facebook/zstd
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Fixes

Browse Source
This commit is contained in:
Nick Terrell 2018-05-22 16:06:33 -07:00
parent 49cf880513
commit e3959d5eba
4 changed files with 74 additions and 78 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
lib/common/fse.h
View File

@ -402,7 +402,6 @@ typedef struct {
const void* stateTable; const void* stateTable;
const void* symbolTT; const void* symbolTT;
unsigned stateLog; unsigned stateLog;
unsigned maxSymbolValue;
} FSE_CState_t; } FSE_CState_t;
static void FSE_initCState(FSE_CState_t* CStatePtr, const FSE_CTable* ct); static void FSE_initCState(FSE_CState_t* CStatePtr, const FSE_CTable* ct);
@ -539,13 +538,11 @@ MEM_STATIC void FSE_initCState(FSE_CState_t* statePtr, const FSE_CTable* ct)
{ {
const void* ptr = ct; const void* ptr = ct;
const U16* u16ptr = (const U16*) ptr; const U16* u16ptr = (const U16*) ptr;
const U32 tableLog = MEM_read16(u16ptr); const U32 tableLog = MEM_read16(ptr);
const U32 maxSymbolValue = MEM_read16(u16ptr + 1);
statePtr->value = (ptrdiff_t)1<<tableLog; statePtr->value = (ptrdiff_t)1<<tableLog;
statePtr->stateTable = u16ptr+2; statePtr->stateTable = u16ptr+2;
statePtr->symbolTT = ((const U32*)ct + 1 + (tableLog ? (1<<(tableLog-1)) : 1)); statePtr->symbolTT = ((const U32*)ct + 1 + (tableLog ? (1<<(tableLog-1)) : 1));
statePtr->stateLog = tableLog; statePtr->stateLog = tableLog;
statePtr->maxSymbolValue = maxSymbolValue;
} }

109
lib/compress/zstd_compress.c
View File

@ -946,10 +946,10 @@ static void ZSTD_reset_compressedBlockState(ZSTD_compressedBlockState_t* bs)
int i; int i;
for (i = 0; i < ZSTD_REP_NUM; ++i) for (i = 0; i < ZSTD_REP_NUM; ++i)
bs->rep[i] = repStartValue[i]; bs->rep[i] = repStartValue[i];
bs->entropy.hufCTable_repeatMode = HUF_repeat_none; bs->entropy.huf.repeatMode = HUF_repeat_none;
bs->entropy.offcode_repeatMode = FSE_repeat_none; bs->entropy.fse.offcode_repeatMode = FSE_repeat_none;
bs->entropy.matchlength_repeatMode = FSE_repeat_none; bs->entropy.fse.matchlength_repeatMode = FSE_repeat_none;
bs->entropy.litlength_repeatMode = FSE_repeat_none; bs->entropy.fse.litlength_repeatMode = FSE_repeat_none;
} }
/*! ZSTD_invalidateMatchState() /*! ZSTD_invalidateMatchState()
@ -1455,8 +1455,8 @@ static size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, cons
static size_t ZSTD_minGain(size_t srcSize) { return (srcSize >> 6) + 2; } static size_t ZSTD_minGain(size_t srcSize) { return (srcSize >> 6) + 2; }
static size_t ZSTD_compressLiterals (ZSTD_entropyCTables_t const* prevEntropy, static size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf,
ZSTD_entropyCTables_t* nextEntropy, ZSTD_hufCTables_t* nextHuf,
ZSTD_strategy strategy, int disableLiteralCompression, ZSTD_strategy strategy, int disableLiteralCompression,
void* dst, size_t dstCapacity, void* dst, size_t dstCapacity,
const void* src, size_t srcSize, const void* src, size_t srcSize,
@ -1473,27 +1473,25 @@ static size_t ZSTD_compressLiterals (ZSTD_entropyCTables_t const* prevEntropy,
disableLiteralCompression); disableLiteralCompression);
/* Prepare nextEntropy assuming reusing the existing table */ /* Prepare nextEntropy assuming reusing the existing table */
nextEntropy->hufCTable_repeatMode = prevEntropy->hufCTable_repeatMode; memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
memcpy(nextEntropy->hufCTable, prevEntropy->hufCTable,
sizeof(prevEntropy->hufCTable));
if (disableLiteralCompression) if (disableLiteralCompression)
return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize); return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
/* small ? don't even attempt compression (speed opt) */ /* small ? don't even attempt compression (speed opt) */
