用到压缩，以前1.1的时候都用的第3方库，这次想尝试一下2.0带的 Compression库。
一用发现这个库压的东西偏大，而且没文件名没时间。

那么到底是为什么会这样呢，难道是我的使用有问题？

决定要搞搞明白，于是有了下面这段代码，用SharpZipLib和2.0自带的库做下对比，大家都采用Gzip压缩

使用2.0的库做压缩

static MemoryStream Deflate(byte[] data)

{

MemoryStream memoryStream = new MemoryStream();

using (GZipStream gzip = new GZipStream(memoryStream, CompressionMode.Compress, true))

{

gzip.Write(data, 0, data.Length);

gzip.Flush();

gzip.Close();

}

return memoryStream;

}

使用SharpZipLib压缩

static MemoryStream DeflateUseSharpZipLib(byte[] data)

{

MemoryStream memoryStream = new MemoryStream();

using (GZipOutputStream outStream = new GZipOutputStream(memoryStream))

{

outStream.IsStreamOwner = false;

outStream.Write(data, 0, data.Length);

outStream.Flush();

outStream.Finish();

}

return memoryStream;

}

ok，之后看看我们的测试文件 1.pdf 3358kb

使用System.IO.Compression
testzip 1.pdf 0.zip 0
使用ICSharpCode.SharpZipLib.GZip
testzip 1.pdf 1.zip 1

压缩后大小：
0.zip 2499kb(System)
1.zip 1612kb(SharpZipLib)

可以看到 ICSharpCode.SharpZipLib.GZip 压缩后1612kb,C# System.IO.Compression.GZipStream 压缩后大小2499kb

而且System.IO.Compression.GZipStream压缩的文件没文件名，时间也是不对的

那么是什么原因呢？
那就让我们跟踪看看

System.IO.Compression.GZipStream的实现

GZipStream类

public override void Write(byte[] array, int offset, int count)

{

if (this.deflateStream == null)

{

throw new ObjectDisposedException(null, SR.GetString("ObjectDisposed_StreamClosed"));

}

this.deflateStream.Write(array, offset, count);

}

DeflateStream类

public override void Write(byte[] array, int offset, int count)

{

this.EnsureCompressionMode();

this.ValidateParameters(array, offset, count);

this.InternalWrite(array, offset, count, false);

}

internal void InternalWrite(byte[] array, int offset, int count, bool isAsync)

{

int deflateOutput;

while (!this.deflater.NeedsInput())

{

deflateOutput = this.deflater.GetDeflateOutput(this.buffer);

if (deflateOutput != 0)

{

if (isAsync)

{

IAsyncResult asyncResult = this._stream.BeginWrite(this.buffer, 0, deflateOutput, null, null);

this._stream.EndWrite(asyncResult);

}

else

{

this._stream.Write(this.buffer, 0, deflateOutput);

}

this.deflater.SetInput(array, offset, count);

while (!this.deflater.NeedsInput())

{

deflateOutput = this.deflater.GetDeflateOutput(this.buffer);

if (deflateOutput != 0)

{

if (isAsync)

{

IAsyncResult result2 = this._stream.BeginWrite(this.buffer, 0, deflateOutput, null, null);

this._stream.EndWrite(result2);

}

else

{

this._stream.Write(this.buffer, 0, deflateOutput);

}

public int GetDeflateOutput(byte[] output)

{

return this.encoder.GetCompressedOutput(output);

}

Write 调用 InternalWrite，而InternalWrite调用GetDeflateOutput
encoder是FastEncoder对象，在Deflate构造函数中初始化

FastEncoder类

public int GetCompressedOutput(byte[] outputBuffer)

{

this.output.UpdateBuffer(outputBuffer);

if (this.usingGzip && !this.hasGzipHeader)

{

this.output.WriteGzipHeader(3);

this.hasGzipHeader = true;

}

if (!this.hasBlockHeader)

{

this.hasBlockHeader = true;

this.output.WritePreamble();

}

do

{

int count = (this.inputBuffer.Count < this.inputWindow.FreeWindowSpace) ? this.inputBuffer.Count : this.inputWindow.FreeWindowSpace;

if (count > 0)

{

this.inputWindow.CopyBytes(this.inputBuffer.Buffer, this.inputBuffer.StartIndex, count);

if (this.usingGzip)

{

this.gzipCrc32 = DecodeHelper.UpdateCrc32(this.gzipCrc32, this.inputBuffer.Buffer, this.inputBuffer.StartIndex, count);

uint num2 = this.inputStreamSize + ((uint) count);

if (num2 < this.inputStreamSize)

{

throw new InvalidDataException(SR.GetString("StreamSizeOverflow"));

}

this.inputStreamSize = num2;

}

this.inputBuffer.ConsumeBytes(count);

}

while ((this.inputWindow.BytesAvailable > 0) && this.output.SafeToWriteTo())

{

this.inputWindow.GetNextSymbolOrMatch(this.currentMatch);

if (this.currentMatch.State == MatchState.HasSymbol)

{

this.output.WriteChar(this.currentMatch.Symbol);

}

else

{

if (this.currentMatch.State == MatchState.HasMatch)

{

this.output.WriteMatch(this.currentMatch.Length, this.currentMatch.Position);

continue;

}

this.output.WriteChar(this.currentMatch.Symbol);

this.output.WriteMatch(this.currentMatch.Length, this.currentMatch.Position);

}

while (this.output.SafeToWriteTo() && !this.NeedsInput());

this.needsEOB = true;

return this.output.BytesWritten;

}

注意到output.WriteGzipHeader(3)函数，汗一下，压缩率写死了。。。

看看WriteGzipHeader是怎么写的

internal void WriteGzipHeader(int compression_level)

{

this.outputBuf[this.outputPos++] = 0x1f;

this.outputBuf[this.outputPos++] = 0x8b;

this.outputBuf[this.outputPos++] = 8;

this.outputBuf[this.outputPos++] = 0;

if (compression_level == 10)

{

this.outputBuf[this.outputPos++] = 2;

}

else

{

this.outputBuf[this.outputPos++] = 4;

}

this.outputBuf[this.outputPos++] = 0;

}

再次晕倒，没扩展头信息，没时间，全部写死，如果看不明白，对照一下gzip的格式就知道了

gzip格式 http://www.gzip.org/zlib/rfc-gzip.html

至此，已经知道为什么2.0的Gzip压缩，没有文件名信息，也没有时间了，真的是很阳春白雪的压缩。

还有另外一个问题，为什么2.0自带的库压缩率低？

ITPub博客

C# 压缩的缺陷

最新文章