diff options
Diffstat (limited to 'contrib')
-rw-r--r-- | contrib/zstd/pool.h | 5 | ||||
-rw-r--r-- | contrib/zstd/zstd.h | 2243 | ||||
-rw-r--r-- | contrib/zstd/zstd_compress_superblock.h | 2 | ||||
-rw-r--r-- | contrib/zstd/zstd_ddict.h | 2 | ||||
-rw-r--r-- | contrib/zstd/zstd_internal.h | 2 | ||||
-rw-r--r-- | contrib/zstd/zstd_ldm.h | 2 |
6 files changed, 1552 insertions, 704 deletions
diff --git a/contrib/zstd/pool.h b/contrib/zstd/pool.h index 259bafc97..7dcaf010d 100644 --- a/contrib/zstd/pool.h +++ b/contrib/zstd/pool.h @@ -17,8 +17,11 @@ extern "C" { #include <stddef.h> /* size_t */ + +#ifndef ZSTD_STATIC_LINKING_ONLY #define ZSTD_STATIC_LINKING_ONLY /* ZSTD_customMem */ -#include "../zstd.h" +#endif +#include "zstd.h" typedef struct POOL_ctx_s POOL_ctx; diff --git a/contrib/zstd/zstd.h b/contrib/zstd/zstd.h index 158d75afb..8c6fc6ae9 100644 --- a/contrib/zstd/zstd.h +++ b/contrib/zstd/zstd.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. + * Copyright (c) 2016-2020, Yann Collet, Facebook, Inc. * All rights reserved. * * This source code is licensed under both the BSD-style license (found in the @@ -15,6 +15,7 @@ extern "C" { #define ZSTD_H_235446 /* ====== Dependency ======*/ +#include <limits.h> /* INT_MAX */ #include <stddef.h> /* size_t */ @@ -35,40 +36,73 @@ extern "C" { #endif -/******************************************************************************************************* +/******************************************************************************* Introduction - zstd, short for Zstandard, is a fast lossless compression algorithm, - targeting real-time compression scenarios at zlib-level and better compression ratios. - The zstd compression library provides in-memory compression and decompression functions. - The library supports compression levels from 1 up to ZSTD_maxCLevel() which is currently 22. - Levels >= 20, labeled `--ultra`, should be used with caution, as they require more memory. + zstd, short for Zstandard, is a fast lossless compression algorithm, targeting + real-time compression scenarios at zlib-level and better compression ratios. + The zstd compression library provides in-memory compression and decompression + functions. + + The library supports regular compression levels from 1 up to ZSTD_maxCLevel(), + which is currently 22. Levels >= 20, labeled `--ultra`, should be used with + caution, as they require more memory. The library also offers negative + compression levels, which extend the range of speed vs. ratio preferences. + The lower the level, the faster the speed (at the cost of compression). + Compression can be done in: - a single step (described as Simple API) - - a single step, reusing a context (described as Explicit memory management) + - a single step, reusing a context (described as Explicit context) - unbounded multiple steps (described as Streaming compression) - The compression ratio achievable on small data can be highly improved using a dictionary in: + + The compression ratio achievable on small data can be highly improved using + a dictionary. Dictionary compression can be performed in: - a single step (described as Simple dictionary API) - - a single step, reusing a dictionary (described as Fast dictionary API) + - a single step, reusing a dictionary (described as Bulk-processing + dictionary API) - Advanced experimental functions can be accessed using #define ZSTD_STATIC_LINKING_ONLY before including zstd.h. - Advanced experimental APIs shall never be used with a dynamic library. - They are not "stable", their definition may change in the future. Only static linking is allowed. -*********************************************************************************************************/ + Advanced experimental functions can be accessed using + `#define ZSTD_STATIC_LINKING_ONLY` before including zstd.h. + + Advanced experimental APIs should never be used with a dynamically-linked + library. They are not "stable"; their definitions or signatures may change in + the future. Only static linking is allowed. +*******************************************************************************/ /*------ Version ------*/ #define ZSTD_VERSION_MAJOR 1 -#define ZSTD_VERSION_MINOR 3 -#define ZSTD_VERSION_RELEASE 1 +#define ZSTD_VERSION_MINOR 4 +#define ZSTD_VERSION_RELEASE 5 #define ZSTD_VERSION_NUMBER (ZSTD_VERSION_MAJOR *100*100 + ZSTD_VERSION_MINOR *100 + ZSTD_VERSION_RELEASE) -ZSTDLIB_API unsigned ZSTD_versionNumber(void); /**< useful to check dll version */ +ZSTDLIB_API unsigned ZSTD_versionNumber(void); /**< to check runtime library version */ #define ZSTD_LIB_VERSION ZSTD_VERSION_MAJOR.ZSTD_VERSION_MINOR.ZSTD_VERSION_RELEASE #define ZSTD_QUOTE(str) #str #define ZSTD_EXPAND_AND_QUOTE(str) ZSTD_QUOTE(str) #define ZSTD_VERSION_STRING ZSTD_EXPAND_AND_QUOTE(ZSTD_LIB_VERSION) -ZSTDLIB_API const char* ZSTD_versionString(void); /* v1.3.0 */ +ZSTDLIB_API const char* ZSTD_versionString(void); /* requires v1.3.0+ */ + +/* ************************************* + * Default constant + ***************************************/ +#ifndef ZSTD_CLEVEL_DEFAULT +# define ZSTD_CLEVEL_DEFAULT 3 +#endif + +/* ************************************* + * Constants + ***************************************/ + +/* All magic numbers are supposed read/written to/from files/memory using little-endian convention */ +#define ZSTD_MAGICNUMBER 0xFD2FB528 /* valid since v0.8.0 */ +#define ZSTD_MAGIC_DICTIONARY 0xEC30A437 /* valid since v0.7.0 */ +#define ZSTD_MAGIC_SKIPPABLE_START 0x184D2A50 /* all 16 values, from 0x184D2A50 to 0x184D2A5F, signal the beginning of a skippable frame */ +#define ZSTD_MAGIC_SKIPPABLE_MASK 0xFFFFFFF0 + +#define ZSTD_BLOCKSIZELOG_MAX 17 +#define ZSTD_BLOCKSIZE_MAX (1<<ZSTD_BLOCKSIZELOG_MAX) + /*************************************** @@ -92,11 +126,11 @@ ZSTDLIB_API size_t ZSTD_compress( void* dst, size_t dstCapacity, ZSTDLIB_API size_t ZSTD_decompress( void* dst, size_t dstCapacity, const void* src, size_t compressedSize); -/*! ZSTD_getFrameContentSize() : v1.3.0 +/*! ZSTD_getFrameContentSize() : requires v1.3.0+ * `src` should point to the start of a ZSTD encoded frame. * `srcSize` must be at least as large as the frame header. * hint : any size >= `ZSTD_frameHeaderSize_max` is large enough. - * @return : - decompressed size of the frame in `src`, if known + * @return : - decompressed size of `src` frame content, if known * - ZSTD_CONTENTSIZE_UNKNOWN if the size cannot be determined * - ZSTD_CONTENTSIZE_ERROR if an error occurred (e.g. invalid magic number, srcSize too small) * note 1 : a 0 return value means the frame is valid but "empty". @@ -106,7 +140,8 @@ ZSTDLIB_API size_t ZSTD_decompress( void* dst, size_t dstCapacity, * Optionally, application can rely on some implicit limit, * as ZSTD_decompress() only needs an upper bound of decompressed size. * (For example, data could be necessarily cut into blocks <= 16 KB). - * note 3 : decompressed size is always present when compression is done with ZSTD_compress() + * note 3 : decompressed size is always present when compression is completed using single-pass functions, + * such as ZSTD_compress(), ZSTD_compressCCtx() ZSTD_compress_usingDict() or ZSTD_compress_usingCDict(). * note 4 : decompressed size can be very large (64-bits value), * potentially larger than what local system can handle as a single memory segment. * In which case, it's necessary to use streaming mode to decompress data. @@ -120,38 +155,56 @@ ZSTDLIB_API unsigned long long ZSTD_getFrameContentSize(const void *src, size_t /*! ZSTD_getDecompressedSize() : * NOTE: This function is now obsolete, in favor of ZSTD_getFrameContentSize(). - * Both functions work the same way, - * but ZSTD_getDecompressedSize() blends - * "empty", "unknown" and "error" results in the same return value (0), - * while ZSTD_getFrameContentSize() distinguishes them. - * - * 'src' is the start of a zstd compressed frame. - * @return : content size to be decompressed, as a 64-bits value _if known and not empty_, 0 otherwise. */ + * Both functions work the same way, but ZSTD_getDecompressedSize() blends + * "empty", "unknown" and "error" results to the same return value (0), + * while ZSTD_getFrameContentSize() gives them separate return values. + * @return : decompressed size of `src` frame content _if known and not empty_, 0 otherwise. */ ZSTDLIB_API unsigned long long ZSTD_getDecompressedSize(const void* src, size_t srcSize); +/*! ZSTD_findFrameCompressedSize() : + * `src` should point to the start of a ZSTD frame or skippable frame. + * `srcSize` must be >= first frame size + * @return : the compressed size of the first frame starting at `src`, + * suitable to pass as `srcSize` to `ZSTD_decompress` or similar, + * or an error code if input is invalid */ +ZSTDLIB_API size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize); + /*====== Helper functions ======*/ -ZSTDLIB_API int ZSTD_maxCLevel(void); /*!< maximum compression level available */ -ZSTDLIB_API size_t ZSTD_compressBound(size_t srcSize); /*!< maximum compressed size in worst case scenario */ +#define ZSTD_COMPRESSBOUND(srcSize) ((srcSize) + ((srcSize)>>8) + (((srcSize) < (128<<10)) ? (((128<<10) - (srcSize)) >> 11) /* margin, from 64 to 0 */ : 0)) /* this formula ensures that bound(A) + bound(B) <= bound(A+B) as long as A and B >= 128 KB */ +ZSTDLIB_API size_t ZSTD_compressBound(size_t srcSize); /*!< maximum compressed size in worst case single-pass scenario */ ZSTDLIB_API unsigned ZSTD_isError(size_t code); /*!< tells if a `size_t` function result is an error code */ ZSTDLIB_API const char* ZSTD_getErrorName(size_t code); /*!< provides readable string from an error code */ +ZSTDLIB_API int ZSTD_minCLevel(void); /*!< minimum negative compression level allowed */ +ZSTDLIB_API int ZSTD_maxCLevel(void); /*!< maximum compression level available */ /*************************************** -* Explicit memory management +* Explicit context ***************************************/ /*= Compression context * When compressing many times, - * it is recommended to allocate a context just once, and re-use it for each successive compression operation. + * it is recommended to allocate a context just once, + * and re-use it for each successive compression operation. * This will make workload friendlier for system's memory. - * Use one context per thread for parallel execution in multi-threaded environments. */ + * Note : re-using context is just a speed / resource optimization. + * It doesn't change the compression ratio, which remains identical. + * Note 2 : In multi-threaded environments, + * use one different context per thread for parallel execution. + */ typedef struct ZSTD_CCtx_s ZSTD_CCtx; ZSTDLIB_API ZSTD_CCtx* ZSTD_createCCtx(void); ZSTDLIB_API size_t ZSTD_freeCCtx(ZSTD_CCtx* cctx); /*! ZSTD_compressCCtx() : - * Same as ZSTD_compress(), requires an allocated ZSTD_CCtx (see ZSTD_createCCtx()). */ -ZSTDLIB_API size_t ZSTD_compressCCtx(ZSTD_CCtx* ctx, + * Same as ZSTD_compress(), using an explicit ZSTD_CCtx. + * Important : in order to behave similarly to `ZSTD_compress()`, + * this function compresses at requested compression level, + * __ignoring any other parameter__ . + * If any advanced parameter was set using the advanced API, + * they will all be reset. Only `compressionLevel` remains. + */ +ZSTDLIB_API size_t ZSTD_compressCCtx(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize, int compressionLevel); @@ -167,82 +220,343 @@ ZSTDLIB_API ZSTD_DCtx* ZSTD_createDCtx(void); ZSTDLIB_API size_t ZSTD_freeDCtx(ZSTD_DCtx* dctx); /*! ZSTD_decompressDCtx() : - * Same as ZSTD_decompress(), requires an allocated ZSTD_DCtx (see ZSTD_createDCtx()) */ -ZSTDLIB_API size_t ZSTD_decompressDCtx(ZSTD_DCtx* ctx, + * Same as ZSTD_decompress(), + * requires an allocated ZSTD_DCtx. + * Compatible with sticky parameters. + */ +ZSTDLIB_API size_t ZSTD_decompressDCtx(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); -/************************** -* Simple dictionary API -***************************/ -/*! ZSTD_compress_usingDict() : - * Compression using a predefined Dictionary (see dictBuilder/zdict.h). - * Note : This function loads the dictionary, resulting in