# define COMPRESS_LITERALS_SIZE_MIN 63 # define COMPRESS_LITERALS_SIZE_MIN 63
{ size_t const minLitSize = (prevEntropy->hufCTable_repeatMode == HUF_repeat_valid) ? 6 : COMPRESS_LITERALS_SIZE_MIN; { size_t const minLitSize = (prevHuf->repeatMode == HUF_repeat_valid) ? 6 : COMPRESS_LITERALS_SIZE_MIN;
if (srcSize <= minLitSize) return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize); if (srcSize <= minLitSize) return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
} }
if (dstCapacity < lhSize+1) return ERROR(dstSize_tooSmall); /* not enough space for compression */ if (dstCapacity < lhSize+1) return ERROR(dstSize_tooSmall); /* not enough space for compression */
{ HUF_repeat repeat = prevEntropy->hufCTable_repeatMode; { HUF_repeat repeat = prevHuf->repeatMode;
int const preferRepeat = strategy < ZSTD_lazy ? srcSize <= 1024 : 0; int const preferRepeat = strategy < ZSTD_lazy ? srcSize <= 1024 : 0;
if (repeat == HUF_repeat_valid && lhSize == 3) singleStream = 1; if (repeat == HUF_repeat_valid && lhSize == 3) singleStream = 1;
cLitSize = singleStream ? HUF_compress1X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11, cLitSize = singleStream ? HUF_compress1X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11,
workspace, HUF_WORKSPACE_SIZE, (HUF_CElt*)nextEntropy->hufCTable, &repeat, preferRepeat, bmi2) workspace, HUF_WORKSPACE_SIZE, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2)
: HUF_compress4X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11, : HUF_compress4X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11,
workspace, HUF_WORKSPACE_SIZE, (HUF_CElt*)nextEntropy->hufCTable, &repeat, preferRepeat, bmi2); workspace, HUF_WORKSPACE_SIZE, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2);
if (repeat != HUF_repeat_none) { if (repeat != HUF_repeat_none) {
/* reused the existing table */ /* reused the existing table */
hType = set_repeat; hType = set_repeat;
@ -1501,17 +1499,17 @@ static size_t ZSTD_compressLiterals (ZSTD_entropyCTables_t const* prevEntropy,
} }
if ((cLitSize==0) | (cLitSize >= srcSize - minGain) | ERR_isError(cLitSize)) { if ((cLitSize==0) | (cLitSize >= srcSize - minGain) | ERR_isError(cLitSize)) {
memcpy(nextEntropy->hufCTable, prevEntropy->hufCTable, sizeof(prevEntropy->hufCTable)); memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize); return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
} }
if (cLitSize==1) { if (cLitSize==1) {
memcpy(nextEntropy->hufCTable, prevEntropy->hufCTable, sizeof(prevEntropy->hufCTable)); memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
return ZSTD_compressRleLiteralsBlock(dst, dstCapacity, src, srcSize); return ZSTD_compressRleLiteralsBlock(dst, dstCapacity, src, srcSize);
} }
if (hType == set_compressed) { if (hType == set_compressed) {
/* using a newly constructed table */ /* using a newly constructed table */
nextEntropy->hufCTable_repeatMode = HUF_repeat_check; nextHuf->repeatMode = HUF_repeat_check;
} }
/* Build header */ /* Build header */
@ -1635,6 +1633,14 @@ static size_t ZSTD_crossEntropyCost(short const* norm, unsigned accuracyLog,
} }
static unsigned ZSTD_getFSEMaxSymbolValue(FSE_CTable const* ctable) {
void const* ptr = ctable;
U16 const* u16ptr = (U16 const*)ptr;
U32 const maxSymbolValue = MEM_read16(u16ptr + 1);
return maxSymbolValue;
}
/** /**
* Returns the cost in bits of encoding the distribution in count using ctable. * Returns the cost in bits of encoding the distribution in count using ctable.
* Returns an error if ctable cannot represent all the symbols in count. * Returns an error if ctable cannot represent all the symbols in count.
