big-data/hadoop
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

HADOOP-17144. Update Hadoop's lz4 to v1.9.2. Contributed by Hemanth Boyina.

Browse Source
This commit is contained in:
hemanthboyina 2020-10-18 18:37:46 +05:30
parent 1e3a6efcef
commit 42e7e0380f
9 changed files with 4380 additions and 1895 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/io/compress/lz4/Lz4Compressor.java
View File

@ -44,6 +44,7 @@ public class Lz4Compressor implements Compressor {
private byte[] userBuf = null; private byte[] userBuf = null;
private int userBufOff = 0, userBufLen = 0; private int userBufOff = 0, userBufLen = 0;
private boolean finish, finished; private boolean finish, finished;
private int dstCapacity;
private long bytesRead = 0L; private long bytesRead = 0L;
private long bytesWritten = 0L; private long bytesWritten = 0L;
@ -77,8 +78,14 @@ public Lz4Compressor(int directBufferSize, boolean useLz4HC) {
this.directBufferSize = directBufferSize; this.directBufferSize = directBufferSize;
uncompressedDirectBuf = ByteBuffer.allocateDirect(directBufferSize); uncompressedDirectBuf = ByteBuffer.allocateDirect(directBufferSize);
compressedDirectBuf = ByteBuffer.allocateDirect(directBufferSize);
compressedDirectBuf.position(directBufferSize); // Compression is guaranteed to succeed if 'dstCapacity' >=
// LZ4_compressBound(srcSize)
// whereas LZ4_compressBound(isize) is (isize) + ((isize)/255) + 16)
this.dstCapacity = (directBufferSize) + ((directBufferSize) / 255) + 16;
compressedDirectBuf = ByteBuffer.allocateDirect(this.dstCapacity);
compressedDirectBuf.position(this.dstCapacity);
} }
/** /**

14
hadoop-common-project/hadoop-common/src/main/native/src/org/apache/hadoop/io/compress/lz4/Lz4Compressor.c
View File

@ -30,7 +30,7 @@
static jfieldID Lz4Compressor_uncompressedDirectBuf; static jfieldID Lz4Compressor_uncompressedDirectBuf;
static jfieldID Lz4Compressor_uncompressedDirectBufLen; static jfieldID Lz4Compressor_uncompressedDirectBufLen;
static jfieldID Lz4Compressor_compressedDirectBuf; static jfieldID Lz4Compressor_compressedDirectBuf;
static jfieldID Lz4Compressor_directBufferSize; static jfieldID Lz4Compressor_dstCapacity;
JNIEXPORT void JNICALL Java_org_apache_hadoop_io_compress_lz4_Lz4Compressor_initIDs JNIEXPORT void JNICALL Java_org_apache_hadoop_io_compress_lz4_Lz4Compressor_initIDs
@ -44,8 +44,8 @@ JNIEXPORT void JNICALL Java_org_apache_hadoop_io_compress_lz4_Lz4Compressor_init
Lz4Compressor_compressedDirectBuf = (*env)->GetFieldID(env, clazz, Lz4Compressor_compressedDirectBuf = (*env)->GetFieldID(env, clazz,
"compressedDirectBuf", "compressedDirectBuf",
"Ljava/nio/Buffer;"); "Ljava/nio/Buffer;");
Lz4Compressor_directBufferSize = (*env)->GetFieldID(env, clazz, Lz4Compressor_dstCapacity = (*env)->GetFieldID(env, clazz,
"directBufferSize", "I"); "dstCapacity", "I");
} }
JNIEXPORT jint JNICALL Java_org_apache_hadoop_io_compress_lz4_Lz4Compressor_compressBytesDirect JNIEXPORT jint JNICALL Java_org_apache_hadoop_io_compress_lz4_Lz4Compressor_compressBytesDirect
@ -57,7 +57,7 @@ JNIEXPORT jint JNICALL Java_org_apache_hadoop_io_compress_lz4_Lz4Compressor_comp
jobject uncompressed_direct_buf = (*env)->GetObjectField(env, thisj, Lz4Compressor_uncompressedDirectBuf); jobject uncompressed_direct_buf = (*env)->GetObjectField(env, thisj, Lz4Compressor_uncompressedDirectBuf);
jint uncompressed_direct_buf_len = (*env)->GetIntField(env, thisj, Lz4Compressor_uncompressedDirectBufLen); jint uncompressed_direct_buf_len = (*env)->GetIntField(env, thisj, Lz4Compressor_uncompressedDirectBufLen);
jobject compressed_direct_buf = (*env)->GetObjectField(env, thisj, Lz4Compressor_compressedDirectBuf); jobject compressed_direct_buf = (*env)->GetObjectField(env, thisj, Lz4Compressor_compressedDirectBuf);
jint compressed_direct_buf_len = (*env)->GetIntField(env, thisj, Lz4Compressor_directBufferSize); jint compressed_direct_buf_len = (*env)->GetIntField(env, thisj, Lz4Compressor_dstCapacity);
// Get the input direct buffer // Get the input direct buffer
uncompressed_bytes = (const char*)(*env)->GetDirectBufferAddress(env, uncompressed_direct_buf); uncompressed_bytes = (const char*)(*env)->GetDirectBufferAddress(env, uncompressed_direct_buf);
@ -73,7 +73,7 @@ JNIEXPORT jint JNICALL Java_org_apache_hadoop_io_compress_lz4_Lz4Compressor_comp
return (jint)0; return (jint)0;
} }
compressed_direct_buf_len = LZ4_compress(uncompressed_bytes, compressed_bytes, uncompressed_direct_buf_len); compressed_direct_buf_len = LZ4_compress_default(uncompressed_bytes, compressed_bytes, uncompressed_direct_buf_len, compressed_direct_buf_len);
if (compressed_direct_buf_len < 0){ if (compressed_direct_buf_len < 0){
THROW(env, "java/lang/InternalError", "LZ4_compress failed"); THROW(env, "java/lang/InternalError", "LZ4_compress failed");
} }
@ -101,7 +101,7 @@ JNIEXPORT jint JNICALL Java_org_apache_hadoop_io_compress_lz4_Lz4Compressor_comp
jobject uncompressed_direct_buf = (*env)->GetObjectField(env, thisj, Lz4Compressor_uncompressedDirectBuf); jobject uncompressed_direct_buf = (*env)->GetObjectField(env, thisj, Lz4Compressor_uncompressedDirectBuf);
jint uncompressed_direct_buf_len = (*env)->GetIntField(env, thisj, Lz4Compressor_uncompressedDirectBufLen); jint uncompressed_direct_buf_len = (*env)->GetIntField(env, thisj, Lz4Compressor_uncompressedDirectBufLen);
jobject compressed_direct_buf = (*env)->GetObjectField(env, thisj, Lz4Compressor_compressedDirectBuf); jobject compressed_direct_buf = (*env)->GetObjectField(env, thisj, Lz4Compressor_compressedDirectBuf);
jint compressed_direct_buf_len = (*env)->GetIntField(env, thisj, Lz4Compressor_directBufferSize); jint compressed_direct_buf_len = (*env)->GetIntField(env, thisj, Lz4Compressor_dstCapacity);
// Get the input direct buffer // Get the input direct buffer
uncompressed_bytes = (const char*)(*env)->GetDirectBufferAddress(env, uncompressed_direct_buf); uncompressed_bytes = (const char*)(*env)->GetDirectBufferAddress(env, uncompressed_direct_buf);
@ -117,7 +117,7 @@ JNIEXPORT jint JNICALL Java_org_apache_hadoop_io_compress_lz4_Lz4Compressor_comp
return (jint)0; return (jint)0;
} }
compressed_direct_buf_len = LZ4_compressHC(uncompressed_bytes, compressed_bytes, uncompressed_direct_buf_len); compressed_direct_buf_len = LZ4_compress_HC(uncompressed_bytes, compressed_bytes, uncompressed_direct_buf_len, compressed_direct_buf_len, 0);
if (compressed_direct_buf_len < 0){ if (compressed_direct_buf_len < 0){
THROW(env, "java/lang/InternalError", "LZ4_compressHC failed"); THROW(env, "java/lang/InternalError", "LZ4_compressHC failed");
} }

2815
hadoop-common-project/hadoop-common/src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4.c
View File

File diff suppressed because it is too large Load Diff

895
hadoop-common-project/hadoop-common/src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4.h
View File

