752 lines
26 KiB
C
752 lines
26 KiB
C
/*
|
|
LZ4 HC - High Compression Mode of LZ4
|
|
Copyright (C) 2011-2014, Yann Collet.
|
|
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
|
|
|
|
Redistribution and use in source and binary forms, with or without
|
|
modification, are permitted provided that the following conditions are
|
|
met:
|
|
|
|
* Redistributions of source code must retain the above copyright
|
|
notice, this list of conditions and the following disclaimer.
|
|
* Redistributions in binary form must reproduce the above
|
|
copyright notice, this list of conditions and the following disclaimer
|
|
in the documentation and/or other materials provided with the
|
|
distribution.
|
|
|
|
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
|
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
|
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
|
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
|
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
|
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
|
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
|
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
|
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
|
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
|
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
|
|
You can contact the author at :
|
|
- LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html
|
|
- LZ4 source repository : http://code.google.com/p/lz4/
|
|
*/
|
|
|
|
|
|
|
|
/**************************************
|
|
Tuning Parameter
|
|
**************************************/
|
|
static const int LZ4HC_compressionLevel_default = 8;
|
|
|
|
|
|
/**************************************
|
|
Includes
|
|
**************************************/
|
|
#include "lz4hc.h"
|
|
|
|
|
|
/**************************************
|
|
Local Compiler Options
|
|
**************************************/
|
|
#if defined(__GNUC__)
|
|
# pragma GCC diagnostic ignored "-Wunused-function"
|
|
#endif
|
|
|
|
#if defined (__clang__)
|
|
# pragma clang diagnostic ignored "-Wunused-function"
|
|
#endif
|
|
|
|
|
|
/**************************************
|
|
Common LZ4 definition
|
|
**************************************/
|
|
#define LZ4_COMMONDEFS_ONLY
|
|
#include "lz4.c"
|
|
|
|
|
|
/**************************************
|
|
Local Constants
|
|
**************************************/
|
|
#define DICTIONARY_LOGSIZE 16
|
|
#define MAXD (1<<DICTIONARY_LOGSIZE)
|
|
#define MAXD_MASK ((U32)(MAXD - 1))
|
|
|
|
#define HASH_LOG (DICTIONARY_LOGSIZE-1)
|
|
#define HASHTABLESIZE (1 << HASH_LOG)
|
|
#define HASH_MASK (HASHTABLESIZE - 1)
|
|
|
|
#define OPTIMAL_ML (int)((ML_MASK-1)+MINMATCH)
|
|
|
|
static const int g_maxCompressionLevel = 16;
|
|
|
|
|
|
/**************************************
|
|
Local Types
|
|
**************************************/
|
|
typedef struct
|
|
{
|
|
U32 hashTable[HASHTABLESIZE];
|
|
U16 chainTable[MAXD];
|
|
const BYTE* end; /* next block here to continue on current prefix */
|
|
const BYTE* base; /* All index relative to this position */
|
|
const BYTE* dictBase; /* alternate base for extDict */
