648db22b |
1 | <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" |
2 | "http://www.w3.org/TR/html4/loose.dtd"> |
9e052883 |
3 | <html> |
4 | <head> |
5 | <meta http-equiv="Content-Type" content="text/html; charset=ISO-8859-1"> |
6 | <title>zlib Usage Example</title> |
648db22b |
7 | <!-- Copyright (c) 2004-2023 Mark Adler. --> |
9e052883 |
8 | </head> |
9 | <body bgcolor="#FFFFFF" text="#000000" link="#0000FF" vlink="#00A000"> |
10 | <h2 align="center"> zlib Usage Example </h2> |
11 | We often get questions about how the <tt>deflate()</tt> and <tt>inflate()</tt> functions should be used. |
12 | Users wonder when they should provide more input, when they should use more output, |
13 | what to do with a <tt>Z_BUF_ERROR</tt>, how to make sure the process terminates properly, and |
14 | so on. So for those who have read <tt>zlib.h</tt> (a few times), and |
15 | would like further edification, below is an annotated example in C of simple routines to compress and decompress |
16 | from an input file to an output file using <tt>deflate()</tt> and <tt>inflate()</tt> respectively. The |
17 | annotations are interspersed between lines of the code. So please read between the lines. |
18 | We hope this helps explain some of the intricacies of <em>zlib</em>. |
19 | <p> |
648db22b |
20 | Without further ado, here is the program <a href="zpipe.c"><tt>zpipe.c</tt></a>: |
9e052883 |
21 | <pre><b> |
22 | /* zpipe.c: example of proper use of zlib's inflate() and deflate() |
23 | Not copyrighted -- provided to the public domain |
24 | Version 1.4 11 December 2005 Mark Adler */ |
25 | |
26 | /* Version history: |
27 | 1.0 30 Oct 2004 First version |
28 | 1.1 8 Nov 2004 Add void casting for unused return values |
29 | Use switch statement for inflate() return values |
30 | 1.2 9 Nov 2004 Add assertions to document zlib guarantees |
31 | 1.3 6 Apr 2005 Remove incorrect assertion in inf() |
32 | 1.4 11 Dec 2005 Add hack to avoid MSDOS end-of-line conversions |
33 | Avoid some compiler warnings for input and output buffers |
34 | */ |
35 | </b></pre><!-- --> |
36 | We now include the header files for the required definitions. From |
37 | <tt>stdio.h</tt> we use <tt>fopen()</tt>, <tt>fread()</tt>, <tt>fwrite()</tt>, |
38 | <tt>feof()</tt>, <tt>ferror()</tt>, and <tt>fclose()</tt> for file i/o, and |
39 | <tt>fputs()</tt> for error messages. From <tt>string.h</tt> we use |
40 | <tt>strcmp()</tt> for command line argument processing. |
41 | From <tt>assert.h</tt> we use the <tt>assert()</tt> macro. |
42 | From <tt>zlib.h</tt> |
43 | we use the basic compression functions <tt>deflateInit()</tt>, |
44 | <tt>deflate()</tt>, and <tt>deflateEnd()</tt>, and the basic decompression |
45 | functions <tt>inflateInit()</tt>, <tt>inflate()</tt>, and |
46 | <tt>inflateEnd()</tt>. |
47 | <pre><b> |
48 | #include <stdio.h> |
49 | #include <string.h> |
50 | #include <assert.h> |
51 | #include "zlib.h" |
52 | </b></pre><!-- --> |
53 | This is an ugly hack required to avoid corruption of the input and output data on |
54 | Windows/MS-DOS systems. Without this, those systems would assume that the input and output |
55 | files are text, and try to convert the end-of-line characters from one standard to |
56 | another. That would corrupt binary data, and in particular would render the compressed data unusable. |
57 | This sets the input and output to binary which suppresses the end-of-line conversions. |
58 | <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 | <pre><b> |
60 | #if defined(MSDOS) || defined(OS2) || defined(WIN32) || defined(__CYGWIN__) |
61 | # include <fcntl.h> |
62 | # include <io.h> |
63 | # define SET_BINARY_MODE(file) setmode(fileno(file), O_BINARY) |
64 | #else |
65 | # define SET_BINARY_MODE(file) |
66 | #endif |
67 | </b></pre><!-- --> |
68 | <tt>CHUNK</tt> is simply the buffer size for feeding data to and pulling data |
69 | from the <em>zlib</em> routines. Larger buffer sizes would be more efficient, |
70 | especially for <tt>inflate()</tt>. If the memory is available, buffers sizes |
71 | on the order of 128K or 256K bytes should be used. |
