j = match.start(0)
+        self.handle_pi(rawdata[i+2: j])
+        j = match.end(0)
+        return j-i
+
+    __starttag_text = None
+    def get_starttag_text(self):
+        return self.__starttag_text
+    
+    # Internal -- handle starttag, return length or -1 if not terminated
+    def parse_starttag(self, i):
+        self.__starttag_text = None
+        start_pos = i
+        rawdata = self.rawdata
+        if shorttagopen.match(rawdata, i):
+            # SGML shorthand: <tag/data/ == <tag>data</tag>
+            # XXX Can data contain &... (entity or char refs)?
+            # XXX Can data contain < or > (tag characters)?
+            # XXX Can there be whitespace before the first /?
+            match = shorttag.match(rawdata, i)
+            if not match:
+                return -1
+            tag, data = match.group(1, 2)
+            self.__starttag_text = '<%s/' % tag
+            tag = string.lower(tag)
+            k = match.end(0)
+            self.finish_shorttag(tag, data)
+            self.__starttag_text = rawdata[start_pos:match.end(1) + 1]
+            return k
+        # XXX The following should skip matching quotes (' or ")
+        match = endbracket.search(rawdata, i+1)
+        if not match:
+            return -1
+        j = match.start(0)
+        # Now parse the data between i+1 and j into a tag and attrs
+        attrs = []
+        if rawdata[i:i+2] == '<>':
+            # SGML shorthand: <> == <last open tag seen>
+            k = j
+            self.handle_data('<>')
+            return k + 1
+        else:
+            match = tagfind.match(rawdata, i+1)
+            if not match:
+                raise RuntimeError, 'unexpected call to parse_starttag'
+            k = match.end(0)
+            tag = string.lower(rawdata[i+1:k])
+            self.lasttag = tag
+        while k < j:
+            match = attrfind.match(rawdata, k)
+            if not match: break
+            attrname, rest, attrvalue = match.group(1, 2, 3)
+            if not rest:
+                attrvalue = attrname
+            elif attrvalue[:1] == '\'' or attrvalue[:1] == '"':
+                attrvalue = attrvalue[1:-1]
+            attrs.append((string.lower(attrname), attrvalue))
+            k = match.end(0)
+        if rawdata[j] == '>':
+            j = j+1
+        self.__starttag_text = rawdata[start_pos:j]
+        self.finish_starttag(tag, attrs)
+        return j
+
+    # Internal -- parse endtag
+    def parse_endtag(self, i):
+        rawdata = self.rawdata
+        match = endbracket.search(rawdata, i+1)
+        if not match:
+            return -1
+        j = match.start(0)
+        tag = string.lower(string.strip(rawdata[i+2:j]))
+        if rawdata[j] == '>':
+            j = j+1
+        self.finish_endtag(tag)
+        return j
+
+    # Internal -- finish parsing of <tag/data/ (same as <tag>data</tag>)
+    def finish_shorttag(self, tag, data):
+        self.finish_starttag(tag, [])
+        self.handle_data(data)
+        self.finish_endtag(tag)
+
+    # Internal -- finish processing of start tag
+    # Return -1 for unknown tag, 0 for open-only tag, 1 for balanced tag
+    def finish_starttag(self, tag, attrs):
+        try:
+            method = getattr(self, 'start_' + tag)
+        except AttributeError:
+            try:
+                method = getattr(self, 'do_' + tag)
+            except AttributeError:
+                self.unknown_starttag(tag, attrs)
+                return -1
+            else:
+                self.handle_starttag(tag, method, attrs)
+                return 0
+        else:
+            self.stack.append(tag)
+            self.handle_starttag(tag, method, attrs)
+            return 1
+
+    # Internal -- finish processing of end tag
+    def finish_endtag(self, tag):
+        if not tag:
+            found = len(self.stack) - 1
+            if found < 0:
+                self.unknown_endtag(tag)
+                return
+        else:
+            if tag not in self.stack:
+                try:
+                    method = getattr(self, 'end_' + tag)
+                except AttributeError:
+                    self.unknown_endtag(tag)
+                else:
+                    self.report_unbalanced(tag)
+                return
+            found = len(self.stack)
+            for i in range(found):
+                if self.stack[i] == tag: found = i
+        while len(self.stack) > found:
+            tag = self.stack[-1]
+            try:
+                method = getattr(self, 'end_' + tag)
+            except AttributeError:
+                method = None
+            if method:
+                self.handle_endtag(tag, method)
+            else:
+                self.unknown_endtag(tag)
+            del self.stack[-1]
+
+    # Overridable -- handle start tag
+    def handle_starttag(self, tag, method, attrs):
+        method(attrs)
+
+    # Overridable -- handle end tag
+    def handle_endtag(self, tag, method):
+        method()
+
+    # Example -- report an unbalanced </...> tag.