|
|
const BYTE* inputBuffer;/* deprecated */
|
|
U32 dictLimit; /* below that point, need extDict */
|
|
U32 lowLimit; /* below that point, no more dict */
|
|
U32 nextToUpdate;
|
|
U32 compressionLevel;
|
|
} LZ4HC_Data_Structure;
|
|
|
|
|
|
/**************************************
|
|
Local Macros
|
|
**************************************/
|
|
#define HASH_FUNCTION(i) (((i) * 2654435761U) >> ((MINMATCH*8)-HASH_LOG))
|
|
#define DELTANEXT(p) chainTable[(size_t)(p) & MAXD_MASK]
|
|
#define GETNEXT(p) ((p) - (size_t)DELTANEXT(p))
|
|
|
|
static U32 LZ4HC_hashPtr(const void* ptr) { return HASH_FUNCTION(LZ4_read32(ptr)); }
|
|
|
|
|
|
|
|
/**************************************
|
|
HC Compression
|
|
**************************************/
|
|
static void LZ4HC_init (LZ4HC_Data_Structure* hc4, const BYTE* start)
|
|
{
|
|
MEM_INIT((void*)hc4->hashTable, 0, sizeof(hc4->hashTable));
|
|
MEM_INIT(hc4->chainTable, 0xFF, sizeof(hc4->chainTable));
|
|
hc4->nextToUpdate = 64 KB;
|
|
hc4->base = start - 64 KB;
|
|
hc4->inputBuffer = start;
|
|
hc4->end = start;
|
|
hc4->dictBase = start - 64 KB;
|
|
hc4->dictLimit = 64 KB;
|
|
hc4->lowLimit = 64 KB;
|
|
}
|
|
|
|
|
|
/* Update chains up to ip (excluded) */
|
|
FORCE_INLINE void LZ4HC_Insert (LZ4HC_Data_Structure* hc4, const BYTE* ip)
|
|
{
|
|
U16* chainTable = hc4->chainTable;
|
|
U32* HashTable = hc4->hashTable;
|
|
const BYTE* const base = hc4->base;
|
|
const U32 target = (U32)(ip - base);
|
|
U32 idx = hc4->nextToUpdate;
|
|
|
|
while(idx < target)
|
|
{
|
|
U32 h = LZ4HC_hashPtr(base+idx);
|
|
size_t delta = idx - HashTable[h];
|
|
if (delta>MAX_DISTANCE) delta = MAX_DISTANCE;
|
|
chainTable[idx & 0xFFFF] = (U16)delta;
|
|
HashTable[h] = idx;
|
|
idx++;
|
|
}
|
|
|
|
hc4->nextToUpdate = target;
|
|
}
|
|
|
|
|
|
FORCE_INLINE int LZ4HC_InsertAndFindBestMatch (LZ4HC_Data_Structure* hc4, /* Index table will be updated */
|
|
const BYTE* ip, const BYTE* const iLimit,
|
|
const BYTE** matchpos,
|
|
const int maxNbAttempts)
|
|
{
|
|
U16* const chainTable = hc4->chainTable;
|
|
U32* const HashTable = hc4->hashTable;
|
|
const BYTE* const base = hc4->base;
|
|
const BYTE* const dictBase = hc4->dictBase;
|
|
const U32 dictLimit = hc4->dictLimit;
|
|
const U32 lowLimit = (hc4->lowLimit + 64 KB > (U32)(ip-base)) ? hc4->lowLimit : (U32)(ip - base) - (64 KB - 1);
|
|
U32 matchIndex;
|
|
const BYTE* match;
|
|
int nbAttempts=maxNbAttempts;
|
|
size_t ml=0;
|
|
|
|
/* HC4 match finder */
|
|
LZ4HC_Insert(hc4, ip);
|
|
matchIndex = HashTable[LZ4HC_hashPtr(ip)];
|
|
|
|
while ((matchIndex>=lowLimit) && (nbAttempts))
|
|
{
|
|
nbAttempts--;
|
|
if (matchIndex >= dictLimit)
|
|
{
|
|
match = base + matchIndex;
|
|
if (*(match+ml) == *(ip+ml)
|
|
&& (LZ4_read32(match) == LZ4_read32(ip)))
|
|
{
|
|
size_t mlt = LZ4_count(ip+MINMATCH, match+MINMATCH, iLimit) + MINMATCH;
|
|
if (mlt > ml) { ml = mlt; *matchpos = match; }
|
|
}
|
|
}
|
|
else
|
|
{
|
|
match = dictBase + matchIndex;
|
|
if (LZ4_read32(match) == LZ4_read32(ip))
|
|
{
|
|
size_t mlt;
|
|
const BYTE* vLimit = ip + (dictLimit - matchIndex);
|
|