72 | <pre><b> |
73 | #define CHUNK 16384 |
74 | </b></pre><!-- --> |
75 | The <tt>def()</tt> routine compresses data from an input file to an output file. The output data |
76 | will be in the <em>zlib</em> format, which is different from the <em>gzip</em> or <em>zip</em> |
77 | formats. The <em>zlib</em> format has a very small header of only two bytes to identify it as |
78 | a <em>zlib</em> stream and to provide decoding information, and a four-byte trailer with a fast |
79 | check value to verify the integrity of the uncompressed data after decoding. |
80 | <pre><b> |
81 | /* Compress from file source to file dest until EOF on source. |
82 | def() returns Z_OK on success, Z_MEM_ERROR if memory could not be |
83 | allocated for processing, Z_STREAM_ERROR if an invalid compression |
84 | level is supplied, Z_VERSION_ERROR if the version of zlib.h and the |
85 | version of the library linked do not match, or Z_ERRNO if there is |
86 | an error reading or writing the files. */ |
87 | int def(FILE *source, FILE *dest, int level) |
88 | { |
89 | </b></pre> |
90 | Here are the local variables for <tt>def()</tt>. <tt>ret</tt> will be used for <em>zlib</em> |
91 | return codes. <tt>flush</tt> will keep track of the current flushing state for <tt>deflate()</tt>, |
92 | which is either no flushing, or flush to completion after the end of the input file is reached. |
93 | <tt>have</tt> is the amount of data returned from <tt>deflate()</tt>. The <tt>strm</tt> structure |
94 | is used to pass information to and from the <em>zlib</em> routines, and to maintain the |
95 | <tt>deflate()</tt> state. <tt>in</tt> and <tt>out</tt> are the input and output buffers for |
96 | <tt>deflate()</tt>. |
97 | <pre><b> |
98 | int ret, flush; |
99 | unsigned have; |
100 | z_stream strm; |
101 | unsigned char in[CHUNK]; |
102 | unsigned char out[CHUNK]; |
103 | </b></pre><!-- --> |
104 | The first thing we do is to initialize the <em>zlib</em> state for compression using |
105 | <tt>deflateInit()</tt>. This must be done before the first use of <tt>deflate()</tt>. |
106 | The <tt>zalloc</tt>, <tt>zfree</tt>, and <tt>opaque</tt> fields in the <tt>strm</tt> |
107 | structure must be initialized before calling <tt>deflateInit()</tt>. Here they are |
108 | set to the <em>zlib</em> constant <tt>Z_NULL</tt> to request that <em>zlib</em> use |
109 | the default memory allocation routines. An application may also choose to provide |
110 | custom memory allocation routines here. <tt>deflateInit()</tt> will allocate on the |
111 | order of 256K bytes for the internal state. |
112 | (See <a href="zlib_tech.html"><em>zlib Technical Details</em></a>.) |
113 | <p> |
114 | <tt>deflateInit()</tt> is called with a pointer to the structure to be initialized and |
115 | the compression level, which is an integer in the range of -1 to 9. Lower compression |
116 | levels result in faster execution, but less compression. Higher levels result in |
117 | greater compression, but slower execution. The <em>zlib</em> constant Z_DEFAULT_COMPRESSION, |
118 | equal to -1, |
119 | provides a good compromise between compression and speed and is equivalent to level 6. |
120 | Level 0 actually does no compression at all, and in fact expands the data slightly to produce |
121 | the <em>zlib</em> format (it is not a byte-for-byte copy of the input). |
122 | More advanced applications of <em>zlib</em> |
123 | may use <tt>deflateInit2()</tt> here instead. Such an application may want to reduce how |
124 | much memory will be used, at some price in compression. Or it may need to request a |
125 | <em>gzip</em> header and trailer instead of a <em>zlib</em> header and trailer, or raw |
126 | encoding with no header or trailer at all. |
127 | <p> |
128 | We must check the return value of <tt>deflateInit()</tt> against the <em>zlib</em> constant |
129 | <tt>Z_OK</tt> to make sure that it was able to |
130 | allocate memory for the internal state, and that the provided arguments were valid. |
131 | <tt>deflateInit()</tt> will also check that the version of <em>zlib</em> that the <tt>zlib.h</tt> |