significant startup delay. - * Note : When `dict == NULL || dictSize < 8` no dictionary is used. */ -ZSTDLIB_API size_t ZSTD_compress_usingDict(ZSTD_CCtx* ctx, - void* dst, size_t dstCapacity, - const void* src, size_t srcSize, - const void* dict,size_t dictSize, - int compressionLevel); +/*************************************** +* Advanced compression API +***************************************/ -/*! ZSTD_decompress_usingDict() : - * Decompression using a predefined Dictionary (see dictBuilder/zdict.h). - * Dictionary must be identical to the one used during compression. - * Note : This function loads the dictionary, resulting in significant startup delay. - * Note : When `dict == NULL || dictSize < 8` no dictionary is used. */ -ZSTDLIB_API size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx, - void* dst, size_t dstCapacity, - const void* src, size_t srcSize, - const void* dict,size_t dictSize); +/* API design : + * Parameters are pushed one by one into an existing context, + * using ZSTD_CCtx_set*() functions. + * Pushed parameters are sticky : they are valid for next compressed frame, and any subsequent frame. + * "sticky" parameters are applicable to `ZSTD_compress2()` and `ZSTD_compressStream*()` ! + * __They do not apply to "simple" one-shot variants such as ZSTD_compressCCtx()__ . + * + * It's possible to reset all parameters to "default" using ZSTD_CCtx_reset(). + * + * This API 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. + */ -/********************************** - * Bulk processing dictionary API - *********************************/ -typedef struct ZSTD_CDict_s ZSTD_CDict; +/* 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, + ZSTD_btultra2=9 + /* note : new strategies _might_ be added in the future. + Only the order (from fast to strong) is guaranteed */ +} ZSTD_strategy; -/*! ZSTD_createCDict() : - * When compressing multiple messages / blocks with the same dictionary, it's recommended to load it just once. - * ZSTD_createCDict() will create a digested dictionary, ready to start future compression operations without startup delay. - * ZSTD_CDict can be created once and shared by multiple threads concurrently, since its usage is read-only. - * `dictBuffer` can be released after ZSTD_CDict creation, since its content is copied within CDict */ -ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict(const void* dictBuffer, size_t dictSize, - int compressionLevel); -/*! ZSTD_freeCDict() : - * Function frees memory allocated by ZSTD_createCDict(). */ -ZSTDLIB_API size_t ZSTD_freeCDict(ZSTD_CDict* CDict); +typedef enum { -/*! ZSTD_compress_usingCDict() : - * Compression using a digested Dictionary. - * Faster startup than ZSTD_compress_usingDict(), recommended when same dictionary is used multiple times. - * Note that compression level is decided during dictionary creation. - * Frame parameters are hardcoded (dictID=yes, contentSize=yes, checksum=no) */ -ZSTDLIB_API size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx, - void* dst, size_t dstCapacity, - const void* src, size_t srcSize, - const ZSTD_CDict* cdict); + /* compression parameters + * Note: When compressing with a ZSTD_CDict these parameters are superseded + * by the parameters used to construct the ZSTD_CDict. + * See ZSTD_CCtx_refCDict() for more info (superseded-by-cdict). */ + ZSTD_c_compressionLevel=100, /* Set compression parameters according to pre-defined cLevel table. + * Note that exact compression parameters are dynamically determined, + * depending on both compression level and srcSize (when known). + * 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. + * Note 2 : setting a level does not automatically set all other compression parameters + * to default. Setting this will however eventually dynamically impact the compression + * parameters which have not been manually set. The manually set + * ones will 'stick'. */ + /* Advanced compression parameters : + * It's possible to pin down compression parameters to some specific values. + * In which case, these values are no longer dynamically selected by the compressor */ + ZSTD_c_windowLog=101, /* Maximum allowed back-reference distance, expressed as power of 2. + * This will set a memory budget for streaming decompression, + * with larger values requiring more memory + * and typically compressing more. + * Must be clamped between ZSTD_WINDOWLOG_MIN and ZSTD_WINDOWLOG_MAX. + * Special: value 0 means "use default windowLog". + * Note: Using a windowLog greater than ZSTD_WINDOWLOG_LIMIT_DEFAULT + * requires explicitly allowing such size at streaming decompression stage. */ + ZSTD_c_hashLog=102, /* Size of the initial probe table, as a power of 2. + * Resulting memory usage is (1 << (hashLog+2)). + * Must be clamped between ZSTD_HASHLOG_MIN and ZSTD_HASHLOG_MAX. + * Larger tables improve compression ratio of strategies <= dFast, + * and improve speed of strategies > dFast. + * Special: value 0 means "use default hashLog". */ + ZSTD_c_chainLog=103, /* Size of the multi-probe search table, as a power of 2. + * Resulting memory usage 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 for "fast" strategy. + * 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_c_searchLog=104, /* Number of search attempts, as a power of 2. + * More attempts result in better and slower compression. + * This parameter is useless for "fast" and "dFast" strategies. + * Special: value 0 means "use default searchLog". */ + ZSTD_c_minMatch=105, /* Minimum size of searched matches. + * Note that Zstandard can still find matches of smaller size, + * it just tweaks its search algorithm to look for this size and larger. + * Larger values increase compression and decompression speed, but decrease ratio. + * Must be clamped between ZSTD_MINMATCH_MIN and ZSTD_MINMATCH_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_c_targetLength=106, /* Impact of this field depends on strategy. + * For strategies btopt, btultra & btultra2: + * 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_c_strategy=107, /* See ZSTD_strategy enum definition. + * 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". */ + + /* LDM mode parameters */ + ZSTD_c_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 default ZSTD_c_windowLog to 128 MB + * except when expressly set to a different value. */ + ZSTD_c_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_c_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_c_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_c_ldmHashRateLog=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 hashRateLog". */ + /* frame parameters */ + ZSTD_c_contentSizeFlag=200, /* Content size will be written into frame header _whenever known_ (default:1) + * Content size must be known at the beginning of compression. + * This is automatically the case when using ZSTD_compress2(), + * For streaming scenarios, content size must be provided with ZSTD_CCtx_setPledgedSrcSize() */ + ZSTD_c_checksumFlag=201, /* A 32-bits checksum of content is written at end of frame (default:0) */ + ZSTD_c_dictIDFlag=202, /* When applicable, dictionary's ID is written into frame header (default:1) */ -typedef struct ZSTD_DDict_s ZSTD_DDict; + /* 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_c_nbWorkers=400, /* Select how many threads will be spawned to compress in parallel. + * When nbWorkers >= 1, triggers asynchronous mode when used with ZSTD_compressStream*() : + * ZSTD_compressStream*() consumes input and flush output if possible, but 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 of ZSTD_compressStream2() sets ZSTD_e_end : + * in which case, ZSTD_compressStream2() delegates to ZSTD_compress2(), which is always 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_c_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 overlap size, or 1 MB, whichever is largest. + * The minimum size is automatically and transparently enforced. */ + ZSTD_c_overlapLog=402, /* Control the overlap size, as a fraction of window size. + * The overlap size is an amount of data reloaded from previous job at the beginning of a new job. + * It helps preserve compression ratio, while each job is compressed in parallel. + * This value is enforced only when nbWorkers >= 1. + * Larger values increase compression ratio, but decrease speed. + * Possible values range from 0 to 9 : + * - 0 means "default" : value will be determined by the library, depending on strategy + * - 1 means "no overlap" + * - 9 means "full overlap", using a full window size. + * Each intermediate rank increases/decreases load size by a factor 2 : + * 9: full window; 8: w/2; 7: w/4; 6: w/8; 5:w/16; 4: w/32; 3:w/64; 2:w/128; 1:no overlap; 0:default + * default value varies between 6 and 9, depending on strategy */ + + /* note : additional experimental parameters are also available + * within the experimental section of the API. + * At the time of this writing, they include : + * ZSTD_c_rsyncable + * ZSTD_c_format + * ZSTD_c_forceMaxWindow + * ZSTD_c_forceAttachDict + * ZSTD_c_literalCompressionMode + * ZSTD_c_targetCBlockSize + * ZSTD_c_srcSizeHint + * Because they are not stable, it's necessary to define ZSTD_STATIC_LINKING_ONLY to access them. + * note : never ever use experimentalParam? names directly; + * also, the enums values themselves are unstable and can still change. + */ + ZSTD_c_experimentalParam1=500, + ZSTD_c_experimentalParam2=10, + ZSTD_c_experimentalParam3=1000, + ZSTD_c_experimentalParam4=1001, + ZSTD_c_experimentalParam5=1002, + ZSTD_c_experimentalParam6=1003, + ZSTD_c_experimentalParam7=1004 +} ZSTD_cParameter; -/*! ZSTD_createDDict() : - * Create a digested dictionary, ready to start decompression operation without startup delay. - * dictBuffer can be released after DDict creation, as its content is copied inside DDict */ -ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict(const void* dictBuffer, size_t dictSize); +typedef struct { + size_t error; + int lowerBound; + int upperBound; +} ZSTD_bounds; + +/*! ZSTD_cParam_getBounds() : + * All parameters must belong to an interval with lower and upper bounds, + * otherwise they will either trigger an error or be automatically clamped. + * @return : a structure, ZSTD_bounds, which contains + * - an error status field, which must be tested using ZSTD_isError() + * - lower and upper bounds, both inclusive + */ +ZSTDLIB_API ZSTD_bounds ZSTD_cParam_getBounds(ZSTD_cParameter cParam); -/*! ZSTD_freeDDict() : - * Function frees memory allocated with ZSTD_createDDict() */ -ZSTDLIB_API size_t ZSTD_freeDDict(ZSTD_DDict* ddict); +/*! ZSTD_CCtx_setParameter() : + * Set one compression parameter, selected by enum ZSTD_cParameter. + * All parameters have valid bounds. Bounds can be queried using ZSTD_cParam_getBounds(). + * Providing a value beyond bound will either clamp it, or trigger an error (depending on parameter). + * 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()). + * @return : an error code (which can be tested using ZSTD_isError()). + */ +ZSTDLIB_API size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, int value); + +/*! ZSTD_CCtx_setPledgedSrcSize() : + * Total input data size to be compressed as a single frame. + * Value will be written in frame header, unless if explicitly forbidden using ZSTD_c_contentSizeFlag. + * This value will also 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 : pledgedSrcSize==0 actually means zero, aka an empty frame. + * In order to mean "unknown content size", pass constant ZSTD_CONTENTSIZE_UNKNOWN. + * ZSTD_CONTENTSIZE_UNKNOWN is default value for any new frame. + * Note 2 : pledgedSrcSize is only valid once, for the next frame. + * It's discarded at the end of the frame, and replaced by ZSTD_CONTENTSIZE_UNKNOWN. + * Note 3 : Whenever all input data is provided and consumed in a single round, + * for example with ZSTD_compress2(), + * or invoking immediately ZSTD_compressStream2(,,,ZSTD_e_end), + * this value is automatically overridden by srcSize instead. + */ +ZSTDLIB_API size_t ZSTD_CCtx_setPledgedSrcSize(ZSTD_CCtx* cctx, unsigned long long pledgedSrcSize); + +typedef enum { + ZSTD_reset_session_only = 1, + ZSTD_reset_parameters = 2, + ZSTD_reset_session_and_parameters = 3 +} ZSTD_ResetDirective; + +/*! 