aboutsummaryrefslogtreecommitdiff
path: root/lib/dictBuilder/zdict.c
diff options
context:
space:
mode:
Diffstat (limited to 'lib/dictBuilder/zdict.c')
-rw-r--r--lib/dictBuilder/zdict.c70
1 files changed, 30 insertions, 40 deletions
diff --git a/lib/dictBuilder/zdict.c b/lib/dictBuilder/zdict.c
index 179e02effa4d..742586eacdd2 100644
--- a/lib/dictBuilder/zdict.c
+++ b/lib/dictBuilder/zdict.c
@@ -94,7 +94,7 @@ const char* ZDICT_getErrorName(size_t errorCode) { return ERR_getErrorName(error
unsigned ZDICT_getDictID(const void* dictBuffer, size_t dictSize)
{
if (dictSize < 8) return 0;
- if (MEM_readLE32(dictBuffer) != ZSTD_DICT_MAGIC) return 0;
+ if (MEM_readLE32(dictBuffer) != ZSTD_MAGIC_DICTIONARY) return 0;
return MEM_readLE32((const char*)dictBuffer + 4);
}
@@ -487,7 +487,7 @@ static U32 ZDICT_dictSize(const dictItem* dictList)
}
-static size_t ZDICT_trainBuffer(dictItem* dictList, U32 dictListSize,
+static size_t ZDICT_trainBuffer_legacy(dictItem* dictList, U32 dictListSize,
const void* const buffer, size_t bufferSize, /* buffer must end with noisy guard band */
const size_t* fileSizes, unsigned nbFiles,
U32 minRatio, U32 notificationLevel)
@@ -576,7 +576,7 @@ typedef struct
{
ZSTD_CCtx* ref;
ZSTD_CCtx* zc;
- void* workPlace; /* must be ZSTD_BLOCKSIZE_ABSOLUTEMAX allocated */
+ void* workPlace; /* must be ZSTD_BLOCKSIZE_MAX allocated */
} EStats_ress_t;
#define MAXREPOFFSET 1024
@@ -585,14 +585,14 @@ 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)
{
- size_t const blockSizeMax = MIN (ZSTD_BLOCKSIZE_ABSOLUTEMAX, 1 << params.cParams.windowLog);
+ 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; }
}
- cSize = ZSTD_compressBlock(esr.zc, esr.workPlace, ZSTD_BLOCKSIZE_ABSOLUTEMAX, src, srcSize);
+ 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 */
@@ -634,17 +634,6 @@ static void ZDICT_countEStats(EStats_ress_t esr, ZSTD_parameters params,
} } }
}
-/*
-static size_t ZDICT_maxSampleSize(const size_t* fileSizes, unsigned nbFiles)
-{
- unsigned u;
- size_t max=0;
- for (u=0; u<nbFiles; u++)
- if (max < fileSizes[u]) max = fileSizes[u];
- return max;
-}
-*/
-
static size_t ZDICT_totalSampleSize(const size_t* fileSizes, unsigned nbFiles)
{
size_t total=0;
@@ -700,7 +689,7 @@ static size_t ZDICT_analyzeEntropy(void* dstBuffer, size_t maxDstSize,
/* init */
esr.ref = ZSTD_createCCtx();
esr.zc = ZSTD_createCCtx();
- esr.workPlace = malloc(ZSTD_BLOCKSIZE_ABSOLUTEMAX);
+ esr.workPlace = malloc(ZSTD_BLOCKSIZE_MAX);
if (!esr.ref || !esr.zc || !esr.workPlace) {
eSize = ERROR(memory_allocation);
DISPLAYLEVEL(1, "Not enough memory \n");
@@ -865,7 +854,7 @@ size_t ZDICT_finalizeDictionary(void* dictBuffer, size_t dictBufferCapacity,
if (dictBufferCapacity < ZDICT_DICTSIZE_MIN) return ERROR(dstSize_tooSmall);
/* dictionary header */
- MEM_writeLE32(header, ZSTD_DICT_MAGIC);
+ MEM_writeLE32(header, ZSTD_MAGIC_DICTIONARY);
{ U64 const randomID = XXH64(customDictContent, dictContentSize, 0);
U32 const compliantID = (randomID % ((1U<<31)-32768)) + 32768;
U32 const dictID = params.dictID ? params.dictID : compliantID;
@@ -917,7 +906,7 @@ size_t ZDICT_addEntropyTablesFromBuffer_advanced(void* dictBuffer, size_t dictCo
}
/* add dictionary header (after entropy tables) */
- MEM_writeLE32(dictBuffer, ZSTD_DICT_MAGIC);
+ MEM_writeLE32(dictBuffer, ZSTD_MAGIC_DICTIONARY);
{ U64 const randomID = XXH64((char*)dictBuffer + dictBufferCapacity - dictContentSize, dictContentSize, 0);
U32 const compliantID = (randomID % ((1U<<31)-32768)) + 32768;
U32 const dictID = params.dictID ? params.dictID : compliantID;
@@ -930,14 +919,14 @@ size_t ZDICT_addEntropyTablesFromBuffer_advanced(void* dictBuffer, size_t dictCo