@ -1649,9 +1655,9 @@ static size_t ZSTD_fseBitCost(
unsigned s; unsigned s;
FSE_CState_t cstate; FSE_CState_t cstate;
FSE_initCState(&cstate, ctable); FSE_initCState(&cstate, ctable);
if (cstate.maxSymbolValue < max) { if (ZSTD_getFSEMaxSymbolValue(ctable) < max) {
DEBUGLOG(5, "Repeat FSE_CTable has maxSymbolValue %u < %u", DEBUGLOG(5, "Repeat FSE_CTable has maxSymbolValue %u < %u",
cstate.maxSymbolValue, max); ZSTD_getFSEMaxSymbolValue(ctable), max);
return ERROR(GENERIC); return ERROR(GENERIC);
} }
for (s = 0; s <= max; ++s) { for (s = 0; s <= max; ++s) {
@ -1964,9 +1970,9 @@ MEM_STATIC size_t ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
const int longOffsets = cctxParams->cParams.windowLog > STREAM_ACCUMULATOR_MIN; const int longOffsets = cctxParams->cParams.windowLog > STREAM_ACCUMULATOR_MIN;
ZSTD_strategy const strategy = cctxParams->cParams.strategy; ZSTD_strategy const strategy = cctxParams->cParams.strategy;
U32 count[MaxSeq+1]; U32 count[MaxSeq+1];
FSE_CTable* CTable_LitLength = nextEntropy->litlengthCTable; FSE_CTable* CTable_LitLength = nextEntropy->fse.litlengthCTable;
FSE_CTable* CTable_OffsetBits = nextEntropy->offcodeCTable; FSE_CTable* CTable_OffsetBits = nextEntropy->fse.offcodeCTable;
FSE_CTable* CTable_MatchLength = nextEntropy->matchlengthCTable; FSE_CTable* CTable_MatchLength = nextEntropy->fse.matchlengthCTable;
U32 LLtype, Offtype, MLtype; /* compressed, raw or rle */ U32 LLtype, Offtype, MLtype; /* compressed, raw or rle */
const seqDef* const sequences = seqStorePtr->sequencesStart; const seqDef* const sequences = seqStorePtr->sequencesStart;
const BYTE* const ofCodeTable = seqStorePtr->ofCode; const BYTE* const ofCodeTable = seqStorePtr->ofCode;
@ -1984,7 +1990,7 @@ MEM_STATIC size_t ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
{ const BYTE* const literals = seqStorePtr->litStart; { const BYTE* const literals = seqStorePtr->litStart;
size_t const litSize = seqStorePtr->lit - literals; size_t const litSize = seqStorePtr->lit - literals;
size_t const cSize = ZSTD_compressLiterals( size_t const cSize = ZSTD_compressLiterals(
prevEntropy, nextEntropy, &prevEntropy->huf, &nextEntropy->huf,
cctxParams->cParams.strategy, cctxParams->disableLiteralCompression, cctxParams->cParams.strategy, cctxParams->disableLiteralCompression,
op, dstCapacity, op, dstCapacity,
literals, litSize, literals, litSize,
@ -2004,19 +2010,8 @@ MEM_STATIC size_t ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
else else
op[0]=0xFF, MEM_writeLE16(op+1, (U16)(nbSeq - LONGNBSEQ)), op+=3; op[0]=0xFF, MEM_writeLE16(op+1, (U16)(nbSeq - LONGNBSEQ)), op+=3;
if (nbSeq==0) { if (nbSeq==0) {
/* Check that all the Huffman data is first */ /* Copy the old tables over as if we repeated them */
ZSTD_STATIC_ASSERT(offsetof(ZSTD_entropyCTables_t, hufCTable) == 0); memcpy(&nextEntropy->fse, &prevEntropy->fse, sizeof(prevEntropy->fse));
ZSTD_STATIC_ASSERT(
offsetof(ZSTD_entropyCTables_t, hufCTable_repeatMode) ==
sizeof(prevEntropy->hufCTable));
ZSTD_STATIC_ASSERT(
offsetof(ZSTD_entropyCTables_t, offcodeCTable) ==
sizeof(prevEntropy->hufCTable) + sizeof(prevEntropy->hufCTable_repeatMode));
/* Copy starting at the first FSE element */
memcpy(
nextEntropy->offcodeCTable,
prevEntropy->offcodeCTable,
sizeof(*prevEntropy) - offsetof(ZSTD_entropyCTables_t, offcodeCTable));
return op - ostart; return op - ostart;
} }
@ -2029,13 +2024,13 @@ MEM_STATIC size_t ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
{ U32 max = MaxLL; { U32 max = MaxLL;
size_t const mostFrequent = FSE_countFast_wksp(count, &max, llCodeTable, nbSeq, workspace); size_t const mostFrequent = FSE_countFast_wksp(count, &max, llCodeTable, nbSeq, workspace);
