|
|
/*
|
|
|
* 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_lazy.h"
|
|
|
|
|
|
|
|
|
/*-*************************************
|
|
|
* Binary Tree search
|
|
|
***************************************/
|
|
|
|
|
|
void ZSTD_updateDUBT(
|
|
|
ZSTD_matchState_t* ms, ZSTD_compressionParameters const* cParams,
|
|
|
const BYTE* ip, const BYTE* iend,
|
|
|
U32 mls)
|
|
|
{
|
|
|
U32* const hashTable = ms->hashTable;
|
|
|
U32 const hashLog = cParams->hashLog;
|
|
|
|
|
|
U32* const bt = ms->chainTable;
|
|
|
U32 const btLog = cParams->chainLog - 1;
|
|
|
U32 const btMask = (1 << btLog) - 1;
|
|
|
|
|
|
const BYTE* const base = ms->window.base;
|
|
|
U32 const target = (U32)(ip - base);
|
|
|
U32 idx = ms->nextToUpdate;
|
|
|
|
|
|
if (idx != target)
|
|
|
DEBUGLOG(7, "ZSTD_updateDUBT, from %u to %u (dictLimit:%u)",
|
|
|
idx, target, ms->window.dictLimit);
|
|
|
assert(ip + 8 <= iend); /* condition for ZSTD_hashPtr */
|
|
|
(void)iend;
|
|
|
|
|
|
assert(idx >= ms->window.dictLimit); /* condition for valid base+idx */
|
|
|
for ( ; idx < target ; idx++) {
|
|
|
size_t const h = ZSTD_hashPtr(base + idx, hashLog, mls); /* assumption : ip + 8 <= iend */
|
|
|
U32 const matchIndex = hashTable[h];
|
|
|
|
|
|
U32* const nextCandidatePtr = bt + 2*(idx&btMask);
|
|
|
U32* const sortMarkPtr = nextCandidatePtr + 1;
|
|
|
|
|
|
DEBUGLOG(8, "ZSTD_updateDUBT: insert %u", idx);
|
|
|
hashTable[h] = idx; /* Update Hash Table */
|
|
|
*nextCandidatePtr = matchIndex; /* update BT like a chain */
|
|
|
*sortMarkPtr = ZSTD_DUBT_UNSORTED_MARK;
|
|
|
}
|
|
|
ms->nextToUpdate = target;
|
|
|
}
|
|
|
|
|
|
|
|
|
/** ZSTD_insertDUBT1() :
|
|
|
* sort one already inserted but unsorted position
|
|
|
* assumption : current >= btlow == (current - btmask)
|
|
|
* doesn't fail */
|
|
|
static void ZSTD_insertDUBT1(
|
|
|
ZSTD_matchState_t* ms, ZSTD_compressionParameters const* cParams,
|
|
|
U32 current, const BYTE* inputEnd,
|
|
|
U32 nbCompares, U32 btLow, int extDict)
|
|
|
{
|
|
|
U32* const bt = ms->chainTable;
|
|
|
U32 const btLog = cParams->chainLog - 1;
|
|
|
U32 const btMask = (1 << btLog) - 1;
|
|
|
size_t commonLengthSmaller=0, commonLengthLarger=0;
|
|
|
const BYTE* const base = ms->window.base;
|
|
|
const BYTE* const dictBase = ms->window.dictBase;
|
|
|
const U32 dictLimit = ms->window.dictLimit;
|
|
|
const BYTE* const ip = (current>=dictLimit) ? base + current : dictBase + current;
|
|
|
const BYTE* const iend = (current>=dictLimit) ? inputEnd : dictBase + dictLimit;
|
|
|
const BYTE* const dictEnd = dictBase + dictLimit;
|
|
|
const BYTE* const prefixStart = base + dictLimit;
|
|
|
const BYTE* match;
|
|
|
U32* smallerPtr = bt + 2*(current&btMask);
|
|
|
U32* largerPtr = smallerPtr + 1;
|
|
|
U32 matchIndex = *smallerPtr;
|
|
|
U32 dummy32; /* to be nullified at the end */
|
|
|
U32 const windowLow = ms->window.lowLimit;
|
|
|
|
|
|
DEBUGLOG(8, "ZSTD_insertDUBT1(%u) (dictLimit=%u, lowLimit=%u)",
|
|
|
current, dictLimit, windowLow);
|
|
|
assert(current >= btLow);
|
|
|
assert(ip < iend); /* condition for ZSTD_count */
|
|
|
|
|
|
while (nbCompares-- && (matchIndex > windowLow)) {
|
|
|
U32* const nextPtr = bt + 2*(matchIndex & btMask);
|
|
|
size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger); /* guaranteed minimum nb of common bytes */
|
|
|
assert(matchIndex < current);
|
|
|
|
|
|
if ( (!extDict)
|
|
|
|| (matchIndex+matchLength >= dictLimit) /* both in current segment*/
|
|
|
|| (current < dictLimit) /* both in extDict */) {
|
|
|
const BYTE* const mBase = !extDict || ((matchIndex+matchLength) >= dictLimit) ? base : dictBase;
|
|
|
assert( (matchIndex+matchLength >= dictLimit) /* might be wrong if extDict is incorrectly set to 0 */
|
|
|
|| (current < dictLimit) );
|
|
|
match = mBase + matchIndex;
|
|
|
matchLength += ZSTD_count(ip+matchLength, match+matchLength, iend);
|
|
|
} else {
|
|
|
match = dictBase + matchIndex;
|
|
|
matchLength += ZSTD_count_2segments(ip+matchLength, match+matchLength, iend, dictEnd, prefixStart);
|
|
|
if (matchIndex+matchLength >= dictLimit)
|
|
|
match = base + matchIndex; /* to prepare for next usage of match[matchLength] */
|
|
|
}
|
|
|
|
|
|
DEBUGLOG(8, "ZSTD_insertDUBT1: comparing %u with %u : found %u common bytes ",
