krak/zstd
krak/zstd
1
0
Fork 0
mirror of https://github.com/facebook/zstd.git synced 2025-03-07 01:10:04 +02:00
Code Issues Releases 1 Activity

Merge pull request #1362 from felixhandte/fix-btlazy-skipping

Browse Source 
`ZSTD_btlazy2`: Avoid Erroneously Trampling on Match with Worse Dictionary Match
This commit is contained in:
Yann Collet 2018-10-08 17:06:43 -07:00 committed by GitHub
commit 92192b267c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 13 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
lib/compress/zstd_lazy.c
View File

@ -147,6 +147,7 @@ ZSTD_DUBT_findBetterDictMatch (
ZSTD_matchState_t* ms, ZSTD_matchState_t* ms,
const BYTE* const ip, const BYTE* const iend, const BYTE* const ip, const BYTE* const iend,
size_t* offsetPtr, size_t* offsetPtr,
size_t bestLength,
U32 nbCompares, U32 nbCompares,
U32 const mls, U32 const mls,
const ZSTD_dictMode_e dictMode) const ZSTD_dictMode_e dictMode)
@ -172,8 +173,7 @@ ZSTD_DUBT_findBetterDictMatch (
U32 const btMask = (1 << btLog) - 1; U32 const btMask = (1 << btLog) - 1;
U32 const btLow = (btMask >= dictHighLimit - dictLowLimit) ? dictLowLimit : dictHighLimit - btMask; U32 const btLow = (btMask >= dictHighLimit - dictLowLimit) ? dictLowLimit : dictHighLimit - btMask;
size_t commonLengthSmaller=0, commonLengthLarger=0, bestLength=0; size_t commonLengthSmaller=0, commonLengthLarger=0;
U32 matchEndIdx = current+8+1;
(void)dictMode; (void)dictMode;
assert(dictMode == ZSTD_dictMatchState); assert(dictMode == ZSTD_dictMatchState);
@ -188,10 +188,8 @@ ZSTD_DUBT_findBetterDictMatch (
if (matchLength > bestLength) { if (matchLength > bestLength) {
U32 matchIndex = dictMatchIndex + dictIndexDelta; U32 matchIndex = dictMatchIndex + dictIndexDelta;
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)) ) { if ( (4*(int)(matchLength-bestLength)) > (int)(ZSTD_highbit32(current-matchIndex+1) - ZSTD_highbit32((U32)offsetPtr[0]+1)) ) {
DEBUGLOG(2, "ZSTD_DUBT_findBestDictMatch(%u) : found better match length %u -> %u and offsetCode %u -> %u (dictMatchIndex %u, matchIndex %u)", DEBUGLOG(9, "ZSTD_DUBT_findBetterDictMatch(%u) : found better match length %u -> %u and offsetCode %u -> %u (dictMatchIndex %u, matchIndex %u)",
current, (U32)bestLength, (U32)matchLength, (U32)*offsetPtr, ZSTD_REP_MOVE + current - matchIndex, dictMatchIndex, matchIndex); current, (U32)bestLength, (U32)matchLength, (U32)*offsetPtr, ZSTD_REP_MOVE + current - matchIndex, dictMatchIndex, matchIndex);
bestLength = matchLength, *offsetPtr = ZSTD_REP_MOVE + current - matchIndex; bestLength = matchLength, *offsetPtr = ZSTD_REP_MOVE + current - matchIndex;
} }
@ -200,7 +198,6 @@ ZSTD_DUBT_findBetterDictMatch (
} }
} }
DEBUGLOG(2, "matchLength:%6zu, match:%p, prefixStart:%p, ip:%p", matchLength, match, prefixStart, ip);
if (match[matchLength] < ip[matchLength]) { if (match[matchLength] < ip[matchLength]) {
if (dictMatchIndex <= btLow) { break; } /* beyond tree size, stop the search */ if (dictMatchIndex <= btLow) { break; } /* beyond tree size, stop the search */
commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */ commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */
@ -215,7 +212,7 @@ ZSTD_DUBT_findBetterDictMatch (
if (bestLength >= MINMATCH) { if (bestLength >= MINMATCH) {
U32 const mIndex = current - ((U32)*offsetPtr - ZSTD_REP_MOVE); (void)mIndex; U32 const mIndex = current - ((U32)*offsetPtr - ZSTD_REP_MOVE); (void)mIndex;
DEBUGLOG(2, "ZSTD_DUBT_findBestDictMatch(%u) : found match of length %u and offsetCode %u (pos %u)", DEBUGLOG(8, "ZSTD_DUBT_findBetterDictMatch(%u) : found match of length %u and offsetCode %u (pos %u)",
current, (U32)bestLength, (U32)*offsetPtr, mIndex); current, (U32)bestLength, (U32)*offsetPtr, mIndex);
} }
return bestLength; return bestLength;
@ -323,6 +320,11 @@ ZSTD_DUBT_findBestMatch(ZSTD_matchState_t* ms,
if ( (4*(int)(matchLength-bestLength)) > (int)(ZSTD_highbit32(current-matchIndex+1) - ZSTD_highbit32((U32)offsetPtr[0]+1)) ) 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; bestLength = matchLength, *offsetPtr = ZSTD_REP_MOVE + current - matchIndex;
if (ip+matchLength == iend) { /* equal : no way to know if inf or sup */ if (ip+matchLength == iend) { /* equal : no way to know if inf or sup */
if (dictMode == ZSTD_dictMatchState) {
nbCompares = 0; /* in addition to avoiding checking any
* further in this loop, make sure we
* skip checking in the dictionary. */
}
break; /* drop, to guarantee consistency (miss a little bit of compression) */ break; /* drop, to guarantee consistency (miss a little bit of compression) */
} }
} }
@ -346,7 +348,10 @@ ZSTD_DUBT_findBestMatch(ZSTD_matchState_t* ms,
*smallerPtr = *largerPtr = 0; *smallerPtr = *largerPtr = 0;
if (dictMode == ZSTD_dictMatchState && nbCompares) { if (dictMode == ZSTD_dictMatchState && nbCompares) {
bestLength = ZSTD_DUBT_findBetterDictMatch(ms, ip, iend, offsetPtr, nbCompares, mls, dictMode); bestLength = ZSTD_DUBT_findBetterDictMatch(
ms, ip, iend,
offsetPtr, bestLength, nbCompares,
mls, dictMode);
} }
assert(matchEndIdx > current+8); /* ensure nextToUpdate is increased */ assert(matchEndIdx > current+8); /* ensure nextToUpdate is increased */