132 | file came from matches the version of <em>zlib</em> actually linked with the program. This |
133 | is especially important for environments in which <em>zlib</em> is a shared library. |
134 | <p> |
135 | Note that an application can initialize multiple, independent <em>zlib</em> streams, which can |
136 | operate in parallel. The state information maintained in the structure allows the <em>zlib</em> |
137 | routines to be reentrant. |
138 | <pre><b> |
139 | /* allocate deflate state */ |
140 | strm.zalloc = Z_NULL; |
141 | strm.zfree = Z_NULL; |
142 | strm.opaque = Z_NULL; |
143 | ret = deflateInit(&strm, level); |
144 | if (ret != Z_OK) |
145 | return ret; |
146 | </b></pre><!-- --> |
147 | With the pleasantries out of the way, now we can get down to business. The outer <tt>do</tt>-loop |
148 | reads all of the input file and exits at the bottom of the loop once end-of-file is reached. |
149 | This loop contains the only call of <tt>deflate()</tt>. So we must make sure that all of the |
150 | input data has been processed and that all of the output data has been generated and consumed |
151 | before we fall out of the loop at the bottom. |
152 | <pre><b> |
153 | /* compress until end of file */ |
154 | do { |
155 | </b></pre> |
156 | We start off by reading data from the input file. The number of bytes read is put directly |
157 | into <tt>avail_in</tt>, and a pointer to those bytes is put into <tt>next_in</tt>. We also |
648db22b |
158 | check to see if end-of-file on the input has been reached using feof(). |
159 | If we are at the end of file, then <tt>flush</tt> is set to the |
9e052883 |
160 | <em>zlib</em> constant <tt>Z_FINISH</tt>, which is later passed to <tt>deflate()</tt> to |
648db22b |
161 | indicate that this is the last chunk of input data to compress. |
162 | If we are not yet at the end of the input, then the <em>zlib</em> |
9e052883 |
163 | constant <tt>Z_NO_FLUSH</tt> will be passed to <tt>deflate</tt> to indicate that we are still |
164 | in the middle of the uncompressed data. |
165 | <p> |
166 | If there is an error in reading from the input file, the process is aborted with |
167 | <tt>deflateEnd()</tt> being called to free the allocated <em>zlib</em> state before returning |
168 | the error. We wouldn't want a memory leak, now would we? <tt>deflateEnd()</tt> can be called |
169 | at any time after the state has been initialized. Once that's done, <tt>deflateInit()</tt> (or |
170 | <tt>deflateInit2()</tt>) would have to be called to start a new compression process. There is |
171 | no point here in checking the <tt>deflateEnd()</tt> return code. The deallocation can't fail. |
172 | <pre><b> |
173 | strm.avail_in = fread(in, 1, CHUNK, source); |
174 | if (ferror(source)) { |
175 | (void)deflateEnd(&strm); |
176 | return Z_ERRNO; |
177 | } |
178 | flush = feof(source) ? Z_FINISH : Z_NO_FLUSH; |
179 | strm.next_in = in; |
180 | </b></pre><!-- --> |
181 | The inner <tt>do</tt>-loop passes our chunk of input data to <tt>deflate()</tt>, and then |
182 | keeps calling <tt>deflate()</tt> until it is done producing output. Once there is no more |
183 | new output, <tt>deflate()</tt> is guaranteed to have consumed all of the input, i.e., |
184 | <tt>avail_in</tt> will be zero. |
185 | <pre><b> |
186 | /* run deflate() on input until output buffer not full, finish |
187 | compression if all of source has been read in */ |
188 | do { |
189 | </b></pre> |
190 | Output space is provided to <tt>deflate()</tt> by setting <tt>avail_out</tt> to the number |
191 | of available output bytes and <tt>next_out</tt> to a pointer to that space. |
192 | <pre><b> |
193 | strm.avail_out = CHUNK; |
194 | strm.next_out = out; |
195 | </b></pre> |
196 | Now we call the compression engine itself, <tt>deflate()</tt>. It takes as many of the |
197 | <tt>avail_in</tt> bytes at <tt>next_in</tt> as it can process, and writes as many as |
198 | <tt>avail_out</tt> bytes to <tt>next_out</tt>. Those counters and pointers are then |
199 | updated past the input data consumed and the output data written. It is the amount of |
