HADOOP-9319. Update bundled LZ4 source to r99. (Binglin Chang via llu)
git-svn-id: https://svn.apache.org/repos/asf/hadoop/common/trunk@1510734 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Luke Lu
parent
d9df191119
commit
c8e200f2c2
@ -283,6 +283,8 @@ Release 2.3.0 - UNRELEASED
|
||||
|
||||
IMPROVEMENTS
|
||||
|
||||
HADOOP-9319. Update bundled LZ4 source to r99. (Binglin Chang via llu)
|
||||
|
||||
HADOOP-9241. DU refresh interval is not configurable (harsh)
|
||||
|
||||
HADOOP-9417. Support for symlink resolution in LocalFileSystem /
|
||||
|
||||
@ -252,24 +252,26 @@ in src/main/native/src/org/apache/hadoop/util:
|
||||
* BSD-style license that can be found in the LICENSE file.
|
||||
*/
|
||||
|
||||
For src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4.c:
|
||||
For src/main/native/src/org/apache/hadoop/io/compress/lz4/{lz4.h,lz4.c,
|
||||
lz4_encoder.h,lz4hc.h,lz4hc.c,lz4hc_encoder.h},
|
||||
|
||||
/*
|
||||
LZ4 - Fast LZ compression algorithm
|
||||
Copyright (C) 2011, Yann Collet.
|
||||
BSD License
|
||||
Header File
|
||||
Copyright (C) 2011-2013, Yann Collet.
|
||||
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are
|
||||
met:
|
||||
|
||||
|
||||
* Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above
|
||||
copyright notice, this list of conditions and the following disclaimer
|
||||
in the documentation and/or other materials provided with the
|
||||
distribution.
|
||||
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
@ -281,4 +283,8 @@ in src/main/native/src/org/apache/hadoop/util:
|
||||
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
You can contact the author at :
|
||||
- LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html
|
||||
- LZ4 source repository : http://code.google.com/p/lz4/
|
||||
*/
|
||||
|
||||
@ -456,7 +456,12 @@
|
||||
<exclude>src/test/empty-file</exclude>
|
||||
<exclude>src/test/all-tests</exclude>
|
||||
<exclude>src/test/resources/kdc/ldif/users.ldif</exclude>
|
||||
<exclude>src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4.h</exclude>
|
||||
<exclude>src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4.c</exclude>
|
||||
<exclude>src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4_encoder.h</exclude>
|
||||
<exclude>src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4hc.h</exclude>
|
||||
<exclude>src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4hc.c</exclude>
|
||||
<exclude>src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4hc_encoder.h</exclude>
|
||||
<exclude>src/test/java/org/apache/hadoop/fs/test-untar.tgz</exclude>
|
||||
</excludes>
|
||||
</configuration>
|
||||
|
||||
@ -170,6 +170,7 @@ add_dual_library(hadoop
|
||||
${D}/io/compress/lz4/Lz4Compressor.c
|
||||
${D}/io/compress/lz4/Lz4Decompressor.c
|
||||
${D}/io/compress/lz4/lz4.c
|
||||
${D}/io/compress/lz4/lz4hc.c
|
||||
${SNAPPY_SOURCE_FILES}
|
||||
${D}/io/compress/zlib/ZlibCompressor.c
|
||||
${D}/io/compress/zlib/ZlibDecompressor.c
|
||||
|
||||
@ -96,7 +96,7 @@ public class CommonConfigurationKeys extends CommonConfigurationKeysPublic {
|
||||
public static final int IO_COMPRESSION_CODEC_SNAPPY_BUFFERSIZE_DEFAULT =
|
||||
256 * 1024;
|
||||
|
||||
/** Internal buffer size for Snappy compressor/decompressors */
|
||||
/** Internal buffer size for Lz4 compressor/decompressors */
|
||||
public static final String IO_COMPRESSION_CODEC_LZ4_BUFFERSIZE_KEY =
|
||||
"io.compression.codec.lz4.buffersize";
|
||||
|
||||
@ -104,6 +104,14 @@ public class CommonConfigurationKeys extends CommonConfigurationKeysPublic {
|
||||
public static final int IO_COMPRESSION_CODEC_LZ4_BUFFERSIZE_DEFAULT =
|
||||
256 * 1024;
|
||||
|
||||
/** Use lz4hc(slow but with high compression ratio) for lz4 compression */
|
||||
public static final String IO_COMPRESSION_CODEC_LZ4_USELZ4HC_KEY =
|
||||
"io.compression.codec.lz4.use.lz4hc";
|
||||
|
||||
/** Default value for IO_COMPRESSION_CODEC_USELZ4HC_KEY */
|
||||
public static final boolean IO_COMPRESSION_CODEC_LZ4_USELZ4HC_DEFAULT =
|
||||
false;
|
||||
|
||||
/**
|
||||
* Service Authorization
|
||||
*/
|
||||
|
||||
@ -107,7 +107,7 @@ public CompressionOutputStream createOutputStream(OutputStream out,
|
||||
CommonConfigurationKeys.IO_COMPRESSION_CODEC_LZ4_BUFFERSIZE_KEY,
|
||||
CommonConfigurationKeys.IO_COMPRESSION_CODEC_LZ4_BUFFERSIZE_DEFAULT);
|
||||
|
||||
int compressionOverhead = Math.max((int)(bufferSize * 0.01), 10);
|
||||
int compressionOverhead = bufferSize/255 + 16;
|
||||
|
||||
return new BlockCompressorStream(out, compressor, bufferSize,
|
||||
compressionOverhead);
|
||||
@ -140,7 +140,10 @@ public Compressor createCompressor() {
|
||||
int bufferSize = conf.getInt(
|
||||
CommonConfigurationKeys.IO_COMPRESSION_CODEC_LZ4_BUFFERSIZE_KEY,
|
||||
CommonConfigurationKeys.IO_COMPRESSION_CODEC_LZ4_BUFFERSIZE_DEFAULT);
|
||||
return new Lz4Compressor(bufferSize);
|
||||
boolean useLz4HC = conf.getBoolean(
|
||||
CommonConfigurationKeys.IO_COMPRESSION_CODEC_LZ4_USELZ4HC_KEY,
|
||||
CommonConfigurationKeys.IO_COMPRESSION_CODEC_LZ4_USELZ4HC_DEFAULT);
|
||||
return new Lz4Compressor(bufferSize, useLz4HC);
|
||||
}
|
||||
|
||||
/**
|
||||
|
||||
@ -52,6 +52,7 @@ public class Lz4Compressor implements Compressor {
|
||||
private long bytesRead = 0L;
|
||||
private long bytesWritten = 0L;
|
||||
|
||||
private final boolean useLz4HC;
|
||||
|
||||
static {
|
||||
if (NativeCodeLoader.isNativeCodeLoaded()) {
|
||||
@ -72,8 +73,11 @@ public class Lz4Compressor implements Compressor {
|
||||
* Creates a new compressor.
|
||||
*
|
||||
* @param directBufferSize size of the direct buffer to be used.
|
||||
* @param useLz4HC use high compression ratio version of lz4,
|
||||
* which trades CPU for compression ratio.
|
||||
*/
|
||||
public Lz4Compressor(int directBufferSize) {
|
||||
public Lz4Compressor(int directBufferSize, boolean useLz4HC) {
|
||||
this.useLz4HC = useLz4HC;
|
||||
this.directBufferSize = directBufferSize;
|
||||
|
||||
uncompressedDirectBuf = ByteBuffer.allocateDirect(directBufferSize);
|
||||
@ -81,6 +85,15 @@ public Lz4Compressor(int directBufferSize) {
|
||||
compressedDirectBuf.position(directBufferSize);
|
||||
}
|
||||
|
||||
/**
|
||||
* Creates a new compressor.
|
||||
*
|
||||
* @param directBufferSize size of the direct buffer to be used.
|
||||
*/
|
||||
public Lz4Compressor(int directBufferSize) {
|
||||
this(directBufferSize, false);
|
||||
}
|
||||
|
||||
/**
|
||||
* Creates a new compressor with the default buffer size.
|
||||
*/
|
||||
@ -227,7 +240,7 @@ public synchronized int compress(byte[] b, int off, int len)
|
||||
}
|
||||
|
||||
// Compress data
|
||||
n = compressBytesDirect();
|
||||
n = useLz4HC ? compressBytesDirectHC() : compressBytesDirect();
|
||||
compressedDirectBuf.limit(n);
|
||||
uncompressedDirectBuf.clear(); // lz4 consumes all buffer input
|
||||
|
||||
@ -297,5 +310,7 @@ public synchronized void end() {
|
||||
|
||||
private native int compressBytesDirect();
|
||||
|
||||
private native int compressBytesDirectHC();
|
||||
|
||||
public native static String getLibraryName();
|
||||
}
|
||||
|
||||
@ -72,6 +72,7 @@
|
||||
</ItemDefinitionGroup>
|
||||
<ItemGroup>
|
||||
<ClCompile Include="src\org\apache\hadoop\io\compress\lz4\lz4.c" />
|
||||
<ClCompile Include="src\org\apache\hadoop\io\compress\lz4\lz4hc.c" />
|
||||
<ClCompile Include="src\org\apache\hadoop\io\compress\lz4\Lz4Compressor.c" />
|
||||
<ClCompile Include="src\org\apache\hadoop\io\compress\lz4\Lz4Decompressor.c" />
|
||||
<ClCompile Include="src\org\apache\hadoop\io\nativeio\file_descriptor.c" />
|
||||
|
||||
@ -51,6 +51,9 @@
|
||||
<ClCompile Include="src\org\apache\hadoop\io\compress\lz4\lz4.c">
|
||||
<Filter>Source Files</Filter>
|
||||
</ClCompile>
|
||||
<ClCompile Include="src\org\apache\hadoop\io\compress\lz4\lz4hc.c">
|
||||
<Filter>Source Files</Filter>
|
||||
</ClCompile>
|
||||
<ClCompile Include="src\org\apache\hadoop\io\compress\lz4\Lz4Compressor.c">
|
||||
<Filter>Source Files</Filter>
|
||||
</ClCompile>
|
||||
|
||||
@ -23,21 +23,9 @@
|
||||
#ifdef UNIX
|
||||
#include "config.h"
|
||||
#endif // UNIX
|
||||
#include "lz4.h"
|
||||
#include "lz4hc.h"
|
||||
|
||||
//****************************
|
||||
// Simple Functions
|
||||
//****************************
|
||||
|
||||
extern int LZ4_compress (const char* source, char* dest, int isize);
|
||||
|
||||
/*
|
||||
LZ4_compress() :
|
||||
return : the number of bytes in compressed buffer dest
|
||||
note : destination buffer must be already allocated.
