From: Yann Collet Date: Thu, 15 Nov 2018 18:51:24 +0000 (-0800) Subject: Merge branch 'dev' into advancedAPI X-Git-Tag: v1.3.8~33^2~31 X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=06c8d5a4f4db1bf965622e20d1343dfe059ef296;p=thirdparty%2Fzstd.git Merge branch 'dev' into advancedAPI fixed rsyncable --- 06c8d5a4f4db1bf965622e20d1343dfe059ef296 diff --cc lib/zstd.h index 0a9227a59,6eb2dd835..3338eae18 --- a/lib/zstd.h +++ b/lib/zstd.h @@@ -473,472 -541,444 +473,494 @@@ ZSTDLIB_API size_t ZSTD_sizeof_DStream( ZSTDLIB_API size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict); ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict); -/*! ZSTD_estimate*() : - * These functions make it possible to estimate memory usage - * of a future {D,C}Ctx, before its creation. - * ZSTD_estimateCCtxSize() will provide a budget large enough for any compression level up to selected one. - * It will also consider src size to be arbitrarily "large", which is worst case. - * If srcSize is known to always be small, ZSTD_estimateCCtxSize_usingCParams() can provide a tighter estimation. - * ZSTD_estimateCCtxSize_usingCParams() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel. - * ZSTD_estimateCCtxSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParam_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_p_nbWorkers is >= 1. - * Note : CCtx size estimation is only correct for single-threaded compression. */ -ZSTDLIB_API size_t ZSTD_estimateCCtxSize(int compressionLevel); -ZSTDLIB_API size_t ZSTD_estimateCCtxSize_usingCParams(ZSTD_compressionParameters cParams); -ZSTDLIB_API size_t ZSTD_estimateCCtxSize_usingCCtxParams(const ZSTD_CCtx_params* params); -ZSTDLIB_API size_t ZSTD_estimateDCtxSize(void); -/*! ZSTD_estimateCStreamSize() : - * ZSTD_estimateCStreamSize() will provide a budget large enough for any compression level up to selected one. - * It will also consider src size to be arbitrarily "large", which is worst case. - * If srcSize is known to always be small, ZSTD_estimateCStreamSize_usingCParams() can provide a tighter estimation. - * ZSTD_estimateCStreamSize_usingCParams() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel. - * ZSTD_estimateCStreamSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParam_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_p_nbWorkers is >= 1. - * Note : CStream size estimation is only correct for single-threaded compression. - * ZSTD_DStream memory budget depends on window Size. - * This information can be passed manually, using ZSTD_estimateDStreamSize, - * or deducted from a valid frame Header, using ZSTD_estimateDStreamSize_fromFrame(); - * Note : if streaming is init with function ZSTD_init?Stream_usingDict(), - * an internal ?Dict will be created, which additional size is not estimated here. - * In this case, get total size by adding ZSTD_estimate?DictSize */ -ZSTDLIB_API size_t ZSTD_estimateCStreamSize(int compressionLevel); -ZSTDLIB_API size_t ZSTD_estimateCStreamSize_usingCParams(ZSTD_compressionParameters cParams); -ZSTDLIB_API size_t ZSTD_estimateCStreamSize_usingCCtxParams(const ZSTD_CCtx_params* params); -ZSTDLIB_API size_t ZSTD_estimateDStreamSize(size_t windowSize); -ZSTDLIB_API size_t ZSTD_estimateDStreamSize_fromFrame(const void* src, size_t srcSize); +/*************************************** +* Advanced compression API +***************************************/ -/*! ZSTD_estimate?DictSize() : - * ZSTD_estimateCDictSize() will bet that src size is relatively "small", and content is copied, like ZSTD_createCDict(). - * ZSTD_estimateCDictSize_advanced() makes it possible to control compression parameters precisely, like ZSTD_createCDict_advanced(). - * Note : dictionaries created by reference (`ZSTD_dlm_byRef`) are logically smaller. +/* API design : + * In this API, parameters are pushed one by one into an existing context, + * using ZSTD_CCtx_set*() functions. + * Pushed parameters are sticky : they are applied to next job, and any subsequent job. + * Note that "sticky" parameters are only applicable with `ZSTD_compress_generic()` ! + * They do not apply should the context be used with a "simple" variant such as ZSTD_compressCCtx() + * + * It's possible to reset all parameters to "default" using ZSTD_CCtx_reset(). + * + * This API gives access to all advanced capabilities. + * It supercedes all other "advanced" API entry points in the experimental section. + * In the future, we expect to remove from experimental API entry points which are redundant with this API. */ -ZSTDLIB_API size_t ZSTD_estimateCDictSize(size_t dictSize, int compressionLevel); -ZSTDLIB_API size_t ZSTD_estimateCDictSize_advanced(size_t dictSize, ZSTD_compressionParameters cParams, ZSTD_dictLoadMethod_e dictLoadMethod); -ZSTDLIB_API size_t ZSTD_estimateDDictSize(size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod); -/*! ZSTD_initStatic*() : - * Initialize an object using a pre-allocated fixed-size buffer. - * workspace: The memory area to emplace the object into. - * Provided pointer *must be 8-bytes aligned*. - * Buffer must outlive object. - * workspaceSize: Use ZSTD_estimate*Size() to determine - * how large workspace must be to support target scenario. - * @return : pointer to object (same address as workspace, just different type), - * or NULL if error (size too small, incorrect alignment, etc.) - * Note : zstd will never resize nor malloc() when using a static buffer. - * If the object requires more memory than available, - * zstd will just error out (typically ZSTD_error_memory_allocation). - * Note 2 : there is no corresponding "free" function. - * Since workspace is allocated externally, it must be freed externally too. - * Note 3 : cParams : use ZSTD_getCParams() to convert a compression level - * into its associated cParams. - * Limitation 1 : currently not compatible with internal dictionary creation, triggered by - * ZSTD_CCtx_loadDictionary(), ZSTD_initCStream_usingDict() or ZSTD_initDStream_usingDict(). - * Limitation 2 : static cctx currently not compatible with multi-threading. - * Limitation 3 : static dctx is incompatible with legacy support. - */ -ZSTDLIB_API ZSTD_CCtx* ZSTD_initStaticCCtx(void* workspace, size_t workspaceSize); -ZSTDLIB_API ZSTD_CStream* ZSTD_initStaticCStream(void* workspace, size_t workspaceSize); /**< same as ZSTD_initStaticCCtx() */ -ZSTDLIB_API ZSTD_DCtx* ZSTD_initStaticDCtx(void* workspace, size_t workspaceSize); -ZSTDLIB_API ZSTD_DStream* ZSTD_initStaticDStream(void* workspace, size_t workspaceSize); /**< same as ZSTD_initStaticDCtx() */ +/* Compression strategies, listed from fastest to strongest */ +typedef enum { ZSTD_fast=1, + ZSTD_dfast=2, + ZSTD_greedy=3, + ZSTD_lazy=4, + ZSTD_lazy2=5, + ZSTD_btlazy2=6, + ZSTD_btopt=7, + ZSTD_btultra=8 + /* note : new strategies might be added in the future */ + } ZSTD_strategy; -ZSTDLIB_API const ZSTD_CDict* ZSTD_initStaticCDict( - void* workspace, size_t workspaceSize, - const void* dict, size_t dictSize, - ZSTD_dictLoadMethod_e dictLoadMethod, - ZSTD_dictContentType_e dictContentType, - ZSTD_compressionParameters cParams); +typedef enum { -ZSTDLIB_API const ZSTD_DDict* ZSTD_initStaticDDict( - void* workspace, size_t workspaceSize, - const void* dict, size_t dictSize, - ZSTD_dictLoadMethod_e dictLoadMethod, - ZSTD_dictContentType_e dictContentType); + /* compression parameters */ + ZSTD_p_compressionLevel=100, /* Update all compression parameters according to pre-defined cLevel table + * Default level is ZSTD_CLEVEL_DEFAULT==3. + * Special: value 0 means default, which is controlled by ZSTD_CLEVEL_DEFAULT. + * Note 1 : it's possible to pass a negative compression level by casting it to unsigned type. + * Note 2 : setting a level sets all default values of other compression parameters */ + ZSTD_p_windowLog=101, /* Maximum allowed back-reference distance, expressed as power of 2. + * Must be clamped between ZSTD_WINDOWLOG_MIN and ZSTD_WINDOWLOG_MAX. + * Special: value 0 means "use default windowLog". + * Note: Using a window size greater than 1< dFast. + * Special: value 0 means "use default hashLog". */ + ZSTD_p_chainLog=103, /* Size of the multi-probe search table, as a power of 2. + * Resulting table size is (1 << (chainLog+2)). + * Must be clamped between ZSTD_CHAINLOG_MIN and ZSTD_CHAINLOG_MAX. + * Larger tables result in better and slower compression. + * This parameter is useless when using "fast" strategy. + * Note it's still useful when using "dfast" strategy, + * in which case it defines a secondary probe table. + * Special: value 0 means "use default chainLog". */ + ZSTD_p_searchLog=104, /* Number of search attempts, as a power of 2. + * More attempts result in better and slower compression. + * This parameter is useless when using "fast" and "dFast" strategies. + * Special: value 0 means "use default searchLog". */ + ZSTD_p_minMatch=105, /* Minimum size of searched matches (note : repCode matches can be smaller). + * Larger values make faster compression and decompression, but decrease ratio. + * Must be clamped between ZSTD_SEARCHLENGTH_MIN and ZSTD_SEARCHLENGTH_MAX. + * Note that currently, for all strategies < btopt, effective minimum is 4. + * , for all strategies > fast, effective maximum is 6. + * Special: value 0 means "use default minMatchLength". */ + ZSTD_p_targetLength=106, /* Impact of this field depends on strategy. + * For strategies btopt & btultra: + * Length of Match considered "good enough" to stop search. + * Larger values make compression stronger, and slower. + * For strategy fast: + * Distance between match sampling. + * Larger values make compression faster, and weaker. + * Special: value 0 means "use default targetLength". */ + ZSTD_p_compressionStrategy=107, /* See ZSTD_strategy enum definition. + * Cast selected strategy as unsigned for ZSTD_CCtx_setParameter() compatibility. + * The higher the value of selected strategy, the more complex it is, + * resulting in stronger and slower compression. + * Special: value 0 means "use default strategy". */ -/*! Custom memory allocation : - * These prototypes make it possible to pass your own allocation/free functions. - * ZSTD_customMem is provided at creation time, using ZSTD_create*_advanced() variants listed below. - * All allocation/free operations will be completed using these custom variants instead of regular ones. - */ -typedef void* (*ZSTD_allocFunction) (void* opaque, size_t size); -typedef void (*ZSTD_freeFunction) (void* opaque, void* address); -typedef struct { ZSTD_allocFunction customAlloc; ZSTD_freeFunction customFree; void* opaque; } ZSTD_customMem; -static ZSTD_customMem const ZSTD_defaultCMem = { NULL, NULL, NULL }; /**< this constant defers to stdlib's functions */ + /* LDM mode parameters */ + ZSTD_p_enableLongDistanceMatching=160, /* Enable long distance matching. + * This parameter is designed to improve compression ratio + * for large inputs, by finding large matches at long distance. + * It increases memory usage and window size. + * Note: enabling this parameter increases ZSTD_p_windowLog to 128 MB + * except when expressly set to a different value. */ + ZSTD_p_ldmHashLog=161, /* Size of the table for long distance matching, as a power of 2. + * Larger values increase memory usage and compression ratio, + * but decrease compression speed. + * Must be clamped between ZSTD_HASHLOG_MIN and ZSTD_HASHLOG_MAX + * default: windowlog - 7. + * Special: value 0 means "automatically determine hashlog". */ + ZSTD_p_ldmMinMatch=162, /* Minimum match size for long distance matcher. + * Larger/too small values usually decrease compression ratio. + * Must be clamped between ZSTD_LDM_MINMATCH_MIN and ZSTD_LDM_MINMATCH_MAX. + * Special: value 0 means "use default value" (default: 64). */ + ZSTD_p_ldmBucketSizeLog=163, /* Log size of each bucket in the LDM hash table for collision resolution. + * Larger values improve collision resolution but decrease compression speed. + * The maximum value is ZSTD_LDM_BUCKETSIZELOG_MAX . + * Special: value 0 means "use default value" (default: 3). */ + ZSTD_p_ldmHashEveryLog=164, /* Frequency of inserting/looking up entries into the LDM hash table. + * Must be clamped between 0 and (ZSTD_WINDOWLOG_MAX - ZSTD_HASHLOG_MIN). + * Default is MAX(0, (windowLog - ldmHashLog)), optimizing hash table usage. + * Larger values improve compression speed. + * Deviating far from default value will likely result in a compression ratio decrease. + * Special: value 0 means "automatically determine hashEveryLog". */ -ZSTDLIB_API ZSTD_CCtx* ZSTD_createCCtx_advanced(ZSTD_customMem customMem); -ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream_advanced(ZSTD_customMem customMem); -ZSTDLIB_API ZSTD_DCtx* ZSTD_createDCtx_advanced(ZSTD_customMem customMem); -ZSTDLIB_API ZSTD_DStream* ZSTD_createDStream_advanced(ZSTD_customMem customMem); + /* frame parameters */ + ZSTD_p_contentSizeFlag=200, /* Content size will be written into frame header _whenever known_ (default:1) + * Content size must be known at the beginning of compression, + * it is provided using ZSTD_CCtx_setPledgedSrcSize() */ + ZSTD_p_checksumFlag=201, /* A 32-bits checksum of content is written at end of frame (default:0) */ + ZSTD_p_dictIDFlag=202, /* When applicable, dictionary's ID is written into frame header (default:1) */ -ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_advanced(const