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

Merge branch 'dev' into d_prefetch_refactor

Browse Source
This commit is contained in:
Yann Collet
2021-05-06 19:49:26 -07:00
parent 8cde167a27 0d05846952
commit ee425faaa7
68 changed files with 1083 additions and 364 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/compress/zstd_compress.c
+96 -51
View File
@@ -559,6 +559,11 @@ ZSTD_bounds ZSTD_cParam_getBounds(ZSTD_cParameter param)
bounds.upperBound = (int)ZSTD_urm_enableRowMatchFinder;
return bounds;
case ZSTD_c_deterministicRefPrefix:
bounds.lowerBound = 0;
bounds.upperBound = 1;
return bounds;
default:
bounds.error = ERROR(parameter_unsupported);
return bounds;
@@ -622,6 +627,7 @@ static int ZSTD_isUpdateAuthorized(ZSTD_cParameter param)
case ZSTD_c_validateSequences:
case ZSTD_c_splitBlocks:
case ZSTD_c_useRowMatchFinder:
case ZSTD_c_deterministicRefPrefix:
default:
return 0;
}
@@ -676,6 +682,7 @@ size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, int value)
case ZSTD_c_validateSequences:
case ZSTD_c_splitBlocks:
case ZSTD_c_useRowMatchFinder:
case ZSTD_c_deterministicRefPrefix:
break;
default: RETURN_ERROR(parameter_unsupported, "unknown parameter");
@@ -897,6 +904,11 @@ size_t ZSTD_CCtxParams_setParameter(ZSTD_CCtx_params* CCtxParams,
CCtxParams->useRowMatchFinder = (ZSTD_useRowMatchFinderMode_e)value;
return CCtxParams->useRowMatchFinder;
case ZSTD_c_deterministicRefPrefix:
BOUNDCHECK(ZSTD_c_deterministicRefPrefix, value);
CCtxParams->deterministicRefPrefix = !!value;
return CCtxParams->deterministicRefPrefix;
default: RETURN_ERROR(parameter_unsupported, "unknown parameter");
}
}
@@ -1026,6 +1038,9 @@ size_t ZSTD_CCtxParams_getParameter(
case ZSTD_c_useRowMatchFinder :
*value = (int)CCtxParams->useRowMatchFinder;
break;
case ZSTD_c_deterministicRefPrefix:
*value = (int)CCtxParams->deterministicRefPrefix;
break;
default: RETURN_ERROR(parameter_unsupported, "unknown parameter");
}
return 0;
@@ -1802,7 +1817,7 @@ static int ZSTD_dictTooBig(size_t const loadedDictSize)
* note : `params` are assumed fully validated at this stage.
*/
static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc,
ZSTD_CCtx_params params,
ZSTD_CCtx_params const* params,
U64 const pledgedSrcSize,
size_t const loadedDictSize,
ZSTD_compResetPolicy_e const crp,
@@ -1810,30 +1825,36 @@ static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc,
{
ZSTD_cwksp* const ws = &zc->workspace;
DEBUGLOG(4, "ZSTD_resetCCtx_internal: pledgedSrcSize=%u, wlog=%u, useRowMatchFinder=%d",
(U32)pledgedSrcSize, params.cParams.windowLog, (int)params.useRowMatchFinder);
assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams)));
(U32)pledgedSrcSize, params->cParams.windowLog, (int)params->useRowMatchFinder);
assert(!ZSTD_isError(ZSTD_checkCParams(params->cParams)));
zc->isFirstBlock = 1;
assert(params.useRowMatchFinder != ZSTD_urm_auto);
if (params.ldmParams.enableLdm) {
/* Set applied params early so we can modify them for LDM,
* and point params at the applied params.
*/
zc->appliedParams = *params;
params = &zc->appliedParams;
assert(params->useRowMatchFinder != ZSTD_urm_auto);
if (params->ldmParams.enableLdm) {
/* Adjust long distance matching parameters */
ZSTD_ldm_adjustParameters(&params.ldmParams, &params.cParams);
assert(params.ldmParams.hashLog >= params.ldmParams.bucketSizeLog);
assert(params.ldmParams.hashRateLog < 32);
ZSTD_ldm_adjustParameters(&zc->appliedParams.ldmParams, &params->cParams);
assert(params->ldmParams.hashLog >= params->ldmParams.bucketSizeLog);
assert(params->ldmParams.hashRateLog < 32);
}
{ size_t const windowSize = MAX(1, (size_t)MIN(((U64)1 << params.cParams.windowLog), pledgedSrcSize));
{ size_t const windowSize = MAX(1, (size_t)MIN(((U64)1 << params->cParams.windowLog), pledgedSrcSize));
size_t const blockSize = MIN(ZSTD_BLOCKSIZE_MAX, windowSize);
U32 const divider = (params.cParams.minMatch==3) ? 3 : 4;
U32 const divider = (params->cParams.minMatch==3) ? 3 : 4;
size_t const maxNbSeq = blockSize / divider;
size_t const buffOutSize = (zbuff == ZSTDb_buffered && params.outBufferMode == ZSTD_bm_buffered)
size_t const buffOutSize = (zbuff == ZSTDb_buffered && params->outBufferMode == ZSTD_bm_buffered)
? ZSTD_compressBound(blockSize) + 1
: 0;
size_t const buffInSize = (zbuff == ZSTDb_buffered && params.inBufferMode == ZSTD_bm_buffered)
size_t const buffInSize = (zbuff == ZSTDb_buffered && params->inBufferMode == ZSTD_bm_buffered)
? windowSize + blockSize
: 0;
size_t const maxNbLdmSeq = ZSTD_ldm_getMaxNbSeq(params.ldmParams, blockSize);
size_t const maxNbLdmSeq = ZSTD_ldm_getMaxNbSeq(params->ldmParams, blockSize);
int const indexTooClose = ZSTD_indexTooCloseToMax(zc->blockState.matchState.window);
int const dictTooBig = ZSTD_dictTooBig(loadedDictSize);