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. + * Compression parameters and dictionary remain unchanged. + * They will be used to compress next frame. + * Resetting session 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_ResetDirective reset); + +/*! ZSTD_compress2() : + * Behave the same as ZSTD_compressCCtx(), but compression parameters are set using the advanced API. + * ZSTD_compress2() always starts a new frame. + * Should cctx hold data from a previously unfinished frame, everything about it is forgotten. + * - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_set*() + * - The function is always blocking, returns when compression is completed. + * Hint : compression runs faster if `dstCapacity` >= `ZSTD_compressBound(srcSize)`. + * @return : compressed size written into `dst` (<= `dstCapacity), + * or an error code if it fails (which can be tested using ZSTD_isError()). + */ +ZSTDLIB_API size_t ZSTD_compress2( ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize); -/*! ZSTD_decompress_usingDDict() : - * Decompression using a digested Dictionary. - * Faster startup than ZSTD_decompress_usingDict(), recommended when same dictionary is used multiple times. */ -ZSTDLIB_API size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx, - void* dst, size_t dstCapacity, - const void* src, size_t srcSize, - const ZSTD_DDict* ddict); + +/*************************************** +* Advanced decompression API +***************************************/ + +/* The advanced API pushes parameters one by one into an existing DCtx context. + * Parameters are sticky, and remain valid for all following frames + * using the same DCtx context. + * It's possible to reset parameters to default values using ZSTD_DCtx_reset(). + * Note : This API is compatible with existing ZSTD_decompressDCtx() and ZSTD_decompressStream(). + * Therefore, no new decompression function is necessary. + */ + +typedef enum { + + ZSTD_d_windowLogMax=100, /* Select a size limit (in power of 2) beyond which + * the streaming API will refuse to allocate memory buffer + * in order to protect the host from unreasonable memory requirements. + * This parameter is only useful in streaming mode, since no internal buffer is allocated in single-pass mode. + * By default, a decompression context accepts window sizes <= (1 << ZSTD_WINDOWLOG_LIMIT_DEFAULT). + * Special: value 0 means "use default maximum windowLog". */ + + /* note : additional experimental parameters are also available + * within the experimental section of the API. + * At the time of this writing, they include : + * ZSTD_d_format + * ZSTD_d_stableOutBuffer + * Because they are not stable, it's necessary to define ZSTD_STATIC_LINKING_ONLY to access them. + * note : never ever use experimentalParam? names directly + */ + ZSTD_d_experimentalParam1=1000, + ZSTD_d_experimentalParam2=1001 + +} ZSTD_dParameter; + +/*! ZSTD_dParam_getBounds() : + * All parameters must belong to an interval with lower and upper bounds, + * otherwise they will either trigger an error or be automatically clamped. + * @return : a structure, ZSTD_bounds, which contains + * - an error status field, which must be tested using ZSTD_isError() + * - both lower and upper bounds, inclusive + */ +ZSTDLIB_API ZSTD_bounds ZSTD_dParam_getBounds(ZSTD_dParameter dParam); + +/*! ZSTD_DCtx_setParameter() : + * Set one compression parameter, selected by enum ZSTD_dParameter. + * All parameters have valid bounds. Bounds can be queried using ZSTD_dParam_getBounds(). + * Providing a value beyond bound will either clamp it, or trigger an error (depending on parameter). + * Setting a parameter is only possible during frame initialization (before starting decompression). + * @return : 0, or an error code (which can be tested using ZSTD_isError()). + */ +ZSTDLIB_API size_t ZSTD_DCtx_setParameter(ZSTD_DCtx* dctx, ZSTD_dParameter param, int value); + +/*! ZSTD_DCtx_reset() : + * Return a DCtx to clean state. + * Session and parameters can be reset jointly or separately. + * Parameters can only be reset when no active frame is being decompressed. + * @return : 0, or an error code, which can be tested with ZSTD_isError() + */ +ZSTDLIB_API size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset); /**************************** @@ -269,57 +583,153 @@ typedef struct ZSTD_outBuffer_s { * A ZSTD_CStream object is required to track streaming operation. * Use ZSTD_createCStream() and ZSTD_freeCStream() to create/release resources. * ZSTD_CStream objects can be reused multiple times on consecutive compression operations. -* It is recommended to re-use ZSTD_CStream in situations where many streaming operations will be achieved consecutively, -* since it will play nicer with system's memory, by re-using already allocated memory. -* Use one separate ZSTD_CStream per thread for parallel execution. +* It is recommended to re-use ZSTD_CStream since it will play nicer with system's memory, by re-using already allocated memory. * -* Start a new compression by initializing ZSTD_CStream. -* Use ZSTD_initCStream() to start a new compression operation. -* Use ZSTD_initCStream_usingDict() or ZSTD_initCStream_usingCDict() for a compression which requires a dictionary (experimental section) +* For parallel execution, use one separate ZSTD_CStream per thread. * -* Use ZSTD_compressStream() repetitively to consume input stream. -* The function will automatically update both `pos` fields. -* Note that it may not consume the entire input, in which case `pos < size`, -* and it's up to the caller to present again remaining data. -* @return : a size hint, preferred nb of bytes to use as input for next function call -* or an error code, which can be tested using ZSTD_isError(). -* Note 1 : it's just a hint, to help latency a little, any other value will work fine. -* Note 2 : size hint is guaranteed to be <= ZSTD_CStreamInSize() +* note : since v1.3.0, ZSTD_CStream and ZSTD_CCtx are the same thing. * -* At any moment, it's possible to flush whatever data remains within internal buffer, using ZSTD_flushStream(). -* `output->pos` will be updated. -* Note that some content might still be left within internal buffer if `output->size` is too small. -* @return : nb of bytes still present within internal buffer (0 if it's empty) +* Parameters are sticky : when starting a new compression on the same context, +* it will re-use the same sticky parameters as previous compression session. +* When in doubt, it's recommended to fully initialize the context before usage. +* Use ZSTD_CCtx_reset() to reset the context and ZSTD_CCtx_setParameter(), +* ZSTD_CCtx_setPledgedSrcSize(), or ZSTD_CCtx_loadDictionary() and friends to +* set more specific parameters, the pledged source size, or load a dictionary. +* +* Use ZSTD_compressStream2() with ZSTD_e_continue as many times as necessary to +* consume input stream. The function will automatically update both `pos` +* fields within `input` and `output`. +* Note that the function may not consume the entire input, for example, because +* the output buffer is already full, in which case `input.pos < input.size`. +* The caller must check if input has been entirely consumed. +* If not, the caller must make some room to receive more compressed data, +* and then present again remaining input data. +* note: ZSTD_e_continue is guaranteed to make some forward progress when called, +* but doesn't guarantee maximal forward progress. This is especially relevant +* when compressing with multiple threads. The call won't block if it can +* consume some input, but if it can't it will wait for some, but not all, +* output to be flushed. +* @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(). +* +* At any moment, it's possible to flush whatever data might remain stuck within internal buffer, +* using ZSTD_compressStream2() with ZSTD_e_flush. `output->pos` will be updated. +* Note that, if `output->size` is too small, a single invocation with ZSTD_e_flush might not be enough (return code > 0). +* In which case, make some room to receive more compressed data, and call again ZSTD_compressStream2() with ZSTD_e_flush. +* You must continue calling ZSTD_compressStream2() with ZSTD_e_flush until it returns 0, at which point you can change the +* operation. +* note: ZSTD_e_flush will flush as much output as possible, meaning when compressing with multiple threads, it will +* block until the flush is complete or the output buffer is full. +* @return : 0 if internal buffers are entirely flushed, +* >0 if some data still present within internal buffer (the value is minimal estimation of remaining size), * or an error code, which can be tested using ZSTD_isError(). * -* ZSTD_endStream() instructs to finish a frame. +* Calling ZSTD_compressStream2() with ZSTD_e_end instructs to finish a frame. * It will perform a flush and write frame epilogue. * The epilogue is required for decoders to consider a frame completed. -* ZSTD_endStream() may not be able to flush full data if `output->size` is too small. -* In which case, call again ZSTD_endStream() to complete the flush. +* flush operation is the same, and follows same rules as calling ZSTD_compressStream2() with ZSTD_e_flush. +* You must continue calling ZSTD_compressStream2() with ZSTD_e_end until it returns 0, at which point you are free to +* start a new frame. +* note: ZSTD_e_end will flush as much output as possible, meaning when compressing with multiple threads, it will +* block until the flush is complete or the output buffer is full. * @return : 0 if frame fully completed and fully flushed, - or >0 if some data is still present within internal buffer - (value is minimum size estimation for remaining data to flush, but it could be more) +* >0 if some data still present within internal buffer (the value is minimal estimation of remaining size), * or an error code, which can be tested using ZSTD_isError(). * * *******************************************************************/ typedef ZSTD_CCtx ZSTD_CStream; /**< CCtx and CStream are now effectively same object (>= v1.3.0) */ - /* Continue to distinguish them for compatibility with versions <= v1.2.0 */ + /* Continue to distinguish them for compatibility with older versions <= v1.2.0 */ /*===== ZSTD_CStream management functions =====*/ ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream(void); ZSTDLIB_API size_t ZSTD_freeCStream(ZSTD_CStream* zcs); /*===== Streaming compression functions =====*/ +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. + * note : multithreaded compression will block to flush as much output as possible. */ + ZSTD_e_end=2 /* flush any remaining data _and_ close current frame. + * note that frame is only closed after compressed data is fully flushed (return value == 0). + * After that point, any additional data starts a new frame. + * note : each frame is independent (does not reference any content from previous frame). + : note : multithreaded compression will block to flush as much output as possible. */ +} ZSTD_EndDirective; + +/*! ZSTD_compressStream2() : + * Behaves about the same as ZSTD_compressStream, with additional control on end directive. + * - 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) + * - output->pos must be <= dstCapacity, input->pos must be <= srcSize + * - output->pos and input->pos will be updated. They are guaranteed to remain below their respective limit. + * - When nbWorkers==0 (default), function is blocking : it completes its job before returning to caller. + * - When nbWorkers>=1, function is non-blocking : it just acquires a copy of input, and distributes jobs to internal worker threads, flush whatever is available, + * 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 : if the first call requests a ZSTD_e_end directive and provides enough dstCapacity, the function delegates to ZSTD_compress2() which is always blocking. + * - @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_compressStream2( ZSTD_CCtx* cctx, + ZSTD_outBuffer* output, + ZSTD_inBuffer* input, + ZSTD_EndDirective endOp); + + +/* These buffer sizes are softly recommended. + * They are not required : ZSTD_compressStream*() happily accepts any buffer size, for both input and output. + * Respecting the recommended size just makes it a bit easier for ZSTD_compressStream*(), + * reducing the amount of memory shuffling and buffering, resulting in minor performance savings. + * + * However, note that these recommendations are from the perspective of a C caller program. + * If the streaming interface is invoked from some other language, + * especially managed ones such as Java or Go, through a foreign function interface such as jni or cgo, + * a major performance rule is to reduce crossing such interface to an absolute minimum. + * It's not rare that performance ends being spent more into the interface, rather than compression itself. + * In which cases, prefer using large buffers, as large as practical, + * for both input and output, to reduce the nb of roundtrips. + */ +ZSTDLIB_API size_t ZSTD_CStreamInSize(void); /**< recommended size for input buffer */ +ZSTDLIB_API size_t ZSTD_CStreamOutSize(void); /**< recommended size for output buffer. Guarantee to successfully flush at least one complete compressed block. */ + + +/* ***************************************************************************** + * This following is a legacy streaming API. + * It can be replaced by ZSTD_CCtx_reset() and ZSTD_compressStream2(). + * It is redundant, but remains fully supported. + * Advanced parameters and dictionary compression can only be used through the + * new API. + ******************************************************************************/ + +/*! + * 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); + */ ZSTDLIB_API size_t ZSTD_initCStream(ZSTD_CStream* zcs, int compressionLevel); +/*! + * Alternative for ZSTD_compressStream2(zcs, output, input, ZSTD_e_continue). + * NOTE: The return value is different. ZSTD_compressStream() returns a hint for + * the next read size (if non-zero and not an error). ZSTD_compressStream2() + * returns the minimum nb of bytes left to flush (if non-zero and not an error). + */ ZSTDLIB_API size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input); +/*! Equivalent to ZSTD_compressStream2(zcs, output, &emptyInput, ZSTD_e_flush). */ ZSTDLIB_API size_t ZSTD_flushStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output); +/*! Equivalent to ZSTD_compressStream2(zcs, output, &emptyInput, ZSTD_e_end). */ ZSTDLIB_API size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output); -ZSTDLIB_API size_t ZSTD_CStreamInSize(void); /**< recommended size for input buffer */ -ZSTDLIB_API size_t ZSTD_CStreamOutSize(void); /**< recommended size for output buffer. Guarantee to successfully flush at least one complete compressed block in all circumstances. */ - - /*-*************************************************************************** * Streaming decompression - HowTo @@ -328,99 +738,399 @@ ZSTDLIB_API size_t ZSTD_CStreamOutSize(void); /**< recommended size for output * Use ZSTD_createDStream() and ZSTD_freeDStream() to create/release resources. * ZSTD_DStream objects can be re-used multiple times. * -* Use ZSTD_initDStream() to start a new decompression operation, -* or ZSTD_initDStream_usingDict() if decompression requires a dictionary. -* @return : recommended first input size +* Use ZSTD_initDStream() to start a new decompression operation. +* @return : recommended first input size +* Alternatively, use advanced API to set specific properties. * * Use ZSTD_decompressStream() repetitively to consume your input. * The function will update both `pos` fields. * If `input.pos < input.size`, some input has not been consumed. * It's up to the caller to present again remaining data. +* The function tries to flush all data decoded immediately, respecting output buffer size. * If `output.pos < output.size`, decoder has flushed everything it could. -* @return : 0 when a frame is completely decoded and fully flushed, -* an error code, which can be tested using ZSTD_isError(), -* any other value > 0, which means there is still some decoding to do to complete current frame. -* The return value is a suggested next input size (a hint to improve latency) that will never load more than the current frame. +* But if `output.pos == output.size`, there might be some data left within internal buffers., +* In which case, call ZSTD_decompressStream() again to flush whatever remains in the buffer. +* Note : with no additional input provided, amount of data flushed is necessarily <= ZSTD_BLOCKSIZE_MAX. +* @return : 0 when a frame is completely decoded and fully flushed, +* or an error code, which can be tested using ZSTD_isError(), +* or any other value > 0, which means there is still some decoding or flushing to do to complete current frame : +* the return value is a suggested next input size (just a hint for better latency) +* that will never request more than the remaining frame size. * *******************************************************************************/ typedef ZSTD_DCtx ZSTD_DStream; /**< DCtx and DStream are now effectively same object (>= v1.3.0) */ - /* Continue to distinguish them for compatibility with versions <= v1.2.0 */ + /* For compatibility with versions <= v1.2.0, prefer differentiating them. */ /*===== ZSTD_DStream management functions =====*/ ZSTDLIB_API ZSTD_DStream* ZSTD_createDStream(void); ZSTDLIB_API size_t ZSTD_freeDStream(ZSTD_DStream* zds); /*===== Streaming decompression functions =====*/ + +/* This function is redundant with the advanced API and equivalent to: + * + * ZSTD_DCtx_reset(zds, ZSTD_reset_session_only); + * ZSTD_DCtx_refDDict(zds, NULL); + */ ZSTDLIB_API size_t ZSTD_initDStream(ZSTD_DStream* zds); + ZSTDLIB_API size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inBuffer* input); ZSTDLIB_API size_t ZSTD_DStreamInSize(void); /*!< recommended size for input buffer */ ZSTDLIB_API size_t ZSTD_DStreamOutSize(void); /*!< recommended size for output buffer. Guarantee to successfully flush at least one complete block in all circumstances. */ -#endif /* ZSTD_H_235446 */ +/************************** +* Simple dictionary API +***************************/ +/*! ZSTD_compress_usingDict() : + * Compression at an explicit compression level using a Dictionary. + * A dictionary can be any arbitrary data segment (also called a prefix), + * or a buffer with specified information (see dictBuilder/zdict.h). + * Note : This function loads the dictionary, resulting in significant startup delay. + * It's intended for a dictionary used only once. + * Note 2 : When `dict == NULL || dictSize < 8` no dictionary is used. */ +ZSTDLIB_API size_t ZSTD_compress_usingDict(ZSTD_CCtx* ctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const void* dict,size_t dictSize, + int compressionLevel); +/*! ZSTD_decompress_usingDict() : + * Decompression using a known Dictionary. + * Dictionary must be identical to the one used during compression. + * Note : This function loads the dictionary, resulting in significant startup delay. + * It's intended for a dictionary used only once. + * Note : When `dict == NULL || dictSize < 8` no dictionary is used. */ +ZSTDLIB_API size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const void* dict,size_t dictSize); -/**************************************************************************************** - * START OF ADVANCED AND EXPERIMENTAL FUNCTIONS - * The definitions in this section are considered experimental. - * They should never be used with a dynamic library, as prototypes may change in the future. + +/*********************************** + * Bulk processing dictionary API + **********************************/ +typedef struct ZSTD_CDict_s ZSTD_CDict; + +/*! ZSTD_createCDict() : + * When compressing multiple messages or blocks using the same dictionary, + * it's recommended to digest the dictionary only once, since it's a costly operation. + * ZSTD_createCDict() will create a state from digesting a dictionary. + * The resulting state can be used for future compression operations with very limited startup cost. + * ZSTD_CDict can be created once and shared by multiple threads concurrently, since its usage is read-only. + * @dictBuffer can be released after ZSTD_CDict creation, because its content is copied within CDict. + * Note 1 : Consider experimental function `ZSTD_createCDict_byReference()` if you prefer to not duplicate @dictBuffer content. + * Note 2 : A ZSTD_CDict can be created from an empty @dictBuffer, + * in which case the only thing that it transports is the @compressionLevel. + * This can be useful in a pipeline featuring ZSTD_compress_usingCDict() exclusively, + * expecting a ZSTD_CDict parameter with any data, including those without a known dictionary. */ +ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict(const void* dictBuffer, size_t dictSize, + int compressionLevel); + +/*! ZSTD_freeCDict() : + * Function frees memory allocated by ZSTD_createCDict(). */ +ZSTDLIB_API size_t ZSTD_freeCDict(ZSTD_CDict* CDict); + +/*! ZSTD_compress_usingCDict() : + * Compression using a digested Dictionary. + * Recommended when same dictionary is used multiple times. + * Note : compression level is _decided at dictionary creation time_, + * and frame parameters are hardcoded (dictID=yes, contentSize=yes, checksum=no) */ +ZSTDLIB_API size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const ZSTD_CDict* cdict); + + +typedef struct ZSTD_DDict_s ZSTD_DDict; + +/*! ZSTD_createDDict() : + * Create a digested dictionary, ready to start decompression operation without startup delay. + * dictBuffer can be released after DDict creation, as its content is copied inside DDict. */ +ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict(const void* dictBuffer, size_t dictSize); + +/*! ZSTD_freeDDict() : + * Function frees memory allocated with ZSTD_createDDict() */ +ZSTDLIB_API size_t ZSTD_freeDDict(ZSTD_DDict* ddict); + +/*! ZSTD_decompress_usingDDict() : + * Decompression using a digested Dictionary. + * Recommended when same dictionary is used multiple times. */ +ZSTDLIB_API size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const ZSTD_DDict* ddict); + + +/******************************** + * Dictionary helper functions + *******************************/ + +/*! 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_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); + + +/******************************************************************************* + * Advanced dictionary and prefix API + * + * This API allows dictionaries to be used with ZSTD_compress2(), + * ZSTD_compressStream2(), and ZSTD_decompress(). Dictionaries are sticky, and + * only reset with the context is reset with ZSTD_reset_parameters or + * ZSTD_reset_session_and_parameters. Prefixes are single-use. + ******************************************************************************/ + + +/*! 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: Loading a NULL (or 0-size) dictionary invalidates previous dictionary, + * meaning "return to no-dictionary mode". + * Note 1 : Dictionary is sticky, it will be used for all future compressed frames. + * To return to "no-dictionary" situation, load a NULL dictionary (or reset parameters). + * Note 2 : Loading a dictionary involves building tables. + * It's also a CPU consuming operation, with non-negligible impact on latency. + * Tables are dependent on compression parameters, and for this reason, + * compression parameters can no longer be changed after loading a dictionary. + * Note 3 :`dict` content will be copied internally. + * Use experimental ZSTD_CCtx_loadDictionary_byReference() to reference 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_CCtx_refCDict() : + * Reference a prepared dictionary, to be used for all next compressed frames. + * Note that compression parameters are enforced from within CDict, + * and supersede any compression parameter previously set within CCtx. + * The parameters ignored are labled as "superseded-by-cdict" in the ZSTD_cParameter enum docs. + * The ignored parameters will be used again if the CCtx is returned to no-dictionary mode. + * The dictionary will remain valid for future compressed frames using same CCtx. + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + * Special : Referencing a NULL CDict means "return to no-dictionary mode". + * Note 1 : Currently, only one dictionary can be managed. + * Referencing a new dictionary effectively "discards" any previous one. + * Note 2 : CDict is just referenced, its lifetime must outlive its usage within CCtx. */ +ZSTDLIB_API size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict); + +/*! ZSTD_CCtx_refPrefix() : + * Reference a prefix (single-usage dictionary) for next compressed frame. + * A prefix is **only used once**. Tables are discarded at end of frame (ZSTD_e_end). + * 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). + * @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. + * 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_c_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_dct_rawContent). + * Use experimental 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_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 size_t ZSTD_DCtx_loadDictionary(ZSTD_DCtx* dctx, const void* dict, size_t dictSize); + +/*! 