关于抓取的用gzlib压缩的网页的解压

最新推荐文章于 2021-08-05 18:41:48 发布

原创最新推荐文章于 2021-08-05 18:41:48 发布 · 748 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#stream #output #buffer #input #up

本文深入探讨了如何通过调用特定函数实现压缩数据的解压与解码过程，包括参数说明、关键步骤及实现细节。重点介绍了如何根据数据类型选择合适的压缩算法，以及解压过程中内存管理的优化策略。

参数source指向的是压缩数据
参数len是压缩数据的长度
参数dest是指向目的的指针的地址
参数gzip为非0表示压缩数据为gzip格式，否则为deflate压缩格式

#define CHUNK 16384
int inflate_read(char *source,int len,char **dest,int gzip) {
int ret;
unsigned have;
z_stream strm;
unsigned char out[CHUNK];
int totalsize = 0;

/* allocate inflate state */
strm.zalloc = Z_NULL;
strm.zfree = Z_NULL;
strm.opaque = Z_NULL;
strm.avail_in = 0;
strm.next_in = Z_NULL;

if(gzip)
ret = inflateInit2(&strm, 47);
else
ret = inflateInit(&strm);

if (ret != Z_OK)
return ret;

strm.avail_in = len;
strm.next_in = source;

/* 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:
inflateEnd(&strm);
return ret;
}
have = CHUNK - strm.avail_out;
totalsize += have;
*dest = realloc(*dest,totalsize);
memcpy(*dest + totalsize - have,out,have);
} while (strm.avail_out == 0);

/* clean up and return */
(void)inflateEnd(&strm);
return ret == Z_STREAM_END ? Z_OK : Z_DATA_ERROR;
}