以下是zlib的官方示例,这里对代码进行一些说明。
/* zpipe.c: example of proper use of zlib's inflate() and deflate()
Not copyrighted -- provided to the public domain
Version 1.4 11 December 2005 Mark Adler */
/* Version history:
1.0 30 Oct 2004 First version
1.1 8 Nov 2004 Add void casting for unused return values
Use switch statement for inflate() return values
1.2 9 Nov 2004 Add assertions to document zlib guarantees
1.3 6 Apr 2005 Remove incorrect assertion in inf()
1.4 11 Dec 2005 Add hack to avoid MSDOS end-of-line conversions
Avoid some compiler warnings for input and output buffers
*/
#include <stdio.h>
#include <string.h>
#include <assert.h>
#include "zlib.h"
#if defined(MSDOS) || defined(OS2) || defined(WIN32) || defined(__CYGWIN__)
# include <fcntl.h>
# include <io.h>
# define SET_BINARY_MODE(file) setmode(fileno(file), O_BINARY)
#else
# define SET_BINARY_MODE(file)
#endif
#define CHUNK 16384
/* Compress from file source to file dest until EOF on source.
def() returns Z_OK on success, Z_MEM_ERROR if memory could not be
allocated for processing, Z_STREAM_ERROR if an invalid compression
level is supplied, Z_VERSION_ERROR if the version of zlib.h and the
version of the library linked do not match, or Z_ERRNO if there is
an error reading or writing the files. */
int def(FILE *source, FILE *dest, int level)
{
int ret, flush;
unsigned have;
z_stream strm;
unsigned char in[CHUNK];
unsigned char out[CHUNK];
/* allocate deflate state */
strm.zalloc = Z_NULL;
strm.zfree = Z_NULL;
strm.opaque = Z_NULL;
ret = deflateInit(&strm, level);
if (ret != Z_OK)
return ret;
/* compress until end of file */
do {
strm.avail_in = fread(in, 1, CHUNK, source);
if (ferror(source)) {
(void)deflateEnd(&strm);
return Z_ERRNO;
}
flush = feof(source) ? Z_FINISH : Z_NO_FLUSH;
strm.next_in = in;
/* run deflate() on input until output buffer not full, finish
compression if all of source has been read in */
do {
strm.avail_out = CHUNK;
strm.next_out = out;
ret = deflate(&strm, flush); /* no bad return value */
assert(ret != Z_STREAM_ERROR); /* state not clobbered */
have = CHUNK - strm.avail_out;
if (fwrite(out, 1, have, dest) != have || ferror(dest)) {
(void)deflateEnd(&strm);
return Z_ERRNO;
}
} while (strm.avail_out == 0);
assert(strm.avail_in == 0); /* all input will be used */
/* done when last data in file processed */
} while (flush != Z_FINISH);
assert(ret == Z_STREAM_END); /* stream will be complete */
/* clean up and return */
(void)deflateEnd(&strm);
return Z_OK;
}
/* Decompress from file source to file dest until stream ends or EOF.