@@ -1842,7 +1863,7 @@ static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc,
size_t const neededSpace =
ZSTD_estimateCCtxSize_usingCCtxParams_internal(
&params.cParams, &params.ldmParams, zc->staticSize != 0, params.useRowMatchFinder,
&params->cParams, &params->ldmParams, zc->staticSize != 0, params->useRowMatchFinder,
buffInSize, buffOutSize, pledgedSrcSize);
int resizeWorkspace;
@@ -1885,8 +1906,7 @@ static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc,
ZSTD_cwksp_clear(ws);
/* init params */
zc->appliedParams = params;
zc->blockState.matchState.cParams = params.cParams;
zc->blockState.matchState.cParams = params->cParams;
zc->pledgedSrcSizePlusOne = pledgedSrcSize+1;
zc->consumedSrcSize = 0;
zc->producedCSize = 0;
@@ -1917,11 +1937,11 @@ static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc,
zc->outBuff = (char*)ZSTD_cwksp_reserve_buffer(ws, buffOutSize);
/* ldm bucketOffsets table */
if (params.ldmParams.enableLdm) {
if (params->ldmParams.enableLdm) {
/* TODO: avoid memset? */
size_t const numBuckets =
((size_t)1) << (params.ldmParams.hashLog -
params.ldmParams.bucketSizeLog);
((size_t)1) << (params->ldmParams.hashLog -
params->ldmParams.bucketSizeLog);
zc->ldmState.bucketOffsets = ZSTD_cwksp_reserve_buffer(ws, numBuckets);
ZSTD_memset(zc->ldmState.bucketOffsets, 0, numBuckets);
}
@@ -1937,16 +1957,16 @@ static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc,
FORWARD_IF_ERROR(ZSTD_reset_matchState(
&zc->blockState.matchState,
ws,
&params.cParams,
params.useRowMatchFinder,
&params->cParams,
params->useRowMatchFinder,
crp,
needsIndexReset,
ZSTD_resetTarget_CCtx), "");
/* ldm hash table */
if (params.ldmParams.enableLdm) {
if (params->ldmParams.enableLdm) {
/* TODO: avoid memset? */
size_t const ldmHSize = ((size_t)1) << params.ldmParams.hashLog;
size_t const ldmHSize = ((size_t)1) << params->ldmParams.hashLog;
zc->ldmState.hashTable = (ldmEntry_t*)ZSTD_cwksp_reserve_aligned(ws, ldmHSize * sizeof(ldmEntry_t));
ZSTD_memset(zc->ldmState.hashTable, 0, ldmHSize * sizeof(ldmEntry_t));
zc->ldmSequences = (rawSeq*)ZSTD_cwksp_reserve_aligned(ws, maxNbLdmSeq * sizeof(rawSeq));
@@ -2014,7 +2034,8 @@ ZSTD_resetCCtx_byAttachingCDict(ZSTD_CCtx* cctx,
U64 pledgedSrcSize,
ZSTD_buffered_policy_e zbuff)
{
DEBUGLOG(4, "ZSTD_resetCCtx_byAttachingCDict() pledgedSrcSize=%zu", pledgedSrcSize);
DEBUGLOG(4, "ZSTD_resetCCtx_byAttachingCDict() pledgedSrcSize=%llu",
(unsigned long long)pledgedSrcSize);
{
ZSTD_compressionParameters adjusted_cdict_cParams = cdict->matchState.cParams;
unsigned const windowLog = params.cParams.windowLog;
@@ -2031,7 +2052,7 @@ ZSTD_resetCCtx_byAttachingCDict(ZSTD_CCtx* cctx,
cdict->dictContentSize, ZSTD_cpm_attachDict);
params.cParams.windowLog = windowLog;
params.useRowMatchFinder = cdict->useRowMatchFinder; /* cdict overrides */
FORWARD_IF_ERROR(ZSTD_resetCCtx_internal(cctx, params, pledgedSrcSize,
FORWARD_IF_ERROR(ZSTD_resetCCtx_internal(cctx, &params, pledgedSrcSize,
/* loadedDictSize */ 0,
ZSTDcrp_makeClean, zbuff), "");
assert(cctx->appliedParams.cParams.strategy == adjusted_cdict_cParams.strategy);
@@ -2076,7 +2097,8 @@ static size_t ZSTD_resetCCtx_byCopyingCDict(ZSTD_CCtx* cctx,
const ZSTD_compressionParameters *cdict_cParams = &cdict->matchState.cParams;
assert(!cdict->matchState.dedicatedDictSearch);
DEBUGLOG(4, "ZSTD_resetCCtx_byCopyingCDict() pledgedSrcSize=%zu", pledgedSrcSize);
DEBUGLOG(4, "ZSTD_resetCCtx_byCopyingCDict() pledgedSrcSize=%llu",
(unsigned long long)pledgedSrcSize);
{ unsigned const windowLog = params.cParams.windowLog;
assert(windowLog != 0);
@@ -2084,7 +2106,7 @@ static size_t ZSTD_resetCCtx_byCopyingCDict(ZSTD_CCtx* cctx,
params.cParams = *cdict_cParams;
params.cParams.windowLog = windowLog;
params.useRowMatchFinder = cdict->useRowMatchFinder;
FORWARD_IF_ERROR(ZSTD_resetCCtx_internal(cctx, params, pledgedSrcSize,
FORWARD_IF_ERROR(ZSTD_resetCCtx_internal(cctx, &params, pledgedSrcSize,
/* loadedDictSize */ 0,
ZSTDcrp_leaveDirty, zbuff), "");
assert(cctx->appliedParams.cParams.strategy == cdict_cParams->strategy);
@@ -2190,7 +2212,7 @@ static size_t ZSTD_copyCCtx_internal(ZSTD_CCtx* dstCCtx,
assert(srcCCtx->appliedParams.useRowMatchFinder != ZSTD_urm_auto);
params.useRowMatchFinder = srcCCtx->appliedParams.useRowMatchFinder;
params.fParams = fParams;
ZSTD_resetCCtx_internal(dstCCtx, params, pledgedSrcSize,
ZSTD_resetCCtx_internal(dstCCtx, &params, pledgedSrcSize,
/* loadedDictSize */ 0,
ZSTDcrp_leaveDirty, zbuff);
assert(dstCCtx->appliedParams.cParams.windowLog == srcCCtx->appliedParams.cParams.windowLog);
@@ -4045,11 +4067,12 @@ static size_t ZSTD_compressContinue_internal (ZSTD_CCtx* cctx,
if (!srcSize) return fhSize; /* do not generate an empty block if no input */
if (!ZSTD_window_update(&ms->window, src, srcSize)) {
if (!ZSTD_window_update(&ms->window, src, srcSize, ms->forceNonContiguous)) {