@ -1,7 +1,8 @@
/* /*
LZ4 - Fast LZ compression algorithm * LZ4 - Fast LZ compression algorithm
Header File * Header File
Copyright (C) 2011-2014, Yann Collet. * Copyright (C) 2011-present, Yann Collet.
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
Redistribution and use in source and binary forms, with or without Redistribution and use in source and binary forms, with or without
@ -28,294 +29,734 @@
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
You can contact the author at : You can contact the author at :
- LZ4 source repository : http://code.google.com/p/lz4/ - LZ4 homepage : http://www.lz4.org
- LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c - LZ4 source repository : https://github.com/lz4/lz4
*/ */
#pragma once
#if defined (__cplusplus) #if defined (__cplusplus)
extern "C" { extern "C" {
#endif #endif
/* #ifndef LZ4_H_2983827168210
* lz4.h provides raw compression format functions, for optimal performance and integration into programs. #define LZ4_H_2983827168210
* If you need to generate data using an inter-operable format (respecting the framing specification),
* please use lz4frame.h instead. /* --- Dependency --- */
#include <stddef.h> /* size_t */
/**
Introduction
LZ4 is lossless compression algorithm, providing compression speed >500 MB/s per core,
scalable with multi-cores CPU. It features an extremely fast decoder, with speed in
multiple GB/s per core, typically reaching RAM speed limits on multi-core systems.
The LZ4 compression library provides in-memory compression and decompression functions.
It gives full buffer control to user.
Compression can be done in:
- a single step (described as Simple Functions)
- a single step, reusing a context (described in Advanced Functions)
- unbounded multiple steps (described as Streaming compression)
lz4.h generates and decodes LZ4-compressed blocks (doc/lz4_Block_format.md).
Decompressing such a compressed block requires additional metadata.
Exact metadata depends on exact decompression function.
For the typical case of LZ4_decompress_safe(),
metadata includes block's compressed size, and maximum bound of decompressed size.
Each application is free to encode and pass such metadata in whichever way it wants.
lz4.h only handle blocks, it can not generate Frames.
Blocks are different from Frames (doc/lz4_Frame_format.md).
Frames bundle both blocks and metadata in a specified manner.
Embedding metadata is required for compressed data to be self-contained and portable.
Frame format is delivered through a companion API, declared in lz4frame.h.
The `lz4` CLI can only manage frames.
*/ */
/************************************** /*^***************************************************************
Version * Export parameters
**************************************/ *****************************************************************/
#define LZ4_VERSION_MAJOR 1 /* for major interface/format changes */
#define LZ4_VERSION_MINOR 3 /* for minor interface/format changes */
#define LZ4_VERSION_RELEASE 1 /* for tweaks, bug-fixes, or development */
#define LZ4_VERSION_NUMBER (LZ4_VERSION_MAJOR *100*100 + LZ4_VERSION_MINOR *100 + LZ4_VERSION_RELEASE)
int LZ4_versionNumber (void);
/**************************************
Tuning parameter
**************************************/
/* /*
* LZ4_DLL_EXPORT :
* Enable exporting of functions when building a Windows DLL
* LZ4LIB_VISIBILITY :
* Control library symbols visibility.
*/
#ifndef LZ4LIB_VISIBILITY
# if defined(__GNUC__) && (__GNUC__ >= 4)
# define LZ4LIB_VISIBILITY __attribute__ ((visibility ("default")))
# else
# define LZ4LIB_VISIBILITY
# endif
#endif
#if defined(LZ4_DLL_EXPORT) && (LZ4_DLL_EXPORT==1)
# define LZ4LIB_API __declspec(dllexport) LZ4LIB_VISIBILITY
#elif defined(LZ4_DLL_IMPORT) && (LZ4_DLL_IMPORT==1)
# define LZ4LIB_API __declspec(dllimport) LZ4LIB_VISIBILITY /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/
#else
# define LZ4LIB_API LZ4LIB_VISIBILITY
#endif
/*------ Version ------*/
#define LZ4_VERSION_MAJOR 1 /* for breaking interface changes */
#define LZ4_VERSION_MINOR 9 /* for new (non-breaking) interface capabilities */
#define LZ4_VERSION_RELEASE 2 /* for tweaks, bug-fixes, or development */
#define LZ4_VERSION_NUMBER (LZ4_VERSION_MAJOR *100*100 + LZ4_VERSION_MINOR *100 + LZ4_VERSION_RELEASE)
#define LZ4_LIB_VERSION LZ4_VERSION_MAJOR.LZ4_VERSION_MINOR.LZ4_VERSION_RELEASE
#define LZ4_QUOTE(str) #str
#define LZ4_EXPAND_AND_QUOTE(str) LZ4_QUOTE(str)
#define LZ4_VERSION_STRING LZ4_EXPAND_AND_QUOTE(LZ4_LIB_VERSION)
LZ4LIB_API int LZ4_versionNumber (void); /**< library version number; useful to check dll version */
LZ4LIB_API const char* LZ4_versionString (void); /**< library version string; useful to check dll version */
/*-************************************
* Tuning parameter
**************************************/
/*!
* LZ4_MEMORY_USAGE : * LZ4_MEMORY_USAGE :
* Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.) * Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.)
* Increasing memory usage improves compression ratio * Increasing memory usage improves compression ratio.
* Reduced memory usage can improve speed, due to cache effect * Reduced memory usage may improve speed, thanks to better cache locality.
* Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache * Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache
*/ */
#define LZ4_MEMORY_USAGE 14 #ifndef LZ4_MEMORY_USAGE
# define LZ4_MEMORY_USAGE 14
#endif
/************************************** /*-************************************
Simple Functions * Simple Functions
**************************************/ **************************************/
/*! LZ4_compress_default() :
* Compresses 'srcSize' bytes from buffer 'src'
* into already allocated 'dst' buffer of size 'dstCapacity'.
* Compression is guaranteed to succeed if 'dstCapacity' >= LZ4_compressBound(srcSize).
* It also runs faster, so it's a recommended setting.
* If the function cannot compress 'src' into a more limited 'dst' budget,
* compression stops *immediately*, and the function result is zero.
* In which case, 'dst' content is undefined (invalid).
* srcSize : max supported value is LZ4_MAX_INPUT_SIZE.
* dstCapacity : size of buffer 'dst' (which must be already allocated)
* @return : the number of bytes written into buffer 'dst' (necessarily <= dstCapacity)
* or 0 if compression fails
* Note : This function is protected against buffer overflow scenarios (never writes outside 'dst' buffer, nor read outside 'source' buffer).
*/
LZ4LIB_API int LZ4_compress_default(const char* src, char* dst, int srcSize, int dstCapacity);
int LZ4_compress (const char* source, char* dest, int sourceSize); /*! LZ4_decompress_safe() :
int LZ4_decompress_safe (const char* source, char* dest, int compressedSize, int maxDecompressedSize); * compressedSize : is the exact complete size of the compressed block.
* dstCapacity : is the size of destination buffer (which must be already allocated), presumed an upper bound of decompressed size.
/* * @return : the number of bytes decompressed into destination buffer (necessarily <= dstCapacity)
LZ4_compress() : * If destination buffer is not large enough, decoding will stop and output an error code (negative value).
Compresses 'sourceSize' bytes from 'source' into 'dest'. * If the source stream is detected malformed, the function will stop decoding and return a negative result.
Destination buffer must be already allocated, * Note 1 : This function is protected against malicious data packets :
and must be sized to handle worst cases situations (input data not compressible) * it will never writes outside 'dst' buffer, nor read outside 'source' buffer,
Worst case size evaluation is provided by function LZ4_compressBound() * even if the compressed block is maliciously modified to order the decoder to do these actions.
inputSize : Max supported value is LZ4_MAX_INPUT_SIZE * In such case, the decoder stops immediately, and considers the compressed block malformed.
return : the number of bytes written in buffer dest * Note 2 : compressedSize and dstCapacity must be provided to the function, the compressed block does not contain them.
or 0 if the compression fails * The implementation is free to send / store / derive this information in whichever way is most beneficial.
* If there is a need for a different format which bundles together both compressed data and its metadata, consider looking at lz4frame.h instead.
LZ4_decompress_safe() : */
compressedSize : is obviously the source size LZ4LIB_API int LZ4_decompress_safe (const char* src, char* dst, int compressedSize, int dstCapacity);
maxDecompressedSize : is the size of the destination buffer, which must be already allocated.
return : the number of bytes decompressed into the destination buffer (necessarily <= maxDecompressedSize)
If the destination buffer is not large enough, decoding will stop and output an error code (<0).
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,
and never writes outside of output buffer, nor reads outside of input buffer.
It is also protected against malicious data packets.
*/
/************************************** /*-************************************
Advanced Functions * Advanced Functions
**************************************/ **************************************/
#define LZ4_MAX_INPUT_SIZE 0x7E000000 /* 2 113 929 216 bytes */ #define LZ4_MAX_INPUT_SIZE 0x7E000000 /* 2 113 929 216 bytes */
#define LZ4_COMPRESSBOUND(isize) ((unsigned int)(isize) > (unsigned int)LZ4_MAX_INPUT_SIZE ? 0 : (isize) + ((isize)/255) + 16) #define LZ4_COMPRESSBOUND(isize) ((unsigned)(isize) > (unsigned)LZ4_MAX_INPUT_SIZE ? 0 : (isize) + ((isize)/255) + 16)
/* /*! LZ4_compressBound() :
LZ4_compressBound() :
Provides the maximum size that LZ4 compression may output in a "worst case" scenario (input data not compressible) Provides the maximum size that LZ4 compression may output in a "worst case" scenario (input data not compressible)
This function is primarily useful for memory allocation purposes (output buffer size). This function is primarily useful for memory allocation purposes (destination buffer size).
Macro LZ4_COMPRESSBOUND() is also provided for compilation-time evaluation (stack memory allocation for example). Macro LZ4_COMPRESSBOUND() is also provided for compilation-time evaluation (stack memory allocation for example).
Note that LZ4_compress_default() compresses faster when dstCapacity is >= LZ4_compressBound(srcSize)
isize : is the input size. Max supported value is LZ4_MAX_INPUT_SIZE inputSize : max supported value is LZ4_MAX_INPUT_SIZE
return : maximum output size in a "worst case" scenario return : maximum output size in a "worst case" scenario
or 0, if input size is too large ( > LZ4_MAX_INPUT_SIZE) or 0, if input size is incorrect (too large or negative)
*/ */
int LZ4_compressBound(int isize); LZ4LIB_API int LZ4_compressBound(int inputSize);
/*! LZ4_compress_fast() :
/* Same as LZ4_compress_default(), but allows selection of "acceleration" factor.
LZ4_compress_limitedOutput() : The larger the acceleration value, the faster the algorithm, but also the lesser the compression.
Compress 'sourceSize' bytes from 'source' into an output buffer 'dest' of maximum size 'maxOutputSize'. It's a trade-off. It can be fine tuned, with each successive value providing roughly +~3% to speed.
If it cannot achieve it, compression will stop, and result of the function will be zero. An acceleration value of "1" is the same as regular LZ4_compress_default()
This saves time and memory on detecting non-compressible (or barely compressible) data. Values <= 0 will be replaced by ACCELERATION_DEFAULT (currently == 1, see lz4.c).
This function never writes outside of provided output buffer.
sourceSize : Max supported value is LZ4_MAX_INPUT_VALUE
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 compression fails
*/ */
int LZ4_compress_limitedOutput (const char* source, char* dest, int sourceSize, int maxOutputSize); LZ4LIB_API int LZ4_compress_fast (const char* src, char* dst, int srcSize, int dstCapacity, int acceleration);
/* /*! LZ4_compress_fast_extState() :
