zstd_fast.c
493 lines
| 21.4 KiB
| text/x-c
|
CLexer
|
r37513 | /* | ||
* Copyright (c) 2016-present, Yann Collet, Facebook, Inc. | ||||
* All rights reserved. | ||||
* | ||||
* This source code is licensed under both the BSD-style license (found in the | ||||
* LICENSE file in the root directory of this source tree) and the GPLv2 (found | ||||
* in the COPYING file in the root directory of this source tree). | ||||
* You may select, at your option, one of the above-listed licenses. | ||||
*/ | ||||
#include "zstd_compress_internal.h" | ||||
#include "zstd_fast.h" | ||||
void ZSTD_fillHashTable(ZSTD_matchState_t* ms, | ||||
|
r43207 | const void* const end, | ||
ZSTD_dictTableLoadMethod_e dtlm) | ||||
|
r37513 | { | ||
|
r40157 | const ZSTD_compressionParameters* const cParams = &ms->cParams; | ||
|
r37513 | U32* const hashTable = ms->hashTable; | ||
U32 const hBits = cParams->hashLog; | ||||
|
r42237 | U32 const mls = cParams->minMatch; | ||
|
r37513 | const BYTE* const base = ms->window.base; | ||
const BYTE* ip = base + ms->nextToUpdate; | ||||
const BYTE* const iend = ((const BYTE*)end) - HASH_READ_SIZE; | ||||
const U32 fastHashFillStep = 3; | ||||
/* Always insert every fastHashFillStep position into the hash table. | ||||
* Insert the other positions if their hash entry is empty. | ||||
*/ | ||||
|
r42237 | for ( ; ip + fastHashFillStep < iend + 2; ip += fastHashFillStep) { | ||
|
r37513 | U32 const current = (U32)(ip - base); | ||
|
r42237 | size_t const hash0 = ZSTD_hashPtr(ip, hBits, mls); | ||
hashTable[hash0] = current; | ||||
if (dtlm == ZSTD_dtlm_fast) continue; | ||||
/* Only load extra positions for ZSTD_dtlm_full */ | ||||
{ U32 p; | ||||
for (p = 1; p < fastHashFillStep; ++p) { | ||||
size_t const hash = ZSTD_hashPtr(ip + p, hBits, mls); | ||||
if (hashTable[hash] == 0) { /* not yet filled */ | ||||
hashTable[hash] = current + p; | ||||
} } } } | ||||
|
r37513 | } | ||
|
r43207 | |||
|
r37513 | FORCE_INLINE_TEMPLATE | ||
size_t ZSTD_compressBlock_fast_generic( | ||||
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], | ||||
void const* src, size_t srcSize, | ||||
|
r43207 | U32 const mls) | ||
{ | ||||
const ZSTD_compressionParameters* const cParams = &ms->cParams; | ||||
U32* const hashTable = ms->hashTable; | ||||
U32 const hlog = cParams->hashLog; | ||||
/* support stepSize of 0 */ | ||||
size_t const stepSize = cParams->targetLength + !(cParams->targetLength) + 1; | ||||
const BYTE* const base = ms->window.base; | ||||
const BYTE* const istart = (const BYTE*)src; | ||||
/* We check ip0 (ip + 0) and ip1 (ip + 1) each loop */ | ||||
const BYTE* ip0 = istart; | ||||
const BYTE* ip1; | ||||
const BYTE* anchor = istart; | ||||
const U32 endIndex = (U32)((size_t)(istart - base) + srcSize); | ||||
const U32 maxDistance = 1U << cParams->windowLog; | ||||
const U32 validStartIndex = ms->window.dictLimit; | ||||
const U32 prefixStartIndex = (endIndex - validStartIndex > maxDistance) ? endIndex - maxDistance : validStartIndex; | ||||
const BYTE* const prefixStart = base + prefixStartIndex; | ||||
const BYTE* const iend = istart + srcSize; | ||||
