ext/zstdruby/libzstd/compress/zstd_fast.c in zstd-ruby-1.4.0.0 vs ext/zstdruby/libzstd/compress/zstd_fast.c in zstd-ruby-1.4.1.0
- old
+ new
@@ -11,11 +11,12 @@
#include "zstd_compress_internal.h"
#include "zstd_fast.h"
void ZSTD_fillHashTable(ZSTD_matchState_t* ms,
- void const* end, ZSTD_dictTableLoadMethod_e dtlm)
+ const void* const end,
+ ZSTD_dictTableLoadMethod_e dtlm)
{
const ZSTD_compressionParameters* const cParams = &ms->cParams;
U32* const hashTable = ms->hashTable;
U32 const hBits = cParams->hashLog;
U32 const mls = cParams->minMatch;
@@ -39,10 +40,11 @@
if (hashTable[hash] == 0) { /* not yet filled */
hashTable[hash] = current + p;
} } } }
}
+
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,
U32 const mls)
@@ -56,11 +58,14 @@
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 prefixStartIndex = ms->window.dictLimit;
+ 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;
@@ -163,11 +168,11 @@
/* 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 iend - anchor;
+ return (size_t)(iend - anchor);
}
size_t ZSTD_compressBlock_fast(
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
@@ -220,12 +225,19 @@
const BYTE* const dictEnd = dms->window.nextSrc;
const U32 dictIndexDelta = prefixStartIndex - (U32)(dictEnd - dictBase);
const U32 dictAndPrefixLength = (U32)(ip - prefixStart + dictEnd - dictStart);
const U32 dictHLog = dictCParams->hashLog;
- /* otherwise, we would get index underflow when translating a dict index
- * into a local index */
+ /* 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));
/* init */
ip += (dictAndPrefixLength == 0);
/* dictMatchState repCode checks don't currently handle repCode == 0
@@ -249,11 +261,11 @@
if ( ((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow : ensure repIndex isn't overlapping dict + prefix */
&& (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++;
- ZSTD_storeSeq(seqStore, ip-anchor, anchor, 0, mLength-MINMATCH);
+ ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, 0, mLength-MINMATCH);
} else if ( (matchIndex <= prefixStartIndex) ) {
size_t const dictHash = ZSTD_hashPtr(ip, dictHLog, mls);
U32 const dictMatchIndex = dictHashTable[dictHash];
const BYTE* dictMatch = dictBase + dictMatchIndex;
if (dictMatchIndex <= dictStartIndex ||
@@ -269,11 +281,11 @@
&& (ip[-1] == dictMatch[-1])) {
ip--; dictMatch--; mLength++;
} /* catch up */
offset_2 = offset_1;
offset_1 = offset;
- ZSTD_storeSeq(seqStore, ip-anchor, anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
+ ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
}
} 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;
@@ -284,11 +296,11 @@
mLength = ZSTD_count(ip+4, match+4, iend) + 4;
while (((ip>anchor) & (match>prefixStart))
&& (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */
offset_2 = offset_1;
offset_1 = offset;
- ZSTD_storeSeq(seqStore, ip-anchor, anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
+ ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
}
/* match found */
ip += mLength;
anchor = ip;
@@ -325,11 +337,11 @@
/* 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 iend - anchor;
+ return (size_t)(iend - anchor);
}
size_t ZSTD_compressBlock_fast_dictMatchState(
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize)
@@ -364,19 +376,28 @@
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;
- const U32 dictStartIndex = ms->window.lowLimit;
+ const U32 endIndex = (U32)((size_t)(istart - base) + srcSize);
+ const U32 maxDistance = 1U << cParams->windowLog;
+ const U32 validLow = ms->window.lowLimit;
+ const U32 lowLimit = (endIndex - validLow > maxDistance) ? endIndex - maxDistance : validLow;
+ const U32 dictStartIndex = lowLimit;
const BYTE* const dictStart = dictBase + dictStartIndex;
- const U32 prefixStartIndex = ms->window.dictLimit;
+ const U32 dictLimit = ms->window.dictLimit;
+ const U32 prefixStartIndex = dictLimit < lowLimit ? lowLimit : dictLimit;
const BYTE* const prefixStart = base + prefixStartIndex;
const BYTE* const dictEnd = dictBase + prefixStartIndex;
const BYTE* const iend = istart + srcSize;
const BYTE* const ilimit = iend - 8;
U32 offset_1=rep[0], offset_2=rep[1];
+ /* 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);
+
/* Search Loop */
while (ip < ilimit) { /* < instead of <=, because (ip+1) */
const size_t h = ZSTD_hashPtr(ip, hlog, mls);
const U32 matchIndex = hashTable[h];
const BYTE* const matchBase = matchIndex < prefixStartIndex ? dictBase : base;
@@ -392,11 +413,11 @@
if ( (((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow */ & (repIndex > dictStartIndex))
&& (MEM_read32(repMatch) == MEM_read32(ip+1)) ) {
const BYTE* repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend;
mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixStart) + 4;
ip++;
- ZSTD_storeSeq(seqStore, ip-anchor, anchor, 0, mLength-MINMATCH);
+ ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, 0, mLength-MINMATCH);
} else {
if ( (matchIndex < dictStartIndex) ||
(MEM_read32(match) != MEM_read32(ip)) ) {
assert(stepSize >= 1);
ip += ((ip-anchor) >> kSearchStrength) + stepSize;
@@ -408,11 +429,11 @@
mLength = ZSTD_count_2segments(ip+4, match+4, iend, matchEnd, prefixStart) + 4;
while (((ip>anchor) & (match>lowMatchPtr)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */
offset = current - matchIndex;
offset_2 = offset_1;
offset_1 = offset;
- ZSTD_storeSeq(seqStore, ip-anchor, anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
+ ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
} }
/* found a match : store it */
ip += mLength;
anchor = ip;
@@ -443,10 +464,10 @@
/* save reps for next block */
rep[0] = offset_1;
rep[1] = offset_2;
/* Return the last literals size */
- return iend - anchor;
+ return (size_t)(iend - anchor);
}
size_t ZSTD_compressBlock_fast_extDict(
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],