void* dict, size_t dictSize, - ZSTD_dictLoadMethod_e dictLoadMethod, - ZSTD_dictContentType_e dictContentType, - ZSTD_compressionParameters cParams, - ZSTD_customMem customMem); - -ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_advanced(const void* dict, size_t dictSize, - ZSTD_dictLoadMethod_e dictLoadMethod, - ZSTD_dictContentType_e dictContentType, - ZSTD_customMem customMem); + /* multi-threading parameters */ + /* These parameters are only useful if multi-threading is enabled (compiled with build macro ZSTD_MULTITHREAD). + * They return an error otherwise. */ + ZSTD_p_nbWorkers=400, /* Select how many threads will be spawned to compress in parallel. + * When nbWorkers >= 1, triggers asynchronous mode : + * ZSTD_compress_generic() consumes some input, flush some output if possible, and immediately gives back control to caller, + * while compression work is performed in parallel, within worker threads. + * (note : a strong exception to this rule is when first invocation sets ZSTD_e_end : it becomes a blocking call). + * More workers improve speed, but also increase memory usage. + * Default value is `0`, aka "single-threaded mode" : no worker is spawned, compression is performed inside Caller's thread, all invocations are blocking */ + ZSTD_p_jobSize=401, /* Size of a compression job. This value is enforced only when nbWorkers >= 1. + * Each compression job is completed in parallel, so this value can indirectly impact the nb of active threads. + * 0 means default, which is dynamically determined based on compression parameters. + * Job size must be a minimum of overlapSize, or 1 MB, whichever is largest. + * The minimum size is automatically and transparently enforced */ + ZSTD_p_overlapSizeLog=402, /* Size of previous input reloaded at the beginning of each job, as a fraction of window size. + * 0 : no overlap; 6(default) : use 1/8th of windowSize; >=9 : use full windowSize */ + /* =================================================================== */ + /* experimental parameters - no stability guaranteed */ + /* => note : should this part be exported in a different section of zstd.h ? */ + /* =================================================================== */ + /* compression format */ + ZSTD_p_format = 10, /* See ZSTD_format_e enum definition. + * Cast selected format as unsigned for ZSTD_CCtx_setParameter() compatibility. */ -/*************************************** -* Advanced compression functions -***************************************/ + ZSTD_p_forceMaxWindow=1100, /* Force back-reference distances to remain < windowSize, + * even when referencing into Dictionary content (default:0) */ + ZSTD_p_forceAttachDict, /* Controls whether the contents of a CDict are + * used in place, or whether they are copied into + * the working context. + * + * Accepts values from the ZSTD_dictAttachPref_e + * enum. See the comments on that enum for an + * explanation of the feature. + */ ++ /* Question : should rsyncable be categorized as experimental, or be candidate for stable ? */ ++ ZSTD_p_rsyncable, /* Enables rsyncable mode, which makes compressed ++ * files more rsync friendly by adding periodic ++ * synchronization points to the compressed data. ++ * The target average block size is ++ * ZSTD_p_jobSize / 2. You can modify the job size ++ * to increase or decrease the granularity of the ++ * synchronization point. Once the jobSize is ++ * smaller than the window size, you will start to ++ * see degraded compression ratio. ++ * NOTE: This only works when multithreading is ++ * enabled. ++ * NOTE: You probably don't want to use this with ++ * long range mode, since that will decrease the ++ * effectiveness of the synchronization points, ++ * but your milage may vary. ++ * NOTE: Rsyncable mode will limit the maximum ++ * compression speed to approximately 400 MB/s. ++ * If your compression level is already running ++ * significantly slower than that (< 200 MB/s), ++ * the speed won't be significantly impacted. ++ */ +} ZSTD_cParameter; -/*! ZSTD_createCDict_byReference() : - * Create a digested dictionary for compression - * Dictionary content is simply referenced, and therefore stays in dictBuffer. - * It is important that dictBuffer outlives CDict, it must remain read accessible throughout the lifetime of CDict */ -ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_byReference(const void* dictBuffer, size_t dictSize, int compressionLevel); -/*! ZSTD_getCParams() : -* @return ZSTD_compressionParameters structure for a selected compression level and estimated srcSize. -* `estimatedSrcSize` value is optional, select 0 if not known */ -ZSTDLIB_API ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long long estimatedSrcSize, size_t dictSize); +/*! ZSTD_CCtx_setParameter() : + * Set one compression parameter, selected by enum ZSTD_cParameter. + * Setting a parameter is generally only possible during frame initialization (before starting compression). + * Exception : when using multi-threading mode (nbWorkers >= 1), + * the following parameters can be updated _during_ compression (within same frame): + * => compressionLevel, hashLog, chainLog, searchLog, minMatch, targetLength and strategy. + * new parameters will be active for next job only (after a flush()). + * Note : when original `value` type is not unsigned (like int, or enum), cast it to unsigned. + * @result : informational value (typically, value being effectively set, after clamping), + * or an error code (which can be tested with ZSTD_isError()). */ +ZSTDLIB_API size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, unsigned value); -/*! ZSTD_getParams() : -* same as ZSTD_getCParams(), but @return a full `ZSTD_parameters` object instead of sub-component `ZSTD_compressionParameters`. -* All fields of `ZSTD_frameParameters` are set to default : contentSize=1, checksum=0, noDictID=0 */ -ZSTDLIB_API ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long long estimatedSrcSize, size_t dictSize); +/*! ZSTD_CCtx_setPledgedSrcSize() : + * Total input data size to be compressed as a single frame. + * This value will be controlled at end of frame, and trigger an error if not respected. + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + * Note 1 : 0 means zero, empty. + * In order to mean "unknown content size", pass constant ZSTD_CONTENTSIZE_UNKNOWN. + * ZSTD_CONTENTSIZE_UNKNOWN is default value for any new compression job. + * Note 2 : If all data is provided and consumed in a single round, + * this value is automatically overriden by srcSize instead. */ +ZSTDLIB_API size_t ZSTD_CCtx_setPledgedSrcSize(ZSTD_CCtx* cctx, unsigned long long