|
|
|
current, matchIndex, (U32)matchLength);
|
|
|
|
|
|
if (ip+matchLength == iend) { /* equal : no way to know if inf or sup */
|
|
|
break; /* drop , to guarantee consistency ; miss a bit of compression, but other solutions can corrupt tree */
|
|
|
}
|
|
|
|
|
|
if (match[matchLength] < ip[matchLength]) { /* necessarily within buffer */
|
|
|
/* match is smaller than current */
|
|
|
*smallerPtr = matchIndex; /* update smaller idx */
|
|
|
commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */
|
|
|
if (matchIndex <= btLow) { smallerPtr=&dummy32; break; } /* beyond tree size, stop searching */
|
|
|
DEBUGLOG(8, "ZSTD_insertDUBT1: %u (>btLow=%u) is smaller : next => %u",
|
|
|
matchIndex, btLow, nextPtr[1]);
|
|
|
smallerPtr = nextPtr+1; /* new "candidate" => larger than match, which was smaller than target */
|
|
|
matchIndex = nextPtr[1]; /* new matchIndex, larger than previous and closer to current */
|
|
|
} else {
|
|
|
/* match is larger than current */
|
|
|
*largerPtr = matchIndex;
|
|
|
commonLengthLarger = matchLength;
|
|
|
if (matchIndex <= btLow) { largerPtr=&dummy32; break; } /* beyond tree size, stop searching */
|
|
|
DEBUGLOG(8, "ZSTD_insertDUBT1: %u (>btLow=%u) is larger => %u",
|
|
|
matchIndex, btLow, nextPtr[0]);
|
|
|
largerPtr = nextPtr;
|
|
|
matchIndex = nextPtr[0];
|
|
|
} }
|
|
|
|
|
|
*smallerPtr = *largerPtr = 0;
|
|
|
}
|
|
|
|
|
|
|
|
|
static size_t ZSTD_DUBT_findBestMatch (
|
|
|
ZSTD_matchState_t* ms, ZSTD_compressionParameters const* cParams,
|
|
|
const BYTE* const ip, const BYTE* const iend,
|
|
|
size_t* offsetPtr,
|
|
|
U32 const mls,
|
|
|
U32 const extDict)
|
|
|
{
|
|
|
U32* const hashTable = ms->hashTable;
|
|
|
U32 const hashLog = cParams->hashLog;
|
|
|
size_t const h = ZSTD_hashPtr(ip, hashLog, mls);
|
|
|
U32 matchIndex = hashTable[h];
|
|
|
|
|
|
const BYTE* const base = ms->window.base;
|
|
|
U32 const current = (U32)(ip-base);
|
|
|
U32 const windowLow = ms->window.lowLimit;
|
|
|
|
|
|
U32* const bt = ms->chainTable;
|
|
|
U32 const btLog = cParams->chainLog - 1;
|
|
|
U32 const btMask = (1 << btLog) - 1;
|
|
|
U32 const btLow = (btMask >= current) ? 0 : current - btMask;
|
|
|
U32 const unsortLimit = MAX(btLow, windowLow);
|
|
|
|
|
|
U32* nextCandidate = bt + 2*(matchIndex&btMask);
|
|
|
U32* unsortedMark = bt + 2*(matchIndex&btMask) + 1;
|
|
|
U32 nbCompares = 1U << cParams->searchLog;
|
|
|
U32 nbCandidates = nbCompares;
|
|
|
U32 previousCandidate = 0;
|
|
|
|
|
|
DEBUGLOG(7, "ZSTD_DUBT_findBestMatch (%u) ", current);
|
|
|
assert(ip <= iend-8); /* required for h calculation */
|
|
|
|
|
|
/* reach end of unsorted candidates list */
|
|
|
while ( (matchIndex > unsortLimit)
|
|
|
&& (*unsortedMark == ZSTD_DUBT_UNSORTED_MARK)
|
|
|
&& (nbCandidates > 1) ) {
|
|
|
DEBUGLOG(8, "ZSTD_DUBT_findBestMatch: candidate %u is unsorted",
|
|
|
matchIndex);
|
|
|
*unsortedMark = previousCandidate;
|
|
|
previousCandidate = matchIndex;
|
|
|
matchIndex = *nextCandidate;
|
|
|
nextCandidate = bt + 2*(matchIndex&btMask);
|
|
|
unsortedMark = bt + 2*(matchIndex&btMask) + 1;
|
|
|
nbCandidates --;
|
|
|
}
|
|
|
|
|
|
if ( (matchIndex > unsortLimit)
|
|
|
&& (*unsortedMark==ZSTD_DUBT_UNSORTED_MARK) ) {
|
|
|
DEBUGLOG(7, "ZSTD_DUBT_findBestMatch: nullify last unsorted candidate %u",
|
|
|
matchIndex);
|
|
|
*nextCandidate = *unsortedMark = 0; /* nullify next candidate if it's still unsorted (note : simplification, detrimental to compression ratio, beneficial for speed) */
|
|
|
}
|
|
|
|
|
|
/* batch sort stacked candidates */
|
|
|
matchIndex = previousCandidate;
|
|
|
while (matchIndex) { /* will end on matchIndex == 0 */
|
|
|
U32* const nextCandidateIdxPtr = bt + 2*(matchIndex&btMask) + 1;
|
|
|
U32 const nextCandidateIdx = *nextCandidateIdxPtr;
|
|
|
ZSTD_insertDUBT1(ms, cParams, matchIndex, iend,
|
|
|
nbCandidates, unsortLimit, extDict);
|
|
|
matchIndex = nextCandidateIdx;
|
|
|
nbCandidates++;
|
|
|
}
|
|
|
|
|
|
/* find longest match */
|
|
|
{ size_t commonLengthSmaller=0, commonLengthLarger=0;
|
|
|
const BYTE* const dictBase = ms->window.dictBase;
|
|
|
const U32 dictLimit = ms->window.dictLimit;
|
|
|
const BYTE* const dictEnd = dictBase + dictLimit;
|
|
|