ms->forceNonContiguous = 0;
ms->nextToUpdate = ms->window.dictLimit;
}
if (cctx->appliedParams.ldmParams.enableLdm) {
ZSTD_window_update(&cctx->ldmState.window, src, srcSize);
ZSTD_window_update(&cctx->ldmState.window, src, srcSize, /* forceNonContiguous */ 0);
}
if (!frame) {
@@ -4141,11 +4164,12 @@ static size_t ZSTD_loadDictionaryContent(ZSTD_matchState_t* ms,
}
DEBUGLOG(4, "ZSTD_loadDictionaryContent(): useRowMatchFinder=%d", (int)params->useRowMatchFinder);
ZSTD_window_update(&ms->window, src, srcSize);
ZSTD_window_update(&ms->window, src, srcSize, /* forceNonContiguous */ 0);
ms->loadedDictEnd = params->forceWindow ? 0 : (U32)(iend - ms->window.base);
ms->forceNonContiguous = params->deterministicRefPrefix;
if (loadLdmDict) {
ZSTD_window_update(&ls->window, src, srcSize);
ZSTD_window_update(&ls->window, src, srcSize, /* forceNonContiguous */ 0);
ls->loadedDictEnd = params->forceWindow ? 0 : (U32)(iend - ls->window.base);
}
@@ -4422,7 +4446,7 @@ static size_t ZSTD_compressBegin_internal(ZSTD_CCtx* cctx,
return ZSTD_resetCCtx_usingCDict(cctx, cdict, params, pledgedSrcSize, zbuff);
}
FORWARD_IF_ERROR( ZSTD_resetCCtx_internal(cctx, *params, pledgedSrcSize,
FORWARD_IF_ERROR( ZSTD_resetCCtx_internal(cctx, params, pledgedSrcSize,
dictContentSize,
ZSTDcrp_makeClean, zbuff) , "");
{ size_t const dictID = cdict ?
@@ -4591,15 +4615,14 @@ size_t ZSTD_compress_advanced (ZSTD_CCtx* cctx,
const void* dict,size_t dictSize,
ZSTD_parameters params)
{
ZSTD_CCtx_params cctxParams;
DEBUGLOG(4, "ZSTD_compress_advanced");
FORWARD_IF_ERROR(ZSTD_checkCParams(params.cParams), "");
ZSTD_CCtxParams_init_internal(&cctxParams, &params, ZSTD_NO_CLEVEL);
ZSTD_CCtxParams_init_internal(&cctx->simpleApiParams, &params, ZSTD_NO_CLEVEL);
return ZSTD_compress_advanced_internal(cctx,
dst, dstCapacity,
src, srcSize,
dict, dictSize,
&cctxParams);
&cctx->simpleApiParams);
}
/* Internal */
@@ -4623,14 +4646,13 @@ size_t ZSTD_compress_usingDict(ZSTD_CCtx* cctx,
const void* dict, size_t dictSize,
int compressionLevel)
{
ZSTD_CCtx_params cctxParams;
{
ZSTD_parameters const params = ZSTD_getParams_internal(compressionLevel, srcSize, dict ? dictSize : 0, ZSTD_cpm_noAttachDict);
assert(params.fParams.contentSizeFlag == 1);
ZSTD_CCtxParams_init_internal(&cctxParams, &params, (compressionLevel == 0) ? ZSTD_CLEVEL_DEFAULT: compressionLevel);
ZSTD_CCtxParams_init_internal(&cctx->simpleApiParams, &params, (compressionLevel == 0) ? ZSTD_CLEVEL_DEFAULT: compressionLevel);
}
DEBUGLOG(4, "ZSTD_compress_usingDict (srcSize=%u)", (unsigned)srcSize);
return ZSTD_compress_advanced_internal(cctx, dst, dstCapacity, src, srcSize, dict, dictSize, &cctxParams);
return ZSTD_compress_advanced_internal(cctx, dst, dstCapacity, src, srcSize, dict, dictSize, &cctx->simpleApiParams);
}
size_t ZSTD_compressCCtx(ZSTD_CCtx* cctx,
@@ -4963,15 +4985,15 @@ unsigned ZSTD_getDictID_fromCDict(const ZSTD_CDict* cdict)
return cdict->dictID;
}
/* ZSTD_compressBegin_usingCDict_advanced() :
* cdict must be != NULL */
size_t ZSTD_compressBegin_usingCDict_advanced(
/* ZSTD_compressBegin_usingCDict_internal() :
* Implementation of various ZSTD_compressBegin_usingCDict* functions.
*/
static size_t ZSTD_compressBegin_usingCDict_internal(
ZSTD_CCtx* const cctx, const ZSTD_CDict* const cdict,
ZSTD_frameParameters const fParams, unsigned long long const pledgedSrcSize)
{
ZSTD_CCtx_params cctxParams;
DEBUGLOG(4, "ZSTD_compressBegin_usingCDict_advanced");
DEBUGLOG(4, "ZSTD_compressBegin_usingCDict_internal");
RETURN_ERROR_IF(cdict==NULL, dictionary_wrong, "NULL pointer!");
/* Initialize the cctxParams from the cdict */
{
@@ -5003,23 +5025,46 @@ size_t ZSTD_compressBegin_usingCDict_advanced(
ZSTDb_not_buffered);
}
/* ZSTD_compressBegin_usingCDict_advanced() :
* This function is DEPRECATED.
* cdict must be != NULL */
size_t ZSTD_compressBegin_usingCDict_advanced(
ZSTD_CCtx* const cctx, const ZSTD_CDict* const cdict,
ZSTD_frameParameters const fParams, unsigned long long const pledgedSrcSize)
{
return ZSTD_compressBegin_usingCDict_internal(cctx, cdict, fParams, pledgedSrcSize);
}
/* ZSTD_compressBegin_usingCDict() :
* pledgedSrcSize=0 means "unknown"
* if pledgedSrcSize>0, it will enable contentSizeFlag */
* cdict must be != NULL */
size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict)
{
ZSTD_frameParameters const fParams = { 0 /*content*/, 0 /*checksum*/, 0 /*noDictID*/ };
DEBUGLOG(4, "ZSTD_compressBegin_usingCDict : dictIDFlag == %u", !fParams.noDictIDFlag);
return ZSTD_compressBegin_usingCDict_advanced(cctx, cdict, fParams, ZSTD_CONTENTSIZE_UNKNOWN);
return ZSTD_compressBegin_usingCDict_internal(cctx, cdict, fParams, ZSTD_CONTENTSIZE_UNKNOWN);
}
/*! ZSTD_compress_usingCDict_internal():
* Implementation of various ZSTD_compress_usingCDict* functions.
