1275793eaSopenharmony_ci<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" 2275793eaSopenharmony_ci "http://www.w3.org/TR/html4/loose.dtd"> 3275793eaSopenharmony_ci<html> 4275793eaSopenharmony_ci<head> 5275793eaSopenharmony_ci<meta http-equiv="Content-Type" content="text/html; charset=ISO-8859-1"> 6275793eaSopenharmony_ci<title>zlib Usage Example</title> 7275793eaSopenharmony_ci<!-- Copyright (c) 2004-2023 Mark Adler. --> 8275793eaSopenharmony_ci</head> 9275793eaSopenharmony_ci<body bgcolor="#FFFFFF" text="#000000" link="#0000FF" vlink="#00A000"> 10275793eaSopenharmony_ci<h2 align="center"> zlib Usage Example </h2> 11275793eaSopenharmony_ciWe often get questions about how the <tt>deflate()</tt> and <tt>inflate()</tt> functions should be used. 12275793eaSopenharmony_ciUsers wonder when they should provide more input, when they should use more output, 13275793eaSopenharmony_ciwhat to do with a <tt>Z_BUF_ERROR</tt>, how to make sure the process terminates properly, and 14275793eaSopenharmony_ciso on. So for those who have read <tt>zlib.h</tt> (a few times), and 15275793eaSopenharmony_ciwould like further edification, below is an annotated example in C of simple routines to compress and decompress 16275793eaSopenharmony_cifrom an input file to an output file using <tt>deflate()</tt> and <tt>inflate()</tt> respectively. The 17275793eaSopenharmony_ciannotations are interspersed between lines of the code. So please read between the lines. 18275793eaSopenharmony_ciWe hope this helps explain some of the intricacies of <em>zlib</em>. 19275793eaSopenharmony_ci<p> 20275793eaSopenharmony_ciWithout further ado, here is the program <a href="zpipe.c"><tt>zpipe.c</tt></a>: 21275793eaSopenharmony_ci<pre><b> 22275793eaSopenharmony_ci/* zpipe.c: example of proper use of zlib's inflate() and deflate() 23275793eaSopenharmony_ci Not copyrighted -- provided to the public domain 24275793eaSopenharmony_ci Version 1.4 11 December 2005 Mark Adler */ 25275793eaSopenharmony_ci 26275793eaSopenharmony_ci/* Version history: 27275793eaSopenharmony_ci 1.0 30 Oct 2004 First version 28275793eaSopenharmony_ci 1.1 8 Nov 2004 Add void casting for unused return values 29275793eaSopenharmony_ci Use switch statement for inflate() return values 30275793eaSopenharmony_ci 1.2 9 Nov 2004 Add assertions to document zlib guarantees 31275793eaSopenharmony_ci 1.3 6 Apr 2005 Remove incorrect assertion in inf() 32275793eaSopenharmony_ci 1.4 11 Dec 2005 Add hack to avoid MSDOS end-of-line conversions 33275793eaSopenharmony_ci Avoid some compiler warnings for input and output buffers 34275793eaSopenharmony_ci */ 35275793eaSopenharmony_ci</b></pre><!-- --> 36275793eaSopenharmony_ciWe now include the header files for the required definitions. From 37275793eaSopenharmony_ci<tt>stdio.h</tt> we use <tt>fopen()</tt>, <tt>fread()</tt>, <tt>fwrite()</tt>, 38275793eaSopenharmony_ci<tt>feof()</tt>, <tt>ferror()</tt>, and <tt>fclose()</tt> for file i/o, and 39275793eaSopenharmony_ci<tt>fputs()</tt> for error messages. From <tt>string.h</tt> we use 40275793eaSopenharmony_ci<tt>strcmp()</tt> for command line argument processing. 41275793eaSopenharmony_ciFrom <tt>assert.h</tt> we use the <tt>assert()</tt> macro. 42275793eaSopenharmony_ciFrom <tt>zlib.h</tt> 43275793eaSopenharmony_ciwe use the basic compression functions <tt>deflateInit()</tt>, 44275793eaSopenharmony_ci<tt>deflate()</tt>, and <tt>deflateEnd()</tt>, and the basic decompression 45275793eaSopenharmony_cifunctions <tt>inflateInit()</tt>, <tt>inflate()</tt>, and 46275793eaSopenharmony_ci<tt>inflateEnd()</tt>. 47275793eaSopenharmony_ci<pre><b> 48275793eaSopenharmony_ci#include <stdio.h> 49275793eaSopenharmony_ci#include <string.h> 50275793eaSopenharmony_ci#include <assert.h> 51275793eaSopenharmony_ci#include "zlib.h" 52275793eaSopenharmony_ci</b></pre><!-- --> 53275793eaSopenharmony_ciThis is an ugly hack required to avoid corruption of the input and output data on 54275793eaSopenharmony_ciWindows/MS-DOS systems. Without this, those systems would assume that the input and output 55275793eaSopenharmony_cifiles are text, and try to convert the end-of-line characters from one standard to 56275793eaSopenharmony_cianother. That would corrupt binary data, and in particular would render the compressed data unusable. 57275793eaSopenharmony_ciThis sets the input and output to binary which suppresses the end-of-line conversions. 58275793eaSopenharmony_ci<tt>SET_BINARY_MODE()</tt> will be used later on <tt>stdin</tt> and <tt>stdout</tt>, at the beginning of <tt>main()</tt>. 59275793eaSopenharmony_ci<pre><b> 60275793eaSopenharmony_ci#if defined(MSDOS) || defined(OS2) || defined(WIN32) || defined(__CYGWIN__) 61275793eaSopenharmony_ci# include <fcntl.h> 62275793eaSopenharmony_ci# include <io.h> 63275793eaSopenharmony_ci# define SET_BINARY_MODE(file) setmode(fileno(file), O_BINARY) 64275793eaSopenharmony_ci#else 65275793eaSopenharmony_ci# define SET_BINARY_MODE(file) 66275793eaSopenharmony_ci#endif 67275793eaSopenharmony_ci</b></pre><!-- --> 68275793eaSopenharmony_ci<tt>CHUNK</tt> is simply the buffer size for feeding data to and pulling data 69275793eaSopenharmony_cifrom the <em>zlib</em> routines. Larger buffer sizes would be more efficient, 70275793eaSopenharmony_ciespecially for <tt>inflate()</tt>. If the memory is available, buffers sizes 71275793eaSopenharmony_cion the order of 128K or 256K bytes should be used. 72275793eaSopenharmony_ci<pre><b> 73275793eaSopenharmony_ci#define CHUNK 16384 74275793eaSopenharmony_ci</b></pre><!