如何让LZO使用文件流?

时间:2010-11-20 21:09:06

标签: c file compression stream lzo

我正在尝试用LZO压缩文件流而不是很远。具体来说,我在提取由compressFileWithLzo1x函数创建的存档文件时会出现分段错误。

我的main函数和原型声明是:

#include <stdio.h>
#include <stdlib.h>
#include "lzo/include/lzo/lzo1x.h"

#define LZO_IN_CHUNK (128*1024L)
#define LZO_OUT_CHUNK (LZO_IN_CHUNK + LZO_IN_CHUNK/16 + 64 + 3)

int compressFileWithLzo1x(const char *inFn, const char *outFn);
int extractFileWithLzo1x(const char *inFn);

int main(int argc, char **argv) {

    const char *inFilename = "test.txt";
    const char *outFilename = "test.txt.lzo1x";

    if ( compressFileWithLzo1x(inFilename, outFilename) != 0 )
        exit(EXIT_FAILURE);

    if ( extractFileWithLzo1x(outFilename) != 0 )
        exit(EXIT_FAILURE);

    return 0;
}

这是我的压缩功能的实现:

int compressFileWithLzo1x(const char *inFn, const char *outFn) {

    FILE *inFnPtr = fopen(outFn, "r");
    FILE *outFnPtr = fopen(outFn, "wb");
    int compressionResult;
    lzo_bytep in;
    lzo_bytep out;
    lzo_voidp wrkmem;
    lzo_uint out_len;
    size_t inResult;

    if (lzo_init() != LZO_E_OK)
        return -1;

    in = (lzo_bytep)malloc(LZO_IN_CHUNK);
    out = (lzo_bytep)malloc(LZO_OUT_CHUNK);
    wrkmem = (lzo_voidp)malloc(LZO1X_1_MEM_COMPRESS);

    do { 
        inResult = fread(in, sizeof(lzo_byte), LZO_IN_CHUNK, inFnPtr);
        if (inResult == 0)
            break;
        compressionResult = lzo1x_1_compress(in, LZO_IN_CHUNK, out, &out_len, wrkmem);
        if ((out_len >= LZO_IN_CHUNK) || (compressionResult != LZO_E_OK))
            return -1;
        if (fwrite(out, sizeof(lzo_byte), (size_t)out_len, outFnPtr) != (size_t)out_len || ferror(outFnPtr))
            return -1;
        fflush(outFnPtr);
    } while (!feof(inFnPtr) && !ferror(inFnPtr));

    free(wrkmem);
    free(out);
    free(in);
    fclose(inFnPtr);
    fclose(outFnPtr);

    return 0;
}

以下是我的解压缩功能的实现:

int extractFileWithLzo1x(const char *inFn) {

    FILE *inFnPtr = fopen(inFn, "rb");
    lzo_bytep in = (lzo_bytep)malloc(LZO_IN_CHUNK);
    lzo_bytep out = (lzo_bytep)malloc(LZO_OUT_CHUNK);
    int extractionResult; 
    size_t inResult;
    lzo_uint new_length;

    if (lzo_init() != LZO_E_OK)
        return -1;

    do {
        new_length = LZO_IN_CHUNK;
        inResult = fread(in, sizeof(lzo_byte), LZO_IN_CHUNK, inFnPtr);
        extractionResult = lzo1x_decompress(out, LZO_OUT_CHUNK, in, &new_length, NULL);
        if ((extractionResult != LZO_E_OK) || (new_length != LZO_IN_CHUNK))
            return -1;
        fprintf(stderr, "out: [%s]\n", (unsigned char *)out);
    } while (!feof(inFnPtr) && (!ferror(inFnPtr));

    free(in);
    free(out);
    fclose(inFnPtr);

    return 0;
}

此处发生分段错误:

extractionResult = lzo1x_decompress(out, LZO_OUT_CHUNK, in, &new_length, NULL);

这种方法导致分段错误有什么问题?

我希望这次没有留下任何代码。如果我需要添加更多信息,请随时告诉我。提前感谢您的建议。

3 个答案:

答案 0 :(得分:2)

您正在压缩独立块。 LZO解压缩器需要压缩数据的字节长度,因为当它解码EOF时,它会检查它是否已经消耗了所有输入字节(如果没有则返回错误),因此你需要存储每个压缩块的长度。因此,您需要更复杂的文件格式。例如:

# compressing, in python-like pseudocode
ifile = open("data", "rb")
ofile = open("data.mylzo", "wb")
input, input_len = ifile.read(65536)
while input_len > 0:
  compressed, compressed_len = lzo1x(input, input_len)
  compressed_len -= 1 # store len-1 of next block
  if compressed_len < 65536 - 1:
    ofile.write(compressed_len & 255) # be sure of endianess in file formats!
    ofile.write(compressed_len >> 8)
    ofile.write(compressed)
  else:
    ofile.write(255) # incompressible block stored it as-is (saves space & time).
    ofile.write(255)
    ofile.write(input)
  input, input_len = ifile.read(65536)
ofile.close()
ifile.close()

# decompressing, in python-like pseudocode
ifile = open("data.mylzo", "rb")
ofile = open("data", "wb")
compressed_len_s = ifile.read(2)
while len(compressed_len_s) == 2:
  compressed_len = (compressed_len_s[0] | (compressed_len_s[1] << 8)) + 1
  if compressed_len == 65536:
    ofile.write(ifile.read(65536)) # this can be done without copying
  else:
    compressed = ifile.read(compressed_len)
    decompressed = lzo1x_decompress(compressed, compressed_len)
    ofile.write(decompressed)
  compressed_len_s = ifile.read(2)
ofile.close()
ifile.close()

如果您希望能够在不跳过的情况下解压缩块(无论是并行解压缩还是随机访问),您应该将压缩块的长度放在第一个块之前的开头。用大量的数量来表示它们。

最后一个块可以短于64k,并且它可以是不可压缩的,但我们仍然会存储压缩格式,即使它比非压缩格式更长,因为只有完整的64k块按原样存储。如果整个文件短于64k,它将会增长。

答案 1 :(得分:1)

您提供的代码将无法编译(=; #defines中的虚假inFilePtr,而不是inFnPtr在各个地方,等等。但是:

  1. 压缩时,您没有考虑fread()返回的实际数据量,这可能会少于LZO_IN_CHUNK

    compressionResult = lzo1x_1_compress(in, LZO_IN_CHUNK, out, &out_len, wrkmem);
    

    应该是

    compressionResult = lzo1x_1_compress(in, inResult, out, &out_len, wrkmem);
    

    (这不太可能是问题,但会在文件末尾添加虚假垃圾。)

  2. 解压缩时,你遇到了类似的问题,输入/输出参数是错误的方式,这可能是你的段错误的原因。

    extractionResult = lzo1x_decompress(out, LZO_OUT_CHUNK, in, &new_length, NULL);
    

    应该是

    extractionResult = lzo1x_decompress(in, inResult, out, &new_length, NULL);
    

答案 2 :(得分:1)

我认为您在int compressFileWithLzo1x打开了错误的文件:

FILE *inFnPtr = fopen(outFn, "r");

应该是

FILE *inFnPtr = fopen(inFn, "r");