1*16dce513Schristos<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" 2*16dce513Schristos "http://www.w3.org/TR/REC-html40/loose.dtd"> 3*16dce513Schristos<html> 4*16dce513Schristos<head> 5*16dce513Schristos<meta http-equiv="Content-Type" content="text/html; charset=ISO-8859-1"> 6*16dce513Schristos<title>zlib Usage Example</title> 7*16dce513Schristos<!-- Copyright (c) 2004, 2005 Mark Adler. --> 8*16dce513Schristos</head> 9*16dce513Schristos<body bgcolor="#FFFFFF" text="#000000" link="#0000FF" vlink="#00A000"> 10*16dce513Schristos<h2 align="center"> zlib Usage Example </h2> 11*16dce513SchristosWe often get questions about how the <tt>deflate()</tt> and <tt>inflate()</tt> functions should be used. 12*16dce513SchristosUsers wonder when they should provide more input, when they should use more output, 13*16dce513Schristoswhat to do with a <tt>Z_BUF_ERROR</tt>, how to make sure the process terminates properly, and 14*16dce513Schristosso on. So for those who have read <tt>zlib.h</tt> (a few times), and 15*16dce513Schristoswould like further edification, below is an annotated example in C of simple routines to compress and decompress 16*16dce513Schristosfrom an input file to an output file using <tt>deflate()</tt> and <tt>inflate()</tt> respectively. The 17*16dce513Schristosannotations are interspersed between lines of the code. So please read between the lines. 18*16dce513SchristosWe hope this helps explain some of the intricacies of <em>zlib</em>. 19*16dce513Schristos<p> 20*16dce513SchristosWithout further adieu, here is the program <a href="zpipe.c"><tt>zpipe.c</tt></a>: 21*16dce513Schristos<pre><b> 22*16dce513Schristos/* zpipe.c: example of proper use of zlib's inflate() and deflate() 23*16dce513Schristos Not copyrighted -- provided to the public domain 24*16dce513Schristos Version 1.4 11 December 2005 Mark Adler */ 25*16dce513Schristos 26*16dce513Schristos/* Version history: 27*16dce513Schristos 1.0 30 Oct 2004 First version 28*16dce513Schristos 1.1 8 Nov 2004 Add void casting for unused return values 29*16dce513Schristos Use switch statement for inflate() return values 30*16dce513Schristos 1.2 9 Nov 2004 Add assertions to document zlib guarantees 31*16dce513Schristos 1.3 6 Apr 2005 Remove incorrect assertion in inf() 32*16dce513Schristos 1.4 11 Dec 2005 Add hack to avoid MSDOS end-of-line conversions 33*16dce513Schristos Avoid some compiler warnings for input and output buffers 34*16dce513Schristos */ 35*16dce513Schristos</b></pre><!-- --> 36*16dce513SchristosWe now include the header files for the required definitions. From 37*16dce513Schristos<tt>stdio.h</tt> we use <tt>fopen()</tt>, <tt>fread()</tt>, <tt>fwrite()</tt>, 38*16dce513Schristos<tt>feof()</tt>, <tt>ferror()</tt>, and <tt>fclose()</tt> for file i/o, and 39*16dce513Schristos<tt>fputs()</tt> for error messages. From <tt>string.h</tt> we use 40*16dce513Schristos<tt>strcmp()</tt> for command line argument processing. 41*16dce513SchristosFrom <tt>assert.h</tt> we use the <tt>assert()</tt> macro. 42*16dce513SchristosFrom <tt>zlib.h</tt> 43*16dce513Schristoswe use the basic compression functions <tt>deflateInit()</tt>, 44*16dce513Schristos<tt>deflate()</tt>, and <tt>deflateEnd()</tt>, and the basic decompression 45*16dce513Schristosfunctions <tt>inflateInit()</tt>, <tt>inflate()</tt>, and 46*16dce513Schristos<tt>inflateEnd()</tt>. 47*16dce513Schristos<pre><b> 48*16dce513Schristos#include <stdio.h> 49*16dce513Schristos#include <string.h> 50*16dce513Schristos#include <assert.h> 51*16dce513Schristos#include "zlib.h" 52*16dce513Schristos</b></pre><!-- --> 53*16dce513SchristosThis is an ugly hack required to avoid corruption of the input and output data on 54*16dce513SchristosWindows/MS-DOS systems. Without this, those systems would assume that the input and output 55*16dce513Schristosfiles are text, and try to convert the end-of-line characters from one standard to 56*16dce513Schristosanother. That would corrupt binary data, and in particular would render the compressed data unusable. 57*16dce513SchristosThis sets the input and output to binary which suppresses the end-of-line conversions. 58*16dce513Schristos<tt>SET_BINARY_MODE()</tt> will be used later on <tt>stdin</tt> and <tt>stdout</tt>, at the beginning of <tt>main()</tt>. 59*16dce513Schristos<pre><b> 60*16dce513Schristos#if defined(MSDOS) || defined(OS2) || defined(WIN32) || defined(__CYGWIN__) 61*16dce513Schristos# include <fcntl.h> 62*16dce513Schristos# include <io.h> 63*16dce513Schristos# define SET_BINARY_MODE(file) setmode(fileno(file), O_BINARY) 64*16dce513Schristos#else 65*16dce513Schristos# define SET_BINARY_MODE(file) 66*16dce513Schristos#endif 67*16dce513Schristos</b></pre><!-- --> 68*16dce513Schristos<tt>CHUNK</tt> is simply the buffer size for feeding data to and pulling data 69*16dce513Schristosfrom the <em>zlib</em> routines. Larger buffer sizes would be more efficient, 70*16dce513Schristosespecially for <tt>inflate()</tt>. If the memory is available, buffers sizes 71*16dce513Schristoson the order of 128K or 256K bytes should be used. 72*16dce513Schristos<pre><b> 73*16dce513Schristos#define CHUNK 16384 74*16dce513Schristos</b></pre><!