const BYTE* const ilimit = iend - HASH_READ_SIZE; | ||||
U32 offset_1=rep[0], offset_2=rep[1]; | ||||
U32 offsetSaved = 0; | ||||
/* init */ | ||||
DEBUGLOG(5, "ZSTD_compressBlock_fast_generic"); | ||||
ip0 += (ip0 == prefixStart); | ||||
ip1 = ip0 + 1; | ||||
{ | ||||
U32 const maxRep = (U32)(ip0 - prefixStart); | ||||
if (offset_2 > maxRep) offsetSaved = offset_2, offset_2 = 0; | ||||
if (offset_1 > maxRep) offsetSaved = offset_1, offset_1 = 0; | ||||
} | ||||
/* Main Search Loop */ | ||||
while (ip1 < ilimit) { /* < instead of <=, because check at ip0+2 */ | ||||
size_t mLength; | ||||
BYTE const* ip2 = ip0 + 2; | ||||
size_t const h0 = ZSTD_hashPtr(ip0, hlog, mls); | ||||
U32 const val0 = MEM_read32(ip0); | ||||
size_t const h1 = ZSTD_hashPtr(ip1, hlog, mls); | ||||
U32 const val1 = MEM_read32(ip1); | ||||
U32 const current0 = (U32)(ip0-base); | ||||
U32 const current1 = (U32)(ip1-base); | ||||
U32 const matchIndex0 = hashTable[h0]; | ||||
U32 const matchIndex1 = hashTable[h1]; | ||||
BYTE const* repMatch = ip2-offset_1; | ||||
const BYTE* match0 = base + matchIndex0; | ||||
const BYTE* match1 = base + matchIndex1; | ||||
U32 offcode; | ||||
hashTable[h0] = current0; /* update hash table */ | ||||
hashTable[h1] = current1; /* update hash table */ | ||||
assert(ip0 + 1 == ip1); | ||||
if ((offset_1 > 0) & (MEM_read32(repMatch) == MEM_read32(ip2))) { | ||||
mLength = ip2[-1] == repMatch[-1] ? 1 : 0; | ||||
ip0 = ip2 - mLength; | ||||
match0 = repMatch - mLength; | ||||
offcode = 0; | ||||
goto _match; | ||||
} | ||||
if ((matchIndex0 > prefixStartIndex) && MEM_read32(match0) == val0) { | ||||
/* found a regular match */ | ||||
goto _offset; | ||||
} | ||||
if ((matchIndex1 > prefixStartIndex) && MEM_read32(match1) == val1) { | ||||
/* found a regular match after one literal */ | ||||
ip0 = ip1; | ||||
match0 = match1; | ||||
goto _offset; | ||||
} | ||||
{ | ||||
size_t const step = ((ip0-anchor) >> (kSearchStrength - 1)) + stepSize; | ||||
assert(step >= 2); | ||||
ip0 += step; | ||||
ip1 += step; | ||||
continue; | ||||
} | ||||
_offset: /* Requires: ip0, match0 */ | ||||
/* Compute the offset code */ | ||||
offset_2 = offset_1; | ||||
offset_1 = (U32)(ip0-match0); | ||||
offcode = offset_1 + ZSTD_REP_MOVE; | ||||
mLength = 0; | ||||
/* Count the backwards match length */ | ||||
while (((ip0>anchor) & (match0>prefixStart)) | ||||
&& (ip0[-1] == match0[-1])) { ip0--; match0--; mLength++; } /* catch up */ | ||||
_match: /* Requires: ip0, match0, offcode */ | ||||
/* Count the forward length */ | ||||
mLength += ZSTD_count(ip0+mLength+4, match0+mLength+4, iend) + 4; | ||||
ZSTD_storeSeq(seqStore, ip0-anchor, anchor, offcode, mLength-MINMATCH); | ||||
/* match found */ | ||||
ip0 += mLength; | ||||
anchor = ip0; | ||||
ip1 = ip0 + 1; | ||||
if (ip0 <= ilimit) { | ||||
/* Fill Table */ | ||||
assert(base+current0+2 > istart); /* check base overflow */ | ||||
hashTable[ZSTD_hashPtr(base+current0+2, hlog, mls)] = current0+2; /* here because current+2 could be > iend-8 */ | ||||
hashTable[ZSTD_hashPtr(ip0-2, hlog, mls)] = (U32)(ip0-2-base); | ||||
while ( (ip0 <= ilimit) | ||||