LZ4_compress_withState() : * Same as LZ4_compress_fast(), using an externally allocated memory space for its state.
Same compression functions, but using an externally allocated memory space to store compression state. * Use LZ4_sizeofState() to know how much memory must be allocated,
Use LZ4_sizeofState() to know how much memory must be allocated, * and allocate it on 8-bytes boundaries (using `malloc()` typically).
and then, provide it as 'void* state' to compression functions. * Then, provide this buffer as `void* state` to compression function.
*/
LZ4LIB_API int LZ4_sizeofState(void);
LZ4LIB_API int LZ4_compress_fast_extState (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration);
/*! LZ4_compress_destSize() :
* Reverse the logic : compresses as much data as possible from 'src' buffer
* into already allocated buffer 'dst', of size >= 'targetDestSize'.
* This function either compresses the entire 'src' content into 'dst' if it's large enough,
* or fill 'dst' buffer completely with as much data as possible from 'src'.
* note: acceleration parameter is fixed to "default".
*
* *srcSizePtr : will be modified to indicate how many bytes where read from 'src' to fill 'dst'.
* New value is necessarily <= input value.
* @return : Nb bytes written into 'dst' (necessarily <= targetDestSize)
* or 0 if compression fails.
*/ */
int LZ4_sizeofState(void); LZ4LIB_API int LZ4_compress_destSize (const char* src, char* dst, int* srcSizePtr, int targetDstSize);
int LZ4_compress_withState (void* state, const char* source, char* dest, int inputSize);
int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize);
/* /*! LZ4_decompress_safe_partial() :
LZ4_decompress_fast() : * Decompress an LZ4 compressed block, of size 'srcSize' at position 'src',
originalSize : is the original and therefore uncompressed size * into destination buffer 'dst' of size 'dstCapacity'.
return : the number of bytes read from the source buffer (in other words, the compressed size) * Up to 'targetOutputSize' bytes will be decoded.
If the source stream is detected malformed, the function will stop decoding and return a negative result. * The function stops decoding on reaching this objective,
Destination buffer must be already allocated. Its size must be a minimum of 'originalSize' bytes. * which can boost performance when only the beginning of a block is required.
note : This function fully respect memory boundaries for properly formed compressed data. *
It is a bit faster than LZ4_decompress_safe(). * @return : the number of bytes decoded in `dst` (necessarily <= dstCapacity)
However, it does not provide any protection against intentionally modified data stream (malicious input). * If source stream is detected malformed, function returns a negative result.
Use this function in trusted environment only (data to decode comes from a trusted source). *
*/ * Note : @return can be < targetOutputSize, if compressed block contains less data.
int LZ4_decompress_fast (const char* source, char* dest, int originalSize); *
* Note 2 : this function features 2 parameters, targetOutputSize and dstCapacity,
* and expects targetOutputSize <= dstCapacity.
* It effectively stops decoding on reaching targetOutputSize,
* so dstCapacity is kind of redundant.
* This is because in a previous version of this function,
* decoding operation would not "break" a sequence in the middle.
* As a consequence, there was no guarantee that decoding would stop at exactly targetOutputSize,
* it could write more bytes, though only up to dstCapacity.
* Some "margin" used to be required for this operation to work properly.
* This is no longer necessary.
* The function nonetheless keeps its signature, in an effort to not break API.
*/
LZ4LIB_API int LZ4_decompress_safe_partial (const char* src, char* dst, int srcSize, int targetOutputSize, int dstCapacity);
/* /*-*********************************************
LZ4_decompress_safe_partial() : * Streaming Compression Functions
This function decompress a compressed block of size 'compressedSize' at position 'source'
into destination buffer 'dest' of size 'maxDecompressedSize'.
The function tries to stop decompressing operation as soon as 'targetOutputSize' has been reached,
reducing decompression time.
return : the number of bytes decoded in the destination buffer (necessarily <= maxDecompressedSize)
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 detected 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_partial (const char* source, char* dest, int compressedSize, int targetOutputSize, int maxDecompressedSize);
/***********************************************
Experimental Streaming Compression Functions
***********************************************/ ***********************************************/
typedef union LZ4_stream_u LZ4_stream_t; /* incomplete type (defined later) */
#define LZ4_STREAMSIZE_U32 ((1 << (LZ4_MEMORY_USAGE-2)) + 8) LZ4LIB_API LZ4_stream_t* LZ4_createStream(void);
#define LZ4_STREAMSIZE (LZ4_STREAMSIZE_U32 * sizeof(unsigned int)) LZ4LIB_API int LZ4_freeStream (LZ4_stream_t* streamPtr);
/*
* LZ4_stream_t /*! LZ4_resetStream_fast() : v1.9.0+
* information structure to track an LZ4 stream. * Use this to prepare an LZ4_stream_t for a new chain of dependent blocks
* important : init this structure content before first use ! * (e.g., LZ4_compress_fast_continue()).
*
* An LZ4_stream_t must be initialized once before usage.
* This is automatically done when created by LZ4_createStream().
* However, should the LZ4_stream_t be simply declared on stack (for example),
* it's necessary to initialize it first, using LZ4_initStream().
*
* After init, start any new stream with LZ4_resetStream_fast().
* A same LZ4_stream_t can be re-used multiple times consecutively
* and compress multiple streams,
* provided that it starts each new stream with LZ4_resetStream_fast().
*
* LZ4_resetStream_fast() is much faster than LZ4_initStream(),
* but is not compatible with memory regions containing garbage data.
*
* Note: it's only useful to call LZ4_resetStream_fast()
* in the context of streaming compression.
* The *extState* functions perform their own resets.
* Invoking LZ4_resetStream_fast() before is redundant, and even counterproductive.
*/ */
typedef struct { unsigned int table[LZ4_STREAMSIZE_U32]; } LZ4_stream_t; LZ4LIB_API void LZ4_resetStream_fast (LZ4_stream_t* streamPtr);
/* /*! LZ4_loadDict() :
* LZ4_resetStream * Use this function to reference a static dictionary into LZ4_stream_t.
* Use this function to init an allocated LZ4_stream_t structure * The dictionary must remain available during compression.
* LZ4_loadDict() triggers a reset, so any previous data will be forgotten.
* The same dictionary will have to be loaded on decompression side for successful decoding.
* Dictionary are useful for better compression of small data (KB range).
* While LZ4 accept any input as dictionary,
* results are generally better when using Zstandard's Dictionary Builder.
* Loading a size of 0 is allowed, and is the same as reset.
* @return : loaded dictionary size, in bytes (necessarily <= 64 KB)
*/ */
void LZ4_resetStream (LZ4_stream_t* LZ4_streamPtr); LZ4LIB_API int LZ4_loadDict (LZ4_stream_t* streamPtr, const char* dictionary, int dictSize);
/* /*! LZ4_compress_fast_continue() :
* If you prefer dynamic allocation methods, * Compress 'src' content using data from previously compressed blocks, for better compression ratio.
* LZ4_createStream will allocate and initialize an LZ4_stream_t structure * 'dst' buffer must be already allocated.
* LZ4_freeStream releases its memory. * If dstCapacity >= LZ4_compressBound(srcSize), compression is guaranteed to succeed, and runs faster.
*
* @return : size of compressed block
* or 0 if there is an error (typically, cannot fit into 'dst').
*
* Note 1 : Each invocation to LZ4_compress_fast_continue() generates a new block.
* Each block has precise boundaries.
* Each block must be decompressed separately, calling LZ4_decompress_*() with relevant metadata.
* It's not possible to append blocks together and expect a single invocation of LZ4_decompress_*() to decompress them together.
*
* Note 2 : The previous 64KB of source data is __assumed__ to remain present, unmodified, at same address in memory !
*
* Note 3 : When input is structured as a double-buffer, each buffer can have any size, including < 64 KB.
* Make sure that buffers are separated, by at least one byte.
* This construction ensures that each block only depends on previous block.
*
* Note 4 : If input buffer is a ring-buffer, it can have any size, including < 64 KB.
*
* Note 5 : After an error, the stream status is undefined (invalid), it can only be reset or freed.
*/ */
LZ4_stream_t* LZ4_createStream(void); LZ4LIB_API int LZ4_compress_fast_continue (LZ4_stream_t* streamPtr, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration);
int LZ4_freeStream (LZ4_stream_t* LZ4_stream);
/* /*! LZ4_saveDict() :
* LZ4_loadDict * If last 64KB data cannot be guaranteed to remain available at its current memory location,
* Use this function to load a static dictionary into LZ4_stream. * save it into a safer place (char* safeBuffer).
* Any previous data will be forgotten, only 'dictionary' will remain in memory. * This is schematically equivalent to a memcpy() followed by LZ4_loadDict(),
* Loading a size of 0 is allowed. * but is much faster, because LZ4_saveDict() doesn't need to rebuild tables.
* Return : 1 if OK, 0 if error * @return : saved dictionary size in bytes (necessarily <= maxDictSize), or 0 if error.
*/ */
int LZ4_loadDict (LZ4_stream_t* LZ4_stream, const char* dictionary, int dictSize); LZ4LIB_API int LZ4_saveDict (LZ4_stream_t* streamPtr, char* safeBuffer, int maxDictSize);
/*
* LZ4_compress_continue
* Compress data block 'source', using blocks compressed before as dictionary to improve compression ratio
* Previous data blocks are assumed to still be present at their previous location.
*/
int LZ4_compress_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize);
/*
* LZ4_compress_limitedOutput_continue
* Same as before, but also specify a maximum target compressed size (maxOutputSize)
* If objective cannot be met, compression exits, and returns a zero.
*/
int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize, int maxOutputSize);
/*
* LZ4_saveDict
* If previously compressed data block is not guaranteed to remain available at its memory location
* save it into a safer place (char* safeBuffer)
* Note : you don't need to call LZ4_loadDict() afterwards,
* dictionary is immediately usable, you can therefore call again LZ4_compress_continue()
* Return : dictionary size in bytes, or 0 if error
* Note : any dictSize > 64 KB will be interpreted as 64KB.
*/
int LZ4_saveDict (LZ4_stream_t* LZ4_stream, char* safeBuffer, int dictSize);
/************************************************ /*-**********************************************
Experimental Streaming Decompression Functions * Streaming Decompression Functions
* Bufferless synchronous API
************************************************/ ************************************************/
typedef union LZ4_streamDecode_u LZ4_streamDecode_t; /* tracking context */
#define LZ4_STREAMDECODESIZE_U32 4 /*! LZ4_createStreamDecode() and LZ4_freeStreamDecode() :
#define LZ4_STREAMDECODESIZE (LZ4_STREAMDECODESIZE_U32 * sizeof(unsigned int)) * creation / destruction of streaming decompression tracking context.
/* * A tracking context can be re-used multiple times.
* LZ4_streamDecode_t
* information structure to track an LZ4 stream.
* important : init this structure content using LZ4_setStreamDecode or memset() before first use !
*/ */
typedef struct { unsigned int table[LZ4_STREAMDECODESIZE_U32]; } LZ4_streamDecode_t; LZ4LIB_API LZ4_streamDecode_t* LZ4_createStreamDecode(void);
LZ4LIB_API int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream);
/* /*! LZ4_setStreamDecode() :
* LZ4_setStreamDecode * An LZ4_streamDecode_t context can be allocated once and re-used multiple times.
* Use this function to instruct where to find the dictionary. * Use this function to start decompression of a new stream of blocks.