-- --> 75*16dce513SchristosThe <tt>def()</tt> routine compresses data from an input file to an output file. The output data 76*16dce513Schristoswill be in the <em>zlib</em> format, which is different from the <em>gzip</em> or <em>zip</em> 77*16dce513Schristosformats. The <em>zlib</em> format has a very small header of only two bytes to identify it as 78*16dce513Schristosa <em>zlib</em> stream and to provide decoding information, and a four-byte trailer with a fast 79*16dce513Schristoscheck value to verify the integrity of the uncompressed data after decoding. 80*16dce513Schristos<pre><b> 81*16dce513Schristos/* Compress from file source to file dest until EOF on source. 82*16dce513Schristos def() returns Z_OK on success, Z_MEM_ERROR if memory could not be 83*16dce513Schristos allocated for processing, Z_STREAM_ERROR if an invalid compression 84*16dce513Schristos level is supplied, Z_VERSION_ERROR if the version of zlib.h and the 85*16dce513Schristos version of the library linked do not match, or Z_ERRNO if there is 86*16dce513Schristos an error reading or writing the files. */ 87*16dce513Schristosint def(FILE *source, FILE *dest, int level) 88*16dce513Schristos{ 89*16dce513Schristos</b></pre> 90*16dce513SchristosHere are the local variables for <tt>def()</tt>. <tt>ret</tt> will be used for <em>zlib</em> 91*16dce513Schristosreturn codes. <tt>flush</tt> will keep track of the current flushing state for <tt>deflate()</tt>, 92*16dce513Schristoswhich is either no flushing, or flush to completion after the end of the input file is reached. 93*16dce513Schristos<tt>have</tt> is the amount of data returned from <tt>deflate()</tt>. The <tt>strm</tt> structure 94*16dce513Schristosis used to pass information to and from the <em>zlib</em> routines, and to maintain the 95*16dce513Schristos<tt>deflate()</tt> state. <tt>in</tt> and <tt>out</tt> are the input and output buffers for 96*16dce513Schristos<tt>deflate()</tt>. 97*16dce513Schristos<pre><b> 98*16dce513Schristos int ret, flush; 99*16dce513Schristos unsigned have; 100*16dce513Schristos z_stream strm; 101*16dce513Schristos unsigned char in[CHUNK]; 102*16dce513Schristos unsigned char out[CHUNK]; 103*16dce513Schristos</b></pre><!-- --> 104*16dce513SchristosThe first thing we do is to initialize the <em>zlib</em> state for compression using 105*16dce513Schristos<tt>deflateInit()</tt>. This must be done before the first use of <tt>deflate()</tt>. 106*16dce513SchristosThe <tt>zalloc</tt>, <tt>zfree</tt>, and <tt>opaque</tt> fields in the <tt>strm</tt> 107*16dce513Schristosstructure must be initialized before calling <tt>deflateInit()</tt>. Here they are 108*16dce513Schristosset to the <em>zlib</em> constant <tt>Z_NULL</tt> to request that <em>zlib</em> use 109*16dce513Schristosthe default memory allocation routines. An application may also choose to provide 110*16dce513Schristoscustom memory allocation routines here. <tt>deflateInit()</tt> will allocate on the 111*16dce513Schristosorder of 256K bytes for the internal state. 112*16dce513Schristos(See <a href="zlib_tech.html"><em>zlib Technical Details</em></a>.) 113*16dce513Schristos<p> 114*16dce513Schristos<tt>deflateInit()</tt> is called with a pointer to the structure to be initialized and 115*16dce513Schristosthe compression level, which is an integer in the range of -1 to 9. Lower compression 116*16dce513Schristoslevels result in faster execution, but less compression. Higher levels result in 117*16dce513Schristosgreater compression, but slower execution. The <em>zlib</em> constant Z_DEFAULT_COMPRESSION, 118*16dce513Schristosequal to -1, 119*16dce513Schristosprovides a good compromise between compression and speed and is equivalent to level 6. 120*16dce513SchristosLevel 0 actually does no compression at all, and in fact expands the data slightly to produce 121*16dce513Schristosthe <em>zlib</em> format (it is not a byte-for-byte copy of the input). 122*16dce513SchristosMore advanced applications of <em>zlib</em> 123*16dce513Schristosmay use <tt>deflateInit2()</tt> here instead. Such an application may want to reduce how 124*16dce513Schristosmuch memory will be used, at some price in compression. Or it may need to request a 125*16dce513Schristos<em>gzip</em> header and trailer instead of a <em>zlib</em> header and trailer, or raw 126*16dce513Schristosencoding with no header or trailer at all. 127*16dce513Schristos<p> 128*16dce513SchristosWe must check the return value of <tt>deflateInit()</tt> against the <em>zlib</em> constant 129*16dce513Schristos<tt>Z_OK</tt> to make sure that it was able to 130*16dce513Schristosallocate memory for the internal state, and that the provided arguments were valid. 