diff options
Diffstat (limited to 'protocols/Telegram/tgl/zlib/examples/zlib_how.html')
| -rw-r--r-- | protocols/Telegram/tgl/zlib/examples/zlib_how.html | 545 |
1 files changed, 545 insertions, 0 deletions
diff --git a/protocols/Telegram/tgl/zlib/examples/zlib_how.html b/protocols/Telegram/tgl/zlib/examples/zlib_how.html new file mode 100644 index 0000000000..444ff1c9a3 --- /dev/null +++ b/protocols/Telegram/tgl/zlib/examples/zlib_how.html @@ -0,0 +1,545 @@ +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" + "http://www.w3.org/TR/REC-html40/loose.dtd"> +<html> +<head> +<meta http-equiv="Content-Type" content="text/html; charset=ISO-8859-1"> +<title>zlib Usage Example</title> +<!-- Copyright (c) 2004, 2005 Mark Adler. --> +</head> +<body bgcolor="#FFFFFF" text="#000000" link="#0000FF" vlink="#00A000"> +<h2 align="center"> zlib Usage Example </h2> +We often get questions about how the <tt>deflate()</tt> and <tt>inflate()</tt> functions should be used. +Users wonder when they should provide more input, when they should use more output, +what to do with a <tt>Z_BUF_ERROR</tt>, how to make sure the process terminates properly, and +so on. So for those who have read <tt>zlib.h</tt> (a few times), and +would like further edification, below is an annotated example in C of simple routines to compress and decompress +from an input file to an output file using <tt>deflate()</tt> and <tt>inflate()</tt> respectively. The +annotations are interspersed between lines of the code. So please read between the lines. +We hope this helps explain some of the intricacies of <em>zlib</em>. +<p> +Without further adieu, here is the program <a href="zpipe.c"><tt>zpipe.c</tt></a>: +<pre><b> +/* zpipe.c: example of proper use of zlib's inflate() and deflate() + Not copyrighted -- provided to the public domain + Version 1.4 11 December 2005 Mark Adler */ + +/* Version history: + 1.0 30 Oct 2004 First version + 1.1 8 Nov 2004 Add void casting for unused return values + Use switch statement for inflate() return values + 1.2 9 Nov 2004 Add assertions to document zlib guarantees + 1.3 6 Apr 2005 Remove incorrect assertion in inf() + 1.4 11 Dec 2005 Add hack to avoid MSDOS end-of-line conversions + Avoid some compiler warnings for input and output buffers + */ +</b></pre><!-- --> +We now include the header files for the required definitions. From +<tt>stdio.h</tt> we use <tt>fopen()</tt>, <tt>fread()</tt>, <tt>fwrite()</tt>, +<tt>feof()</tt>, <tt>ferror()</tt>, and <tt>fclose()</tt> for file i/o, and +<tt>fputs()</tt> for error messages. From <tt>string.h</tt> we use +<tt>strcmp()</tt> for command line argument processing. +From <tt>assert.h</tt> we use the <tt>assert()</tt> macro. +From <tt>zlib.h</tt> +we use the basic compression functions <tt>deflateInit()</tt>, +<tt>deflate()</tt>, and <tt>deflateEnd()</tt>, and the basic decompression +functions <tt>inflateInit()</tt>, <tt>inflate()</tt>, and +<tt>inflateEnd()</tt>. +<pre><b> +#include <stdio.h> +#include <string.h> +#include <assert.h> +#include "zlib.h" +</b></pre><!-- --> +This is an ugly hack required to avoid corruption of the input and output data on +Windows/MS-DOS systems. Without this, those systems would assume that the input and output +files are text, and try to convert the end-of-line characters from one standard to +another. That would corrupt binary data, and in particular would render the compressed data unusable. +This sets the input and output to binary which suppresses the end-of-line conversions. +<tt>SET_BINARY_MODE()</tt> will be used later on <tt>stdin</tt> and <tt>stdout</tt>, at the beginning of <tt>main()</tt>. +<pre><b> +#if defined(MSDOS) || defined(OS2) || defined(WIN32) || defined(__CYGWIN__) +# include <fcntl.h> +# include <io.h> +# define SET_BINARY_MODE(file) setmode(fileno(file), O_BINARY) +#else +# define SET_BINARY_MODE(file) +#endif +</b></pre><!-- --> +<tt>CHUNK</tt> is simply the buffer size for feeding data to and pulling data +from the <em>zlib</em> routines. Larger buffer sizes would be more efficient, +especially for <tt>inflate()</tt>. If the memory is available, buffers sizes +on the order of 128K or 256K bytes should be used. +<pre><b> +#define CHUNK 16384 +</b></pre><!