|
||||
To avoid any problem, size it to handle worst cases situations (input data not compressible)
|
||||
Worst case size is : "inputsize + 0.4%", with "0.4%" being at least 8 bytes.
|
||||
|
||||
*/
|
||||
|
||||
static jfieldID Lz4Compressor_clazz;
|
||||
static jfieldID Lz4Compressor_uncompressedDirectBuf;
|
||||
@ -107,5 +95,45 @@ JNIEXPORT jstring JNICALL
|
||||
Java_org_apache_hadoop_io_compress_lz4_Lz4Compressor_getLibraryName(
|
||||
JNIEnv *env, jclass class
|
||||
) {
|
||||
return (*env)->NewStringUTF(env, "revision:43");
|
||||
return (*env)->NewStringUTF(env, "revision:99");
|
||||
}
|
||||
|
||||
JNIEXPORT jint JNICALL Java_org_apache_hadoop_io_compress_lz4_Lz4Compressor_compressBytesDirectHC
|
||||
(JNIEnv *env, jobject thisj){
|
||||
const char* uncompressed_bytes = NULL;
|
||||
char* compressed_bytes = NULL;
|
||||
|
||||
// Get members of Lz4Compressor
|
||||
jobject clazz = (*env)->GetStaticObjectField(env, thisj, Lz4Compressor_clazz);
|
||||
jobject uncompressed_direct_buf = (*env)->GetObjectField(env, thisj, Lz4Compressor_uncompressedDirectBuf);
|
||||
jint uncompressed_direct_buf_len = (*env)->GetIntField(env, thisj, Lz4Compressor_uncompressedDirectBufLen);
|
||||
jobject compressed_direct_buf = (*env)->GetObjectField(env, thisj, Lz4Compressor_compressedDirectBuf);
|
||||
jint compressed_direct_buf_len = (*env)->GetIntField(env, thisj, Lz4Compressor_directBufferSize);
|
||||
|
||||
// Get the input direct buffer
|
||||
LOCK_CLASS(env, clazz, "Lz4Compressor");
|
||||
uncompressed_bytes = (const char*)(*env)->GetDirectBufferAddress(env, uncompressed_direct_buf);
|
||||
UNLOCK_CLASS(env, clazz, "Lz4Compressor");
|
||||
|
||||
if (uncompressed_bytes == 0) {
|
||||
return (jint)0;
|
||||
}
|
||||
|
||||
// Get the output direct buffer
|
||||
LOCK_CLASS(env, clazz, "Lz4Compressor");
|
||||
compressed_bytes = (char *)(*env)->GetDirectBufferAddress(env, compressed_direct_buf);
|
||||
UNLOCK_CLASS(env, clazz, "Lz4Compressor");
|
||||
|
||||
if (compressed_bytes == 0) {
|
||||
return (jint)0;
|
||||
}
|
||||
|
||||
compressed_direct_buf_len = LZ4_compressHC(uncompressed_bytes, compressed_bytes, uncompressed_direct_buf_len);
|
||||
if (compressed_direct_buf_len < 0){
|
||||
THROW(env, "java/lang/InternalError", "LZ4_compressHC failed");
|
||||
}
|
||||
|
||||
(*env)->SetIntField(env, thisj, Lz4Compressor_uncompressedDirectBufLen, 0);
|
||||
|
||||
return (jint)compressed_direct_buf_len;
|
||||
}
|
||||
|
||||
@ -22,18 +22,7 @@
|
||||
#ifdef UNIX
|
||||
#include "config.h"
|
||||
#endif // UNIX
|
||||
|
||||
int LZ4_uncompress_unknownOutputSize(const char* source, char* dest, int isize, int maxOutputSize);
|
||||
|
||||
/*
|
||||
LZ4_uncompress_unknownOutputSize() :
|
||||
isize : is the input size, therefore the compressed size
|
||||
maxOutputSize : is the size of the destination buffer (which must be already allocated)
|
||||
return : the number of bytes decoded in the destination buffer (necessarily <= maxOutputSize)
|
||||
If the source stream is malformed, the function will stop decoding and return a negative result, indicating the byte position of the faulty instruction
|
||||
This version never writes beyond dest + maxOutputSize, and is therefore protected against malicious data packets
|
||||
note : This version is a bit slower than LZ4_uncompress
|
||||
*/
|
||||
#include "lz4.h"
|
||||
|
||||
|
||||
static jfieldID Lz4Decompressor_clazz;
|
||||
@ -89,7 +78,7 @@ JNIEXPORT jint JNICALL Java_org_apache_hadoop_io_compress_lz4_Lz4Decompressor_de
|
||||
return (jint)0;
|
||||
}
|
||||
|
||||
uncompressed_direct_buf_len = LZ4_uncompress_unknownOutputSize(compressed_bytes, uncompressed_bytes, compressed_direct_buf_len, uncompressed_direct_buf_len);
|
||||
uncompressed_direct_buf_len = LZ4_decompress_safe(compressed_bytes, uncompressed_bytes, compressed_direct_buf_len, uncompressed_direct_buf_len);
|
||||
if (uncompressed_direct_buf_len < 0) {
|
||||
THROW(env, "java/lang/InternalError", "LZ4_uncompress_unknownOutputSize failed.");
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@ -0,0 +1,179 @@
|
||||
/*
|
||||
LZ4 - Fast LZ compression algorithm
|
||||
Header File
|
||||
Copyright (C) 2011-2013, Yann Collet.
|
||||
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are
|
||||
met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above
|
||||
copyright notice, this list of conditions and the following disclaimer
|
||||
in the documentation and/or other materials provided with the
|
||||
distribution.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
You can contact the author at :
|
||||
- LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html
|
||||
- LZ4 source repository : http://code.google.com/p/lz4/
|
||||
*/
|
||||
|
||||
/*
|
||||
Copied from:
|
||||
URL: http://lz4.googlecode.com/svn/trunk
|
||||
Repository Root: http://lz4.googlecode.com/svn
|
||||
Repository UUID: 650e7d94-2a16-8b24-b05c-7c0b3f6821cd
|
||||
Revision: 99
|
||||
Node Kind: directory
|
||||
Schedule: normal
|
||||
Last Changed Author: yann.collet.73@gmail.com
|
||||
Last Changed Rev: 99
|
||||
Last Changed Date: 2013-07-27 19:19:31 +0800 (Sat, 27 Jul 2013)
|
||||
*/
|
||||
|
||||
#pragma once
|
||||
|
||||
#if defined (__cplusplus)
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
|
||||
//**************************************
|
||||
// Compiler Options
|
||||
//**************************************
|
||||
#if defined(_MSC_VER) && !defined(__cplusplus) // Visual Studio
|
||||
# define inline __inline // Visual C is not C99, but supports some kind of inline
|
||||
#endif
|
||||
|
||||
|
||||
//****************************
|
||||
// Simple Functions
|
||||
//****************************
|
||||
|
||||
int LZ4_compress (const char* source, char* dest, int inputSize);
|
||||
int LZ4_decompress_safe (const char* source, char* dest, int inputSize, int maxOutputSize);
|
||||
|
||||
/*
|
||||
LZ4_compress() :
|
||||
Compresses 'inputSize' bytes from 'source' into 'dest'.
|
||||
Destination buffer must be already allocated,
|
||||
and must be sized to handle worst cases situations (input data not compressible)
|
||||
Worst case size evaluation is provided by function LZ4_compressBound()
|
||||
inputSize : Max supported value is ~1.9GB
|
||||
return : the number of bytes written in buffer dest
|
||||
or 0 if the compression fails
|
||||
|
||||
LZ4_decompress_safe() :
|
||||
maxOutputSize : is the size of the destination buffer (which must be already allocated)
|
||||
return : the number of bytes decoded in the destination buffer (necessarily <= maxOutputSize)
|
||||
If the source stream is detected malformed, the function will stop decoding and return a negative result.
|
||||
This function is protected against buffer overflow exploits (never writes outside of output buffer, and never reads outside of input buffer). Therefore, it is protected against malicious data packets
|
||||
*/
|
||||
|
||||
|
||||
//****************************
|
||||
// Advanced Functions
|
||||
//****************************
|
||||
|
||||
static inline int LZ4_compressBound(int isize) { return ((isize) + ((isize)/255) + 16); }
|
||||
#define LZ4_COMPRESSBOUND( isize) ((isize) + ((isize)/255) + 16)
|
||||
|
||||
/*
|
||||
LZ4_compressBound() :
|
||||
Provides the maximum size that LZ4 may output in a "worst case" scenario (input data not compressible)
|
||||
primarily useful for memory allocation of output buffer.
|
||||
inline function is recommended for the general case,
|
||||
macro is also provided when result needs to be evaluated at compilation (such as table size allocation).
|
||||
|
||||
isize : is the input size. Max supported value is ~1.9GB
|
||||
return : maximum output size in a "worst case" scenario
|
||||
note : this function is limited by "int" range (2^31-1)
|
||||
*/
|
||||
|
||||
|
||||
int LZ4_compress_limitedOutput (const char* source, char* dest, int inputSize, int maxOutputSize);
|
||||
|
||||
/*
|
||||
LZ4_compress_limitedOutput() :
|
||||
Compress 'inputSize' bytes from 'source' into an output buffer 'dest' of maximum size 'maxOutputSize'.
|
||||
If it cannot achieve it, compression will stop, and result of the function will be zero.
|
||||
This function never writes outside of provided output buffer.
