krak/zstd
krak/zstd
1
0
Fork 0
mirror of https://github.com/facebook/zstd.git synced 2025-03-06 08:49:28 +02:00
Code Issues Releases 1 Activity

implemented ZSTD_refPrefix()

Browse Source
This commit is contained in:
Yann Collet 2017-06-27 15:49:12 -07:00
parent 7d3816183f
commit b7372933b8
4 changed files with 61 additions and 57 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
doc/zstd_manual.html
View File

@ -348,7 +348,7 @@ static const ZSTD_customMem ZSTD_defaultCMem = { NULL, NULL, NULL };
<pre><b>size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize);
</b><p> `src` should point to the start of a ZSTD encoded frame or skippable frame
`srcSize` must be at least as large as the frame
@return : the compressed size of the frame pointed to by `src`,FUZ_rand(&lseed) & 1)
@return : the compressed size of the frame pointed to by `src`,
suitable to pass to `ZSTD_decompress` or similar,
or an error code if given invalid input.
</p></pre><BR>
@ -806,20 +806,13 @@ void ZSTD_copyDCtx(ZSTD_DCtx* dctx, const ZSTD_DCtx* preparedDCtx);
* The higher the value of selected strategy, the more complex it is,
* resulting in stronger and slower compression.
* Special: value 0 means "do not change strategy". */
#if 0
ZSTD_p_windowSize, </b>/* Maximum allowed back-reference distance.<b>
* Can be set to a more precise value than windowLog.
* Will be transparently reduced to closest possible inferior value
* (see Zstandard compression format) */
</b>/* Not ready yet ! */<b>
#endif
</b>/* frame parameters */<b>
ZSTD_p_contentSizeFlag=200, </b>/* Content size is written into frame header _whenever known_ (default:1) */<b>
ZSTD_p_checksumFlag, </b>/* A 32-bits checksum of content is written at end of frame (default:0) */<b>
ZSTD_p_dictIDFlag, </b>/* When applicable, dictID of dictionary is provided in frame header (default:1) */<b>
</b>/* dictionary parameters (must be set before loading) */<b>
</b>/* dictionary parameters (must be set before ZSTD_CCtx_loadDictionary) */<b>
ZSTD_p_dictMode=300, </b>/* Select how dictionary content must be interpreted. Value must be from type ZSTD_dictMode_e.<b>
* default : 0==auto : dictionary will be "full" if it respects specification, otherwise it will be "rawContent" */
ZSTD_p_refDictContent, </b>/* Dictionary content will be referenced, instead of copied (default:0==byCopy).<b>
@ -876,7 +869,7 @@ void ZSTD_copyDCtx(ZSTD_DCtx* dctx, const ZSTD_DCtx* preparedDCtx);
</p></pre><BR>
<pre><b>size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict);
</b><p> Ref a prepared dictionary, to be used for all next compression jobs.
</b><p> Reference a prepared dictionary, to be used for all next compression jobs.
Note that compression parameters are enforced from within CDict,
and supercede any compression parameter previously set within CCtx.
The dictionary will remain valid for future compression jobs using same CCtx.
@ -888,16 +881,18 @@ void ZSTD_copyDCtx(ZSTD_DCtx* dctx, const ZSTD_DCtx* preparedDCtx);
</p></pre><BR>
<pre><b>size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize); </b>/* Not ready yet ! <===================================== */<b>
</b><p> Reference a prefix (raw-content dictionary) for next compression job.
Decompression will have to use same prefix.
Prefix is only used once. Tables are discarded at end of compression job.
If there is a need to use same prefix multiple times, consider embedding it into a ZSTD_CDict.
<pre><b>size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize);
</b><p> Reference a prefix (single-usage dictionary) for next compression job.
Decompression need same prefix to properly regenerate data.
Prefix is **only used once**. Tables are discarded at end of compression job.
Subsequent compression jobs will be done without prefix (if none is explicitly referenced).
If there is a need to use same prefix multiple times, consider embedding it into a ZSTD_CDict instead.
@result : 0, or an error code (which can be tested with ZSTD_isError()).
Special : Adding a NULL (or 0-size) dictionary invalidates any previous prefix, meaning "return to no-dictionary mode".
Special : Adding any prefix (including NULL) invalidates any previous prefix or dictionary
Note 1 : Prefix buffer is referenced. It must outlive compression job.
Note 2 : Referencing a prefix involves building tables, which are dependent on compression parameters.
It's a CPU-heavy operation, with non-negligible impact on latency.
It's a CPU-heavy operation, with non-negligible impact on latency.
Note 3 : it's possible to alter ZSTD_p_dictMode using ZSTD_CCtx_setParameter()
</p></pre><BR>
<pre><b>typedef enum {