inf() returns Z_OK on success, Z_MEM_ERROR if memory could not be
allocated for processing, Z_DATA_ERROR if the deflate data is
invalid or incomplete, Z_VERSION_ERROR if the version of zlib.h and
the version of the library linked do not match, or Z_ERRNO if there
is an error reading or writing the files. */
int inf(FILE *source, FILE *dest)
{
int ret;
unsigned have;
z_stream strm;
unsigned char in[CHUNK];
unsigned char out[CHUNK];
/* allocate inflate state */
strm.zalloc = Z_NULL;
strm.zfree = Z_NULL;
strm.opaque = Z_NULL;
strm.avail_in = 0;
strm.next_in = Z_NULL;
ret = inflateInit(&strm);
if (ret != Z_OK)
return ret;
/* decompress until deflate stream ends or end of file */
do {
strm.avail_in = fread(in, 1, CHUNK, source);
if (ferror(source)) {
(void)inflateEnd(&strm);
return Z_ERRNO;
}
if (strm.avail_in == 0)
break;
strm.next_in = in;
/* run inflate() on input until output buffer not full */
do {
strm.avail_out = CHUNK;
strm.next_out = out;
ret = inflate(&strm, Z_NO_FLUSH);
assert(ret != Z_STREAM_ERROR); /* state not clobbered */
switch (ret) {
case Z_NEED_DICT:
ret = Z_DATA_ERROR; /* and fall through */
case Z_DATA_ERROR:
case Z_MEM_ERROR:
(void)inflateEnd(&strm);
return ret;
}
have = CHUNK - strm.avail_out;
if (fwrite(out, 1, have, dest) != have || ferror(dest)) {
(void)inflateEnd(&strm);
return Z_ERRNO;
}
} while (strm.avail_out == 0);
/* done when inflate() says it's done */
} while (ret != Z_STREAM_END);
/* clean up and return */
(void)inflateEnd(&strm);
return ret == Z_STREAM_END ? Z_OK : Z_DATA_ERROR;
}
/* report a zlib or i/o error */
void zerr(int ret)
{
fputs("zpipe: ", stderr);
switch (ret) {
case Z_ERRNO:
if (ferror(stdin))
fputs("error reading stdin\n", stderr);
if (ferror(stdout))
fputs("error writing stdout\n", stderr);
break;
case Z_STREAM_ERROR:
fputs("invalid compression level\n", stderr);
break;
case Z_DATA_ERROR:
fputs("invalid or incomplete deflate data\n", stderr);
break;
case Z_MEM_ERROR:
fputs("out of memory\n", stderr);
break;
case Z_VERSION_ERROR:
fputs("zlib version mismatch!\n", stderr);
}
}
/* compress or decompress from stdin to stdout */
int main(int argc, char **argv)
{
int ret;
/* avoid end-of-line conversions */
SET_BINARY_MODE(stdin);
SET_BINARY_MODE(stdout);
/* do compression if no arguments */
if (argc == 1) {
ret = def(stdin, stdout, Z_DEFAULT_COMPRESSION);
if (ret != Z_OK)
zerr(ret);
return ret;
}
/* do decompression if -d specified */
else if (argc == 2 && strcmp(argv[1], "-d") == 0) {
ret = inf(stdin, stdout);
if (ret != Z_OK)
zerr(ret);
return ret;
}
/* otherwise, report usage */
else {
fputs("zpipe usage: zpipe [-d] < source > dest\n", stderr);
return 1;
}
}
这个程序的输入是文件名,作用是输入的文件压缩成压缩文件或者是将压缩文件解压。根据输入参数的不同,相应地调到def函数或是inf函数,分别代表压缩和解压。def函数和inf函数的输入输出均是文件指针。
压缩的过程如下:
-
z_stream保存了当前压缩的上下文状态。压缩的过程首先对z_stream进行初始化,设置压缩等级,其中的几个函数等。
-
用一个大循环从输入文件中最多读出CHUNK字节的数据到in这个buffer中。
-
判断文件是否已经到最后了,以判断是否需要进行flush操作。
-
设置z_stream的next_in为in这个buffer,设置z_stream的avail_in为从文件读到in中的字节数。
-
然后设置z_stream的avail_out为CHUNK,next_out为out这个buffer。
-
然后对z_stream调用deflate,如果已经到了文件的结尾,需要告诉deflate函数。
-
计算出本次deflate操作产出的数据量,
have = CHUNK - strm.avail_out;
。 -
将本次操作产出的压缩数据写到压缩文件中。
-
内部这个while循环有些不好理解:
- deflate这个函数完成后会更新z_stream中的avail_out, next_out。我们要保证next_out有空间给我们来输出,也就是avail_out不为0。如果输出空间不够了,deflate会停止压缩。
- Z_NO_FLUSH这个标志使deflate可能不会完全将输入一一对应地压缩出来,deflate中会有一些残留的输入还没有输出。这样做是为了提高压缩率。
- 由于2中的特征,一次deflate可能不能将输入next_in压缩完,因为输出buffer满了。这种情况下我们要判断输出buffer是否已经满了,即avail_out为0。如果是的话,就要重复循环中的过程,确保输入被压缩完。
-
如果到了文件的结尾,对deflate的调用有Z_FINISH这个标志,使deflate将数据完全压缩后输出到文件。
解压过程和压缩过程区别在于deflate被换成了inflate,过程和压缩过程完全一样。