*/
static size_t ZSTD_compress_usingCDict_internal(ZSTD_CCtx* cctx,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
const ZSTD_CDict* cdict, ZSTD_frameParameters fParams)
{
FORWARD_IF_ERROR(ZSTD_compressBegin_usingCDict_internal(cctx, cdict, fParams, srcSize), ""); /* will check if cdict != NULL */
return ZSTD_compressEnd(cctx, dst, dstCapacity, src, srcSize);
}
/*! ZSTD_compress_usingCDict_advanced():
* This function is DEPRECATED.
*/
size_t ZSTD_compress_usingCDict_advanced(ZSTD_CCtx* cctx,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
const ZSTD_CDict* cdict, ZSTD_frameParameters fParams)
{
FORWARD_IF_ERROR(ZSTD_compressBegin_usingCDict_advanced(cctx, cdict, fParams, srcSize), ""); /* will check if cdict != NULL */
return ZSTD_compressEnd(cctx, dst, dstCapacity, src, srcSize);
return ZSTD_compress_usingCDict_internal(cctx, dst, dstCapacity, src, srcSize, cdict, fParams);
}
/*! ZSTD_compress_usingCDict() :
@@ -5033,7 +5078,7 @@ size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx,
const ZSTD_CDict* cdict)
{
ZSTD_frameParameters const fParams = { 1 /*content*/, 0 /*checksum*/, 0 /*noDictID*/ };
return ZSTD_compress_usingCDict_advanced(cctx, dst, dstCapacity, src, srcSize, cdict, fParams);
return ZSTD_compress_usingCDict_internal(cctx, dst, dstCapacity, src, srcSize, cdict, fParams);
}
lib/compress/zstd_compress_internal.h
+9 -2
View File
@@ -219,6 +219,8 @@ struct ZSTD_matchState_t {
U32* hashTable3;
U32* chainTable;
U32 forceNonContiguous; /* Non-zero if we should force non-contiguous load for the next window update. */
int dedicatedDictSearch; /* Indicates whether this matchState is using the
* dedicated dictionary search structure.
*/
@@ -317,6 +319,9 @@ struct ZSTD_CCtx_params_s {
/* Param for deciding whether to use row-based matchfinder */
ZSTD_useRowMatchFinderMode_e useRowMatchFinder;
/* Always load a dictionary in ext-dict mode (not prefix mode)? */
int deterministicRefPrefix;
/* Internal use, for createCCtxParams() and freeCCtxParams() only */
ZSTD_customMem customMem;
}; /* typedef'd to ZSTD_CCtx_params within "zstd.h" */
@@ -340,6 +345,7 @@ struct ZSTD_CCtx_s {
int bmi2; /* == 1 if the CPU supports BMI2 and 0 otherwise. CPU support is determined dynamically once per context lifetime. */
ZSTD_CCtx_params requestedParams;
ZSTD_CCtx_params appliedParams;
ZSTD_CCtx_params simpleApiParams; /* Param storage used by the simple API - not sticky. Must only be used in top-level simple API functions for storage. */
U32 dictID;
size_t dictContentSize;
@@ -1138,7 +1144,8 @@ MEM_STATIC void ZSTD_window_init(ZSTD_window_t* window) {
* Returns non-zero if the segment is contiguous.
*/
MEM_STATIC U32 ZSTD_window_update(ZSTD_window_t* window,
void const* src, size_t srcSize)
void const* src, size_t srcSize,
int forceNonContiguous)
{
BYTE const* const ip = (BYTE const*)src;
U32 contiguous = 1;
@@ -1148,7 +1155,7 @@ MEM_STATIC U32 ZSTD_window_update(ZSTD_window_t* window,
assert(window->base != NULL);
assert(window->dictBase != NULL);
/* Check if blocks follow each other */
if (src != window->nextSrc) {
if (src != window->nextSrc || forceNonContiguous) {
/* not contiguous */
size_t const distanceFromBase = (size_t)(window->nextSrc - window->base);
DEBUGLOG(5, "Non contiguous blocks, new segment starts at %u", window->dictLimit);
lib/compress/zstdmt_compress.c
+12 -2
View File
@@ -512,7 +512,7 @@ ZSTDMT_serialState_reset(serialState_t* serialState,
if (dictSize > 0) {
if (dictContentType == ZSTD_dct_rawContent) {
BYTE const* const dictEnd = (const BYTE*)dict + dictSize;
ZSTD_window_update(&serialState->ldmState.window, dict, dictSize);
ZSTD_window_update(&serialState->ldmState.window, dict, dictSize, /* forceNonContiguous */ 0);
ZSTD_ldm_fillHashTable(&serialState->ldmState, (const BYTE*)dict, dictEnd, &params.ldmParams);
serialState->ldmState.loadedDictEnd = params.forceWindow ? 0 : (U32)(dictEnd - serialState->ldmState.window.base);
} else {
@@ -569,7 +569,7 @@ static void ZSTDMT_serialState_update(serialState_t* serialState,
assert(seqStore.seq != NULL && seqStore.pos == 0 &&
seqStore.size == 0 && seqStore.capacity > 0);
assert(src.size <= serialState->params.jobSize);
ZSTD_window_update(&serialState->ldmState.window, src.start, src.size);
ZSTD_window_update(&serialState->ldmState.window, src.start, src.size, /* forceNonContiguous */ 0);
error = ZSTD_ldm_generateSequences(
&serialState->ldmState, &seqStore,
&serialState->params.ldmParams, src.start, src.size);
@@ -695,6 +695,10 @@ static void ZSTDMT_compressionJob(void* jobDescription)
{ size_t const forceWindowError = ZSTD_CCtxParams_setParameter(&jobParams, ZSTD_c_forceMaxWindow, !job->firstJob);
if (ZSTD_isError(forceWindowError)) JOB_ERROR(forceWindowError);
}
if (!job->firstJob) {
size_t const err = ZSTD_CCtxParams_setParameter(&jobParams, ZSTD_c_deterministicRefPrefix, 0);
if (ZSTD_isError(err)) JOB_ERROR(err);
}
{ size_t const initError = ZSTD_compressBegin_advanced_internal(cctx,
job->prefix.start, job->prefix.size, ZSTD_dct_rawContent, /* load dictionary in "content-only" mode (no header analysis) */
ZSTD_dtlm_fast,
@@ -750,6 +754,12 @@ static void ZSTDMT_compressionJob(void* jobDescription)
if (ZSTD_isError(cSize)) JOB_ERROR(cSize);
lastCBlockSize = cSize;
} }
if (!job->firstJob) {
/* Double check that we don't have an ext-dict, because then our
* repcode invalidation doesn't work.