-- --> +The <tt>def()</tt> routine compresses data from an input file to an output file. The output data +will be in the <em>zlib</em> format, which is different from the <em>gzip</em> or <em>zip</em> +formats. The <em>zlib</em> format has a very small header of only two bytes to identify it as +a <em>zlib</em> stream and to provide decoding information, and a four-byte trailer with a fast +check value to verify the integrity of the uncompressed data after decoding. +<pre><b> +/* Compress from file source to file dest until EOF on source. + def() returns Z_OK on success, Z_MEM_ERROR if memory could not be + allocated for processing, Z_STREAM_ERROR if an invalid compression + level is supplied, Z_VERSION_ERROR if the version of zlib.h and the + version of the library linked do not match, or Z_ERRNO if there is + an error reading or writing the files. */ +int def(FILE *source, FILE *dest, int level) +{ +</b></pre> +Here are the local variables for <tt>def()</tt>. <tt>ret</tt> will be used for <em>zlib</em> +return codes. <tt>flush</tt> will keep track of the current flushing state for <tt>deflate()</tt>, +which is either no flushing, or flush to completion after the end of the input file is reached. +<tt>have</tt> is the amount of data returned from <tt>deflate()</tt>. The <tt>strm</tt> structure +is used to pass information to and from the <em>zlib</em> routines, and to maintain the +<tt>deflate()</tt> state. <tt>in</tt> and <tt>out</tt> are the input and output buffers for +<tt>deflate()</tt>. +<pre><b> + int ret, flush; + unsigned have; + z_stream strm; + unsigned char in[CHUNK]; + unsigned char out[CHUNK]; +</b></pre><!-- --> +The first thing we do is to initialize the <em>zlib</em> state for compression using +<tt>deflateInit()</tt>. This must be done before the first use of <tt>deflate()</tt>. +The <tt>zalloc</tt>, <tt>zfree</tt>, and <tt>opaque</tt> fields in the <tt>strm</tt> +structure must be initialized before calling <tt>deflateInit()</tt>. Here they are +set to the <em>zlib</em> constant <tt>Z_NULL</tt> to request that <em>zlib</em> use +the default memory allocation routines. An application may also choose to provide +custom memory allocation routines here. <tt>deflateInit()</tt> will allocate on the +order of 256K bytes for the internal state. +(See <a href="zlib_tech.html"><em>zlib Technical Details</em></a>.) +<p> +<tt>deflateInit()</tt> is called with a pointer to the structure to be initialized and +the compression level, which is an integer in the range of -1 to 9. Lower compression +levels result in faster execution, but less compression. Higher levels result in +greater compression, but slower execution. The <em>zlib</em> constant Z_DEFAULT_COMPRESSION, +equal to -1, +provides a good compromise between compression and speed and is equivalent to level 6. +Level 0 actually does no compression at all, and in fact expands the data slightly to produce +the <em>zlib</em> format (it is not a byte-for-byte copy of the input). +More advanced applications of <em>zlib</em> +may use <tt>deflateInit2()</tt> here instead. Such an application may want to reduce how +much memory will be used, at some price in compression. Or it may need to request a +<em>gzip</em> header and trailer instead of a <em>zlib</em> header and trailer, or raw +encoding with no header or trailer at all. +<p> +We must check the return value of <tt>deflateInit()</tt> against the <em>zlib</em> constant +<tt>Z_OK</tt> to make sure that it was able to +allocate memory for the internal state, and that the provided arguments were valid. +<tt>deflateInit()</tt> will also check that the version of <em>zlib</em> that the <tt>zlib.h</tt> +file came from matches the version of <em>zlib</em> actually linked with the program. This +is especially important for environments in which <em>zlib</em> is a shared library. +<p> +Note that an application can initialize multiple, independent <em>zlib</em> streams, which can +operate in parallel. The state information maintained in the structure allows the <em>zlib</em> +routines to be reentrant. +<pre><b> + /* allocate deflate state */ + strm.zalloc = Z_NULL; + strm.zfree = Z_NULL; + strm.opaque = Z_NULL; + ret = deflateInit(&strm, level); + if (ret != Z_OK) + return ret; +</b></pre><!