|
||||
|
||||
inputSize : Max supported value is ~1.9GB
|
||||
maxOutputSize : is the size of the destination buffer (which must be already allocated)
|
||||
return : the number of bytes written in buffer 'dest'
|
||||
or 0 if the compression fails
|
||||
*/
|
||||
|
||||
|
||||
int LZ4_decompress_fast (const char* source, char* dest, int outputSize);
|
||||
|
||||
/*
|
||||
LZ4_decompress_fast() :
|
||||
outputSize : is the original (uncompressed) size
|
||||
return : the number of bytes read from the source buffer (in other words, the compressed size)
|
||||
If the source stream is malformed, the function will stop decoding and return a negative result.
|
||||
note : This function is a bit faster than LZ4_decompress_safe()
|
||||
This function never writes outside of output buffers, and never read before input buffer, but may read beyond input buffer (since it doesn't know its size) in case of malicious data packet.
|
||||
Use this function preferably into a trusted environment (data to decode comes from a trusted source).
|
||||
Destination buffer must be already allocated. Its size must be a minimum of 'outputSize' bytes.
|
||||
*/
|
||||
|
||||
int LZ4_decompress_safe_partial (const char* source, char* dest, int inputSize, int targetOutputSize, int maxOutputSize);
|
||||
|
||||
/*
|
||||
LZ4_decompress_safe_partial() :
|
||||
This function decompress a compressed block of size 'inputSize' at position 'source'
|
||||
into output buffer 'dest' of size 'maxOutputSize'.
|
||||
The function stops decompressing operation as soon as 'targetOutputSize' has been reached,
|
||||
reducing decompression time.
|
||||
return : the number of bytes decoded in the destination buffer (necessarily <= maxOutputSize)
|
||||
Note : this number can be < 'targetOutputSize' should the compressed block to decode be smaller.
|
||||
Always control how many bytes were decoded.
|
||||
If the source stream is malformed, the function will stop decoding and return a negative result.
|
||||
This function never writes outside of output buffer, and never reads outside of input buffer. It is therefore protected against malicious data packets
|
||||
*/
|
||||
|
||||
|
||||
int LZ4_decompress_safe_withPrefix64k (const char* source, char* dest, int inputSize, int maxOutputSize);
|
||||
int LZ4_decompress_fast_withPrefix64k (const char* source, char* dest, int outputSize);
|
||||
|
||||
/*
|
||||
*_withPrefix64k() :
|
||||
These decoding functions work the same as their "normal name" versions,
|
||||
but will potentially use up to 64KB of data in front of 'char* dest'.
|
||||
These functions are used for decoding inter-dependant blocks.
|
||||
*/
|
||||
|
||||
|
||||
//****************************
|
||||
// Obsolete Functions
|
||||
//****************************
|
||||
|
||||
static inline int LZ4_uncompress (const char* source, char* dest, int outputSize) { return LZ4_decompress_fast(source, dest, outputSize); }
|
||||
static inline int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize) { return LZ4_decompress_safe(source, dest, isize, maxOutputSize); }
|
||||
|
||||
/*
|
||||
These functions are deprecated and should no longer be used.
|
||||
They are provided here for compatibility with existing user programs.
|
||||
*/
|
||||
|
||||
|
||||
|
||||
#if defined (__cplusplus)
|
||||
}
|
||||
#endif
|
||||
@ -0,0 +1,258 @@
|
||||
/*
|
||||
LZ4 Encoder - Part of LZ4 compression algorithm
|
||||
Copyright (C) 2011-2013, Yann Collet.
|
||||
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are
|
||||
met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above
|
||||
copyright notice, this list of conditions and the following disclaimer
|
||||
in the documentation and/or other materials provided with the
|
||||
distribution.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
You can contact the author at :
|
||||
- LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html
|
||||
- LZ4 source repository : http://code.google.com/p/lz4/
|
||||
*/
|
||||
|
||||
/* lz4_encoder.h must be included into lz4.c
|
||||
The objective of this file is to create a single LZ4 compression function source
|
||||
which will be instanciated multiple times with minor variations
|
||||
depending on a set of #define.
|
||||
*/
|
||||
|
||||
|
||||
|
||||
//****************************
|
||||
// Check required defines
|
||||
//****************************
|
||||
|
||||
#ifndef FUNCTION_NAME
|
||||
# error "FUNTION_NAME is not defined"
|
||||
#endif
|
||||
|
||||
|
||||
//****************************
|
||||
// Local definitions
|
||||
//****************************
|
||||
|
||||
#ifdef COMPRESS_64K
|
||||
# define HASHLOG (MEMORY_USAGE-1)
|
||||
# define CURRENT_H_TYPE U16
|
||||
# define CURRENTBASE(base) const BYTE* const base = ip
|
||||
#else
|
||||
# define HASHLOG (MEMORY_USAGE-2)
|
||||
# define CURRENT_H_TYPE HTYPE
|
||||
# define CURRENTBASE(base) INITBASE(base)
|
||||
#endif
|
||||
|
||||
#define HASHTABLE_NBCELLS (1U<<HASHLOG)
|
||||
#define LZ4_HASH(i) (((i) * 2654435761U) >> ((MINMATCH*8)-HASHLOG))
|
||||
#define LZ4_HASHVALUE(p) LZ4_HASH(A32(p))
|
||||
|
||||
|
||||
|
||||
//****************************
|
||||
// Function code
|
||||
//****************************
|
||||
|
||||
int FUNCTION_NAME(
|
||||
#ifdef USE_HEAPMEMORY
|
||||
void* ctx,
|
||||
#endif
|
||||
const char* source,
|
||||
char* dest,
|
||||
int inputSize
|
||||
#ifdef LIMITED_OUTPUT
|
||||
,int maxOutputSize
|
||||
#endif
|
||||
)
|
||||
{
|
||||
#ifdef USE_HEAPMEMORY
|
||||
CURRENT_H_TYPE* HashTable = (CURRENT_H_TYPE*)ctx;
|
||||
#else
|
||||
CURRENT_H_TYPE HashTable[HASHTABLE_NBCELLS] = {0};
|
||||
#endif
|
||||
|
||||
const BYTE* ip = (BYTE*) source;
|
||||
CURRENTBASE(base);
|
||||
const BYTE* anchor = ip;
|
||||
const BYTE* const iend = ip + inputSize;
|
||||
const BYTE* const mflimit = iend - MFLIMIT;
|
||||
#define matchlimit (iend - LASTLITERALS)
|
||||
|
||||
BYTE* op = (BYTE*) dest;
|
||||
#ifdef LIMITED_OUTPUT
|
||||
BYTE* const oend = op + maxOutputSize;
|
||||
#endif
|
||||
|
||||
int length;
|
||||
const int skipStrength = SKIPSTRENGTH;
|
||||
U32 forwardH;
|
||||
|
||||
|
||||
// Init
|
||||
if (inputSize<MINLENGTH) goto _last_literals;
|
||||
#ifdef COMPRESS_64K
|
||||
if (inputSize>=LZ4_64KLIMIT) return 0; // Size too large (not within 64K limit)
|
||||
#endif
|
||||
#ifdef USE_HEAPMEMORY
|
||||
memset((void*)HashTable, 0, HASHTABLESIZE);
|
||||
#endif
|
||||
|
||||
// First Byte
|
||||
HashTable[LZ4_HASHVALUE(ip)] = (CURRENT_H_TYPE)(ip - base);
|
||||
ip++; forwardH = LZ4_HASHVALUE(ip);
|
||||
|
||||
// Main Loop
|
||||
for ( ; ; )
|
||||
{
|
||||
int findMatchAttempts = (1U << skipStrength) + 3;
|
||||
const BYTE* forwardIp = ip;
|
||||
const BYTE* ref;
|
||||
BYTE* token;
|
||||
|
||||
// Find a match
|
||||
do {
|
||||
U32 h = forwardH;
|
||||
int step = findMatchAttempts++ >> skipStrength;
|
||||
ip = forwardIp;
|
||||
forwardIp = ip + step;
|
||||
|
||||
if unlikely(forwardIp > mflimit) { goto _last_literals; }
|
||||
|
||||
forwardH = LZ4_HASHVALUE(forwardIp);
|
||||
ref = base + HashTable[h];
|
||||
HashTable[h] = (CURRENT_H_TYPE)(ip - base);
|
||||
|
||||
} while ((ref < ip - MAX_DISTANCE) || (A32(ref) != A32(ip)));
|
||||
|
||||
// Catch up
|
||||
while ((ip>anchor) && (ref>(BYTE*)source) && unlikely(ip[-1]==ref[-1])) { ip--; ref--; }
|
||||
|
||||
// Encode Literal length
|
||||
length = (int)(ip - anchor);
|
||||
token = op++;
|
||||
#ifdef LIMITED_OUTPUT
|
||||
if unlikely(op + length + (2 + 1 + LASTLITERALS) + (length>>8) > oend) return 0; // Check output limit
