压缩示例代码libarchive,zlib

---

---

---

前言

记录用C/C++实现数据压缩的代码

一、zlib库

home page: https://zlib.net/

manual: https://zlib.net/manual.html

use example: https://zlib.net/zlib_how.html

在内存中对数据进行压缩，defalteInit函数默认压缩为zlib格式

zpip.c

/* 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;
    }
}

在内存中将数据压缩为gzip格式

int def(unsigned char **in, uint32_t *len, int level)
{
    int ret, flush;
    z_stream strm;
    strm.zalloc = Z_NULL;
    strm.zfree = Z_NULL;
    strm.opaque = Z_NULL;
    // gzip格式
    ret = deflateInit2(&strm, level, Z_DEFLATED, 15 | 16, 8, Z_DEFAULT_STRATEGY);
    if (ret != Z_OK)
    {
        return ret;
    }
    do
    {
        strm.avail_in = *len;
        flush = Z_FINISH;
        strm.next_in = *in;
        do
        {
            strm.avail_out = *len;
            strm.next_out = out;
            ret = deflate(&strm, flush);
            if (ret == Z_STREAM_ERROR)
            {
                (void)deflateEnd(&strm);
                free(out);
                return Z_STREAM_ERROR;
            }
        } while (0);
        if (strm.avail_in != 0)
        {
            free(out);
            (void)deflateEnd(&strm);
            return Z_STREAM_ERROR;
        }
        
    } while (0);
    if (ret != Z_STREAM_END)
    {
        free(out);
        (void)deflateEnd(&strm);
        return Z_STREAM_ERROR;
    }
    *len = *len - strm.avail_out;
    *in = out;
    (void)deflateEnd(&strm);
    return Z_OK;
}

二、libarchive库

压缩为tar.gz文件

#include <stdio.h>
#include <archive.h>
#include <archive_entry.h>

#define CHUNK 16384

void write_archive(const char* outname, char** filename)
{
    struct archive *a;
    struct archive_entry *entry;
    struct stat st;
    char buf[BUFSIZ];
    int len;
    int fd;
    a = archive_write_new();
    archive_write_add_filter_gzip(a);
    archive_write_set_format_pax_restricted(a);
    archive_write_open_filename(a, outname);
    while (*filename)
    {
        stat(*filename, &st);
        entry = archive_entry_new();
        archive_entry_set_pathname(entry, *filename);
        archive_entry_set_size(entry, st.st_size);
        archive_entry_set_filetype(entry, AE_IFREG);
        archive_entry_set_perm(entry, 0644);
        archive_write_header(a, entry);
        fd = open(*filename, O_RDONLY);
        len = read(fd, buf, BUFSIZ);
        while (len > 0)
        {
            archive_write_data(a, buf, len);
            len = read(fd, buf, BUFSIZ);
        }
        close(fd);
        archive_entry_free(entry);
        filename++;
        
    }
    archive_write_close(a);
    archive_write_free(a);
}

---

总结

无