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: referencing 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_DCtx_refDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict); + +/*! ZSTD_DCtx_refPrefix() : + * Reference a prefix (single-usage dictionary) to decompress next frame. + * 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_decompressStream() 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. + * Prefix buffer must remain unmodified up to the end of frame, + * reached when ZSTD_decompressStream() returns 0. + * Note 3 : By default, the prefix is treated as raw content (ZSTD_dct_rawContent). + * Use ZSTD_CCtx_refPrefix_advanced() to alter dictMode (Experimental section) + * Note 4 : Referencing a raw content prefix has almost no cpu nor memory cost. + * A full dictionary is more costly, as it requires building tables. + */ +ZSTDLIB_API size_t ZSTD_DCtx_refPrefix(ZSTD_DCtx* dctx, + const void* prefix, size_t prefixSize); + +/* === Memory management === */ + +/*! ZSTD_sizeof_*() : + * These functions give the _current_ memory usage of selected object. + * Note that object memory usage can evolve (increase or decrease) over time. */ +ZSTDLIB_API size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx); +ZSTDLIB_API size_t ZSTD_sizeof_DCtx(const ZSTD_DCtx* dctx); +ZSTDLIB_API size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs); +ZSTDLIB_API size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds); +ZSTDLIB_API size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict); +ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict); + +#endif /* ZSTD_H_235446 */ + + +/* ************************************************************************************** + * ADVANCED AND EXPERIMENTAL FUNCTIONS + **************************************************************************************** + * The definitions in the following section are considered experimental. * They are provided for advanced scenarios. + * They should never be used with a dynamic library, as prototypes may change in the future. * Use them only in association with static linking. * ***************************************************************************************/ #if defined(ZSTD_STATIC_LINKING_ONLY) && !defined(ZSTD_H_ZSTD_STATIC_LINKING_ONLY) #define ZSTD_H_ZSTD_STATIC_LINKING_ONLY -/* --- Constants ---*/ -#define ZSTD_MAGICNUMBER 0xFD2FB528 /* >= v0.8.0 */ -#define ZSTD_MAGIC_SKIPPABLE_START 0x184D2A50U -#define ZSTD_MAGIC_DICTIONARY 0xEC30A437 /* v0.7+ */ - -#define ZSTD_WINDOWLOG_MAX_32 27 -#define ZSTD_WINDOWLOG_MAX_64 27 -#define ZSTD_WINDOWLOG_MAX ((unsigned)(sizeof(size_t) == 4 ? ZSTD_WINDOWLOG_MAX_32 : ZSTD_WINDOWLOG_MAX_64)) -#define ZSTD_WINDOWLOG_MIN 10 -#define ZSTD_HASHLOG_MAX ZSTD_WINDOWLOG_MAX -#define ZSTD_HASHLOG_MIN 6 -#define ZSTD_CHAINLOG_MAX (ZSTD_WINDOWLOG_MAX+1) -#define ZSTD_CHAINLOG_MIN ZSTD_HASHLOG_MIN -#define ZSTD_HASHLOG3_MAX 17 -#define ZSTD_SEARCHLOG_MAX (ZSTD_WINDOWLOG_MAX-1) -#define ZSTD_SEARCHLOG_MIN 1 -#define ZSTD_SEARCHLENGTH_MAX 7 /* only for ZSTD_fast, other strategies are limited to 6 */ -#define ZSTD_SEARCHLENGTH_MIN 3 /* only for ZSTD_btopt, other strategies are limited to 4 */ -#define ZSTD_TARGETLENGTH_MIN 4 -#define ZSTD_TARGETLENGTH_MAX 999 -#define ZSTD_LDM_MINMATCH_MIN 4 -#define ZSTD_LDM_MINMATCH_MAX 4096 -#define ZSTD_LDM_BUCKETSIZELOG_MAX 8 - -#define ZSTD_FRAMEHEADERSIZE_MAX 18 /* for static allocation */ -#define ZSTD_FRAMEHEADERSIZE_MIN 6 -static const size_t ZSTD_frameHeaderSize_prefix = 5; /* minimum input size to know frame header size */ -static const size_t ZSTD_frameHeaderSize_max = ZSTD_FRAMEHEADERSIZE_MAX; -static const size_t ZSTD_frameHeaderSize_min = ZSTD_FRAMEHEADERSIZE_MIN; -static const size_t ZSTD_skippableHeaderSize = 8; /* magic number + skippable frame length */ - - -/*--- Advanced types ---*/ -typedef enum { ZSTD_fast=1, ZSTD_dfast, ZSTD_greedy, ZSTD_lazy, ZSTD_lazy2, - ZSTD_btlazy2, ZSTD_btopt, ZSTD_btultra } ZSTD_strategy; /* from faster to stronger */ +/**************************************************************************************** + * experimental API (static linking only) + **************************************************************************************** + * The following symbols and constants + * are not planned to join "stable API" status in the near future. + * They can still change in future versions. + * Some of them are planned to remain in the static_only section indefinitely. + * Some of them might be removed in the future (especially when redundant with existing stable functions) + * ***************************************************************************************/ + +#define ZSTD_FRAMEHEADERSIZE_PREFIX(format) ((format) == ZSTD_f_zstd1 ? 5 : 1) /* minimum input size required to query frame header size */ +#define ZSTD_FRAMEHEADERSIZE_MIN(format) ((format) == ZSTD_f_zstd1 ? 6 : 2) +#define ZSTD_FRAMEHEADERSIZE_MAX 18 /* can be useful for static allocation */ +#define ZSTD_SKIPPABLEHEADERSIZE 8 + +/* compression parameter bounds */ +#define ZSTD_WINDOWLOG_MAX_32 30 +#define ZSTD_WINDOWLOG_MAX_64 31 +#define ZSTD_WINDOWLOG_MAX ((int)(sizeof(size_t) == 4 ? ZSTD_WINDOWLOG_MAX_32 : ZSTD_WINDOWLOG_MAX_64)) +#define ZSTD_WINDOWLOG_MIN 10 +#define ZSTD_HASHLOG_MAX ((ZSTD_WINDOWLOG_MAX < 30) ? ZSTD_WINDOWLOG_MAX : 30) +#define ZSTD_HASHLOG_MIN 6 +#define ZSTD_CHAINLOG_MAX_32 29 +#define ZSTD_CHAINLOG_MAX_64 30 +#define ZSTD_CHAINLOG_MAX ((int)(sizeof(size_t) == 4 ? ZSTD_CHAINLOG_MAX_32 : ZSTD_CHAINLOG_MAX_64)) +#define ZSTD_CHAINLOG_MIN ZSTD_HASHLOG_MIN +#define ZSTD_SEARCHLOG_MAX (ZSTD_WINDOWLOG_MAX-1) +#define ZSTD_SEARCHLOG_MIN 1 +#define ZSTD_MINMATCH_MAX 7 /* only for ZSTD_fast, other strategies are limited to 6 */ +#define ZSTD_MINMATCH_MIN 3 /* only for ZSTD_btopt+, faster strategies are limited to 4 */ +#define ZSTD_TARGETLENGTH_MAX ZSTD_BLOCKSIZE_MAX +#define ZSTD_TARGETLENGTH_MIN 0 /* note : comparing this constant to an unsigned results in a tautological test */ +#define ZSTD_STRATEGY_MIN ZSTD_fast +#define ZSTD_STRATEGY_MAX ZSTD_btultra2 + + +#define ZSTD_OVERLAPLOG_MIN 0 +#define ZSTD_OVERLAPLOG_MAX 9 + +#define ZSTD_WINDOWLOG_LIMIT_DEFAULT 27 /* by default, the streaming decoder will refuse any frame + * requiring larger than (1<<ZSTD_WINDOWLOG_LIMIT_DEFAULT) window size, + * to preserve host's memory from unreasonable requirements. + * This limit can be overridden using ZSTD_DCtx_setParameter(,ZSTD_d_windowLogMax,). + * The limit does not apply for one-pass decoders (such as ZSTD_decompress()), since no additional memory is allocated */ + + +/* LDM parameter bounds */ +#define ZSTD_LDM_HASHLOG_MIN ZSTD_HASHLOG_MIN +#define ZSTD_LDM_HASHLOG_MAX ZSTD_HASHLOG_MAX +#define ZSTD_LDM_MINMATCH_MIN 4 +#define ZSTD_LDM_MINMATCH_MAX 4096 +#define ZSTD_LDM_BUCKETSIZELOG_MIN 1 +#define ZSTD_LDM_BUCKETSIZELOG_MAX 8 +#define ZSTD_LDM_HASHRATELOG_MIN 0 +#define ZSTD_LDM_HASHRATELOG_MAX (ZSTD_WINDOWLOG_MAX - ZSTD_HASHLOG_MIN) + +/* Advanced parameter bounds */ +#define ZSTD_TARGETCBLOCKSIZE_MIN 64 +#define ZSTD_TARGETCBLOCKSIZE_MAX ZSTD_BLOCKSIZE_MAX +#define ZSTD_SRCSIZEHINT_MIN 0 +#define ZSTD_SRCSIZEHINT_MAX INT_MAX + +/* internal */ +#define ZSTD_HASHLOG3_MAX 17 + + +/* --- Advanced types --- */ + +typedef struct ZSTD_CCtx_params_s ZSTD_CCtx_params; + +typedef struct { + unsigned int matchPos; /* Match pos in dst */ + /* If seqDef.offset > 3, then this is seqDef.offset - 3 + * If seqDef.offset < 3, then this is the corresponding repeat offset + * But if seqDef.offset < 3 and litLength == 0, this is the + * repeat offset before the corresponding repeat offset + * And if seqDef.offset == 3 and litLength == 0, this is the + * most recent repeat offset - 1 + */ + unsigned int offset; + unsigned int litLength; /* Literal length */ + unsigned int matchLength; /* Match length */ + /* 0 when seq not rep and seqDef.offset otherwise + * when litLength == 0 this will be <= 4, otherwise <= 3 like normal + */ + unsigned int rep; +} ZSTD_Sequence; typedef struct { - 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; + 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 minMatch; /**< 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 at end of frame, for error detection */ - unsigned noDictIDFlag; /**< 1: no dictID will be saved into frame header (if dictionary compression) */ + int contentSizeFlag; /**< 1: content size will be in frame header (when known) */ + int checksumFlag; /**< 1: generate a 32-bits checksum using XXH64 algorithm at end of frame, for error detection */ + int noDictIDFlag; /**< 1: no dictID will be saved into frame header (dictID is only useful for dictionary compression) */ } ZSTD_frameParameters; typedef struct { @@ -428,32 +1138,81 @@ typedef struct { ZSTD_frameParameters fParams; } ZSTD_parameters; -typedef struct ZSTD_CCtx_params_s ZSTD_CCtx_params; +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; -/*= Custom memory allocation functions */ -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; -/* use this constant to defer to stdlib's functions */ -static const ZSTD_customMem ZSTD_defaultCMem = { NULL, NULL, NULL }; +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 { + ZSTD_f_zstd1 = 0, /* zstd frame format, specified in zstd_compression_format.md (default) */ + ZSTD_f_zstd1_magicless = 1 /* Variant of zstd frame format, without initial 4-bytes magic number. + * Useful to save 4 bytes per generated frame. + * Decoder cannot recognise automatically this format, requiring this instruction. */ +} ZSTD_format_e; + +typedef enum { + /* Note: this enum and the behavior it controls are effectively internal + * implementation details of the compressor. They are expected to continue + * to evolve and should be considered only in the context of extremely + * advanced performance tuning. + * + * Zstd currently supports the use of a CDict in three ways: + * + * - The contents of the CDict can be copied into the working context. This + * means that the compression can search both the dictionary and input + * while operating on a single set of internal tables. This makes + * the compression faster per-byte of input. However, the initial copy of + * the CDict's tables incurs a fixed cost at the beginning of the + * compression. For small compressions (< 8 KB), that copy can dominate + * the cost of the compression. + * + * - The CDict's tables can be used in-place. In this model, compression is + * slower per input byte, because the compressor has to search two sets of + * tables. However, this model incurs no start-up cost (as long as the + * working context's tables can be reused). For small inputs, this can be + * faster than copying the CDict's tables. + * + * - The CDict's tables are not used at all, and instead we use the working + * context alone to reload the dictionary and use params based on the source + * size. See ZSTD_compress_insertDictionary() and ZSTD_compress_usingDict(). + * This method is effective when the dictionary sizes are very small relative + * to the input size, and the input size is fairly large to begin with. + * + * Zstd has a simple internal