pledgedSrcSize); -/*! ZSTD_checkCParams() : -* Ensure param values remain within authorized range */ -ZSTDLIB_API size_t ZSTD_checkCParams(ZSTD_compressionParameters params); +/*! ZSTD_CCtx_loadDictionary() : + * Create an internal CDict from `dict` buffer. + * Decompression will have to use same dictionary. + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + * Special: Adding a NULL (or 0-size) dictionary invalidates previous dictionary, + * meaning "return to no-dictionary mode". + * Note 1 : Dictionary will be used for all future compression jobs. + * To return to "no-dictionary" situation, load a NULL dictionary + * Note 2 : Loading a dictionary involves building tables, which are dependent on compression parameters. + * For this reason, compression parameters cannot be changed anymore after loading a dictionary. + * It's also a CPU consuming operation, with non-negligible impact on latency. + * Note 3 :`dict` content will be copied internally. + * Use ZSTD_CCtx_loadDictionary_byReference() to reference dictionary content instead. + * In such a case, dictionary buffer must outlive its users. + * Note 4 : Use ZSTD_CCtx_loadDictionary_advanced() + * to precisely select how dictionary content must be interpreted. */ +ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, size_t dictSize); -/*! ZSTD_adjustCParams() : - * optimize params for a given `srcSize` and `dictSize`. - * both values are optional, select `0` if unknown. */ -ZSTDLIB_API ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize); +/*! ZSTD_CCtx_refCDict() : + * 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. + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + * Special : adding a NULL CDict means "return to no-dictionary mode". + * Note 1 : Currently, only one dictionary can be managed. + * Adding a new dictionary effectively "discards" any previous one. + * Note 2 : CDict is just referenced, its lifetime must outlive CCtx. */ +ZSTDLIB_API size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict); -/*! ZSTD_compress_advanced() : -* Same as ZSTD_compress_usingDict(), with fine-tune control over each compression parameter */ -ZSTDLIB_API 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_CCtx_refPrefix() : + * Reference a prefix (single-usage dictionary) for next compression job. + * Decompression will need same prefix to properly regenerate data. + * Compressing with a prefix is similar in outcome as performing a diff and compressing it, + * but performs much faster, especially during decompression (compression speed is tunable with compression level). + * Note that prefix is **only used once**. Tables are discarded at end of compression job (ZSTD_e_end). + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + * Special: Adding any prefix (including NULL) invalidates any previous prefix or dictionary + * Note 1 : Prefix buffer is referenced. It **must** outlive compression job. + * Its content must remain unmodified during compression. + * Note 2 : If the intention is to diff some large src data blob with some prior version of itself, + * ensure that the window size is large enough to contain the entire source. + * See ZSTD_p_windowLog. + * Note 3 : Referencing a prefix involves building tables, which are dependent on compression parameters. + * It's a CPU consuming operation, with non-negligible impact on latency. + * If there is a need to use the same prefix multiple times, consider loadDictionary instead. + * Note 4 : By default, the prefix is interpreted as raw content (ZSTD_dm_rawContent). + * Use ZSTD_CCtx_refPrefix_advanced() to alter dictionary interpretation. */ +ZSTDLIB_API size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, + const void* prefix, size_t prefixSize); -/*! ZSTD_compress_usingCDict_advanced() : -* Same as ZSTD_compress_usingCDict(), with fine-tune control over frame parameters */ -ZSTDLIB_API 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); +typedef enum { + ZSTD_CCtx_reset_session_only = 1, + ZSTD_CCtx_reset_parameters = 2, + ZSTD_CCtx_reset_session_and_parameters = 3 +} ZSTD_CCtx_reset_directive; -/*--- Advanced decompression functions ---*/ +/*! ZSTD_CCtx_reset() : + * There are 2 different things that can be reset, independently or jointly : + * - The session : will stop compressing current frame, and make CCtx ready to start a new one. + * Useful after an error, or to interrupt any ongoing compression. + * Any internal data not yet flushed is cancelled. + * But parameters and dictionary are kept unchanged. + * Therefore, same parameters and dictionary will be used for next frame. + * This action never fails. + * - The parameters : changes all parameters back to "default". + * This removes any reference to any dictionary too. + * Parameters can only be changed between 2 sessions (i.e. no compression is currently ongoing) + * otherwise the reset fails, and function returns an error value (which can be tested using ZSTD_isError()) + * - Both : similar to resetting the session, followed by resetting parameters. + */ +ZSTDLIB_API size_t ZSTD_CCtx_reset(ZSTD_CCtx* cctx, ZSTD_CCtx_reset_directive zcrd); -/*! ZSTD_isFrame() : - * Tells if the content of `buffer` starts with a valid Frame Identifier. - * Note : Frame Identifier is 4 bytes. If `size < 4`, @return will always be 0. - * Note 2 : Legacy Frame Identifiers are considered valid only if Legacy Support is enabled. - * Note 3 : Skippable Frame Identifiers are considered valid. */ -ZSTDLIB_API unsigned ZSTD_isFrame(const void* buffer, size_t size); -/*! ZSTD_createDDict_byReference() : - * Create a digested dictionary, ready to start decompression operation without startup delay. - * Dictionary content is referenced, and therefore stays in dictBuffer. - * It is important that dictBuffer outlives DDict, - * it must remain read accessible throughout the lifetime of DDict */ -ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, size_t dictSize); +typedef enum { + ZSTD_e_continue=0, /* collect more data, encoder decides when to output compressed result, for optimal compression ratio */ + ZSTD_e_flush=1, /* flush any data provided so far, + * it creates (at least) one new block, that can be decoded immediately on reception; + * frame will continue: any future data can still reference previously compressed data, improving compression. */ + ZSTD_e_end=2 /* flush any remaining data and close current frame. + * any additional data starts a new frame. + * each frame is independent (does not reference any content from previous frame). */ +} ZSTD_EndDirective; -/*! ZSTD_getDictID_fromDict() : - * Provides the dictID stored within dictionary. - * if @return == 0, the