* This function can be used to specify a static dictionary, * A dictionary can optionally be set. Use NULL or size 0 for a reset order.
* or to instruct where to find some previously decoded data saved into a different memory space. * Dictionary is presumed stable : it must remain accessible and unmodified during next decompression.
* Setting a size of 0 is allowed (same effect as no dictionary). * @return : 1 if OK, 0 if error
* Return : 1 if OK, 0 if error
*/ */
int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize); LZ4LIB_API int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize);
/* /*! LZ4_decoderRingBufferSize() : v1.8.2+
* If you prefer dynamic allocation methods, * Note : in a ring buffer scenario (optional),
* LZ4_createStreamDecode will allocate and initialize an LZ4_streamDecode_t structure * blocks are presumed decompressed next to each other
* LZ4_freeStreamDecode releases its memory. * up to the moment there is not enough remaining space for next block (remainingSize < maxBlockSize),
* at which stage it resumes from beginning of ring buffer.
* When setting such a ring buffer for streaming decompression,
* provides the minimum size of this ring buffer
* to be compatible with any source respecting maxBlockSize condition.
* @return : minimum ring buffer size,
* or 0 if there is an error (invalid maxBlockSize).
*/ */
LZ4_streamDecode_t* LZ4_createStreamDecode(void); LZ4LIB_API int LZ4_decoderRingBufferSize(int maxBlockSize);
int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream); #define LZ4_DECODER_RING_BUFFER_SIZE(maxBlockSize) (65536 + 14 + (maxBlockSize)) /* for static allocation; maxBlockSize presumed valid */
/* /*! LZ4_decompress_*_continue() :
*_continue() : * These decoding functions allow decompression of consecutive blocks in "streaming" mode.
These decoding functions allow decompression of multiple blocks in "streaming" mode. * A block is an unsplittable entity, it must be presented entirely to a decompression function.
Previously decoded blocks must still be available at the memory position where they were decoded. * Decompression functions only accepts one block at a time.
If it's not possible, save the relevant part of decoded data into a safe buffer, * The last 64KB of previously decoded data *must* remain available and unmodified at the memory position where they were decoded.
and indicate where its new address using LZ4_setStreamDecode() * If less than 64KB of data has been decoded, all the data must be present.
*
* Special : if decompression side sets a ring buffer, it must respect one of the following conditions :
* - Decompression buffer size is _at least_ LZ4_decoderRingBufferSize(maxBlockSize).
* maxBlockSize is the maximum size of any single block. It can have any value > 16 bytes.
* In which case, encoding and decoding buffers do not need to be synchronized.
* Actually, data can be produced by any source compliant with LZ4 format specification, and respecting maxBlockSize.
* - Synchronized mode :
* Decompression buffer size is _exactly_ the same as compression buffer size,
* and follows exactly same update rule (block boundaries at same positions),
* and decoding function is provided with exact decompressed size of each block (exception for last block of the stream),
* _then_ decoding & encoding ring buffer can have any size, including small ones ( < 64 KB).
* - Decompression buffer is larger than encoding buffer, by a minimum of maxBlockSize more bytes.
* In which case, encoding and decoding buffers do not need to be synchronized,
* and encoding ring buffer can have any size, including small ones ( < 64 KB).
*
* Whenever these conditions are not possible,
* save the last 64KB of decoded data into a safe buffer where it can't be modified during decompression,
* then indicate where this data is saved using LZ4_setStreamDecode(), before decompressing next block.
*/ */
int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int compressedSize, int maxDecompressedSize); LZ4LIB_API int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* src, char* dst, int srcSize, int dstCapacity);
int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize);
/* /*! LZ4_decompress_*_usingDict() :
Advanced decoding functions : * These decoding functions work the same as
*_usingDict() : * a combination of LZ4_setStreamDecode() followed by LZ4_decompress_*_continue()
These decoding functions work the same as * They are stand-alone, and don't need an LZ4_streamDecode_t structure.
a combination of LZ4_setDictDecode() followed by LZ4_decompress_x_continue() * Dictionary is presumed stable : it must remain accessible and unmodified during decompression.
They don't use nor update an LZ4_streamDecode_t structure. * Performance tip : Decompression speed can be substantially increased
*/ * when dst == dictStart + dictSize.
int LZ4_decompress_safe_usingDict (const char* source, char* dest, int compressedSize, int maxDecompressedSize, const char* dictStart, int dictSize); */
int LZ4_decompress_fast_usingDict (const char* source, char* dest, int originalSize, const char* dictStart, int dictSize); LZ4LIB_API int LZ4_decompress_safe_usingDict (const char* src, char* dst, int srcSize, int dstCapcity, const char* dictStart, int dictSize);
#endif /* LZ4_H_2983827168210 */
/*^*************************************
* !!!!!! STATIC LINKING ONLY !!!!!!
***************************************/
/*-****************************************************************************
* Experimental section
*
* Symbols declared in this section must be considered unstable. Their
* signatures or semantics may change, or they may be removed altogether in the
* future. They are therefore only safe to depend on when the caller is
* statically linked against the library.
*
* To protect against unsafe usage, not only are the declarations guarded,
* the definitions are hidden by default
* when building LZ4 as a shared/dynamic library.
*
* In order to access these declarations,
* define LZ4_STATIC_LINKING_ONLY in your application
* before including LZ4's headers.
*
* In order to make their implementations accessible dynamically, you must
* define LZ4_PUBLISH_STATIC_FUNCTIONS when building the LZ4 library.
******************************************************************************/
#ifdef LZ4_STATIC_LINKING_ONLY
#ifndef LZ4_STATIC_3504398509
#define LZ4_STATIC_3504398509
#ifdef LZ4_PUBLISH_STATIC_FUNCTIONS
#define LZ4LIB_STATIC_API LZ4LIB_API
#else
#define LZ4LIB_STATIC_API
#endif
/*! LZ4_compress_fast_extState_fastReset() :
* A variant of LZ4_compress_fast_extState().
*
* Using this variant avoids an expensive initialization step.
* It is only safe to call if the state buffer is known to be correctly initialized already
* (see above comment on LZ4_resetStream_fast() for a definition of "correctly initialized").
* From a high level, the difference is that
* this function initializes the provided state with a call to something like LZ4_resetStream_fast()
* while LZ4_compress_fast_extState() starts with a call to LZ4_resetStream().
*/
LZ4LIB_STATIC_API int LZ4_compress_fast_extState_fastReset (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration);
/*! LZ4_attach_dictionary() :
* This is an experimental API that allows
* efficient use of a static dictionary many times.
*
* Rather than re-loading the dictionary buffer into a working context before
* each compression, or copying a pre-loaded dictionary's LZ4_stream_t into a
* working LZ4_stream_t, this function introduces a no-copy setup mechanism,
* in which the working stream references the dictionary stream in-place.
*
* Several assumptions are made about the state of the dictionary stream.
* Currently, only streams which have been prepared by LZ4_loadDict() should
* be expected to work.
*
* Alternatively, the provided dictionaryStream may be NULL,
* in which case any existing dictionary stream is unset.
*
* If a dictionary is provided, it replaces any pre-existing stream history.
* The dictionary contents are the only history that can be referenced and
* logically immediately precede the data compressed in the first subsequent
* compression call.
*
* The dictionary will only remain attached to the working stream through the
* first compression call, at the end of which it is cleared. The dictionary
* stream (and source buffer) must remain in-place / accessible / unchanged
* through the completion of the first compression call on the stream.
*/
LZ4LIB_STATIC_API void LZ4_attach_dictionary(LZ4_stream_t* workingStream, const LZ4_stream_t* dictionaryStream);
/*! In-place compression and decompression
*
* It's possible to have input and output sharing the same buffer,
* for highly contrained memory environments.
* In both cases, it requires input to lay at the end of the buffer,
* and decompression to start at beginning of the buffer.
* Buffer size must feature some margin, hence be larger than final size.
*
* |<------------------------buffer--------------------------------->|
* |<-----------compressed data--------->|
* |<-----------decompressed size------------------>|
* |<----margin---->|
*
* This technique is more useful for decompression,
* since decompressed size is typically larger,
* and margin is short.
*
* In-place decompression will work inside any buffer
* which size is >= LZ4_DECOMPRESS_INPLACE_BUFFER_SIZE(decompressedSize).
* This presumes that decompressedSize > compressedSize.
* Otherwise, it means compression actually expanded data,
* and it would be more efficient to store such data with a flag indicating it's not compressed.
* This can happen when data is not compressible (already compressed, or encrypted).
*
* For in-place compression, margin is larger, as it must be able to cope with both
* history preservation, requiring input data to remain unmodified up to LZ4_DISTANCE_MAX,
* and data expansion, which can happen when input is not compressible.
* As a consequence, buffer size requirements are much higher,
* and memory savings offered by in-place compression are more limited.
*
* There are ways to limit this cost for compression :
* - Reduce history size, by modifying LZ4_DISTANCE_MAX.
* Note that it is a compile-time constant, so all compressions will apply this limit.
* Lower values will reduce compression ratio, except when input_size < LZ4_DISTANCE_MAX,
* so it's a reasonable trick when inputs are known to be small.
* - Require the compressor to deliver a "maximum compressed size".
* This is the `dstCapacity` parameter in `LZ4_compress*()`.
* When this size is < LZ4_COMPRESSBOUND(inputSize), then compression can fail,
* in which case, the return code will be 0 (zero).
* The caller must be ready for these cases to happen,
* and typically design a backup scheme to send data uncompressed.
* The combination of both techniques can significantly reduce
* the amount of margin required for in-place compression.
*
* In-place compression can work in any buffer
* which size is >= (maxCompressedSize)
* with maxCompressedSize == LZ4_COMPRESSBOUND(srcSize) for guaranteed compression success.
* LZ4_COMPRESS_INPLACE_BUFFER_SIZE() depends on both maxCompressedSize and LZ4_DISTANCE_MAX,
* so it's possible to reduce memory requirements by playing with them.
*/
#define LZ4_DECOMPRESS_INPLACE_MARGIN(compressedSize) (((compressedSize) >> 8) + 32)
#define LZ4_DECOMPRESS_INPLACE_BUFFER_SIZE(decompressedSize) ((decompressedSize) + LZ4_DECOMPRESS_INPLACE_MARGIN(decompressedSize)) /**< note: presumes that compressedSize < decompressedSize. note2: margin is overestimated a bit, since it could use compressedSize instead */
#ifndef LZ4_DISTANCE_MAX /* history window size; can be user-defined at compile time */
# define LZ4_DISTANCE_MAX 65535 /* set to maximum value by default */
#endif
#define LZ4_COMPRESS_INPLACE_MARGIN (LZ4_DISTANCE_MAX + 32) /* LZ4_DISTANCE_MAX can be safely replaced by srcSize when it's smaller */
#define LZ4_COMPRESS_INPLACE_BUFFER_SIZE(maxCompressedSize) ((maxCompressedSize) + LZ4_COMPRESS_INPLACE_MARGIN) /**< maxCompressedSize is generally LZ4_COMPRESSBOUND(inputSize), but can be set to any lower value, with the risk that compression can fail (return code 0(zero)) */
#endif /* LZ4_STATIC_3504398509 */