*/
assert(!ZSTD_window_hasExtDict(cctx->blockState.matchState.window));
}
ZSTD_CCtx_trace(cctx, 0);
_endJob:
lib/decompress/zstd_decompress_block.c
+6 -12
View File
@@ -1109,7 +1109,6 @@ ZSTD_decompressSequences_body( ZSTD_DCtx* dctx,
/* Regen sequences */
if (nbSeq) {
seqState_t seqState;
size_t error = 0;
dctx->fseEntropy = 1;
{ U32 i; for (i=0; i<ZSTD_REP_NUM; i++) seqState.prevOffset[i] = dctx->entropy.rep[i]; }
RETURN_ERROR_IF(
@@ -1173,22 +1172,17 @@ ZSTD_decompressSequences_body( ZSTD_DCtx* dctx,
assert(!ZSTD_isError(oneSeqSize));
if (frame) ZSTD_assertValidSequence(dctx, op, oend, sequence, prefixStart, vBase);
#endif
if (UNLIKELY(ZSTD_isError(oneSeqSize)))
return oneSeqSize;
DEBUGLOG(6, "regenerated sequence size : %u", (U32)oneSeqSize);
BIT_reloadDStream(&(seqState.DStream));
op += oneSeqSize;
/* gcc and clang both don't like early returns in this loop.
* Instead break and check for an error at the end of the loop.
*/
if (UNLIKELY(ZSTD_isError(oneSeqSize))) {
error = oneSeqSize;
if (UNLIKELY(!--nbSeq))
break;
}
if (UNLIKELY(!--nbSeq)) break;
BIT_reloadDStream(&(seqState.DStream));
}
/* check if reached exact end */
DEBUGLOG(5, "ZSTD_decompressSequences_body: after decode loop, remaining nbSeq : %i", nbSeq);
if (ZSTD_isError(error)) return error;
RETURN_ERROR_IF(nbSeq, corruption_detected, "");
RETURN_ERROR_IF(BIT_reloadDStream(&seqState.DStream) < BIT_DStream_completed, corruption_detected, "");
/* save reps for next block */
@@ -1259,9 +1253,9 @@ ZSTD_decompressSequencesLong_body(
/* Regen sequences */
if (nbSeq) {
#define STORED_SEQS 4
#define STORED_SEQS 8
#define STORED_SEQS_MASK (STORED_SEQS-1)
#define ADVANCED_SEQS 4
#define ADVANCED_SEQS STORED_SEQS
seq_t sequences[STORED_SEQS];
int const seqAdvance = MIN(nbSeq, ADVANCED_SEQS);
seqState_t seqState;
lib/zdict.h
+147 -1
View File
@@ -36,6 +36,145 @@ extern "C" {
# define ZDICTLIB_API ZDICTLIB_VISIBILITY
#endif
/*******************************************************************************
* Zstd dictionary builder
*
* FAQ
* ===
* Why should I use a dictionary?
* ------------------------------
*
* Zstd can use dictionaries to improve compression ratio of small data.
* Traditionally small files don't compress well because there is very little
* repetion in a single sample, since it is small. But, if you are compressing
* many similar files, like a bunch of JSON records that share the same
* structure, you can train a dictionary on ahead of time on some samples of
* these files. Then, zstd can use the dictionary to find repetitions that are
* present across samples. This can vastly improve compression ratio.
*
* When is a dictionary useful?
* ----------------------------
*
* Dictionaries are useful when compressing many small files that are similar.
* The larger a file is, the less benefit a dictionary will have. Generally,
* we don't expect dictionary compression to be effective past 100KB. And the
* smaller a file is, the more we would expect the dictionary to help.
*
* How do I use a dictionary?
* --------------------------
*
* Simply pass the dictionary to the zstd compressor with
* `ZSTD_CCtx_loadDictionary()`. The same dictionary must then be passed to
* the decompressor, using `ZSTD_DCtx_loadDictionary()`. There are other
* more advanced functions that allow selecting some options, see zstd.h for
* complete documentation.
*
* What is a zstd dictionary?
* --------------------------
*
* A zstd dictionary has two pieces: Its header, and its content. The header
* contains a magic number, the dictionary ID, and entropy tables. These
* entropy tables allow zstd to save on header costs in the compressed file,
* which really matters for small data. The content is just bytes, which are
* repeated content that is common across many samples.
*
* What is a raw content dictionary?
* ---------------------------------
*
* A raw content dictionary is just bytes. It doesn't have a zstd dictionary
* header, a dictionary ID, or entropy tables. Any buffer is a valid raw
* content dictionary.
*
* How do I train a dictionary?
* ----------------------------
*
* Gather samples from your use case. These samples should be similar to each
* other. If you have several use cases, you could try to train one dictionary
* per use case.
*
* Pass those samples to `ZDICT_trainFromBuffer()` and that will train your
* dictionary. There are a few advanced versions of this function, but this
* is a great starting point. If you want to further tune your dictionary
* you could try `ZDICT_optimizeTrainFromBuffer_cover()`. If that is too slow
* you can try `ZDICT_optimizeTrainFromBuffer_fastCover()`.
*
* If the dictionary training function fails, that is likely because you
* either passed too few samples, or a dictionary would not be effective
* for your data. Look at the messages that the dictionary trainer printed,
* if it doesn't say too few samples, then a dictionary would not be effective.
*
* How large should my dictionary be?
* ----------------------------------
*
* A reasonable dictionary size, the `dictBufferCapacity`, is about 100KB.