DEBUGLOG(5, "Building LL table"); DEBUGLOG(5, "Building LL table");
nextEntropy->litlength_repeatMode = prevEntropy->litlength_repeatMode; nextEntropy->fse.litlength_repeatMode = prevEntropy->fse.litlength_repeatMode;
LLtype = ZSTD_selectEncodingType(&nextEntropy->litlength_repeatMode, count, max, mostFrequent, nbSeq, LLFSELog, prevEntropy->litlengthCTable, LL_defaultNorm, LL_defaultNormLog, ZSTD_defaultAllowed, strategy); LLtype = ZSTD_selectEncodingType(&nextEntropy->fse.litlength_repeatMode, count, max, mostFrequent, nbSeq, LLFSELog, prevEntropy->fse.litlengthCTable, LL_defaultNorm, LL_defaultNormLog, ZSTD_defaultAllowed, strategy);
assert(set_basic < set_compressed && set_rle < set_compressed); assert(set_basic < set_compressed && set_rle < set_compressed);
assert(!(LLtype < set_compressed && nextEntropy->litlength_repeatMode != FSE_repeat_none)); /* We don't copy tables */ assert(!(LLtype < set_compressed && nextEntropy->fse.litlength_repeatMode != FSE_repeat_none)); /* We don't copy tables */
{ size_t const countSize = ZSTD_buildCTable(op, oend - op, CTable_LitLength, LLFSELog, (symbolEncodingType_e)LLtype, { size_t const countSize = ZSTD_buildCTable(op, oend - op, CTable_LitLength, LLFSELog, (symbolEncodingType_e)LLtype,
count, max, llCodeTable, nbSeq, LL_defaultNorm, LL_defaultNormLog, MaxLL, count, max, llCodeTable, nbSeq, LL_defaultNorm, LL_defaultNormLog, MaxLL,
prevEntropy->litlengthCTable, sizeof(prevEntropy->litlengthCTable), prevEntropy->fse.litlengthCTable, sizeof(prevEntropy->fse.litlengthCTable),
workspace, HUF_WORKSPACE_SIZE); workspace, HUF_WORKSPACE_SIZE);
if (ZSTD_isError(countSize)) return countSize; if (ZSTD_isError(countSize)) return countSize;
op += countSize; op += countSize;
@ -2046,12 +2041,12 @@ MEM_STATIC size_t ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
/* We can only use the basic table if max <= DefaultMaxOff, otherwise the offsets are too large */ /* We can only use the basic table if max <= DefaultMaxOff, otherwise the offsets are too large */
ZSTD_defaultPolicy_e const defaultPolicy = (max <= DefaultMaxOff) ? ZSTD_defaultAllowed : ZSTD_defaultDisallowed; ZSTD_defaultPolicy_e const defaultPolicy = (max <= DefaultMaxOff) ? ZSTD_defaultAllowed : ZSTD_defaultDisallowed;
DEBUGLOG(5, "Building OF table"); DEBUGLOG(5, "Building OF table");
nextEntropy->offcode_repeatMode = prevEntropy->offcode_repeatMode; nextEntropy->fse.offcode_repeatMode = prevEntropy->fse.offcode_repeatMode;
Offtype = ZSTD_selectEncodingType(&nextEntropy->offcode_repeatMode, count, max, mostFrequent, nbSeq, OffFSELog, prevEntropy->offcodeCTable, OF_defaultNorm, OF_defaultNormLog, defaultPolicy, strategy); Offtype = ZSTD_selectEncodingType(&nextEntropy->fse.offcode_repeatMode, count, max, mostFrequent, nbSeq, OffFSELog, prevEntropy->fse.offcodeCTable, OF_defaultNorm, OF_defaultNormLog, defaultPolicy, strategy);
assert(!(Offtype < set_compressed && nextEntropy->offcode_repeatMode != FSE_repeat_none)); /* We don't copy tables */ assert(!(Offtype < set_compressed && nextEntropy->fse.offcode_repeatMode != FSE_repeat_none)); /* We don't copy tables */
{ size_t const countSize = ZSTD_buildCTable(op, oend - op, CTable_OffsetBits, OffFSELog, (symbolEncodingType_e)Offtype, { size_t const countSize = ZSTD_buildCTable(op, oend - op, CTable_OffsetBits, OffFSELog, (symbolEncodingType_e)Offtype,
count, max, ofCodeTable, nbSeq, OF_defaultNorm, OF_defaultNormLog, DefaultMaxOff, count, max, ofCodeTable, nbSeq, OF_defaultNorm, OF_defaultNormLog, DefaultMaxOff,