+    def report_unbalanced(self, tag):
+        if self.verbose:
+            print '*** Unbalanced </' + tag + '>'
+            print '*** Stack:', self.stack
+
+    # Example -- handle character reference, no need to override
+    def handle_charref(self, name):
+        try:
+            n = string.atoi(name)
+        except string.atoi_error:
+            self.unknown_charref(name)
+            return
+        if not 0 <= n <= 255:
+            self.unknown_charref(name)
+            return
+        self.handle_data(chr(n))
+
+    # Definition of entities -- derived classes may override
+    entitydefs = \
+            {'lt': '<', 'gt': '>', 'amp': '&', 'quot': '"', 'apos': '\''}
+
+    # Example -- handle entity reference, no need to override
+    def handle_entityref(self, name):
+        table = self.entitydefs
+        if table.has_key(name):
+            self.handle_data(table[name])
+        else:
+            self.unknown_entityref(name)
+            return
+
+    # Example -- handle data, should be overridden
+    def handle_data(self, data):
+        pass
+
+    # Example -- handle comment, could be overridden
+    def handle_comment(self, data):
+        pass
+
+    # Example -- handle processing instruction, could be overridden
+    def handle_pi(self, data):
+        pass
+
+    # To be overridden -- handlers for unknown objects
+    def unknown_starttag(self, tag, attrs): pass
+    def unknown_endtag(self, tag): pass
+    def unknown_charref(self, ref): pass
+    def unknown_entityref(self, ref): pass
+
+
+class TestSGMLParser(SGMLParser):
+
+    def __init__(self, verbose=0):
+        self.testdata = ""
+        SGMLParser.__init__(self, verbose)
+
+    def handle_data(self, data):
+        self.testdata = self.testdata + data
+        if len(`self.testdata`) >= 70:
+            self.flush()
+
+    def flush(self):
+        data = self.testdata
+        if data:
+            self.testdata = ""
+            print 'data:', `data`
+
+    def handle_comment(self, data):
+        self.flush()
+        r = `data`
+        if len(r) > 68:
+            r = r[:32] + '...' + r[-32:]
+        print 'comment:', r
+
+    def unknown_starttag(self, tag, attrs):
+        self.flush()
+        if not attrs:
+            print 'start tag: <' + tag + '>'
+        else:
+            print 'start tag: <' + tag,
+            for name, value in attrs:
+                print name + '=' + '"' + value + '"',
+            print '>'
+
+    def unknown_endtag(self, tag):
+        self.flush()
+        print 'end tag: </' + tag + '>'
+
+    def unknown_entityref(self, ref):
+        self.flush()
+        print '*** unknown entity ref: &' + ref + ';'
+
+    def unknown_charref(self, ref):
+        self.flush()
+        print '*** unknown char ref: &#' + ref + ';'
+
+    def close(self):
+        SGMLParser.close(self)
+        self.flush()
+
+
+def test(args = None):
+    import sys
+
+    if not args:
+        args = sys.argv[1:]
+
+    if args and args[0] == '-s':
+        args = args[1:]
+        klass = SGMLParser
+    else:
+        klass = TestSGMLParser
+
+    if args:
+        file = args[0]
+    else:
+        file = 'test.html'
+
+    if file == '-':
+        f = sys.stdin
+    else:
+        try:
+            f = open(file, 'r')
+        except IOError, msg:
+            print file, ":", msg
+            sys.exit(1)
+
+    data = f.read()
+    if f is not sys.stdin:
+        f.close()
+
+    x = klass()
+    for c in data:
+        x.feed(c)
+    x.close()
+
+
+if __name__ == '__main__':
+    test()
diff --git a/ekhtml/testsuite/gen_html.py b/ekhtml/testsuite/gen_html.py
new file mode 100644
index 0000000..dc61ffc
--- /dev/null
+++ b/ekhtml/testsuite/gen_html.py
@@ -0,0 +1,154 @@
+#!/usr/bin/env python
+
+#
+# gen_html: An HTML generation utility
+#
+# This utility is used to generate random HTML for the parser to
+# deal with.  Flags for each of the components allow variations
+# on HTML, so as to spew either valid or invalid HTML.