const BYTE* const prefixStart = base + dictLimit;
|
|
|
U32* smallerPtr = bt + 2*(current&btMask);
|
|
|
U32* largerPtr = bt + 2*(current&btMask) + 1;
|
|
|
U32 matchEndIdx = current+8+1;
|
|
|
U32 dummy32; /* to be nullified at the end */
|
|
|
size_t bestLength = 0;
|
|
|
|
|
|
matchIndex = hashTable[h];
|
|
|
hashTable[h] = current; /* Update Hash Table */
|
|
|
|
|
|
while (nbCompares-- && (matchIndex > windowLow)) {
|
|
|
U32* const nextPtr = bt + 2*(matchIndex & btMask);
|
|
|
size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger); /* guaranteed minimum nb of common bytes */
|
|
|
const BYTE* match;
|
|
|
|
|
|
if ((!extDict) || (matchIndex+matchLength >= dictLimit)) {
|
|
|
match = base + matchIndex;
|
|
|
matchLength += ZSTD_count(ip+matchLength, match+matchLength, iend);
|
|
|
} else {
|
|
|
match = dictBase + matchIndex;
|
|
|
matchLength += ZSTD_count_2segments(ip+matchLength, match+matchLength, iend, dictEnd, prefixStart);
|
|
|
if (matchIndex+matchLength >= dictLimit)
|
|
|
match = base + matchIndex; /* to prepare for next usage of match[matchLength] */
|
|
|
}
|
|
|
|
|
|
if (matchLength > bestLength) {
|
|
|
if (matchLength > matchEndIdx - matchIndex)
|
|
|
matchEndIdx = matchIndex + (U32)matchLength;
|
|
|
if ( (4*(int)(matchLength-bestLength)) > (int)(ZSTD_highbit32(current-matchIndex+1) - ZSTD_highbit32((U32)offsetPtr[0]+1)) )
|
|
|
bestLength = matchLength, *offsetPtr = ZSTD_REP_MOVE + current - matchIndex;
|
|
|
if (ip+matchLength == iend) { /* equal : no way to know if inf or sup */
|
|
|
break; /* drop, to guarantee consistency (miss a little bit of compression) */
|
|
|
}
|
|
|
}
|
|
|
|
|
|
if (match[matchLength] < ip[matchLength]) {
|
|
|
/* match is smaller than current */
|
|
|
*smallerPtr = matchIndex; /* update smaller idx */
|
|
|
commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */
|
|
|
if (matchIndex <= btLow) { smallerPtr=&dummy32; break; } /* beyond tree size, stop the search */
|
|
|
smallerPtr = nextPtr+1; /* new "smaller" => larger of match */
|
|
|
matchIndex = nextPtr[1]; /* new matchIndex larger than previous (closer to current) */
|
|
|
} else {
|
|
|
/* match is larger than current */
|
|
|
*largerPtr = matchIndex;
|
|
|
commonLengthLarger = matchLength;
|
|
|
if (matchIndex <= btLow) { largerPtr=&dummy32; break; } /* beyond tree size, stop the search */
|
|
|
largerPtr = nextPtr;
|
|
|
matchIndex = nextPtr[0];
|
|
|
} }
|
|
|
|
|
|
*smallerPtr = *largerPtr = 0;
|
|
|
|
|
|
assert(matchEndIdx > current+8); /* ensure nextToUpdate is increased */
|
|
|
ms->nextToUpdate = matchEndIdx - 8; /* skip repetitive patterns */
|
|
|
if (bestLength >= MINMATCH) {
|
|
|
U32 const mIndex = current - ((U32)*offsetPtr - ZSTD_REP_MOVE); (void)mIndex;
|
|
|
DEBUGLOG(8, "ZSTD_DUBT_findBestMatch(%u) : found match of length %u and offsetCode %u (pos %u)",
|
|
|
current, (U32)bestLength, (U32)*offsetPtr, mIndex);
|
|
|
}
|
|
|
return bestLength;
|
|
|
}
|
|
|
}
|
|
|
|
|
|
|
|
|
/** ZSTD_BtFindBestMatch() : Tree updater, providing best match */
|
|
|
static size_t ZSTD_BtFindBestMatch (
|
|
|
ZSTD_matchState_t* ms, ZSTD_compressionParameters const* cParams,
|
|
|
const BYTE* const ip, const BYTE* const iLimit,
|
|
|
size_t* offsetPtr,
|
|
|
const U32 mls /* template */)
|
|
|
{
|
|
|
DEBUGLOG(7, "ZSTD_BtFindBestMatch");
|
|
|
if (ip < ms->window.base + ms->nextToUpdate) return 0; /* skipped area */
|
|
|
ZSTD_updateDUBT(ms, cParams, ip, iLimit, mls);
|
|
|
return ZSTD_DUBT_findBestMatch(ms, cParams, ip, iLimit, offsetPtr, mls, 0);
|
|
|
}
|
|
|
|
|
|
|
|
|
static size_t ZSTD_BtFindBestMatch_selectMLS (
|
|
|
ZSTD_matchState_t* ms, ZSTD_compressionParameters const* cParams,
|
|
|
const BYTE* ip, const BYTE* const iLimit,
|
|
|
size_t* offsetPtr)
|
|
|
{
|
|
|
switch(cParams->searchLength)
|
|
|
{
|
|
|
default : /* includes case 3 */
|
|
|
case 4 : return ZSTD_BtFindBestMatch(ms, cParams, ip, iLimit, offsetPtr, 4);
|
|
|
case 5 : return ZSTD_BtFindBestMatch(ms, cParams, ip, iLimit, offsetPtr, 5);
|
|
|
case 7 :
|
|
|
case 6 : return ZSTD_BtFindBestMatch(ms, cParams, ip, iLimit, offsetPtr, 6);
|
|
|
}
|
|
|
}
|
|
|
|
|
|
|
|
|
/** Tree updater, providing best match */
|
|
|
static size_t ZSTD_BtFindBestMatch_extDict (
|
|