#endif /* LZ4_STATIC_LINKING_ONLY */
/************************************** #ifndef LZ4_H_98237428734687
Obsolete Functions #define LZ4_H_98237428734687
/*-************************************************************
* PRIVATE DEFINITIONS
**************************************************************
* Do not use these definitions directly.
* They are only exposed to allow static allocation of `LZ4_stream_t` and `LZ4_streamDecode_t`.
* Accessing members will expose code to API and/or ABI break in future versions of the library.
**************************************************************/
#define LZ4_HASHLOG (LZ4_MEMORY_USAGE-2)
#define LZ4_HASHTABLESIZE (1 << LZ4_MEMORY_USAGE)
#define LZ4_HASH_SIZE_U32 (1 << LZ4_HASHLOG) /* required as macro for static allocation */
#if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */)
#include <stdint.h>
typedef struct LZ4_stream_t_internal LZ4_stream_t_internal;
struct LZ4_stream_t_internal {
uint32_t hashTable[LZ4_HASH_SIZE_U32];
uint32_t currentOffset;
uint16_t dirty;
uint16_t tableType;
const uint8_t* dictionary;
const LZ4_stream_t_internal* dictCtx;
uint32_t dictSize;
};
typedef struct {
const uint8_t* externalDict;
size_t extDictSize;
const uint8_t* prefixEnd;
size_t prefixSize;
} LZ4_streamDecode_t_internal;
#else
typedef struct LZ4_stream_t_internal LZ4_stream_t_internal;
struct LZ4_stream_t_internal {
unsigned int hashTable[LZ4_HASH_SIZE_U32];
unsigned int currentOffset;
unsigned short dirty;
unsigned short tableType;
const unsigned char* dictionary;
const LZ4_stream_t_internal* dictCtx;
unsigned int dictSize;
};
typedef struct {
const unsigned char* externalDict;
const unsigned char* prefixEnd;
size_t extDictSize;
size_t prefixSize;
} LZ4_streamDecode_t_internal;
#endif
/*! LZ4_stream_t :
* information structure to track an LZ4 stream.
* LZ4_stream_t can also be created using LZ4_createStream(), which is recommended.
* The structure definition can be convenient for static allocation
* (on stack, or as part of larger structure).
* Init this structure with LZ4_initStream() before first use.
* note : only use this definition in association with static linking !
* this definition is not API/ABI safe, and may change in a future version.
*/
#define LZ4_STREAMSIZE_U64 ((1 << (LZ4_MEMORY_USAGE-3)) + 4 + ((sizeof(void*)==16) ? 4 : 0) /*AS-400*/ )
#define LZ4_STREAMSIZE (LZ4_STREAMSIZE_U64 * sizeof(unsigned long long))
union LZ4_stream_u {
unsigned long long table[LZ4_STREAMSIZE_U64];
LZ4_stream_t_internal internal_donotuse;
} ; /* previously typedef'd to LZ4_stream_t */
/*! LZ4_initStream() : v1.9.0+
* An LZ4_stream_t structure must be initialized at least once.
* This is automatically done when invoking LZ4_createStream(),
* but it's not when the structure is simply declared on stack (for example).
*
* Use LZ4_initStream() to properly initialize a newly declared LZ4_stream_t.
* It can also initialize any arbitrary buffer of sufficient size,
* and will @return a pointer of proper type upon initialization.
*
* Note : initialization fails if size and alignment conditions are not respected.
* In which case, the function will @return NULL.
* Note2: An LZ4_stream_t structure guarantees correct alignment and size.
* Note3: Before v1.9.0, use LZ4_resetStream() instead
*/
LZ4LIB_API LZ4_stream_t* LZ4_initStream (void* buffer, size_t size);
/*! LZ4_streamDecode_t :
* information structure to track an LZ4 stream during decompression.
* init this structure using LZ4_setStreamDecode() before first use.
* note : only use in association with static linking !
* this definition is not API/ABI safe,
* and may change in a future version !
*/
#define LZ4_STREAMDECODESIZE_U64 (4 + ((sizeof(void*)==16) ? 2 : 0) /*AS-400*/ )
#define LZ4_STREAMDECODESIZE (LZ4_STREAMDECODESIZE_U64 * sizeof(unsigned long long))
union LZ4_streamDecode_u {
unsigned long long table[LZ4_STREAMDECODESIZE_U64];
LZ4_streamDecode_t_internal internal_donotuse;
} ; /* previously typedef'd to LZ4_streamDecode_t */
/*-************************************
* Obsolete Functions
**************************************/ **************************************/
/*
Obsolete decompression functions
These function names are deprecated and should no longer be used.
They are only provided here for compatibility with older user programs.
- LZ4_uncompress is the same as LZ4_decompress_fast
- LZ4_uncompress_unknownOutputSize is the same as LZ4_decompress_safe
These function prototypes are now disabled; uncomment them if you really need them.
It is highly recommended to stop using these functions and migrated to newer ones */
/* int LZ4_uncompress (const char* source, char* dest, int outputSize); */
/* int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize); */
/* /*! Deprecation warnings
* If you prefer dynamic allocation methods, *
* LZ4_createStreamDecode() * Deprecated functions make the compiler generate a warning when invoked.
* provides a pointer (void*) towards an initialized LZ4_streamDecode_t structure. * This is meant to invite users to update their source code.
* LZ4_free just frees it. * Should deprecation warnings be a problem, it is generally possible to disable them,
* typically with -Wno-deprecated-declarations for gcc
* or _CRT_SECURE_NO_WARNINGS in Visual.
*
* Another method is to define LZ4_DISABLE_DEPRECATE_WARNINGS
* before including the header file.
*/ */
/* void* LZ4_createStreamDecode(void); */ #ifdef LZ4_DISABLE_DEPRECATE_WARNINGS
/*int LZ4_free (void* LZ4_stream); yes, it's the same one as for compression */ # define LZ4_DEPRECATED(message) /* disable deprecation warnings */
#else
# define LZ4_GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__)
# if defined (__cplusplus) && (__cplusplus >= 201402) /* C++14 or greater */
# define LZ4_DEPRECATED(message) [[deprecated(message)]]
# elif (LZ4_GCC_VERSION >= 405) || defined(__clang__)
# define LZ4_DEPRECATED(message) __attribute__((deprecated(message)))
# elif (LZ4_GCC_VERSION >= 301)
# define LZ4_DEPRECATED(message) __attribute__((deprecated))
# elif defined(_MSC_VER)
# define LZ4_DEPRECATED(message) __declspec(deprecated(message))
# else
# pragma message("WARNING: You need to implement LZ4_DEPRECATED for this compiler")
# define LZ4_DEPRECATED(message)
# endif
#endif /* LZ4_DISABLE_DEPRECATE_WARNINGS */
/* Obsolete streaming functions; use new streaming interface whenever possible */ /* Obsolete compression functions */
void* LZ4_create (const char* inputBuffer); LZ4_DEPRECATED("use LZ4_compress_default() instead") LZ4LIB_API int LZ4_compress (const char* src, char* dest, int srcSize);
int LZ4_sizeofStreamState(void); LZ4_DEPRECATED("use LZ4_compress_default() instead") LZ4LIB_API int LZ4_compress_limitedOutput (const char* src, char* dest, int srcSize, int maxOutputSize);
int LZ4_resetStreamState(void* state, const char* inputBuffer); LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") LZ4LIB_API int LZ4_compress_withState (void* state, const char* source, char* dest, int inputSize);
char* LZ4_slideInputBuffer (void* state); LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") LZ4LIB_API int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize);
LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") LZ4LIB_API int LZ4_compress_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize);
LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") LZ4LIB_API int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize, int maxOutputSize);
/* Obsolete decompression functions */
LZ4_DEPRECATED("use LZ4_decompress_fast() instead") LZ4LIB_API int LZ4_uncompress (const char* source, char* dest, int outputSize);
LZ4_DEPRECATED("use LZ4_decompress_safe() instead") LZ4LIB_API int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize);
/* Obsolete streaming functions; degraded functionality; do not use!
*
* In order to perform streaming compression, these functions depended on data
* that is no longer tracked in the state. They have been preserved as well as
* possible: using them will still produce a correct output. However, they don't
* actually retain any history between compression calls. The compression ratio
* achieved will therefore be no better than compressing each chunk
* independently.
*/
LZ4_DEPRECATED("Use LZ4_createStream() instead") LZ4LIB_API void* LZ4_create (char* inputBuffer);
LZ4_DEPRECATED("Use LZ4_createStream() instead") LZ4LIB_API int LZ4_sizeofStreamState(void);
LZ4_DEPRECATED("Use LZ4_resetStream() instead") LZ4LIB_API int LZ4_resetStreamState(void* state, char* inputBuffer);
LZ4_DEPRECATED("Use LZ4_saveDict() instead") LZ4LIB_API char* LZ4_slideInputBuffer (void* state);
/* Obsolete streaming decoding functions */ /* Obsolete streaming decoding functions */
int LZ4_decompress_safe_withPrefix64k (const char* source, char* dest, int compressedSize, int maxOutputSize); LZ4_DEPRECATED("use LZ4_decompress_safe_usingDict() instead") LZ4LIB_API int LZ4_decompress_safe_withPrefix64k (const char* src, char* dst, int compressedSize, int maxDstSize);
int LZ4_decompress_fast_withPrefix64k (const char* source, char* dest, int originalSize); LZ4_DEPRECATED("use LZ4_decompress_fast_usingDict() instead") LZ4LIB_API int LZ4_decompress_fast_withPrefix64k (const char* src, char* dst, int originalSize);
/*! LZ4_decompress_fast() : **unsafe!**
* These functions used to be faster than LZ4_decompress_safe(),
* but it has changed, and they are now slower than LZ4_decompress_safe().
* This is because LZ4_decompress_fast() doesn't know the input size,
* and therefore must progress more cautiously in the input buffer to not read beyond the end of block.
* On top of that `LZ4_decompress_fast()` is not protected vs malformed or malicious inputs, making it a security liability.
* As a consequence, LZ4_decompress_fast() is strongly discouraged, and deprecated.
*
* The last remaining LZ4_decompress_fast() specificity is that
* it can decompress a block without knowing its compressed size.
* Such functionality could be achieved in a more secure manner,
* by also providing the maximum size of input buffer,
* but it would require new prototypes, and adaptation of the implementation to this new use case.
*
* Parameters:
* originalSize : is the uncompressed size to regenerate.
* `dst` must be already allocated, its size must be >= 'originalSize' bytes.
* @return : number of bytes read from source buffer (== compressed size).
* The function expects to finish at block's end exactly.
* If the source stream is detected malformed, the function stops decoding and returns a negative result.
* note : LZ4_decompress_fast*() requires originalSize. Thanks to this information, it never writes past the output buffer.
* However, since it doesn't know its 'src' size, it may read an unknown amount of input, past input buffer bounds.
* Also, since match offsets are not validated, match reads from 'src' may underflow too.
* These issues never happen if input (compressed) data is correct.
* But they may happen if input data is invalid (error or intentional tampering).
* As a consequence, use these functions in trusted environments with trusted data **only**.
*/
LZ4_DEPRECATED("This function is deprecated and unsafe. Consider using LZ4_decompress_safe() instead")
LZ4LIB_API int LZ4_decompress_fast (const char* src, char* dst, int originalSize);
LZ4_DEPRECATED("This function is deprecated and unsafe. Consider using LZ4_decompress_safe_continue() instead")
LZ4LIB_API int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* src, char* dst, int originalSize);
LZ4_DEPRECATED("This function is deprecated and unsafe. Consider using LZ4_decompress_safe_usingDict() instead")
LZ4LIB_API int LZ4_decompress_fast_usingDict (const char* src, char* dst, int originalSize, const char* dictStart, int dictSize);
/*! LZ4_resetStream() :
* An LZ4_stream_t structure must be initialized at least once.
* This is done with LZ4_initStream(), or LZ4_resetStream().
* Consider switching to LZ4_initStream(),
* invoking LZ4_resetStream() will trigger deprecation warnings in the future.
*/
LZ4LIB_API void LZ4_resetStream (LZ4_stream_t* streamPtr);
#endif /* LZ4_H_98237428734687 */
#if defined (__cplusplus) #if defined (__cplusplus)

