ddidderr/zstd-rs
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

added a test case for dictBuilder failure

Browse Source 
cyclic data set makes the entropy stage fails
now, onto a fix for #304 ...
This commit is contained in:
Yann Collet
2018-01-11 09:42:38 -08:00
parent 06995775b0
commit 218e9fe0fc
5 changed files with 120 additions and 94 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/dictBuilder/zdict.c
+55 -42
View File
@@ -207,7 +207,6 @@ static dictItem ZDICT_analyzePos(
U32 cumulLength[LLIMIT] = {0};
U32 savings[LLIMIT] = {0};
const BYTE* b = (const BYTE*)buffer;
size_t length;
size_t maxLength = LLIMIT;
size_t pos = suffix[start];
U32 end = start;
@@ -222,26 +221,30 @@ static dictItem ZDICT_analyzePos(
||(MEM_read16(b+pos+1) == MEM_read16(b+pos+3))
||(MEM_read16(b+pos+2) == MEM_read16(b+pos+4)) ) {
/* skip and mark segment */
U16 u16 = MEM_read16(b+pos+4);
U32 u, e = 6;
while (MEM_read16(b+pos+e) == u16) e+=2 ;
if (b[pos+e] == b[pos+e-1]) e++;
for (u=1; u<e; u++)
U16 const pattern16 = MEM_read16(b+pos+4);
U32 u, patternEnd = 6;
while (MEM_read16(b+pos+patternEnd) == pattern16) patternEnd+=2 ;
if (b[pos+patternEnd] == b[pos+patternEnd-1]) patternEnd++;
for (u=1; u<patternEnd; u++)
doneMarks[pos+u] = 1;
return solution;
}
/* look forward */
do {
end++;
length = ZDICT_count(b + pos, b + suffix[end]);
} while (length >=MINMATCHLENGTH);
{ size_t length;
do {
end++;
length = ZDICT_count(b + pos, b + suffix[end]);
} while (length >= MINMATCHLENGTH);
}
/* look backward */
do {
length = ZDICT_count(b + pos, b + *(suffix+start-1));
if (length >=MINMATCHLENGTH) start--;
} while(length >= MINMATCHLENGTH);
{ size_t length;
do {
length = ZDICT_count(b + pos, b + *(suffix+start-1));
if (length >=MINMATCHLENGTH) start--;
} while(length >= MINMATCHLENGTH);
}
/* exit if not found a minimum nb of repetitions */
if (end-start < minRatio) {
@@ -268,7 +271,7 @@ static dictItem ZDICT_analyzePos(
U32 selectedCount = 0;
U32 selectedID = currentID;
for (id =refinedStart; id < refinedEnd; id++) {
if (b[ suffix[id] + searchLength] != currentChar) {
if (b[suffix[id] + searchLength] != currentChar) {
if (currentCount > selectedCount) {
selectedCount = currentCount;
selectedID = currentID;
@@ -297,20 +300,23 @@ static dictItem ZDICT_analyzePos(
memset(lengthList, 0, sizeof(lengthList));
/* look forward */
do {
end++;
length = ZDICT_count(b + pos, b + suffix[end]);
if (length >= LLIMIT) length = LLIMIT-1;
lengthList[length]++;
} while (length >=MINMATCHLENGTH);
{ size_t length;
do {
end++;
length = ZDICT_count(b + pos, b + suffix[end]);
if (length >= LLIMIT) length = LLIMIT-1;
lengthList[length]++;
} while (length >=MINMATCHLENGTH);
}
/* look backward */
length = MINMATCHLENGTH;
while ((length >= MINMATCHLENGTH) & (start > 0)) {
length = ZDICT_count(b + pos, b + suffix[start - 1]);
if (length >= LLIMIT) length = LLIMIT - 1;
lengthList[length]++;
if (length >= MINMATCHLENGTH) start--;
{ size_t length = MINMATCHLENGTH;
while ((length >= MINMATCHLENGTH) & (start > 0)) {
length = ZDICT_count(b + pos, b + suffix[start - 1]);
if (length >= LLIMIT) length = LLIMIT - 1;
lengthList[length]++;
if (length >= MINMATCHLENGTH) start--;
}
}
/* largest useful length */
@@ -345,12 +351,12 @@ static dictItem ZDICT_analyzePos(
/* mark positions done */
{ U32 id;
for (id=start; id<end; id++) {
U32 p, pEnd;
U32 p, pEnd, length;
U32 const testedPos = suffix[id];
if (testedPos == pos)
length = solution.length;
else {
length = ZDICT_count(b+pos, b+testedPos);
length = (U32)ZDICT_count(b+pos, b+testedPos);
if (length > solution.length) length = solution.length;
}
pEnd = (U32)(testedPos + length);
@@ -575,29 +581,30 @@ static void ZDICT_fillNoise(void* buffer, size_t length)
typedef struct
{
ZSTD_CCtx* ref;
ZSTD_CCtx* zc;
ZSTD_CCtx* ref; /* contains reference to dictionary */
ZSTD_CCtx* zc; /* working context */