|
ZSTD_matchState_t* ms, ZSTD_compressionParameters const* cParams,
|
|
|
const BYTE* const ip, const BYTE* const iLimit,
|
|
|
size_t* offsetPtr,
|
|
|
const U32 mls)
|
|
|
{
|
|
|
DEBUGLOG(7, "ZSTD_BtFindBestMatch_extDict");
|
|
|
if (ip < ms->window.base + ms->nextToUpdate) return 0; /* skipped area */
|
|
|
ZSTD_updateDUBT(ms, cParams, ip, iLimit, mls);
|
|
|
return ZSTD_DUBT_findBestMatch(ms, cParams, ip, iLimit, offsetPtr, mls, 1);
|
|
|
}
|
|
|
|
|
|
|
|
|
static size_t ZSTD_BtFindBestMatch_selectMLS_extDict (
|
|
|
ZSTD_matchState_t* ms, ZSTD_compressionParameters const* cParams,
|
|
|
const BYTE* ip, const BYTE* const iLimit,
|
|
|
size_t* offsetPtr)
|
|
|
{
|
|
|
switch(cParams->searchLength)
|
|
|
{
|
|
|
default : /* includes case 3 */
|
|
|
case 4 : return ZSTD_BtFindBestMatch_extDict(ms, cParams, ip, iLimit, offsetPtr, 4);
|
|
|
case 5 : return ZSTD_BtFindBestMatch_extDict(ms, cParams, ip, iLimit, offsetPtr, 5);
|
|
|
case 7 :
|
|
|
case 6 : return ZSTD_BtFindBestMatch_extDict(ms, cParams, ip, iLimit, offsetPtr, 6);
|
|
|
}
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/* *********************************
|
|
|
* Hash Chain
|
|
|
***********************************/
|
|
|
#define NEXT_IN_CHAIN(d, mask) chainTable[(d) & mask]
|
|
|
|
|
|
/* Update chains up to ip (excluded)
|
|
|
Assumption : always within prefix (i.e. not within extDict) */
|
|
|
static U32 ZSTD_insertAndFindFirstIndex_internal(
|
|
|
ZSTD_matchState_t* ms, ZSTD_compressionParameters const* cParams,
|
|
|
const BYTE* ip, U32 const mls)
|
|
|
{
|
|
|
U32* const hashTable = ms->hashTable;
|
|
|
const U32 hashLog = cParams->hashLog;
|
|
|
U32* const chainTable = ms->chainTable;
|
|
|
const U32 chainMask = (1 << cParams->chainLog) - 1;
|
|
|
const BYTE* const base = ms->window.base;
|
|
|
const U32 target = (U32)(ip - base);
|
|
|
U32 idx = ms->nextToUpdate;
|
|
|
|
|
|
while(idx < target) { /* catch up */
|
|
|
size_t const h = ZSTD_hashPtr(base+idx, hashLog, mls);
|
|
|
NEXT_IN_CHAIN(idx, chainMask) = hashTable[h];
|
|
|
hashTable[h] = idx;
|
|
|
idx++;
|
|
|
}
|
|
|
|
|
|
ms->nextToUpdate = target;
|
|
|
return hashTable[ZSTD_hashPtr(ip, hashLog, mls)];
|
|
|
}
|
|
|
|
|
|
U32 ZSTD_insertAndFindFirstIndex(
|
|
|
ZSTD_matchState_t* ms, ZSTD_compressionParameters const* cParams,
|
|
|
const BYTE* ip)
|
|
|
{
|
|
|
return ZSTD_insertAndFindFirstIndex_internal(ms, cParams, ip, cParams->searchLength);
|
|
|
}
|
|
|
|
|
|
|
|
|
/* inlining is important to hardwire a hot branch (template emulation) */
|
|
|
FORCE_INLINE_TEMPLATE
|
|
|
size_t ZSTD_HcFindBestMatch_generic (
|
|
|
ZSTD_matchState_t* ms, ZSTD_compressionParameters const* cParams,
|
|
|
const BYTE* const ip, const BYTE* const iLimit,
|
|
|
size_t* offsetPtr,
|
|
|
const U32 mls, const U32 extDict)
|
|
|
{
|
|
|
U32* const chainTable = ms->chainTable;
|
|
|
const U32 chainSize = (1 << cParams->chainLog);
|
|
|
const U32 chainMask = chainSize-1;
|
|
|
const BYTE* const base = ms->window.base;
|
|
|
const BYTE* const dictBase = ms->window.dictBase;
|
|
|
const U32 dictLimit = ms->window.dictLimit;
|
|
|
const BYTE* const prefixStart = base + dictLimit;
|
|
|
const BYTE* const dictEnd = dictBase + dictLimit;
|
|
|
const U32 lowLimit = ms->window.lowLimit;
|
|
|
const U32 current = (U32)(ip-base);
|
|
|
const U32 minChain = current > chainSize ? current - chainSize : 0;
|
|
|
U32 nbAttempts = 1U << cParams->searchLog;
|
|
|
size_t ml=4-1;
|
|
|
|
|
|
/* HC4 match finder */
|
|
|
U32 matchIndex = ZSTD_insertAndFindFirstIndex_internal(ms, cParams, ip, mls);
|
|
|
|
|
|
for ( ; (matchIndex>lowLimit) & (nbAttempts>0) ; nbAttempts--) {
|
|
|
size_t currentMl=0;
|
|
|
if ((!extDict) || matchIndex >= dictLimit) {
|
|
|
const BYTE* const match = base + matchIndex;
|
|
|
if (match[ml] == ip[ml]) /* potentially better */
|
|
|
currentMl = ZSTD_count(ip, match, iLimit);
|
|
|
} else {
|
|
|
const BYTE* const match = dictBase + matchIndex;
|
|
|
assert(match+4 <= dictEnd);
|
|
|
if (MEM_read32(match) == MEM_read32(ip)) /* assumption : matchIndex <= dictLimit-4 (by table construction) */
|
|
|
currentMl = ZSTD_count_2segments(ip+4, match+4, iLimit, dictEnd, prefixStart) + 4;
|
|
|
}
|
|
|
|
|
|
/* save best solution */