|
||||
#endif
|
||||
if (length>=(int)RUN_MASK)
|
||||
{
|
||||
int len = length-RUN_MASK;
|
||||
*token=(RUN_MASK<<ML_BITS);
|
||||
for(; len >= 255 ; len-=255) *op++ = 255;
|
||||
*op++ = (BYTE)len;
|
||||
}
|
||||
else *token = (BYTE)(length<<ML_BITS);
|
||||
|
||||
// Copy Literals
|
||||
LZ4_BLINDCOPY(anchor, op, length);
|
||||
|
||||
_next_match:
|
||||
// Encode Offset
|
||||
LZ4_WRITE_LITTLEENDIAN_16(op,(U16)(ip-ref));
|
||||
|
||||
// Start Counting
|
||||
ip+=MINMATCH; ref+=MINMATCH; // MinMatch already verified
|
||||
anchor = ip;
|
||||
while likely(ip<matchlimit-(STEPSIZE-1))
|
||||
{
|
||||
size_t diff = AARCH(ref) ^ AARCH(ip);
|
||||
if (!diff) { ip+=STEPSIZE; ref+=STEPSIZE; continue; }
|
||||
ip += LZ4_NbCommonBytes(diff);
|
||||
goto _endCount;
|
||||
}
|
||||
if (LZ4_ARCH64) if ((ip<(matchlimit-3)) && (A32(ref) == A32(ip))) { ip+=4; ref+=4; }
|
||||
if ((ip<(matchlimit-1)) && (A16(ref) == A16(ip))) { ip+=2; ref+=2; }
|
||||
if ((ip<matchlimit) && (*ref == *ip)) ip++;
|
||||
_endCount:
|
||||
|
||||
// Encode MatchLength
|
||||
length = (int)(ip - anchor);
|
||||
#ifdef LIMITED_OUTPUT
|
||||
if unlikely(op + (1 + LASTLITERALS) + (length>>8) > oend) return 0; // Check output limit
|
||||
#endif
|
||||
if (length>=(int)ML_MASK)
|
||||
{
|
||||
*token += ML_MASK;
|
||||
length -= ML_MASK;
|
||||
for (; length > 509 ; length-=510) { *op++ = 255; *op++ = 255; }
|
||||
if (length >= 255) { length-=255; *op++ = 255; }
|
||||
*op++ = (BYTE)length;
|
||||
}
|
||||
else *token += (BYTE)(length);
|
||||
|
||||
// Test end of chunk
|
||||
if (ip > mflimit) { anchor = ip; break; }
|
||||
|
||||
// Fill table
|
||||
HashTable[LZ4_HASHVALUE(ip-2)] = (CURRENT_H_TYPE)(ip - 2 - base);
|
||||
|
||||
// Test next position
|
||||
ref = base + HashTable[LZ4_HASHVALUE(ip)];
|
||||
HashTable[LZ4_HASHVALUE(ip)] = (CURRENT_H_TYPE)(ip - base);
|
||||
if ((ref >= ip - MAX_DISTANCE) && (A32(ref) == A32(ip))) { token = op++; *token=0; goto _next_match; }
|
||||
|
||||
// Prepare next loop
|
||||
anchor = ip++;
|
||||
forwardH = LZ4_HASHVALUE(ip);
|
||||
}
|
||||
|
||||
_last_literals:
|
||||
// Encode Last Literals
|
||||
{
|
||||
int lastRun = (int)(iend - anchor);
|
||||
#ifdef LIMITED_OUTPUT
|
||||
if (((char*)op - dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize) return 0; // Check output limit
|
||||
#endif
|
||||
if (lastRun>=(int)RUN_MASK) { *op++=(RUN_MASK<<ML_BITS); lastRun-=RUN_MASK; for(; lastRun >= 255 ; lastRun-=255) *op++ = 255; *op++ = (BYTE) lastRun; }
|
||||
else *op++ = (BYTE)(lastRun<<ML_BITS);
|
||||
memcpy(op, anchor, iend - anchor);
|
||||
op += iend-anchor;
|
||||
}
|
||||
|
||||
// End
|
||||
return (int) (((char*)op)-dest);
|
||||
}
|
||||
|
||||
|
||||
|
||||
//****************************
|
||||
// Clean defines
|
||||
//****************************
|
||||
|
||||
// Required defines
|
||||
#undef FUNCTION_NAME
|
||||
|
||||
// Locally Generated
|
||||
#undef HASHLOG
|
||||
#undef HASHTABLE_NBCELLS
|
||||
#undef LZ4_HASH
|
||||
#undef LZ4_HASHVALUE
|
||||
#undef CURRENT_H_TYPE
|
||||
#undef CURRENTBASE
|
||||
|
||||
// Optional defines
|
||||
#ifdef LIMITED_OUTPUT
|
||||
#undef LIMITED_OUTPUT
|
||||
#endif
|
||||
|
||||
#ifdef USE_HEAPMEMORY
|
||||
#undef USE_HEAPMEMORY
|
||||
#endif
|
||||
@ -0,0 +1,584 @@
|
||||
/*
|
||||
LZ4 HC - High Compression Mode of LZ4
|
||||
Copyright (C) 2011-2013, Yann Collet.
|
||||
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are
|
||||
met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above
|
||||
copyright notice, this list of conditions and the following disclaimer
|
||||
in the documentation and/or other materials provided with the
|
||||
distribution.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
You can contact the author at :
|
||||
- LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html
|
||||
- LZ4 source repository : http://code.google.com/p/lz4/
|
||||
*/
|
||||
|
||||
/*
|
||||
Note : this source file requires "lz4hc_encoder.h"
|
||||
*/
|
||||
|
||||
|
||||
//**************************************
|
||||
// Memory routines
|
||||
//**************************************
|
||||
#include <stdlib.h> // calloc, free
|
||||
#define ALLOCATOR(s) calloc(1,s)
|
||||
#define FREEMEM free
|
||||
#include <string.h> // memset, memcpy
|
||||
#define MEM_INIT memset
|
||||
|
||||
|
||||
//**************************************
|
||||
// CPU Feature Detection
|
||||
//**************************************
|
||||
// 32 or 64 bits ?
|
||||
#if (defined(__x86_64__) || defined(_M_X64) || defined(_WIN64) \
|
||||
|| defined(__powerpc64__) || defined(__ppc64__) || defined(__PPC64__) \
|
||||
|| defined(__64BIT__) || defined(_LP64) || defined(__LP64__) \
|
||||
|| defined(__ia64) || defined(__itanium__) || defined(_M_IA64) ) // Detects 64 bits mode
|
||||
# define LZ4_ARCH64 1
|
||||
#else
|
||||
# define LZ4_ARCH64 0
|
||||
#endif
|
||||
|
||||
// Little Endian or Big Endian ?
|
||||
// Overwrite the #define below if you know your architecture endianess
|
||||
#if defined (__GLIBC__)
|
||||
# include <endian.h>
|
||||
# if (__BYTE_ORDER == __BIG_ENDIAN)
|
||||
# define LZ4_BIG_ENDIAN 1
|
||||
# endif
|
||||
#elif (defined(__BIG_ENDIAN__) || defined(__BIG_ENDIAN) || defined(_BIG_ENDIAN)) && !(defined(__LITTLE_ENDIAN__) || defined(__LITTLE_ENDIAN) || defined(_LITTLE_ENDIAN))
|
||||
# define LZ4_BIG_ENDIAN 1
|
||||
#elif defined(__sparc) || defined(__sparc__) \
|
||||
|| defined(__powerpc__) || defined(__ppc__) || defined(__PPC__) \
|
||||
|| defined(__hpux) || defined(__hppa) \
|
||||
|| defined(_MIPSEB) || defined(__s390__)
|
||||
# define LZ4_BIG_ENDIAN 1
|
||||
#else
|
||||
// Little Endian assumed. PDP Endian and other very rare endian format are unsupported.
|
||||
#endif
|
||||
|
||||
// Unaligned memory access is automatically enabled for "common" CPU, such as x86.
|
||||
// For others CPU, the compiler will be more cautious, and insert extra code to ensure aligned access is respected
|
||||
// If you know your target CPU supports unaligned memory access, you want to force this option manually to improve performance
|
||||
#if defined(__ARM_FEATURE_UNALIGNED)
|
||||
# define LZ4_FORCE_UNALIGNED_ACCESS 1
|
||||
#endif
|
||||
|
||||
// Define this parameter if your target system or compiler does not support hardware bit count
|
||||
#if defined(_MSC_VER) && defined(_WIN32_WCE) // Visual Studio for Windows CE does not support Hardware bit count
|
||||
# define LZ4_FORCE_SW_BITCOUNT
|
||||
#endif
|
||||
|
||||
|
||||
//**************************************
|
||||
// Compiler Options
|
||||
//**************************************
|
||||
#if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L // C99
|
||||
/* "restrict" is a known keyword */
|
||||
#else
|
||||
# define restrict // Disable restrict
|
||||
#endif
|
||||
|
||||
#ifdef _MSC_VER // Visual Studio
|
||||
# define forceinline static __forceinline
|
||||
# include <intrin.h> // For Visual 2005
|
||||
# if LZ4_ARCH64 // 64-bits
|
||||
# pragma intrinsic(_BitScanForward64) // For Visual 2005
|
||||
# pragma intrinsic(_BitScanReverse64) // For Visual 2005
|
||||
# else // 32-bits
|
||||
# pragma intrinsic(_BitScanForward) // For Visual 2005
|
||||
# pragma intrinsic(_BitScanReverse) // For Visual 2005
|
||||
# endif
|
||||
# pragma warning(disable : 4127) // disable: C4127: conditional expression is constant
|
||||
# pragma warning(disable : 4701) // disable: C4701: potentially uninitialized local variable used
|
||||
#else
|
||||
# ifdef __GNUC__
|
||||