200 | output space available that may limit how much input is consumed. |
201 | Hence the inner loop to make sure that |
202 | all of the input is consumed by providing more output space each time. Since <tt>avail_in</tt> |
203 | and <tt>next_in</tt> are updated by <tt>deflate()</tt>, we don't have to mess with those |
204 | between <tt>deflate()</tt> calls until it's all used up. |
205 | <p> |
206 | The parameters to <tt>deflate()</tt> are a pointer to the <tt>strm</tt> structure containing |
207 | the input and output information and the internal compression engine state, and a parameter |
208 | indicating whether and how to flush data to the output. Normally <tt>deflate</tt> will consume |
209 | several K bytes of input data before producing any output (except for the header), in order |
210 | to accumulate statistics on the data for optimum compression. It will then put out a burst of |
211 | compressed data, and proceed to consume more input before the next burst. Eventually, |
212 | <tt>deflate()</tt> |
213 | must be told to terminate the stream, complete the compression with provided input data, and |
214 | write out the trailer check value. <tt>deflate()</tt> will continue to compress normally as long |
215 | as the flush parameter is <tt>Z_NO_FLUSH</tt>. Once the <tt>Z_FINISH</tt> parameter is provided, |
216 | <tt>deflate()</tt> will begin to complete the compressed output stream. However depending on how |
217 | much output space is provided, <tt>deflate()</tt> may have to be called several times until it |
218 | has provided the complete compressed stream, even after it has consumed all of the input. The flush |
219 | parameter must continue to be <tt>Z_FINISH</tt> for those subsequent calls. |
220 | <p> |
221 | There are other values of the flush parameter that are used in more advanced applications. You can |
222 | force <tt>deflate()</tt> to produce a burst of output that encodes all of the input data provided |
223 | so far, even if it wouldn't have otherwise, for example to control data latency on a link with |
224 | compressed data. You can also ask that <tt>deflate()</tt> do that as well as erase any history up to |
225 | that point so that what follows can be decompressed independently, for example for random access |
226 | applications. Both requests will degrade compression by an amount depending on how often such |
227 | requests are made. |
228 | <p> |
229 | <tt>deflate()</tt> has a return value that can indicate errors, yet we do not check it here. Why |
230 | not? Well, it turns out that <tt>deflate()</tt> can do no wrong here. Let's go through |
231 | <tt>deflate()</tt>'s return values and dispense with them one by one. The possible values are |
232 | <tt>Z_OK</tt>, <tt>Z_STREAM_END</tt>, <tt>Z_STREAM_ERROR</tt>, or <tt>Z_BUF_ERROR</tt>. <tt>Z_OK</tt> |
233 | is, well, ok. <tt>Z_STREAM_END</tt> is also ok and will be returned for the last call of |
234 | <tt>deflate()</tt>. This is already guaranteed by calling <tt>deflate()</tt> with <tt>Z_FINISH</tt> |
235 | until it has no more output. <tt>Z_STREAM_ERROR</tt> is only possible if the stream is not |
236 | initialized properly, but we did initialize it properly. There is no harm in checking for |
237 | <tt>Z_STREAM_ERROR</tt> here, for example to check for the possibility that some |
238 | other part of the application inadvertently clobbered the memory containing the <em>zlib</em> state. |
239 | <tt>Z_BUF_ERROR</tt> will be explained further below, but |
240 | suffice it to say that this is simply an indication that <tt>deflate()</tt> could not consume |
241 | more input or produce more output. <tt>deflate()</tt> can be called again with more output space |
242 | or more available input, which it will be in this code. |
243 | <pre><b> |
244 | ret = deflate(&strm, flush); /* no bad return value */ |
245 | assert(ret != Z_STREAM_ERROR); /* state not clobbered */ |
246 | </b></pre> |
247 | Now we compute how much output <tt>deflate()</tt> provided on the last call, which is the |
248 | difference between how much space was provided before the call, and how much output space |