&& ( (offset_2>0) | ||||
& (MEM_read32(ip0) == MEM_read32(ip0 - offset_2)) )) { | ||||
/* store sequence */ | ||||
size_t const rLength = ZSTD_count(ip0+4, ip0+4-offset_2, iend) + 4; | ||||
U32 const tmpOff = offset_2; offset_2 = offset_1; offset_1 = tmpOff; /* swap offset_2 <=> offset_1 */ | ||||
hashTable[ZSTD_hashPtr(ip0, hlog, mls)] = (U32)(ip0-base); | ||||
ip0 += rLength; | ||||
ip1 = ip0 + 1; | ||||
ZSTD_storeSeq(seqStore, 0, anchor, 0, rLength-MINMATCH); | ||||
anchor = ip0; | ||||
continue; /* faster when present (confirmed on gcc-8) ... (?) */ | ||||
} | ||||
} | ||||
} | ||||
/* save reps for next block */ | ||||
rep[0] = offset_1 ? offset_1 : offsetSaved; | ||||
rep[1] = offset_2 ? offset_2 : offsetSaved; | ||||
/* Return the last literals size */ | ||||
return (size_t)(iend - anchor); | ||||
} | ||||
size_t ZSTD_compressBlock_fast( | ||||
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], | ||||
void const* src, size_t srcSize) | ||||
{ | ||||
ZSTD_compressionParameters const* cParams = &ms->cParams; | ||||
U32 const mls = cParams->minMatch; | ||||
assert(ms->dictMatchState == NULL); | ||||
switch(mls) | ||||
{ | ||||
default: /* includes case 3 */ | ||||
case 4 : | ||||
return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 4); | ||||
case 5 : | ||||
return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 5); | ||||
case 6 : | ||||
return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 6); | ||||
case 7 : | ||||
return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 7); | ||||
} | ||||
} | ||||
FORCE_INLINE_TEMPLATE | ||||
size_t ZSTD_compressBlock_fast_dictMatchState_generic( | ||||
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], | ||||
void const* src, size_t srcSize, U32 const mls) | ||||
|
r37513 | { | ||
|
r40157 | const ZSTD_compressionParameters* const cParams = &ms->cParams; | ||
|
r37513 | U32* const hashTable = ms->hashTable; | ||
|
r40157 | U32 const hlog = cParams->hashLog; | ||
/* support stepSize of 0 */ | ||||
U32 const stepSize = cParams->targetLength + !(cParams->targetLength); | ||||
|
r37513 | const BYTE* const base = ms->window.base; | ||
const BYTE* const istart = (const BYTE*)src; | ||||
const BYTE* ip = istart; | ||||
const BYTE* anchor = istart; | ||||
|
r40157 | const U32 prefixStartIndex = ms->window.dictLimit; | ||
const BYTE* const prefixStart = base + prefixStartIndex; | ||||
|
r37513 | const BYTE* const iend = istart + srcSize; | ||
const BYTE* const ilimit = iend - HASH_READ_SIZE; | ||||
U32 offset_1=rep[0], offset_2=rep[1]; | ||||
U32 offsetSaved = 0; | ||||
|
r40157 | const ZSTD_matchState_t* const dms = ms->dictMatchState; | ||
|
r43207 | const ZSTD_compressionParameters* const dictCParams = &dms->cParams ; | ||
const U32* const dictHashTable = dms->hashTable; | ||||
const U32 dictStartIndex = dms->window.dictLimit; | ||||
const BYTE* const dictBase = dms->window.base; | ||||
const BYTE* const dictStart = dictBase + dictStartIndex; | ||||
const BYTE* const dictEnd = dms->window.nextSrc; | ||||
const U32 dictIndexDelta = prefixStartIndex - (U32)(dictEnd - dictBase); | ||||
|
