--- a/contrib/python-zstandard/zstd/dictBuilder/zdict.c Tue Sep 25 20:55:03 2018 +0900
+++ b/contrib/python-zstandard/zstd/dictBuilder/zdict.c Mon Oct 08 16:27:40 2018 -0700
@@ -293,7 +293,7 @@
refinedEnd = refinedStart + selectedCount;
}
- /* evaluate gain based on new ref */
+ /* evaluate gain based on new dict */
start = refinedStart;
pos = suffix[refinedStart];
end = start;
@@ -341,7 +341,7 @@
for (i=MINMATCHLENGTH; i<=(int)maxLength; i++)
savings[i] = savings[i-1] + (lengthList[i] * (i-3));
- DISPLAYLEVEL(4, "Selected ref at position %u, of length %u : saves %u (ratio: %.2f) \n",
+ DISPLAYLEVEL(4, "Selected dict at position %u, of length %u : saves %u (ratio: %.2f) \n",
(U32)pos, (U32)maxLength, savings[maxLength], (double)savings[maxLength] / maxLength);
solution.pos = (U32)pos;
@@ -581,7 +581,7 @@
typedef struct
{
- ZSTD_CCtx* ref; /* contains reference to dictionary */
+ ZSTD_CDict* dict; /* dictionary */
ZSTD_CCtx* zc; /* working context */
void* workPlace; /* must be ZSTD_BLOCKSIZE_MAX allocated */
} EStats_ress_t;
@@ -597,8 +597,9 @@
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_compressBegin_usingCDict(esr.zc, esr.dict);
+ if (ZSTD_isError(errorCode)) { DISPLAYLEVEL(1, "warning : ZSTD_compressBegin_usingCDict 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; }
@@ -697,7 +698,7 @@
short litLengthNCount[MaxLL+1];
U32 repOffset[MAXREPOFFSET];
offsetCount_t bestRepOffset[ZSTD_REP_NUM+1];
- EStats_ress_t esr;
+ EStats_ress_t esr = { NULL, NULL, NULL };
ZSTD_parameters params;
U32 u, huffLog = 11, Offlog = OffFSELog, mlLog = MLFSELog, llLog = LLFSELog, total;
size_t pos = 0, errorCode;
@@ -708,14 +709,6 @@
/* init */
DEBUGLOG(4, "ZDICT_analyzeEntropy");
- esr.ref = ZSTD_createCCtx();
- esr.zc = ZSTD_createCCtx();
- esr.workPlace = malloc(ZSTD_BLOCKSIZE_MAX);
- if (!esr.ref || !esr.zc || !esr.workPlace) {
- eSize = ERROR(memory_allocation);
- DISPLAYLEVEL(1, "Not enough memory \n");
- goto _cleanup;
- }
if (offcodeMax>OFFCODE_MAX) { eSize = ERROR(dictionaryCreation_failed); goto _cleanup; } /* too large dictionary */
for (u=0; u<256; u++) countLit[u] = 1; /* any character must be described */
for (u=0; u<=offcodeMax; u++) offcodeCount[u] = 1;
@@ -724,14 +717,17 @@
memset(repOffset, 0, sizeof(repOffset));
repOffset[1] = repOffset[4] = repOffset[8] = 1;
memset(bestRepOffset, 0, sizeof(bestRepOffset));
- if (compressionLevel<=0) compressionLevel = g_compressionLevel_default;
+ if (compressionLevel==0) compressionLevel = g_compressionLevel_default;
params = ZSTD_getParams(compressionLevel, averageSampleSize, dictBufferSize);
- { size_t const beginResult = ZSTD_compressBegin_advanced(esr.ref, dictBuffer, dictBufferSize, params, 0);
- if (ZSTD_isError(beginResult)) {
- DISPLAYLEVEL(1, "error : ZSTD_compressBegin_advanced() failed : %s \n", ZSTD_getErrorName(beginResult));
- eSize = ERROR(GENERIC);
- goto _cleanup;
- } }
+
+ esr.dict = ZSTD_createCDict_advanced(dictBuffer, dictBufferSize, ZSTD_dlm_byRef, ZSTD_dct_rawContent, params.cParams, ZSTD_defaultCMem);
+ esr.zc = ZSTD_createCCtx();
+ esr.workPlace = malloc(ZSTD_BLOCKSIZE_MAX);
+ if (!esr.dict || !esr.zc || !esr.workPlace) {
+ eSize = ERROR(memory_allocation);
+ DISPLAYLEVEL(1, "Not enough memory \n");
+ goto _cleanup;
+ }
/* collect stats on all samples */
for (u=0; u<nbFiles; u++) {
@@ -856,7 +852,7 @@
eSize += 12;
_cleanup:
- ZSTD_freeCCtx(esr.ref);
+ ZSTD_freeCDict(esr.dict);
ZSTD_freeCCtx(esr.zc);
free(esr.workPlace);
@@ -867,13 +863,13 @@
size_t ZDICT_finalizeDictionary(void* dictBuffer, size_t dictBufferCapacity,
const void* customDictContent, size_t dictContentSize,
- const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
- ZDICT_params_t params)
+ const void* samplesBuffer, const size_t* samplesSizes,
+ unsigned nbSamples, ZDICT_params_t params)
{
size_t hSize;
#define HBUFFSIZE 256 /* should prove large enough for all entropy headers */
BYTE header[HBUFFSIZE];
- int const compressionLevel = (params.compressionLevel <= 0) ? g_compressionLevel_default : params.compressionLevel;
+ int const compressionLevel = (params.compressionLevel == 0) ? g_compressionLevel_default : params.compressionLevel;
U32 const notificationLevel = params.notificationLevel;
/* check conditions */
@@ -914,11 +910,12 @@
}
-size_t ZDICT_addEntropyTablesFromBuffer_advanced(void* dictBuffer, size_t dictContentSize, size_t dictBufferCapacity,
- const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
- ZDICT_params_t params)
+static size_t ZDICT_addEntropyTablesFromBuffer_advanced(
+ void* dictBuffer, size_t dictContentSize, size_t dictBufferCapacity,
+ const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
+ ZDICT_params_t params)
{
- int const compressionLevel = (params.compressionLevel <= 0) ? g_compressionLevel_default : params.compressionLevel;
+ int const compressionLevel = (params.compressionLevel == 0) ? g_compressionLevel_default : params.compressionLevel;
U32 const notificationLevel = params.notificationLevel;
size_t hSize = 8;
@@ -947,7 +944,11 @@
return MIN(dictBufferCapacity, hSize+dictContentSize);
}
-
+/* Hidden declaration for dbio.c */
+size_t ZDICT_trainFromBuffer_unsafe_legacy(
+ void* dictBuffer, size_t maxDictSize,
+ const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
+ ZDICT_legacy_params_t params);
/*! ZDICT_trainFromBuffer_unsafe_legacy() :
* Warning : `samplesBuffer` must be followed by noisy guard band.
* @return : size of dictionary, or an error code which can be tested with ZDICT_isError()
@@ -991,8 +992,10 @@
U32 const pos = dictList[u].pos;
U32 const length = dictList[u].length;
U32 const printedLength = MIN(40, length);
- if ((pos > samplesBuffSize) || ((pos + length) > samplesBuffSize))
+ if ((pos > samplesBuffSize) || ((pos + length) > samplesBuffSize)) {
+ free(dictList);
return ERROR(GENERIC); /* should never happen */
+ }
DISPLAYLEVEL(3, "%3u:%3u bytes at pos %8u, savings %7u bytes |",
u, length, pos, dictList[u].savings);
ZDICT_printHex((const char*)samplesBuffer+pos, printedLength);
@@ -1082,17 +1085,17 @@
size_t ZDICT_trainFromBuffer(void* dictBuffer, size_t dictBufferCapacity,
const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples)
{
- ZDICT_cover_params_t params;
+ ZDICT_fastCover_params_t params;
DEBUGLOG(3, "ZDICT_trainFromBuffer");
memset(¶ms, 0, sizeof(params));
params.d = 8;
params.steps = 4;
/* 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;
+ params.zParams.compressionLevel = 3;
+#if defined(DEBUGLEVEL) && (DEBUGLEVEL>=1)
+ params.zParams.notificationLevel = DEBUGLEVEL;
#endif
- return ZDICT_optimizeTrainFromBuffer_cover(dictBuffer, dictBufferCapacity,
+ return ZDICT_optimizeTrainFromBuffer_fastCover(dictBuffer, dictBufferCapacity,
samplesBuffer, samplesSizes, nbSamples,
¶ms);
}