prevEntropy->offcodeCTable, sizeof(prevEntropy->offcodeCTable), prevEntropy->fse.offcodeCTable, sizeof(prevEntropy->fse.offcodeCTable),
workspace, HUF_WORKSPACE_SIZE); workspace, HUF_WORKSPACE_SIZE);
if (ZSTD_isError(countSize)) return countSize; if (ZSTD_isError(countSize)) return countSize;
op += countSize; op += countSize;
@ -2060,12 +2055,12 @@ MEM_STATIC size_t ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
{ U32 max = MaxML; { U32 max = MaxML;
size_t const mostFrequent = FSE_countFast_wksp(count, &max, mlCodeTable, nbSeq, workspace); size_t const mostFrequent = FSE_countFast_wksp(count, &max, mlCodeTable, nbSeq, workspace);
DEBUGLOG(5, "Building ML table"); DEBUGLOG(5, "Building ML table");
nextEntropy->matchlength_repeatMode = prevEntropy->matchlength_repeatMode; nextEntropy->fse.matchlength_repeatMode = prevEntropy->fse.matchlength_repeatMode;
MLtype = ZSTD_selectEncodingType(&nextEntropy->matchlength_repeatMode, count, max, mostFrequent, nbSeq, MLFSELog, prevEntropy->matchlengthCTable, ML_defaultNorm, ML_defaultNormLog, ZSTD_defaultAllowed, strategy); MLtype = ZSTD_selectEncodingType(&nextEntropy->fse.matchlength_repeatMode, count, max, mostFrequent, nbSeq, MLFSELog, prevEntropy->fse.matchlengthCTable, ML_defaultNorm, ML_defaultNormLog, ZSTD_defaultAllowed, strategy);
assert(!(MLtype < set_compressed && nextEntropy->matchlength_repeatMode != FSE_repeat_none)); /* We don't copy tables */ assert(!(MLtype < set_compressed && nextEntropy->fse.matchlength_repeatMode != FSE_repeat_none)); /* We don't copy tables */
{ size_t const countSize = ZSTD_buildCTable(op, oend - op, CTable_MatchLength, MLFSELog, (symbolEncodingType_e)MLtype, { size_t const countSize = ZSTD_buildCTable(op, oend - op, CTable_MatchLength, MLFSELog, (symbolEncodingType_e)MLtype,
count, max, mlCodeTable, nbSeq, ML_defaultNorm, ML_defaultNormLog, MaxML, count, max, mlCodeTable, nbSeq, ML_defaultNorm, ML_defaultNormLog, MaxML,
prevEntropy->matchlengthCTable, sizeof(prevEntropy->matchlengthCTable), prevEntropy->fse.matchlengthCTable, sizeof(prevEntropy->fse.matchlengthCTable),
workspace, HUF_WORKSPACE_SIZE); workspace, HUF_WORKSPACE_SIZE);
if (ZSTD_isError(countSize)) return countSize; if (ZSTD_isError(countSize)) return countSize;
op += countSize; op += countSize;
@ -2113,8 +2108,8 @@ MEM_STATIC size_t ZSTD_compressSequences(seqStore_t* seqStorePtr,
* block. After the first block, the offcode table might not have large * block. After the first block, the offcode table might not have large
* enough codes to represent the offsets in the data. * enough codes to represent the offsets in the data.
*/ */
if (nextEntropy->offcode_repeatMode == FSE_repeat_valid) if (nextEntropy->fse.offcode_repeatMode == FSE_repeat_valid)
nextEntropy->offcode_repeatMode = FSE_repeat_check; nextEntropy->fse.offcode_repeatMode = FSE_repeat_check;
return cSize; return cSize;
} }
@ -2555,7 +2550,7 @@ static size_t ZSTD_loadZstdDictionary(ZSTD_compressedBlockState_t* bs,
dictPtr += 4; dictPtr += 4;
{ unsigned maxSymbolValue = 255; { unsigned maxSymbolValue = 255;
size_t const hufHeaderSize = HUF_readCTable((HUF_CElt*)bs->entropy.hufCTable, &maxSymbolValue, dictPtr, dictEnd-dictPtr); size_t const hufHeaderSize = HUF_readCTable((HUF_CElt*)bs->entropy.huf.CTable, &maxSymbolValue, dictPtr, dictEnd-dictPtr);
if (HUF_isError(hufHeaderSize)) return ERROR(dictionary_corrupted); if (HUF_isError(hufHeaderSize)) return ERROR(dictionary_corrupted);
if (maxSymbolValue < 255) return ERROR(dictionary_corrupted); if (maxSymbolValue < 255) return ERROR(dictionary_corrupted);
dictPtr += hufHeaderSize; dictPtr += hufHeaderSize;