* The zstd CLI defaults to a 110KB dictionary. You likely don't need a
* dictionary larger than that. But, most use cases can get away with a
* smaller dictionary. The advanced dictionary builders can automatically
* shrink the dictionary for you, and select a the smallest size that
* doesn't hurt compression ratio too much. See the `shrinkDict` parameter.
* A smaller dictionary can save memory, and potentially speed up
* compression.
*
* How many samples should I provide to the dictionary builder?
* ------------------------------------------------------------
*
* We generally recommend passing ~100x the size of the dictionary
* in samples. A few thousand should suffice. Having too few samples
* can hurt the dictionaries effectiveness. Having more samples will
* only improve the dictionaries effectiveness. But having too many
* samples can slow down the dictionary builder.
*
* How do I determine if a dictionary will be effective?
* -----------------------------------------------------
*
* Simply train a dictionary and try it out. You can use zstd's built in
* benchmarking tool to test the dictionary effectiveness.
*
* # Benchmark levels 1-3 without a dictionary
* zstd -b1e3 -r /path/to/my/files
* # Benchmark levels 1-3 with a dictioanry
* zstd -b1e3 -r /path/to/my/files -D /path/to/my/dictionary
*
* When should I retrain a dictionary?
* -----------------------------------
*
* You should retrain a dictionary when its effectiveness drops. Dictionary
* effectiveness drops as the data you are compressing changes. Generally, we do
* expect dictionaries to "decay" over time, as your data changes, but the rate
* at which they decay depends on your use case. Internally, we regularly
* retrain dictionaries, and if the new dictionary performs significantly
* better than the old dictionary, we will ship the new dictionary.
*
* I have a raw content dictionary, how do I turn it into a zstd dictionary?
* -------------------------------------------------------------------------
*
* If you have a raw content dictionary, e.g. by manually constructing it, or
* using a third-party dictionary builder, you can turn it into a zstd
* dictionary by using `ZDICT_finalizeDictionary()`. You'll also have to
* provide some samples of the data. It will add the zstd header to the
* raw content, which contains a dictionary ID and entropy tables, which
* will improve compression ratio, and allow zstd to write the dictionary ID
* into the frame, if you so choose.
*
* Do I have to use zstd's dictionary builder?
* -------------------------------------------
*
* No! You can construct dictionary content however you please, it is just
* bytes. It will always be valid as a raw content dictionary. If you want
* a zstd dictionary, which can improve compression ratio, use
* `ZDICT_finalizeDictionary()`.
*
* What is the attack surface of a zstd dictionary?
* ------------------------------------------------
*
* Zstd is heavily fuzz tested, including loading fuzzed dictionaries, so
* zstd should never crash, or access out-of-bounds memory no matter what
* the dictionary is. However, if an attacker can control the dictionary
* during decompression, they can cause zstd to generate arbitrary bytes,
* just like if they controlled the compressed data.
*
******************************************************************************/
/*! ZDICT_trainFromBuffer():
* Train a dictionary from an array of samples.
@@ -64,7 +203,14 @@ ZDICTLIB_API size_t ZDICT_trainFromBuffer(void* dictBuffer, size_t dictBufferCap
typedef struct {
int compressionLevel; /*< optimize for a specific zstd compression level; 0 means default */
unsigned notificationLevel; /*< Write log to stderr; 0 = none (default); 1 = errors; 2 = progression; 3 = details; 4 = debug; */
unsigned dictID; /*< force dictID value; 0 means auto mode (32-bits random value) */
unsigned dictID; /*< force dictID value; 0 means auto mode (32-bits random value)
* NOTE: The zstd format reserves some dictionary IDs for future use.
* You may use them in private settings, but be warned that they
* may be used by zstd in a public dictionary registry in the future.
* These dictionary IDs are:
* - low range : <= 32767
* - high range : >= (2^31)
*/
} ZDICT_params_t;
/*! ZDICT_finalizeDictionary():
lib/zstd.h
+87 -34
View File
@@ -449,7 +449,8 @@ typedef enum {
ZSTD_c_experimentalParam11=1008,
ZSTD_c_experimentalParam12=1009,
ZSTD_c_experimentalParam13=1010,
ZSTD_c_experimentalParam14=1011
ZSTD_c_experimentalParam14=1011,
ZSTD_c_experimentalParam15=1012
} ZSTD_cParameter;
typedef struct {
@@ -1085,6 +1086,28 @@ ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
#if defined(ZSTD_STATIC_LINKING_ONLY) && !defined(ZSTD_H_ZSTD_STATIC_LINKING_ONLY)
#define ZSTD_H_ZSTD_STATIC_LINKING_ONLY
/* Deprecation warnings :
* Should these warnings be a problem, it is generally possible to disable them,
* typically with -Wno-deprecated-declarations for gcc or _CRT_SECURE_NO_WARNINGS in Visual.
* Otherwise, it's also possible to define ZSTD_DISABLE_DEPRECATE_WARNINGS.
*/
#ifdef ZSTD_DISABLE_DEPRECATE_WARNINGS
# define ZSTD_DEPRECATED(message) ZSTDLIB_API /* disable deprecation warnings */
#else
# if defined (__cplusplus) && (__cplusplus >= 201402) /* C++14 or greater */
# define ZSTD_DEPRECATED(message) [[deprecated(message)]] ZSTDLIB_API
# elif (defined(GNUC) && (GNUC > 4 || (GNUC == 4 && GNUC_MINOR >= 5))) || defined(__clang__)
# define ZSTD_DEPRECATED(message) ZSTDLIB_API __attribute__((deprecated(message)))
# elif defined(__GNUC__) && (__GNUC__ >= 3)
# define ZSTD_DEPRECATED(message) ZSTDLIB_API __attribute__((deprecated))
# elif defined(_MSC_VER)
# define ZSTD_DEPRECATED(message) ZSTDLIB_API __declspec(deprecated(message))
# else
# pragma message("WARNING: You need to implement ZSTD_DEPRECATED for this compiler")
# define ZSTD_DEPRECATED(message) ZSTDLIB_API
# endif
#endif /* ZSTD_DISABLE_DEPRECATE_WARNINGS */
/****************************************************************************************
* experimental API (static linking only)
****************************************************************************************
@@ -1620,18 +1643,20 @@ ZSTDLIB_API ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParame
/*! ZSTD_compress_advanced() :
* Note : this function is now DEPRECATED.