|
|
|
if (currentMl > ml) {
|
|
|
ml = currentMl;
|
|
|
*offsetPtr = current - matchIndex + ZSTD_REP_MOVE;
|
|
|
if (ip+currentMl == iLimit) break; /* best possible, avoids read overflow on next attempt */
|
|
|
}
|
|
|
|
|
|
if (matchIndex <= minChain) break;
|
|
|
matchIndex = NEXT_IN_CHAIN(matchIndex, chainMask);
|
|
|
}
|
|
|
|
|
|
return ml;
|
|
|
}
|
|
|
|
|
|
|
|
|
FORCE_INLINE_TEMPLATE size_t ZSTD_HcFindBestMatch_selectMLS (
|
|
|
ZSTD_matchState_t* ms, ZSTD_compressionParameters const* cParams,
|
|
|
const BYTE* ip, const BYTE* const iLimit,
|
|
|
size_t* offsetPtr)
|
|
|
{
|
|
|
switch(cParams->searchLength)
|
|
|
{
|
|
|
default : /* includes case 3 */
|
|
|
case 4 : return ZSTD_HcFindBestMatch_generic(ms, cParams, ip, iLimit, offsetPtr, 4, 0);
|
|
|
case 5 : return ZSTD_HcFindBestMatch_generic(ms, cParams, ip, iLimit, offsetPtr, 5, 0);
|
|
|
case 7 :
|
|
|
case 6 : return ZSTD_HcFindBestMatch_generic(ms, cParams, ip, iLimit, offsetPtr, 6, 0);
|
|
|
}
|
|
|
}
|
|
|
|
|
|
|
|
|
FORCE_INLINE_TEMPLATE size_t ZSTD_HcFindBestMatch_extDict_selectMLS (
|
|
|
ZSTD_matchState_t* ms, ZSTD_compressionParameters const* cParams,
|
|
|
const BYTE* ip, const BYTE* const iLimit,
|
|
|
size_t* const offsetPtr)
|
|
|
{
|
|
|
switch(cParams->searchLength)
|
|
|
{
|
|
|
default : /* includes case 3 */
|
|
|
case 4 : return ZSTD_HcFindBestMatch_generic(ms, cParams, ip, iLimit, offsetPtr, 4, 1);
|
|
|
case 5 : return ZSTD_HcFindBestMatch_generic(ms, cParams, ip, iLimit, offsetPtr, 5, 1);
|
|
|
case 7 :
|
|
|
case 6 : return ZSTD_HcFindBestMatch_generic(ms, cParams, ip, iLimit, offsetPtr, 6, 1);
|
|
|
}
|
|
|
}
|
|
|
|
|
|
|
|
|
/* *******************************
|
|
|
* Common parser - lazy strategy
|
|
|
*********************************/
|
|
|
FORCE_INLINE_TEMPLATE
|
|
|
size_t ZSTD_compressBlock_lazy_generic(
|
|
|
ZSTD_matchState_t* ms, seqStore_t* seqStore,
|
|
|
U32 rep[ZSTD_REP_NUM],
|
|
|
ZSTD_compressionParameters const* cParams,
|
|
|
const void* src, size_t srcSize,
|
|
|
const U32 searchMethod, const U32 depth)
|
|
|
{
|
|
|
const BYTE* const istart = (const BYTE*)src;
|
|
|
const BYTE* ip = istart;
|
|
|
const BYTE* anchor = istart;
|
|
|
const BYTE* const iend = istart + srcSize;
|
|
|
const BYTE* const ilimit = iend - 8;
|
|
|
const BYTE* const base = ms->window.base + ms->window.dictLimit;
|
|
|
|
|
|
typedef size_t (*searchMax_f)(
|
|
|
ZSTD_matchState_t* ms, ZSTD_compressionParameters const* cParams,
|
|
|
const BYTE* ip, const BYTE* iLimit, size_t* offsetPtr);
|
|
|
searchMax_f const searchMax = searchMethod ? ZSTD_BtFindBestMatch_selectMLS : ZSTD_HcFindBestMatch_selectMLS;
|
|
|
U32 offset_1 = rep[0], offset_2 = rep[1], savedOffset=0;
|
|
|
|
|
|
/* init */
|
|
|
ip += (ip==base);
|
|
|
ms->nextToUpdate3 = ms->nextToUpdate;
|
|
|
{ U32 const maxRep = (U32)(ip-base);
|
|
|
if (offset_2 > maxRep) savedOffset = offset_2, offset_2 = 0;
|
|
|
if (offset_1 > maxRep) savedOffset = offset_1, offset_1 = 0;
|
|
|
}
|
|
|
|
|
|
/* Match Loop */
|
|
|
while (ip < ilimit) {
|
|
|
size_t matchLength=0;
|
|
|
size_t offset=0;
|
|
|
const BYTE* start=ip+1;
|
|
|
|
|
|
/* check repCode */
|
|
|
if ((offset_1>0) & (MEM_read32(ip+1) == MEM_read32(ip+1 - offset_1))) {
|
|
|
/* repcode : we take it */
|
|
|
matchLength = ZSTD_count(ip+1+4, ip+1+4-offset_1, iend) + 4;
|
|
|
if (depth==0) goto _storeSequence;
|
|
|
}
|
|
|
|
|
|
/* first search (depth 0) */
|
|
|
{ size_t offsetFound = 99999999;
|
|
|
size_t const ml2 = searchMax(ms, cParams, ip, iend, &offsetFound);
|
|
|
if (ml2 > matchLength)
|
|
|
matchLength = ml2, start = ip, offset=offsetFound;
|
|
|
}
|
|
|
|
|
|
if (matchLength < 4) {
|
|
|
ip += ((ip-anchor) >> kSearchStrength) + 1; /* jump faster over incompressible sections */
|
|
|
continue;
|
|
|
}
|
|
|
|
|
|
/* let's try to find a better solution */
|
|
|
if (depth>=1)
|
|
|
while (ip<ilimit) {
|
|
|
ip ++;
|
|
|
if ((offset) && ((offset_1>0) & (MEM_read32(ip) == MEM_read32(ip - offset_1)))) {
|
|
|
size_t const mlRep = ZSTD_count(ip+4, ip+4-offset_1, iend) + 4;
|
|
|
int const gain2 = (int)(mlRep * 3);
|
|
|
int const gain1 = (int)(matchLength*3 - ZSTD_highbit32((U32)offset+1) + 1);
|
|
|
if ((mlRep >= 4) && (gain2 > gain1))
|
|
|