# define forceinline static inline __attribute__((always_inline))
|
||||
# else
|
||||
# define forceinline static inline
|
||||
# endif
|
||||
#endif
|
||||
|
||||
#ifdef _MSC_VER // Visual Studio
|
||||
# define lz4_bswap16(x) _byteswap_ushort(x)
|
||||
#else
|
||||
# define lz4_bswap16(x) ((unsigned short int) ((((x) >> 8) & 0xffu) | (((x) & 0xffu) << 8)))
|
||||
#endif
|
||||
|
||||
|
||||
//**************************************
|
||||
// Includes
|
||||
//**************************************
|
||||
#include "lz4hc.h"
|
||||
#include "lz4.h"
|
||||
|
||||
|
||||
//**************************************
|
||||
// Basic Types
|
||||
//**************************************
|
||||
#if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L // C99
|
||||
# include <stdint.h>
|
||||
typedef uint8_t BYTE;
|
||||
typedef uint16_t U16;
|
||||
typedef uint32_t U32;
|
||||
typedef int32_t S32;
|
||||
typedef uint64_t U64;
|
||||
#else
|
||||
typedef unsigned char BYTE;
|
||||
typedef unsigned short U16;
|
||||
typedef unsigned int U32;
|
||||
typedef signed int S32;
|
||||
typedef unsigned long long U64;
|
||||
#endif
|
||||
|
||||
#if defined(__GNUC__) && !defined(LZ4_FORCE_UNALIGNED_ACCESS)
|
||||
# define _PACKED __attribute__ ((packed))
|
||||
#else
|
||||
# define _PACKED
|
||||
#endif
|
||||
|
||||
#if !defined(LZ4_FORCE_UNALIGNED_ACCESS) && !defined(__GNUC__)
|
||||
# ifdef __IBMC__
|
||||
# pragma pack(1)
|
||||
# else
|
||||
# pragma pack(push, 1)
|
||||
# endif
|
||||
#endif
|
||||
|
||||
typedef struct _U16_S { U16 v; } _PACKED U16_S;
|
||||
typedef struct _U32_S { U32 v; } _PACKED U32_S;
|
||||
typedef struct _U64_S { U64 v; } _PACKED U64_S;
|
||||
|
||||
#if !defined(LZ4_FORCE_UNALIGNED_ACCESS) && !defined(__GNUC__)
|
||||
# pragma pack(pop)
|
||||
#endif
|
||||
|
||||
#define A64(x) (((U64_S *)(x))->v)
|
||||
#define A32(x) (((U32_S *)(x))->v)
|
||||
#define A16(x) (((U16_S *)(x))->v)
|
||||
|
||||
|
||||
//**************************************
|
||||
// Constants
|
||||
//**************************************
|
||||
#define MINMATCH 4
|
||||
|
||||
#define DICTIONARY_LOGSIZE 16
|
||||
#define MAXD (1<<DICTIONARY_LOGSIZE)
|
||||
#define MAXD_MASK ((U32)(MAXD - 1))
|
||||
#define MAX_DISTANCE (MAXD - 1)
|
||||
|
||||
#define HASH_LOG (DICTIONARY_LOGSIZE-1)
|
||||
#define HASHTABLESIZE (1 << HASH_LOG)
|
||||
#define HASH_MASK (HASHTABLESIZE - 1)
|
||||
|
||||
#define MAX_NB_ATTEMPTS 256
|
||||
|
||||
#define ML_BITS 4
|
||||
#define ML_MASK (size_t)((1U<<ML_BITS)-1)
|
||||
#define RUN_BITS (8-ML_BITS)
|
||||
#define RUN_MASK ((1U<<RUN_BITS)-1)
|
||||
|
||||
#define COPYLENGTH 8
|
||||
#define LASTLITERALS 5
|
||||
#define MFLIMIT (COPYLENGTH+MINMATCH)
|
||||
#define MINLENGTH (MFLIMIT+1)
|
||||
#define OPTIMAL_ML (int)((ML_MASK-1)+MINMATCH)
|
||||
|
||||
#define KB *(1U<<10)
|
||||
#define MB *(1U<<20)
|
||||
#define GB *(1U<<30)
|
||||
|
||||
|
||||
//**************************************
|
||||
// Architecture-specific macros
|
||||
//**************************************
|
||||
#if LZ4_ARCH64 // 64-bit
|
||||
# define STEPSIZE 8
|
||||
# define LZ4_COPYSTEP(s,d) A64(d) = A64(s); d+=8; s+=8;
|
||||
# define LZ4_COPYPACKET(s,d) LZ4_COPYSTEP(s,d)
|
||||
# define UARCH U64
|
||||
# define AARCH A64
|
||||
# define HTYPE U32
|
||||
# define INITBASE(b,s) const BYTE* const b = s
|
||||
#else // 32-bit
|
||||
# define STEPSIZE 4
|
||||
# define LZ4_COPYSTEP(s,d) A32(d) = A32(s); d+=4; s+=4;
|
||||
# define LZ4_COPYPACKET(s,d) LZ4_COPYSTEP(s,d); LZ4_COPYSTEP(s,d);
|
||||
# define UARCH U32
|
||||
# define AARCH A32
|
||||
//# define HTYPE const BYTE*
|
||||
//# define INITBASE(b,s) const int b = 0
|
||||
# define HTYPE U32
|
||||
# define INITBASE(b,s) const BYTE* const b = s
|
||||
#endif
|
||||
|
||||
#if defined(LZ4_BIG_ENDIAN)
|
||||
# define LZ4_READ_LITTLEENDIAN_16(d,s,p) { U16 v = A16(p); v = lz4_bswap16(v); d = (s) - v; }
|
||||
# define LZ4_WRITE_LITTLEENDIAN_16(p,i) { U16 v = (U16)(i); v = lz4_bswap16(v); A16(p) = v; p+=2; }
|
||||
#else // Little Endian
|
||||
# define LZ4_READ_LITTLEENDIAN_16(d,s,p) { d = (s) - A16(p); }
|
||||
# define LZ4_WRITE_LITTLEENDIAN_16(p,v) { A16(p) = v; p+=2; }
|
||||
#endif
|
||||
|
||||
|
||||
//************************************************************
|
||||
// Local Types
|
||||
//************************************************************
|
||||
typedef struct
|
||||
{
|
||||
const BYTE* inputBuffer;
|
||||
const BYTE* base;
|
||||
const BYTE* end;
|
||||
HTYPE hashTable[HASHTABLESIZE];
|
||||
U16 chainTable[MAXD];
|
||||
const BYTE* nextToUpdate;
|
||||
} LZ4HC_Data_Structure;
|
||||
|
||||
|
||||
//**************************************
|
||||
// Macros
|
||||
//**************************************
|
||||
#define LZ4_WILDCOPY(s,d,e) do { LZ4_COPYPACKET(s,d) } while (d<e);
|
||||
#define LZ4_BLINDCOPY(s,d,l) { BYTE* e=d+l; LZ4_WILDCOPY(s,d,e); d=e; }
|
||||
#define HASH_FUNCTION(i) (((i) * 2654435761U) >> ((MINMATCH*8)-HASH_LOG))
|
||||
#define HASH_VALUE(p) HASH_FUNCTION(A32(p))
|
||||
#define HASH_POINTER(p) (HashTable[HASH_VALUE(p)] + base)
|
||||
#define DELTANEXT(p) chainTable[(size_t)(p) & MAXD_MASK]
|
||||
#define GETNEXT(p) ((p) - (size_t)DELTANEXT(p))
|
||||
|
||||
|
||||
//**************************************
|
||||
// Private functions
|
||||
//**************************************
|
||||
#if LZ4_ARCH64
|
||||
|
||||
forceinline int LZ4_NbCommonBytes (register U64 val)
|
||||
{
|
||||
#if defined(LZ4_BIG_ENDIAN)
|
||||
# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
|
||||
unsigned long r = 0;
|
||||
_BitScanReverse64( &r, val );
|
||||
return (int)(r>>3);
|
||||
# elif defined(__GNUC__) && ((__GNUC__ * 100 + __GNUC_MINOR__) >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)
|
||||
return (__builtin_clzll(val) >> 3);
|
||||
# else
|
||||
int r;
|
||||
if (!(val>>32)) { r=4; } else { r=0; val>>=32; }
|
||||
if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; }
|
||||
r += (!val);
|
||||
return r;
|
||||
# endif
|
||||
#else
|
||||
# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
|
||||
unsigned long r = 0;
|
||||
_BitScanForward64( &r, val );
|
||||
return (int)(r>>3);
|
||||
# elif defined(__GNUC__) && ((__GNUC__ * 100 + __GNUC_MINOR__) >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)
|
||||
return (__builtin_ctzll(val) >> 3);
|
||||
# else
|
||||
static const int DeBruijnBytePos[64] = { 0, 0, 0, 0, 0, 1, 1, 2, 0, 3, 1, 3, 1, 4, 2, 7, 0, 2, 3, 6, 1, 5, 3, 5, 1, 3, 4, 4, 2, 5, 6, 7, 7, 0, 1, 2, 3, 3, 4, 6, 2, 6, 5, 5, 3, 4, 5, 6, 7, 1, 2, 4, 6, 4, 4, 5, 7, 2, 6, 5, 7, 6, 7, 7 };
|
||||
return DeBruijnBytePos[((U64)((val & -val) * 0x0218A392CDABBD3F)) >> 58];
|
||||
# endif
|
||||
#endif
|
||||
}
|
||||
|
||||
#else
|
||||
|
||||
forceinline int LZ4_NbCommonBytes (register U32 val)
|
||||
{
|
||||
#if defined(LZ4_BIG_ENDIAN)
|
||||
# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
|
||||
unsigned long r;
|
||||
_BitScanReverse( &r, val );
|
||||
return (int)(r>>3);
|
||||
# elif defined(__GNUC__) && ((__GNUC__ * 100 + __GNUC_MINOR__) >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)
|
||||
return (__builtin_clz(val) >> 3);
|
||||
# else
|
||||
int r;
|
||||
if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; }
|
||||
r += (!val);
|
||||
return r;
|
||||
# endif
|
||||
#else
|
||||
# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
|
||||
unsigned long r;
|
||||
_BitScanForward( &r, val );
|
||||
return (int)(r>>3);
|
||||
# elif defined(__GNUC__) && ((__GNUC__ * 100 + __GNUC_MINOR__) >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)
|