void* workPlace; /* must be ZSTD_BLOCKSIZE_MAX allocated */
} EStats_ress_t;
#define MAXREPOFFSET 1024
static void ZDICT_countEStats(EStats_ress_t esr, ZSTD_parameters params,
U32* countLit, U32* offsetcodeCount, U32* matchlengthCount, U32* litlengthCount, U32* repOffsets,
const void* src, size_t srcSize, U32 notificationLevel)
U32* countLit, U32* offsetcodeCount, U32* matchlengthCount, U32* litlengthCount, U32* repOffsets,
const void* src, size_t srcSize,
U32 notificationLevel)
{
size_t const blockSizeMax = MIN (ZSTD_BLOCKSIZE_MAX, 1 << params.cParams.windowLog);
size_t cSize;
if (srcSize > blockSizeMax) srcSize = blockSizeMax; /* protection vs large samples */
{ size_t const errorCode = ZSTD_copyCCtx(esr.zc, esr.ref, 0);
if (ZSTD_isError(errorCode)) { DISPLAYLEVEL(1, "warning : ZSTD_copyCCtx failed \n"); return; }
{ size_t const errorCode = ZSTD_copyCCtx(esr.zc, esr.ref, 0);
if (ZSTD_isError(errorCode)) { DISPLAYLEVEL(1, "warning : ZSTD_copyCCtx failed \n"); return; }
}
cSize = ZSTD_compressBlock(esr.zc, esr.workPlace, ZSTD_BLOCKSIZE_MAX, src, srcSize);
if (ZSTD_isError(cSize)) { DISPLAYLEVEL(3, "warning : could not compress sample size %u \n", (U32)srcSize); return; }
if (cSize) { /* if == 0; block is not compressible */
const seqStore_t* seqStorePtr = ZSTD_getSeqStore(esr.zc);
const seqStore_t* const seqStorePtr = ZSTD_getSeqStore(esr.zc);
/* literals stats */
{ const BYTE* bytePtr;
@@ -688,6 +695,7 @@ static size_t ZDICT_analyzeEntropy(void* dstBuffer, size_t maxDstSize,
BYTE* dstPtr = (BYTE*)dstBuffer;
/* init */
DEBUGLOG(4, "ZDICT_analyzeEntropy");
esr.ref = ZSTD_createCCtx();
esr.zc = ZSTD_createCCtx();
esr.workPlace = malloc(ZSTD_BLOCKSIZE_MAX);
@@ -713,7 +721,7 @@ static size_t ZDICT_analyzeEntropy(void* dstBuffer, size_t maxDstSize,
goto _cleanup;
} }
/* collect stats on all files */
/* collect stats on all samples */
for (u=0; u<nbFiles; u++) {
ZDICT_countEStats(esr, params,
countLit, offcodeCount, matchLengthCount, litLengthCount, repOffset,
@@ -726,7 +734,7 @@ static size_t ZDICT_analyzeEntropy(void* dstBuffer, size_t maxDstSize,
errorCode = HUF_buildCTable (hufTable, countLit, 255, huffLog);
if (HUF_isError(errorCode)) {
eSize = ERROR(GENERIC);
DISPLAYLEVEL(1, "HUF_buildCTable error \n");
DISPLAYLEVEL(1, " HUF_buildCTable error \n");
goto _cleanup;
}
huffLog = (U32)errorCode;
@@ -850,6 +858,7 @@ size_t ZDICT_finalizeDictionary(void* dictBuffer, size_t dictBufferCapacity,
U32 const notificationLevel = params.notificationLevel;
/* check conditions */
DEBUGLOG(4, "ZDICT_finalizeDictionary");
if (dictBufferCapacity < dictContentSize) return ERROR(dstSize_tooSmall);
if (dictContentSize < ZDICT_CONTENTSIZE_MIN) return ERROR(srcSize_wrong);
if (dictBufferCapacity < ZDICT_DICTSIZE_MIN) return ERROR(dstSize_tooSmall);
@@ -1054,18 +1063,22 @@ size_t ZDICT_trainFromBuffer(void* dictBuffer, size_t dictBufferCapacity,
const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples)
{
ZDICT_cover_params_t params;
DEBUGLOG(3, "ZDICT_trainFromBuffer");
memset(&params, 0, sizeof(params));
params.d = 8;
params.steps = 4;
/* Default to level 6 since no compression level information is avaialble */
/* Default to level 6 since no compression level information is available */
params.zParams.compressionLevel = 6;
#if defined(ZSTD_DEBUG) && (ZSTD_DEBUG>=1)
params.zParams.notificationLevel = ZSTD_DEBUG;
#endif
return ZDICT_optimizeTrainFromBuffer_cover(dictBuffer, dictBufferCapacity,
samplesBuffer, samplesSizes,
nbSamples, &params);
samplesBuffer, samplesSizes, nbSamples,
&params);
}
size_t ZDICT_addEntropyTablesFromBuffer(void* dictBuffer, size_t dictContentSize, size_t dictBufferCapacity,
const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples)
const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples)
{
ZDICT_params_t params;
memset(&params, 0, sizeof(params));