131*16dce513Schristos<tt>deflateInit()</tt> will also check that the version of <em>zlib</em> that the <tt>zlib.h</tt> 132*16dce513Schristosfile came from matches the version of <em>zlib</em> actually linked with the program. This 133*16dce513Schristosis especially important for environments in which <em>zlib</em> is a shared library. 134*16dce513Schristos<p> 135*16dce513SchristosNote that an application can initialize multiple, independent <em>zlib</em> streams, which can 136*16dce513Schristosoperate in parallel. The state information maintained in the structure allows the <em>zlib</em> 137*16dce513Schristosroutines to be reentrant. 138*16dce513Schristos<pre><b> 139*16dce513Schristos /* allocate deflate state */ 140*16dce513Schristos strm.zalloc = Z_NULL; 141*16dce513Schristos strm.zfree = Z_NULL; 142*16dce513Schristos strm.opaque = Z_NULL; 143*16dce513Schristos ret = deflateInit(&strm, level); 144*16dce513Schristos if (ret != Z_OK) 145*16dce513Schristos return ret; 146*16dce513Schristos</b></pre><!-- --> 147*16dce513SchristosWith the pleasantries out of the way, now we can get down to business. The outer <tt>do</tt>-loop 148*16dce513Schristosreads all of the input file and exits at the bottom of the loop once end-of-file is reached. 149*16dce513SchristosThis loop contains the only call of <tt>deflate()</tt>. So we must make sure that all of the 150*16dce513Schristosinput data has been processed and that all of the output data has been generated and consumed 151*16dce513Schristosbefore we fall out of the loop at the bottom. 152*16dce513Schristos<pre><b> 153*16dce513Schristos /* compress until end of file */ 154*16dce513Schristos do { 155*16dce513Schristos</b></pre> 156*16dce513SchristosWe start off by reading data from the input file. The number of bytes read is put directly 157*16dce513Schristosinto <tt>avail_in</tt>, and a pointer to those bytes is put into <tt>next_in</tt>. We also 158*16dce513Schristoscheck 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 159*16dce513Schristos<em>zlib</em> constant <tt>Z_FINISH</tt>, which is later passed to <tt>deflate()</tt> to 160*16dce513Schristosindicate that this is the last chunk of input data to compress. We need to use <tt>feof()</tt> 161*16dce513Schristosto check for end-of-file as opposed to seeing if fewer than <tt>CHUNK</tt> bytes have been read. The 162*16dce513Schristosreason is that if the input file length is an exact multiple of <tt>CHUNK</tt>, we will miss 163*16dce513Schristosthe fact that we got to the end-of-file, and not know to tell <tt>deflate()</tt> to finish 164*16dce513Schristosup the compressed stream. If we are not yet at the end of the input, then the <em>zlib</em> 165*16dce513Schristosconstant <tt>Z_NO_FLUSH</tt> will be passed to <tt>deflate</tt> to indicate that we are still 166*16dce513Schristosin the middle of the uncompressed data. 167*16dce513Schristos<p> 168*16dce513SchristosIf there is an error in reading from the input file, the process is aborted with 169*16dce513Schristos<tt>deflateEnd()</tt> being called to free the allocated <em>zlib</em> state before returning 170*16dce513Schristosthe error. We wouldn't want a memory leak, now would we? <tt>deflateEnd()</tt> can be called 171*16dce513Schristosat any time after the state has been initialized. Once that's done, <tt>deflateInit()</tt> (or 172*16dce513Schristos<tt>deflateInit2()</tt>) would have to be called to start a new compression process. There is 173*16dce513Schristosno point here in checking the <tt>deflateEnd()</tt> return code. The deallocation can't fail. 174*16dce513Schristos<pre><b> 175*16dce513Schristos strm.avail_in = fread(in, 1, CHUNK, source); 176*16dce513Schristos if (ferror(source)) { 177*16dce513Schristos (void)deflateEnd(&strm); 178*16dce513Schristos return Z_ERRNO; 179*16dce513Schristos } 180*16dce513Schristos flush = feof(source) ? Z_FINISH : Z_NO_FLUSH; 181*16dce513Schristos strm.next_in = in; 182*16dce513Schristos</b></pre><!-- --> 183*16dce513SchristosThe inner <tt>do</tt>-loop passes our chunk of input data to <tt>deflate()</tt>, and then 184*16dce513Schristoskeeps calling <tt>deflate()</tt> until it is done producing output. Once there is no more 185*16dce513Schristosnew output, <tt>deflate()</tt> is guaranteed to have consumed all of the input, i.e., 186*16dce513Schristos<tt>avail_in</tt> will be zero. 187*16dce513Schristos<pre><b> 188*16dce513Schristos /* run deflate() on input until output buffer not full, finish 189*16dce513Schristos compression if all of source has been read in */ 190*16dce513Schristos do { 191*16dce513Schristos</b></pre> 192*16dce513SchristosOutput space is provided to <tt>deflate()</tt> by setting <tt>avail_out</tt> to the number 193*16dce513Schristosof available output bytes and <tt>next_out</tt> to a pointer to that space. 194*16dce513Schristos<pre><b> 195*16dce513Schristos strm.avail_out = CHUNK; 196*16dce513Schristos strm.next_out = out; 197*16dce513Schristos</b></pre> 198*16dce513SchristosNow we call the compression engine itself, <tt>deflate()</tt>. It takes as many of the 199*16dce513Schristos<tt>avail_in</tt> bytes at <tt>next_in</tt> as it can process, and writes as many as 200*16dce513Schristos<tt>avail_out</tt> bytes to <tt>next_out</tt>. Those counters and pointers are then 201*16dce513Schristosupdated past the input data consumed and the output data written. It is the amount of 202*16dce513Schristosoutput space available that may limit how much input is consumed. 