@ -2567,7 +2562,7 @@ static size_t ZSTD_loadZstdDictionary(ZSTD_compressedBlockState_t* bs,
if (offcodeLog > OffFSELog) return ERROR(dictionary_corrupted); if (offcodeLog > OffFSELog) return ERROR(dictionary_corrupted);
/* Defer checking offcodeMaxValue because we need to know the size of the dictionary content */ /* Defer checking offcodeMaxValue because we need to know the size of the dictionary content */
/* fill all offset symbols to avoid garbage at end of table */ /* fill all offset symbols to avoid garbage at end of table */
CHECK_E( FSE_buildCTable_wksp(bs->entropy.offcodeCTable, offcodeNCount, MaxOff, offcodeLog, workspace, HUF_WORKSPACE_SIZE), CHECK_E( FSE_buildCTable_wksp(bs->entropy.fse.offcodeCTable, offcodeNCount, MaxOff, offcodeLog, workspace, HUF_WORKSPACE_SIZE),
dictionary_corrupted); dictionary_corrupted);
dictPtr += offcodeHeaderSize; dictPtr += offcodeHeaderSize;
} }
@ -2579,7 +2574,7 @@ static size_t ZSTD_loadZstdDictionary(ZSTD_compressedBlockState_t* bs,
if (matchlengthLog > MLFSELog) return ERROR(dictionary_corrupted); if (matchlengthLog > MLFSELog) return ERROR(dictionary_corrupted);
/* Every match length code must have non-zero probability */ /* Every match length code must have non-zero probability */
CHECK_F( ZSTD_checkDictNCount(matchlengthNCount, matchlengthMaxValue, MaxML)); CHECK_F( ZSTD_checkDictNCount(matchlengthNCount, matchlengthMaxValue, MaxML));
CHECK_E( FSE_buildCTable_wksp(bs->entropy.matchlengthCTable, matchlengthNCount, matchlengthMaxValue, matchlengthLog, workspace, HUF_WORKSPACE_SIZE), CHECK_E( FSE_buildCTable_wksp(bs->entropy.fse.matchlengthCTable, matchlengthNCount, matchlengthMaxValue, matchlengthLog, workspace, HUF_WORKSPACE_SIZE),
dictionary_corrupted); dictionary_corrupted);
dictPtr += matchlengthHeaderSize; dictPtr += matchlengthHeaderSize;
} }
@ -2591,7 +2586,7 @@ static size_t ZSTD_loadZstdDictionary(ZSTD_compressedBlockState_t* bs,
if (litlengthLog > LLFSELog) return ERROR(dictionary_corrupted); if (litlengthLog > LLFSELog) return ERROR(dictionary_corrupted);
/* Every literal length code must have non-zero probability */ /* Every literal length code must have non-zero probability */
CHECK_F( ZSTD_checkDictNCount(litlengthNCount, litlengthMaxValue, MaxLL)); CHECK_F( ZSTD_checkDictNCount(litlengthNCount, litlengthMaxValue, MaxLL));
CHECK_E( FSE_buildCTable_wksp(bs->entropy.litlengthCTable, litlengthNCount, litlengthMaxValue, litlengthLog, workspace, HUF_WORKSPACE_SIZE), CHECK_E( FSE_buildCTable_wksp(bs->entropy.fse.litlengthCTable, litlengthNCount, litlengthMaxValue, litlengthLog, workspace, HUF_WORKSPACE_SIZE),
dictionary_corrupted); dictionary_corrupted);
dictPtr += litlengthHeaderSize; dictPtr += litlengthHeaderSize;
} }
@ -2617,10 +2612,10 @@ static size_t ZSTD_loadZstdDictionary(ZSTD_compressedBlockState_t* bs,
if (bs->rep[u] > dictContentSize) return ERROR(dictionary_corrupted); if (bs->rep[u] > dictContentSize) return ERROR(dictionary_corrupted);
} } } }
bs->entropy.hufCTable_repeatMode = HUF_repeat_valid; bs->entropy.huf.repeatMode = HUF_repeat_valid;
bs->entropy.offcode_repeatMode = FSE_repeat_valid; bs->entropy.fse.offcode_repeatMode = FSE_repeat_valid;
bs->entropy.matchlength_repeatMode = FSE_repeat_valid; bs->entropy.fse.matchlength_repeatMode = FSE_repeat_valid;
bs->entropy.litlength_repeatMode = FSE_repeat_valid; bs->entropy.fse.litlength_repeatMode = FSE_repeat_valid;
CHECK_F(ZSTD_loadDictionaryContent(ms, params, dictPtr, dictContentSize, dtlm)); CHECK_F(ZSTD_loadDictionaryContent(ms, params, dictPtr, dictContentSize, dtlm));
return dictID; return dictID;
} }

16