||||
return (__builtin_ctz(val) >> 3);
|
||||
# else
|
||||
static const int DeBruijnBytePos[32] = { 0, 0, 3, 0, 3, 1, 3, 0, 3, 2, 2, 1, 3, 2, 0, 1, 3, 3, 1, 2, 2, 2, 2, 0, 3, 1, 2, 0, 1, 0, 1, 1 };
|
||||
return DeBruijnBytePos[((U32)((val & -(S32)val) * 0x077CB531U)) >> 27];
|
||||
# endif
|
||||
#endif
|
||||
}
|
||||
|
||||
#endif
|
||||
|
||||
|
||||
forceinline int LZ4_InitHC (LZ4HC_Data_Structure* hc4, const BYTE* base)
|
||||
{
|
||||
MEM_INIT((void*)hc4->hashTable, 0, sizeof(hc4->hashTable));
|
||||
MEM_INIT(hc4->chainTable, 0xFF, sizeof(hc4->chainTable));
|
||||
hc4->nextToUpdate = base + 1;
|
||||
hc4->base = base;
|
||||
hc4->inputBuffer = base;
|
||||
hc4->end = base;
|
||||
return 1;
|
||||
}
|
||||
|
||||
|
||||
void* LZ4_createHC (const char* slidingInputBuffer)
|
||||
{
|
||||
void* hc4 = ALLOCATOR(sizeof(LZ4HC_Data_Structure));
|
||||
LZ4_InitHC ((LZ4HC_Data_Structure*)hc4, (const BYTE*)slidingInputBuffer);
|
||||
return hc4;
|
||||
}
|
||||
|
||||
|
||||
int LZ4_freeHC (void* LZ4HC_Data)
|
||||
{
|
||||
FREEMEM(LZ4HC_Data);
|
||||
return (0);
|
||||
}
|
||||
|
||||
|
||||
// Update chains up to ip (excluded)
|
||||
forceinline void LZ4HC_Insert (LZ4HC_Data_Structure* hc4, const BYTE* ip)
|
||||
{
|
||||
U16* chainTable = hc4->chainTable;
|
||||
HTYPE* HashTable = hc4->hashTable;
|
||||
INITBASE(base,hc4->base);
|
||||
|
||||
while(hc4->nextToUpdate < ip)
|
||||
{
|
||||
const BYTE* const p = hc4->nextToUpdate;
|
||||
size_t delta = (p) - HASH_POINTER(p);
|
||||
if (delta>MAX_DISTANCE) delta = MAX_DISTANCE;
|
||||
DELTANEXT(p) = (U16)delta;
|
||||
HashTable[HASH_VALUE(p)] = (HTYPE)((p) - base);
|
||||
hc4->nextToUpdate++;
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
char* LZ4_slideInputBufferHC(void* LZ4HC_Data)
|
||||
{
|
||||
LZ4HC_Data_Structure* hc4 = (LZ4HC_Data_Structure*)LZ4HC_Data;
|
||||
U32 distance = (U32)(hc4->end - hc4->inputBuffer) - 64 KB;
|
||||
distance = (distance >> 16) << 16; // Must be a multiple of 64 KB
|
||||
LZ4HC_Insert(hc4, hc4->end - MINMATCH);
|
||||
memcpy((void*)(hc4->end - 64 KB - distance), (const void*)(hc4->end - 64 KB), 64 KB);
|
||||
hc4->nextToUpdate -= distance;
|
||||
hc4->base -= distance;
|
||||
if ((U32)(hc4->inputBuffer - hc4->base) > 1 GB + 64 KB) // Avoid overflow
|
||||
{
|
||||
int i;
|
||||
hc4->base += 1 GB;
|
||||
for (i=0; i<HASHTABLESIZE; i++) hc4->hashTable[i] -= 1 GB;
|
||||
}
|
||||
hc4->end -= distance;
|
||||
return (char*)(hc4->end);
|
||||
}
|
||||
|
||||
|
||||
forceinline size_t LZ4HC_CommonLength (const BYTE* p1, const BYTE* p2, const BYTE* const matchlimit)
|
||||
{
|
||||
const BYTE* p1t = p1;
|
||||
|
||||
while (p1t<matchlimit-(STEPSIZE-1))
|
||||
{
|
||||
UARCH diff = AARCH(p2) ^ AARCH(p1t);
|
||||
if (!diff) { p1t+=STEPSIZE; p2+=STEPSIZE; continue; }
|
||||
p1t += LZ4_NbCommonBytes(diff);
|
||||
return (p1t - p1);
|
||||
}
|
||||
if (LZ4_ARCH64) if ((p1t<(matchlimit-3)) && (A32(p2) == A32(p1t))) { p1t+=4; p2+=4; }
|
||||
if ((p1t<(matchlimit-1)) && (A16(p2) == A16(p1t))) { p1t+=2; p2+=2; }
|
||||
if ((p1t<matchlimit) && (*p2 == *p1t)) p1t++;
|
||||
return (p1t - p1);
|
||||
}
|
||||
|
||||
|
||||
forceinline int LZ4HC_InsertAndFindBestMatch (LZ4HC_Data_Structure* hc4, const BYTE* ip, const BYTE* const matchlimit, const BYTE** matchpos)
|
||||
{
|
||||
U16* const chainTable = hc4->chainTable;
|
||||
HTYPE* const HashTable = hc4->hashTable;
|
||||
const BYTE* ref;
|
||||
INITBASE(base,hc4->base);
|
||||
int nbAttempts=MAX_NB_ATTEMPTS;
|
||||
size_t repl=0, ml=0;
|
||||
U16 delta=0; // useless assignment, to remove an uninitialization warning
|
||||
|
||||
// HC4 match finder
|
||||
LZ4HC_Insert(hc4, ip);
|
||||
ref = HASH_POINTER(ip);
|
||||
|
||||
#define REPEAT_OPTIMIZATION
|
||||
#ifdef REPEAT_OPTIMIZATION
|
||||
// Detect repetitive sequences of length <= 4
|
||||
if ((U32)(ip-ref) <= 4) // potential repetition
|
||||
{
|
||||
if (A32(ref) == A32(ip)) // confirmed
|
||||
{
|
||||
delta = (U16)(ip-ref);
|
||||
repl = ml = LZ4HC_CommonLength(ip+MINMATCH, ref+MINMATCH, matchlimit) + MINMATCH;
|
||||
*matchpos = ref;
|
||||
}
|
||||
ref = GETNEXT(ref);
|
||||
}
|
||||
#endif
|
||||
|
||||
while (((U32)(ip-ref) <= MAX_DISTANCE) && (nbAttempts))
|
||||
{
|
||||
nbAttempts--;
|
||||
if (*(ref+ml) == *(ip+ml))
|
||||
if (A32(ref) == A32(ip))
|
||||
{
|
||||
size_t mlt = LZ4HC_CommonLength(ip+MINMATCH, ref+MINMATCH, matchlimit) + MINMATCH;
|
||||
if (mlt > ml) { ml = mlt; *matchpos = ref; }
|
||||
}
|
||||
ref = GETNEXT(ref);
|
||||
}
|
||||
|
||||
#ifdef REPEAT_OPTIMIZATION
|
||||
// Complete table
|
||||
if (repl)
|
||||
{
|
||||
const BYTE* ptr = ip;
|
||||
const BYTE* end;
|
||||
|
||||
end = ip + repl - (MINMATCH-1);
|
||||
while(ptr < end-delta)
|
||||
{
|
||||
DELTANEXT(ptr) = delta; // Pre-Load
|
||||
ptr++;
|
||||
}
|
||||
do
|
||||
{
|
||||
DELTANEXT(ptr) = delta;
|
||||
HashTable[HASH_VALUE(ptr)] = (HTYPE)((ptr) - base); // Head of chain
|
||||
ptr++;
|
||||
} while(ptr < end);
|
||||
hc4->nextToUpdate = end;
|
||||
}
|
||||
#endif
|
||||
|
||||
return (int)ml;
|
||||
}
|
||||
|
||||
|
||||
forceinline int LZ4HC_InsertAndGetWiderMatch (LZ4HC_Data_Structure* hc4, const BYTE* ip, const BYTE* startLimit, const BYTE* matchlimit, int longest, const BYTE** matchpos, const BYTE** startpos)
|
||||
{
|
||||
U16* const chainTable = hc4->chainTable;
|
||||
HTYPE* const HashTable = hc4->hashTable;
|
||||
INITBASE(base,hc4->base);
|
||||
const BYTE* ref;
|
||||
int nbAttempts = MAX_NB_ATTEMPTS;
|
||||
int delta = (int)(ip-startLimit);
|
||||
|
||||
// First Match
|
||||
LZ4HC_Insert(hc4, ip);
|
||||
ref = HASH_POINTER(ip);
|
||||
|
||||
while (((U32)(ip-ref) <= MAX_DISTANCE) && (nbAttempts))
|
||||
{
|
||||
nbAttempts--;
|
||||
if (*(startLimit + longest) == *(ref - delta + longest))
|
||||
if (A32(ref) == A32(ip))
|
||||
{
|
||||
#if 1
|
||||
const BYTE* reft = ref+MINMATCH;
|
||||
const BYTE* ipt = ip+MINMATCH;
|
||||
const BYTE* startt = ip;
|
||||
|
||||
while (ipt<matchlimit-(STEPSIZE-1))
|
||||
{
|
||||
UARCH diff = AARCH(reft) ^ AARCH(ipt);
|
||||
if (!diff) { ipt+=STEPSIZE; reft+=STEPSIZE; continue; }
|
||||
ipt += LZ4_NbCommonBytes(diff);
|
||||
goto _endCount;
|
||||
}
|
||||
if (LZ4_ARCH64) if ((ipt<(matchlimit-3)) && (A32(reft) == A32(ipt))) { ipt+=4; reft+=4; }
|
||||
if ((ipt<(matchlimit-1)) && (A16(reft) == A16(ipt))) { ipt+=2; reft+=2; }
|
||||
if ((ipt<matchlimit) && (*reft == *ipt)) ipt++;
|
||||
_endCount:
|
||||
reft = ref;
|
||||
#else
|
||||
// Easier for code maintenance, but unfortunately slower too
|
||||
const BYTE* startt = ip;
|
||||
const BYTE* reft = ref;
|
||||
const BYTE* ipt = ip + MINMATCH + LZ4HC_CommonLength(ip+MINMATCH, ref+MINMATCH, matchlimit);
|
||||
#endif
|
||||
|
||||
while ((startt>startLimit) && (reft > hc4->inputBuffer) && (startt[-1] == reft[-1])) {startt--; reft--;}
|
||||
|
||||
if ((ipt-startt) > longest)
|
||||
{
|
||||
longest = (int)(ipt-startt);
|
||||
*matchpos = reft;
|
||||
*startpos = startt;
|
||||
}
|
||||
}
|
||||
ref = GETNEXT(ref);
|
||||
}
|
||||
|
||||
return longest;
|
||||
}
|
||||
|
||||
|
||||
|
||||
//**************************************
|
||||
// Compression functions
|
||||
//**************************************
|
||||
|
||||
/*
|
||||
int LZ4_compressHC(
|
||||
const char* source,
|
||||
char* dest,
|
||||
int inputSize)
|
||||
|
||||
Compress 'inputSize' bytes from 'source' into an output buffer 'dest'.
|
||||
Destination buffer must be already allocated, and sized at a minimum of LZ4_compressBound(inputSize).