-- --> +With the pleasantries out of the way, now we can get down to business. The outer <tt>do</tt>-loop +reads all of the input file and exits at the bottom of the loop once end-of-file is reached. +This loop contains the only call of <tt>deflate()</tt>. So we must make sure that all of the +input data has been processed and that all of the output data has been generated and consumed +before we fall out of the loop at the bottom. +<pre><b> + /* compress until end of file */ + do { +</b></pre> +We start off by reading data from the input file. The number of bytes read is put directly +into <tt>avail_in</tt>, and a pointer to those bytes is put into <tt>next_in</tt>. We also +check to see if end-of-file on the input has been reached. If we are at the end of file, then <tt>flush</tt> is set to the +<em>zlib</em> constant <tt>Z_FINISH</tt>, which is later passed to <tt>deflate()</tt> to +indicate that this is the last chunk of input data to compress. We need to use <tt>feof()</tt> +to check for end-of-file as opposed to seeing if fewer than <tt>CHUNK</tt> bytes have been read. The +reason is that if the input file length is an exact multiple of <tt>CHUNK</tt>, we will miss +the fact that we got to the end-of-file, and not know to tell <tt>deflate()</tt> to finish +up the compressed stream. If we are not yet at the end of the input, then the <em>zlib</em> +constant <tt>Z_NO_FLUSH</tt> will be passed to <tt>deflate</tt> to indicate that we are still +in the middle of the uncompressed data. +<p> +If there is an error in reading from the input file, the process is aborted with +<tt>deflateEnd()</tt> being called to free the allocated <em>zlib</em> state before returning +the error. We wouldn't want a memory leak, now would we? <tt>deflateEnd()</tt> can be called +at any time after the state has been initialized. Once that's done, <tt>deflateInit()</tt> (or +<tt>deflateInit2()</tt>) would have to be called to start a new compression process. There is +no point here in checking the <tt>deflateEnd()</tt> return code. The deallocation can't fail. +<pre><b> + strm.avail_in = fread(in, 1, CHUNK, source); + if (ferror(source)) { + (void)deflateEnd(&strm); + return Z_ERRNO; + } + flush = feof(source) ? Z_FINISH : Z_NO_FLUSH; + strm.next_in = in; +</b></pre><!-- --> +The inner <tt>do</tt>-loop passes our chunk of input data to <tt>deflate()</tt>, and then +keeps calling <tt>deflate()</tt> until it is done producing output. Once there is no more +new output, <tt>deflate()</tt> is guaranteed to have consumed all of the input, i.e., +<tt>avail_in</tt> will be zero. +<pre><b> + /* run deflate() on input until output buffer not full, finish + compression if all of source has been read in */ + do { +</b></pre> +Output space is provided to <tt>deflate()</tt> by setting <tt>avail_out</tt> to the number +of available output bytes and <tt>next_out</tt> to a pointer to that space. +<pre><b> + strm.avail_out = CHUNK; + strm.next_out = out; +</b></pre> +Now we call the compression engine itself, <tt>deflate()</tt>. It takes as many of the +<tt>avail_in</tt> bytes at <tt>next_in</tt> as it can process, and writes as many as +<tt>avail_out</tt> bytes to <tt>next_out</tt>. Those counters and pointers are then +updated past the input data consumed and the output data written. It is the amount of +output space available that may limit how much input is consumed. +Hence the inner loop to make sure that +all of the input is consumed by providing more output space each time. Since <tt>avail_in</tt> +and <tt>next_in</tt> are updated by <tt>deflate()</tt>, we don't have to mess with those +between <tt>deflate()</tt> calls until it's all used up. +<p> +The parameters to <tt>deflate()</tt> are a pointer to the <tt>strm</tt> structure containing +the input and output information and the internal compression engine state, and a parameter +indicating whether and how to flush data to the output. Normally <tt>deflate</tt> will consume +several K bytes of input data before producing any output (except for the header), in order +to accumulate statistics on the data for optimum compression. It will then put out a burst of +compressed data, and proceed to consume more input before