dictionary is not conformant with Zstandard specification. - * It can still be loaded, but as a content-only dictionary. */ -ZSTDLIB_API unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize); +/*! ZSTD_compress_generic() : + * Behave about the same as ZSTD_compressStream. To note : + * - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_set*() + * - Compression parameters cannot be changed once compression is started (save a list of exceptions in multi-threading mode) + * - outpot->pos must be <= dstCapacity, input->pos must be <= srcSize + * - outpot->pos and input->pos will be updated. They are guaranteed to remain below their respective limit. + * - In single-thread mode (default), function is blocking : it completes its job before returning to caller. + * - In multi-thread mode, function is non-blocking : it just acquires a copy of input, and distribute job to internal worker threads, + * and then immediately returns, just indicating that there is some data remaining to be flushed. + * The function nonetheless guarantees forward progress : it will return only after it reads or write at least 1+ byte. + * - Exception : in multi-threading mode, if the first call requests a ZSTD_e_end directive, it is blocking : it will complete compression before giving back control to caller. + * - @return provides a minimum amount of data remaining to be flushed from internal buffers + * or an error code, which can be tested using ZSTD_isError(). + * if @return != 0, flush is not fully completed, there is still some data left within internal buffers. + * This is useful for ZSTD_e_flush, since in this case more flushes are necessary to empty all buffers. + * For ZSTD_e_end, @return == 0 when internal buffers are fully flushed and frame is completed. + * - after a ZSTD_e_end directive, if internal buffer is not fully flushed (@return != 0), + * only ZSTD_e_end or ZSTD_e_flush operations are allowed. + * Before starting a new compression job, or changing compression parameters, + * it is required to fully flush internal buffers. + */ +ZSTDLIB_API size_t ZSTD_compress_generic (ZSTD_CCtx* cctx, + ZSTD_outBuffer* output, + ZSTD_inBuffer* input, + ZSTD_EndDirective endOp); -/*! ZSTD_getDictID_fromDDict() : - * Provides the dictID of the dictionary loaded into `ddict`. - * If @return == 0, the dictionary is not conformant to Zstandard specification, or empty. - * Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */ -ZSTDLIB_API unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict); -/*! ZSTD_getDictID_fromFrame() : - * Provides the dictID required to decompressed the frame stored within `src`. - * If @return == 0, the dictID could not be decoded. - * This could for one of the following reasons : - * - The frame does not require a dictionary to be decoded (most common case). - * - The frame was built with dictID intentionally removed. Whatever dictionary is necessary is a hidden information. - * Note : this use case also happens when using a non-conformant dictionary. - * - `srcSize` is too small, and as a result, the frame header could not be decoded (only possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`). - * - This is not a Zstandard frame. - * When identifying the exact failure cause, it's possible to use ZSTD_getFrameHeader(), which will provide a more precise error code. */ -ZSTDLIB_API unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize); +/*! ZSTD_compress_generic_simpleArgs() : + * Same as ZSTD_compress_generic(), + * but using only integral types as arguments. + * This variant might be helpful for binders from dynamic languages + * which have troubles handling structures containing memory pointers. + */ +ZSTDLIB_API size_t ZSTD_compress_generic_simpleArgs ( + ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, size_t* dstPos, + const void* src, size_t srcSize, size_t* srcPos, + ZSTD_EndDirective endOp); -/******************************************************************** -* Advanced streaming functions -********************************************************************/ -/*===== Advanced Streaming compression functions =====*/ -ZSTDLIB_API size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize); /**< 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. */ -ZSTDLIB_API size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel); /**< creates of an internal CDict (incompatible with static CCtx), except if dict == NULL or dictSize < 8, in which case no dict is used. Note: dict is loaded with ZSTD_dm_auto (treated as a full zstd dictionary if it begins with ZSTD_MAGIC_DICTIONARY, else as raw content) and ZSTD_dlm_byCopy.*/ -ZSTDLIB_API size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, const void* dict, size_t dictSize, - ZSTD_parameters params, unsigned long long pledgedSrcSize); /**< pledgedSrcSize must be correct. If srcSize is not known at init time, use value ZSTD_CONTENTSIZE_UNKNOWN. dict is loaded with ZSTD_dm_auto and ZSTD_dlm_byCopy. */ -ZSTDLIB_API size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict); /**< note : cdict will just be referenced, and must outlive compression session */ -ZSTDLIB_API size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict* cdict, ZSTD_frameParameters fParams, unsigned long long pledgedSrcSize); /**< 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. */ +/* ============================== */ +/* Advanced decompression API */ +/* ============================== */ -/*! ZSTD_resetCStream() : - * start a new compression job, using same parameters from previous job. - * This is typically useful to skip dictionary loading stage, since it will re-use it in-place. - * Note that zcs must be init at least once before using ZSTD_resetCStream(). - * If pledgedSrcSize is not known at reset time, use macro ZSTD_CONTENTSIZE_UNKNOWN. - * If pledgedSrcSize > 0, its value must be correct, as it will be written in header, and controlled at the end. - * 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()) +/* The following API works the same way as the advanced compression API : + * a context is created, parameters are pushed into it one by one, + * then the context can be used to decompress data + * using ZSTD_decompress_generic(), similar to the streaming API. + * Note that sticky parameters only apply to ZSTD_decompress_generic() and ZSTD_decompress_generic_simpleArgs(). + * They are not valid if a "simple" function is used on the context (like `ZSTD_decompressDCtx()`). */ -ZSTDLIB_API size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize); + /*! ZSTD_DCtx_setMaxWindowSize() : + * Refuses allocating internal buffers for frames requiring a window size