-- --> 75275793eaSopenharmony_ciThe <tt>def()</tt> routine compresses data from an input file to an output file. The output data 76275793eaSopenharmony_ciwill be in the <em>zlib</em> format, which is different from the <em>gzip</em> or <em>zip</em> 77275793eaSopenharmony_ciformats. The <em>zlib</em> format has a very small header of only two bytes to identify it as 78275793eaSopenharmony_cia <em>zlib</em> stream and to provide decoding information, and a four-byte trailer with a fast 79275793eaSopenharmony_cicheck value to verify the integrity of the uncompressed data after decoding. 80275793eaSopenharmony_ci<pre><b> 81275793eaSopenharmony_ci/* Compress from file source to file dest until EOF on source. 82275793eaSopenharmony_ci def() returns Z_OK on success, Z_MEM_ERROR if memory could not be 83275793eaSopenharmony_ci allocated for processing, Z_STREAM_ERROR if an invalid compression 84275793eaSopenharmony_ci level is supplied, Z_VERSION_ERROR if the version of zlib.h and the 85275793eaSopenharmony_ci version of the library linked do not match, or Z_ERRNO if there is 86275793eaSopenharmony_ci an error reading or writing the files. */ 87275793eaSopenharmony_ciint def(FILE *source, FILE *dest, int level) 88275793eaSopenharmony_ci{ 89275793eaSopenharmony_ci</b></pre> 90275793eaSopenharmony_ciHere are the local variables for <tt>def()</tt>. <tt>ret</tt> will be used for <em>zlib</em> 91275793eaSopenharmony_cireturn codes. <tt>flush</tt> will keep track of the current flushing state for <tt>deflate()</tt>, 92275793eaSopenharmony_ciwhich is either no flushing, or flush to completion after the end of the input file is reached. 93275793eaSopenharmony_ci<tt>have</tt> is the amount of data returned from <tt>deflate()</tt>. The <tt>strm</tt> structure 94275793eaSopenharmony_ciis used to pass information to and from the <em>zlib</em> routines, and to maintain the 95275793eaSopenharmony_ci<tt>deflate()</tt> state. <tt>in</tt> and <tt>out</tt> are the input and output buffers for 96275793eaSopenharmony_ci<tt>deflate()</tt>. 97275793eaSopenharmony_ci<pre><b> 98275793eaSopenharmony_ci int ret, flush; 99275793eaSopenharmony_ci unsigned have; 100275793eaSopenharmony_ci z_stream strm; 101275793eaSopenharmony_ci unsigned char in[CHUNK]; 102275793eaSopenharmony_ci unsigned char out[CHUNK]; 103275793eaSopenharmony_ci</b></pre><!-- --> 104275793eaSopenharmony_ciThe first thing we do is to initialize the <em>zlib</em> state for compression using 105275793eaSopenharmony_ci<tt>deflateInit()</tt>. This must be done before the first use of <tt>deflate()</tt>. 106275793eaSopenharmony_ciThe <tt>zalloc</tt>, <tt>zfree</tt>, and <tt>opaque</tt> fields in the <tt>strm</tt> 107275793eaSopenharmony_cistructure must be initialized before calling <tt>deflateInit()</tt>. Here they are 108275793eaSopenharmony_ciset to the <em>zlib</em> constant <tt>Z_NULL</tt> to request that <em>zlib</em> use 109275793eaSopenharmony_cithe default memory allocation routines. An application may also choose to provide 110275793eaSopenharmony_cicustom memory allocation routines here. <tt>deflateInit()</tt> will allocate on the 111275793eaSopenharmony_ciorder of 256K bytes for the internal state. 112275793eaSopenharmony_ci(See <a href="zlib_tech.html"><em>zlib Technical Details</em></a>.) 113275793eaSopenharmony_ci<p> 114275793eaSopenharmony_ci<tt>deflateInit()</tt> is called with a pointer to the structure to be initialized and 115275793eaSopenharmony_cithe compression level, which is an integer in the range of -1 to 9. Lower compression 116275793eaSopenharmony_cilevels result in faster execution, but less compression. Higher levels result in 117275793eaSopenharmony_cigreater compression, but slower execution. The <em>zlib</em> constant Z_DEFAULT_COMPRESSION, 118275793eaSopenharmony_ciequal to -1, 119275793eaSopenharmony_ciprovides a good compromise between compression and speed and is equivalent to level 6. 120275793eaSopenharmony_ciLevel 0 actually does no compression at all, and in fact expands the data slightly to produce 121275793eaSopenharmony_cithe <em>zlib</em> format (it is not a byte-for-byte copy of the input). 122275793eaSopenharmony_ciMore advanced applications of <em>zlib</em> 123275793eaSopenharmony_cimay use <tt>deflateInit2()</tt> here instead. Such an application may want to reduce how 124275793eaSopenharmony_cimuch memory will be used, at some price in compression. Or it may need to request a 125275793eaSopenharmony_ci<em>gzip</em> header and trailer instead of a <em>zlib</em> header and trailer, or raw 126275793eaSopenharmony_ciencoding with no header or trailer at all. 127275793eaSopenharmony_ci<p> 128275793eaSopenharmony_ciWe must check the return value of <tt>deflateInit()</tt> against the <em>zlib</em> constant 129275793eaSopenharmony_ci<tt>Z_OK</tt> to make sure that it was able to 130275793eaSopenharmony_ciallocate memory for the internal state, and that the provided arguments were valid. 131275793eaSopenharmony_ci<tt>deflateInit()</tt> will also check that the version of <em>zlib</em> that the <tt>zlib.h</tt> 132275793eaSopenharmony_cifile came from matches the version of <em>zlib</em> actually linked with the program. This 133275793eaSopenharmony_ciis especially important for environments in which <em>zlib</em> is a shared library. 