r40157 | const U32 dictAndPrefixLength = (U32)(ip - prefixStart + dictEnd - dictStart); | ||
|
r43207 | const U32 dictHLog = dictCParams->hashLog; | ||
|
r40157 | |||
|
r43207 | /* if a dictionary is still attached, it necessarily means that | ||
* it is within window size. So we just check it. */ | ||||
const U32 maxDistance = 1U << cParams->windowLog; | ||||
const U32 endIndex = (U32)((size_t)(ip - base) + srcSize); | ||||
assert(endIndex - prefixStartIndex <= maxDistance); | ||||
(void)maxDistance; (void)endIndex; /* these variables are not used when assert() is disabled */ | ||||
/* ensure there will be no no underflow | ||||
* when translating a dict index into a local index */ | ||||
assert(prefixStartIndex >= (U32)(dictEnd - dictBase)); | ||||
|
r40157 | |||
|
r37513 | /* init */ | ||
|
r43207 | DEBUGLOG(5, "ZSTD_compressBlock_fast_dictMatchState_generic"); | ||
|
r40157 | ip += (dictAndPrefixLength == 0); | ||
|
r43207 | /* dictMatchState repCode checks don't currently handle repCode == 0 | ||
* disabling. */ | ||||
assert(offset_1 <= dictAndPrefixLength); | ||||
assert(offset_2 <= dictAndPrefixLength); | ||||
|
r37513 | |||
/* Main Search Loop */ | ||||
while (ip < ilimit) { /* < instead of <=, because repcode check at (ip+1) */ | ||||
size_t mLength; | ||||
size_t const h = ZSTD_hashPtr(ip, hlog, mls); | ||||
U32 const current = (U32)(ip-base); | ||||
U32 const matchIndex = hashTable[h]; | ||||
const BYTE* match = base + matchIndex; | ||||
|
r40157 | const U32 repIndex = current + 1 - offset_1; | ||
|
r43207 | const BYTE* repMatch = (repIndex < prefixStartIndex) ? | ||
|
r40157 | dictBase + (repIndex - dictIndexDelta) : | ||
base + repIndex; | ||||
|
r37513 | hashTable[h] = current; /* update hash table */ | ||
|
r43207 | if ( ((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow : ensure repIndex isn't overlapping dict + prefix */ | ||
|
r40157 | && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) { | ||
const BYTE* const repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend; | ||||
mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixStart) + 4; | ||||
ip++; | ||||
|
r43207 | ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, 0, mLength-MINMATCH); | ||
|
r40157 | } else if ( (matchIndex <= prefixStartIndex) ) { | ||
|
r43207 | size_t const dictHash = ZSTD_hashPtr(ip, dictHLog, mls); | ||
U32 const dictMatchIndex = dictHashTable[dictHash]; | ||||
const BYTE* dictMatch = dictBase + dictMatchIndex; | ||||
if (dictMatchIndex <= dictStartIndex || | ||||
MEM_read32(dictMatch) != MEM_read32(ip)) { | ||||
|
r37513 | assert(stepSize >= 1); | ||
ip += ((ip-anchor) >> kSearchStrength) + stepSize; | ||||
continue; | ||||
|
r43207 | } else { | ||
/* found a dict match */ | ||||
U32 const offset = (U32)(current-dictMatchIndex-dictIndexDelta); | ||||
mLength = ZSTD_count_2segments(ip+4, dictMatch+4, iend, dictEnd, prefixStart) + 4; | ||||
while (((ip>anchor) & (dictMatch>dictStart)) | ||||
&& (ip[-1] == dictMatch[-1])) { | ||||
ip--; dictMatch--; mLength++; | ||||
} /* catch up */ | ||||
offset_2 = offset_1; | ||||
offset_1 = offset; | ||||
ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH); | ||||
