From 944d0d22852696d25e0b749961ab25236a92d45f Mon Sep 17 00:00:00 2001 From: Yann Collet Date: Fri, 4 Mar 2016 19:26:59 +0100 Subject: [PATCH] updated fse version --- lib/fse.c | 53 +++++++++--------- lib/fse.h | 164 ++++++++++++++++++++++++------------------------------ 2 files changed, 100 insertions(+), 117 deletions(-) diff --git a/lib/fse.c b/lib/fse.c index 986a0da15..a445f3285 100644 --- a/lib/fse.c +++ b/lib/fse.c @@ -628,12 +628,12 @@ size_t FSE_count(unsigned* count, unsigned* maxSymbolValuePtr, /*-************************************************************** * FSE Compression Code ****************************************************************/ -/*! -FSE_CTable is a variable size structure which contains : - U16 tableLog; - U16 maxSymbolValue; - U16 nextStateNumber[1 << tableLog]; // This size is variable - FSE_symbolCompressionTransform symbolTT[maxSymbolValue+1]; // This size is variable +/*! FSE_sizeof_CTable() : + FSE_CTable is a variable size structure which contains : + `U16 tableLog;` + `U16 maxSymbolValue;` + `U16 nextStateNumber[1 << tableLog];` // This size is variable + `FSE_symbolCompressionTransform symbolTT[maxSymbolValue+1];` // This size is variable Allocation is manual, since C standard does not support variable-size structures. */ @@ -654,10 +654,7 @@ FSE_CTable* FSE_createCTable (unsigned maxSymbolValue, unsigned tableLog) return (FSE_CTable*)malloc(size); } -void FSE_freeCTable (FSE_CTable* ct) -{ - free(ct); -} +void FSE_freeCTable (FSE_CTable* ct) { free(ct); } /* provides the minimum logSize to safely represent a distribution */ static unsigned FSE_minTableLog(size_t srcSize, unsigned maxSymbolValue) @@ -888,31 +885,32 @@ static size_t FSE_compress_usingCTable_generic (void* dst, size_t dstSize, const FSE_CTable* ct, const unsigned fast) { const BYTE* const istart = (const BYTE*) src; - const BYTE* ip; const BYTE* const iend = istart + srcSize; + const BYTE* ip=iend; size_t errorCode; BIT_CStream_t bitC; FSE_CState_t CState1, CState2; - /* init */ + if (srcSize <= 2) return 0; errorCode = BIT_initCStream(&bitC, dst, dstSize); if (FSE_isError(errorCode)) return 0; - FSE_initCState(&CState1, ct); - CState2 = CState1; - - ip=iend; #define FSE_FLUSHBITS(s) (fast ? BIT_flushBitsFast(s) : BIT_flushBits(s)) - /* join to even */ if (srcSize & 1) { + FSE_initCState2(&CState1, ct, *--ip); + FSE_initCState2(&CState2, ct, *--ip); FSE_encodeSymbol(&bitC, &CState1, *--ip); FSE_FLUSHBITS(&bitC); + } else { + FSE_initCState2(&CState2, ct, *--ip); + FSE_initCState2(&CState1, ct, *--ip); } /* join to mod 4 */ + srcSize -= 2; if ((sizeof(bitC.bitContainer)*8 > FSE_MAX_TABLELOG*4+7 ) && (srcSize & 2)) { /* test bit 2 */ FSE_encodeSymbol(&bitC, &CState2, *--ip); FSE_encodeSymbol(&bitC, &CState1, *--ip); @@ -1106,24 +1104,25 @@ FORCE_INLINE size_t FSE_decompress_usingDTable_generic( /* tail */ /* note : BIT_reloadDStream(&bitD) >= FSE_DStream_partiallyFilled; Ends at exactly BIT_DStream_completed */ while (1) { - if ( (BIT_reloadDStream(&bitD)>BIT_DStream_completed) || (op==omax) || (BIT_endOfDStream(&bitD) && (fast || FSE_endOfDState(&state1))) ) - break; + if (op>(omax-2)) return ERROR(dstSize_tooSmall); *op++ = FSE_GETSYMBOL(&state1); - if ( (BIT_reloadDStream(&bitD)>BIT_DStream_completed) || (op==omax) || (BIT_endOfDStream(&bitD) && (fast || FSE_endOfDState(&state2))) ) + if (BIT_reloadDStream(&bitD)==BIT_DStream_overflow) { + *op++ = FSE_GETSYMBOL(&state2); break; + } + + if (op>(omax-2)) return ERROR(dstSize_tooSmall); *op++ = FSE_GETSYMBOL(&state2); - } - /* end ? */ - if (BIT_endOfDStream(&bitD) && FSE_endOfDState(&state1) && FSE_endOfDState(&state2)) - return op-ostart; + if (BIT_reloadDStream(&bitD)==BIT_DStream_overflow) { + *op++ = FSE_GETSYMBOL(&state1); + break; + } } - if (op==omax) return ERROR(dstSize_tooSmall); /* dst buffer is full, but cSrc unfinished */ - - return ERROR(corruption_detected); + return op-ostart; } diff --git a/lib/fse.h b/lib/fse.h index db6f49cfa..6dce68300 100644 --- a/lib/fse.h +++ b/lib/fse.h @@ -1,7 +1,7 @@ /* ****************************************************************** - FSE : Finite State Entropy coder - header file - Copyright (C) 2013-2015, Yann Collet. + FSE : Finite State Entropy codec + Public Prototypes declaration + Copyright (C) 2013-2016, Yann Collet. BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) @@ -30,7 +30,6 @@ You can contact the author at : - Source repository : https://github.com/Cyan4973/FiniteStateEntropy - - Public forum : https://groups.google.com/forum/#!forum/lz4c ****************************************************************** */ #ifndef FSE_H #define FSE_H @@ -40,8 +39,8 @@ extern "C" { #endif -/* ***************************************** -* Includes +/*-***************************************** +* Dependencies ******************************************/ #include /* size_t, ptrdiff_t */ @@ -49,32 +48,32 @@ extern "C" { /*-**************************************** * FSE simple functions ******************************************/ -size_t FSE_compress(void* dst, size_t maxDstSize, - const void* src, size_t srcSize); -size_t FSE_decompress(void* dst, size_t maxDstSize, - const void* cSrc, size_t cSrcSize); -/*! -FSE_compress(): +/*! FSE_compress() : Compress content of buffer 'src', of size 'srcSize', into destination buffer 'dst'. - 'dst' buffer must be already allocated. Compression runs faster is maxDstSize >= FSE_compressBound(srcSize) - return : size of compressed data (<= maxDstSize) + 'dst' buffer must be already allocated. Compression runs faster is dstCapacity >= FSE_compressBound(srcSize). + @return : size of compressed data (<= dstCapacity). Special values : if return == 0, srcData is not compressible => Nothing is stored within dst !!! if return == 1, srcData is a single byte symbol * srcSize times. Use RLE compression instead. if FSE_isError(return), compression failed (more details using FSE_getErrorName()) +*/ +size_t FSE_compress(void* dst, size_t dstCapacity, + const void* src, size_t srcSize); -FSE_decompress(): +/*! FSE_decompress(): Decompress FSE data from buffer 'cSrc', of size 'cSrcSize', - into already allocated destination buffer 'dst', of size 'maxDstSize'. - return : size of regenerated data (<= maxDstSize) - or an error code, which can be tested using FSE_isError() + into already allocated destination buffer 'dst', of size 'dstCapacity'. + @return : size of regenerated data (<= maxDstSize), + or an error code, which can be tested using FSE_isError() . - ** Important ** : FSE_decompress() doesn't decompress non-compressible nor RLE data !!! + ** Important ** : FSE_decompress() does not decompress non-compressible nor RLE data !!! Why ? : making this distinction requires a header. Header management is intentionally delegated to the user layer, which can better manage special cases. */ +size_t FSE_decompress(void* dst, size_t dstCapacity, + const void* cSrc, size_t cSrcSize); -/* ***************************************** +/*-***************************************** * Tool functions ******************************************/ size_t FSE_compressBound(size_t size); /* maximum compressed size */ @@ -84,14 +83,13 @@ unsigned FSE_isError(size_t code); /* tells if a return value is an er const char* FSE_getErrorName(size_t code); /* provides error code string (useful for debugging) */ -/* ***************************************** +/*-***************************************** * FSE advanced functions ******************************************/ -/*! -FSE_compress2(): +/*! FSE_compress2() : Same as FSE_compress(), but allows the selection of 'maxSymbolValue' and 'tableLog' Both parameters can be defined as '0' to mean : use default value - return : size of compressed data + @return : size of compressed data Special values : if return == 0, srcData is not compressible => Nothing is stored within cSrc !!! if return == 1, srcData is a single byte symbol * srcSize times. Use RLE compression. if FSE_isError(return), it's an error code. @@ -99,7 +97,7 @@ FSE_compress2(): size_t FSE_compress2 (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog); -/* ***************************************** +/*-***************************************** * FSE detailed API ******************************************/ /*! @@ -122,65 +120,56 @@ or to save and provide normalized distribution using external method. /* *** COMPRESSION *** */ -/*! -FSE_count(): - Provides the precise count of each byte within a table 