134275793eaSopenharmony_ci<p> 135275793eaSopenharmony_ciNote that an application can initialize multiple, independent <em>zlib</em> streams, which can 136275793eaSopenharmony_cioperate in parallel. The state information maintained in the structure allows the <em>zlib</em> 137275793eaSopenharmony_ciroutines to be reentrant. 138275793eaSopenharmony_ci<pre><b> 139275793eaSopenharmony_ci /* allocate deflate state */ 140275793eaSopenharmony_ci strm.zalloc = Z_NULL; 141275793eaSopenharmony_ci strm.zfree = Z_NULL; 142275793eaSopenharmony_ci strm.opaque = Z_NULL; 143275793eaSopenharmony_ci ret = deflateInit(&strm, level); 144275793eaSopenharmony_ci if (ret != Z_OK) 145275793eaSopenharmony_ci return ret; 146275793eaSopenharmony_ci</b></pre><!-- --> 147275793eaSopenharmony_ciWith the pleasantries out of the way, now we can get down to business. The outer <tt>do</tt>-loop 148275793eaSopenharmony_cireads all of the input file and exits at the bottom of the loop once end-of-file is reached. 149275793eaSopenharmony_ciThis loop contains the only call of <tt>deflate()</tt>. So we must make sure that all of the 150275793eaSopenharmony_ciinput data has been processed and that all of the output data has been generated and consumed 151275793eaSopenharmony_cibefore we fall out of the loop at the bottom. 152275793eaSopenharmony_ci<pre><b> 153275793eaSopenharmony_ci /* compress until end of file */ 154275793eaSopenharmony_ci do { 155275793eaSopenharmony_ci</b></pre> 156275793eaSopenharmony_ciWe start off by reading data from the input file. The number of bytes read is put directly 157275793eaSopenharmony_ciinto <tt>avail_in</tt>, and a pointer to those bytes is put into <tt>next_in</tt>. We also 158275793eaSopenharmony_cicheck to see if end-of-file on the input has been reached using feof(). 159275793eaSopenharmony_ciIf we are at the end of file, then <tt>flush</tt> is set to the 160275793eaSopenharmony_ci<em>zlib</em> constant <tt>Z_FINISH</tt>, which is later passed to <tt>deflate()</tt> to 161275793eaSopenharmony_ciindicate that this is the last chunk of input data to compress. 162275793eaSopenharmony_ciIf we are not yet at the end of the input, then the <em>zlib</em> 163275793eaSopenharmony_ciconstant <tt>Z_NO_FLUSH</tt> will be passed to <tt>deflate</tt> to indicate that we are still 164275793eaSopenharmony_ciin the middle of the uncompressed data. 165275793eaSopenharmony_ci<p> 166275793eaSopenharmony_ciIf there is an error in reading from the input file, the process is aborted with 167275793eaSopenharmony_ci<tt>deflateEnd()</tt> being called to free the allocated <em>zlib</em> state before returning 168275793eaSopenharmony_cithe error. We wouldn't want a memory leak, now would we? <tt>deflateEnd()</tt> can be called 169275793eaSopenharmony_ciat any time after the state has been initialized. Once that's done, <tt>deflateInit()</tt> (or 170275793eaSopenharmony_ci<tt>deflateInit2()</tt>) would have to be called to start a new compression process. There is 171275793eaSopenharmony_cino point here in checking the <tt>deflateEnd()</tt> return code. The deallocation can't fail. 172275793eaSopenharmony_ci<pre><b> 173275793eaSopenharmony_ci strm.avail_in = fread(in, 1, CHUNK, source); 174275793eaSopenharmony_ci if (ferror(source)) { 175275793eaSopenharmony_ci (void)deflateEnd(&strm); 176275793eaSopenharmony_ci return Z_ERRNO; 177275793eaSopenharmony_ci } 178275793eaSopenharmony_ci flush = feof(source) ? Z_FINISH : Z_NO_FLUSH; 179275793eaSopenharmony_ci strm.next_in = in; 180275793eaSopenharmony_ci</b></pre><!-- --> 181275793eaSopenharmony_ciThe inner <tt>do</tt>-loop passes our chunk of input data to <tt>deflate()</tt>, and then 182275793eaSopenharmony_cikeeps calling <tt>deflate()</tt> until it is done producing output. Once there is no more 183275793eaSopenharmony_cinew output, <tt>deflate()</tt> is guaranteed to have consumed all of the input, i.e., 184275793eaSopenharmony_ci<tt>avail_in</tt> will be zero. 185275793eaSopenharmony_ci<pre><b> 186275793eaSopenharmony_ci /* run deflate() on input until output buffer not full, finish 187275793eaSopenharmony_ci compression if all of source has been read in */ 188275793eaSopenharmony_ci do { 189275793eaSopenharmony_ci</b></pre> 190275793eaSopenharmony_ciOutput space is provided to <tt>deflate()</tt> by setting <tt>avail_out</tt> to the number 191275793eaSopenharmony_ciof available output bytes and <tt>next_out</tt> to a pointer to that space. 192275793eaSopenharmony_ci<pre><b> 193275793eaSopenharmony_ci strm.avail_out = CHUNK; 194275793eaSopenharmony_ci strm.next_out = out; 195275793eaSopenharmony_ci</b></pre> 196275793eaSopenharmony_ciNow we call the compression engine itself, <tt>deflate()</tt>. It takes as many of the 197275793eaSopenharmony_ci<tt>avail_in</tt> bytes at <tt>next_in</tt> as it can process, and writes as many as 198275793eaSopenharmony_ci<tt>avail_out</tt> bytes to <tt>next_out</tt>. Those counters and pointers are then 199275793eaSopenharmony_ciupdated past the input data consumed and the output data written. It is the amount of 200275793eaSopenharmony_cioutput space available that may limit how much input is consumed. 