249 | is still available after the call. Then that data, if any, is written to the output file. |
250 | We can then reuse the output buffer for the next call of <tt>deflate()</tt>. Again if there |
251 | is a file i/o error, we call <tt>deflateEnd()</tt> before returning to avoid a memory leak. |
252 | <pre><b> |
253 | have = CHUNK - strm.avail_out; |
254 | if (fwrite(out, 1, have, dest) != have || ferror(dest)) { |
255 | (void)deflateEnd(&strm); |
256 | return Z_ERRNO; |
257 | } |
258 | </b></pre> |
259 | The inner <tt>do</tt>-loop is repeated until the last <tt>deflate()</tt> call fails to fill the |
260 | provided output buffer. Then we know that <tt>deflate()</tt> has done as much as it can with |
261 | the provided input, and that all of that input has been consumed. We can then fall out of this |
262 | loop and reuse the input buffer. |
263 | <p> |
264 | The way we tell that <tt>deflate()</tt> has no more output is by seeing that it did not fill |
265 | the output buffer, leaving <tt>avail_out</tt> greater than zero. However suppose that |
266 | <tt>deflate()</tt> has no more output, but just so happened to exactly fill the output buffer! |
267 | <tt>avail_out</tt> is zero, and we can't tell that <tt>deflate()</tt> has done all it can. |
268 | As far as we know, <tt>deflate()</tt> |
269 | has more output for us. So we call it again. But now <tt>deflate()</tt> produces no output |
270 | at all, and <tt>avail_out</tt> remains unchanged as <tt>CHUNK</tt>. That <tt>deflate()</tt> call |
271 | wasn't able to do anything, either consume input or produce output, and so it returns |
272 | <tt>Z_BUF_ERROR</tt>. (See, I told you I'd cover this later.) However this is not a problem at |
273 | all. Now we finally have the desired indication that <tt>deflate()</tt> is really done, |
274 | and so we drop out of the inner loop to provide more input to <tt>deflate()</tt>. |
275 | <p> |
276 | With <tt>flush</tt> set to <tt>Z_FINISH</tt>, this final set of <tt>deflate()</tt> calls will |
277 | complete the output stream. Once that is done, subsequent calls of <tt>deflate()</tt> would return |
278 | <tt>Z_STREAM_ERROR</tt> if the flush parameter is not <tt>Z_FINISH</tt>, and do no more processing |
279 | until the state is reinitialized. |
280 | <p> |
281 | Some applications of <em>zlib</em> have two loops that call <tt>deflate()</tt> |
282 | instead of the single inner loop we have here. The first loop would call |
283 | without flushing and feed all of the data to <tt>deflate()</tt>. The second loop would call |
284 | <tt>deflate()</tt> with no more |
285 | data and the <tt>Z_FINISH</tt> parameter to complete the process. As you can see from this |
286 | example, that can be avoided by simply keeping track of the current flush state. |
287 | <pre><b> |
288 | } while (strm.avail_out == 0); |
289 | assert(strm.avail_in == 0); /* all input will be used */ |
290 | </b></pre><!-- --> |
291 | Now we check to see if we have already processed all of the input file. That information was |
292 | saved in the <tt>flush</tt> variable, so we see if that was set to <tt>Z_FINISH</tt>. If so, |
293 | then we're done and we fall out of the outer loop. We're guaranteed to get <tt>Z_STREAM_END</tt> |
294 | from the last <tt>deflate()</tt> call, since we ran it until the last chunk of input was |
295 | consumed and all of the output was generated. |
296 | <pre><b> |
297 | /* done when last data in file processed */ |
298 | } while (flush != Z_FINISH); |
299 | assert(ret == Z_STREAM_END); /* stream will be complete */ |
300 | </b></pre><!-- --> |
301 | The process is complete, but we still need to deallocate the state to avoid a memory leak |
302 | (or rather more like a memory hemorrhage if you didn't do this). Then |
303 | finally we can return with a happy return value. |
304 | <pre><b> |
305 | /* clean up and return */ |
306 | (void)deflateEnd(&strm); |
307 | return Z_OK; |
308 | } |
309 | </b></pre><!-- --> |
310 | Now we do the same thing for decompression in the <tt>inf()</tt> routine. <tt>inf()</tt> |