203*16dce513SchristosHence the inner loop to make sure that 204*16dce513Schristosall of the input is consumed by providing more output space each time. Since <tt>avail_in</tt> 205*16dce513Schristosand <tt>next_in</tt> are updated by <tt>deflate()</tt>, we don't have to mess with those 206*16dce513Schristosbetween <tt>deflate()</tt> calls until it's all used up. 207*16dce513Schristos<p> 208*16dce513SchristosThe parameters to <tt>deflate()</tt> are a pointer to the <tt>strm</tt> structure containing 209*16dce513Schristosthe input and output information and the internal compression engine state, and a parameter 210*16dce513Schristosindicating whether and how to flush data to the output. Normally <tt>deflate</tt> will consume 211*16dce513Schristosseveral K bytes of input data before producing any output (except for the header), in order 212*16dce513Schristosto accumulate statistics on the data for optimum compression. It will then put out a burst of 213*16dce513Schristoscompressed data, and proceed to consume more input before the next burst. Eventually, 214*16dce513Schristos<tt>deflate()</tt> 215*16dce513Schristosmust be told to terminate the stream, complete the compression with provided input data, and 216*16dce513Schristoswrite out the trailer check value. <tt>deflate()</tt> will continue to compress normally as long 217*16dce513Schristosas the flush parameter is <tt>Z_NO_FLUSH</tt>. Once the <tt>Z_FINISH</tt> parameter is provided, 218*16dce513Schristos<tt>deflate()</tt> will begin to complete the compressed output stream. However depending on how 219*16dce513Schristosmuch output space is provided, <tt>deflate()</tt> may have to be called several times until it 220*16dce513Schristoshas provided the complete compressed stream, even after it has consumed all of the input. The flush 221*16dce513Schristosparameter must continue to be <tt>Z_FINISH</tt> for those subsequent calls. 222*16dce513Schristos<p> 223*16dce513SchristosThere are other values of the flush parameter that are used in more advanced applications. You can 224*16dce513Schristosforce <tt>deflate()</tt> to produce a burst of output that encodes all of the input data provided 225*16dce513Schristosso far, even if it wouldn't have otherwise, for example to control data latency on a link with 226*16dce513Schristoscompressed data. You can also ask that <tt>deflate()</tt> do that as well as erase any history up to 227*16dce513Schristosthat point so that what follows can be decompressed independently, for example for random access 228*16dce513Schristosapplications. Both requests will degrade compression by an amount depending on how often such 229*16dce513Schristosrequests are made. 230*16dce513Schristos<p> 231*16dce513Schristos<tt>deflate()</tt> has a return value that can indicate errors, yet we do not check it here. Why 232*16dce513Schristosnot? Well, it turns out that <tt>deflate()</tt> can do no wrong here. Let's go through 233*16dce513Schristos<tt>deflate()</tt>'s return values and dispense with them one by one. The possible values are 234*16dce513Schristos<tt>Z_OK</tt>, <tt>Z_STREAM_END</tt>, <tt>Z_STREAM_ERROR</tt>, or <tt>Z_BUF_ERROR</tt>. <tt>Z_OK</tt> 235*16dce513Schristosis, well, ok. <tt>Z_STREAM_END</tt> is also ok and will be returned for the last call of 236*16dce513Schristos<tt>deflate()</tt>. This is already guaranteed by calling <tt>deflate()</tt> with <tt>Z_FINISH</tt> 237*16dce513Schristosuntil it has no more output. <tt>Z_STREAM_ERROR</tt> is only possible if the stream is not 238*16dce513Schristosinitialized properly, but we did initialize it properly. There is no harm in checking for 239*16dce513Schristos<tt>Z_STREAM_ERROR</tt> here, for example to check for the possibility that some 240*16dce513Schristosother part of the application inadvertently clobbered the memory containing the <em>zlib</em> state. 241*16dce513Schristos<tt>Z_BUF_ERROR</tt> will be explained further below, but 242*16dce513Schristossuffice it to say that this is simply an indication that <tt>deflate()</tt> could not consume 243*16dce513Schristosmore input or produce more output. <tt>deflate()</tt> can be called again with more output space 244*16dce513Schristosor more available input, which it will be in this code. 245*16dce513Schristos<pre><b> 246*16dce513Schristos ret = deflate(&strm, flush); /* no bad return value */ 247*16dce513Schristos assert(ret != Z_STREAM_ERROR); /* state not clobbered */ 248*16dce513Schristos</b></pre> 249*16dce513SchristosNow we compute how much output <tt>deflate()</tt> provided on the last call, which is the 250*16dce513Schristosdifference between how much space was provided before the call, and how