larger than provided limit. + * This protects a decoder context from reserving too much memory for itself (potential attack scenario). + * This parameter is only useful in streaming mode, since no internal buffer is allocated in single-pass mode. + * By default, a decompression context accepts all window sizes <= (1 << ZSTD_WINDOWLOG_LIMIT_DEFAULT) + * @return : 0, or an error code (which can be tested using ZSTD_isError()). + */ + ZSTDLIB_API size_t ZSTD_DCtx_setMaxWindowSize(ZSTD_DCtx* dctx, size_t maxWindowSize); -typedef struct { - unsigned long long ingested; /* nb input bytes read and buffered */ - unsigned long long consumed; /* nb input bytes actually compressed */ - unsigned long long produced; /* nb of compressed bytes generated and buffered */ - unsigned long long flushed; /* nb of compressed bytes flushed : not provided; can be tracked from caller side */ - unsigned currentJobID; /* MT only : latest started job nb */ - unsigned nbActiveWorkers; /* MT only : nb of workers actively compressing at probe time */ -} ZSTD_frameProgression; - -/* ZSTD_getFrameProgression() : - * tells how much data has been ingested (read from input) - * consumed (input actually compressed) and produced (output) for current frame. - * Note : (ingested - consumed) is amount of input data buffered internally, not yet compressed. - * Aggregates progression inside active worker threads. +/*! ZSTD_DCtx_loadDictionary() : + * Create an internal DDict from dict buffer, + * to be used to decompress next frames. + * The dictionary remains valid for all future frames, until explicitly invalidated. + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + * Special : Adding a NULL (or 0-size) dictionary invalidates any previous dictionary, + * meaning "return to no-dictionary mode". + * Note 1 : Loading a dictionary involves building tables, + * which has a non-negligible impact on CPU usage and latency. + * It's recommended to "load once, use many times", to amortize the cost + * Note 2 :`dict` content will be copied internally, so `dict` can be released after loading. + * Use ZSTD_DCtx_loadDictionary_byReference() to reference dictionary content instead. + * Note 3 : Use ZSTD_DCtx_loadDictionary_advanced() to take control of + * how dictionary content is loaded and interpreted. */ -ZSTDLIB_API ZSTD_frameProgression ZSTD_getFrameProgression(const ZSTD_CCtx* cctx); +ZSTDLIB_API size_t ZSTD_DCtx_loadDictionary(ZSTD_DCtx* dctx, const void* dict, size_t dictSize); -/*! ZSTD_toFlushNow() : - * Tell how many bytes are ready to be flushed immediately. - * Useful for multithreading scenarios (nbWorkers >= 1). - * Probe the oldest active job, defined as oldest job not yet entirely flushed, - * and check its output buffer. - * @return : amount of data stored in oldest job and ready to be flushed immediately. - * if @return == 0, it means either : - * + there is no active job (could be checked with ZSTD_frameProgression()), or - * + oldest job is still actively compressing data, - * but everything it has produced has also been flushed so far, - * therefore flushing speed is currently limited by production speed of oldest job - * irrespective of the speed of concurrent newer jobs. +/*! ZSTD_DCtx_refDDict() : + * Reference a prepared dictionary, to be used to decompress next frames. + * The dictionary remains active for decompression of future frames using same DCtx. + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + * Note 1 : Currently, only one dictionary can be managed. + * Referencing a new dictionary effectively "discards" any previous one. + * Special : adding a NULL DDict means "return to no-dictionary mode". + * Note 2 : DDict is just referenced, its lifetime must outlive its usage from DCtx. */ -ZSTDLIB_API size_t ZSTD_toFlushNow(ZSTD_CCtx* cctx); - - - -/*===== Advanced Streaming decompression functions =====*/ -typedef enum { DStream_p_maxWindowSize } ZSTD_DStreamParameter_e; -ZSTDLIB_API size_t ZSTD_setDStreamParameter(ZSTD_DStream* zds, ZSTD_DStreamParameter_e paramType, unsigned paramValue); /* obsolete : this API will be removed in a future version */ -ZSTDLIB_API size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize); /**< note: no dictionary will be used if dict == NULL or dictSize < 8 */ -ZSTDLIB_API size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* zds, const ZSTD_DDict* ddict); /**< note : ddict is referenced, it must outlive decompression session */ -ZSTDLIB_API size_t ZSTD_resetDStream(ZSTD_DStream* zds); /**< re-use decompression parameters from previous init; saves dictionary loading */ - - -/********************************************************************* -* Buffer-less and synchronous inner streaming functions -* -* This is an advanced API, giving full control over buffer management, for users which need direct control over memory. -* But it's also a complex one, with several restrictions, documented below. -* Prefer normal streaming API for an easier experience. -********************************************************************* */ - -/** - Buffer-less streaming compression (synchronous mode) - - A ZSTD_CCtx object is required to track streaming operations. - Use ZSTD_createCCtx() / ZSTD_freeCCtx() to manage resource. - 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. - It's also possible to duplicate a reference context which has already been initialized, using ZSTD_copyCCtx() - - Then, consume your input using ZSTD_compressContinue(). - There are some important considerations to keep in mind when using this advanced function : - - ZSTD_compressContinue() has no internal buffer. It uses externally provided buffers only. - - Interface is synchronous : input is consumed entirely and produces 1+ compressed blocks. - - Caller must ensure there is enough space in `dst` to store compressed data under worst case scenario. - Worst case evaluation is provided by ZSTD_compressBound(). - ZSTD_compressContinue() doesn't guarantee recover after a failed compression. - - ZSTD_compressContinue() presumes prior input ***is still accessible and unmodified*** (up to maximum distance size, see WindowLog). - It remembers all previous contiguous blocks, plus one separated memory segment (which can itself consists of multiple contiguous blocks) - - ZSTD_compressContinue() detects that prior input has been overwritten when `src` buffer overlaps. - In which case, it will "discard" the relevant memory section from its history. - - Finish a frame with ZSTD_compressEnd(), which will write the last block(s) and optional checksum. - It's possible to use srcSize==0, in which case, it will write a final empty block to end the frame. - Without