|
r37513 | } | ||
|
r40157 | } else if (MEM_read32(match) != MEM_read32(ip)) { | ||
/* it's not a match, and we're not going to check the dictionary */ | ||||
assert(stepSize >= 1); | ||||
ip += ((ip-anchor) >> kSearchStrength) + stepSize; | ||||
continue; | ||||
} else { | ||||
/* found a regular match */ | ||||
U32 const offset = (U32)(ip-match); | ||||
|
r37513 | mLength = ZSTD_count(ip+4, match+4, iend) + 4; | ||
|
r40157 | while (((ip>anchor) & (match>prefixStart)) | ||
&& (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */ | ||||
offset_2 = offset_1; | ||||
offset_1 = offset; | ||||
|
r43207 | ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH); | ||
|
r40157 | } | ||
|
r37513 | |||
/* match found */ | ||||
ip += mLength; | ||||
anchor = ip; | ||||
if (ip <= ilimit) { | ||||
/* Fill Table */ | ||||
|
r40157 | assert(base+current+2 > istart); /* check base overflow */ | ||
|
r37513 | hashTable[ZSTD_hashPtr(base+current+2, hlog, mls)] = current+2; /* here because current+2 could be > iend-8 */ | ||
hashTable[ZSTD_hashPtr(ip-2, hlog, mls)] = (U32)(ip-2-base); | ||||
|
r40157 | |||
|
r37513 | /* check immediate repcode */ | ||
|
r43207 | while (ip <= ilimit) { | ||
U32 const current2 = (U32)(ip-base); | ||||
U32 const repIndex2 = current2 - offset_2; | ||||
const BYTE* repMatch2 = repIndex2 < prefixStartIndex ? | ||||
dictBase - dictIndexDelta + repIndex2 : | ||||
base + repIndex2; | ||||
if ( ((U32)((prefixStartIndex-1) - (U32)repIndex2) >= 3 /* intentional overflow */) | ||||
&& (MEM_read32(repMatch2) == MEM_read32(ip)) ) { | ||||
const BYTE* const repEnd2 = repIndex2 < prefixStartIndex ? dictEnd : iend; | ||||
size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixStart) + 4; | ||||
U32 tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset; /* swap offset_2 <=> offset_1 */ | ||||
ZSTD_storeSeq(seqStore, 0, anchor, 0, repLength2-MINMATCH); | ||||
hashTable[ZSTD_hashPtr(ip, hlog, mls)] = current2; | ||||
ip += repLength2; | ||||
anchor = ip; | ||||
continue; | ||||
|
r40157 | } | ||
|
r43207 | break; | ||
|
r40157 | } | ||
|
r43207 | } | ||
} | ||||
|
r37513 | |||
/* save reps for next block */ | ||||
rep[0] = offset_1 ? offset_1 : offsetSaved; | ||||
rep[1] = offset_2 ? offset_2 : offsetSaved; | ||||
/* Return the last literals size */ | ||||
|
r43207 | return (size_t)(iend - anchor); | ||
|
r40157 | } | ||
size_t ZSTD_compressBlock_fast_dictMatchState( | ||||
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], | ||||
void const* src, size_t srcSize) | ||||
{ | ||||
ZSTD_compressionParameters const* cParams = &ms->cParams; | ||||
|
r42237 | U32 const mls = cParams->minMatch; | ||
|
r40157 | assert(ms->dictMatchState != NULL); | ||
switch(mls) | ||||
{ | ||||
default: /* includes case 3 */ | ||||
case 4 : | ||||
|
r43207 | return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 4); | ||
|
r40157 | case 5 : | ||
|
r43207 | return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 5); | ||
|
r40157 | case 6 : | ||
|
r43207 | return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 6); | ||
|
r40157 | case 7 : | ||
|