much output space 251*16dce513Schristosis still available after the call. Then that data, if any, is written to the output file. 252*16dce513SchristosWe can then reuse the output buffer for the next call of <tt>deflate()</tt>. Again if there 253*16dce513Schristosis a file i/o error, we call <tt>deflateEnd()</tt> before returning to avoid a memory leak. 254*16dce513Schristos<pre><b> 255*16dce513Schristos have = CHUNK - strm.avail_out; 256*16dce513Schristos if (fwrite(out, 1, have, dest) != have || ferror(dest)) { 257*16dce513Schristos (void)deflateEnd(&strm); 258*16dce513Schristos return Z_ERRNO; 259*16dce513Schristos } 260*16dce513Schristos</b></pre> 261*16dce513SchristosThe inner <tt>do</tt>-loop is repeated until the last <tt>deflate()</tt> call fails to fill the 262*16dce513Schristosprovided output buffer. Then we know that <tt>deflate()</tt> has done as much as it can with 263*16dce513Schristosthe provided input, and that all of that input has been consumed. We can then fall out of this 264*16dce513Schristosloop and reuse the input buffer. 265*16dce513Schristos<p> 266*16dce513SchristosThe way we tell that <tt>deflate()</tt> has no more output is by seeing that it did not fill 267*16dce513Schristosthe output buffer, leaving <tt>avail_out</tt> greater than zero. However suppose that 268*16dce513Schristos<tt>deflate()</tt> has no more output, but just so happened to exactly fill the output buffer! 269*16dce513Schristos<tt>avail_out</tt> is zero, and we can't tell that <tt>deflate()</tt> has done all it can. 270*16dce513SchristosAs far as we know, <tt>deflate()</tt> 271*16dce513Schristoshas more output for us. So we call it again. But now <tt>deflate()</tt> produces no output 272*16dce513Schristosat all, and <tt>avail_out</tt> remains unchanged as <tt>CHUNK</tt>. That <tt>deflate()</tt> call 273*16dce513Schristoswasn't able to do anything, either consume input or produce output, and so it returns 274*16dce513Schristos<tt>Z_BUF_ERROR</tt>. (See, I told you I'd cover this later.) However this is not a problem at 275*16dce513Schristosall. Now we finally have the desired indication that <tt>deflate()</tt> is really done, 276*16dce513Schristosand so we drop out of the inner loop to provide more input to <tt>deflate()</tt>. 277*16dce513Schristos<p> 278*16dce513SchristosWith <tt>flush</tt> set to <tt>Z_FINISH</tt>, this final set of <tt>deflate()</tt> calls will 279*16dce513Schristoscomplete the output stream. Once that is done, subsequent calls of <tt>deflate()</tt> would return 280*16dce513Schristos<tt>Z_STREAM_ERROR</tt> if the flush parameter is not <tt>Z_FINISH</tt>, and do no more processing 281*16dce513Schristosuntil the state is reinitialized. 282*16dce513Schristos<p> 283*16dce513SchristosSome applications of <em>zlib</em> have two loops that call <tt>deflate()</tt> 284*16dce513Schristosinstead of the single inner loop we have here. The first loop would call 285*16dce513Schristoswithout flushing and feed all of the data to <tt>deflate()</tt>. The second loop would call 286*16dce513Schristos<tt>deflate()</tt> with no more 287*16dce513Schristosdata and the <tt>Z_FINISH</tt> parameter to complete the process. As you can see from this 288*16dce513Schristosexample, that can be avoided by simply keeping track of the current flush state. 289*16dce513Schristos<pre><b> 290*16dce513Schristos } while (strm.avail_out == 0); 291*16dce513Schristos assert(strm.avail_in == 0); /* all input will be used */ 292*16dce513Schristos</b></pre><!-- --> 293*16dce513SchristosNow we check to see if we have already processed all of the input file. That information was 294*16dce513Schristossaved in the <tt>flush</tt> variable, so we see if that was set to <tt>Z_FINISH</tt>. If so, 295*16dce513Schristosthen we're done and we fall out of the outer loop. We're guaranteed to get <tt>Z_STREAM_END</tt> 296*16dce513Schristosfrom the last <tt>deflate()</tt> call, since we ran it until the last chunk of input was 297*16dce513Schristosconsumed and all of the output was generated. 298*16dce513Schristos<pre><b> 299*16dce513Schristos /* done when last data in file processed */ 300*16dce513Schristos } while (flush != Z_FINISH); 301*16dce513Schristos assert(ret == Z_STREAM_END); /* stream will be complete */ 302*16dce513Schristos</b></pre><!-- --> 303*16dce513SchristosThe process is complete, but we still need to deallocate the state to avoid a memory leak 304*16dce513Schristos(or rather more like a memory hemorrhage if you didn't do this). Then 305*16dce513Schristosfinally we can return with a happy return value. 306*16dce513Schristos<pre><b> 307*16dce513Schristos /* clean up and return */ 308*16dce513Schristos (void)deflateEnd(&strm); 309*16dce513Schristos return Z_OK; 310*16dce513Schristos} 311*16dce513Schristos</b></pre><!