56
lib/compress/zstd_compress.c
View File

@ -88,8 +88,6 @@ struct ZSTD_CCtx_s {
U32 hashLog3; /* dispatch table : larger == faster, more memory */
U32 loadedDictEnd; /* index of end of dictionary */
U32 forceWindow; /* force back-references to respect limit of 1<<wLog, even for dictionary */
ZSTD_dictMode_e dictMode; /* select restricting dictionary to "rawContent" or "fullDict" only */
U32 dictContentByRef;
ZSTD_compressionStage_e stage;
U32 rep[ZSTD_REP_NUM];
U32 repToConfirm[ZSTD_REP_NUM];
@ -119,8 +117,6 @@ struct ZSTD_CCtx_s {
unsigned* entropyScratchSpace;
/* streaming */
ZSTD_CDict* cdictLocal;
const ZSTD_CDict* cdict;
char* inBuff;
size_t inBuffSize;
size_t inToCompress;
@ -133,6 +129,14 @@ struct ZSTD_CCtx_s {
ZSTD_cStreamStage streamStage;
U32 frameEnded;
/* Dictionary */
ZSTD_dictMode_e dictMode; /* select restricting dictionary to "rawContent" or "fullDict" only */
U32 dictContentByRef;
ZSTD_CDict* cdictLocal;
const ZSTD_CDict* cdict;
const void* prefix;
size_t prefixSize;
/* Multi-threading */
U32 nbThreads;
ZSTDMT_CCtx* mtctx;
@ -427,19 +431,22 @@ ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, s
return 0;
}
/* Not ready yet ! */
size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize)
{
(void)cctx; (void)prefix; (void)prefixSize; /* to be done later */
if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
return ERROR(compressionParameter_unsupported);
}
size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict)
{
if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
cctx->cdict = cdict;
return ERROR(compressionParameter_unsupported);
cctx->prefix = NULL; /* exclusive */
cctx->prefixSize = 0;
return 0;
}
size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize)
{
if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
cctx->cdict = NULL; /* prefix discards any prior cdict */
cctx->prefix = prefix;
cctx->prefixSize = prefixSize;
return 0;
}
static void ZSTD_startNewCompression(ZSTD_CCtx* cctx)
@ -3622,14 +3629,17 @@ size_t ZSTD_CStreamOutSize(void)
}
static size_t ZSTD_resetCStream_internal(ZSTD_CStream* zcs,
ZSTD_parameters params,
unsigned long long pledgedSrcSize)
const void* dict, size_t dictSize, const ZSTD_CDict* cdict,
ZSTD_parameters params, unsigned long long pledgedSrcSize)
{
DEBUGLOG(5, "ZSTD_resetCStream_internal");
/* params are supposed to be fully validated at this point */
assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams)));
assert(!((dict) && (cdict))); /* either dict or cdict, not both */
CHECK_F( ZSTD_compressBegin_internal(zcs,
NULL, 0, ZSTD_dm_auto,
zcs->cdict,
dict, dictSize, ZSTD_dm_auto, /* <========= Todo : make dictMode controllable ! */
cdict,
params, pledgedSrcSize,
ZSTDb_buffered) );
@ -3650,10 +3660,11 @@ size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize)
if (zcs->compressionLevel != ZSTD_CLEVEL_CUSTOM) {
params.cParams = ZSTD_getCParams(zcs->compressionLevel, pledgedSrcSize, 0 /* dictSize */);
}
return ZSTD_resetCStream_internal(zcs, params, pledgedSrcSize);
return ZSTD_resetCStream_internal(zcs, NULL, 0, zcs->cdict, params, pledgedSrcSize);
}
/*! ZSTD_initCStream_internal() :
* Note : not static, but hidden (not exposed). Used by zstdmt_compress.c
* Assumption 1 : params are valid
* Assumption 2 : either dict, or cdict, is defined, not both */
size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs,
@ -3672,7 +3683,7 @@ size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs,
}
ZSTD_freeCDict(zcs->cdictLocal);
zcs->cdictLocal = ZSTD_createCDict_advanced(dict, dictSize,
0 /* byReference */, ZSTD_dm_auto,
0 /* byReference */, ZSTD_dm_auto, /* <======== Todo : make dictMode controllable */
params.cParams, zcs->customMem);
zcs->cdict = zcs->cdictLocal;
if (zcs->cdictLocal == NULL) return ERROR(memory_allocation);
@ -3688,7 +3699,7 @@ size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs,
zcs->requestedParams = params;
zcs->compressionLevel = ZSTD_CLEVEL_CUSTOM;
return ZSTD_resetCStream_internal(zcs, params, pledgedSrcSize);
return ZSTD_resetCStream_internal(zcs, NULL, 0, zcs->cdict, params, pledgedSrcSize);
}
/* ZSTD_initCStream_usingCDict_advanced() :
@ -3925,7 +3936,10 @@ size_t ZSTD_compress_generic (ZSTD_CCtx* cctx,
} else
#endif
{
CHECK_F( ZSTD_resetCStream_internal(cctx, params, cctx->pledgedSrcSizePlusOne-1) );
const void* const prefix = cctx->prefix;
size_t const prefixSize = cctx->prefixSize;
cctx->prefix = NULL; cctx->prefixSize = 0; /* single usage */
CHECK_F( ZSTD_resetCStream_internal(cctx, prefix, prefixSize, cctx->cdict, params, cctx->pledgedSrcSizePlusOne-1) );
} }
#ifdef ZSTD_MULTITHREAD

