summaryrefslogtreecommitdiffstats
path: root/lib/dictBuilder/zdict.c
diff options
context:
space:
mode:
Diffstat (limited to 'lib/dictBuilder/zdict.c')
-rw-r--r--lib/dictBuilder/zdict.c59
1 files changed, 29 insertions, 30 deletions
diff --git a/lib/dictBuilder/zdict.c b/lib/dictBuilder/zdict.c
index 6d0b042..459cbe4 100644
--- a/lib/dictBuilder/zdict.c
+++ b/lib/dictBuilder/zdict.c
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2016-2020, Yann Collet, Facebook, Inc.
+ * Copyright (c) Yann Collet, Facebook, Inc.
* All rights reserved.
*
* This source code is licensed under both the BSD-style license (found in the
@@ -23,9 +23,13 @@
/* Unix Large Files support (>4GB) */
#define _FILE_OFFSET_BITS 64
#if (defined(__sun__) && (!defined(__LP64__))) /* Sun Solaris 32-bits requires specific definitions */
+# ifndef _LARGEFILE_SOURCE
# define _LARGEFILE_SOURCE
+# endif
#elif ! defined(__LP64__) /* No point defining Large file for 64 bit */
+# ifndef _LARGEFILE64_SOURCE
# define _LARGEFILE64_SOURCE
+# endif
#endif
@@ -37,18 +41,19 @@
#include <stdio.h> /* fprintf, fopen, ftello64 */
#include <time.h> /* clock */
+#ifndef ZDICT_STATIC_LINKING_ONLY
+# define ZDICT_STATIC_LINKING_ONLY
+#endif
+#define HUF_STATIC_LINKING_ONLY
+
#include "../common/mem.h" /* read */
#include "../common/fse.h" /* FSE_normalizeCount, FSE_writeNCount */
-#define HUF_STATIC_LINKING_ONLY
#include "../common/huf.h" /* HUF_buildCTable, HUF_writeCTable */
#include "../common/zstd_internal.h" /* includes zstd.h */
#include "../common/xxhash.h" /* XXH64 */
-#include "divsufsort.h"
-#ifndef ZDICT_STATIC_LINKING_ONLY
-# define ZDICT_STATIC_LINKING_ONLY
-#endif
-#include "zdict.h"
#include "../compress/zstd_compress_internal.h" /* ZSTD_loadCEntropy() */
+#include "../zdict.h"
+#include "divsufsort.h"
/*-*************************************
@@ -62,14 +67,15 @@
#define NOISELENGTH 32
-static const int g_compressionLevel_default = 3;
static const U32 g_selectivity_default = 9;
/*-*************************************
* Console display
***************************************/
+#undef DISPLAY
#define DISPLAY(...) { fprintf(stderr, __VA_ARGS__); fflush( stderr ); }
+#undef DISPLAYLEVEL
#define DISPLAYLEVEL(l, ...) if (notificationLevel>=l) { DISPLAY(__VA_ARGS__); } /* 0 : no display; 1: errors; 2: default; 3: details; 4: debug */
static clock_t ZDICT_clockSpan(clock_t nPrevious) { return clock() - nPrevious; }
@@ -105,20 +111,17 @@ size_t ZDICT_getDictHeaderSize(const void* dictBuffer, size_t dictSize)
size_t headerSize;
if (dictSize <= 8 || MEM_readLE32(dictBuffer) != ZSTD_MAGIC_DICTIONARY) return ERROR(dictionary_corrupted);
- { unsigned offcodeMaxValue = MaxOff;
- ZSTD_compressedBlockState_t* bs = (ZSTD_compressedBlockState_t*)malloc(sizeof(ZSTD_compressedBlockState_t));
+ { ZSTD_compressedBlockState_t* bs = (ZSTD_compressedBlockState_t*)malloc(sizeof(ZSTD_compressedBlockState_t));
U32* wksp = (U32*)malloc(HUF_WORKSPACE_SIZE);
- short* offcodeNCount = (short*)malloc((MaxOff+1)*sizeof(short));
- if (!bs || !wksp || !offcodeNCount) {
+ if (!bs || !wksp) {
headerSize = ERROR(memory_allocation);
} else {
ZSTD_reset_compressedBlockState(bs);
- headerSize = ZSTD_loadCEntropy(bs, wksp, offcodeNCount, &offcodeMaxValue, dictBuffer, dictSize);
+ headerSize = ZSTD_loadCEntropy(bs, wksp, dictBuffer, dictSize);
}
free(bs);
free(wksp);
- free(offcodeNCount);
}
return headerSize;
@@ -532,6 +535,7 @@ static size_t ZDICT_trainBuffer_legacy(dictItem* dictList, U32 dictListSize,
clock_t displayClock = 0;
clock_t const refreshRate = CLOCKS_PER_SEC * 3 / 10;
+# undef DISPLAYUPDATE
# define DISPLAYUPDATE(l, ...) if (notificationLevel>=l) { \
if (ZDICT_clockSpan(displayClock) > refreshRate) \
{ displayClock = clock(); DISPLAY(__VA_ARGS__); \