if (vLimit > iLimit) vLimit = iLimit;
|
|
mlt = LZ4_count(ip+MINMATCH, match+MINMATCH, vLimit) + MINMATCH;
|
|
if ((ip+mlt == vLimit) && (vLimit < iLimit))
|
|
mlt += LZ4_count(ip+mlt, base+dictLimit, iLimit);
|
|
if (mlt > ml) { ml = mlt; *matchpos = base + matchIndex; } /* virtual matchpos */
|
|
}
|
|
}
|
|
matchIndex -= chainTable[matchIndex & 0xFFFF];
|
|
}
|
|
|
|
return (int)ml;
|
|
}
|
|
|
|
|
|
FORCE_INLINE int LZ4HC_InsertAndGetWiderMatch (
|
|
LZ4HC_Data_Structure* hc4,
|
|
const BYTE* ip,
|
|
const BYTE* iLowLimit,
|
|
const BYTE* iHighLimit,
|
|
int longest,
|
|
const BYTE** matchpos,
|
|
const BYTE** startpos,
|
|
const int maxNbAttempts)
|
|
{
|
|
U16* const chainTable = hc4->chainTable;
|
|
U32* const HashTable = hc4->hashTable;
|
|
const BYTE* const base = hc4->base;
|
|
const U32 dictLimit = hc4->dictLimit;
|
|
const U32 lowLimit = (hc4->lowLimit + 64 KB > (U32)(ip-base)) ? hc4->lowLimit : (U32)(ip - base) - (64 KB - 1);
|
|
const BYTE* const dictBase = hc4->dictBase;
|
|
const BYTE* match;
|
|
U32 matchIndex;
|
|
int nbAttempts = maxNbAttempts;
|
|
int delta = (int)(ip-iLowLimit);
|
|
|
|
|
|
/* First Match */
|
|
LZ4HC_Insert(hc4, ip);
|
|
matchIndex = HashTable[LZ4HC_hashPtr(ip)];
|
|
|
|
while ((matchIndex>=lowLimit) && (nbAttempts))
|
|
{
|
|
nbAttempts--;
|
|
if (matchIndex >= dictLimit)
|
|
{
|
|
match = base + matchIndex;
|
|
if (*(iLowLimit + longest) == *(match - delta + longest))
|
|
if (LZ4_read32(match) == LZ4_read32(ip))
|
|
{
|
|
const BYTE* startt = ip;
|
|
const BYTE* tmpMatch = match;
|
|
const BYTE* const matchEnd = ip + MINMATCH + LZ4_count(ip+MINMATCH, match+MINMATCH, iHighLimit);
|
|
|
|
while ((startt>iLowLimit) && (tmpMatch > iLowLimit) && (startt[-1] == tmpMatch[-1])) {startt--; tmpMatch--;}
|
|
|
|
if ((matchEnd-startt) > longest)
|
|
{
|
|
longest = (int)(matchEnd-startt);
|
|
*matchpos = tmpMatch;
|
|
*startpos = startt;
|
|
}
|
|
}
|
|
}
|
|
else
|
|
{
|
|
match = dictBase + matchIndex;
|
|
if (LZ4_read32(match) == LZ4_read32(ip))
|
|
{
|
|
size_t mlt;
|
|
int back=0;
|
|
const BYTE* vLimit = ip + (dictLimit - matchIndex);
|
|
if (vLimit > iHighLimit) vLimit = iHighLimit;
|
|
mlt = LZ4_count(ip+MINMATCH, match+MINMATCH, vLimit) + MINMATCH;
|
|
if ((ip+mlt == vLimit) && (vLimit < iHighLimit))
|
|
mlt += LZ4_count(ip+mlt, base+dictLimit, iHighLimit);
|
|
while ((ip+back > iLowLimit) && (matchIndex+back > lowLimit) && (ip[back-1] == match[back-1])) back--;
|
|
mlt -= back;
|
|
if ((int)mlt > longest) { longest = (int)mlt; *matchpos = base + matchIndex + back; *startpos = ip+back; }
|
|
}
|
|
}
|
|
matchIndex -= chainTable[matchIndex & 0xFFFF];
|
|
}
|
|
|
|
return longest;
|
|
}
|
|
|
|
|
|
typedef enum { noLimit = 0, limitedOutput = 1 } limitedOutput_directive;
|
|
|
|
#define LZ4HC_DEBUG 0
|
|
#if LZ4HC_DEBUG
|
|
static unsigned debug = 0;
|
|
#endif
|
|
|
|
FORCE_INLINE int LZ4HC_encodeSequence (
|
|
const BYTE** ip,
|
|
BYTE** op,
|
|
const BYTE** anchor,
|
|
int matchLength,
|
|
const BYTE* const match,
|
|
limitedOutput_directive limitedOutputBuffer,
|
|
BYTE* oend)
|
|
{
|
|
int length;
|
|
BYTE* token;
|
|
|
|
#if LZ4HC_DEBUG
|
|