+#
+
+from string import *
+from ek_sgmllib import tagfind
+from random import randint
+import re, sys
+
+attrname   = re.compile('[a-zA-Z_][-.a-zA-Z_0-9]*')
+attrvalue  = re.compile('[-a-zA-Z0-9@./:+*%?!&$\(\)_#=~]')    
+quotedattrvalueset = digits + '#$%&()*+,-./:;=?@[\]^_`{|}~' 
+attrvalueset = '-@./:+*%?!&$()_#=~*' + letters + digits
+
+DataString = ['In A.D. 2101',
+	      'War was beginning.',
+	      'What happen?',
+              'Somebody set up us the bomb',
+              'We get signal',
+              'What!',
+              'Main screen turn on',
+              "It's You!!",
+              'How are you gentlemen!!',
+              'All your base are belong to us',
+              'You are on the way to destruction',
+              'What you say!!',
+              'You have no chance to survive make your time',
+              'HA HA HA HA ....',
+              "Take off every 'zig'",
+              'You know what you doing',
+              "Move 'zig'",
+              'For great justice']
+
+DataWords = split(join(DataString, ' '))
+
+def get_word(matcher, bogus=0):
+    while 1:
+        res = DataWords[randint(0, len(DataWords)-1)]
+        if not bogus:
+            z = matcher.match(res)
+            if not z or z.end(0) != len(res):
+                continue
+        return res
+    
+def get_tagname(bogus=0):
+    return upper(get_word(tagfind, bogus))
+
+def get_whitespace():
+    return join(map(lambda x: whitespace[randint(0,len(whitespace) - 1)],
+                                         range(randint(0, 3))), '')
+
+def get_attrname(bogus=0):
+    return get_word(attrname, bogus)
+
+
+def get_quoted_attrvalue(bogus=0):
+    quoteidx   = randint(0, 1)
+    quote      = ["'", '"'][quoteidx]
+    otherquote = ["'", '"'][not quoteidx]
+
+    res = quote
+    for i in range(randint(0, 20)):
+        if not randint(0, 5):
+            res = res +quotedattrvalueset[randint(0,len(quotedattrvalueset)-1)]
+        elif not randint(0, 5):
+            res = res + otherquote
+        elif not randint(0, 5):
+            res = res + get_whitespace()
+        else:
+            res = res + get_attrname(0)
+
+    if not bogus:
+        res = res + quote
+    else:
+        res = res + [otherquote, '<', '>'][randint(0, 2)]
+    return res
+
+def get_unquoted_attrvalue(bogus=0):
+    res = ''
+    for i in range(randint(not bogus, 20)):
+        if not randint(0, 5):
+            res = res + get_tagname(bogus)
+        elif bogus and not randint(0, 5):
+            res = res + get_whitespace()
+        else:
+            res = res + attrvalueset[randint(0, len(attrvalueset)-1)]
+
+    return res
+
+def get_starttag(bogus=0):
+    res = '<'
+    if bogus and not randint(0, 10):
+        res = res + whitespace[randint(0, len(whitespace)-1)]
+
+    res = res + get_tagname(bogus)
+    if not randint(0, 5):
+        res = res + get_whitespace()
+
+    for nattrs in range(randint(0, 4)):