heuristic that selects which strategy to use + * at the beginning of a compression. However, if experimentation shows that + * Zstd is making poor choices, it is possible to override that choice with + * this enum. + */ + ZSTD_dictDefaultAttach = 0, /* Use the default heuristic. */ + ZSTD_dictForceAttach = 1, /* Never copy the dictionary. */ + ZSTD_dictForceCopy = 2, /* Always copy the dictionary. */ + ZSTD_dictForceLoad = 3 /* Always reload the dictionary */ +} ZSTD_dictAttachPref_e; + +typedef enum { + ZSTD_lcm_auto = 0, /**< Automatically determine the compression mode based on the compression level. + * Negative compression levels will be uncompressed, and positive compression + * levels will be compressed. */ + ZSTD_lcm_huffman = 1, /**< Always attempt Huffman compression. Uncompressed literals will still be + * emitted if Huffman compression is not profitable. */ + ZSTD_lcm_uncompressed = 2 /**< Always emit uncompressed literals. */ +} ZSTD_literalCompressionMode_e; /*************************************** * Frame size functions ***************************************/ -/*! ZSTD_findFrameCompressedSize() : - * `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 first frame starting at `src`, - * suitable to pass to `ZSTD_decompress` or similar, - * or an error code if input is invalid */ -ZSTDLIB_API size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize); - /*! ZSTD_findDecompressedSize() : - * `src` should point the start of a series of ZSTD encoded and/or skippable frames + * `src` should point to the start of a series of ZSTD encoded and/or skippable frames * `srcSize` must be the _exact_ size of this series - * (i.e. there should be a frame boundary exactly at `srcSize` bytes after `src`) + * (i.e. there should be a frame boundary at `src + srcSize`) * @return : - decompressed size of all data in all successive frames * - if the decompressed size cannot be determined: ZSTD_CONTENTSIZE_UNKNOWN * - if an error occurred: ZSTD_CONTENTSIZE_ERROR @@ -473,48 +1232,76 @@ ZSTDLIB_API size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize) * however it does mean that all frame data must be present and valid. */ ZSTDLIB_API unsigned long long ZSTD_findDecompressedSize(const void* src, size_t srcSize); +/*! ZSTD_decompressBound() : + * `src` should point to the start of a series of ZSTD encoded and/or skippable frames + * `srcSize` must be the _exact_ size of this series + * (i.e. there should be a frame boundary at `src + srcSize`) + * @return : - upper-bound for the decompressed size of all data in all successive frames + * - if an error occured: ZSTD_CONTENTSIZE_ERROR + * + * note 1 : an error can occur if `src` contains an invalid or incorrectly formatted frame. + * note 2 : the upper-bound is exact when the decompressed size field is available in every ZSTD encoded frame of `src`. + * in this case, `ZSTD_findDecompressedSize` and `ZSTD_decompressBound` return the same value. + * note 3 : when the decompressed size field isn't available, the upper-bound for that frame is calculated by: + * upper-bound = # blocks * min(128 KB, Window_Size) + */ +ZSTDLIB_API unsigned long long ZSTD_decompressBound(const void* src, size_t srcSize); + /*! ZSTD_frameHeaderSize() : -* `src` should point to the start of a ZSTD frame -* `srcSize` must be >= ZSTD_frameHeaderSize_prefix. -* @return : size of the Frame Header */ + * srcSize must be >= ZSTD_FRAMEHEADERSIZE_PREFIX. + * @return : size of the Frame Header, + * or an error code (if srcSize is too small) */ ZSTDLIB_API size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize); +/*! ZSTD_getSequences() : + * Extract sequences from the sequence store + * zc can be used to insert custom compression params. + * This function invokes ZSTD_compress2 + * @return : number of sequences extracted + */ +ZSTDLIB_API size_t ZSTD_getSequences(ZSTD_CCtx* zc, ZSTD_Sequence* outSeqs, + size_t outSeqsSize, const void* src, size_t srcSize); + /*************************************** -* Context memory usage +* Memory management ***************************************/ -/*! ZSTD_sizeof_*() : - * These functions give the current memory usage of selected object. - * Object memory usage can evolve if it's re-used multiple times. */ -ZSTDLIB_API size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx); -ZSTDLIB_API size_t ZSTD_sizeof_DCtx(const ZSTD_DCtx* dctx); -ZSTDLIB_API size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs); -ZSTDLIB_API size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds); -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_advanced_usingCParams() can provide a tighter estimation. - * ZSTD_estimateCCtxSize_advanced_usingCParams() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel. - * ZSTD_estimateCCtxSize_advanced_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_nbThreads is > 1. - * Note : CCtx estimation is only correct for single-threaded compression */ + * + * ZSTD_estimateCCtxSize() will provide a memory budget large enough + * for any compression level up to selected one. + * Note : Unlike ZSTD_estimateCStreamSize*(), this estimate + * does not include space for a window buffer. + * Therefore, the estimation is only guaranteed for single-shot compressions, not streaming. + * The estimate will assume the input may be arbitrarily large, + * which is the worst case. + * + * When srcSize can be bound by a known and rather "small" value, + * this fact can be used to provide a tighter estimation + * because the CCtx compression context will need less memory. + * This tighter estimation can be provided by more advanced functions + * ZSTD_estimateCCtxSize_usingCParams(), which can be used in tandem with ZSTD_getCParams(), + * and ZSTD_estimateCCtxSize_usingCCtxParams(), which can be used in tandem with ZSTD_CCtxParams_setParameter(). + * Both can be used to estimate memory using custom compression parameters and arbitrary srcSize limits. + * + * Note 2 : only single-threaded compression is supported. + * ZSTD_estimateCCtxSize_usingCCtxParams() will return an error code if ZSTD_c_nbWorkers is >= 1. + */ ZSTDLIB_API size_t ZSTD_estimateCCtxSize(int compressionLevel); -ZSTDLIB_API size_t ZSTD_estimateCCtxSize_advanced_usingCParams(ZSTD_compressionParameters cParams); -ZSTDLIB_API size_t ZSTD_estimateCCtxSize_advanced_usingCCtxParams(const ZSTD_CCtx_params* params); +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_advanced_usingCParams() can provide a tighter estimation. - * ZSTD_estimateCStreamSize_advanced_usingCParams() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel. - * ZSTD_estimateCStreamSize_advanced_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_nbThreads is set to a value > 1. - * Note : CStream estimation is only correct for single-threaded compression. + * 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_CCtxParams_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_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(); @@ -522,124 +1309,301 @@ ZSTDLIB_API size_t ZSTD_estimateDCtxSize(void); * 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_advanced_usingCParams(ZSTD_compressionParameters cParams); -ZSTDLIB_API size_t ZSTD_estimateCStreamSize_advanced_usingCCtxParams(const ZSTD_CCtx_params* params); +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); -typedef enum { - ZSTD_dlm_byCopy = 0, /* Copy dictionary content internally. */ - ZSTD_dlm_byRef, /* Reference dictionary content -- the dictionary buffer must outlives its users. */ -} ZSTD_dictLoadMethod_e; - /*! ZSTD_estimate?DictSize() : * ZSTD_estimateCDictSize() will bet that src size is relatively "small", and content is copied, like ZSTD_createCDict(). - * ZSTD_estimateCStreamSize_advanced_usingCParams() makes it possible to control precisely compression parameters, like ZSTD_createCDict_advanced(). - * Note : dictionary created by reference using ZSTD_dlm_byRef are smaller + * 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. */ 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); - -/*************************************** -* Advanced compression functions -***************************************/ -/*! ZSTD_createCCtx_advanced() : - * Create a ZSTD compression context using external alloc and free functions */ -ZSTDLIB_API ZSTD_CCtx* ZSTD_createCCtx_advanced(ZSTD_customMem customMem); - -/*! ZSTD_initStaticCCtx() : initialize a fixed-size zstd compression context - * workspace: The memory area to emplace the context into. - * Provided pointer must 8-bytes aligned. - * It must outlive context usage. - * workspaceSize: Use ZSTD_estimateCCtxSize() or ZSTD_estimateCStreamSize() - * to determine how large workspace must be to support scenario. - * @return : pointer to ZSTD_CCtx*, or NULL if error (size too small) - * Note : zstd will never resize nor malloc() when using a static cctx. - * If it needs more memory than available, it will simply error out. +/*! 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 was allocated externally, it must be freed externally too. - * Limitation 1 : currently not compatible with internal CDict creation, such as - * ZSTD_CCtx_loadDictionary() or ZSTD_initCStream_usingDict(). - * Limitation 2 : currently not compatible with multi-threading + * 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_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() */ -/*! 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); +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); + +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); + + +/*! 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 <stdlib.h> 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 */ + +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); -typedef enum { ZSTD_dm_auto=0, /* dictionary is "full" if it starts with ZSTD_MAGIC_DICTIONARY, otherwise it is "rawContent" */ - ZSTD_dm_rawContent, /* ensures dictionary is always loaded as rawContent, even if it starts with ZSTD_MAGIC_DICTIONARY */ - ZSTD_dm_fullDict /* refuses to load a dictionary if it does not respect Zstandard's specification */ -} ZSTD_dictMode_e; -/*! ZSTD_createCDict_advanced() : - * Create a ZSTD_CDict using external alloc and free, and customized compression parameters */ ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_advanced(const void* dict, size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod, - ZSTD_dictMode_e dictMode, + ZSTD_dictContentType_e dictContentType, ZSTD_compressionParameters cParams, ZSTD_customMem customMem); -/*! ZSTD_initStaticCDict_advanced() : - * Generate a digested dictionary in provided memory area. - * workspace: The memory area to emplace the dictionary into. - * Provided pointer must 8-bytes aligned. - * It must outlive dictionary usage. - * workspaceSize: Use ZSTD_estimateCDictSize() - * to determine how large workspace must be. - * cParams : use ZSTD_getCParams() to transform a compression level - * into its relevants cParams. - * @return : pointer to ZSTD_CDict*, or NULL if error (size too small) - * Note : there is no corresponding "free" function. - * Since workspace was allocated externally, it must be freed externally. - */ -ZSTDLIB_API ZSTD_CDict* ZSTD_initStaticCDict( - void* workspace, size_t workspaceSize, - const void* dict, size_t dictSize, - ZSTD_dictLoadMethod_e dictLoadMethod, ZSTD_dictMode_e dictMode, - ZSTD_compressionParameters cParams); +ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_advanced(const void* dict, size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_dictContentType_e dictContentType, + ZSTD_customMem customMem); + + + +/*************************************** +* Advanced compression functions +***************************************/ + +/*! ZSTD_createCDict_byReference() : + * Create a digested dictionary for compression + * Dictionary content is just referenced, not duplicated. + * As a consequence, `dictBuffer` **must** outlive CDict, + * and its content must remain unmodified throughout the lifetime of CDict. + * note: equivalent to ZSTD_createCDict_advanced(), with dictLoadMethod==ZSTD_dlm_byRef */ +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 */ + * @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_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 (0) */ + * 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_checkCParams() : -* Ensure param values remain within authorized range */ + * Ensure param values remain within authorized range. + * @return 0 on success, or an error code (can be checked with ZSTD_isError()) */ ZSTDLIB_API size_t ZSTD_checkCParams(ZSTD_compressionParameters params); /*! ZSTD_adjustCParams() : * optimize params for a given `srcSize` and `dictSize`. - * both values are optional, select `0` if unknown. */ + * `srcSize` can be unknown, in which case use ZSTD_CONTENTSIZE_UNKNOWN. + * `dictSize` must be `0` when there is no dictionary. + * cPar can be invalid : all parameters will be clamped within valid range in the @return struct. + * This function never fails (wide contract) */ ZSTDLIB_API ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize); /*! 