if (debug) printf("literal : %u -- match : %u -- offset : %u\n", (U32)(*ip - *anchor), (U32)matchLength, (U32)(*ip-match));
|
|
#endif
|
|
|
|
/* Encode Literal length */
|
|
length = (int)(*ip - *anchor);
|
|
token = (*op)++;
|
|
if ((limitedOutputBuffer) && ((*op + (length>>8) + length + (2 + 1 + LASTLITERALS)) > oend)) return 1; /* Check output limit */
|
|
if (length>=(int)RUN_MASK) { int len; *token=(RUN_MASK<<ML_BITS); len = length-RUN_MASK; for(; len > 254 ; len-=255) *(*op)++ = 255; *(*op)++ = (BYTE)len; }
|
|
else *token = (BYTE)(length<<ML_BITS);
|
|
|
|
/* Copy Literals */
|
|
LZ4_wildCopy(*op, *anchor, (*op) + length);
|
|
*op += length;
|
|
|
|
/* Encode Offset */
|
|
LZ4_writeLE16(*op, (U16)(*ip-match)); *op += 2;
|
|
|
|
/* Encode MatchLength */
|
|
length = (int)(matchLength-MINMATCH);
|
|
if ((limitedOutputBuffer) && (*op + (length>>8) + (1 + LASTLITERALS) > oend)) return 1; /* Check output limit */
|
|
if (length>=(int)ML_MASK) { *token+=ML_MASK; length-=ML_MASK; for(; length > 509 ; length-=510) { *(*op)++ = 255; *(*op)++ = 255; } if (length > 254) { length-=255; *(*op)++ = 255; } *(*op)++ = (BYTE)length; }
|
|
else *token += (BYTE)(length);
|
|
|
|
/* Prepare next loop */
|
|
*ip += matchLength;
|
|
*anchor = *ip;
|
|
|
|
return 0;
|
|
}
|
|
|
|
|
|
static int LZ4HC_compress_generic (
|
|
void* ctxvoid,
|
|
const char* source,
|
|
char* dest,
|
|
int inputSize,
|
|
int maxOutputSize,
|
|
int compressionLevel,
|
|
limitedOutput_directive limit
|
|
)
|
|
{
|
|
LZ4HC_Data_Structure* ctx = (LZ4HC_Data_Structure*) ctxvoid;
|
|
const BYTE* ip = (const BYTE*) source;
|
|
const BYTE* anchor = ip;
|
|
const BYTE* const iend = ip + inputSize;
|
|
const BYTE* const mflimit = iend - MFLIMIT;
|
|
const BYTE* const matchlimit = (iend - LASTLITERALS);
|
|
|
|
BYTE* op = (BYTE*) dest;
|
|
BYTE* const oend = op + maxOutputSize;
|
|
|
|
unsigned maxNbAttempts;
|
|
int ml, ml2, ml3, ml0;
|
|
const BYTE* ref=NULL;
|
|
const BYTE* start2=NULL;
|
|
const BYTE* ref2=NULL;
|
|
const BYTE* start3=NULL;
|
|
const BYTE* ref3=NULL;
|
|
const BYTE* start0;
|
|
const BYTE* ref0;
|
|
|
|
|
|
/* init */
|
|
if (compressionLevel > g_maxCompressionLevel) compressionLevel = g_maxCompressionLevel;
|
|
if (compressionLevel < 1) compressionLevel = LZ4HC_compressionLevel_default;
|
|
maxNbAttempts = 1 << (compressionLevel-1);
|
|
ctx->end += inputSize;
|
|
|
|
ip++;
|
|
|
|
/* Main Loop */
|
|
while (ip < mflimit)
|
|
{
|
|
ml = LZ4HC_InsertAndFindBestMatch (ctx, ip, matchlimit, (&ref), maxNbAttempts);
|
|
if (!ml) { ip++; continue; }
|
|
|
|
/* saved, in case we would skip too much */
|
|
start0 = ip;
|
|
ref0 = ref;
|
|
ml0 = ml;
|
|
|
|
_Search2:
|
|
if (ip+ml < mflimit)
|
|
ml2 = LZ4HC_InsertAndGetWiderMatch(ctx, ip + ml - 2, ip + 1, matchlimit, ml, &ref2, &start2, maxNbAttempts);
|
|
else ml2 = ml;
|
|
|
|
if (ml2 == ml) /* No better match */
|
|
{
|
|
if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml, ref, limit, oend)) return 0;
|
|
continue;
|
|
}
|
|
|
|
if (start0 < ip)
|
|
{
|
|
if (start2 < ip + ml0) /* empirical */
|
|
{
|
|
ip = start0;
|
|
ref = ref0;
|
|
ml = ml0;
|
|
}
|
|
}
|
|
|