+        res = res + whitespace[randint(0, len(whitespace)-1)]
+        res = res + get_whitespace()
+        res = res + get_attrname(bogus)
+        t = randint(0, 1)
+        if t:
+            res = res + get_whitespace() + '=' + get_whitespace() + \
+                  get_quoted_attrvalue(randint(0, bogus))
+        else:
+            res = res + get_whitespace() + '=' + get_whitespace() + \
+                  get_unquoted_attrvalue(randint(0, bogus))
+
+    if bogus and not randint(0, 5):
+        res = res + get_whitespace() + '>'
+    else:
+        res = res + '>'
+
+    return res
+
+def get_comment():
+    res = '<!--'
+
+    for i in range(randint(0, 100)):
+        res = res + get_whitespace()
+        res = res + get_attrname(0)
+        if not randint(0, 5):
+            res = res + '--'
+        elif not randint(0, 10):
+            res = res + '->'
+    res = res + get_whitespace() + '--' + get_whitespace() + '>'
+    return res
+
+def get_endtag():
+    return '</' + get_attrname() + get_whitespace() + '>'
+    
+
+if __name__ == '__main__':
+    if len(sys.argv) < 3:
+        print 'Syntax: %s <# items> <bogus>' % sys.argv[0]
+        sys.exit(1)
+        
+    isbogus = int(sys.argv[2])
+    for i in xrange(int(sys.argv[1])):
+        x = randint(0, 2)
+        if x == 0:
+            print get_starttag(isbogus)
+        elif x == 1:
+            print get_comment()
+        elif x == 2:
+            print get_endtag()
diff --git a/ekhtml/testsuite/plparser.pl b/ekhtml/testsuite/plparser.pl
new file mode 100644
index 0000000..f7ee4a1
--- /dev/null
+++ b/ekhtml/testsuite/plparser.pl
@@ -0,0 +1,38 @@
+#!/usr/bin/perl
+use HTML::Parser();
+use strict;
+sub start_handler
+{
+    my ($tag, $self) = @_;
+    print "START: \"".$tag."\"\n";
+}
+
+sub end_handler
+{
+    my ($tag, $self) = @_;
+    print "END: \"".$tag."\"\n";
+}
+
+sub text_handler
+{
+    my ($text, $self) = @_;
+    print $text;
+}
+
+sub comment_handler
+{
+    my ($text, $self) = @_;
+    print "COMMENT: \"";
+    foreach my $cur_comment (@$text) {
+        print $cur_comment;
+    }
+    print "\"\n";
+}
+
+my $p = HTML::Parser->new(api_version => 3);
+$p->handler( start => \&start_handler, "tagname,self");
+$p->handler( end => \&end_handler, "tagname,self");
+$p->handler( text => \&text_handler, "dtext, self");
+$p->handler( comment => \&comment_handler, "tokens, self");
+$p->parse_file(shift || die) || die $!;
+
diff --git a/ekhtml/testsuite/pyparser.py b/ekhtml/testsuite/pyparser.py
new file mode 100644
index 0000000..a96d999
--- /dev/null
+++ b/ekhtml/testsuite/pyparser.py
@@ -0,0 +1,44 @@
+#! /usr/bin/env python
+
+import ek_sgmllib, sys, string
+
+class myparser(ek_sgmllib.SGMLParser):
+    def __init__(self):
+        ek_sgmllib.SGMLParser.__init__(self)
+
+    def handle_data(self, data):
+        sys.stdout.write(data)
+
+    def start_way(self, attrs):
+        print 'GOT WAY START!'