201275793eaSopenharmony_ciHence the inner loop to make sure that 202275793eaSopenharmony_ciall of the input is consumed by providing more output space each time. Since <tt>avail_in</tt> 203275793eaSopenharmony_ciand <tt>next_in</tt> are updated by <tt>deflate()</tt>, we don't have to mess with those 204275793eaSopenharmony_cibetween <tt>deflate()</tt> calls until it's all used up. 205275793eaSopenharmony_ci<p> 206275793eaSopenharmony_ciThe parameters to <tt>deflate()</tt> are a pointer to the <tt>strm</tt> structure containing 207275793eaSopenharmony_cithe input and output information and the internal compression engine state, and a parameter 208275793eaSopenharmony_ciindicating whether and how to flush data to the output. Normally <tt>deflate</tt> will consume 209275793eaSopenharmony_ciseveral K bytes of input data before producing any output (except for the header), in order 210275793eaSopenharmony_cito accumulate statistics on the data for optimum compression. It will then put out a burst of 211275793eaSopenharmony_cicompressed data, and proceed to consume more input before the next burst. Eventually, 212275793eaSopenharmony_ci<tt>deflate()</tt> 213275793eaSopenharmony_cimust be told to terminate the stream, complete the compression with provided input data, and 214275793eaSopenharmony_ciwrite out the trailer check value. <tt>deflate()</tt> will continue to compress normally as long 215275793eaSopenharmony_cias the flush parameter is <tt>Z_NO_FLUSH</tt>. Once the <tt>Z_FINISH</tt> parameter is provided, 216275793eaSopenharmony_ci<tt>deflate()</tt> will begin to complete the compressed output stream. However depending on how 217275793eaSopenharmony_cimuch output space is provided, <tt>deflate()</tt> may have to be called several times until it 218275793eaSopenharmony_cihas provided the complete compressed stream, even after it has consumed all of the input. The flush 219275793eaSopenharmony_ciparameter must continue to be <tt>Z_FINISH</tt> for those subsequent calls. 220275793eaSopenharmony_ci<p> 221275793eaSopenharmony_ciThere are other values of the flush parameter that are used in more advanced applications. You can 222275793eaSopenharmony_ciforce <tt>deflate()</tt> to produce a burst of output that encodes all of the input data provided 223275793eaSopenharmony_ciso far, even if it wouldn't have otherwise, for example to control data latency on a link with 224275793eaSopenharmony_cicompressed data. You can also ask that <tt>deflate()</tt> do that as well as erase any history up to 225275793eaSopenharmony_cithat point so that what follows can be decompressed independently, for example for random access 226275793eaSopenharmony_ciapplications. Both requests will degrade compression by an amount depending on how often such 227275793eaSopenharmony_cirequests are made. 228275793eaSopenharmony_ci<p> 229275793eaSopenharmony_ci<tt>deflate()</tt> has a return value that can indicate errors, yet we do not check it here. Why 230275793eaSopenharmony_cinot? Well, it turns out that <tt>deflate()</tt> can do no wrong here. Let's go through 231275793eaSopenharmony_ci<tt>deflate()</tt>'s return values and dispense with them one by one. The possible values are 232275793eaSopenharmony_ci<tt>Z_OK</tt>, <tt>Z_STREAM_END</tt>, <tt>Z_STREAM_ERROR</tt>, or <tt>Z_BUF_ERROR</tt>. <tt>Z_OK</tt> 233275793eaSopenharmony_ciis, well, ok. <tt>Z_STREAM_END</tt> is also ok and will be returned for the last call of 234275793eaSopenharmony_ci<tt>deflate()</tt>. This is already guaranteed by calling <tt>deflate()</tt> with <tt>Z_FINISH</tt> 235275793eaSopenharmony_ciuntil it has no more output. <tt>Z_STREAM_ERROR</tt> is only possible if the stream is not 236275793eaSopenharmony_ciinitialized properly, but we did initialize it properly. There is no harm in checking for 237275793eaSopenharmony_ci<tt>Z_STREAM_ERROR</tt> here, for example to check for the possibility that some 238275793eaSopenharmony_ciother part of the application inadvertently clobbered the memory containing the <em>zlib</em> state. 239275793eaSopenharmony_ci<tt>Z_BUF_ERROR</tt> will be explained further below, but 240275793eaSopenharmony_cisuffice it to say that this is simply an indication that <tt>deflate()</tt> could not consume 241275793eaSopenharmony_cimore input or produce more output. <tt>deflate()</tt> can be called again with more output space 242275793eaSopenharmony_cior more available input, which it will be in this code. 243275793eaSopenharmony_ci<pre><b> 244275793eaSopenharmony_ci ret = deflate(&strm, flush); /* no bad return value */ 245275793eaSopenharmony_ci assert(ret != Z_STREAM_ERROR); /* state not clobbered */ 246275793eaSopenharmony_ci</b></pre> 247275793eaSopenharmony_ciNow we compute how much output <tt>deflate()</tt> provided on the last call, which is the 248275793eaSopenharmony_cidifference between how much space was provided before the call, and how much output space 249275793eaSopenharmony_ciis still available after the call. Then that data, if any, is written to the output file. 250275793eaSopenharmony_ciWe can then reuse the output buffer for the next call of <tt>deflate()</tt>. Again if there 251275793eaSopenharmony_ciis a file i/o error, we call <tt>deflateEnd()</tt> before returning to avoid a memory leak. 252275793eaSopenharmony_ci<pre><b> 253275793eaSopenharmony_ci have = CHUNK - strm.avail_out; 254275793eaSopenharmony_ci if (fwrite(out, 1, have, dest) != have || ferror(dest)) { 255275793eaSopenharmony_ci (void)deflateEnd(&strm); 256275793eaSopenharmony_ci return Z_ERRNO; 257275793eaSopenharmony_ci } 258275793eaSopenharmony_ci</b></pre> 259275793eaSopenharmony_ciThe inner <tt>do</tt>-loop is repeated until the last <tt>deflate()</tt> call fails to fill the 260275793eaSopenharmony_ciprovided output buffer. Then we know that <tt>deflate()</tt> has done as much as it can with 261275793eaSopenharmony_cithe provided input, and that all of that input has been consumed. We can then fall out of this 262275793eaSopenharmony_ciloop and reuse the input buffer. 