}
-/*! ZDICT_trainFromBuffer_unsafe() :
+/*! 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()
*/
-size_t ZDICT_trainFromBuffer_unsafe(
+size_t ZDICT_trainFromBuffer_unsafe_legacy(
void* dictBuffer, size_t maxDictSize,
const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
- ZDICT_params_t params)
+ ZDICT_legacy_params_t params)
{
U32 const dictListSize = MAX(MAX(DICTLISTSIZE_DEFAULT, nbSamples), (U32)(maxDictSize/16));
dictItem* const dictList = (dictItem*)malloc(dictListSize * sizeof(*dictList));
@@ -946,7 +935,7 @@ size_t ZDICT_trainFromBuffer_unsafe(
size_t const targetDictSize = maxDictSize;
size_t const samplesBuffSize = ZDICT_totalSampleSize(samplesSizes, nbSamples);
size_t dictSize = 0;
- U32 const notificationLevel = params.notificationLevel;
+ U32 const notificationLevel = params.zParams.notificationLevel;
/* checks */
if (!dictList) return ERROR(memory_allocation);
@@ -957,13 +946,13 @@ size_t ZDICT_trainFromBuffer_unsafe(
ZDICT_initDictItem(dictList);
/* build dictionary */
- ZDICT_trainBuffer(dictList, dictListSize,
- samplesBuffer, samplesBuffSize,
- samplesSizes, nbSamples,
- minRep, notificationLevel);
+ ZDICT_trainBuffer_legacy(dictList, dictListSize,
+ samplesBuffer, samplesBuffSize,
+ samplesSizes, nbSamples,
+ minRep, notificationLevel);
/* display best matches */
- if (params.notificationLevel>= 3) {
+ if (params.zParams.notificationLevel>= 3) {
U32 const nb = MIN(25, dictList[0].pos);
U32 const dictContentSize = ZDICT_dictSize(dictList);
U32 u;
@@ -1026,7 +1015,7 @@ size_t ZDICT_trainFromBuffer_unsafe(
dictSize = ZDICT_addEntropyTablesFromBuffer_advanced(dictBuffer, dictContentSize, maxDictSize,
samplesBuffer, samplesSizes, nbSamples,
- params);
+ params.zParams);
}
/* clean up */
@@ -1037,9 +1026,9 @@ size_t ZDICT_trainFromBuffer_unsafe(
/* issue : samplesBuffer need to be followed by a noisy guard band.
* work around : duplicate the buffer, and add the noise */
-size_t ZDICT_trainFromBuffer_advanced(void* dictBuffer, size_t dictBufferCapacity,
- const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
- ZDICT_params_t params)
+size_t ZDICT_trainFromBuffer_legacy(void* dictBuffer, size_t dictBufferCapacity,
+ const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
+ ZDICT_legacy_params_t params)
{
size_t result;
void* newBuff;
@@ -1052,10 +1041,9 @@ size_t ZDICT_trainFromBuffer_advanced(void* dictBuffer, size_t dictBufferCapacit
memcpy(newBuff, samplesBuffer, sBuffSize);
ZDICT_fillNoise((char*)newBuff + sBuffSize, NOISELENGTH); /* guard band, for end of buffer condition */
- result = ZDICT_trainFromBuffer_unsafe(
- dictBuffer, dictBufferCapacity,
- newBuff, samplesSizes, nbSamples,
- params);
+ result =
+ ZDICT_trainFromBuffer_unsafe_legacy(dictBuffer, dictBufferCapacity, newBuff,
+ samplesSizes, nbSamples, params);
free(newBuff);
return result;
}
@@ -1064,11 +1052,13 @@ size_t ZDICT_trainFromBuffer_advanced(void* dictBuffer, size_t dictBufferCapacit
size_t ZDICT_trainFromBuffer(void* dictBuffer, size_t dictBufferCapacity,
const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples)
{
- ZDICT_params_t params;
+ ZDICT_cover_params_t params;
memset(&params, 0, sizeof(params));
- return ZDICT_trainFromBuffer_advanced(dictBuffer, dictBufferCapacity,
- samplesBuffer, samplesSizes, nbSamples,
- params);
+ params.d = 8;
+ params.steps = 4;
+ return ZDICT_optimizeTrainFromBuffer_cover(dictBuffer, dictBufferCapacity,
+ samplesBuffer, samplesSizes,
+ nbSamples, &params);
}
size_t ZDICT_addEntropyTablesFromBuffer(void* dictBuffer, size_t dictContentSize, size_t dictBufferCapacity,
generated by cgit v1.2.3 (git 2.25.1) at 2025-02-22 13:35:33 +0000