* It can be replaced by ZSTD_compress2(), in combination with ZSTD_CCtx_setParameter() and other parameter setters.
* This prototype will be marked as deprecated and generate compilation warning on reaching v1.5.x */
ZSTDLIB_API size_t ZSTD_compress_advanced(ZSTD_CCtx* cctx,
* This prototype will generate compilation warnings. */
ZSTD_DEPRECATED("use ZSTD_compress2")
size_t ZSTD_compress_advanced(ZSTD_CCtx* cctx,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
const void* dict,size_t dictSize,
ZSTD_parameters params);
/*! ZSTD_compress_usingCDict_advanced() :
* Note : this function is now REDUNDANT.
* Note : this function is now DEPRECATED.
* It can be replaced by ZSTD_compress2(), in combination with ZSTD_CCtx_loadDictionary() and other parameter setters.
* This prototype will be marked as deprecated and generate compilation warning in some future version */
ZSTDLIB_API size_t ZSTD_compress_usingCDict_advanced(ZSTD_CCtx* cctx,
* This prototype will generate compilation warnings. */
ZSTD_DEPRECATED("use ZSTD_compress2 with ZSTD_CCtx_loadDictionary")
size_t ZSTD_compress_usingCDict_advanced(ZSTD_CCtx* cctx,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
const ZSTD_CDict* cdict,
@@ -1859,6 +1884,26 @@ ZSTDLIB_API size_t ZSTD_CCtx_refPrefix_advanced(ZSTD_CCtx* cctx, const void* pre
*/
#define ZSTD_c_useRowMatchFinder ZSTD_c_experimentalParam14
/* ZSTD_c_deterministicRefPrefix
* Default is 0 == disabled. Set to 1 to enable.
*
* Zstd produces different results for prefix compression when the prefix is
* directly adjacent to the data about to be compressed vs. when it isn't.
* This is because zstd detects that the two buffers are contiguous and it can
* use a more efficient match finding algorithm. However, this produces different
* results than when the two buffers are non-contiguous. This flag forces zstd
* to always load the prefix in non-contiguous mode, even if it happens to be
* adjacent to the data, to guarantee determinism.
*
* If you really care about determinism when using a dictionary or prefix,
* like when doing delta compression, you should select this option. It comes
* at a speed penalty of about ~2.5% if the dictionary and data happened to be
* contiguous, and is free if they weren't contiguous. We don't expect that
* intentionally making the dictionary and data contiguous will be worth the
* cost to memcpy() the data.
*/
#define ZSTD_c_deterministicRefPrefix ZSTD_c_experimentalParam15
/*! ZSTD_CCtx_getParameter() :
* Get the requested compression parameter value, selected by enum ZSTD_cParameter,
* and store it into int* value.
@@ -2070,11 +2115,13 @@ ZSTDLIB_API size_t ZSTD_DCtx_getParameter(ZSTD_DCtx* dctx, ZSTD_dParameter param
/*! ZSTD_DCtx_setFormat() :
* This function is REDUNDANT. Prefer ZSTD_DCtx_setParameter().
* Instruct the decoder context about what kind of data to decode next.
* This instruction is mandatory to decode data without a fully-formed header,
* such ZSTD_f_zstd1_magicless for example.
* @return : 0, or an error code (which can be tested using ZSTD_isError()). */
ZSTDLIB_API size_t ZSTD_DCtx_setFormat(ZSTD_DCtx* dctx, ZSTD_format_e format);
ZSTD_DEPRECATED("use ZSTD_DCtx_setParameter() instead")
size_t ZSTD_DCtx_setFormat(ZSTD_DCtx* dctx, ZSTD_format_e format);
/*! ZSTD_decompressStream_simpleArgs() :
* Same as ZSTD_decompressStream(),
@@ -2098,7 +2145,7 @@ ZSTDLIB_API size_t ZSTD_decompressStream_simpleArgs (
/*===== Advanced Streaming compression functions =====*/
/*! ZSTD_initCStream_srcSize() :
* This function is deprecated, and equivalent to:
* This function is DEPRECATED, and equivalent to:
* ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
* ZSTD_CCtx_refCDict(zcs, NULL); // clear the dictionary (if any)
* ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel);
@@ -2107,15 +2154,15 @@ ZSTDLIB_API size_t ZSTD_decompressStream_simpleArgs (
* pledgedSrcSize must be correct. If it is not known at init time, use
* ZSTD_CONTENTSIZE_UNKNOWN. Note that, for compatibility with older programs,
* "0" also disables frame content size field. It may be enabled in the future.
* Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x
* This prototype will generate compilation warnings.
*/
ZSTDLIB_API size_t
ZSTD_initCStream_srcSize(ZSTD_CStream* zcs,
ZSTD_DEPRECATED("use ZSTD_CCtx_reset, see zstd.h for detailed instructions")
size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs,
int compressionLevel,
unsigned long long pledgedSrcSize);
/*! ZSTD_initCStream_usingDict() :
* This function is deprecated, and is equivalent to:
* This function is DEPRECATED, and is equivalent to:
* ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
* ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel);
* ZSTD_CCtx_loadDictionary(zcs, dict, dictSize);
@@ -2124,15 +2171,15 @@ ZSTD_initCStream_srcSize(ZSTD_CStream* zcs,
* dict == NULL or dictSize < 8, in which case no dict is used.
* Note: dict is loaded with ZSTD_dct_auto (treated as a full zstd dictionary if
* it begins with ZSTD_MAGIC_DICTIONARY, else as raw content) and ZSTD_dlm_byCopy.
* Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x
* This prototype will generate compilation warnings.
*/
ZSTDLIB_API size_t
ZSTD_initCStream_usingDict(ZSTD_CStream* zcs,
ZSTD_DEPRECATED("use ZSTD_CCtx_reset, see zstd.h for detailed instructions")
size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs,
const void* dict, size_t dictSize,
int compressionLevel);
/*! ZSTD_initCStream_advanced() :
* This function is deprecated, and is approximately equivalent to:
* This function is DEPRECATED, and is approximately equivalent to:
* ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
* // Pseudocode: Set each zstd parameter and leave the rest as-is.
* for ((param, value) : params) {
@@ -2144,23 +2191,24 @@ ZSTD_initCStream_usingDict(ZSTD_CStream* zcs,
* dict is loaded with ZSTD_dct_auto and ZSTD_dlm_byCopy.