'count' - 'count' is a table of unsigned int, of minimum size (*maxSymbolValuePtr+1). - *maxSymbolValuePtr will be updated if detected smaller than initial value. - @return : the count of the most frequent symbol (which is not identified) - if return == srcSize, there is only one symbol. - Can also return an error code, which can be tested with FSE_isError() */ +/*! FSE_count(): + Provides the precise count of each byte within a table 'count'. + 'count' is a table of unsigned int, of minimum size (*maxSymbolValuePtr+1). + *maxSymbolValuePtr will be updated if detected smaller than initial value. + @return : the count of the most frequent symbol (which is not identified). + if return == srcSize, there is only one symbol. + Can also return an error code, which can be tested with FSE_isError(). */ size_t FSE_count(unsigned* count, unsigned* maxSymbolValuePtr, const void* src, size_t srcSize); -/*! -FSE_optimalTableLog(): - dynamically downsize 'tableLog' when conditions are met. - It saves CPU time, by using smaller tables, while preserving or even improving compression ratio. - return : recommended tableLog (necessarily <= initial 'tableLog') */ +/*! FSE_optimalTableLog(): + dynamically downsize 'tableLog' when conditions are met. + It saves CPU time, by using smaller tables, while preserving or even improving compression ratio. + @return : recommended tableLog (necessarily <= initial 'tableLog') */ unsigned FSE_optimalTableLog(unsigned tableLog, size_t srcSize, unsigned maxSymbolValue); -/*! -FSE_normalizeCount(): - normalize counters so that sum(count[]) == Power_of_2 (2^tableLog) - 'normalizedCounter' is a table of short, of minimum size (maxSymbolValue+1). - return : tableLog, - or an errorCode, which can be tested using FSE_isError() */ +/*! FSE_normalizeCount(): + normalize counts so that sum(count[]) == Power_of_2 (2^tableLog) + 'normalizedCounter' is a table of short, of minimum size (maxSymbolValue+1). + @return : tableLog, + or an errorCode, which can be tested using FSE_isError() */ size_t FSE_normalizeCount(short* normalizedCounter, unsigned tableLog, const unsigned* count, size_t srcSize, unsigned maxSymbolValue); -/*! -FSE_NCountWriteBound(): - Provides the maximum possible size of an FSE normalized table, given 'maxSymbolValue' and 'tableLog' - Typically useful for allocation purpose. */ +/*! FSE_NCountWriteBound(): + Provides the maximum possible size of an FSE normalized table, given 'maxSymbolValue' and 'tableLog'. + Typically useful for allocation purpose. */ size_t FSE_NCountWriteBound(unsigned maxSymbolValue, unsigned tableLog); -/*! -FSE_writeNCount(): - Compactly save 'normalizedCounter' into 'buffer'. - return : size of the compressed table - or an errorCode, which can be tested using FSE_isError() */ +/*! FSE_writeNCount(): + Compactly save 'normalizedCounter' into 'buffer'. + @return : size of the compressed table, + or an errorCode, which can be tested using FSE_isError(). */ size_t FSE_writeNCount (void* buffer, size_t bufferSize, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog); -/*! -Constructor and Destructor of type FSE_CTable - Note that its size depends on 'tableLog' and 'maxSymbolValue' */ +/*! Constructor and Destructor of FSE_CTable. + Note that FSE_CTable size depends on 'tableLog' and 'maxSymbolValue' */ typedef unsigned FSE_CTable; /* don't allocate that. It's only meant to be more restrictive than void* */ FSE_CTable* FSE_createCTable (unsigned tableLog, unsigned maxSymbolValue); void FSE_freeCTable (FSE_CTable* ct); -/*! -FSE_buildCTable(): - Builds @ct, which must be already allocated, using FSE_createCTable() - return : 0 - or an errorCode, which can be tested using FSE_isError() */ +/*! FSE_buildCTable(): + Builds `ct`, which must be already allocated, using FSE_createCTable(). + @return : 0, or an errorCode, which can be tested using FSE_isError() */ size_t FSE_buildCTable(FSE_CTable* ct, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog); -/*! -FSE_compress_usingCTable(): - Compress @src using @ct into @dst which must be already allocated - return : size of compressed data (<= @dstCapacity) - or 0 if compressed data could not fit into @dst - or an errorCode, which can be tested using FSE_isError() */ +/*! FSE_compress_usingCTable(): + Compress `src` using `ct` into `dst` which must be already allocated. + @return : size of compressed data (<= `dstCapacity`), + or 0 if compressed data could not fit into `dst`, + or an errorCode, which can be tested using FSE_isError() */ size_t FSE_compress_usingCTable (void* dst, size_t dstCapacity, const void* src, size_t srcSize, const FSE_CTable* ct); /*! @@ -221,7 +210,7 @@ If there is an error, both functions will return an ErrorCode (which can be test 'CTable' can then be used to compress 'src', with FSE_compress_usingCTable(). Similar to FSE_count(), the convention is that 'src' is assumed to be a table of char of size 'srcSize' -The function returns the size of compressed data (without header), necessarily <= @dstCapacity. +The function returns the size of compressed data (without header), necessarily <= `dstCapacity`. If it returns '0', compressed data could not fit into 'dst'. If there is an error, the function will return an ErrorCode (which can be tested using FSE_isError()). */ @@ -229,34 +218,29 @@ If there is an error, the function will return an ErrorCode (which can be tested /* *** DECOMPRESSION *** */ -/*! -FSE_readNCount(): - Read compactly saved 'normalizedCounter' from 'rBuffer'. - return : size read from 'rBuffer' - or an errorCode, which can be tested using FSE_isError() - maxSymbolValuePtr[0] and tableLogPtr[0] will also be updated with their respective values */ +/*! FSE_readNCount(): + Read compactly saved 'normalizedCounter' from 'rBuffer'. + @return : size read from 'rBuffer', + or an errorCode, which can be tested using FSE_isError(). + maxSymbolValuePtr[0] and tableLogPtr[0] will also be updated with their respective values */ size_t FSE_readNCount (short* normalizedCounter, unsigned* maxSymbolValuePtr, unsigned* tableLogPtr, const void* rBuffer, size_t rBuffSize); -/*! -Constructor and Destructor of type FSE_DTable +/*! Constructor and Destructor of FSE_DTable. Note that its size depends on 'tableLog' */ typedef unsigned FSE_DTable; /* don't allocate that. It's just a way to be more restrictive than void* */ FSE_DTable* FSE_createDTable(unsigned tableLog); void FSE_freeDTable(FSE_DTable* dt); -/*! -FSE_buildDTable(): - Builds 'dt', which must be already allocated, using FSE_createDTable() - return : 0, - or an errorCode, which can be tested using FSE_isError() */ +/*! FSE_buildDTable(): + Builds 'dt', which must be already allocated, using FSE_createDTable(). + return : 0, or an errorCode, which can be tested using FSE_isError() */ size_t FSE_buildDTable (FSE_DTable* dt, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog); -/*! -FSE_decompress_usingDTable(): - Decompress compressed source @cSrc of size @cSrcSize using @dt - into @dst which must be already allocated. - return : size of regenerated data (necessarily <= @dstCapacity) - or an errorCode, which can be tested using FSE_isError() */ +/*! FSE_decompress_usingDTable(): + Decompress compressed source `cSrc` of size `cSrcSize` using `dt` + into `dst` which must be already allocated. + @return : size of regenerated data (necessarily <= `dstCapacity`), + or an errorCode, which can be tested using FSE_isError() */ size_t FSE_decompress_usingDTable(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, const FSE_DTable* dt); /*! @@ -281,9 +265,9 @@ This is performed by the function FSE_buildDTable(). The space required by 'FSE_DTable' must be already allocated using FSE_createDTable(). If there is an error, the function will return an error code, which can be tested using FSE_isError(). -'FSE_DTable' can then be used to decompress 'cSrc', with FSE_decompress_usingDTable(). -'cSrcSize' must be strictly correct, otherwise decompression will fail. -FSE_decompress_usingDTable() result will tell how many bytes were regenerated (<=maxDstSize). +`FSE_DTable` can then be used to decompress `cSrc`, with FSE_decompress_usingDTable(). +`cSrcSize` must be strictly correct, otherwise decompression will fail. +FSE_decompress_usingDTable() result will tell how many bytes were regenerated (<=`dstCapacity`). If there is an error, the function will return an error code, which can be tested using FSE_isError(). (ex: dst buffer too small) */