r43207 | return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 7); | ||
|
r37513 | } | ||
} | ||||
static size_t ZSTD_compressBlock_fast_extDict_generic( | ||||
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], | ||||
|
r40157 | void const* src, size_t srcSize, U32 const mls) | ||
|
r37513 | { | ||
|
r40157 | const ZSTD_compressionParameters* const cParams = &ms->cParams; | ||
U32* const hashTable = ms->hashTable; | ||||
U32 const hlog = cParams->hashLog; | ||||
/* support stepSize of 0 */ | ||||
U32 const stepSize = cParams->targetLength + !(cParams->targetLength); | ||||
|
r37513 | const BYTE* const base = ms->window.base; | ||
const BYTE* const dictBase = ms->window.dictBase; | ||||
const BYTE* const istart = (const BYTE*)src; | ||||
const BYTE* ip = istart; | ||||
const BYTE* anchor = istart; | ||||
|
r43207 | const U32 endIndex = (U32)((size_t)(istart - base) + srcSize); | ||
const U32 lowLimit = ZSTD_getLowestMatchIndex(ms, endIndex, cParams->windowLog); | ||||
const U32 dictStartIndex = lowLimit; | ||||
|
r40157 | const BYTE* const dictStart = dictBase + dictStartIndex; | ||
|
r43207 | const U32 dictLimit = ms->window.dictLimit; | ||
const U32 prefixStartIndex = dictLimit < lowLimit ? lowLimit : dictLimit; | ||||
|
r40157 | const BYTE* const prefixStart = base + prefixStartIndex; | ||
const BYTE* const dictEnd = dictBase + prefixStartIndex; | ||||
|
r37513 | const BYTE* const iend = istart + srcSize; | ||
const BYTE* const ilimit = iend - 8; | ||||
U32 offset_1=rep[0], offset_2=rep[1]; | ||||
|
r43207 | DEBUGLOG(5, "ZSTD_compressBlock_fast_extDict_generic"); | ||
/* switch to "regular" variant if extDict is invalidated due to maxDistance */ | ||||
if (prefixStartIndex == dictStartIndex) | ||||
return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, mls); | ||||
|
r37513 | /* Search Loop */ | ||
while (ip < ilimit) { /* < instead of <=, because (ip+1) */ | ||||
const size_t h = ZSTD_hashPtr(ip, hlog, mls); | ||||
|
r40157 | const U32 matchIndex = hashTable[h]; | ||
const BYTE* const matchBase = matchIndex < prefixStartIndex ? dictBase : base; | ||||
const BYTE* match = matchBase + matchIndex; | ||||
const U32 current = (U32)(ip-base); | ||||
const U32 repIndex = current + 1 - offset_1; | ||||
const BYTE* const repBase = repIndex < prefixStartIndex ? dictBase : base; | ||||
const BYTE* const repMatch = repBase + repIndex; | ||||
|
r37513 | size_t mLength; | ||
hashTable[h] = current; /* update hash table */ | ||||
|
r40157 | assert(offset_1 <= current +1); /* check repIndex */ | ||
|
r37513 | |||
|
r40157 | if ( (((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow */ & (repIndex > dictStartIndex)) | ||
|
r37513 | && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) { | ||
|
r43207 | const BYTE* const repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend; | ||
mLength = ZSTD_count_2segments(ip+1 +4, repMatch +4, iend, repMatchEnd, prefixStart) + 4; | ||||
|
r37513 | ip++; | ||
|
r43207 | ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, 0, mLength-MINMATCH); | ||
|
r37513 | } else { | ||
|
r40157 | if ( (matchIndex < dictStartIndex) || | ||