263275793eaSopenharmony_ci<p> 264275793eaSopenharmony_ciThe way we tell that <tt>deflate()</tt> has no more output is by seeing that it did not fill 265275793eaSopenharmony_cithe output buffer, leaving <tt>avail_out</tt> greater than zero. However suppose that 266275793eaSopenharmony_ci<tt>deflate()</tt> has no more output, but just so happened to exactly fill the output buffer! 267275793eaSopenharmony_ci<tt>avail_out</tt> is zero, and we can't tell that <tt>deflate()</tt> has done all it can. 268275793eaSopenharmony_ciAs far as we know, <tt>deflate()</tt> 269275793eaSopenharmony_cihas more output for us. So we call it again. But now <tt>deflate()</tt> produces no output 270275793eaSopenharmony_ciat all, and <tt>avail_out</tt> remains unchanged as <tt>CHUNK</tt>. That <tt>deflate()</tt> call 271275793eaSopenharmony_ciwasn't able to do anything, either consume input or produce output, and so it returns 272275793eaSopenharmony_ci<tt>Z_BUF_ERROR</tt>. (See, I told you I'd cover this later.) However this is not a problem at 273275793eaSopenharmony_ciall. Now we finally have the desired indication that <tt>deflate()</tt> is really done, 274275793eaSopenharmony_ciand so we drop out of the inner loop to provide more input to <tt>deflate()</tt>. 275275793eaSopenharmony_ci<p> 276275793eaSopenharmony_ciWith <tt>flush</tt> set to <tt>Z_FINISH</tt>, this final set of <tt>deflate()</tt> calls will 277275793eaSopenharmony_cicomplete the output stream. Once that is done, subsequent calls of <tt>deflate()</tt> would return 278275793eaSopenharmony_ci<tt>Z_STREAM_ERROR</tt> if the flush parameter is not <tt>Z_FINISH</tt>, and do no more processing 279275793eaSopenharmony_ciuntil the state is reinitialized. 280275793eaSopenharmony_ci<p> 281275793eaSopenharmony_ciSome applications of <em>zlib</em> have two loops that call <tt>deflate()</tt> 282275793eaSopenharmony_ciinstead of the single inner loop we have here. The first loop would call 283275793eaSopenharmony_ciwithout flushing and feed all of the data to <tt>deflate()</tt>. The second loop would call 284275793eaSopenharmony_ci<tt>deflate()</tt> with no more 285275793eaSopenharmony_cidata and the <tt>Z_FINISH</tt> parameter to complete the process. As you can see from this 286275793eaSopenharmony_ciexample, that can be avoided by simply keeping track of the current flush state. 287275793eaSopenharmony_ci<pre><b> 288275793eaSopenharmony_ci } while (strm.avail_out == 0); 289275793eaSopenharmony_ci assert(strm.avail_in == 0); /* all input will be used */ 290275793eaSopenharmony_ci</b></pre><!-- --> 291275793eaSopenharmony_ciNow we check to see if we have already processed all of the input file. That information was 292275793eaSopenharmony_cisaved in the <tt>flush</tt> variable, so we see if that was set to <tt>Z_FINISH</tt>. If so, 293275793eaSopenharmony_cithen we're done and we fall out of the outer loop. We're guaranteed to get <tt>Z_STREAM_END</tt> 294275793eaSopenharmony_cifrom the last <tt>deflate()</tt> call, since we ran it until the last chunk of input was 295275793eaSopenharmony_ciconsumed and all of the output was generated. 296275793eaSopenharmony_ci<pre><b> 297275793eaSopenharmony_ci /* done when last data in file processed */ 298275793eaSopenharmony_ci } while (flush != Z_FINISH); 299275793eaSopenharmony_ci assert(ret == Z_STREAM_END); /* stream will be complete */ 300275793eaSopenharmony_ci</b></pre><!-- --> 301275793eaSopenharmony_ciThe process is complete, but we still need to deallocate the state to avoid a memory leak 302275793eaSopenharmony_ci(or rather more like a memory hemorrhage if you didn't do this). Then 303275793eaSopenharmony_cifinally we can return with a happy return value. 304275793eaSopenharmony_ci<pre><b> 305275793eaSopenharmony_ci /* clean up and return */ 306275793eaSopenharmony_ci (void)deflateEnd(&strm); 307275793eaSopenharmony_ci return Z_OK; 308275793eaSopenharmony_ci} 309275793eaSopenharmony_ci</b></pre><!-- --> 310275793eaSopenharmony_ciNow we do the same thing for decompression in the <tt>inf()</tt> routine. <tt>inf()</tt> 311275793eaSopenharmony_cidecompresses what is hopefully a valid <em>zlib</em> stream from the input file and writes the 312275793eaSopenharmony_ciuncompressed data to the output file. Much of the discussion above for <tt>def()</tt> 313275793eaSopenharmony_ciapplies to <tt>inf()</tt> as well, so the discussion here will focus on the differences between 314275793eaSopenharmony_cithe two. 315275793eaSopenharmony_ci<pre><b> 316275793eaSopenharmony_ci/* Decompress from file source to file dest until stream ends or EOF. 317275793eaSopenharmony_ci inf() returns Z_OK on success, Z_MEM_ERROR if memory could not be 318275793eaSopenharmony_ci allocated for processing, Z_DATA_ERROR if the deflate data is 319275793eaSopenharmony_ci invalid or incomplete, Z_VERSION_ERROR if the version of zlib.h and 320275793eaSopenharmony_ci the version of the library linked do not match, or Z_ERRNO if there 321275793eaSopenharmony_ci is an error reading or writing the files. */ 322275793eaSopenharmony_ciint inf(FILE *source, FILE *dest) 323275793eaSopenharmony_ci{ 324275793eaSopenharmony_ci</b></pre> 325275793eaSopenharmony_ciThe local variables have the same functionality as they do for <tt>def()</tt>. The 326275793eaSopenharmony_cionly difference is that there is no <tt>flush</tt> variable, since <tt>inflate()</tt> 327275793eaSopenharmony_cican tell from the <em>zlib</em> stream itself when the stream is complete. 