|
||||
return : the number of bytes written in buffer 'dest'
|
||||
*/
|
||||
#define FUNCTION_NAME LZ4_compressHC
|
||||
#include "lz4hc_encoder.h"
|
||||
|
||||
|
||||
/*
|
||||
int LZ4_compressHC_limitedOutput(
|
||||
const char* source,
|
||||
char* dest,
|
||||
int inputSize,
|
||||
int maxOutputSize)
|
||||
|
||||
Compress 'inputSize' bytes from 'source' into an output buffer 'dest' of maximum size 'maxOutputSize'.
|
||||
If it cannot achieve it, compression will stop, and result of the function will be zero.
|
||||
return : the number of bytes written in buffer 'dest', or 0 if the compression fails
|
||||
*/
|
||||
#define FUNCTION_NAME LZ4_compressHC_limitedOutput
|
||||
#define LIMITED_OUTPUT
|
||||
#include "lz4hc_encoder.h"
|
||||
|
||||
@ -0,0 +1,111 @@
|
||||
/*
|
||||
LZ4 HC - High Compression Mode of LZ4
|
||||
Header File
|
||||
Copyright (C) 2011-2013, Yann Collet.
|
||||
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are
|
||||
met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above
|
||||
copyright notice, this list of conditions and the following disclaimer
|
||||
in the documentation and/or other materials provided with the
|
||||
distribution.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
You can contact the author at :
|
||||
- LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html
|
||||
- LZ4 source repository : http://code.google.com/p/lz4/
|
||||
*/
|
||||
#pragma once
|
||||
|
||||
|
||||
#if defined (__cplusplus)
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
|
||||
int LZ4_compressHC (const char* source, char* dest, int inputSize);
|
||||
/*
|
||||
LZ4_compressHC :
|
||||
return : the number of bytes in compressed buffer dest
|
||||
or 0 if compression fails.
|
||||
note : destination buffer must be already allocated.
|
||||
To avoid any problem, size it to handle worst cases situations (input data not compressible)
|
||||
Worst case size evaluation is provided by function LZ4_compressBound() (see "lz4.h")
|
||||
*/
|
||||
|
||||
int LZ4_compressHC_limitedOutput (const char* source, char* dest, int inputSize, int maxOutputSize);
|
||||
/*
|
||||
LZ4_compress_limitedOutput() :
|
||||
Compress 'inputSize' bytes from 'source' into an output buffer 'dest' of maximum size 'maxOutputSize'.
|
||||
If it cannot achieve it, compression will stop, and result of the function will be zero.
|
||||
This function never writes outside of provided output buffer.
|
||||
|
||||
inputSize : Max supported value is 1 GB
|
||||
maxOutputSize : is maximum allowed size into the destination buffer (which must be already allocated)
|
||||
return : the number of output bytes written in buffer 'dest'
|
||||
or 0 if compression fails.
|
||||
*/
|
||||
|
||||
|
||||
/* Note :
|
||||
Decompression functions are provided within LZ4 source code (see "lz4.h") (BSD license)
|
||||
*/
|
||||
|
||||
|
||||
/* Advanced Functions */
|
||||
|
||||
void* LZ4_createHC (const char* slidingInputBuffer);
|
||||
int LZ4_compressHC_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize);
|
||||
int LZ4_compressHC_limitedOutput_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int maxOutputSize);
|
||||
char* LZ4_slideInputBufferHC (void* LZ4HC_Data);
|
||||
int LZ4_freeHC (void* LZ4HC_Data);
|
||||
|
||||
/*
|
||||
These functions allow the compression of dependent blocks, where each block benefits from prior 64 KB within preceding blocks.
|
||||
In order to achieve this, it is necessary to start creating the LZ4HC Data Structure, thanks to the function :
|
||||
|
||||
void* LZ4_createHC (const char* slidingInputBuffer);
|
||||
The result of the function is the (void*) pointer on the LZ4HC Data Structure.
|
||||
This pointer will be needed in all other functions.
|
||||
If the pointer returned is NULL, then the allocation has failed, and compression must be aborted.
|
||||
The only parameter 'const char* slidingInputBuffer' must, obviously, point at the beginning of input buffer.
|
||||
The input buffer must be already allocated, and size at least 192KB.
|
||||
'slidingInputBuffer' will also be the 'const char* source' of the first block.
|
||||
|
||||
All blocks are expected to lay next to each other within the input buffer, starting from 'slidingInputBuffer'.
|
||||
To compress each block, use either LZ4_compressHC_continue() or LZ4_compressHC_limitedOutput_continue().
|
||||
Their behavior are identical to LZ4_compressHC() or LZ4_compressHC_limitedOutput(),
|
||||
but require the LZ4HC Data Structure as their first argument, and check that each block starts right after the previous one.
|
||||
If next block does not begin immediately after the previous one, the compression will fail (return 0).
|
||||
|
||||
When it's no longer possible to lay the next block after the previous one (not enough space left into input buffer), a call to :
|
||||
char* LZ4_slideInputBufferHC(void* LZ4HC_Data);
|
||||
must be performed. It will typically copy the latest 64KB of input at the beginning of input buffer.
|
||||
Note that, for this function to work properly, minimum size of an input buffer must be 192KB.
|
||||
==> The memory position where the next input data block must start is provided as the result of the function.
|
||||
|
||||
Compression can then resume, using LZ4_compressHC_continue() or LZ4_compressHC_limitedOutput_continue(), as usual.
|
||||
|
||||
When compression is completed, a call to LZ4_freeHC() will release the memory used by the LZ4HC Data Structure.
|
||||
*/
|
||||
|
||||
|
||||
#if defined (__cplusplus)
|
||||
}
|
||||
#endif
|
||||
@ -0,0 +1,349 @@
|
||||
/*
|
||||
LZ4 HC Encoder - Part of LZ4 HC algorithm
|
||||
Copyright (C) 2011-2013, Yann Collet.
|
||||
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are
|
||||
met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above
|
||||
copyright notice, this list of conditions and the following disclaimer
|
||||
in the documentation and/or other materials provided with the
|
||||
distribution.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
You can contact the author at :
|
||||
- LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html
|
||||
- LZ4 source repository : http://code.google.com/p/lz4/
|
||||
*/
|
||||
|
||||
/* lz4hc_encoder.h must be included into lz4hc.c
|
||||
The objective of this file is to create a single LZ4 compression function source
|
||||
which will be instanciated multiple times with minor variations
|
||||
depending on a set of #define.
|
||||
*/
|
||||
|
||||
//****************************
|
||||
// Check required defines
|
||||
//****************************
|
||||
|
||||
#ifndef FUNCTION_NAME
|
||||
# error "FUNTION_NAME is not defined"
|
||||
#endif
|
||||
|
||||
|
||||
//****************************
|
||||
// Local definitions
|
||||
//****************************
|
||||
#define COMBINED_NAME_RAW(n1,n2) n1 ## n2
|
||||
#define COMBINED_NAME(n1,n2) COMBINED_NAME_RAW(n1,n2)
|
||||
#define ENCODE_SEQUENCE_NAME COMBINED_NAME(FUNCTION_NAME,_encodeSequence)
|
||||
#ifdef LIMITED_OUTPUT
|
||||
# define ENCODE_SEQUENCE(i,o,a,m,r,d) if (ENCODE_SEQUENCE_NAME(i,o,a,m,r,d)) return 0;
|
||||
#else
|
||||
# define ENCODE_SEQUENCE(i,o,a,m,r,d) ENCODE_SEQUENCE_NAME(i,o,a,m,r)
|
||||
#endif
|
||||
|
||||
//****************************
|
||||
// Function code
|
||||
//****************************
|
||||
|
||||
forceinline int ENCODE_SEQUENCE_NAME (
|
||||
const BYTE** ip,
|
||||
BYTE** op,
|
||||
const BYTE** anchor,
|
||||
int matchLength,
|
||||
const BYTE* ref
|
||||
#ifdef LIMITED_OUTPUT
|
||||
,BYTE* oend
|
||||
#endif
|
||||
)
|
||||
{
|
||||
int length, len;
|
||||
BYTE* token;
|
||||
|
||||
// Encode Literal length
|
||||
length = (int)(*ip - *anchor);
|
||||
token = (*op)++;
|
||||
#ifdef LIMITED_OUTPUT
|
||||
if ((*op + length + (2 + 1 + LASTLITERALS) + (length>>8)) > oend) return 1; // Check output limit
|
||||
#endif
|
||||
if (length>=(int)RUN_MASK) { *token=(RUN_MASK<<ML_BITS); len = length-RUN_MASK; for(; len > 254 ; len-=255) *(*op)++ = 255; *(*op)++ = (BYTE)len; }
|
||||
