# Apple的LZF算法解析

有关LZF算法的相关解析文档比较少，但是Apple对LZF的开源，可以让我们对该算法进行一个简单的解析。LZFSE 基于 Lempel-Ziv ，并使用了有限状态熵编码。LZF采用类似lz77和lzss的混合编码。使用3种“起始标记”来代表每段输出的数据串。

接下来看一下开源的LZF算法的实现源码。

1.定义的全局字段：

```       private readonly long[] _hashTable = new long[Hsize];

private const uint Hlog = 14;

private const uint Hsize = (1 << 14);

private const uint MaxLit = (1 << 5);

private const uint MaxOff = (1 << 13);

private const uint MaxRef = ((1 << 8) + (1 << 3));```

2.使用LibLZF算法压缩数据：

```        /// <summary>
/// 使用LibLZF算法压缩数据
/// </summary>
/// <param name="input">需要压缩的数据</param>
/// <param name="inputLength">要压缩的数据的长度</param>
/// <param name="output">引用将包含压缩数据的缓冲区</param>
/// <param name="outputLength">压缩缓冲区的长度（应大于输入缓冲区）</param>
/// <returns>输出缓冲区中压缩归档的大小</returns>
public int Compress(byte[] input, int inputLength, byte[] output, int outputLength)
{
Array.Clear(_hashTable, 0, (int)Hsize);
uint iidx = 0;
uint oidx = 0;
var hval = (uint)(((input[iidx]) << 8) | input[iidx + 1]);
var lit = 0;
for (; ; )
{
if (iidx < inputLength - 2)
{
hval = (hval << 8) | input[iidx + 2];
long hslot = ((hval ^ (hval << 5)) >> (int)(((3 * 8 - Hlog)) - hval * 5) & (Hsize - 1));
var reference = _hashTable[hslot];
_hashTable[hslot] = iidx;
long off;
if ((off = iidx - reference - 1) < MaxOff
&& iidx + 4 < inputLength
&& reference > 0
&& input[reference + 0] == input[iidx + 0]
&& input[reference + 1] == input[iidx + 1]
&& input[reference + 2] == input[iidx + 2]
)
{
uint len = 2;
var maxlen = (uint)inputLength - iidx - len;
maxlen = maxlen > MaxRef ? MaxRef : maxlen;
if (oidx + lit + 1 + 3 >= outputLength)
return 0;
do
len++;
while (len < maxlen && input[reference + len] == input[iidx + len]);
if (lit != 0)
{
output[oidx++] = (byte)(lit - 1);
lit = -lit;
do
output[oidx++] = input[iidx + lit];
while ((++lit) != 0);
}
len -= 2;
iidx++;
if (len < 7)
{
output[oidx++] = (byte)((off >> 8) + (len << 5));
}
else
{
output[oidx++] = (byte)((off >> 8) + (7 << 5));
output[oidx++] = (byte)(len - 7);
}
output[oidx++] = (byte)off;
iidx += len - 1;
hval = (uint)(((input[iidx]) << 8) | input[iidx + 1]);
hval = (hval << 8) | input[iidx + 2];
_hashTable[((hval ^ (hval << 5)) >> (int)(((3 * 8 - Hlog)) - hval * 5) & (Hsize - 1))] = iidx;
iidx++;
hval = (hval << 8) | input[iidx + 2];
_hashTable[((hval ^ (hval << 5)) >> (int)(((3 * 8 - Hlog)) - hval * 5) & (Hsize - 1))] = iidx;
iidx++;
continue;
}
}
else if (iidx == inputLength)
break;
lit++;
iidx++;
if (lit != MaxLit) continue;
if (oidx + 1 + MaxLit >= outputLength)
return 0;

output[oidx++] = (byte)(MaxLit - 1);
lit = -lit;
do
output[oidx++] = input[iidx + lit];
while ((++lit) != 0);
}
if (lit == 0) return (int)oidx;
if (oidx + lit + 1 >= outputLength)
return 0;
output[oidx++] = (byte)(lit - 1);
lit = -lit;
do
output[oidx++] = input[iidx + lit];
while ((++lit) != 0);

return (int)oidx;
}```

3.

```        /// <summary>
/// 使用LibLZF算法解压缩数据
/// </summary>
/// <param name="input">参考数据进行解压缩</param>
/// <param name="inputLength">要解压缩的数据的长度</param>
/// <param name="output">引用包含解压缩数据的缓冲区</param>
/// <param name="outputLength">输出缓冲区中压缩归档的大小</param>
/// <returns>返回解压缩大小</returns>
public int Decompress(byte[] input, int inputLength, byte[] output, int outputLength)
{
uint iidx = 0;
uint oidx = 0;
do
{
uint ctrl = input[iidx++];

if (ctrl < (1 << 5))
{
ctrl++;

if (oidx + ctrl > outputLength)
{
return 0;
}

do
output[oidx++] = input[iidx++];
while ((--ctrl) != 0);
}
else
{
var len = ctrl >> 5;
var reference = (int)(oidx - ((ctrl & 0x1f) << 8) - 1);
if (len == 7)
len += input[iidx++];
reference -= input[iidx++];
if (oidx + len + 2 > outputLength)
{
return 0;
}
if (reference < 0)
{
return 0;
}
output[oidx++] = output[reference++];
output[oidx++] = output[reference++];
do
output[oidx++] = output[reference++];
while ((--len) != 0);
}
}
while (iidx < inputLength);

return (int)oidx;
}```

以上是LZF算法的代码。

80 篇文章31 人订阅

0 条评论

## 相关文章

1334

2589

2416

6499

### 可视化（番外篇）——在Eclipse RCP中玩转OpenGL

最近在看有关Eclipse RCP方面的东西，鉴于Gephi是使用opengl作为绘图引擎，所以，萌生了在Eclipse RCP下添加画布，使用opengl...

2125

1172

1301

1663

3501

1543