|
/* Here, start0==ip */
|
|
if ((start2 - ip) < 3) /* First Match too small : removed */
|
|
{
|
|
ml = ml2;
|
|
ip = start2;
|
|
ref =ref2;
|
|
goto _Search2;
|
|
}
|
|
|
|
_Search3:
|
|
/*
|
|
* Currently we have :
|
|
* ml2 > ml1, and
|
|
* ip1+3 <= ip2 (usually < ip1+ml1)
|
|
*/
|
|
if ((start2 - ip) < OPTIMAL_ML)
|
|
{
|
|
int correction;
|
|
int new_ml = ml;
|
|
if (new_ml > OPTIMAL_ML) new_ml = OPTIMAL_ML;
|
|
if (ip+new_ml > start2 + ml2 - MINMATCH) new_ml = (int)(start2 - ip) + ml2 - MINMATCH;
|
|
correction = new_ml - (int)(start2 - ip);
|
|
if (correction > 0)
|
|
{
|
|
start2 += correction;
|
|
ref2 += correction;
|
|
ml2 -= correction;
|
|
}
|
|
}
|
|
/* Now, we have start2 = ip+new_ml, with new_ml = min(ml, OPTIMAL_ML=18) */
|
|
|
|
if (start2 + ml2 < mflimit)
|
|
ml3 = LZ4HC_InsertAndGetWiderMatch(ctx, start2 + ml2 - 3, start2, matchlimit, ml2, &ref3, &start3, maxNbAttempts);
|
|
else ml3 = ml2;
|
|
|
|
if (ml3 == ml2) /* No better match : 2 sequences to encode */
|
|
{
|
|
/* ip & ref are known; Now for ml */
|
|
if (start2 < ip+ml) ml = (int)(start2 - ip);
|
|
/* Now, encode 2 sequences */
|
|
if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml, ref, limit, oend)) return 0;
|
|
ip = start2;
|
|
if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml2, ref2, limit, oend)) return 0;
|
|
continue;
|
|
}
|
|
|
|
if (start3 < ip+ml+3) /* Not enough space for match 2 : remove it */
|
|
{
|
|
if (start3 >= (ip+ml)) /* can write Seq1 immediately ==> Seq2 is removed, so Seq3 becomes Seq1 */
|
|
{
|
|
if (start2 < ip+ml)
|
|
{
|
|
int correction = (int)(ip+ml - start2);
|
|
start2 += correction;
|
|
ref2 += correction;
|
|
ml2 -= correction;
|
|
if (ml2 < MINMATCH)
|
|
{
|
|
start2 = start3;
|
|
ref2 = ref3;
|
|
ml2 = ml3;
|
|
}
|
|
}
|
|
|
|
if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml, ref, limit, oend)) return 0;
|
|
ip = start3;
|
|
ref = ref3;
|
|
ml = ml3;
|
|
|
|
start0 = start2;
|
|
ref0 = ref2;
|
|
ml0 = ml2;
|
|
goto _Search2;
|
|
}
|
|
|
|
start2 = start3;
|
|
ref2 = ref3;
|
|
ml2 = ml3;
|
|
goto _Search3;
|
|
}
|
|
|
|
/*
|
|
* OK, now we have 3 ascending matches; let's write at least the first one
|
|
* ip & ref are known; Now for ml
|
|
*/
|
|
if (start2 < ip+ml)
|
|
{
|
|
if ((start2 - ip) < (int)ML_MASK)
|
|
{
|
|
int correction;
|
|
if (ml > OPTIMAL_ML) ml = OPTIMAL_ML;
|
|
if (ip + ml > start2 + ml2 - MINMATCH) ml = (int)(start2 - ip) + ml2 - MINMATCH;
|
|
correction = ml - (int)(start2 - ip);
|
|
if (correction > 0)
|
|
{
|
|
start2 += correction;
|
|
ref2 += correction;
|
|
ml2 -= correction;
|
|
}
|
|
}
|
|
else
|
|
{
|
|
ml = (int)(start2 - ip);
|
|
}
|
|
}
|
|
if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml, ref, limit, oend)) return 0;
|
|
|
|
ip = start2;
|
|
ref = ref2;
|
|
ml = ml2;
|
|
|
|
start2 = start3;
|
|
ref2 = ref3;
|
|
ml2 = ml3;
|
|
|
|
goto _Search3;
|
|
}
|
|
|
|
/* Encode Last Literals */
|
|
{
|
|
int lastRun = (int)(iend - anchor);
|
|
if ((limit) && (((char*)op - dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize)) return 0; /* Check output limit */
|
|