+        
+    def unknown_starttag(self, tag, attrs):
+        print 'START: "%s"' % tag
+        for i in range(len(attrs) - 1, -1, -1):
+            key, val = attrs[i]
+            print 'ATTRIBUTE: "%s" = "%s"' % (key, val)
+        
+    def unknown_endtag(self, tag):
+        print 'END: "%s"' % tag
+    
+    def handle_comment(self, comment):
+ 	print 'COMMENT: "%s"' % comment
+    
+    def handle_entityref(self, name):
+        self.handle_data('&' + name + ';')
+
+    def handle_charref(self, name):
+        self.handle_data('&#' + name + ';')
+        
+def testit(data):
+    x = myparser()
+    x.feed(data)
+    x.close()
+    
+if __name__ == '__main__':
+    if len(sys.argv) == 1:
+        f = sys.stdin
+    else:
+        f = open(sys.argv[1])
+        
+    testit(f.read())
diff --git a/ekhtml/testsuite/test_basic.sh b/ekhtml/testsuite/test_basic.sh
new file mode 100644
index 0000000..87d2e64
--- /dev/null
+++ b/ekhtml/testsuite/test_basic.sh
@@ -0,0 +1,10 @@
+#! /bin/bash
+
+for i in `find tstpages -type f | sort`
+do
+    echo Testing page: $i
+    ./tester 1 < $i > ek.test
+    ./pyparser.py $i > py.test
+    diff -a -i -u ek.test py.test || exit 1
+done
+
diff --git a/ekhtml/testsuite/test_bogus_feedsize.sh b/ekhtml/testsuite/test_bogus_feedsize.sh
new file mode 100644
index 0000000..12cf9ab
--- /dev/null
+++ b/ekhtml/testsuite/test_bogus_feedsize.sh
@@ -0,0 +1,27 @@
+#! /bin/bash
+#
+# Test the e-k parser to make sure that altering the feedsize doesn't change
+# which tags get recognized.  This is really a boundary condition.
+#
+
+NUMTAGS=1000
+NUMFEED=1024
+
+echo Generating crazy.page with $NUMTAGS tags
+python gen_html.py $NUMTAGS 1 > crazy.page
+
+feedsize=1
+
+echo "Parsing with $NUMFEED different feed sizes"
+while [ $(($feedsize < $NUMFEED)) -eq 1 ]; do
+    ./tester $feedsize < crazy.page > crazy.page.out.$feedsize
+    feedsize=$(($feedsize + 1))
+done
+
+NUMSIZES=`ls -la crazy.page.out.* | awk '{print $5}' | sort | uniq | wc -l`
+if [ $NUMSIZES -ne 1 ] ; then
+    echo 'FAILURE -- Leaving crazy.page.out.* for examination'
+    exit 1
+fi
+
+rm -f crazy.page.out.*
diff --git a/ekhtml/testsuite/test_crazypage.sh b/ekhtml/testsuite/test_crazypage.sh
new file mode 100644
index 0000000..adcd98c
--- /dev/null
+++ b/ekhtml/testsuite/test_crazypage.sh
@@ -0,0 +1,16 @@
+#! /bin/bash
+
+for ntags in 1 10 100 1000
+do
+    for bogus in 0 1
+    do
+	python gen_html.py $ntags $bogus > crazy.page
+	for bytesize in 1 13 162 983 8192
+	do
+	    echo numElements=$ntags allowBogusTags=$bogus feedSize=$bytesize
+	    ./tester $bytesize < crazy.page > ek.test
+	    ./pyparser.py < crazy.page > py.test
+	    diff -i -u ek.test py.test || exit 1
+	done
+    done
+done
diff --git a/ekhtml/testsuite/tester.c b/ekhtml/testsuite/tester.c
new file mode 100644
index 0000000..972a156
--- /dev/null
+++ b/ekhtml/testsuite/tester.c
@@ -0,0 +1,158 @@
+/*
+ * Copyright (c) 2002, Jon Travis
+ * All rights reserved.
+ * 
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. 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.
