C++ LZMA SDK : Uncompress function for LZMA2 compressed file

Question

我正在尝试创建一个解压缩 LZAM2 压缩数据的函数。我的灵感来自 this tutorial这对 LZMA 非常有效，我尝试将其改编为 LZMA2。我成功地为 LZMA2 创建了压缩函数，但我没有成功创建解压缩函数。

这里是压缩函数:

static void Compress2Inc(std::vector<unsigned char> &outBuf,
                         const std::vector<unsigned char> &inBuf)
{
    CLzma2EncHandle enc = Lzma2Enc_Create(&SzAllocForLzma, &SzAllocForLzma2);
    assert(enc);

    CLzma2EncProps props;
    Lzma2EncProps_Init(&props);
    props.lzmaProps.writeEndMark = 1; // 0 or 1

    SRes res = Lzma2Enc_SetProps(enc, &props);
    assert(res == SZ_OK);

    unsigned propsSize = LZMA_PROPS_SIZE;
    outBuf.resize(propsSize);

    res = Lzma2Enc_WriteProperties(enc);
    //cout << res;
    //assert(res == SZ_OK && propsSize == LZMA_PROPS_SIZE);

    VectorInStream inStream = { &VectorInStream_Read, &inBuf, 0 };
    VectorOutStream outStream = { &VectorOutStream_Write, &outBuf };

    res = Lzma2Enc_Encode(enc,
        (ISeqOutStream*)&outStream, (ISeqInStream*)&inStream,
        0);
    assert(res == SZ_OK);

    Lzma2Enc_Destroy(enc);
}

地点:

static void *AllocForLzma2(void *, size_t size) { return BigAlloc(size); }
static void FreeForLzma2(void *, void *address) { BigFree(address); }
static ISzAlloc SzAllocForLzma2 = { AllocForLzma2, FreeForLzma2 };

static void *AllocForLzma(void *, size_t size) { return MyAlloc(size); }
static void FreeForLzma(void *, void *address) { MyFree(address); }
static ISzAlloc SzAllocForLzma = { AllocForLzma, FreeForLzma };

typedef struct
{
    ISeqInStream SeqInStream;
    const std::vector<unsigned char> *Buf;
    unsigned BufPos;
} VectorInStream;

SRes VectorInStream_Read(void *p, void *buf, size_t *size)
{
    VectorInStream *ctx = (VectorInStream*)p;
    *size = min(*size, ctx->Buf->size() - ctx->BufPos);
    if (*size)
        memcpy(buf, &(*ctx->Buf)[ctx->BufPos], *size);
    ctx->BufPos += *size;
    return SZ_OK;
}

typedef struct
{
    ISeqOutStream SeqOutStream;
    std::vector<unsigned char> *Buf;
} VectorOutStream;

size_t VectorOutStream_Write(void *p, const void *buf, size_t size)
{
    VectorOutStream *ctx = (VectorOutStream*)p;
    if (size)
    {
        unsigned oldSize = ctx->Buf->size();
        ctx->Buf->resize(oldSize + size);
        memcpy(&(*ctx->Buf)[oldSize], buf, size);
    }
    return size;
}

到目前为止，这是我对解压缩函数的了解，但是 Lzma2Dec_DecodeToBuf 函数返回错误代码 1(SZ_ERROR_DATA) 而我就是不能'在网络上找不到与此相关的任何信息。

static void Uncompress2Inc(std::vector<unsigned char> &outBuf,
                           const std::vector<unsigned char> &inBuf)
{
    CLzma2Dec dec;
    Lzma2Dec_Construct(&dec);

    SRes res = Lzma2Dec_Allocate(&dec, outBuf.size(), &SzAllocForLzma);
    assert(res == SZ_OK);

    Lzma2Dec_Init(&dec);

    outBuf.resize(UNCOMPRESSED_SIZE);
    unsigned outPos = 0, inPos = LZMA_PROPS_SIZE;
    ELzmaStatus status;
    const unsigned BUF_SIZE = 10240;
    while (outPos < outBuf.size())
    {
        unsigned destLen = min(BUF_SIZE, outBuf.size() - outPos);
        unsigned srcLen  = min(BUF_SIZE, inBuf.size() - inPos);
        unsigned srcLenOld = srcLen, destLenOld = destLen;

        res = Lzma2Dec_DecodeToBuf(&dec,
                                   &outBuf[outPos], &destLen,
                                   &inBuf[inPos], &srcLen,
                                   (outPos + destLen == outBuf.size()) ? LZMA_FINISH_END : LZMA_FINISH_ANY,
                                   &status);

        assert(res == SZ_OK);
        inPos += srcLen;
        outPos += destLen;
        if (status == LZMA_STATUS_FINISHED_WITH_MARK)
            break;
    }

    Lzma2Dec_Free(&dec, &SzAllocForLzma);
    outBuf.resize(outPos);
}

我正在使用从 here 下载的 Visual Studio 2008 和 LZMA SDK .有人here有完全相同的问题，但我无法使用他的代码...