2023
hadoop-common-project/hadoop-common/src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4hc.c
View File

File diff suppressed because it is too large Load Diff

507
hadoop-common-project/hadoop-common/src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4hc.h
View File

@ -1,7 +1,7 @@
/* /*
LZ4 HC - High Compression Mode of LZ4 LZ4 HC - High Compression Mode of LZ4
Header File Header File
Copyright (C) 2011-2014, Yann Collet. Copyright (C) 2011-2017, Yann Collet.
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
Redistribution and use in source and binary forms, with or without Redistribution and use in source and binary forms, with or without
@ -28,146 +28,411 @@
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
You can contact the author at : You can contact the author at :
- LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html - LZ4 source repository : https://github.com/lz4/lz4
- LZ4 source repository : http://code.google.com/p/lz4/ - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c
*/ */
#pragma once #ifndef LZ4_HC_H_19834876238432
#define LZ4_HC_H_19834876238432
#if defined (__cplusplus) #if defined (__cplusplus)
extern "C" { extern "C" {
#endif #endif
/* --- Dependency --- */
int LZ4_compressHC (const char* source, char* dest, int inputSize); /* note : lz4hc requires lz4.h/lz4.c for compilation */
/* #include "lz4.h" /* stddef, LZ4LIB_API, LZ4_DEPRECATED */
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.
*/
int LZ4_compressHC2 (const char* source, char* dest, int inputSize, int compressionLevel); /* --- Useful constants --- */
int LZ4_compressHC2_limitedOutput (const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel); #define LZ4HC_CLEVEL_MIN 3
/* #define LZ4HC_CLEVEL_DEFAULT 9
Same functions as above, but with programmable 'compressionLevel'. #define LZ4HC_CLEVEL_OPT_MIN 10
Recommended values are between 4 and 9, although any value between 0 and 16 will work. #define LZ4HC_CLEVEL_MAX 12
'compressionLevel'==0 means use default 'compressionLevel' value.
Values above 16 behave the same as 16.
Equivalent variants exist for all other compression functions below. /*-************************************
*/ * Block Compression
**************************************/
/*! LZ4_compress_HC() :
* Compress data from `src` into `dst`, using the powerful but slower "HC" algorithm.
* `dst` must be already allocated.
* Compression is guaranteed to succeed if `dstCapacity >= LZ4_compressBound(srcSize)` (see "lz4.h")
* Max supported `srcSize` value is LZ4_MAX_INPUT_SIZE (see "lz4.h")
* `compressionLevel` : any value between 1 and LZ4HC_CLEVEL_MAX will work.
* Values > LZ4HC_CLEVEL_MAX behave the same as LZ4HC_CLEVEL_MAX.
* @return : the number of bytes written into 'dst'
* or 0 if compression fails.
*/
LZ4LIB_API int LZ4_compress_HC (const char* src, char* dst, int srcSize, int dstCapacity, int compressionLevel);
/* Note : /* Note :
Decompression functions are provided within LZ4 source code (see "lz4.h") (BSD license) * Decompression functions are provided within "lz4.h" (BSD license)
*/
/*! LZ4_compress_HC_extStateHC() :
* Same as LZ4_compress_HC(), but using an externally allocated memory segment for `state`.
* `state` size is provided by LZ4_sizeofStateHC().
* Memory segment must be aligned on 8-bytes boundaries (which a normal malloc() should do properly).
*/
LZ4LIB_API int LZ4_sizeofStateHC(void);
LZ4LIB_API int LZ4_compress_HC_extStateHC(void* stateHC, const char* src, char* dst, int srcSize, int maxDstSize, int compressionLevel);
/*! LZ4_compress_HC_destSize() : v1.9.0+
* Will compress as much data as possible from `src`
* to fit into `targetDstSize` budget.
* Result is provided in 2 parts :
* @return : the number of bytes written into 'dst' (necessarily <= targetDstSize)
* or 0 if compression fails.
* `srcSizePtr` : on success, *srcSizePtr is updated to indicate how much bytes were read from `src`
*/
LZ4LIB_API int LZ4_compress_HC_destSize(void* stateHC,
const char* src, char* dst,
int* srcSizePtr, int targetDstSize,
int compressionLevel);
/*-************************************
* Streaming Compression
* Bufferless synchronous API
**************************************/
typedef union LZ4_streamHC_u LZ4_streamHC_t; /* incomplete type (defined later) */
/*! LZ4_createStreamHC() and LZ4_freeStreamHC() :
* These functions create and release memory for LZ4 HC streaming state.
* Newly created states are automatically initialized.
* A same state can be used multiple times consecutively,
* starting with LZ4_resetStreamHC_fast() to start a new stream of blocks.
*/
LZ4LIB_API LZ4_streamHC_t* LZ4_createStreamHC(void);
LZ4LIB_API int LZ4_freeStreamHC (LZ4_streamHC_t* streamHCPtr);
/*
These functions compress data in successive blocks of any size,
using previous blocks as dictionary, to improve compression ratio.
One key assumption is that previous blocks (up to 64 KB) remain read-accessible while compressing next blocks.
There is an exception for ring buffers, which can be smaller than 64 KB.
Ring-buffer scenario is automatically detected and handled within LZ4_compress_HC_continue().
Before starting compression, state must be allocated and properly initialized.
LZ4_createStreamHC() does both, though compression level is set to LZ4HC_CLEVEL_DEFAULT.
Selecting the compression level can be done with LZ4_resetStreamHC_fast() (starts a new stream)
or LZ4_setCompressionLevel() (anytime, between blocks in the same stream) (experimental).
LZ4_resetStreamHC_fast() only works on states which have been properly initialized at least once,
which is automatically the case when state is created using LZ4_createStreamHC().
After reset, a first "fictional block" can be designated as initial dictionary,
using LZ4_loadDictHC() (Optional).
Invoke LZ4_compress_HC_continue() to compress each successive block.
The number of blocks is unlimited.
Previous input blocks, including initial dictionary when present,
must remain accessible and unmodified during compression.
It's allowed to update compression level anytime between blocks,
using LZ4_setCompressionLevel() (experimental).
'dst' buffer should be sized to handle worst case scenarios
(see LZ4_compressBound(), it ensures compression success).
In case of failure, the API does not guarantee recovery,
so the state _must_ be reset.
To ensure compression success
whenever `dst` buffer size cannot be made >= LZ4_compressBound(),
consider using LZ4_compress_HC_continue_destSize().
Whenever previous input blocks can't be preserved unmodified in-place during compression of next blocks,
it's possible to copy the last blocks into a more stable memory space, using LZ4_saveDictHC().
Return value of LZ4_saveDictHC() is the size of dictionary effectively saved into 'safeBuffer' (<= 64 KB)
After completing a streaming compression,
it's possible to start a new stream of blocks, using the same LZ4_streamHC_t state,
just by resetting it, using LZ4_resetStreamHC_fast().
*/ */
LZ4LIB_API void LZ4_resetStreamHC_fast(LZ4_streamHC_t* streamHCPtr, int compressionLevel); /* v1.9.0+ */
LZ4LIB_API int LZ4_loadDictHC (LZ4_streamHC_t* streamHCPtr, const char* dictionary, int dictSize);
/************************************** LZ4LIB_API int LZ4_compress_HC_continue (LZ4_streamHC_t* streamHCPtr,
Using an external allocation const char* src, char* dst,
int srcSize, int maxDstSize);
/*! LZ4_compress_HC_continue_destSize() : v1.9.0+
* Similar to LZ4_compress_HC_continue(),
* but will read as much data as possible from `src`
* to fit into `targetDstSize` budget.
* Result is provided into 2 parts :
* @return : the number of bytes written into 'dst' (necessarily <= targetDstSize)
* or 0 if compression fails.
* `srcSizePtr` : on success, *srcSizePtr will be updated to indicate how much bytes were read from `src`.
* Note that this function may not consume the entire input.
*/
LZ4LIB_API int LZ4_compress_HC_continue_destSize(LZ4_streamHC_t* LZ4_streamHCPtr,
const char* src, char* dst,
int* srcSizePtr, int targetDstSize);
LZ4LIB_API int LZ4_saveDictHC (LZ4_streamHC_t* streamHCPtr, char* safeBuffer, int maxDictSize);
/*^**********************************************
* !!!!!! STATIC LINKING ONLY !!!!!!
***********************************************/
/*-******************************************************************
* PRIVATE DEFINITIONS :
* Do not use these definitions directly.
* They are merely exposed to allow static allocation of `LZ4_streamHC_t`.
* Declare an `LZ4_streamHC_t` directly, rather than any type below.
* Even then, only do so in the context of static linking, as definitions may change between versions.
********************************************************************/
#define LZ4HC_DICTIONARY_LOGSIZE 16
#define LZ4HC_MAXD (1<<LZ4HC_DICTIONARY_LOGSIZE)
#define LZ4HC_MAXD_MASK (LZ4HC_MAXD - 1)
#define LZ4HC_HASH_LOG 15
#define LZ4HC_HASHTABLESIZE (1 << LZ4HC_HASH_LOG)
#define LZ4HC_HASH_MASK (LZ4HC_HASHTABLESIZE - 1)
#if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */)
#include <stdint.h>
typedef struct LZ4HC_CCtx_internal LZ4HC_CCtx_internal;
struct LZ4HC_CCtx_internal
{
uint32_t hashTable[LZ4HC_HASHTABLESIZE];
uint16_t chainTable[LZ4HC_MAXD];
const uint8_t* end; /* next block here to continue on current prefix */
const uint8_t* base; /* All index relative to this position */
const uint8_t* dictBase; /* alternate base for extDict */
uint32_t dictLimit; /* below that point, need extDict */
uint32_t lowLimit; /* below that point, no more dict */
uint32_t nextToUpdate; /* index from which to continue dictionary update */
short compressionLevel;
int8_t favorDecSpeed; /* favor decompression speed if this flag set,
otherwise, favor compression ratio */
int8_t dirty; /* stream has to be fully reset if this flag is set */
const LZ4HC_CCtx_internal* dictCtx;
};
#else
typedef struct LZ4HC_CCtx_internal LZ4HC_CCtx_internal;
struct LZ4HC_CCtx_internal
{
unsigned int hashTable[LZ4HC_HASHTABLESIZE];
unsigned short chainTable[LZ4HC_MAXD];
const unsigned char* end; /* next block here to continue on current prefix */
const unsigned char* base; /* All index relative to this position */
const unsigned char* dictBase; /* alternate base for extDict */
unsigned int dictLimit; /* below that point, need extDict */
unsigned int lowLimit; /* below that point, no more dict */
unsigned int nextToUpdate; /* index from which to continue dictionary update */
short compressionLevel;
char favorDecSpeed; /* favor decompression speed if this flag set,
otherwise, favor compression ratio */
char dirty; /* stream has to be fully reset if this flag is set */
const LZ4HC_CCtx_internal* dictCtx;
};
#endif
/* Do not use these definitions directly !
* Declare or allocate an LZ4_streamHC_t instead.
*/
#define LZ4_STREAMHCSIZE (4*LZ4HC_HASHTABLESIZE + 2*LZ4HC_MAXD + 56 + ((sizeof(void*)==16) ? 56 : 0) /* AS400*/ ) /* 262200 or 262256*/
#define LZ4_STREAMHCSIZE_SIZET (LZ4_STREAMHCSIZE / sizeof(size_t))
union LZ4_streamHC_u {
size_t table[LZ4_STREAMHCSIZE_SIZET];
LZ4HC_CCtx_internal internal_donotuse;
}; /* previously typedef'd to LZ4_streamHC_t */
/* LZ4_streamHC_t :
* This structure allows static allocation of LZ4 HC streaming state.
* This can be used to allocate statically, on state, or as part of a larger structure.
*
* Such state **must** be initialized using LZ4_initStreamHC() before first use.
*
* Note that invoking LZ4_initStreamHC() is not required when
* the state was created using LZ4_createStreamHC() (which is recommended).
* Using the normal builder, a newly created state is automatically initialized.
*
* Static allocation shall only be used in combination with static linking.
*/
/* LZ4_initStreamHC() : v1.9.0+
* Required before first use of a statically allocated LZ4_streamHC_t.
* Before v1.9.0 : use LZ4_resetStreamHC() instead
*/
LZ4LIB_API LZ4_streamHC_t* LZ4_initStreamHC (void* buffer, size_t size);