last block mark, frames are considered unfinished (hence corrupted) by compliant decoders. - - `ZSTD_CCtx` object can be re-used (ZSTD_compressBegin()) to compress again. -*/ - -/*===== 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_DCtx_refDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict); -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); +/*! ZSTD_DCtx_refPrefix() : + * Reference a prefix (single-usage dictionary) for next compression job. + * This is the reverse operation of ZSTD_CCtx_refPrefix(), + * and must use the same prefix as the one used during compression. + * Prefix is **only used once**. Reference is discarded at end of frame. + * End of frame is reached when ZSTD_DCtx_decompress_generic() returns 0. + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + * Note 1 : Adding any prefix (including NULL) invalidates any previously set prefix or dictionary + * Note 2 : Prefix buffer is referenced. It **must** outlive decompression job. + * Prefix buffer must remain unmodified up to the end of frame, + * reached when ZSTD_DCtx_decompress_generic() returns 0. + * Note 3 : By default, the prefix is treated as raw content (ZSTD_dm_rawContent). + * Use ZSTD_CCtx_refPrefix_advanced() to alter dictMode. + * Note 4 : Referencing a raw content prefix has almost no cpu nor memory cost. + * A fulldict prefix requires building tables, hence is more costly. + */ +ZSTDLIB_API size_t ZSTD_DCtx_refPrefix(ZSTD_DCtx* dctx, + const void* prefix, size_t prefixSize); +/*! ZSTD_DCtx_reset() : + * Return a DCtx to clean state. + * If a decompression was ongoing, any internal data not yet flushed is cancelled. + * All parameters are back to default values, including sticky ones. + * Dictionary (if any) is dropped. + * Parameters can be modified again after a reset. + */ +ZSTDLIB_API void ZSTD_DCtx_reset(ZSTD_DCtx* dctx); /* <==== There is a discrepancy with ZSTD_CCtx_reset(): here it necessarily resets everything (context and parameters) */ -/*- - Buffer-less streaming decompression (synchronous mode) - A ZSTD_DCtx object is required to track streaming operations. - Use ZSTD_createDCtx() / ZSTD_freeDCtx() to manage it. - A ZSTD_DCtx object can be re-used multiple times. +/*! ZSTD_decompress_generic() : + * Behave the same as ZSTD_decompressStream. + * Decompression parameters cannot be changed once decompression is started. + * @return : an error code, which can be tested using ZSTD_isError() + * if >0, a hint, nb of expected input bytes for next invocation. + * `0` means : a frame has just been fully decoded and flushed. + */ +ZSTDLIB_API size_t ZSTD_decompress_generic(ZSTD_DCtx* dctx, + ZSTD_outBuffer* output, + ZSTD_inBuffer* input); - First typical operation is to retrieve frame parameters, using ZSTD_getFrameHeader(). - Frame header is extracted from the beginning of compressed frame, so providing only the frame's beginning is enough. - Data fragment must be large enough to ensure successful decoding. - `ZSTD_frameHeaderSize_max` bytes is guaranteed to always be large enough. - @result : 0 : successful decoding, the `ZSTD_frameHeader` structure is correctly filled. - >0 : `srcSize` is too small, please provide at least @result bytes on next attempt. - errorCode, which can be tested using ZSTD_isError(). - It fills a ZSTD_frameHeader structure with important information to correctly decode the frame, - such as the dictionary ID, content size, or maximum back-reference distance (`windowSize`). - Note that these values could be wrong, either because of data corruption, or because a 3rd party deliberately spoofs false information. - As a consequence, check that values remain within valid application range. - For example, do not allocate memory blindly, check that `windowSize` is within expectation. - Each application can set its own limits, depending on local restrictions. - For extended interoperability, it is recommended to support `windowSize` of at least 8 MB. +/*! ZSTD_decompress_generic_simpleArgs() : + * Same as ZSTD_decompress_generic(), + * but using only integral types as arguments. + * This can be helpful for binders from dynamic languages + * which have troubles handling structures containing memory pointers. + */ +ZSTDLIB_API size_t ZSTD_decompress_generic_simpleArgs ( + ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, size_t* dstPos, + const void* src, size_t srcSize, size_t* srcPos); - ZSTD_decompressContinue() needs previous data blocks during decompression, up to `windowSize` bytes. - ZSTD_decompressContinue() is very sensitive to contiguity, - if 2 blocks don't follow each other, make sure that either the compressor breaks contiguity at the same place, - or that previous contiguous segment is large enough to properly handle maximum back-reference distance. - There are multiple ways to guarantee this condition. - The most memory efficient way is to use a round buffer of sufficient size. - Sufficient size is determined by invoking ZSTD_decodingBufferSize_min(), - which can @return an error code if required value is too large for current system (in 32-bits mode). - In a round buffer methodology, ZSTD_decompressContinue() decompresses each block next to previous one, - up to the moment there is not enough room left in the buffer to guarantee decoding another full block, - which maximum size is provided in `ZSTD_frameHeader` structure, field `blockSizeMax`. - At which point, decoding can resume from the beginning of the buffer. - Note that already decoded data stored in the buffer should be flushed before being overwritten. - There are alternatives possible, for example using two or more buffers of size `windowSize` each, though they consume more memory. - Finally, if you control the compression process, you can also ignore all buffer size rules, - as long as the encoder and decoder progress in "lock-step", - aka use exactly the same buffer sizes, break contiguity at the same place, etc. - Once buffers are setup, start decompression, with ZSTD_decompressBegin(). - If decompression requires a dictionary, use ZSTD_decompressBegin_usingDict() or ZSTD_decompressBegin_usingDDict(). - Then use ZSTD_nextSrcSizeToDecompress() and ZSTD_decompressContinue() alternatively. - ZSTD_nextSrcSizeToDecompress() tells how many bytes to provide as 'srcSize' to ZSTD_decompressContinue(). - ZSTD_decompressContinue() requires this _exact_ amount of bytes, or it will fail. +/**************************************************************************************** + * experimental API (static linking only) + **************************************************************************************** + * The following symbols and