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); + * 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, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const void* dict,size_t dictSize, + ZSTD_parameters params); /*! ZSTD_compress_usingCDict_advanced() : -* Same as ZSTD_compress_usingCDict(), with fine-tune control over frame parameters */ + * Note : this function is now REDUNDANT. + * 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, - void* dst, size_t dstCapacity, - const void* src, size_t srcSize, - const ZSTD_CDict* cdict, ZSTD_frameParameters fParams); + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const ZSTD_CDict* cdict, + ZSTD_frameParameters fParams); + + +/*! ZSTD_CCtx_loadDictionary_byReference() : + * Same as ZSTD_CCtx_loadDictionary(), but dictionary content is referenced, instead of being copied into CCtx. + * It saves some memory, but also requires that `dict` outlives its usage within `cctx` */ +ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary_byReference(ZSTD_CCtx* cctx, const void* dict, size_t dictSize); +/*! ZSTD_CCtx_loadDictionary_advanced() : + * Same as ZSTD_CCtx_loadDictionary(), but gives finer control over + * how to load the dictionary (by copy ? by reference ?) + * and how to interpret it (automatic ? force raw mode ? full mode only ?) */ +ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary_advanced(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod, ZSTD_dictContentType_e dictContentType); + +/*! ZSTD_CCtx_refPrefix_advanced() : + * Same as ZSTD_CCtx_refPrefix(), but gives finer control over + * how to interpret prefix content (automatic ? force raw mode (default) ? full mode only ?) */ +ZSTDLIB_API size_t ZSTD_CCtx_refPrefix_advanced(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize, ZSTD_dictContentType_e dictContentType); + +/* === experimental parameters === */ +/* these parameters can be used with ZSTD_setParameter() + * they are not guaranteed to remain supported in the future */ + + /* 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_c_jobSize / 2. + * It's possible to modify the job size to increase or decrease + * the granularity of the synchronization point. + * Once the jobSize is smaller than the window size, + * it will result in compression ratio degradation. + * NOTE 1: rsyncable mode only works when multithreading is enabled. + * NOTE 2: rsyncable performs poorly in combination with long range mode, + * since it will decrease the effectiveness of synchronization points, + * though mileage may vary. + * NOTE 3: Rsyncable mode limits maximum compression speed to ~400 MB/s. + * If the selected compression level is already running significantly slower, + * the overall speed won't be significantly impacted. + */ + #define ZSTD_c_rsyncable ZSTD_c_experimentalParam1 + +/* Select a compression format. + * The value must be of type ZSTD_format_e. + * See ZSTD_format_e enum definition for details */ +#define ZSTD_c_format ZSTD_c_experimentalParam2 + +/* Force back-reference distances to remain < windowSize, + * even when referencing into Dictionary content (default:0) */ +#define ZSTD_c_forceMaxWindow ZSTD_c_experimentalParam3 + +/* Controls whether the contents of a CDict + * are used in place, or 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. */ +#define ZSTD_c_forceAttachDict ZSTD_c_experimentalParam4 + +/* Controls how the literals are compressed (default is auto). + * The value must be of type ZSTD_literalCompressionMode_e. + * See ZSTD_literalCompressionMode_t enum definition for details. + */ +#define ZSTD_c_literalCompressionMode ZSTD_c_experimentalParam5 + +/* Tries to fit compressed block size to be around targetCBlockSize. + * No target when targetCBlockSize == 0. + * There is no guarantee on compressed block size (default:0) */ +#define ZSTD_c_targetCBlockSize ZSTD_c_experimentalParam6 + +/* User's best guess of source size. + * Hint is not valid when srcSizeHint == 0. + * There is no guarantee that hint is close to actual source size, + * but compression ratio may regress significantly if guess considerably underestimates */ +#define ZSTD_c_srcSizeHint ZSTD_c_experimentalParam7 + +/*! ZSTD_CCtx_getParameter() : + * Get the requested compression parameter value, selected by enum ZSTD_cParameter, + * and store it into int* value. + * @return : 0, or an error code (which can be tested with ZSTD_isError()). + */ +ZSTDLIB_API size_t ZSTD_CCtx_getParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, int* value); -/*--- Advanced decompression functions ---*/ + +/*! ZSTD_CCtx_params : + * Quick howto : + * - ZSTD_createCCtxParams() : Create a ZSTD_CCtx_params structure + * - ZSTD_CCtxParams_setParameter() : Push parameters one by one into + * an existing ZSTD_CCtx_params structure. + * This is similar to + * ZSTD_CCtx_setParameter(). + * - ZSTD_CCtx_setParametersUsingCCtxParams() : Apply parameters to + * an existing CCtx. + * These parameters will be applied to + * all subsequent frames. + * - ZSTD_compressStream2() : Do compression using the CCtx. + * - ZSTD_freeCCtxParams() : Free the memory. + * + * This can be used with ZSTD_estimateCCtxSize_advanced_usingCCtxParams() + * for static allocation of CCtx for single-threaded compression. + */ +ZSTDLIB_API ZSTD_CCtx_params* ZSTD_createCCtxParams(void); +ZSTDLIB_API size_t ZSTD_freeCCtxParams(ZSTD_CCtx_params* params); + +/*! ZSTD_CCtxParams_reset() : + * Reset params to default values. + */ +ZSTDLIB_API size_t ZSTD_CCtxParams_reset(ZSTD_CCtx_params* params); + +/*! ZSTD_CCtxParams_init() : + * Initializes the compression parameters of cctxParams according to + * compression level. All other parameters are reset to their default values. + */ +ZSTDLIB_API size_t ZSTD_CCtxParams_init(ZSTD_CCtx_params* cctxParams, int compressionLevel); + +/*! ZSTD_CCtxParams_init_advanced() : + * Initializes the compression and frame parameters of cctxParams according to + * params. All other parameters are reset to their default values. + */ +ZSTDLIB_API size_t ZSTD_CCtxParams_init_advanced(ZSTD_CCtx_params* cctxParams, ZSTD_parameters params); + +/*! ZSTD_CCtxParams_setParameter() : + * Similar to ZSTD_CCtx_setParameter. + * Set one compression parameter, selected by enum ZSTD_cParameter. + * Parameters must be applied to a ZSTD_CCtx using ZSTD_CCtx_setParametersUsingCCtxParams(). + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + */ +ZSTDLIB_API size_t ZSTD_CCtxParams_setParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int value); + +/*! ZSTD_CCtxParams_getParameter() : + * Similar to ZSTD_CCtx_getParameter. + * Get the requested value of one compression parameter, selected by enum ZSTD_cParameter. + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + */ +ZSTDLIB_API size_t ZSTD_CCtxParams_getParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int* value); + +/*! ZSTD_CCtx_setParametersUsingCCtxParams() : + * Apply a set of ZSTD_CCtx_params to the compression context. + * This can be done even after compression is started, + * if nbWorkers==0, this will have no impact until a new compression is started. + * if nbWorkers>=1, new parameters will be picked up at next job, + * with a few restrictions (windowLog, pledgedSrcSize, nbWorkers, jobSize, and overlapLog are not updated). + */ +ZSTDLIB_API size_t ZSTD_CCtx_setParametersUsingCCtxParams( + ZSTD_CCtx* cctx, const ZSTD_CCtx_params* params); + +/*! ZSTD_compressStream2_simpleArgs() : + * Same as ZSTD_compressStream2(), + * 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_compressStream2_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 decompression functions +***************************************/ /*! ZSTD_isFrame() : * Tells if the content of `buffer` starts with a valid Frame Identifier. @@ -648,27 +1612,6 @@ ZSTDLIB_API size_t ZSTD_compress_usingCDict_advanced(ZSTD_CCtx* cctx, * Note 3 : Skippable Frame Identifiers are considered valid. */ ZSTDLIB_API unsigned ZSTD_isFrame(const void* buffer, size_t size); -/*! ZSTD_createDCtx_advanced() : - * Create a ZSTD decompression context using external alloc and free functions */ -ZSTDLIB_API ZSTD_DCtx* ZSTD_createDCtx_advanced(ZSTD_customMem customMem); - -/*! ZSTD_initStaticDCtx() : initialize a fixed-size zstd decompression context - * workspace: The memory area to emplace the context into. - * Provided pointer must 8-bytes aligned. - * It must outlive context usage. - * workspaceSize: Use ZSTD_estimateDCtxSize() or ZSTD_estimateDStreamSize() - * to determine how large workspace must be to support scenario. - * @return : pointer to ZSTD_DCtx*, or NULL if error (size too small) - * Note : zstd will never resize nor malloc() when using a static dctx. - * If it needs more memory than available, it will simply error out. - * Note 2 : static dctx is incompatible with legacy support - * Note 3 : there is no corresponding "free" function. - * Since workspace was allocated externally, it must be freed externally. - * Limitation : currently not compatible with internal DDict creation, - * such as ZSTD_initDStream_usingDict(). - */ -ZSTDLIB_API ZSTD_DCtx* ZSTD_initStaticDCtx(void* workspace, size_t workspaceSize); - /*! ZSTD_createDDict_byReference() : * Create a digested dictionary, ready to start decompression operation without startup delay. * Dictionary content is referenced, and therefore stays in dictBuffer. @@ -676,92 +1619,275 @@ ZSTDLIB_API ZSTD_DCtx* ZSTD_initStaticDCtx(void* workspace, size_t workspaceSize * it must remain read accessible throughout the lifetime of DDict */ ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, size_t dictSize); -/*! ZSTD_createDDict_advanced() : - * Create a ZSTD_DDict using external alloc and free, optionally by reference */ -ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_advanced(const void* dict, size_t dictSize, - ZSTD_dictLoadMethod_e dictLoadMethod, - ZSTD_customMem customMem); - -/*! ZSTD_initStaticDDict() : - * Generate a digested dictionary in provided memory area. - * workspace: The memory area to emplace the dictionary into. - * Provided pointer must 8-bytes aligned. - * It must outlive dictionary usage. - * workspaceSize: Use ZSTD_estimateDDictSize() - * to determine how large workspace must be. - * @return : pointer to ZSTD_DDict*, or NULL if error (size too small) - * Note : there is no corresponding "free" function. - * Since workspace was allocated externally, it must be freed externally. +/*! ZSTD_DCtx_loadDictionary_byReference() : + * Same as ZSTD_DCtx_loadDictionary(), + * but references `dict` content instead of copying it into `dctx`. + * This saves memory if `dict` remains around., + * However, it's imperative that `dict` remains accessible (and unmodified) while being used, so it must outlive decompression. */ +ZSTDLIB_API size_t ZSTD_DCtx_loadDictionary_byReference(ZSTD_DCtx* dctx, const void* dict, size_t dictSize); + +/*! ZSTD_DCtx_loadDictionary_advanced() : + * Same as ZSTD_DCtx_loadDictionary(), + * but gives direct control over + * how to load the dictionary (by copy ? by reference ?) + * and how to interpret it (automatic ? force raw mode ? full mode only ?). */ +ZSTDLIB_API size_t ZSTD_DCtx_loadDictionary_advanced(ZSTD_DCtx* dctx, const void* dict, size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod, ZSTD_dictContentType_e dictContentType); + +/*! ZSTD_DCtx_refPrefix_advanced() : + * Same as ZSTD_DCtx_refPrefix(), but gives finer control over + * how to interpret prefix content (automatic ? force raw mode (default) ? full mode only ?) */ +ZSTDLIB_API size_t ZSTD_DCtx_refPrefix_advanced(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSize, ZSTD_dictContentType_e dictContentType); + +/*! 