27
lib/zstd.h
View File

@ -947,20 +947,13 @@ typedef enum {
* The higher the value of selected strategy, the more complex it is,
* resulting in stronger and slower compression.
* Special: value 0 means "do not change strategy". */
#if 0
ZSTD_p_windowSize, /* Maximum allowed back-reference distance.
* Can be set to a more precise value than windowLog.
* Will be transparently reduced to closest possible inferior value
* (see Zstandard compression format) */
/* Not ready yet ! */
#endif
/* frame parameters */
ZSTD_p_contentSizeFlag=200, /* Content size is written into frame header _whenever known_ (default:1) */
ZSTD_p_checksumFlag, /* A 32-bits checksum of content is written at end of frame (default:0) */
ZSTD_p_dictIDFlag, /* When applicable, dictID of dictionary is provided in frame header (default:1) */
/* dictionary parameters (must be set before loading) */
/* dictionary parameters (must be set before ZSTD_CCtx_loadDictionary) */
ZSTD_p_dictMode=300, /* Select how dictionary content must be interpreted. Value must be from type ZSTD_dictMode_e.
* default : 0==auto : dictionary will be "full" if it respects specification, otherwise it will be "rawContent" */
ZSTD_p_refDictContent, /* Dictionary content will be referenced, instead of copied (default:0==byCopy).
@ -1018,7 +1011,7 @@ ZSTDLIB_API size_t ZSTD_CCtx_setPledgedSrcSize(ZSTD_CCtx* cctx, unsigned long lo
ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, size_t dictSize);
/*! ZSTD_CCtx_refCDict() :
* Ref a prepared dictionary, to be used for all next compression jobs.
* Reference a prepared dictionary, to be used for all next compression jobs.
* Note that compression parameters are enforced from within CDict,
* and supercede any compression parameter previously set within CCtx.
* The dictionary will remain valid for future compression jobs using same CCtx.
@ -1031,16 +1024,18 @@ ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, s
ZSTDLIB_API size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict);
/*! ZSTD_CCtx_refPrefix() :
* Reference a prefix (raw-content dictionary) for next compression job.
* Decompression will have to use same prefix.
* Prefix is only used once. Tables are discarded at end of compression job.
* If there is a need to use same prefix multiple times, consider embedding it into a ZSTD_CDict.
* Reference a prefix (single-usage dictionary) for next compression job.
* Decompression need same prefix to properly regenerate data.
* Prefix is **only used once**. Tables are discarded at end of compression job.
* Subsequent compression jobs will be done without prefix (if none is explicitly referenced).
* If there is a need to use same prefix multiple times, consider embedding it into a ZSTD_CDict instead.
* @result : 0, or an error code (which can be tested with ZSTD_isError()).
* Special : Adding a NULL (or 0-size) dictionary invalidates any previous prefix, meaning "return to no-dictionary mode".
* Special : Adding any prefix (including NULL) invalidates any previous prefix or dictionary
* Note 1 : Prefix buffer is referenced. It must outlive compression job.
* Note 2 : Referencing a prefix involves building tables, which are dependent on compression parameters.
* It's a CPU-heavy operation, with non-negligible impact on latency. */
ZSTDLIB_API size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize); /* Not ready yet ! <===================================== */
* It's a CPU-heavy operation, with non-negligible impact on latency.
* Note 3 : it's possible to alter ZSTD_p_dictMode using ZSTD_CCtx_setParameter() */
ZSTDLIB_API size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize);