if (lastRun>=(int)RUN_MASK) { *op++=(RUN_MASK<<ML_BITS); lastRun-=RUN_MASK; for(; lastRun > 254 ; lastRun-=255) *op++ = 255; *op++ = (BYTE) lastRun; }
|
|
else *op++ = (BYTE)(lastRun<<ML_BITS);
|
|
memcpy(op, anchor, iend - anchor);
|
|
op += iend-anchor;
|
|
}
|
|
|
|
/* End */
|
|
return (int) (((char*)op)-dest);
|
|
}
|
|
|
|
|
|
int LZ4_compressHC2(const char* source, char* dest, int inputSize, int compressionLevel)
|
|
{
|
|
LZ4HC_Data_Structure ctx;
|
|
LZ4HC_init(&ctx, (const BYTE*)source);
|
|
return LZ4HC_compress_generic (&ctx, source, dest, inputSize, 0, compressionLevel, noLimit);
|
|
}
|
|
|
|
int LZ4_compressHC(const char* source, char* dest, int inputSize) { return LZ4_compressHC2(source, dest, inputSize, 0); }
|
|
|
|
int LZ4_compressHC2_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel)
|
|
{
|
|
LZ4HC_Data_Structure ctx;
|
|
LZ4HC_init(&ctx, (const BYTE*)source);
|
|
return LZ4HC_compress_generic (&ctx, source, dest, inputSize, maxOutputSize, compressionLevel, limitedOutput);
|
|
}
|
|
|
|
int LZ4_compressHC_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize)
|
|
{
|
|
return LZ4_compressHC2_limitedOutput(source, dest, inputSize, maxOutputSize, 0);
|
|
}
|
|
|
|
|
|
/*****************************
|
|
* Using external allocation
|
|
* ***************************/
|
|
int LZ4_sizeofStateHC(void) { return sizeof(LZ4HC_Data_Structure); }
|
|
|
|
|
|
int LZ4_compressHC2_withStateHC (void* state, const char* source, char* dest, int inputSize, int compressionLevel)
|
|
{
|
|
if (((size_t)(state)&(sizeof(void*)-1)) != 0) return 0; /* Error : state is not aligned for pointers (32 or 64 bits) */
|
|
LZ4HC_init ((LZ4HC_Data_Structure*)state, (const BYTE*)source);
|
|
return LZ4HC_compress_generic (state, source, dest, inputSize, 0, compressionLevel, noLimit);
|
|
}
|
|
|
|
int LZ4_compressHC_withStateHC (void* state, const char* source, char* dest, int inputSize)
|
|
{ return LZ4_compressHC2_withStateHC (state, source, dest, inputSize, 0); }
|
|
|
|
|
|
int LZ4_compressHC2_limitedOutput_withStateHC (void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel)
|
|
{
|
|
if (((size_t)(state)&(sizeof(void*)-1)) != 0) return 0; /* Error : state is not aligned for pointers (32 or 64 bits) */
|
|
LZ4HC_init ((LZ4HC_Data_Structure*)state, (const BYTE*)source);
|
|
return LZ4HC_compress_generic (state, source, dest, inputSize, maxOutputSize, compressionLevel, limitedOutput);
|
|
}
|
|
|
|
int LZ4_compressHC_limitedOutput_withStateHC (void* state, const char* source, char* dest, int inputSize, int maxOutputSize)
|
|
{ return LZ4_compressHC2_limitedOutput_withStateHC (state, source, dest, inputSize, maxOutputSize, 0); }
|
|
|
|
|
|
|
|
/**************************************
|
|
* Streaming Functions
|
|
* ************************************/
|
|
/* allocation */
|
|
LZ4_streamHC_t* LZ4_createStreamHC(void) { return (LZ4_streamHC_t*)malloc(sizeof(LZ4_streamHC_t)); }
|
|
int LZ4_freeStreamHC (LZ4_streamHC_t* LZ4_streamHCPtr) { free(LZ4_streamHCPtr); return 0; }
|
|
|
|
|
|
/* initialization */
|
|
void LZ4_resetStreamHC (LZ4_streamHC_t* LZ4_streamHCPtr, int compressionLevel)
|
|
{
|
|