lib/compress/zstd_compress_internal.h
View File

@ -53,18 +53,22 @@ typedef struct ZSTD_prefixDict_s {
} ZSTD_prefixDict; } ZSTD_prefixDict;
typedef struct { typedef struct {
/* Huffman data U32 CTable[HUF_CTABLE_SIZE_U32(255)];
* Must be before the FSE data. HUF_repeat repeatMode;
*/ } ZSTD_hufCTables_t;
U32 hufCTable[HUF_CTABLE_SIZE_U32(255)];
HUF_repeat hufCTable_repeatMode; typedef struct {
/* FSE data */
FSE_CTable offcodeCTable[FSE_CTABLE_SIZE_U32(OffFSELog, MaxOff)]; FSE_CTable offcodeCTable[FSE_CTABLE_SIZE_U32(OffFSELog, MaxOff)];
FSE_CTable matchlengthCTable[FSE_CTABLE_SIZE_U32(MLFSELog, MaxML)]; FSE_CTable matchlengthCTable[FSE_CTABLE_SIZE_U32(MLFSELog, MaxML)];
FSE_CTable litlengthCTable[FSE_CTABLE_SIZE_U32(LLFSELog, MaxLL)]; FSE_CTable litlengthCTable[FSE_CTABLE_SIZE_U32(LLFSELog, MaxLL)];
FSE_repeat offcode_repeatMode; FSE_repeat offcode_repeatMode;
FSE_repeat matchlength_repeatMode; FSE_repeat matchlength_repeatMode;
FSE_repeat litlength_repeatMode; FSE_repeat litlength_repeatMode;
} ZSTD_fseCTables_t;
typedef struct {
ZSTD_hufCTables_t huf;
ZSTD_fseCTables_t fse;
} ZSTD_entropyCTables_t; } ZSTD_entropyCTables_t;
typedef struct { typedef struct {

22
lib/compress/zstd_opt.c
View File

@ -39,7 +39,7 @@ static void ZSTD_rescaleFreqs(optState_t* const optPtr,
optPtr->priceType = zop_predef; optPtr->priceType = zop_predef;
assert(optPtr->symbolCosts != NULL); assert(optPtr->symbolCosts != NULL);
if (optPtr->symbolCosts->hufCTable_repeatMode == HUF_repeat_valid) { /* huffman table presumed generated by dictionary */ if (optPtr->symbolCosts->huf.repeatMode == HUF_repeat_valid) { /* huffman table presumed generated by dictionary */
if (srcSize <= 8192) /* heuristic */ if (srcSize <= 8192) /* heuristic */
optPtr->priceType = zop_static; optPtr->priceType = zop_static;
else { else {
@ -52,7 +52,7 @@ static void ZSTD_rescaleFreqs(optState_t* const optPtr,
{ unsigned lit; { unsigned lit;
for (lit=0; lit<=MaxLit; lit++) { for (lit=0; lit<=MaxLit; lit++) {
U32 const scaleLog = 11; /* scale to 2K */ U32 const scaleLog = 11; /* scale to 2K */
U32 const bitCost = HUF_getNbBits(optPtr->symbolCosts->hufCTable, lit); U32 const bitCost = HUF_getNbBits(optPtr->symbolCosts->huf.CTable, lit);
assert(bitCost <= scaleLog); assert(bitCost <= scaleLog);
optPtr->litFreq[lit] = bitCost ? 1 << (scaleLog-bitCost) : 1 /*minimum to calculate cost*/; optPtr->litFreq[lit] = bitCost ? 1 << (scaleLog-bitCost) : 1 /*minimum to calculate cost*/;
optPtr->litSum += optPtr->litFreq[lit]; optPtr->litSum += optPtr->litFreq[lit];
@ -60,7 +60,7 @@ static void ZSTD_rescaleFreqs(optState_t* const optPtr,
{ unsigned ll; { unsigned ll;
FSE_CState_t llstate; FSE_CState_t llstate;
FSE_initCState(&llstate, optPtr->symbolCosts->litlengthCTable); FSE_initCState(&llstate, optPtr->symbolCosts->fse.litlengthCTable);
optPtr->litLengthSum = 0; optPtr->litLengthSum = 0;
for (ll=0; ll<=MaxLL; ll++) { for (ll=0; ll<=MaxLL; ll++) {
U32 const scaleLog = 10; /* scale to 1K */ U32 const scaleLog = 10; /* scale to 1K */
@ -72,7 +72,7 @@ static void ZSTD_rescaleFreqs(optState_t* const optPtr,
{ unsigned ml; { unsigned ml;
FSE_CState_t mlstate; FSE_CState_t mlstate;
FSE_initCState(&mlstate, optPtr->symbolCosts->matchlengthCTable); FSE_initCState(&mlstate, optPtr->symbolCosts->fse.matchlengthCTable);
optPtr->matchLengthSum = 0; optPtr->matchLengthSum = 0;
for (ml=0; ml<=MaxML; ml++) { for (ml=0; ml<=MaxML; ml++) {
U32 const scaleLog = 10; U32 const scaleLog = 10;
@ -84,7 +84,7 @@ static void ZSTD_rescaleFreqs(optState_t* const optPtr,
{ unsigned of; { unsigned of;
FSE_CState_t ofstate; FSE_CState_t ofstate;