311 | decompresses what is hopefully a valid <em>zlib</em> stream from the input file and writes the |
312 | uncompressed data to the output file. Much of the discussion above for <tt>def()</tt> |
313 | applies to <tt>inf()</tt> as well, so the discussion here will focus on the differences between |
314 | the two. |
315 | <pre><b> |
316 | /* Decompress from file source to file dest until stream ends or EOF. |
317 | inf() returns Z_OK on success, Z_MEM_ERROR if memory could not be |
318 | allocated for processing, Z_DATA_ERROR if the deflate data is |
319 | invalid or incomplete, Z_VERSION_ERROR if the version of zlib.h and |
320 | the version of the library linked do not match, or Z_ERRNO if there |
321 | is an error reading or writing the files. */ |
322 | int inf(FILE *source, FILE *dest) |
323 | { |
324 | </b></pre> |
325 | The local variables have the same functionality as they do for <tt>def()</tt>. The |
326 | only difference is that there is no <tt>flush</tt> variable, since <tt>inflate()</tt> |
327 | can tell from the <em>zlib</em> stream itself when the stream is complete. |
328 | <pre><b> |
329 | int ret; |
330 | unsigned have; |
331 | z_stream strm; |
332 | unsigned char in[CHUNK]; |
333 | unsigned char out[CHUNK]; |
334 | </b></pre><!-- --> |
335 | The initialization of the state is the same, except that there is no compression level, |
336 | of course, and two more elements of the structure are initialized. <tt>avail_in</tt> |
337 | and <tt>next_in</tt> must be initialized before calling <tt>inflateInit()</tt>. This |
338 | is because the application has the option to provide the start of the zlib stream in |
339 | order for <tt>inflateInit()</tt> to have access to information about the compression |
340 | method to aid in memory allocation. In the current implementation of <em>zlib</em> |
341 | (up through versions 1.2.x), the method-dependent memory allocations are deferred to the first call of |
342 | <tt>inflate()</tt> anyway. However those fields must be initialized since later versions |
343 | of <em>zlib</em> that provide more compression methods may take advantage of this interface. |
344 | In any case, no decompression is performed by <tt>inflateInit()</tt>, so the |
345 | <tt>avail_out</tt> and <tt>next_out</tt> fields do not need to be initialized before calling. |
346 | <p> |
347 | Here <tt>avail_in</tt> is set to zero and <tt>next_in</tt> is set to <tt>Z_NULL</tt> to |
348 | indicate that no input data is being provided. |
349 | <pre><b> |
350 | /* allocate inflate state */ |
351 | strm.zalloc = Z_NULL; |
352 | strm.zfree = Z_NULL; |
353 | strm.opaque = Z_NULL; |
354 | strm.avail_in = 0; |
355 | strm.next_in = Z_NULL; |
356 | ret = inflateInit(&strm); |
357 | if (ret != Z_OK) |
358 | return ret; |
359 | </b></pre><!-- --> |
360 | The outer <tt>do</tt>-loop decompresses input until <tt>inflate()</tt> indicates |
361 | that it has reached the end of the compressed data and has produced all of the uncompressed |
362 | output. This is in contrast to <tt>def()</tt> which processes all of the input file. |
363 | If end-of-file is reached before the compressed data self-terminates, then the compressed |
364 | data is incomplete and an error is returned. |
365 | <pre><b> |
366 | /* decompress until deflate stream ends or end of file */ |
367 | do { |
368 | </b></pre> |
369 | We read input data and set the <tt>strm</tt> structure accordingly. If we've reached the |
370 | end of the input file, then we leave the outer loop and report an error, since the |
371 | compressed data is incomplete. Note that we may read more data than is eventually consumed |
372 | by <tt>inflate()</tt>, if the input file continues past the <em>zlib</em> stream. |
373 | For applications where <em>zlib</em> streams are embedded in other data, this routine would |
374 | need to be modified to return the unused data, or at least indicate how much of the input |
375 | data was not used, so the application would know where to pick up after the <em>zlib</em> stream. |
376 | <pre><b> |
377 | strm.avail_in = fread(in, 1, CHUNK, source); |
378 | if (ferror(source)) { |