328275793eaSopenharmony_ci<pre><b> 329275793eaSopenharmony_ci int ret; 330275793eaSopenharmony_ci unsigned have; 331275793eaSopenharmony_ci z_stream strm; 332275793eaSopenharmony_ci unsigned char in[CHUNK]; 333275793eaSopenharmony_ci unsigned char out[CHUNK]; 334275793eaSopenharmony_ci</b></pre><!-- --> 335275793eaSopenharmony_ciThe initialization of the state is the same, except that there is no compression level, 336275793eaSopenharmony_ciof course, and two more elements of the structure are initialized. <tt>avail_in</tt> 337275793eaSopenharmony_ciand <tt>next_in</tt> must be initialized before calling <tt>inflateInit()</tt>. This 338275793eaSopenharmony_ciis because the application has the option to provide the start of the zlib stream in 339275793eaSopenharmony_ciorder for <tt>inflateInit()</tt> to have access to information about the compression 340275793eaSopenharmony_cimethod to aid in memory allocation. In the current implementation of <em>zlib</em> 341275793eaSopenharmony_ci(up through versions 1.2.x), the method-dependent memory allocations are deferred to the first call of 342275793eaSopenharmony_ci<tt>inflate()</tt> anyway. However those fields must be initialized since later versions 343275793eaSopenharmony_ciof <em>zlib</em> that provide more compression methods may take advantage of this interface. 344275793eaSopenharmony_ciIn any case, no decompression is performed by <tt>inflateInit()</tt>, so the 345275793eaSopenharmony_ci<tt>avail_out</tt> and <tt>next_out</tt> fields do not need to be initialized before calling. 346275793eaSopenharmony_ci<p> 347275793eaSopenharmony_ciHere <tt>avail_in</tt> is set to zero and <tt>next_in</tt> is set to <tt>Z_NULL</tt> to 348275793eaSopenharmony_ciindicate that no input data is being provided. 349275793eaSopenharmony_ci<pre><b> 350275793eaSopenharmony_ci /* allocate inflate state */ 351275793eaSopenharmony_ci strm.zalloc = Z_NULL; 352275793eaSopenharmony_ci strm.zfree = Z_NULL; 353275793eaSopenharmony_ci strm.opaque = Z_NULL; 354275793eaSopenharmony_ci strm.avail_in = 0; 355275793eaSopenharmony_ci strm.next_in = Z_NULL; 356275793eaSopenharmony_ci ret = inflateInit(&strm); 357275793eaSopenharmony_ci if (ret != Z_OK) 358275793eaSopenharmony_ci return ret; 359275793eaSopenharmony_ci</b></pre><!-- --> 360275793eaSopenharmony_ciThe outer <tt>do</tt>-loop decompresses input until <tt>inflate()</tt> indicates 361275793eaSopenharmony_cithat it has reached the end of the compressed data and has produced all of the uncompressed 362275793eaSopenharmony_cioutput. This is in contrast to <tt>def()</tt> which processes all of the input file. 363275793eaSopenharmony_ciIf end-of-file is reached before the compressed data self-terminates, then the compressed 364275793eaSopenharmony_cidata is incomplete and an error is returned. 365275793eaSopenharmony_ci<pre><b> 366275793eaSopenharmony_ci /* decompress until deflate stream ends or end of file */ 367275793eaSopenharmony_ci do { 368275793eaSopenharmony_ci</b></pre> 369275793eaSopenharmony_ciWe read input data and set the <tt>strm</tt> structure accordingly. If we've reached the 370275793eaSopenharmony_ciend of the input file, then we leave the outer loop and report an error, since the 371275793eaSopenharmony_cicompressed data is incomplete. Note that we may read more data than is eventually consumed 372275793eaSopenharmony_ciby <tt>inflate()</tt>, if the input file continues past the <em>zlib</em> stream. 373275793eaSopenharmony_ciFor applications where <em>zlib</em> streams are embedded in other data, this routine would 374275793eaSopenharmony_cineed to be modified to return the unused data, or at least indicate how much of the input 375275793eaSopenharmony_cidata was not used, so the application would know where to pick up after the <em>zlib</em> stream. 376275793eaSopenharmony_ci<pre><b> 377275793eaSopenharmony_ci strm.avail_in = fread(in, 1, CHUNK, source); 378275793eaSopenharmony_ci if (ferror(source)) { 379275793eaSopenharmony_ci (void)inflateEnd(&strm); 380275793eaSopenharmony_ci return Z_ERRNO; 381275793eaSopenharmony_ci } 382275793eaSopenharmony_ci if (strm.avail_in == 0) 383275793eaSopenharmony_ci break; 384275793eaSopenharmony_ci strm.next_in = in; 385275793eaSopenharmony_ci</b></pre><!-- --> 386275793eaSopenharmony_ciThe inner <tt>do</tt>-loop has the same function it did in <tt>def()</tt>, which is to 387275793eaSopenharmony_cikeep calling <tt>inflate()</tt> until has generated all of the output it can with the 388275793eaSopenharmony_ciprovided input. 