constants + * are not planned to join "stable API" status anytime soon. + * Some of them will never reach "stable", and are planned to remain in the static_only section indefinitely. + * Some of them might even be removed in the future. + * ***************************************************************************************/ - @result of ZSTD_decompressContinue() is the number of bytes regenerated within 'dst' (necessarily <= dstCapacity). - It can be zero : it just means ZSTD_decompressContinue() has decoded some metadata item. - It can also be an error code, which can be tested with ZSTD_isError(). +#define ZSTD_HASHLOG3_MAX 17 - A frame is fully decoded when ZSTD_nextSrcSizeToDecompress() returns zero. - Context can then be reset to start a new decompression. +#define ZSTD_FRAMEHEADERSIZE_PREFIX 5 /* minimum input size required to query frame header size */ +#define ZSTD_FRAMEHEADERSIZE_MIN 6 +#define ZSTD_FRAMEHEADERSIZE_MAX 18 /* can be useful for static allocation */ +#define ZSTD_SKIPPABLEHEADERSIZE 8 - Note : it's possible to know if next input to present is a header or a block, using ZSTD_nextInputType(). - This information is not required to properly decode a frame. - == Special case : skippable frames == +/* --- Advanced types --- */ - Skippable frames allow integration of user-defined data into a flow of concatenated frames. - Skippable frames will be ignored (skipped) by decompressor. - The format of skippable frames is as follows : - a) Skippable frame ID - 4 Bytes, Little endian format, any value from 0x184D2A50 to 0x184D2A5F - b) Frame Size - 4 Bytes, Little endian format, unsigned 32-bits - c) Frame Content - any content (User Data) of length equal to Frame Size - For skippable frames ZSTD_getFrameHeader() returns zfhPtr->frameType==ZSTD_skippableFrame. - For skippable frames ZSTD_decompressContinue() always returns 0 : it only skips the content. -*/ +typedef struct ZSTD_CCtx_params_s ZSTD_CCtx_params; -/*===== Buffer-less streaming decompression functions =====*/ -typedef enum { ZSTD_frame, ZSTD_skippableFrame } ZSTD_frameType_e; typedef struct { - unsigned long long frameContentSize; /* if == ZSTD_CONTENTSIZE_UNKNOWN, it means this field is not available. 0 means "empty" */ - unsigned long long windowSize; /* can be very large, up to <= frameContentSize */ - unsigned blockSizeMax; - ZSTD_frameType_e frameType; /* if == ZSTD_skippableFrame, frameContentSize is the size of skippable content */ - unsigned headerSize; - unsigned dictID; - unsigned checksumFlag; -} ZSTD_frameHeader; -/** ZSTD_getFrameHeader() : - * decode Frame Header, or requires larger `srcSize`. - * @return : 0, `zfhPtr` is correctly filled, - * >0, `srcSize` is too small, value is wanted `srcSize` amount, - * or an error code, which can be tested using ZSTD_isError() */ -ZSTDLIB_API size_t ZSTD_getFrameHeader(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize); /**< doesn't consume input */ -ZSTDLIB_API size_t ZSTD_decodingBufferSize_min(unsigned long long windowSize, unsigned long long frameContentSize); /**< when frame content size is not known, pass in frameContentSize == ZSTD_CONTENTSIZE_UNKNOWN */ - -ZSTDLIB_API size_t ZSTD_decompressBegin(ZSTD_DCtx* dctx); -ZSTDLIB_API size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx* dctx, const void* dict, size_t dictSize); -ZSTDLIB_API size_t ZSTD_decompressBegin_usingDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict); - -ZSTDLIB_API size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx* dctx); -ZSTDLIB_API size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); - -/* misc */ -ZSTDLIB_API void ZSTD_copyDCtx(ZSTD_DCtx* dctx, const ZSTD_DCtx* preparedDCtx); -typedef enum { ZSTDnit_frameHeader, ZSTDnit_blockHeader, ZSTDnit_block, ZSTDnit_lastBlock, ZSTDnit_checksum, ZSTDnit_skippableFrame } ZSTD_nextInputType_e; -ZSTDLIB_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx); - + unsigned windowLog; /**< largest match distance : larger == more compression, more memory needed during decompression */ + unsigned chainLog; /**< fully searched segment : larger == more compression, slower, more memory (useless for fast) */ + unsigned hashLog; /**< dispatch table : larger == faster, more memory */ + unsigned searchLog; /**< nb of searches : larger == more compression, slower */ + unsigned searchLength; /**< match length searched : larger == faster decompression, sometimes less compression */ + unsigned targetLength; /**< acceptable match size for optimal parser (only) : larger == more compression, slower */ + ZSTD_strategy strategy; /**< see ZSTD_strategy definition above */ +} ZSTD_compressionParameters; +typedef struct { + unsigned contentSizeFlag; /**< 1: content size will be in frame header (when known) */ + unsigned checksumFlag; /**< 1: generate a 32-bits checksum using XXH64 algorithm at end of frame, for error detection */ + unsigned noDictIDFlag; /**< 1: no dictID will be saved into frame header (dictID is only useful for dictionary compression) */ +} ZSTD_frameParameters; -/* ============================================ */ -/** New advanced API (experimental) */ -/* ============================================ */ +typedef struct { + ZSTD_compressionParameters cParams; + ZSTD_frameParameters fParams; +} ZSTD_parameters; -/* API design : - * In this advanced API, parameters are pushed one by one into an existing context, - * using ZSTD_CCtx_set*() functions. - * Pushed parameters are sticky : they are applied to next job, and any subsequent job. - * It's possible to reset parameters to "default" using ZSTD_CCtx_reset(). - * Important : "sticky" parameters only work with `ZSTD_compress_generic()` ! - * For any other entry point, "sticky" parameters are ignored ! - * - * This API is intended to replace all others advanced / experimental API entry points. - */ +typedef enum { + ZSTD_dct_auto = 0, /* dictionary is "full" when starting with ZSTD_MAGIC_DICTIONARY, otherwise it is "rawContent" */ + ZSTD_dct_rawContent = 1, /* ensures dictionary is always loaded as rawContent, even if it starts with ZSTD_MAGIC_DICTIONARY */ + ZSTD_dct_fullDict = 2 /* refuses to load a dictionary if it does not respect Zstandard's specification, starting with ZSTD_MAGIC_DICTIONARY */ +} ZSTD_dictContentType_e; -/* note on enum design : - * All enum will be pinned to explicit values before reaching "stable API" status */ +typedef enum { + ZSTD_dlm_byCopy = 0, /**< Copy dictionary content internally */ + ZSTD_dlm_byRef = 1, /**< Reference dictionary content -- the dictionary buffer must outlive its users. */ +} ZSTD_dictLoadMethod_e; typedef enum { /* Opened question : should we have a format ZSTD_f_auto ?