379 | (void)inflateEnd(&strm); |
380 | return Z_ERRNO; |
381 | } |
382 | if (strm.avail_in == 0) |
383 | break; |
384 | strm.next_in = in; |
385 | </b></pre><!-- --> |
386 | The inner <tt>do</tt>-loop has the same function it did in <tt>def()</tt>, which is to |
387 | keep calling <tt>inflate()</tt> until has generated all of the output it can with the |
388 | provided input. |
389 | <pre><b> |
390 | /* run inflate() on input until output buffer not full */ |
391 | do { |
392 | </b></pre> |
393 | Just like in <tt>def()</tt>, the same output space is provided for each call of <tt>inflate()</tt>. |
394 | <pre><b> |
395 | strm.avail_out = CHUNK; |
396 | strm.next_out = out; |
397 | </b></pre> |
398 | Now we run the decompression engine itself. There is no need to adjust the flush parameter, since |
399 | the <em>zlib</em> format is self-terminating. The main difference here is that there are |
400 | return values that we need to pay attention to. <tt>Z_DATA_ERROR</tt> |
401 | indicates that <tt>inflate()</tt> detected an error in the <em>zlib</em> compressed data format, |
402 | which means that either the data is not a <em>zlib</em> stream to begin with, or that the data was |
403 | corrupted somewhere along the way since it was compressed. The other error to be processed is |
404 | <tt>Z_MEM_ERROR</tt>, which can occur since memory allocation is deferred until <tt>inflate()</tt> |
405 | needs it, unlike <tt>deflate()</tt>, whose memory is allocated at the start by <tt>deflateInit()</tt>. |
406 | <p> |
407 | Advanced applications may use |
408 | <tt>deflateSetDictionary()</tt> to prime <tt>deflate()</tt> with a set of likely data to improve the |
409 | first 32K or so of compression. This is noted in the <em>zlib</em> header, so <tt>inflate()</tt> |
410 | requests that that dictionary be provided before it can start to decompress. Without the dictionary, |
411 | correct decompression is not possible. For this routine, we have no idea what the dictionary is, |
412 | so the <tt>Z_NEED_DICT</tt> indication is converted to a <tt>Z_DATA_ERROR</tt>. |
413 | <p> |
414 | <tt>inflate()</tt> can also return <tt>Z_STREAM_ERROR</tt>, which should not be possible here, |
415 | but could be checked for as noted above for <tt>def()</tt>. <tt>Z_BUF_ERROR</tt> does not need to be |
416 | checked for here, for the same reasons noted for <tt>def()</tt>. <tt>Z_STREAM_END</tt> will be |
417 | checked for later. |
418 | <pre><b> |
419 | ret = inflate(&strm, Z_NO_FLUSH); |
420 | assert(ret != Z_STREAM_ERROR); /* state not clobbered */ |
421 | switch (ret) { |
422 | case Z_NEED_DICT: |
423 | ret = Z_DATA_ERROR; /* and fall through */ |
424 | case Z_DATA_ERROR: |
425 | case Z_MEM_ERROR: |
426 | (void)inflateEnd(&strm); |
427 | return ret; |
428 | } |
429 | </b></pre> |
430 | The output of <tt>inflate()</tt> is handled identically to that of <tt>deflate()</tt>. |
431 | <pre><b> |
432 | have = CHUNK - strm.avail_out; |
433 | if (fwrite(out, 1, have, dest) != have || ferror(dest)) { |
434 | (void)inflateEnd(&strm); |
435 | return Z_ERRNO; |
436 | } |
437 | </b></pre> |
438 | The inner <tt>do</tt>-loop ends when <tt>inflate()</tt> has no more output as indicated |
439 | by not filling the output buffer, just as for <tt>deflate()</tt>. In this case, we cannot |
440 | assert that <tt>strm.avail_in</tt> will be zero, since the deflate stream may end before the file |
441 | does. |
442 | <pre><b> |
443 | } while (strm.avail_out == 0); |
444 | </b></pre><!-- --> |
445 | The outer <tt>do</tt>-loop ends when <tt>inflate()</tt> reports that it has reached the |
446 | end of the input <em>zlib</em> stream, has completed the decompression and integrity |
447 | check, and has provided all of the output. This is indicated by the <tt>inflate()</tt> |
448 | return value <tt>Z_STREAM_END</tt>. The inner loop is guaranteed to leave <tt>ret</tt> |
449 | equal to <tt>Z_STREAM_END</tt> if the last chunk of the input file read contained the end |
450 | of the <em>zlib</em> stream. So if the return value is not <tt>Z_STREAM_END</tt>, the |
451 | loop continues to read more input. |