LZ4_STATIC_ASSERT(sizeof(LZ4HC_Data_Structure) <= LZ4_STREAMHCSIZE); /* if compilation fails here, LZ4_STREAMHCSIZE must be increased */
|
|
((LZ4HC_Data_Structure*)LZ4_streamHCPtr)->base = NULL;
|
|
((LZ4HC_Data_Structure*)LZ4_streamHCPtr)->compressionLevel = (unsigned)compressionLevel;
|
|
}
|
|
|
|
int LZ4_loadDictHC (LZ4_streamHC_t* LZ4_streamHCPtr, const char* dictionary, int dictSize)
|
|
{
|
|
LZ4HC_Data_Structure* ctxPtr = (LZ4HC_Data_Structure*) LZ4_streamHCPtr;
|
|
if (dictSize > 64 KB)
|
|
{
|
|
dictionary += dictSize - 64 KB;
|
|
dictSize = 64 KB;
|
|
}
|
|
LZ4HC_init (ctxPtr, (const BYTE*)dictionary);
|
|
if (dictSize >= 4) LZ4HC_Insert (ctxPtr, (const BYTE*)dictionary +(dictSize-3));
|
|
ctxPtr->end = (const BYTE*)dictionary + dictSize;
|
|
return dictSize;
|
|
}
|
|
|
|
|
|
/* compression */
|
|
|
|
static void LZ4HC_setExternalDict(LZ4HC_Data_Structure* ctxPtr, const BYTE* newBlock)
|
|
{
|
|
if (ctxPtr->end >= ctxPtr->base + 4)
|
|
LZ4HC_Insert (ctxPtr, ctxPtr->end-3); /* Referencing remaining dictionary content */
|
|
/* Only one memory segment for extDict, so any previous extDict is lost at this stage */
|
|
ctxPtr->lowLimit = ctxPtr->dictLimit;
|
|
ctxPtr->dictLimit = (U32)(ctxPtr->end - ctxPtr->base);
|
|
ctxPtr->dictBase = ctxPtr->base;
|
|
ctxPtr->base = newBlock - ctxPtr->dictLimit;
|
|
ctxPtr->end = newBlock;
|
|
ctxPtr->nextToUpdate = ctxPtr->dictLimit; /* match referencing will resume from there */
|
|
}
|
|
|
|
static int LZ4_compressHC_continue_generic (LZ4HC_Data_Structure* ctxPtr,
|
|
const char* source, char* dest,
|
|
int inputSize, int maxOutputSize, limitedOutput_directive limit)
|
|
{
|
|
/* auto-init if forgotten */
|
|
if (ctxPtr->base == NULL)
|
|
LZ4HC_init (ctxPtr, (const BYTE*) source);
|
|
|
|
/* Check overflow */
|
|
if ((size_t)(ctxPtr->end - ctxPtr->base) > 2 GB)
|
|
{
|
|
size_t dictSize = (size_t)(ctxPtr->end - ctxPtr->base) - ctxPtr->dictLimit;
|
|
if (dictSize > 64 KB) dictSize = 64 KB;
|
|
|
|
LZ4_loadDictHC((LZ4_streamHC_t*)ctxPtr, (const char*)(ctxPtr->end) - dictSize, (int)dictSize);
|
|
}
|
|
|
|
/* Check if blocks follow each other */
|
|
if ((const BYTE*)source != ctxPtr->end) LZ4HC_setExternalDict(ctxPtr, (const BYTE*)source);
|
|
|
|
/* Check overlapping input/dictionary space */
|
|
{
|
|
const BYTE* sourceEnd = (const BYTE*) source + inputSize;
|
|
const BYTE* dictBegin = ctxPtr->dictBase + ctxPtr->lowLimit;
|
|
const BYTE* dictEnd = ctxPtr->dictBase + ctxPtr->dictLimit;
|
|
if ((sourceEnd > dictBegin) && ((BYTE*)source < dictEnd))
|
|
{
|
|
if (sourceEnd > dictEnd) sourceEnd = dictEnd;
|
|
ctxPtr->lowLimit = (U32)(sourceEnd - ctxPtr->dictBase);
|
|
if (ctxPtr->dictLimit - ctxPtr->lowLimit < 4) ctxPtr->lowLimit = ctxPtr->dictLimit;
|
|
}
|
|
}
|
|
|
|
return LZ4HC_compress_generic (ctxPtr, source, dest, inputSize, maxOutputSize, ctxPtr->compressionLevel, limit);
|
|
}
|
|
|
|
int LZ4_compressHC_continue (LZ4_streamHC_t* LZ4_streamHCPtr, const char* source, char* dest, int inputSize)
|
|
{
|
|
return LZ4_compressHC_continue_generic ((LZ4HC_Data_Structure*)LZ4_streamHCPtr, source, dest, inputSize, 0, noLimit);
|
|
}
|
|
|
|