+ * 
+ * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``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 AUTHOR 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.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <assert.h>
+
+#include "ekhtml.h"
+
+#define MAGIC_DOODIE 0xf9d33bc1
+
+typedef struct {
+    unsigned int n_starttags;
+    unsigned int n_endtags;
+    unsigned int n_comments;
+    unsigned int n_data;
+    unsigned int magic_doodie;
+    unsigned int only_parse;
+} tester_cbdata;
+
+static void handle_starttag_way(void *cbdata, ekhtml_string_t *tag,
+                                ekhtml_attr_t *attrs)
+{
+    printf("GOT WAY START!\n");
+}
+
+static void handle_starttag(void *cbdata, ekhtml_string_t *tag,
+			    ekhtml_attr_t *attrs)
+{
+    ekhtml_attr_t *attr;
+    tester_cbdata *tdata = cbdata;
+    
+    assert(tdata->magic_doodie == MAGIC_DOODIE);
+    tdata->n_starttags++;
+    if(tdata->only_parse)
+        return;
+    
+    printf("START: \"%.*s\"\n", tag->len, tag->str);
+    for(attr=attrs; attr; attr=attr->next) {
+        printf("ATTRIBUTE: \"%.*s\" = ", attr->name.len, attr->name.str);
+        if(!attr->isBoolean)
+            printf("\"%.*s\"\n", attr->val.len, attr->val.str);
+        else
+            printf("\"%.*s\"\n", attr->name.len, attr->name.str);
+    }
+}
+
+static void handle_endtag(void *cbdata, ekhtml_string_t *str){
+    tester_cbdata *tdata = cbdata;
+    
+    assert(tdata->magic_doodie == MAGIC_DOODIE);
+    tdata->n_endtags++;
+    if(tdata->only_parse)
+        return;
+    
+    printf("END: \"%.*s\"\n", str->len, str->str);
+}
+
+static void handle_comment(void *cbdata, ekhtml_string_t *str){
+    tester_cbdata *tdata = cbdata;
+    
+    assert(tdata->magic_doodie == MAGIC_DOODIE);
+    tdata->n_comments++;
+    if(tdata->only_parse)
+        return;
+    
+    printf("COMMENT: \"%.*s\"\n", str->len, str->str);
+}
+
+static void handle_data(void *cbdata, ekhtml_string_t *str){
+    tester_cbdata *tdata = cbdata;
+    
+    assert(tdata->magic_doodie == MAGIC_DOODIE);
+    tdata->n_data++;
+    if(tdata->only_parse)
+        return;
+    
+    fwrite(str->str, str->len, 1, stdout);
+}
+
+int main(int argc, char *argv[]){
+    tester_cbdata cbdata;
+    ekhtml_parser_t *ekparser;
+    char *buf;
+    size_t nbuf;
+    int feedsize;
+    
+    if(argc < 2){
+        fprintf(stderr, "Syntax: %s <feedsize> [1|0 (to print debug)]\n", 
+                argv[0]);
+        return -1;
+    }
+    
+    feedsize = atoi(argv[1]);
+    
+    ekparser = ekhtml_parser_new(NULL);
+    
+    cbdata.n_starttags  = 0;
+    cbdata.n_endtags    = 0;
+    cbdata.n_comments   = 0;
+    cbdata.n_data       = 0;
+    cbdata.magic_doodie = MAGIC_DOODIE;
+    cbdata.only_parse   = argc == 3;
+    
+    ekhtml_parser_datacb_set(ekparser, handle_data);
+    ekhtml_parser_commentcb_set(ekparser, handle_comment);
+    ekhtml_parser_startcb_add(ekparser, "WAY", handle_starttag_way);