有没有人使用LZMA SDK成功解压过LZMA2压缩文件？

请帮忙!

Answer 1

临时解决方法是将 SRes res = Lzma2Dec_Allocate(&dec, outBuf.size(), &SzAllocForLzma); 替换为 SRes res = Lzma2Dec_Allocate(&dec, 8, &SzAllocForLzma); 在 Uncompress2Inc 函数中，其中 8 是一个魔数(Magic Number)...

然而这不是解决问题的正确方法...

第一个错误是 Lzma2Enc_WriteProperties 没有返回结果，而是一个属性字节，它必须用作 Uncompress2Inc 函数中 Lzma2Dec_Allocate 调用的第二个参数.结果，我们将魔数(Magic Number) 8 替换为属性字节，一切都按预期进行。

为了实现这一点，必须将 5 字节的 header 添加到将在解码函数中提取的编码数据。这是一个在 VS2008 中工作的例子(不是最完美的代码，但它工作......我稍后会回来，当我有时间时，有一个更好的例子):

void Lzma2Benchmark::compressChunk(std::vector<unsigned char> &outBuf, const std::vector<unsigned char> &inBuf)
{
    //! \todo This is a temporary workaround, size needs to be added to the 
    m_uncompressedSize = inBuf.size();

    std::cout << "Uncompressed size is: " << inBuf.size() << std::endl;

    DWORD tickCountBeforeCompression = GetTickCount();

    CLzma2EncHandle enc = Lzma2Enc_Create(&m_szAllocForLzma, &m_szAllocForLzma2);
    assert(enc);

    CLzma2EncProps props;
    Lzma2EncProps_Init(&props);
    props.lzmaProps.writeEndMark = 1; // 0 or 1
    props.lzmaProps.level = 9;
    props.lzmaProps.numThreads = 3;
    //props.numTotalThreads = 2;

    SRes res = Lzma2Enc_SetProps(enc, &props);
    assert(res == SZ_OK);

    // LZMA_PROPS_SIZE == 5 bytes
    unsigned propsSize = LZMA_PROPS_SIZE;
    outBuf.resize(propsSize);

    // I think Lzma2Enc_WriteProperties returns the encoding properties in 1 Byte
    Byte properties = Lzma2Enc_WriteProperties(enc);

    //! \todo This is a temporary workaround
    m_propByte = properties;

    //! \todo Here m_propByte and m_uncompressedSize need to be added to outBuf's 5 byte header so simply add those 2 values to outBuf and start the encoding from there.

    BenchmarkUtils::VectorInStream inStream = { &BenchmarkUtils::VectorInStream_Read, &inBuf, 0 };
    BenchmarkUtils::VectorOutStream outStream = { &BenchmarkUtils::VectorOutStream_Write, &outBuf };

    res = Lzma2Enc_Encode(enc,
                          (ISeqOutStream*)&outStream,
                          (ISeqInStream*)&inStream,
                          0);

    std::cout << "Compress time is: " << GetTickCount() - tickCountBeforeCompression << " milliseconds.\n";

    assert(res == SZ_OK);

    Lzma2Enc_Destroy(enc);

    std::cout << "Compressed size is: " << outBuf.size() << std::endl;
}

void Lzma2Benchmark::unCompressChunk(std::vector<unsigned char> &outBuf, const std::vector<unsigned char> &inBuf)
{
    DWORD tickCountBeforeUncompression = GetTickCount();

    CLzma2Dec dec;
    Lzma2Dec_Construct(&dec);

    //! \todo Heere the property size and the uncompressed size need to be extracted from inBuf, which is the compressed data.

    // The second parameter is a temporary workaround.
    SRes res = Lzma2Dec_Allocate(&dec, m_propByte/*8*/, &m_szAllocForLzma);
    assert(res == SZ_OK);

    Lzma2Dec_Init(&dec);

    outBuf.resize(m_uncompressedSize);
    unsigned outPos = 0, inPos = LZMA_PROPS_SIZE;
    ELzmaStatus status;
    const unsigned BUF_SIZE = 10240;

    while(outPos < outBuf.size())
    {
        SizeT destLen = std::min(BUF_SIZE, outBuf.size() - outPos);
        SizeT srcLen  = std::min(BUF_SIZE, inBuf.size() - inPos);
        SizeT srcLenOld = srcLen, destLenOld = destLen;

        res = Lzma2Dec_DecodeToBuf(&dec,
                                   &outBuf[outPos],
                                   &destLen,
                                   &inBuf[inPos],
                                   &srcLen,
                                   (outPos + destLen == outBuf.size()) ? LZMA_FINISH_END : LZMA_FINISH_ANY,
                                   &status);

        assert(res == SZ_OK);
        inPos += srcLen;
        outPos += destLen;

        if(status == LZMA_STATUS_FINISHED_WITH_MARK)
        {
            break;
        }
    }

    Lzma2Dec_Free(&dec, &m_szAllocForLzma);

    outBuf.resize(outPos);

    std::cout << "Uncompress time is: " << GetTickCount() - tickCountBeforeUncompression << " milliseconds.\n";
}