the next burst. Eventually, +<tt>deflate()</tt> +must be told to terminate the stream, complete the compression with provided input data, and +write out the trailer check value. <tt>deflate()</tt> will continue to compress normally as long +as the flush parameter is <tt>Z_NO_FLUSH</tt>. Once the <tt>Z_FINISH</tt> parameter is provided, +<tt>deflate()</tt> will begin to complete the compressed output stream. However depending on how +much output space is provided, <tt>deflate()</tt> may have to be called several times until it +has provided the complete compressed stream, even after it has consumed all of the input. The flush +parameter must continue to be <tt>Z_FINISH</tt> for those subsequent calls. +<p> +There are other values of the flush parameter that are used in more advanced applications. You can +force <tt>deflate()</tt> to produce a burst of output that encodes all of the input data provided +so far, even if it wouldn't have otherwise, for example to control data latency on a link with +compressed data. You can also ask that <tt>deflate()</tt> do that as well as erase any history up to +that point so that what follows can be decompressed independently, for example for random access +applications. Both requests will degrade compression by an amount depending on how often such +requests are made. +<p> +<tt>deflate()</tt> has a return value that can indicate errors, yet we do not check it here. Why +not? Well, it turns out that <tt>deflate()</tt> can do no wrong here. Let's go through +<tt>deflate()</tt>'s return values and dispense with them one by one. The possible values are +<tt>Z_OK</tt>, <tt>Z_STREAM_END</tt>, <tt>Z_STREAM_ERROR</tt>, or <tt>Z_BUF_ERROR</tt>. <tt>Z_OK</tt> +is, well, ok. <tt>Z_STREAM_END</tt> is also ok and will be returned for the last call of +<tt>deflate()</tt>. This is already guaranteed by calling <tt>deflate()</tt> with <tt>Z_FINISH</tt> +until it has no more output. <tt>Z_STREAM_ERROR</tt> is only possible if the stream is not +initialized properly, but we did initialize it properly. There is no harm in checking for +<tt>Z_STREAM_ERROR</tt> here, for example to check for the possibility that some +other part of the application inadvertently clobbered the memory containing the <em>zlib</em> state. +<tt>Z_BUF_ERROR</tt> will be explained further below, but +suffice it to say that this is simply an indication that <tt>deflate()</tt> could not consume +more input or produce more output. <tt>deflate()</tt> can be called again with more output space +or more available input, which it will be in this code. +<pre><b> + ret = deflate(&strm, flush); /* no bad return value */ + assert(ret != Z_STREAM_ERROR); /* state not clobbered */ +</b></pre> +Now we compute how much output <tt>deflate()</tt> provided on the last call, which is the +difference between how much space was provided before the call, and how much output space +is still available after the call. Then that data, if any, is written to the output file. +We can then reuse the output buffer for the next call of <tt>deflate()</tt>. Again if there +is a file i/o error, we call <tt>deflateEnd()</tt> before returning to avoid a memory leak. +<pre><b> + have = CHUNK - strm.avail_out; + if (fwrite(out, 1, have, dest) != have || ferror(dest)) { + (void)deflateEnd(&strm); + return Z_ERRNO; + } +</b></pre> +The inner <tt>do</tt>-loop is repeated until the last <tt>deflate()</tt> call fails to fill the +provided output buffer. Then we know that <tt>deflate()</tt> has done as much as it can with +the provided input, and that all of that input has been consumed. We can then fall out of this +loop and reuse the input buffer. +<p> +The way we tell that <tt>deflate()</tt> has no more output is by seeing that it did not fill +the output buffer, leaving <tt>avail_out</tt> greater than zero. However suppose that +<tt>deflate()</tt> has no more output, but just so happened to exactly fill the output buffer! +<tt>avail_out</tt> is zero, and we can't tell that <tt>deflate()</tt> has done all it can. +As far as we know, <tt>deflate()</tt> +has more output for us. So we call it again. But now <tt>deflate()</tt> produces no output +at all, and <tt>avail_out</tt> remains unchanged as <tt>CHUNK</tt>. That <tt>deflate()</tt> call +wasn't able to do anything, either consume input or produce output, and so it returns +<tt>Z_BUF_ERROR</tt>. (See, I told you I'd cover this later.) However this is not a problem at +all. Now we finally have the desired indication that <tt>deflate()</tt> is really done, +and so we drop out of the inner loop to provide more input to <tt>deflate()</tt>. +<p> +With <tt>flush</tt> set to <tt>Z_FINISH</tt>, this final set of <tt>deflate()</tt> calls will +complete the output stream. Once that is done, subsequent calls of <tt>deflate()</tt> would return +<tt>Z_STREAM_ERROR</tt> if the flush parameter is not <tt>Z_FINISH</tt>, and do no more processing +until the state is reinitialized. +<p> +Some applications of <em>zlib</em> have two loops that call <tt>deflate()</tt> +instead of the single inner loop we have here. The first loop would call +without flushing and feed all of the data to <tt>deflate()</tt>. The second loop would call +<tt>deflate()</tt> with no more +data and the <tt>Z_FINISH</tt> parameter to complete the process. As you can see from this +example, that can be avoided by simply keeping track of the current flush state. +<pre><b> + } while (strm.avail_out == 0); + assert(strm.avail_in == 0); /* all input will be used */ +</b></pre><!-- --> +Now we check to see if we have already processed all of the input file. That information was +saved in the <tt>flush</tt> variable, so we see if that was set to <tt>Z_FINISH</tt>. If so, +then we're done and we fall out of the outer loop. We're guaranteed to get <tt>Z_STREAM_END</tt> +from the last <tt>deflate()</tt> call, since we ran it until the last chunk of input was +consumed and all of the output was generated. +<pre><b> + /* done when last data in file processed */ + } while (flush != Z_FINISH); + assert(ret == Z_STREAM_END); /* stream will be complete */ +</b></pre><!-- --> +The process is complete, but we still need to deallocate the state to avoid a memory leak +(or rather more like a memory hemorrhage if you didn't do this). Then +finally we can return with a happy return value. +<pre><b> + /* clean up and return */ + (void)deflateEnd(&strm); + return Z_OK; +} +</b></pre><!-- --> +Now we do the same thing for decompression in the <tt>inf()</tt> routine. <tt>inf()</tt> +decompresses what is hopefully a valid <em>zlib</em> stream from the input file and writes the +uncompressed data to the output file. Much of the discussion above for <tt>def()</tt> +applies to <tt>inf()</tt> as well, so the discussion here will focus on the differences between +the two. +<pre><b> +/* Decompress from file source to file dest until stream ends or EOF. + inf() returns Z_OK on success, Z_MEM_ERROR if memory could not be + allocated for processing, Z_DATA_ERROR if the deflate data is + invalid or incomplete, Z_VERSION_ERROR if the version of zlib.h and + the version of the library linked do not match, or Z_ERRNO if there + is an error reading or writing the files. */ +int inf(FILE *source, FILE *dest) +{ +</b></pre> +The local variables have the same functionality as they do for <tt>def()</tt>. The +only difference is that there is no <tt>flush</tt> variable, since <tt>inflate()</tt> +can tell from the <em>zlib</em> stream itself when the stream is complete. +<pre><b> + int ret; + unsigned have; + z_stream strm; + unsigned char in[CHUNK]; + unsigned char out[CHUNK]; +</b></pre><!-- --> +The initialization of the state is the same, except that there is no compression level, +of course, and two more elements of the structure are initialized. <tt>avail_in</tt> +and <tt>next_in</tt> must be initialized before calling <tt>inflateInit()</tt>. This +is because the application has the option to provide the start of the zlib stream in +order for <tt>inflateInit()</tt> to have access to information about the compression +method to aid in memory allocation. In the current implementation of <em>zlib</em> +(up through versions 1.2.x), the method-dependent memory allocations are deferred to the first call of +<tt>inflate()</tt> anyway. However those fields must be initialized since later versions +of <em>zlib</em> that provide more compression methods may take advantage of this interface. +In any case, no decompression is performed by <tt>inflateInit()</tt>, so the +<tt>avail_out</tt> and <tt>next_out</tt> fields do not need to be initialized before calling. +<p> +Here <tt>avail_in</tt> is set to zero and <tt>next_in</tt> is set to <tt>Z_NULL</tt> to +indicate that no input data is being provided. +<pre><b> + /* allocate inflate state */ + strm.zalloc = Z_NULL; + strm.zfree = Z_NULL; + strm.opaque = Z_NULL; + strm.avail_in = 0; + strm.next_in = Z_NULL; + ret = inflateInit(&strm); + if (ret != Z_OK) + return ret; +</b></pre><!