* pledgedSrcSize must be correct.
* If srcSize is not known at init time, use value ZSTD_CONTENTSIZE_UNKNOWN.
* Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x
* This prototype will generate compilation warnings.
*/
ZSTDLIB_API size_t
ZSTD_initCStream_advanced(ZSTD_CStream* zcs,
ZSTD_DEPRECATED("use ZSTD_CCtx_reset, see zstd.h for detailed instructions")
size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs,
const void* dict, size_t dictSize,
ZSTD_parameters params,
unsigned long long pledgedSrcSize);
/*! ZSTD_initCStream_usingCDict() :
* This function is deprecated, and equivalent to:
* This function is DEPRECATED, and equivalent to:
* ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
* ZSTD_CCtx_refCDict(zcs, cdict);
*
*
* note : cdict will just be referenced, and must outlive compression session
* Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x
* This prototype will generate compilation warnings.
*/
ZSTDLIB_API size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict);
ZSTD_DEPRECATED("use ZSTD_CCtx_reset and ZSTD_CCtx_refCDict, see zstd.h for detailed instructions")
size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict);
/*! ZSTD_initCStream_usingCDict_advanced() :
* This function is DEPRECATED, and is approximately equivalent to:
@@ -2175,18 +2223,21 @@ ZSTDLIB_API size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDi
* same as ZSTD_initCStream_usingCDict(), with control over frame parameters.
* pledgedSrcSize must be correct. If srcSize is not known at init time, use
* value ZSTD_CONTENTSIZE_UNKNOWN.
* Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x
* This prototype will generate compilation warnings.
*/
ZSTDLIB_API size_t
ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs,
ZSTD_DEPRECATED("use ZSTD_CCtx_reset and ZSTD_CCtx_refCDict, see zstd.h for detailed instructions")
size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs,
const ZSTD_CDict* cdict,
ZSTD_frameParameters fParams,
unsigned long long pledgedSrcSize);
/*! ZSTD_resetCStream() :
* This function is deprecated, and is equivalent to:
* This function is DEPRECATED, and is equivalent to:
* ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
* ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize);
* Note: ZSTD_resetCStream() interprets pledgedSrcSize == 0 as ZSTD_CONTENTSIZE_UNKNOWN, but
* ZSTD_CCtx_setPledgedSrcSize() does not do the same, so ZSTD_CONTENTSIZE_UNKNOWN must be
* explicitly specified.
*
* start a new frame, using same parameters from previous frame.
* This is typically useful to skip dictionary loading stage, since it will re-use it in-place.
@@ -2196,9 +2247,10 @@ ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs,
* For the time being, pledgedSrcSize==0 is interpreted as "srcSize unknown" for compatibility with older programs,
* but it will change to mean "empty" in future version, so use macro ZSTD_CONTENTSIZE_UNKNOWN instead.
* @return : 0, or an error code (which can be tested using ZSTD_isError())
* Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x
* This prototype will generate compilation warnings.
*/
ZSTDLIB_API size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize);
ZSTD_DEPRECATED("use ZSTD_CCtx_reset, see zstd.h for detailed instructions")
size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize);
typedef struct {
@@ -2285,8 +2337,7 @@ ZSTDLIB_API size_t ZSTD_resetDStream(ZSTD_DStream* zds);
ZSTD_CCtx object can be re-used multiple times within successive compression operations.
Start by initializing a context.
Use ZSTD_compressBegin(), or ZSTD_compressBegin_usingDict() for dictionary compression,
or ZSTD_compressBegin_advanced(), for finer parameter control.
Use ZSTD_compressBegin(), or ZSTD_compressBegin_usingDict() for dictionary compression.
It's also possible to duplicate a reference context which has already been initialized, using ZSTD_copyCCtx()
Then, consume your input using ZSTD_compressContinue().
@@ -2311,15 +2362,17 @@ ZSTDLIB_API size_t ZSTD_resetDStream(ZSTD_DStream* zds);
/*===== Buffer-less streaming compression functions =====*/
ZSTDLIB_API size_t ZSTD_compressBegin(ZSTD_CCtx* cctx, int compressionLevel);
ZSTDLIB_API size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, int compressionLevel);
ZSTDLIB_API size_t ZSTD_compressBegin_advanced(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, ZSTD_parameters params, unsigned long long pledgedSrcSize); /**< pledgedSrcSize : If srcSize is not known at init time, use ZSTD_CONTENTSIZE_UNKNOWN */
ZSTDLIB_API size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict); /**< note: fails if cdict==NULL */
ZSTDLIB_API size_t ZSTD_compressBegin_usingCDict_advanced(ZSTD_CCtx* const cctx, const ZSTD_CDict* const cdict, ZSTD_frameParameters const fParams, unsigned long long const pledgedSrcSize); /* compression parameters are already set within cdict. pledgedSrcSize must be correct. If srcSize is not known, use macro ZSTD_CONTENTSIZE_UNKNOWN */
ZSTDLIB_API size_t ZSTD_copyCCtx(ZSTD_CCtx* cctx, const ZSTD_CCtx* preparedCCtx, unsigned long long pledgedSrcSize); /**< note: if pledgedSrcSize is not known, use ZSTD_CONTENTSIZE_UNKNOWN */
ZSTDLIB_API size_t ZSTD_compressContinue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
ZSTDLIB_API size_t ZSTD_compressEnd(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
/* The ZSTD_compressBegin_advanced() and ZSTD_compressBegin_usingCDict_advanced() are now DEPRECATED and will generate a compiler warning */
ZSTD_DEPRECATED("use advanced API to access custom parameters")
size_t ZSTD_compressBegin_advanced(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, ZSTD_parameters params, unsigned long long pledgedSrcSize); /**< pledgedSrcSize : If srcSize is not known at init time, use ZSTD_CONTENTSIZE_UNKNOWN */
ZSTD_DEPRECATED("use advanced API to access custom parameters")
size_t ZSTD_compressBegin_usingCDict_advanced(ZSTD_CCtx* const cctx, const ZSTD_CDict* const cdict, ZSTD_frameParameters const fParams, unsigned long long const pledgedSrcSize); /* compression parameters are already set within cdict. pledgedSrcSize must be correct. If srcSize is not known, use macro ZSTD_CONTENTSIZE_UNKNOWN */
/**
Buffer-less streaming decompression (synchronous mode)