else *token = (BYTE)(length<<ML_BITS);
|
||||
|
||||
// Copy Literals
|
||||
LZ4_BLINDCOPY(*anchor, *op, length);
|
||||
|
||||
// Encode Offset
|
||||
LZ4_WRITE_LITTLEENDIAN_16(*op,(U16)(*ip-ref));
|
||||
|
||||
// Encode MatchLength
|
||||
length = (int)(matchLength-MINMATCH);
|
||||
#ifdef LIMITED_OUTPUT
|
||||
if (*op + (1 + LASTLITERALS) + (length>>8) > oend) return 1; // Check output limit
|
||||
#endif
|
||||
if (length>=(int)ML_MASK) { *token+=ML_MASK; length-=ML_MASK; for(; length > 509 ; length-=510) { *(*op)++ = 255; *(*op)++ = 255; } if (length > 254) { length-=255; *(*op)++ = 255; } *(*op)++ = (BYTE)length; }
|
||||
else *token += (BYTE)(length);
|
||||
|
||||
// Prepare next loop
|
||||
*ip += matchLength;
|
||||
*anchor = *ip;
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
||||
int COMBINED_NAME(FUNCTION_NAME,_continue) (
|
||||
void* ctxvoid,
|
||||
const char* source,
|
||||
char* dest,
|
||||
int inputSize
|
||||
#ifdef LIMITED_OUTPUT
|
||||
,int maxOutputSize
|
||||
#endif
|
||||
)
|
||||
{
|
||||
LZ4HC_Data_Structure* ctx = (LZ4HC_Data_Structure*) ctxvoid;
|
||||
const BYTE* ip = (const BYTE*) source;
|
||||
const BYTE* anchor = ip;
|
||||
const BYTE* const iend = ip + inputSize;
|
||||
const BYTE* const mflimit = iend - MFLIMIT;
|
||||
const BYTE* const matchlimit = (iend - LASTLITERALS);
|
||||
|
||||
BYTE* op = (BYTE*) dest;
|
||||
#ifdef LIMITED_OUTPUT
|
||||
BYTE* const oend = op + maxOutputSize;
|
||||
#endif
|
||||
|
||||
int ml, ml2, ml3, ml0;
|
||||
const BYTE* ref=NULL;
|
||||
const BYTE* start2=NULL;
|
||||
const BYTE* ref2=NULL;
|
||||
const BYTE* start3=NULL;
|
||||
const BYTE* ref3=NULL;
|
||||
const BYTE* start0;
|
||||
const BYTE* ref0;
|
||||
|
||||
// Ensure blocks follow each other
|
||||
if (ip != ctx->end) return 0;
|
||||
ctx->end += inputSize;
|
||||
|
||||
ip++;
|
||||
|
||||
// Main Loop
|
||||
while (ip < mflimit)
|
||||
{
|
||||
ml = LZ4HC_InsertAndFindBestMatch (ctx, ip, matchlimit, (&ref));
|
||||
if (!ml) { ip++; continue; }
|
||||
|
||||
// saved, in case we would skip too much
|
||||
start0 = ip;
|
||||
ref0 = ref;
|
||||
ml0 = ml;
|
||||
|
||||
_Search2:
|
||||
if (ip+ml < mflimit)
|
||||
ml2 = LZ4HC_InsertAndGetWiderMatch(ctx, ip + ml - 2, ip + 1, matchlimit, ml, &ref2, &start2);
|
||||
else ml2 = ml;
|
||||
|
||||
if (ml2 == ml) // No better match
|
||||
{
|
||||
ENCODE_SEQUENCE(&ip, &op, &anchor, ml, ref, oend);
|
||||
continue;
|
||||
}
|
||||
|
||||
if (start0 < ip)
|
||||
{
|
||||
if (start2 < ip + ml0) // empirical
|
||||
{
|
||||
ip = start0;
|
||||
ref = ref0;
|
||||
ml = ml0;
|
||||
}
|
||||
}
|
||||
|
||||
// Here, start0==ip
|
||||
if ((start2 - ip) < 3) // First Match too small : removed
|
||||
{
|
||||
ml = ml2;
|
||||
ip = start2;
|
||||
ref =ref2;
|
||||
goto _Search2;
|
||||
}
|
||||
|
||||
_Search3:
|
||||
// Currently we have :
|
||||
// ml2 > ml1, and
|
||||
// ip1+3 <= ip2 (usually < ip1+ml1)
|
||||
if ((start2 - ip) < OPTIMAL_ML)
|
||||
{
|
||||
int correction;
|
||||
int new_ml = ml;
|
||||
if (new_ml > OPTIMAL_ML) new_ml = OPTIMAL_ML;
|
||||
if (ip+new_ml > start2 + ml2 - MINMATCH) new_ml = (int)(start2 - ip) + ml2 - MINMATCH;
|
||||
correction = new_ml - (int)(start2 - ip);
|
||||
if (correction > 0)
|
||||
{
|
||||
start2 += correction;
|
||||
ref2 += correction;
|
||||
ml2 -= correction;
|
||||
}
|
||||
}
|
||||
// Now, we have start2 = ip+new_ml, with new_ml = min(ml, OPTIMAL_ML=18)
|
||||
|
||||
if (start2 + ml2 < mflimit)
|
||||
ml3 = LZ4HC_InsertAndGetWiderMatch(ctx, start2 + ml2 - 3, start2, matchlimit, ml2, &ref3, &start3);
|
||||
else ml3 = ml2;
|
||||
|
||||
if (ml3 == ml2) // No better match : 2 sequences to encode
|
||||
{
|
||||
// ip & ref are known; Now for ml
|
||||
if (start2 < ip+ml) ml = (int)(start2 - ip);
|
||||
// Now, encode 2 sequences
|
||||
ENCODE_SEQUENCE(&ip, &op, &anchor, ml, ref, oend);
|
||||
ip = start2;
|
||||
ENCODE_SEQUENCE(&ip, &op, &anchor, ml2, ref2, oend);
|
||||
continue;
|
||||
}
|
||||
|
||||
if (start3 < ip+ml+3) // Not enough space for match 2 : remove it
|
||||
{
|
||||
if (start3 >= (ip+ml)) // can write Seq1 immediately ==> Seq2 is removed, so Seq3 becomes Seq1
|
||||
{
|
||||
if (start2 < ip+ml)
|
||||
{
|
||||
int correction = (int)(ip+ml - start2);
|
||||
start2 += correction;
|
||||
ref2 += correction;
|
||||
ml2 -= correction;
|
||||
if (ml2 < MINMATCH)
|
||||
{
|
||||
start2 = start3;
|
||||
ref2 = ref3;
|
||||
ml2 = ml3;
|
||||
}
|
||||
}
|
||||
|
||||
ENCODE_SEQUENCE(&ip, &op, &anchor, ml, ref, oend);
|
||||
ip = start3;
|
||||
ref = ref3;
|
||||
ml = ml3;
|
||||
|
||||
start0 = start2;
|
||||
ref0 = ref2;
|
||||
ml0 = ml2;
|
||||
goto _Search2;
|
||||
}
|
||||
|
||||
start2 = start3;
|
||||
ref2 = ref3;
|
||||
ml2 = ml3;
|
||||
goto _Search3;
|
||||
}
|
||||
|
||||
// OK, now we have 3 ascending matches; let's write at least the first one
|
||||
// ip & ref are known; Now for ml
|
||||
if (start2 < ip+ml)
|
||||
{
|
||||
if ((start2 - ip) < (int)ML_MASK)
|
||||
{
|
||||
int correction;
|
||||
if (ml > OPTIMAL_ML) ml = OPTIMAL_ML;
|
||||
if (ip + ml > start2 + ml2 - MINMATCH) ml = (int)(start2 - ip) + ml2 - MINMATCH;
|
||||
correction = ml - (int)(start2 - ip);
|
||||
if (correction > 0)
|
||||
{
|
||||
start2 += correction;
|
||||
ref2 += correction;
|
||||
ml2 -= correction;
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
ml = (int)(start2 - ip);
|
||||
}
|
||||
}
|
||||
ENCODE_SEQUENCE(&ip, &op, &anchor, ml, ref, oend);
|
||||
|
||||
ip = start2;
|
||||
ref = ref2;
|
||||
ml = ml2;
|
||||
|
||||
start2 = start3;
|
||||
ref2 = ref3;
|
||||
ml2 = ml3;
|
||||
|
||||
goto _Search3;
|
||||
|
||||
}
|
||||
|
||||
// Encode Last Literals
|
||||
{
|
||||
int lastRun = (int)(iend - anchor);
|
||||
#ifdef LIMITED_OUTPUT
|
||||
if (((char*)op - dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize) return 0; // Check output limit
|
||||
#endif
|
||||
if (lastRun>=(int)RUN_MASK) { *op++=(RUN_MASK<<ML_BITS); lastRun-=RUN_MASK; for(; lastRun > 254 ; lastRun-=255) *op++ = 255; *op++ = (BYTE) lastRun; }
|
||||
else *op++ = (BYTE)(lastRun<<ML_BITS);
|
||||
memcpy(op, anchor, iend - anchor);
|
||||
op += iend-anchor;
|
||||
}
|
||||
|
||||
// End
|
||||
return (int) (((char*)op)-dest);
|
||||
}
|
||||
|
||||
|
||||
int FUNCTION_NAME (const char* source,
|
||||
char* dest,
|
||||
int inputSize
|
||||
#ifdef LIMITED_OUTPUT
|
||||
,int maxOutputSize
|
||||
#endif
|
||||
)
|
||||
{
|
||||
void* ctx = LZ4_createHC(source);
|
||||
int result;
|
||||
if (ctx==NULL) return 0;
|
||||
#ifdef LIMITED_OUTPUT
|
||||
result = COMBINED_NAME(FUNCTION_NAME,_continue) (ctx, source, dest, inputSize, maxOutputSize);
|
||||
#else
|
||||
result = COMBINED_NAME(FUNCTION_NAME,_continue) (ctx, source, dest, inputSize);
|
||||
#endif
|
||||
LZ4_freeHC(ctx);
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
|
||||
//****************************
|
||||
// Clean defines
|
||||
//****************************
|
||||
|
||||
// Required defines
|
||||
#undef FUNCTION_NAME
|
||||
|
||||
// Locally Generated
|
||||
#undef ENCODE_SEQUENCE
|
||||
#undef ENCODE_SEQUENCE_NAME
|
||||
|
||||
// Optional defines
|
||||
#ifdef LIMITED_OUTPUT
|
||||
#undef LIMITED_OUTPUT
|
||||
#endif
|
||||
|
||||
|
||||
@ -134,6 +134,14 @@ public void testSnappyCodec() throws IOException {
|
||||
public void testLz4Codec() throws IOException {
|
||||
if (NativeCodeLoader.isNativeCodeLoaded()) {
|
||||
if (Lz4Codec.isNativeCodeLoaded()) {
|
||||
conf.setBoolean(
|
||||
CommonConfigurationKeys.IO_COMPRESSION_CODEC_LZ4_USELZ4HC_KEY,
|
||||
false);
|
||||
codecTest(conf, seed, 0, "org.apache.hadoop.io.compress.Lz4Codec");
|
||||
codecTest(conf, seed, count, "org.apache.hadoop.io.compress.Lz4Codec");
|
||||
conf.setBoolean(
|
||||
CommonConfigurationKeys.IO_COMPRESSION_CODEC_LZ4_USELZ4HC_KEY,
|
||||
true);
|
||||
codecTest(conf, seed, 0, "org.apache.hadoop.io.compress.Lz4Codec");
|
||||
codecTest(conf, seed, count, "org.apache.hadoop.io.compress.Lz4Codec");
|
||||
} else {
|
||||
|
||||
Loading…
Reference in New Issue
Block a user