matchLength = mlRep, offset = 0, start = ip;
|
|
|
}
|
|
|
{ size_t offset2=99999999;
|
|
|
size_t const ml2 = searchMax(ms, cParams, ip, iend, &offset2);
|
|
|
int const gain2 = (int)(ml2*4 - ZSTD_highbit32((U32)offset2+1)); /* raw approx */
|
|
|
int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)offset+1) + 4);
|
|
|
if ((ml2 >= 4) && (gain2 > gain1)) {
|
|
|
matchLength = ml2, offset = offset2, start = ip;
|
|
|
continue; /* search a better one */
|
|
|
} }
|
|
|
|
|
|
/* let's find an even better one */
|
|
|
if ((depth==2) && (ip<ilimit)) {
|
|
|
ip ++;
|
|
|
if ((offset) && ((offset_1>0) & (MEM_read32(ip) == MEM_read32(ip - offset_1)))) {
|
|
|
size_t const ml2 = ZSTD_count(ip+4, ip+4-offset_1, iend) + 4;
|
|
|
int const gain2 = (int)(ml2 * 4);
|
|
|
int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)offset+1) + 1);
|
|
|
if ((ml2 >= 4) && (gain2 > gain1))
|
|
|
matchLength = ml2, offset = 0, start = ip;
|
|
|
}
|
|
|
{ size_t offset2=99999999;
|
|
|
size_t const ml2 = searchMax(ms, cParams, ip, iend, &offset2);
|
|
|
int const gain2 = (int)(ml2*4 - ZSTD_highbit32((U32)offset2+1)); /* raw approx */
|
|
|
int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)offset+1) + 7);
|
|
|
if ((ml2 >= 4) && (gain2 > gain1)) {
|
|
|
matchLength = ml2, offset = offset2, start = ip;
|
|
|
continue;
|
|
|
} } }
|
|
|
break; /* nothing found : store previous solution */
|
|
|
}
|
|
|
|
|
|
/* NOTE:
|
|
|
* start[-offset+ZSTD_REP_MOVE-1] is undefined behavior.
|
|
|
* (-offset+ZSTD_REP_MOVE-1) is unsigned, and is added to start, which
|
|
|
* overflows the pointer, which is undefined behavior.
|
|
|
*/
|
|
|
/* catch up */
|
|
|
if (offset) {
|
|
|
while ( ((start > anchor) & (start - (offset-ZSTD_REP_MOVE) > base))
|
|
|
&& (start[-1] == (start-(offset-ZSTD_REP_MOVE))[-1]) ) /* only search for offset within prefix */
|
|
|
{ start--; matchLength++; }
|
|
|
offset_2 = offset_1; offset_1 = (U32)(offset - ZSTD_REP_MOVE);
|
|
|
}
|
|
|
/* store sequence */
|
|
|
_storeSequence:
|
|
|
{ size_t const litLength = start - anchor;
|
|
|
ZSTD_storeSeq(seqStore, litLength, anchor, (U32)offset, matchLength-MINMATCH);
|
|
|
anchor = ip = start + matchLength;
|
|
|
}
|
|
|
|
|
|
/* check immediate repcode */
|
|
|
while ( ((ip <= ilimit) & (offset_2>0))
|
|
|
&& (MEM_read32(ip) == MEM_read32(ip - offset_2)) ) {
|
|
|
/* store sequence */
|
|
|
matchLength = ZSTD_count(ip+4, ip+4-offset_2, iend) + 4;
|
|
|
offset = offset_2; offset_2 = offset_1; offset_1 = (U32)offset; /* swap repcodes */
|
|
|
ZSTD_storeSeq(seqStore, 0, anchor, 0, matchLength-MINMATCH);
|
|
|
ip += matchLength;
|
|
|
anchor = ip;
|
|
|
continue; /* faster when present ... (?) */
|
|
|
} }
|
|
|
|
|
|
/* Save reps for next block */
|
|
|
rep[0] = offset_1 ? offset_1 : savedOffset;
|
|
|
rep[1] = offset_2 ? offset_2 : savedOffset;
|
|
|
|
|
|
/* Return the last literals size */
|
|
|
return iend - anchor;
|
|
|
}
|
|
|
|
|
|
|
|
|
size_t ZSTD_compressBlock_btlazy2(
|
|
|
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
|
|
|
ZSTD_compressionParameters const* cParams, void const* src, size_t srcSize)
|
|
|
{
|
|
|
return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, cParams, src, srcSize, 1, 2);
|
|
|
}
|
|
|
|
|
|
size_t ZSTD_compressBlock_lazy2(
|
|
|
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
|
|
|
ZSTD_compressionParameters const* cParams, void const* src, size_t srcSize)
|
|
|
{
|
|
|
return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, cParams, src, srcSize, 0, 2);
|
|
|
}
|
|
|
|
|
|
size_t ZSTD_compressBlock_lazy(
|
|
|
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
|
|
|
ZSTD_compressionParameters const* cParams, void const* src, size_t srcSize)
|
|
|
{
|
|
|
return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, cParams, src, srcSize, 0, 1);
|
|
|
}
|
|
|
|
|
|
size_t ZSTD_compressBlock_greedy(
|
|
|
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
|
|
|
ZSTD_compressionParameters const* cParams, void const* src, size_t srcSize)
|
|
|
{
|
|
|
return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, cParams, src, srcSize, 0, 0);
|
|
|
}
|
|
|
|
|
|
|
|
|
FORCE_INLINE_TEMPLATE
|
|
|
size_t ZSTD_compressBlock_lazy_extDict_generic(
|
|
|