-- --> 312*16dce513SchristosNow we do the same thing for decompression in the <tt>inf()</tt> routine. <tt>inf()</tt> 313*16dce513Schristosdecompresses what is hopefully a valid <em>zlib</em> stream from the input file and writes the 314*16dce513Schristosuncompressed data to the output file. Much of the discussion above for <tt>def()</tt> 315*16dce513Schristosapplies to <tt>inf()</tt> as well, so the discussion here will focus on the differences between 316*16dce513Schristosthe two. 317*16dce513Schristos<pre><b> 318*16dce513Schristos/* Decompress from file source to file dest until stream ends or EOF. 319*16dce513Schristos inf() returns Z_OK on success, Z_MEM_ERROR if memory could not be 320*16dce513Schristos allocated for processing, Z_DATA_ERROR if the deflate data is 321*16dce513Schristos invalid or incomplete, Z_VERSION_ERROR if the version of zlib.h and 322*16dce513Schristos the version of the library linked do not match, or Z_ERRNO if there 323*16dce513Schristos is an error reading or writing the files. */ 324*16dce513Schristosint inf(FILE *source, FILE *dest) 325*16dce513Schristos{ 326*16dce513Schristos</b></pre> 327*16dce513SchristosThe local variables have the same functionality as they do for <tt>def()</tt>. The 328*16dce513Schristosonly difference is that there is no <tt>flush</tt> variable, since <tt>inflate()</tt> 329*16dce513Schristoscan tell from the <em>zlib</em> stream itself when the stream is complete. 330*16dce513Schristos<pre><b> 331*16dce513Schristos int ret; 332*16dce513Schristos unsigned have; 333*16dce513Schristos z_stream strm; 334*16dce513Schristos unsigned char in[CHUNK]; 335*16dce513Schristos unsigned char out[CHUNK]; 336*16dce513Schristos</b></pre><!-- --> 337*16dce513SchristosThe initialization of the state is the same, except that there is no compression level, 338*16dce513Schristosof course, and two more elements of the structure are initialized. <tt>avail_in</tt> 339*16dce513Schristosand <tt>next_in</tt> must be initialized before calling <tt>inflateInit()</tt>. This 340*16dce513Schristosis because the application has the option to provide the start of the zlib stream in 341*16dce513Schristosorder for <tt>inflateInit()</tt> to have access to information about the compression 342*16dce513Schristosmethod to aid in memory allocation. In the current implementation of <em>zlib</em> 343*16dce513Schristos(up through versions 1.2.x), the method-dependent memory allocations are deferred to the first call of 344*16dce513Schristos<tt>inflate()</tt> anyway. However those fields must be initialized since later versions 345*16dce513Schristosof <em>zlib</em> that provide more compression methods may take advantage of this interface. 346*16dce513SchristosIn any case, no decompression is performed by <tt>inflateInit()</tt>, so the 347*16dce513Schristos<tt>avail_out</tt> and <tt>next_out</tt> fields do not need to be initialized before calling. 348*16dce513Schristos<p> 349*16dce513SchristosHere <tt>avail_in</tt> is set to zero and <tt>next_in</tt> is set to <tt>Z_NULL</tt> to 350*16dce513Schristosindicate that no input data is being provided. 351*16dce513Schristos<pre><b> 352*16dce513Schristos /* allocate inflate state */ 353*16dce513Schristos strm.zalloc = Z_NULL; 354*16dce513Schristos strm.zfree = Z_NULL; 355*16dce513Schristos strm.opaque = Z_NULL; 356*16dce513Schristos strm.avail_in = 0; 357*16dce513Schristos strm.next_in = Z_NULL; 358*16dce513Schristos ret = inflateInit(&strm); 359*16dce513Schristos if (ret != Z_OK) 360*16dce513Schristos return ret; 361*16dce513Schristos</b></pre><!-- --> 362*16dce513SchristosThe outer <tt>do</tt>-loop decompresses input until <tt>inflate()</tt> indicates 363*16dce513Schristosthat it has reached the end of the compressed data and has produced all of the uncompressed 364*16dce513Schristosoutput. This is in contrast to <tt>def()</tt> which processes all of the input file. 365*16dce513SchristosIf end-of-file is reached before the compressed data self-terminates, then the compressed 366*16dce513Schristosdata is incomplete and an error is returned. 367*16dce513Schristos<pre><b> 368*16dce513Schristos /* decompress until deflate stream ends or end of file */ 369*16dce513Schristos do { 370*16dce513Schristos</b></pre> 371*16dce513SchristosWe read input data and set the <tt>strm</tt> structure accordingly. If we've reached the 372*16dce513Schristosend of the input file, then we leave the outer loop and report an error, since the 373*16dce513Schristoscompressed data is incomplete. Note that we may read more data than is eventually consumed 374*16dce513Schristosby <tt>inflate()</tt>, if the input file continues past the <em>zlib</em> stream. 375*16dce513SchristosFor applications where <em>zlib</em> streams are embedded in other data, this routine would 376*16dce513Schristosneed to be modified to return the unused data, or at least indicate how much of the input 377*16dce513Schristosdata was not used, so the application would know where to pick up after the <em>zlib</em> stream. 