FSE_initCState(&ofstate, optPtr->symbolCosts->offcodeCTable); FSE_initCState(&ofstate, optPtr->symbolCosts->fse.offcodeCTable);
optPtr->offCodeSum = 0; optPtr->offCodeSum = 0;
for (of=0; of<=MaxOff; of++) { for (of=0; of<=MaxOff; of++) {
U32 const scaleLog = 10; U32 const scaleLog = 10;
@ -180,9 +180,9 @@ static U32 ZSTD_rawLiteralsCost(const BYTE* const literals, U32 const litLength,
if (optPtr->priceType == zop_static) { if (optPtr->priceType == zop_static) {
U32 u, cost; U32 u, cost;
assert(optPtr->symbolCosts != NULL); assert(optPtr->symbolCosts != NULL);
assert(optPtr->symbolCosts->hufCTable_repeatMode == HUF_repeat_valid); assert(optPtr->symbolCosts->huf.repeatMode == HUF_repeat_valid);
for (u=0, cost=0; u < litLength; u++) for (u=0, cost=0; u < litLength; u++)
cost += HUF_getNbBits(optPtr->symbolCosts->hufCTable, literals[u]); cost += HUF_getNbBits(optPtr->symbolCosts->huf.CTable, literals[u]);
return cost * BITCOST_MULTIPLIER; return cost * BITCOST_MULTIPLIER;
} }
@ -202,7 +202,7 @@ static U32 ZSTD_litLengthPrice(U32 const litLength, const optState_t* const optP
if (optPtr->priceType == zop_static) { if (optPtr->priceType == zop_static) {
U32 const llCode = ZSTD_LLcode(litLength); U32 const llCode = ZSTD_LLcode(litLength);
FSE_CState_t cstate; FSE_CState_t cstate;
FSE_initCState(&cstate, optPtr->symbolCosts->litlengthCTable); FSE_initCState(&cstate, optPtr->symbolCosts->fse.litlengthCTable);
{ U32 const price = LL_bits[llCode]*BITCOST_MULTIPLIER + BITCOST_SYMBOL(cstate.symbolTT, cstate.stateLog, llCode); { U32 const price = LL_bits[llCode]*BITCOST_MULTIPLIER + BITCOST_SYMBOL(cstate.symbolTT, cstate.stateLog, llCode);
DEBUGLOG(8, "ZSTD_litLengthPrice: ll=%u, bitCost=%.2f", litLength, (double)price / BITCOST_MULTIPLIER); DEBUGLOG(8, "ZSTD_litLengthPrice: ll=%u, bitCost=%.2f", litLength, (double)price / BITCOST_MULTIPLIER);
return price; return price;
@ -234,7 +234,7 @@ static int ZSTD_litLengthContribution(U32 const litLength, const optState_t* con
if (optPtr->priceType == zop_static) { if (optPtr->priceType == zop_static) {
U32 const llCode = ZSTD_LLcode(litLength); U32 const llCode = ZSTD_LLcode(litLength);
FSE_CState_t cstate; FSE_CState_t cstate;
FSE_initCState(&cstate, optPtr->symbolCosts->litlengthCTable); FSE_initCState(&cstate, optPtr->symbolCosts->fse.litlengthCTable);
return (int)(LL_bits[llCode] * BITCOST_MULTIPLIER) return (int)(LL_bits[llCode] * BITCOST_MULTIPLIER)
+ BITCOST_SYMBOL(cstate.symbolTT, cstate.stateLog, llCode) + BITCOST_SYMBOL(cstate.symbolTT, cstate.stateLog, llCode)
- BITCOST_SYMBOL(cstate.symbolTT, cstate.stateLog, 0); - BITCOST_SYMBOL(cstate.symbolTT, cstate.stateLog, 0);
@ -284,8 +284,8 @@ ZSTD_getMatchPrice(U32 const offset, U32 const matchLength,
if (optPtr->priceType == zop_static) { if (optPtr->priceType == zop_static) {
U32 const mlCode = ZSTD_MLcode(mlBase); U32 const mlCode = ZSTD_MLcode(mlBase);
FSE_CState_t mlstate, offstate; FSE_CState_t mlstate, offstate;
FSE_initCState(&mlstate, optPtr->symbolCosts->matchlengthCTable); FSE_initCState(&mlstate, optPtr->symbolCosts->fse.matchlengthCTable);
FSE_initCState(&offstate, optPtr->symbolCosts->offcodeCTable); FSE_initCState(&offstate, optPtr->symbolCosts->fse.offcodeCTable);
return BITCOST_SYMBOL(offstate.symbolTT, offstate.stateLog, offCode) + offCode*BITCOST_MULTIPLIER return BITCOST_SYMBOL(offstate.symbolTT, offstate.stateLog, offCode) + offCode*BITCOST_MULTIPLIER
+ BITCOST_SYMBOL(mlstate.symbolTT, mlstate.stateLog, mlCode) + ML_bits[mlCode]*BITCOST_MULTIPLIER; + BITCOST_SYMBOL(mlstate.symbolTT, mlstate.stateLog, mlCode) + ML_bits[mlCode]*BITCOST_MULTIPLIER;
} }