ZSTD_matchState_t* ms, seqStore_t* seqStore,
|
|
|
U32 rep[ZSTD_REP_NUM],
|
|
|
ZSTD_compressionParameters const* cParams,
|
|
|
const void* src, size_t srcSize,
|
|
|
const U32 searchMethod, const U32 depth)
|
|
|
{
|
|
|
const BYTE* const istart = (const BYTE*)src;
|
|
|
const BYTE* ip = istart;
|
|
|
const BYTE* anchor = istart;
|
|
|
const BYTE* const iend = istart + srcSize;
|
|
|
const BYTE* const ilimit = iend - 8;
|
|
|
const BYTE* const base = ms->window.base;
|
|
|
const U32 dictLimit = ms->window.dictLimit;
|
|
|
const U32 lowestIndex = ms->window.lowLimit;
|
|
|
const BYTE* const prefixStart = base + dictLimit;
|
|
|
const BYTE* const dictBase = ms->window.dictBase;
|
|
|
const BYTE* const dictEnd = dictBase + dictLimit;
|
|
|
const BYTE* const dictStart = dictBase + lowestIndex;
|
|
|
|
|
|
typedef size_t (*searchMax_f)(
|
|
|
ZSTD_matchState_t* ms, ZSTD_compressionParameters const* cParams,
|
|
|
const BYTE* ip, const BYTE* iLimit, size_t* offsetPtr);
|
|
|
searchMax_f searchMax = searchMethod ? ZSTD_BtFindBestMatch_selectMLS_extDict : ZSTD_HcFindBestMatch_extDict_selectMLS;
|
|
|
|
|
|
U32 offset_1 = rep[0], offset_2 = rep[1];
|
|
|
|
|
|
/* init */
|
|
|
ms->nextToUpdate3 = ms->nextToUpdate;
|
|
|
ip += (ip == prefixStart);
|
|
|
|
|
|
/* Match Loop */
|
|
|
while (ip < ilimit) {
|
|
|
size_t matchLength=0;
|
|
|
size_t offset=0;
|
|
|
const BYTE* start=ip+1;
|
|
|
U32 current = (U32)(ip-base);
|
|
|
|
|
|
/* check repCode */
|
|
|
{ const U32 repIndex = (U32)(current+1 - offset_1);
|
|
|
const BYTE* const repBase = repIndex < dictLimit ? dictBase : base;
|
|
|
const BYTE* const repMatch = repBase + repIndex;
|
|
|
if (((U32)((dictLimit-1) - repIndex) >= 3) & (repIndex > lowestIndex)) /* intentional overflow */
|
|
|
if (MEM_read32(ip+1) == MEM_read32(repMatch)) {
|
|
|
/* repcode detected we should take it */
|
|
|
const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend;
|
|
|
matchLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repEnd, prefixStart) + 4;
|
|
|
if (depth==0) goto _storeSequence;
|
|
|
} }
|
|
|
|
|
|
/* first search (depth 0) */
|
|
|
{ size_t offsetFound = 99999999;
|
|
|
size_t const ml2 = searchMax(ms, cParams, ip, iend, &offsetFound);
|
|
|
if (ml2 > matchLength)
|
|
|
matchLength = ml2, start = ip, offset=offsetFound;
|
|
|
}
|
|
|
|
|
|
if (matchLength < 4) {
|
|
|
ip += ((ip-anchor) >> kSearchStrength) + 1; /* jump faster over incompressible sections */
|
|
|
continue;
|
|
|
}
|
|
|
|
|
|
/* let's try to find a better solution */
|
|
|
if (depth>=1)
|
|
|
while (ip<ilimit) {
|
|
|
ip ++;
|
|
|
current++;
|
|
|
/* check repCode */
|
|
|
if (offset) {
|
|
|
const U32 repIndex = (U32)(current - offset_1);
|
|
|
const BYTE* const repBase = repIndex < dictLimit ? dictBase : base;
|
|
|
const BYTE* const repMatch = repBase + repIndex;
|
|
|
if (((U32)((dictLimit-1) - repIndex) >= 3) & (repIndex > lowestIndex)) /* intentional overflow */
|
|
|
if (MEM_read32(ip) == MEM_read32(repMatch)) {
|
|
|
/* repcode detected */
|
|
|
const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend;
|
|
|
size_t const repLength = ZSTD_count_2segments(ip+4, repMatch+4, iend, repEnd, prefixStart) + 4;
|
|
|
int const gain2 = (int)(repLength * 3);
|
|
|
int const gain1 = (int)(matchLength*3 - ZSTD_highbit32((U32)offset+1) + 1);
|
|
|
if ((repLength >= 4) && (gain2 > gain1))
|
|
|
matchLength = repLength, offset = 0, start = ip;
|
|
|
} }
|
|
|
|
|
|
/* search match, depth 1 */
|
|
|
{ size_t offset2=99999999;
|
|
|
size_t const ml2 = searchMax(ms, cParams, ip, iend, &offset2);
|
|
|
int const gain2 = (int)(ml2*4 - ZSTD_highbit32((U32)offset2+1)); /* raw approx */
|
|
|
int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)offset+1) + 4);
|
|
|
if ((ml2 >= 4) && (gain2 > gain1)) {
|
|
|
matchLength = ml2, offset = offset2, start = ip;
|
|
|
continue; /* search a better one */
|
|
|
} }
|
|
|
|
|
|
/* let's find an even better one */
|
|
|
if ((depth==2) && (ip<ilimit)) {
|
|
|
ip ++;
|
|
|
current++;
|
|
|
/* check repCode */
|
|
|
if (offset) {
|
|
|
const U32 repIndex = (U32)(current - offset_1);
|
|
|
const BYTE* const repBase = repIndex < dictLimit ? dictBase : base;
|
|
|
const BYTE* const repMatch = repBase + repIndex;