378*16dce513Schristos<pre><b> 379*16dce513Schristos strm.avail_in = fread(in, 1, CHUNK, source); 380*16dce513Schristos if (ferror(source)) { 381*16dce513Schristos (void)inflateEnd(&strm); 382*16dce513Schristos return Z_ERRNO; 383*16dce513Schristos } 384*16dce513Schristos if (strm.avail_in == 0) 385*16dce513Schristos break; 386*16dce513Schristos strm.next_in = in; 387*16dce513Schristos</b></pre><!-- --> 388*16dce513SchristosThe inner <tt>do</tt>-loop has the same function it did in <tt>def()</tt>, which is to 389*16dce513Schristoskeep calling <tt>inflate()</tt> until has generated all of the output it can with the 390*16dce513Schristosprovided input. 391*16dce513Schristos<pre><b> 392*16dce513Schristos /* run inflate() on input until output buffer not full */ 393*16dce513Schristos do { 394*16dce513Schristos</b></pre> 395*16dce513SchristosJust like in <tt>def()</tt>, the same output space is provided for each call of <tt>inflate()</tt>. 396*16dce513Schristos<pre><b> 397*16dce513Schristos strm.avail_out = CHUNK; 398*16dce513Schristos strm.next_out = out; 399*16dce513Schristos</b></pre> 400*16dce513SchristosNow we run the decompression engine itself. There is no need to adjust the flush parameter, since 401*16dce513Schristosthe <em>zlib</em> format is self-terminating. The main difference here is that there are 402*16dce513Schristosreturn values that we need to pay attention to. <tt>Z_DATA_ERROR</tt> 403*16dce513Schristosindicates that <tt>inflate()</tt> detected an error in the <em>zlib</em> compressed data format, 404*16dce513Schristoswhich means that either the data is not a <em>zlib</em> stream to begin with, or that the data was 405*16dce513Schristoscorrupted somewhere along the way since it was compressed. The other error to be processed is 406*16dce513Schristos<tt>Z_MEM_ERROR</tt>, which can occur since memory allocation is deferred until <tt>inflate()</tt> 407*16dce513Schristosneeds it, unlike <tt>deflate()</tt>, whose memory is allocated at the start by <tt>deflateInit()</tt>. 408*16dce513Schristos<p> 409*16dce513SchristosAdvanced applications may use 410*16dce513Schristos<tt>deflateSetDictionary()</tt> to prime <tt>deflate()</tt> with a set of likely data to improve the 411*16dce513Schristosfirst 32K or so of compression. This is noted in the <em>zlib</em> header, so <tt>inflate()</tt> 412*16dce513Schristosrequests that that dictionary be provided before it can start to decompress. Without the dictionary, 413*16dce513Schristoscorrect decompression is not possible. For this routine, we have no idea what the dictionary is, 414*16dce513Schristosso the <tt>Z_NEED_DICT</tt> indication is converted to a <tt>Z_DATA_ERROR</tt>. 415*16dce513Schristos<p> 416*16dce513Schristos<tt>inflate()</tt> can also return <tt>Z_STREAM_ERROR</tt>, which should not be possible here, 417*16dce513Schristosbut could be checked for as noted above for <tt>def()</tt>. <tt>Z_BUF_ERROR</tt> does not need to be 418*16dce513Schristoschecked for here, for the same reasons noted for <tt>def()</tt>. <tt>Z_STREAM_END</tt> will be 419*16dce513Schristoschecked for later. 420*16dce513Schristos<pre><b> 421*16dce513Schristos ret = inflate(&strm, Z_NO_FLUSH); 422*16dce513Schristos assert(ret != Z_STREAM_ERROR); /* state not clobbered */ 423*16dce513Schristos switch (ret) { 424*16dce513Schristos case Z_NEED_DICT: 425*16dce513Schristos ret = Z_DATA_ERROR; /* and fall through */ 426*16dce513Schristos case Z_DATA_ERROR: 427*16dce513Schristos case Z_MEM_ERROR: 428*16dce513Schristos (void)inflateEnd(&strm); 429*16dce513Schristos return ret; 430*16dce513Schristos } 431*16dce513Schristos</b></pre> 432*16dce513SchristosThe output of <tt>inflate()</tt> is handled identically to that of <tt>deflate()</tt>. 433*16dce513Schristos<pre><b> 434*16dce513Schristos have = CHUNK - strm.avail_out; 435*16dce513Schristos if (fwrite(out, 1, have, dest) != have || ferror(dest)) { 436*16dce513Schristos (void)inflateEnd(&strm); 437*16dce513Schristos return Z_ERRNO; 438*16dce513Schristos } 439*16dce513Schristos</b></pre> 440*16dce513SchristosThe inner <tt>do</tt>-loop ends when <tt>inflate()</tt> has no more output as indicated 441*16dce513Schristosby not filling the output buffer, just as for <tt>deflate()</tt>. In this case, we cannot 442*16dce513Schristosassert that <tt>strm.avail_in</tt> will be zero, since the deflate stream may end before the file 443*16dce513Schristosdoes. 444*16dce513Schristos<pre><b> 445*16dce513Schristos } while (strm.avail_out == 0); 446*16dce513Schristos</b></pre><!-- --> 447*16dce513SchristosThe outer <tt>do</tt>-loop ends when <tt>inflate()</tt> reports that it has reached the 448*16dce513Schristosend of the input <em>zlib</em> stream, has completed the decompression and integrity 449*16dce513Schristoscheck, and has provided all of the output. This is indicated by the <tt>inflate()</tt> 450*16dce513Schristosreturn value <tt>Z_STREAM_END</tt>. The inner loop is guaranteed to leave <tt>ret</tt> 451*16dce513Schristosequal to <tt>Z_STREAM_END</tt> if the last chunk of the input file read contained the end 452*16dce513Schristosof the <em>zlib</em> stream. So if the return value is not <tt>Z_STREAM_END</tt>, the 453*16dce513Schristosloop continues to read more input. 