@@ -706,7 +710,7 @@ static void ZDICT_flatLit(unsigned* countLit)
#define OFFCODE_MAX 30 /* only applicable to first block */
static size_t ZDICT_analyzeEntropy(void* dstBuffer, size_t maxDstSize,
- unsigned compressionLevel,
+ int compressionLevel,
const void* srcBuffer, const size_t* fileSizes, unsigned nbFiles,
const void* dictBuffer, size_t dictBufferSize,
unsigned notificationLevel)
@@ -741,7 +745,7 @@ static size_t ZDICT_analyzeEntropy(void* dstBuffer, size_t maxDstSize,
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 = ZSTD_CLEVEL_DEFAULT;
params = ZSTD_getParams(compressionLevel, averageSampleSize, dictBufferSize);
esr.dict = ZSTD_createCDict_advanced(dictBuffer, dictBufferSize, ZSTD_dlm_byRef, ZSTD_dct_rawContent, params.cParams, ZSTD_defaultCMem);
@@ -786,7 +790,7 @@ static size_t ZDICT_analyzeEntropy(void* dstBuffer, size_t maxDstSize,
/* note : the result of this phase should be used to better appreciate the impact on statistics */
total=0; for (u=0; u<=offcodeMax; u++) total+=offcodeCount[u];
- errorCode = FSE_normalizeCount(offcodeNCount, Offlog, offcodeCount, total, offcodeMax);
+ errorCode = FSE_normalizeCount(offcodeNCount, Offlog, offcodeCount, total, offcodeMax, /* useLowProbCount */ 1);
if (FSE_isError(errorCode)) {
eSize = errorCode;
DISPLAYLEVEL(1, "FSE_normalizeCount error with offcodeCount \n");
@@ -795,7 +799,7 @@ static size_t ZDICT_analyzeEntropy(void* dstBuffer, size_t maxDstSize,
Offlog = (U32)errorCode;
total=0; for (u=0; u<=MaxML; u++) total+=matchLengthCount[u];
- errorCode = FSE_normalizeCount(matchLengthNCount, mlLog, matchLengthCount, total, MaxML);
+ errorCode = FSE_normalizeCount(matchLengthNCount, mlLog, matchLengthCount, total, MaxML, /* useLowProbCount */ 1);
if (FSE_isError(errorCode)) {
eSize = errorCode;
DISPLAYLEVEL(1, "FSE_normalizeCount error with matchLengthCount \n");
@@ -804,7 +808,7 @@ static size_t ZDICT_analyzeEntropy(void* dstBuffer, size_t maxDstSize,
mlLog = (U32)errorCode;
total=0; for (u=0; u<=MaxLL; u++) total+=litLengthCount[u];
- errorCode = FSE_normalizeCount(litLengthNCount, llLog, litLengthCount, total, MaxLL);
+ errorCode = FSE_normalizeCount(litLengthNCount, llLog, litLengthCount, total, MaxLL, /* useLowProbCount */ 1);
if (FSE_isError(errorCode)) {
eSize = errorCode;
DISPLAYLEVEL(1, "FSE_normalizeCount error with litLengthCount \n");
@@ -893,7 +897,7 @@ size_t ZDICT_finalizeDictionary(void* dictBuffer, size_t dictBufferCapacity,
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) ? ZSTD_CLEVEL_DEFAULT : params.compressionLevel;
U32 const notificationLevel = params.notificationLevel;
/* check conditions */
@@ -939,7 +943,7 @@ static size_t ZDICT_addEntropyTablesFromBuffer_advanced(
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) ? ZSTD_CLEVEL_DEFAULT : params.compressionLevel;
U32 const notificationLevel = params.notificationLevel;
size_t hSize = 8;
@@ -968,16 +972,11 @@ static size_t ZDICT_addEntropyTablesFromBuffer_advanced(
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.
+* 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_legacy(
+static 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)
@@ -1114,8 +1113,8 @@ size_t ZDICT_trainFromBuffer(void* dictBuffer, size_t dictBufferCapacity,
memset(&params, 0, sizeof(params));
params.d = 8;
params.steps = 4;
- /* Default to level 6 since no compression level information is available */
- params.zParams.compressionLevel = 3;
+ /* Use default level since no compression level information is available */
+ params.zParams.compressionLevel = ZSTD_CLEVEL_DEFAULT;
#if defined(DEBUGLEVEL) && (DEBUGLEVEL>=1)
params.zParams.notificationLevel = DEBUGLEVEL;
#endif
generated by cgit v0.12 at 2025-02-03 15:23:48 (GMT)