6
tests/zstreamtest.c
View File

@ -1266,11 +1266,11 @@ static int fuzzerTests_newAPI(U32 seed, U32 nbTests, unsigned startTest, double
}
/* compression init */
CHECK_Z( ZSTD_CCtx_loadDictionary(zc, NULL, 0) ); /* cancel previous dict /*/
if ((FUZ_rand(&lseed)&1) /* at beginning, to keep same nb of rand */
&& oldTestLog /* at least one test happened */ && resetAllowed) {
maxTestSize = FUZ_randomLength(&lseed, oldTestLog+2);
if (maxTestSize >= srcBufferSize) maxTestSize = srcBufferSize-1;
CHECK_Z( ZSTD_CCtx_loadDictionary(zc, NULL, 0) );
{ int const compressionLevel = (FUZ_rand(&lseed) % 5) + 1;
CHECK_Z( ZSTD_CCtx_setParameter(zc, ZSTD_p_compressionLevel, compressionLevel) );
}
@ -1294,7 +1294,6 @@ static int fuzzerTests_newAPI(U32 seed, U32 nbTests, unsigned startTest, double
ZSTD_compressionParameters cParams = ZSTD_getCParams(cLevel, pledgedSrcSize, dictSize);
/* mess with compression parameters */
CHECK_Z( ZSTD_CCtx_loadDictionary(zc, NULL, 0) ); /* cancel previous dict, to allow new compression parameters */
cParams.windowLog += (FUZ_rand(&lseed) & 3) - 1;
cParams.hashLog += (FUZ_rand(&lseed) & 3) - 1;
cParams.chainLog += (FUZ_rand(&lseed) & 3) - 1;
@ -1312,7 +1311,8 @@ static int fuzzerTests_newAPI(U32 seed, U32 nbTests, unsigned startTest, double
/* unconditionally set, to be sync with decoder */
if (FUZ_rand(&lseed) & 1) CHECK_Z( ZSTD_CCtx_setParameter(zc, ZSTD_p_refDictContent, FUZ_rand(&lseed) & 1) );
CHECK_Z( ZSTD_CCtx_loadDictionary(zc, dict, dictSize) );
if (FUZ_rand(&lseed) & 1) { CHECK_Z( ZSTD_CCtx_loadDictionary(zc, dict, dictSize) ); }
else { CHECK_Z( ZSTD_CCtx_refPrefix(zc, dict, dictSize) ); }
if (dict && dictSize) {
/* test that compression parameters are correctly rejected after setting a dictionary */