-- --> +The outer <tt>do</tt>-loop decompresses input until <tt>inflate()</tt> indicates +that it has reached the end of the compressed data and has produced all of the uncompressed +output. This is in contrast to <tt>def()</tt> which processes all of the input file. +If end-of-file is reached before the compressed data self-terminates, then the compressed +data is incomplete and an error is returned. +<pre><b> + /* decompress until deflate stream ends or end of file */ + do { +</b></pre> +We read input data and set the <tt>strm</tt> structure accordingly. If we've reached the +end of the input file, then we leave the outer loop and report an error, since the +compressed data is incomplete. Note that we may read more data than is eventually consumed +by <tt>inflate()</tt>, if the input file continues past the <em>zlib</em> stream. +For applications where <em>zlib</em> streams are embedded in other data, this routine would +need to be modified to return the unused data, or at least indicate how much of the input +data was not used, so the application would know where to pick up after the <em>zlib</em> stream. +<pre><b> + strm.avail_in = fread(in, 1, CHUNK, source); + if (ferror(source)) { + (void)inflateEnd(&strm); + return Z_ERRNO; + } + if (strm.avail_in == 0) + break; + strm.next_in = in; +</b></pre><!-- --> +The inner <tt>do</tt>-loop has the same function it did in <tt>def()</tt>, which is to +keep calling <tt>inflate()</tt> until has generated all of the output it can with the +provided input. +<pre><b> + /* run inflate() on input until output buffer not full */ + do { +</b></pre> +Just like in <tt>def()</tt>, the same output space is provided for each call of <tt>inflate()</tt>. +<pre><b> + strm.avail_out = CHUNK; + strm.next_out = out; +</b></pre> +Now we run the decompression engine itself. There is no need to adjust the flush parameter, since +the <em>zlib</em> format is self-terminating. The main difference here is that there are +return values that we need to pay attention to. <tt>Z_DATA_ERROR</tt> +indicates that <tt>inflate()</tt> detected an error in the <em>zlib</em> compressed data format, +which means that either the data is not a <em>zlib</em> stream to begin with, or that the data was +corrupted somewhere along the way since it was compressed. The other error to be processed is +<tt>Z_MEM_ERROR</tt>, which can occur since memory allocation is deferred until <tt>inflate()</tt> +needs it, unlike <tt>deflate()</tt>, whose memory is allocated at the start by <tt>deflateInit()</tt>. +<p> +Advanced applications may use +<tt>deflateSetDictionary()</tt> to prime <tt>deflate()</tt> with a set of likely data to improve the +first 32K or so of compression. This is noted in the <em>zlib</em> header, so <tt>inflate()</tt> +requests that that dictionary be provided before it can start to decompress. Without the dictionary, +correct decompression is not possible. For this routine, we have no idea what the dictionary is, +so the <tt>Z_NEED_DICT</tt> indication is converted to a <tt>Z_DATA_ERROR</tt>. +<p> +<tt>inflate()</tt> can also return <tt>Z_STREAM_ERROR</tt>, which should not be possible here, +but could be checked for as noted above for <tt>def()</tt>. <tt>Z_BUF_ERROR</tt> does not need to be +checked for here, for the same reasons noted for <tt>def()</tt>. <tt>Z_STREAM_END</tt> will be +checked for later. +<pre><b> + ret = inflate(&strm, Z_NO_FLUSH); + assert(ret != Z_STREAM_ERROR); /* state not clobbered */ + switch (ret) { + case Z_NEED_DICT: + ret = Z_DATA_ERROR; /* and fall through */ + case Z_DATA_ERROR: + case Z_MEM_ERROR: + (void)inflateEnd(&strm); + return ret; + } +</b></pre> +The output of <tt>inflate()</tt> is handled identically to that of <tt>deflate()</tt>. +<pre><b> + have = CHUNK - strm.avail_out; + if (fwrite(out, 1, have, dest) != have || ferror(dest)) { + (void)inflateEnd(&strm); + return Z_ERRNO; + } +</b></pre> +The inner <tt>do</tt>-loop ends when <tt>inflate()</tt> has no more output as indicated +by not filling the output buffer, just as for <tt>deflate()</tt>. In this case, we cannot +assert that <tt>strm.avail_in</tt> will be zero, since the deflate stream may end before the file +does. +<pre><b> + } while (strm.avail_out == 0); +</b></pre><!