|
|
|
if (((U32)((dictLimit-1) - repIndex) >= 3) & (repIndex > lowestIndex)) /* intentional overflow */
|
|
|
if (MEM_read32(ip) == MEM_read32(repMatch)) {
|
|
|
/* repcode detected */
|
|
|
const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend;
|
|
|
size_t const repLength = ZSTD_count_2segments(ip+4, repMatch+4, iend, repEnd, prefixStart) + 4;
|
|
|
int const gain2 = (int)(repLength * 4);
|
|
|
int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)offset+1) + 1);
|
|
|
if ((repLength >= 4) && (gain2 > gain1))
|
|
|
matchLength = repLength, offset = 0, start = ip;
|
|
|
} }
|
|
|
|
|
|
/* search match, depth 2 */
|
|
|
{ size_t offset2=99999999;
|
|
|
size_t const ml2 = searchMax(ms, cParams, ip, iend, &offset2);
|
|
|
int const gain2 = (int)(ml2*4 - ZSTD_highbit32((U32)offset2+1)); /* raw approx */
|
|
|
int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)offset+1) + 7);
|
|
|
if ((ml2 >= 4) && (gain2 > gain1)) {
|
|
|
matchLength = ml2, offset = offset2, start = ip;
|
|
|
continue;
|
|
|
} } }
|
|
|
break; /* nothing found : store previous solution */
|
|
|
}
|
|
|
|
|
|
/* catch up */
|
|
|
if (offset) {
|
|
|
U32 const matchIndex = (U32)((start-base) - (offset - ZSTD_REP_MOVE));
|
|
|
const BYTE* match = (matchIndex < dictLimit) ? dictBase + matchIndex : base + matchIndex;
|
|
|
const BYTE* const mStart = (matchIndex < dictLimit) ? dictStart : prefixStart;
|
|
|
while ((start>anchor) && (match>mStart) && (start[-1] == match[-1])) { start--; match--; matchLength++; } /* catch up */
|
|
|
offset_2 = offset_1; offset_1 = (U32)(offset - ZSTD_REP_MOVE);
|
|
|
}
|
|
|
|
|
|
/* store sequence */
|
|
|
_storeSequence:
|
|
|
{ size_t const litLength = start - anchor;
|
|
|
ZSTD_storeSeq(seqStore, litLength, anchor, (U32)offset, matchLength-MINMATCH);
|
|
|
anchor = ip = start + matchLength;
|
|
|
}
|
|
|
|
|
|
/* check immediate repcode */
|
|
|
while (ip <= ilimit) {
|
|
|
const U32 repIndex = (U32)((ip-base) - offset_2);
|
|
|
const BYTE* const repBase = repIndex < dictLimit ? dictBase : base;
|
|
|
const BYTE* const repMatch = repBase + repIndex;
|
|
|
if (((U32)((dictLimit-1) - repIndex) >= 3) & (repIndex > lowestIndex)) /* intentional overflow */
|
|
|
if (MEM_read32(ip) == MEM_read32(repMatch)) {
|
|
|
/* repcode detected we should take it */
|
|
|
const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend;
|
|
|
matchLength = ZSTD_count_2segments(ip+4, repMatch+4, iend, repEnd, prefixStart) + 4;
|
|
|
offset = offset_2; offset_2 = offset_1; offset_1 = (U32)offset; /* swap offset history */
|
|
|
ZSTD_storeSeq(seqStore, 0, anchor, 0, matchLength-MINMATCH);
|
|
|
ip += matchLength;
|
|
|
anchor = ip;
|
|
|
continue; /* faster when present ... (?) */
|
|
|
}
|
|
|
break;
|
|
|
} }
|
|
|
|
|
|
/* Save reps for next block */
|
|
|
rep[0] = offset_1;
|
|
|
rep[1] = offset_2;
|
|
|
|
|
|
/* Return the last literals size */
|
|
|
return iend - anchor;
|
|
|
}
|
|
|
|
|
|
|
|
|
size_t ZSTD_compressBlock_greedy_extDict(
|
|
|
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
|
|
|
ZSTD_compressionParameters const* cParams, void const* src, size_t srcSize)
|
|
|
{
|
|
|
return ZSTD_compressBlock_lazy_extDict_generic(ms, seqStore, rep, cParams, src, srcSize, 0, 0);
|
|
|
}
|
|
|
|
|
|
size_t ZSTD_compressBlock_lazy_extDict(
|
|
|
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
|
|
|
ZSTD_compressionParameters const* cParams, void const* src, size_t srcSize)
|
|
|
|
|
|
{
|
|
|
return ZSTD_compressBlock_lazy_extDict_generic(ms, seqStore, rep, cParams, src, srcSize, 0, 1);
|
|
|
}
|
|
|
|
|
|
size_t ZSTD_compressBlock_lazy2_extDict(
|
|
|
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
|
|
|
ZSTD_compressionParameters const* cParams, void const* src, size_t srcSize)
|
|
|
|
|
|
{
|
|
|
return ZSTD_compressBlock_lazy_extDict_generic(ms, seqStore, rep, cParams, src, srcSize, 0, 2);
|
|
|
}
|
|
|
|
|
|
size_t ZSTD_compressBlock_btlazy2_extDict(
|
|
|
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
|
|
|
ZSTD_compressionParameters const* cParams, void const* src, size_t srcSize)
|
|
|
|
|
|
{
|
|
|
return ZSTD_compressBlock_lazy_extDict_generic(ms, seqStore, rep, cParams, src, srcSize, 1, 2);
|
|
|
}
|
|
|
|