/*-************************************
* Deprecated Functions
**************************************/ **************************************/
int LZ4_sizeofStateHC(void); /* see lz4.h LZ4_DISABLE_DEPRECATE_WARNINGS to turn off deprecation warnings */
int LZ4_compressHC_withStateHC (void* state, const char* source, char* dest, int inputSize);
int LZ4_compressHC_limitedOutput_withStateHC (void* state, const char* source, char* dest, int inputSize, int maxOutputSize);
int LZ4_compressHC2_withStateHC (void* state, const char* source, char* dest, int inputSize, int compressionLevel); /* deprecated compression functions */
int LZ4_compressHC2_limitedOutput_withStateHC(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel); LZ4_DEPRECATED("use LZ4_compress_HC() instead") LZ4LIB_API int LZ4_compressHC (const char* source, char* dest, int inputSize);
LZ4_DEPRECATED("use LZ4_compress_HC() instead") LZ4LIB_API int LZ4_compressHC_limitedOutput (const char* source, char* dest, int inputSize, int maxOutputSize);
LZ4_DEPRECATED("use LZ4_compress_HC() instead") LZ4LIB_API int LZ4_compressHC2 (const char* source, char* dest, int inputSize, int compressionLevel);
LZ4_DEPRECATED("use LZ4_compress_HC() instead") LZ4LIB_API int LZ4_compressHC2_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel);
LZ4_DEPRECATED("use LZ4_compress_HC_extStateHC() instead") LZ4LIB_API int LZ4_compressHC_withStateHC (void* state, const char* source, char* dest, int inputSize);
LZ4_DEPRECATED("use LZ4_compress_HC_extStateHC() instead") LZ4LIB_API int LZ4_compressHC_limitedOutput_withStateHC (void* state, const char* source, char* dest, int inputSize, int maxOutputSize);
LZ4_DEPRECATED("use LZ4_compress_HC_extStateHC() instead") LZ4LIB_API int LZ4_compressHC2_withStateHC (void* state, const char* source, char* dest, int inputSize, int compressionLevel);
LZ4_DEPRECATED("use LZ4_compress_HC_extStateHC() instead") LZ4LIB_API int LZ4_compressHC2_limitedOutput_withStateHC(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel);
LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") LZ4LIB_API int LZ4_compressHC_continue (LZ4_streamHC_t* LZ4_streamHCPtr, const char* source, char* dest, int inputSize);
LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") LZ4LIB_API int LZ4_compressHC_limitedOutput_continue (LZ4_streamHC_t* LZ4_streamHCPtr, const char* source, char* dest, int inputSize, int maxOutputSize);
/* /* Obsolete streaming functions; degraded functionality; do not use!
These functions are provided should you prefer to allocate memory for compression tables with your own allocation methods. *
To know how much memory must be allocated for the compression tables, use : * In order to perform streaming compression, these functions depended on data
int LZ4_sizeofStateHC(); * that is no longer tracked in the state. They have been preserved as well as
* possible: using them will still produce a correct output. However, use of
Note that tables must be aligned for pointer (32 or 64 bits), otherwise compression will fail (return code 0). * LZ4_slideInputBufferHC() will truncate the history of the stream, rather
* than preserve a window-sized chunk of history.
The allocated memory can be provided to the compressions functions using 'void* state' parameter. */
LZ4_compress_withStateHC() and LZ4_compress_limitedOutput_withStateHC() are equivalent to previously described functions. LZ4_DEPRECATED("use LZ4_createStreamHC() instead") LZ4LIB_API void* LZ4_createHC (const char* inputBuffer);
They just use the externally allocated memory area instead of allocating their own (on stack, or on heap). LZ4_DEPRECATED("use LZ4_saveDictHC() instead") LZ4LIB_API char* LZ4_slideInputBufferHC (void* LZ4HC_Data);
*/ LZ4_DEPRECATED("use LZ4_freeStreamHC() instead") LZ4LIB_API int LZ4_freeHC (void* LZ4HC_Data);
LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") LZ4LIB_API int LZ4_compressHC2_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int compressionLevel);
LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") LZ4LIB_API int LZ4_compressHC2_limitedOutput_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel);
LZ4_DEPRECATED("use LZ4_createStreamHC() instead") LZ4LIB_API int LZ4_sizeofStreamStateHC(void);
LZ4_DEPRECATED("use LZ4_initStreamHC() instead") LZ4LIB_API int LZ4_resetStreamStateHC(void* state, char* inputBuffer);
/************************************** /* LZ4_resetStreamHC() is now replaced by LZ4_initStreamHC().
Streaming Functions * The intention is to emphasize the difference with LZ4_resetStreamHC_fast(),
**************************************/ * which is now the recommended function to start a new stream of blocks,
/* Note : these streaming functions still follows the older model */ * but cannot be used to initialize a memory segment containing arbitrary garbage data.
void* LZ4_createHC (const char* inputBuffer); *
int LZ4_compressHC_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize); * It is recommended to switch to LZ4_initStreamHC().
int LZ4_compressHC_limitedOutput_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int maxOutputSize); * LZ4_resetStreamHC() will generate deprecation warnings in a future version.
char* LZ4_slideInputBufferHC (void* LZ4HC_Data); */
int LZ4_freeHC (void* LZ4HC_Data); LZ4LIB_API void LZ4_resetStreamHC (LZ4_streamHC_t* streamHCPtr, int compressionLevel);
int LZ4_compressHC2_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int compressionLevel);
int LZ4_compressHC2_limitedOutput_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel);
/*
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* inputBuffer);
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* inputBuffer' must, obviously, point at the beginning of input buffer.
The input buffer must be already allocated, and size at least 192KB.
'inputBuffer' 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 'inputBuffer'.
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.
*/
int LZ4_sizeofStreamStateHC(void);
int LZ4_resetStreamStateHC(void* state, const char* inputBuffer);
/*
These functions achieve the same result as :
void* LZ4_createHC (const char* inputBuffer);
They are provided here to allow the user program to allocate memory using its own routines.
To know how much space must be allocated, use LZ4_sizeofStreamStateHC();
Note also that space must be aligned for pointers (32 or 64 bits).
Once space is allocated, you must initialize it using : LZ4_resetStreamStateHC(void* state, const char* inputBuffer);
void* state is a pointer to the space allocated.
It must be aligned for pointers (32 or 64 bits), and be large enough.
The parameter 'const char* inputBuffer' must, obviously, point at the beginning of input buffer.
The input buffer must be already allocated, and size at least 192KB.
'inputBuffer' will also be the 'const char* source' of the first block.
The same space can be re-used multiple times, just by initializing it each time with LZ4_resetStreamState().
return value of LZ4_resetStreamStateHC() must be 0 is OK.
Any other value means there was an error (typically, state is not aligned for pointers (32 or 64 bits)).
*/
#if defined (__cplusplus) #if defined (__cplusplus)
} }
#endif #endif
#endif /* LZ4_HC_H_19834876238432 */
/*-**************************************************
* !!!!! STATIC LINKING ONLY !!!!!
* Following definitions are considered experimental.
* They should not be linked from DLL,
* as there is no guarantee of API stability yet.
* Prototypes will be promoted to "stable" status
* after successfull usage in real-life scenarios.
***************************************************/
#ifdef LZ4_HC_STATIC_LINKING_ONLY /* protection macro */
#ifndef LZ4_HC_SLO_098092834
#define LZ4_HC_SLO_098092834
#define LZ4_STATIC_LINKING_ONLY /* LZ4LIB_STATIC_API */
#include "lz4.h"
#if defined (__cplusplus)
extern "C" {
#endif
/*! LZ4_setCompressionLevel() : v1.8.0+ (experimental)
* It's possible to change compression level
* between successive invocations of LZ4_compress_HC_continue*()
* for dynamic adaptation.
*/
LZ4LIB_STATIC_API void LZ4_setCompressionLevel(
LZ4_streamHC_t* LZ4_streamHCPtr, int compressionLevel);
/*! LZ4_favorDecompressionSpeed() : v1.8.2+ (experimental)
* Opt. Parser will favor decompression speed over compression ratio.
* Only applicable to levels >= LZ4HC_CLEVEL_OPT_MIN.
*/
LZ4LIB_STATIC_API void LZ4_favorDecompressionSpeed(
LZ4_streamHC_t* LZ4_streamHCPtr, int favor);
/*! LZ4_resetStreamHC_fast() : v1.9.0+
* When an LZ4_streamHC_t is known to be in a internally coherent state,
* it can often be prepared for a new compression with almost no work, only
* sometimes falling back to the full, expensive reset that is always required
* when the stream is in an indeterminate state (i.e., the reset performed by
* LZ4_resetStreamHC()).
*
* LZ4_streamHCs are guaranteed to be in a valid state when:
* - returned from LZ4_createStreamHC()
* - reset by LZ4_resetStreamHC()
* - memset(stream, 0, sizeof(LZ4_streamHC_t))
* - the stream was in a valid state and was reset by LZ4_resetStreamHC_fast()
* - the stream was in a valid state and was then used in any compression call
* that returned success
* - the stream was in an indeterminate state and was used in a compression
* call that fully reset the state (LZ4_compress_HC_extStateHC()) and that
* returned success
*
* Note:
* A stream that was last used in a compression call that returned an error
* may be passed to this function. However, it will be fully reset, which will
* clear any existing history and settings from the context.
*/
LZ4LIB_STATIC_API void LZ4_resetStreamHC_fast(
LZ4_streamHC_t* LZ4_streamHCPtr, int compressionLevel);
/*! LZ4_compress_HC_extStateHC_fastReset() :
* A variant of LZ4_compress_HC_extStateHC().
*
* Using this variant avoids an expensive initialization step. It is only safe
* to call if the state buffer is known to be correctly initialized already
* (see above comment on LZ4_resetStreamHC_fast() for a definition of
* "correctly initialized"). From a high level, the difference is that this
* function initializes the provided state with a call to
* LZ4_resetStreamHC_fast() while LZ4_compress_HC_extStateHC() starts with a
* call to LZ4_resetStreamHC().
*/
LZ4LIB_STATIC_API int LZ4_compress_HC_extStateHC_fastReset (
void* state,
const char* src, char* dst,
int srcSize, int dstCapacity,
int compressionLevel);
/*! LZ4_attach_HC_dictionary() :
* This is an experimental API that allows for the efficient use of a
* static dictionary many times.
*
* Rather than re-loading the dictionary buffer into a working context before
* each compression, or copying a pre-loaded dictionary's LZ4_streamHC_t into a
* working LZ4_streamHC_t, this function introduces a no-copy setup mechanism,
* in which the working stream references the dictionary stream in-place.
*
* Several assumptions are made about the state of the dictionary stream.
* Currently, only streams which have been prepared by LZ4_loadDictHC() should
* be expected to work.
*
* Alternatively, the provided dictionary stream pointer may be NULL, in which
* case any existing dictionary stream is unset.
*
* A dictionary should only be attached to a stream without any history (i.e.,
* a stream that has just been reset).
*
* The dictionary will remain attached to the working stream only for the
* current stream session. Calls to LZ4_resetStreamHC(_fast) will remove the
* dictionary context association from the working stream. The dictionary
* stream (and source buffer) must remain in-place / accessible / unchanged
* through the lifetime of the stream session.
*/
LZ4LIB_STATIC_API void LZ4_attach_HC_dictionary(
LZ4_streamHC_t *working_stream,
const LZ4_streamHC_t *dictionary_stream);
#if defined (__cplusplus)
}
#endif
#endif /* LZ4_HC_SLO_098092834 */
#endif /* LZ4_HC_STATIC_LINKING_ONLY */