389275793eaSopenharmony_ci<pre><b> 390275793eaSopenharmony_ci /* run inflate() on input until output buffer not full */ 391275793eaSopenharmony_ci do { 392275793eaSopenharmony_ci</b></pre> 393275793eaSopenharmony_ciJust like in <tt>def()</tt>, the same output space is provided for each call of <tt>inflate()</tt>. 394275793eaSopenharmony_ci<pre><b> 395275793eaSopenharmony_ci strm.avail_out = CHUNK; 396275793eaSopenharmony_ci strm.next_out = out; 397275793eaSopenharmony_ci</b></pre> 398275793eaSopenharmony_ciNow we run the decompression engine itself. There is no need to adjust the flush parameter, since 399275793eaSopenharmony_cithe <em>zlib</em> format is self-terminating. The main difference here is that there are 400275793eaSopenharmony_cireturn values that we need to pay attention to. <tt>Z_DATA_ERROR</tt> 401275793eaSopenharmony_ciindicates that <tt>inflate()</tt> detected an error in the <em>zlib</em> compressed data format, 402275793eaSopenharmony_ciwhich means that either the data is not a <em>zlib</em> stream to begin with, or that the data was 403275793eaSopenharmony_cicorrupted somewhere along the way since it was compressed. The other error to be processed is 404275793eaSopenharmony_ci<tt>Z_MEM_ERROR</tt>, which can occur since memory allocation is deferred until <tt>inflate()</tt> 405275793eaSopenharmony_cineeds it, unlike <tt>deflate()</tt>, whose memory is allocated at the start by <tt>deflateInit()</tt>. 406275793eaSopenharmony_ci<p> 407275793eaSopenharmony_ciAdvanced applications may use 408275793eaSopenharmony_ci<tt>deflateSetDictionary()</tt> to prime <tt>deflate()</tt> with a set of likely data to improve the 409275793eaSopenharmony_cifirst 32K or so of compression. This is noted in the <em>zlib</em> header, so <tt>inflate()</tt> 410275793eaSopenharmony_cirequests that that dictionary be provided before it can start to decompress. Without the dictionary, 411275793eaSopenharmony_cicorrect decompression is not possible. For this routine, we have no idea what the dictionary is, 412275793eaSopenharmony_ciso the <tt>Z_NEED_DICT</tt> indication is converted to a <tt>Z_DATA_ERROR</tt>. 413275793eaSopenharmony_ci<p> 414275793eaSopenharmony_ci<tt>inflate()</tt> can also return <tt>Z_STREAM_ERROR</tt>, which should not be possible here, 415275793eaSopenharmony_cibut could be checked for as noted above for <tt>def()</tt>. <tt>Z_BUF_ERROR</tt> does not need to be 416275793eaSopenharmony_cichecked for here, for the same reasons noted for <tt>def()</tt>. <tt>Z_STREAM_END</tt> will be 417275793eaSopenharmony_cichecked for later. 418275793eaSopenharmony_ci<pre><b> 419275793eaSopenharmony_ci ret = inflate(&strm, Z_NO_FLUSH); 420275793eaSopenharmony_ci assert(ret != Z_STREAM_ERROR); /* state not clobbered */ 421275793eaSopenharmony_ci switch (ret) { 422275793eaSopenharmony_ci case Z_NEED_DICT: 423275793eaSopenharmony_ci ret = Z_DATA_ERROR; /* and fall through */ 424275793eaSopenharmony_ci case Z_DATA_ERROR: 425275793eaSopenharmony_ci case Z_MEM_ERROR: 426275793eaSopenharmony_ci (void)inflateEnd(&strm); 427275793eaSopenharmony_ci return ret; 428275793eaSopenharmony_ci } 429275793eaSopenharmony_ci</b></pre> 430275793eaSopenharmony_ciThe output of <tt>inflate()</tt> is handled identically to that of <tt>deflate()</tt>. 431275793eaSopenharmony_ci<pre><b> 432275793eaSopenharmony_ci have = CHUNK - strm.avail_out; 433275793eaSopenharmony_ci if (fwrite(out, 1, have, dest) != have || ferror(dest)) { 434275793eaSopenharmony_ci (void)inflateEnd(&strm); 435275793eaSopenharmony_ci return Z_ERRNO; 436275793eaSopenharmony_ci } 437275793eaSopenharmony_ci</b></pre> 438275793eaSopenharmony_ciThe inner <tt>do</tt>-loop ends when <tt>inflate()</tt> has no more output as indicated 439275793eaSopenharmony_ciby not filling the output buffer, just as for <tt>deflate()</tt>. In this case, we cannot 440275793eaSopenharmony_ciassert that <tt>strm.avail_in</tt> will be zero, since the deflate stream may end before the file 441275793eaSopenharmony_cidoes. 442275793eaSopenharmony_ci<pre><b> 443275793eaSopenharmony_ci } while (strm.avail_out == 0); 444275793eaSopenharmony_ci</b></pre><!-- --> 445275793eaSopenharmony_ciThe outer <tt>do</tt>-loop ends when <tt>inflate()</tt> reports that it has reached the 446275793eaSopenharmony_ciend of the input <em>zlib</em> stream, has completed the decompression and integrity 447275793eaSopenharmony_cicheck, and has provided all of the output. This is indicated by the <tt>inflate()</tt> 448275793eaSopenharmony_cireturn value <tt>Z_STREAM_END</tt>. The inner loop is guaranteed to leave <tt>ret</tt> 449275793eaSopenharmony_ciequal to <tt>Z_STREAM_END</tt> if the last chunk of the input file read contained the end 450275793eaSopenharmony_ciof the <em>zlib</em> stream. So if the return value is not <tt>Z_STREAM_END</tt>, the 451275793eaSopenharmony_ciloop continues to read more input. 452275793eaSopenharmony_ci<pre><b> 453275793eaSopenharmony_ci /* done when inflate() says it's done */ 454275793eaSopenharmony_ci } while (ret != Z_STREAM_END); 455275793eaSopenharmony_ci</b></pre><!