454*16dce513Schristos<pre><b> 455*16dce513Schristos /* done when inflate() says it's done */ 456*16dce513Schristos } while (ret != Z_STREAM_END); 457*16dce513Schristos</b></pre><!-- --> 458*16dce513SchristosAt this point, decompression successfully completed, or we broke out of the loop due to no 459*16dce513Schristosmore data being available from the input file. If the last <tt>inflate()</tt> return value 460*16dce513Schristosis not <tt>Z_STREAM_END</tt>, then the <em>zlib</em> stream was incomplete and a data error 461*16dce513Schristosis returned. Otherwise, we return with a happy return value. Of course, <tt>inflateEnd()</tt> 462*16dce513Schristosis called first to avoid a memory leak. 463*16dce513Schristos<pre><b> 464*16dce513Schristos /* clean up and return */ 465*16dce513Schristos (void)inflateEnd(&strm); 466*16dce513Schristos return ret == Z_STREAM_END ? Z_OK : Z_DATA_ERROR; 467*16dce513Schristos} 468*16dce513Schristos</b></pre><!-- --> 469*16dce513SchristosThat ends the routines that directly use <em>zlib</em>. The following routines make this 470*16dce513Schristosa command-line program by running data through the above routines from <tt>stdin</tt> to 471*16dce513Schristos<tt>stdout</tt>, and handling any errors reported by <tt>def()</tt> or <tt>inf()</tt>. 472*16dce513Schristos<p> 473*16dce513Schristos<tt>zerr()</tt> is used to interpret the possible error codes from <tt>def()</tt> 474*16dce513Schristosand <tt>inf()</tt>, as detailed in their comments above, and print out an error message. 475*16dce513SchristosNote that these are only a subset of the possible return values from <tt>deflate()</tt> 476*16dce513Schristosand <tt>inflate()</tt>. 477*16dce513Schristos<pre><b> 478*16dce513Schristos/* report a zlib or i/o error */ 479*16dce513Schristosvoid zerr(int ret) 480*16dce513Schristos{ 481*16dce513Schristos fputs("zpipe: ", stderr); 482*16dce513Schristos switch (ret) { 483*16dce513Schristos case Z_ERRNO: 484*16dce513Schristos if (ferror(stdin)) 485*16dce513Schristos fputs("error reading stdin\n", stderr); 486*16dce513Schristos if (ferror(stdout)) 487*16dce513Schristos fputs("error writing stdout\n", stderr); 488*16dce513Schristos break; 489*16dce513Schristos case Z_STREAM_ERROR: 490*16dce513Schristos fputs("invalid compression level\n", stderr); 491*16dce513Schristos break; 492*16dce513Schristos case Z_DATA_ERROR: 493*16dce513Schristos fputs("invalid or incomplete deflate data\n", stderr); 494*16dce513Schristos break; 495*16dce513Schristos case Z_MEM_ERROR: 496*16dce513Schristos fputs("out of memory\n", stderr); 497*16dce513Schristos break; 498*16dce513Schristos case Z_VERSION_ERROR: 499*16dce513Schristos fputs("zlib version mismatch!\n", stderr); 500*16dce513Schristos } 501*16dce513Schristos} 502*16dce513Schristos</b></pre><!-- --> 503*16dce513SchristosHere is the <tt>main()</tt> routine used to test <tt>def()</tt> and <tt>inf()</tt>. The 504*16dce513Schristos<tt>zpipe</tt> command is simply a compression pipe from <tt>stdin</tt> to <tt>stdout</tt>, if 505*16dce513Schristosno arguments are given, or it is a decompression pipe if <tt>zpipe -d</tt> is used. If any other 506*16dce513Schristosarguments are provided, no compression or decompression is performed. Instead a usage 507*16dce513Schristosmessage is displayed. Examples are <tt>zpipe < foo.txt > foo.txt.z</tt> to compress, and 508*16dce513Schristos<tt>zpipe -d < foo.txt.z > foo.txt</tt> to decompress. 509*16dce513Schristos<pre><b> 510*16dce513Schristos/* compress or decompress from stdin to stdout */ 511*16dce513Schristosint main(int argc, char **argv) 512*16dce513Schristos{ 513*16dce513Schristos int ret; 514*16dce513Schristos 515*16dce513Schristos /* avoid end-of-line conversions */ 516*16dce513Schristos SET_BINARY_MODE(stdin); 517*16dce513Schristos SET_BINARY_MODE(stdout); 518*16dce513Schristos 519*16dce513Schristos /* do compression if no arguments */ 520*16dce513Schristos if (argc == 1) { 521*16dce513Schristos ret = def(stdin, stdout, Z_DEFAULT_COMPRESSION); 522*16dce513Schristos if (ret != Z_OK) 523*16dce513Schristos zerr(ret); 524*16dce513Schristos return ret; 525*16dce513Schristos } 526*16dce513Schristos 527*16dce513Schristos /* do decompression if -d specified */ 528*16dce513Schristos else if (argc == 2 && strcmp(argv[1], "-d") == 0) { 529*16dce513Schristos ret = inf(stdin, stdout); 530*16dce513Schristos if (ret != Z_OK) 531*16dce513Schristos zerr(ret); 532*16dce513Schristos return ret; 533*16dce513Schristos } 534*16dce513Schristos 535*16dce513Schristos /* otherwise, report usage */ 536*16dce513Schristos else { 537*16dce513Schristos fputs("zpipe usage: zpipe [-d] < source > dest\n", stderr); 538*16dce513Schristos return 1; 539*16dce513Schristos } 540*16dce513Schristos} 541*16dce513Schristos</b></pre> 542*16dce513Schristos<hr> 543*16dce513Schristos<i>Copyright (c) 2004, 2005 by Mark Adler<br>Last modified 11 December 2005</i> 544*16dce513Schristos</body> 545*16dce513Schristos</html> 546