-- --> +The outer <tt>do</tt>-loop ends when <tt>inflate()</tt> reports that it has reached the +end of the input <em>zlib</em> stream, has completed the decompression and integrity +check, and has provided all of the output. This is indicated by the <tt>inflate()</tt> +return value <tt>Z_STREAM_END</tt>. The inner loop is guaranteed to leave <tt>ret</tt> +equal to <tt>Z_STREAM_END</tt> if the last chunk of the input file read contained the end +of the <em>zlib</em> stream. So if the return value is not <tt>Z_STREAM_END</tt>, the +loop continues to read more input. +<pre><b> + /* done when inflate() says it's done */ + } while (ret != Z_STREAM_END); +</b></pre><!-- --> +At this point, decompression successfully completed, or we broke out of the loop due to no +more data being available from the input file. If the last <tt>inflate()</tt> return value +is not <tt>Z_STREAM_END</tt>, then the <em>zlib</em> stream was incomplete and a data error +is returned. Otherwise, we return with a happy return value. Of course, <tt>inflateEnd()</tt> +is called first to avoid a memory leak. +<pre><b> + /* clean up and return */ + (void)inflateEnd(&strm); + return ret == Z_STREAM_END ? Z_OK : Z_DATA_ERROR; +} +</b></pre><!-- --> +That ends the routines that directly use <em>zlib</em>. The following routines make this +a command-line program by running data through the above routines from <tt>stdin</tt> to +<tt>stdout</tt>, and handling any errors reported by <tt>def()</tt> or <tt>inf()</tt>. +<p> +<tt>zerr()</tt> is used to interpret the possible error codes from <tt>def()</tt> +and <tt>inf()</tt>, as detailed in their comments above, and print out an error message. +Note that these are only a subset of the possible return values from <tt>deflate()</tt> +and <tt>inflate()</tt>. +<pre><b> +/* report a zlib or i/o error */ +void zerr(int ret) +{ + fputs("zpipe: ", stderr); + switch (ret) { + case Z_ERRNO: + if (ferror(stdin)) + fputs("error reading stdin\n", stderr); + if (ferror(stdout)) + fputs("error writing stdout\n", stderr); + break; + case Z_STREAM_ERROR: + fputs("invalid compression level\n", stderr); + break; + case Z_DATA_ERROR: + fputs("invalid or incomplete deflate data\n", stderr); + break; + case Z_MEM_ERROR: + fputs("out of memory\n", stderr); + break; + case Z_VERSION_ERROR: + fputs("zlib version mismatch!\n", stderr); + } +} +</b></pre><!-- --> +Here is the <tt>main()</tt> routine used to test <tt>def()</tt> and <tt>inf()</tt>. The +<tt>zpipe</tt> command is simply a compression pipe from <tt>stdin</tt> to <tt>stdout</tt>, if +no arguments are given, or it is a decompression pipe if <tt>zpipe -d</tt> is used. If any other +arguments are provided, no compression or decompression is performed. Instead a usage +message is displayed. Examples are <tt>zpipe < foo.txt > foo.txt.z</tt> to compress, and +<tt>zpipe -d < foo.txt.z > foo.txt</tt> to decompress. +<pre><b> +/* compress or decompress from stdin to stdout */ +int main(int argc, char **argv) +{ + int ret; + + /* avoid end-of-line conversions */ + SET_BINARY_MODE(stdin); + SET_BINARY_MODE(stdout); + + /* do compression if no arguments */ + if (argc == 1) { + ret = def(stdin, stdout, Z_DEFAULT_COMPRESSION); + if (ret != Z_OK) + zerr(ret); + return ret; + } + + /* do decompression if -d specified */ + else if (argc == 2 && strcmp(argv[1], "-d") == 0) { + ret = inf(stdin, stdout); + if (ret != Z_OK) + zerr(ret); + return ret; + } + + /* otherwise, report usage */ + else { + fputs("zpipe usage: zpipe [-d] < source > dest\n", stderr); + return 1; + } +} +</b></pre> +<hr> +<i>Copyright (c) 2004, 2005 by Mark Adler<br>Last modified 11 December 2005</i> +</body> +</html> |