-- --> 456275793eaSopenharmony_ciAt this point, decompression successfully completed, or we broke out of the loop due to no 457275793eaSopenharmony_cimore data being available from the input file. If the last <tt>inflate()</tt> return value 458275793eaSopenharmony_ciis not <tt>Z_STREAM_END</tt>, then the <em>zlib</em> stream was incomplete and a data error 459275793eaSopenharmony_ciis returned. Otherwise, we return with a happy return value. Of course, <tt>inflateEnd()</tt> 460275793eaSopenharmony_ciis called first to avoid a memory leak. 461275793eaSopenharmony_ci<pre><b> 462275793eaSopenharmony_ci /* clean up and return */ 463275793eaSopenharmony_ci (void)inflateEnd(&strm); 464275793eaSopenharmony_ci return ret == Z_STREAM_END ? Z_OK : Z_DATA_ERROR; 465275793eaSopenharmony_ci} 466275793eaSopenharmony_ci</b></pre><!-- --> 467275793eaSopenharmony_ciThat ends the routines that directly use <em>zlib</em>. The following routines make this 468275793eaSopenharmony_cia command-line program by running data through the above routines from <tt>stdin</tt> to 469275793eaSopenharmony_ci<tt>stdout</tt>, and handling any errors reported by <tt>def()</tt> or <tt>inf()</tt>. 470275793eaSopenharmony_ci<p> 471275793eaSopenharmony_ci<tt>zerr()</tt> is used to interpret the possible error codes from <tt>def()</tt> 472275793eaSopenharmony_ciand <tt>inf()</tt>, as detailed in their comments above, and print out an error message. 473275793eaSopenharmony_ciNote that these are only a subset of the possible return values from <tt>deflate()</tt> 474275793eaSopenharmony_ciand <tt>inflate()</tt>. 475275793eaSopenharmony_ci<pre><b> 476275793eaSopenharmony_ci/* report a zlib or i/o error */ 477275793eaSopenharmony_civoid zerr(int ret) 478275793eaSopenharmony_ci{ 479275793eaSopenharmony_ci fputs("zpipe: ", stderr); 480275793eaSopenharmony_ci switch (ret) { 481275793eaSopenharmony_ci case Z_ERRNO: 482275793eaSopenharmony_ci if (ferror(stdin)) 483275793eaSopenharmony_ci fputs("error reading stdin\n", stderr); 484275793eaSopenharmony_ci if (ferror(stdout)) 485275793eaSopenharmony_ci fputs("error writing stdout\n", stderr); 486275793eaSopenharmony_ci break; 487275793eaSopenharmony_ci case Z_STREAM_ERROR: 488275793eaSopenharmony_ci fputs("invalid compression level\n", stderr); 489275793eaSopenharmony_ci break; 490275793eaSopenharmony_ci case Z_DATA_ERROR: 491275793eaSopenharmony_ci fputs("invalid or incomplete deflate data\n", stderr); 492275793eaSopenharmony_ci break; 493275793eaSopenharmony_ci case Z_MEM_ERROR: 494275793eaSopenharmony_ci fputs("out of memory\n", stderr); 495275793eaSopenharmony_ci break; 496275793eaSopenharmony_ci case Z_VERSION_ERROR: 497275793eaSopenharmony_ci fputs("zlib version mismatch!\n", stderr); 498275793eaSopenharmony_ci } 499275793eaSopenharmony_ci} 500275793eaSopenharmony_ci</b></pre><!-- --> 501275793eaSopenharmony_ciHere is the <tt>main()</tt> routine used to test <tt>def()</tt> and <tt>inf()</tt>. The 502275793eaSopenharmony_ci<tt>zpipe</tt> command is simply a compression pipe from <tt>stdin</tt> to <tt>stdout</tt>, if 503275793eaSopenharmony_cino arguments are given, or it is a decompression pipe if <tt>zpipe -d</tt> is used. If any other 504275793eaSopenharmony_ciarguments are provided, no compression or decompression is performed. Instead a usage 505275793eaSopenharmony_cimessage is displayed. Examples are <tt>zpipe < foo.txt > foo.txt.z</tt> to compress, and 506275793eaSopenharmony_ci<tt>zpipe -d < foo.txt.z > foo.txt</tt> to decompress. 507275793eaSopenharmony_ci<pre><b> 508275793eaSopenharmony_ci/* compress or decompress from stdin to stdout */ 509275793eaSopenharmony_ciint main(int argc, char **argv) 510275793eaSopenharmony_ci{ 511275793eaSopenharmony_ci int ret; 512275793eaSopenharmony_ci 513275793eaSopenharmony_ci /* avoid end-of-line conversions */ 514275793eaSopenharmony_ci SET_BINARY_MODE(stdin); 515275793eaSopenharmony_ci SET_BINARY_MODE(stdout); 516275793eaSopenharmony_ci 517275793eaSopenharmony_ci /* do compression if no arguments */ 518275793eaSopenharmony_ci if (argc == 1) { 519275793eaSopenharmony_ci ret = def(stdin, stdout, Z_DEFAULT_COMPRESSION); 520275793eaSopenharmony_ci if (ret != Z_OK) 521275793eaSopenharmony_ci zerr(ret); 522275793eaSopenharmony_ci return ret; 523275793eaSopenharmony_ci } 524275793eaSopenharmony_ci 525275793eaSopenharmony_ci /* do decompression if -d specified */ 526275793eaSopenharmony_ci else if (argc == 2 && strcmp(argv[1], "-d") == 0) { 527275793eaSopenharmony_ci ret = inf(stdin, stdout); 528275793eaSopenharmony_ci if (ret != Z_OK) 529275793eaSopenharmony_ci zerr(ret); 530275793eaSopenharmony_ci return ret; 531275793eaSopenharmony_ci } 532275793eaSopenharmony_ci 533275793eaSopenharmony_ci /* otherwise, report usage */ 534275793eaSopenharmony_ci else { 535275793eaSopenharmony_ci fputs("zpipe usage: zpipe [-d] < source > dest\n", stderr); 536275793eaSopenharmony_ci return 1; 537275793eaSopenharmony_ci } 538275793eaSopenharmony_ci} 539275793eaSopenharmony_ci</b></pre> 540275793eaSopenharmony_ci<hr> 541275793eaSopenharmony_ci<i>Last modified 24 January 2023<br> 542275793eaSopenharmony_ciCopyright © 2004-2023 Mark Adler</i><br> 543275793eaSopenharmony_ci<a rel="license" href="http://creativecommons.org/licenses/by-nd/4.0/"> 544275793eaSopenharmony_ci<img alt="Creative Commons License" style="border-width:0" 545275793eaSopenharmony_cisrc="https://i.creativecommons.org/l/by-nd/4.0/88x31.png"></a> 546275793eaSopenharmony_ci<a rel="license" href="http://creativecommons.org/licenses/by-nd/4.0/"> 547275793eaSopenharmony_ciCreative Commons Attribution-NoDerivatives 4.0 International License</a>. 548275793eaSopenharmony_ci</body> 549275793eaSopenharmony_ci</html> 550