+    ekhtml_parser_startcb_add(ekparser, NULL, handle_starttag);
+    ekhtml_parser_endcb_add(ekparser, NULL, handle_endtag);
+    ekhtml_parser_cbdata_set(ekparser, &cbdata);
+    buf = malloc(feedsize);
+    
+    while((nbuf = fread(buf, 1, feedsize, stdin))){
+        ekhtml_string_t str;
+
+        str.str = buf;
+        str.len = nbuf;
+        ekhtml_parser_feed(ekparser, &str);
+        ekhtml_parser_flush(ekparser, 0);
+    }
+    ekhtml_parser_flush(ekparser, 1);
+    ekhtml_parser_destroy(ekparser);
+    free(buf);
+    
+    if(argc == 3){
+        fprintf(stderr, 
+                "# starttags: %u\n"
+                "# endtags:   %u\n"
+                "# comments:  %u\n"
+                "# data:      %u\n", cbdata.n_starttags,
+                cbdata.n_endtags, cbdata.n_comments, cbdata.n_data);
+    }
+    
+    return 0;
+}
diff --git a/ekhtml/testsuite/tstpages/01_stock_cases/comment.suite b/ekhtml/testsuite/tstpages/01_stock_cases/comment.suite
new file mode 100644
index 0000000..88ce043
--- /dev/null
+++ b/ekhtml/testsuite/tstpages/01_stock_cases/comment.suite
@@ -0,0 +1,18 @@
+<!---->
+<!-- -->
+<!-- -- >
+<!--
+
+--
+
+--
+
+>
+<!-- A comment string -->
+<!-- More comments
+-- 
+>
+<!-- More comments
+-->
+<!-- And even -- more -- comments - from the -- peanut -- gallery -->
+
diff --git a/ekhtml/testsuite/tstpages/01_stock_cases/endtag.suite b/ekhtml/testsuite/tstpages/01_stock_cases/endtag.suite
new file mode 100644
index 0000000..869db71
--- /dev/null
+++ b/ekhtml/testsuite/tstpages/01_stock_cases/endtag.suite
@@ -0,0 +1,13 @@
+First start out with some properly formed end tags
+</F></FO></FOO>
+
+Now something a little more interesting
+</></FOO BAR></FOO BAR >
+
+Some weird stuff
+</ ></ FOO BAR></ FOO BAR  >
+</FOO
+
+></ 
+
+>
diff --git a/ekhtml/testsuite/tstpages/01_stock_cases/special.suite b/ekhtml/testsuite/tstpages/01_stock_cases/special.suite
new file mode 100644
index 0000000..ffd6517
--- /dev/null
+++ b/ekhtml/testsuite/tstpages/01_stock_cases/special.suite
@@ -0,0 +1,11 @@
+<!>
+<!->
+<!- >
+<!FOOBAR BAZ QUUX!>
+<!FOO
+BAR
+BAZ
+>
+<!FOO
+BAR
+BAZ>
diff --git a/ekhtml/testsuite/tstpages/01_stock_cases/starttag.suite b/ekhtml/testsuite/tstpages/01_stock_cases/starttag.suite
new file mode 100644
index 0000000..c1a03af
--- /dev/null
+++ b/ekhtml/testsuite/tstpages/01_stock_cases/starttag.suite
@@ -0,0 +1,21 @@
+First, valid tags
+<TAG>
+<TAG BOOLATTR>
+<TAG ATTR1=1>
+<TAG ATTR1="1">
+<TAG ATTR1='1'>
+<TAG ATTR1='"1'>
+<TAG ATTR1='""1'>
+<TAG ATTR1='""1"'>
+<TAG ATTR1='""1""'>
+<TAG ATTR1='"1""'>
+<TAG ATTR1='1""'>
+<TAG ATTR1='1"'>
+
+<TAG ATTR1
+ATTR2>
+<TAG ATTR1
+ATTR2
+>
+<TAG ATTR1="foo"
+ATTR2>
diff --git a/ekhtml/testsuite/tstpages/01_stock_cases/way.suite b/ekhtml/testsuite/tstpages/01_stock_cases/way.suite
new file mode 100644
index 0000000..c33756c
--- /dev/null
+++ b/ekhtml/testsuite/tstpages/01_stock_cases/way.suite
@@ -0,0 +1,4 @@
+<WAY>
+
+<WAY COOL>
+<WAY COOL=bar>
\ No newline at end of file