2
hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-nativetask/src/main/native/src/codec/Lz4Codec.cc
View File

@ -35,7 +35,7 @@ Lz4CompressStream::Lz4CompressStream(OutputStream * stream, uint32_t bufferSizeH
void Lz4CompressStream::compressOneBlock(const void * buff, uint32_t length) { void Lz4CompressStream::compressOneBlock(const void * buff, uint32_t length) {
size_t compressedLength = _tempBufferSize - 8; size_t compressedLength = _tempBufferSize - 8;
int ret = LZ4_compress((char*)buff, _tempBuffer + 8, length); int ret = LZ4_compress_default((char*)buff, _tempBuffer + 8, length, LZ4_compressBound(length));
if (ret > 0) { if (ret > 0) {
compressedLength = ret; compressedLength = ret;
((uint32_t*)_tempBuffer)[0] = bswap(length); ((uint32_t*)_tempBuffer)[0] = bswap(length);

2
hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-nativetask/src/main/native/test/TestCompressions.cc
View File

@ -185,7 +185,7 @@ void MeasureSingleFileLz4(const string & path, CompressResult & total, size_t bl
size_t currentblocksize = std::min(data.length() - start, blockSize); size_t currentblocksize = std::min(data.length() - start, blockSize);
uint64_t startTime = t.now(); uint64_t startTime = t.now();
for (int i = 0; i < times; i++) { for (int i = 0; i < times; i++) {
int osize = LZ4_compress((char*)data.data() + start, outputBuffer, currentblocksize); int osize = LZ4_compress_default((char*)data.data() + start, outputBuffer, currentblocksize, LZ4_compressBound(currentblocksize));
result.compressedSize += osize; result.compressedSize += osize;
result.uncompressedSize += currentblocksize; result.uncompressedSize += currentblocksize;
} }

6
licenses/LICENSE-lz4.txt
View File

@ -1,6 +1,6 @@
LZ4 - Fast LZ compression algorithm LZ4 - Fast LZ compression algorithm
Header File Header File
Copyright (C) 2011-2014, Yann Collet. Copyright (C) 2011-present, Yann Collet.
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
Redistribution and use in source and binary forms, with or without Redistribution and use in source and binary forms, with or without
@ -27,5 +27,5 @@
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
You can contact the author at : You can contact the author at :
- LZ4 source repository : http://code.google.com/p/lz4/ - LZ4 homepage : http://www.lz4.org
- LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c - LZ4 source repository : https://github.com/lz4/lz4