int LZ4_compressHC_limitedOutput_continue (LZ4_streamHC_t* LZ4_streamHCPtr, const char* source, char* dest, int inputSize, int maxOutputSize)
|
|
{
|
|
return LZ4_compressHC_continue_generic ((LZ4HC_Data_Structure*)LZ4_streamHCPtr, source, dest, inputSize, maxOutputSize, limitedOutput);
|
|
}
|
|
|
|
|
|
/* dictionary saving */
|
|
|
|
int LZ4_saveDictHC (LZ4_streamHC_t* LZ4_streamHCPtr, char* safeBuffer, int dictSize)
|
|
{
|
|
LZ4HC_Data_Structure* streamPtr = (LZ4HC_Data_Structure*)LZ4_streamHCPtr;
|
|
int prefixSize = (int)(streamPtr->end - (streamPtr->base + streamPtr->dictLimit));
|
|
if (dictSize > 64 KB) dictSize = 64 KB;
|
|
if (dictSize < 4) dictSize = 0;
|
|
if (dictSize > prefixSize) dictSize = prefixSize;
|
|
memcpy(safeBuffer, streamPtr->end - dictSize, dictSize);
|
|
{
|
|
U32 endIndex = (U32)(streamPtr->end - streamPtr->base);
|
|
streamPtr->end = (const BYTE*)safeBuffer + dictSize;
|
|
streamPtr->base = streamPtr->end - endIndex;
|
|
streamPtr->dictLimit = endIndex - dictSize;
|
|
streamPtr->lowLimit = endIndex - dictSize;
|
|
if (streamPtr->nextToUpdate < streamPtr->dictLimit) streamPtr->nextToUpdate = streamPtr->dictLimit;
|
|
}
|
|
return dictSize;
|
|
}
|
|
|
|
|
|
/***********************************
|
|
* Deprecated Functions
|
|
***********************************/
|
|
int LZ4_sizeofStreamStateHC(void) { return LZ4_STREAMHCSIZE; }
|
|
|
|
int LZ4_resetStreamStateHC(void* state, const char* inputBuffer)
|
|
{
|
|
if ((((size_t)state) & (sizeof(void*)-1)) != 0) return 1; /* Error : pointer is not aligned for pointer (32 or 64 bits) */
|
|
LZ4HC_init((LZ4HC_Data_Structure*)state, (const BYTE*)inputBuffer);
|
|
return 0;
|
|
}
|
|
|
|
void* LZ4_createHC (const char* inputBuffer)
|
|
{
|
|
void* hc4 = ALLOCATOR(1, sizeof(LZ4HC_Data_Structure));
|
|
LZ4HC_init ((LZ4HC_Data_Structure*)hc4, (const BYTE*)inputBuffer);
|
|
return hc4;
|
|
}
|
|
|
|
int LZ4_freeHC (void* LZ4HC_Data)
|
|
{
|
|
FREEMEM(LZ4HC_Data);
|
|
return (0);
|
|
}
|
|
|
|
/*
|
|
int LZ4_compressHC_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize)
|
|
{
|
|
return LZ4HC_compress_generic (LZ4HC_Data, source, dest, inputSize, 0, 0, noLimit);
|
|
}
|
|
int LZ4_compressHC_limitedOutput_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int maxOutputSize)
|
|
{
|
|
return LZ4HC_compress_generic (LZ4HC_Data, source, dest, inputSize, maxOutputSize, 0, limitedOutput);
|
|
}
|
|
*/
|
|
|
|
int LZ4_compressHC2_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int compressionLevel)
|
|
{
|
|
return LZ4HC_compress_generic (LZ4HC_Data, source, dest, inputSize, 0, compressionLevel, noLimit);
|
|
}
|
|
|
|
int LZ4_compressHC2_limitedOutput_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel)
|
|
{
|
|
return LZ4HC_compress_generic (LZ4HC_Data, source, dest, inputSize, maxOutputSize, compressionLevel, limitedOutput);
|
|
}
|
|
|
|
char* LZ4_slideInputBufferHC(void* LZ4HC_Data)
|
|
{
|
|
LZ4HC_Data_Structure* hc4 = (LZ4HC_Data_Structure*)LZ4HC_Data;
|
|
int dictSize = LZ4_saveDictHC((LZ4_streamHC_t*)LZ4HC_Data, (char*)(hc4->inputBuffer), 64 KB);
|
|
return (char*)(hc4->inputBuffer + dictSize);
|
|
}
|