|
r37513 | (MEM_read32(match) != MEM_read32(ip)) ) { | ||
assert(stepSize >= 1); | ||||
ip += ((ip-anchor) >> kSearchStrength) + stepSize; | ||||
continue; | ||||
} | ||||
|
r43207 | { const BYTE* const matchEnd = matchIndex < prefixStartIndex ? dictEnd : iend; | ||
const BYTE* const lowMatchPtr = matchIndex < prefixStartIndex ? dictStart : prefixStart; | ||||
|
r37513 | U32 offset; | ||
|
r40157 | mLength = ZSTD_count_2segments(ip+4, match+4, iend, matchEnd, prefixStart) + 4; | ||
|
r37513 | while (((ip>anchor) & (match>lowMatchPtr)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */ | ||
offset = current - matchIndex; | ||||
offset_2 = offset_1; | ||||
offset_1 = offset; | ||||
|
r43207 | ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH); | ||
|
r37513 | } } | ||
/* found a match : store it */ | ||||
ip += mLength; | ||||
anchor = ip; | ||||
if (ip <= ilimit) { | ||||
/* Fill Table */ | ||||
hashTable[ZSTD_hashPtr(base+current+2, hlog, mls)] = current+2; | ||||
hashTable[ZSTD_hashPtr(ip-2, hlog, mls)] = (U32)(ip-2-base); | ||||
/* check immediate repcode */ | ||||
while (ip <= ilimit) { | ||||
U32 const current2 = (U32)(ip-base); | ||||
U32 const repIndex2 = current2 - offset_2; | ||||
|
r40157 | const BYTE* repMatch2 = repIndex2 < prefixStartIndex ? dictBase + repIndex2 : base + repIndex2; | ||
if ( (((U32)((prefixStartIndex-1) - repIndex2) >= 3) & (repIndex2 > dictStartIndex)) /* intentional overflow */ | ||||
|
r37513 | && (MEM_read32(repMatch2) == MEM_read32(ip)) ) { | ||
|
r40157 | const BYTE* const repEnd2 = repIndex2 < prefixStartIndex ? dictEnd : iend; | ||
size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixStart) + 4; | ||||
|
r43207 | U32 const tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset; /* swap offset_2 <=> offset_1 */ | ||
|
r37513 | ZSTD_storeSeq(seqStore, 0, anchor, 0, repLength2-MINMATCH); | ||
hashTable[ZSTD_hashPtr(ip, hlog, mls)] = current2; | ||||
ip += repLength2; | ||||
anchor = ip; | ||||
continue; | ||||
} | ||||
break; | ||||
} } } | ||||
/* save reps for next block */ | ||||
rep[0] = offset_1; | ||||
rep[1] = offset_2; | ||||
/* Return the last literals size */ | ||||
|
r43207 | return (size_t)(iend - anchor); | ||
|
r37513 | } | ||
size_t ZSTD_compressBlock_fast_extDict( | ||||
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], | ||||
|
r40157 | void const* src, size_t srcSize) | ||
|
r37513 | { | ||
|
r40157 | ZSTD_compressionParameters const* cParams = &ms->cParams; | ||
|
r42237 | U32 const mls = cParams->minMatch; | ||
|
r37513 | switch(mls) | ||
{ | ||||
default: /* includes case 3 */ | ||||
case 4 : | ||||
|
r40157 | return ZSTD_compressBlock_fast_extDict_generic(ms, seqStore, rep, src, srcSize, 4); | ||
|
r37513 | case 5 : | ||
|
r40157 | return ZSTD_compressBlock_fast_extDict_generic(ms, seqStore, rep, src, srcSize, 5); | ||
|
r37513 | case 6 : | ||
|
r40157 | return ZSTD_compressBlock_fast_extDict_generic(ms, seqStore, rep, src, srcSize, 6); | ||
|
r37513 | case 7 : | ||
|
r40157 | return ZSTD_compressBlock_fast_extDict_generic(ms, seqStore, rep, src, srcSize, 7); | ||
|
r37513 | } | ||
} | ||||