452 | <pre><b> |
453 | /* done when inflate() says it's done */ |
454 | } while (ret != Z_STREAM_END); |
455 | </b></pre><!-- --> |
456 | At this point, decompression successfully completed, or we broke out of the loop due to no |
457 | more data being available from the input file. If the last <tt>inflate()</tt> return value |
458 | is not <tt>Z_STREAM_END</tt>, then the <em>zlib</em> stream was incomplete and a data error |
459 | is returned. Otherwise, we return with a happy return value. Of course, <tt>inflateEnd()</tt> |
460 | is called first to avoid a memory leak. |
461 | <pre><b> |
462 | /* clean up and return */ |
463 | (void)inflateEnd(&strm); |
464 | return ret == Z_STREAM_END ? Z_OK : Z_DATA_ERROR; |
465 | } |
466 | </b></pre><!-- --> |
467 | That ends the routines that directly use <em>zlib</em>. The following routines make this |
468 | a command-line program by running data through the above routines from <tt>stdin</tt> to |
469 | <tt>stdout</tt>, and handling any errors reported by <tt>def()</tt> or <tt>inf()</tt>. |
470 | <p> |
471 | <tt>zerr()</tt> is used to interpret the possible error codes from <tt>def()</tt> |
472 | and <tt>inf()</tt>, as detailed in their comments above, and print out an error message. |
473 | Note that these are only a subset of the possible return values from <tt>deflate()</tt> |
474 | and <tt>inflate()</tt>. |
475 | <pre><b> |
476 | /* report a zlib or i/o error */ |
477 | void zerr(int ret) |
478 | { |
479 | fputs("zpipe: ", stderr); |
480 | switch (ret) { |
481 | case Z_ERRNO: |
482 | if (ferror(stdin)) |
483 | fputs("error reading stdin\n", stderr); |
484 | if (ferror(stdout)) |
485 | fputs("error writing stdout\n", stderr); |
486 | break; |
487 | case Z_STREAM_ERROR: |
488 | fputs("invalid compression level\n", stderr); |
489 | break; |
490 | case Z_DATA_ERROR: |
491 | fputs("invalid or incomplete deflate data\n", stderr); |
492 | break; |
493 | case Z_MEM_ERROR: |
494 | fputs("out of memory\n", stderr); |
495 | break; |
496 | case Z_VERSION_ERROR: |
497 | fputs("zlib version mismatch!\n", stderr); |
498 | } |
499 | } |
500 | </b></pre><!-- --> |
501 | Here is the <tt>main()</tt> routine used to test <tt>def()</tt> and <tt>inf()</tt>. The |
502 | <tt>zpipe</tt> command is simply a compression pipe from <tt>stdin</tt> to <tt>stdout</tt>, if |
503 | no arguments are given, or it is a decompression pipe if <tt>zpipe -d</tt> is used. If any other |
504 | arguments are provided, no compression or decompression is performed. Instead a usage |
505 | message is displayed. Examples are <tt>zpipe < foo.txt > foo.txt.z</tt> to compress, and |
506 | <tt>zpipe -d < foo.txt.z > foo.txt</tt> to decompress. |
507 | <pre><b> |
508 | /* compress or decompress from stdin to stdout */ |
509 | int main(int argc, char **argv) |
510 | { |
511 | int ret; |
512 | |
513 | /* avoid end-of-line conversions */ |
514 | SET_BINARY_MODE(stdin); |
515 | SET_BINARY_MODE(stdout); |
516 | |
517 | /* do compression if no arguments */ |
518 | if (argc == 1) { |
519 | ret = def(stdin, stdout, Z_DEFAULT_COMPRESSION); |
520 | if (ret != Z_OK) |
521 | zerr(ret); |
522 | return ret; |
523 | } |
524 | |
525 | /* do decompression if -d specified */ |
526 | else if (argc == 2 && strcmp(argv[1], "-d") == 0) { |
527 | ret = inf(stdin, stdout); |
528 | if (ret != Z_OK) |
529 | zerr(ret); |
530 | return ret; |
531 | } |
532 | |
533 | /* otherwise, report usage */ |
534 | else { |
535 | fputs("zpipe usage: zpipe [-d] < source > dest\n", stderr); |
536 | return 1; |
537 | } |
538 | } |
539 | </b></pre> |
540 | <hr> |
648db22b |
541 | <i>Last modified 24 January 2023<br> |
542 | Copyright © 2004-2023 Mark Adler</i><br> |
543 | <a rel="license" href="http://creativecommons.org/licenses/by-nd/4.0/"> |
544 | <img alt="Creative Commons License" style="border-width:0" |
545 | src="https://i.creativecommons.org/l/by-nd/4.0/88x31.png"></a> |
546 | <a rel="license" href="http://creativecommons.org/licenses/by-nd/4.0/"> |
547 | Creative Commons Attribution-NoDerivatives 4.0 International License</a>. |
9e052883 |
548 | </body> |
549 | </html> |