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 ZSTD_DDict* ZSTD_initStaticDDict(void* workspace, size_t workspaceSize, - const void* dict, size_t dictSize, - ZSTD_dictLoadMethod_e dictLoadMethod); +ZSTDLIB_API size_t ZSTD_DCtx_setMaxWindowSize(ZSTD_DCtx* dctx, size_t maxWindowSize); -/*! 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_d_format + * experimental parameter, + * allowing selection between ZSTD_format_e input compression formats + */ +#define ZSTD_d_format ZSTD_d_experimentalParam1 +/* ZSTD_d_stableOutBuffer + * Experimental parameter. + * Default is 0 == disabled. Set to 1 to enable. + * + * Tells the decompressor that the ZSTD_outBuffer will ALWAYS be the same + * between calls, except for the modifications that zstd makes to pos (the + * caller must not modify pos). This is checked by the decompressor, and + * decompression will fail if it ever changes. Therefore the ZSTD_outBuffer + * MUST be large enough to fit the entire decompressed frame. This will be + * checked when the frame content size is known. The data in the ZSTD_outBuffer + * in the range [dst, dst + pos) MUST not be modified during decompression + * or you will get data corruption. + * + * When this flags is enabled zstd won't allocate an output buffer, because + * it can write directly to the ZSTD_outBuffer, but it will still allocate + * an input buffer large enough to fit any compressed block. This will also + * avoid the memcpy() from the internal output buffer to the ZSTD_outBuffer. + * If you need to avoid the input buffer allocation use the buffer-less + * streaming API. + * + * NOTE: So long as the ZSTD_outBuffer always points to valid memory, using + * this flag is ALWAYS memory safe, and will never access out-of-bounds + * memory. However, decompression WILL fail if you violate the preconditions. + * + * WARNING: The data in the ZSTD_outBuffer in the range [dst, dst + pos) MUST + * not be modified during decompression or you will get data corruption. This + * is because zstd needs to reference data in the ZSTD_outBuffer to regenerate + * matches. Normally zstd maintains its own buffer for this purpose, but passing + * this flag tells zstd to use the user provided buffer. + */ +#define ZSTD_d_stableOutBuffer ZSTD_d_experimentalParam2 -/*! 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_DCtx_setFormat() : + * 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_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_decompressStream_simpleArgs() : + * Same as ZSTD_decompressStream(), + * 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_decompressStream_simpleArgs ( + ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, size_t* dstPos, + const void* src, size_t srcSize, size_t* srcPos); /******************************************************************** * Advanced streaming functions +* Warning : most of these functions are now redundant with the Advanced API. +* Once Advanced API reaches "stable" status, +* redundant functions will be deprecated, and then at some point removed. ********************************************************************/ /*===== Advanced Streaming compression functions =====*/ -ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream_advanced(ZSTD_customMem customMem); -ZSTDLIB_API ZSTD_CStream* ZSTD_initStaticCStream(void* workspace, size_t workspaceSize); /**< same as ZSTD_initStaticCCtx() */ -ZSTDLIB_API size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize); /**< pledgedSrcSize must be correct, a size of 0 means unknown. for a frame size of 0 use initCStream_advanced */ -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 is optional and can be 0 (meaning unknown). note: if the contentSizeFlag is set, pledgedSrcSize == 0 means the source size is actually 0. 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 */ +/**! ZSTD_initCStream_srcSize() : + * 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); + * ZSTD_CCtx_setPledgedSrcSize(zcs, 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. + * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x + */ +ZSTDLIB_API 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: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel); + * ZSTD_CCtx_loadDictionary(zcs, dict, dictSize); + * + * 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_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 + */ +ZSTDLIB_API 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: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * // Pseudocode: Set each zstd parameter and leave the rest as-is. + * for ((param, value) : params) { + * ZSTD_CCtx_setParameter(zcs, param, value); + * } + * ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize); + * ZSTD_CCtx_loadDictionary(zcs, dict, dictSize); + * + * 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 + */ +ZSTDLIB_API 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: + * 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 + */ +ZSTDLIB_API 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: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * // Pseudocode: Set each zstd frame parameter and leave the rest as-is. + * for ((fParam, value) : fParams) { + * ZSTD_CCtx_setParameter(zcs, fParam, value); + * } + * ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize); + * ZSTD_CCtx_refCDict(zcs, cdict); + * + * 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 + */ +ZSTDLIB_API size_t +ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, + const ZSTD_CDict* cdict, + ZSTD_frameParameters fParams, + unsigned long long pledgedSrcSize); /*! 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.. + * This function is deprecated, and is equivalent to: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize); + * + * 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. * Note that zcs must be init at least once before using ZSTD_resetCStream(). - * pledgedSrcSize==0 means "srcSize unknown". + * 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. - * @return : 0, or an error code (which can be tested using ZSTD_isError()) */ + * 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 + */ ZSTDLIB_API size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize); +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. + */ +ZSTDLIB_API ZSTD_frameProgression ZSTD_getFrameProgression(const ZSTD_CCtx* cctx); + +/*! 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 flush speed is limited by production speed of oldest job + * irrespective of the speed of concurrent (and newer) jobs. + */ +ZSTDLIB_API size_t ZSTD_toFlushNow(ZSTD_CCtx* cctx); + + /*===== Advanced Streaming decompression functions =====*/ -typedef enum { DStream_p_maxWindowSize } ZSTD_DStreamParameter_e; -ZSTDLIB_API ZSTD_DStream* ZSTD_createDStream_advanced(ZSTD_customMem customMem); -ZSTDLIB_API ZSTD_DStream* ZSTD_initStaticDStream(void* workspace, size_t workspaceSize); /**< same as ZSTD_initStaticDCtx() */ -ZSTDLIB_API size_t ZSTD_setDStreamParameter(ZSTD_DStream* zds, ZSTD_DStreamParameter_e paramType, unsigned paramValue); -ZSTDLIB_API size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize); /**< note: a dict will not be used if dict == NULL or dictSize < 8 */ -ZSTDLIB_API size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* zds, const ZSTD_DDict* ddict); /**< note : ddict will just be referenced, and must outlive decompression session */ -ZSTDLIB_API size_t ZSTD_resetDStream(ZSTD_DStream* zds); /**< re-use decompression parameters from previous init; saves dictionary loading */ +/** + * This function is deprecated, and is equivalent to: + * + * ZSTD_DCtx_reset(zds, ZSTD_reset_session_only); + * ZSTD_DCtx_loadDictionary(zds, dict, dictSize); + * + * note: no dictionary will be used if dict == NULL or dictSize < 8 + * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x + */ +ZSTDLIB_API size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize); + +/** + * This function is deprecated, and is equivalent to: + * + * ZSTD_DCtx_reset(zds, ZSTD_reset_session_only); + * ZSTD_DCtx_refDDict(zds, ddict); + * + * note : ddict is referenced, it must outlive decompression session + * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x + */ +ZSTDLIB_API size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* zds, const ZSTD_DDict* ddict); + +/** + * This function is deprecated, and is equivalent to: + * + * ZSTD_DCtx_reset(zds, ZSTD_reset_session_only); + * + * re-use decompression parameters from previous init; saves dictionary loading + * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x + */ +ZSTDLIB_API size_t ZSTD_resetDStream(ZSTD_DStream* zds); /********************************************************************* * 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 many restrictions (documented below). -* Prefer using normal streaming API for an easier experience +* But it's also a complex one, with several restrictions, documented below. +* Prefer normal streaming API for an easier experience. ********************************************************************* */ /** @@ -778,8 +1904,8 @@ ZSTDLIB_API size_t ZSTD_resetDStream(ZSTD_DStream* zds); /**< re-use decompress 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 buffer only. - - Interface is synchronous : input is consumed entirely and produce 1+ (or more) compressed blocks. + - 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. @@ -790,18 +1916,18 @@ ZSTDLIB_API size_t ZSTD_resetDStream(ZSTD_DStream* zds); /**< re-use decompress 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 will be considered unfinished (corrupted) by decoders. + Without last block mark, frames are considered unfinished (hence corrupted) by compliant decoders. - `ZSTD_CCtx` object can be re-used (ZSTD_compressBegin()) to compress some new frame. + `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 is optional and can be 0 (meaning unknown). note: if the contentSizeFlag is set, pledgedSrcSize == 0 means the source size is actually 0 */ +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=0 means null-size */ -ZSTDLIB_API size_t ZSTD_copyCCtx(ZSTD_CCtx* cctx, const ZSTD_CCtx* preparedCCtx, unsigned long long pledgedSrcSize); /**< note: if pledgedSrcSize can be 0, indicating unknown size. if it is non-zero, it must be accurate. for 0 size frames, use compressBegin_advanced */ +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); @@ -891,7 +2017,17 @@ typedef struct { 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 */ +/*! ZSTD_getFrameHeader_advanced() : + * same as ZSTD_getFrameHeader(), + * with added capability to select a format (like ZSTD_f_zstd1_magicless) */ +ZSTDLIB_API size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize, ZSTD_format_e format); 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); @@ -908,306 +2044,15 @@ ZSTDLIB_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx); -/*=== New advanced API (experimental, and compression only) ===*/ - -/* notes on API design : - * In this proposal, parameters are pushed one by one into an existing CCtx, - * and then applied on all subsequent compression jobs. - * When no parameter is ever provided, CCtx is created with compression level ZSTD_CLEVEL_DEFAULT. - * - * This API is intended to replace all others experimental API. - * It can basically do all other use cases, and even new ones. - * It stands a good chance to become "stable", - * after a reasonable testing period. - */ - -/* note on naming convention : - * Initially, the API favored names like ZSTD_setCCtxParameter() . - * In this proposal, convention is changed towards ZSTD_CCtx_setParameter() . - * The main driver is that it identifies more clearly the target object type. - * It feels clearer in light of potential variants : - * ZSTD_CDict_setParameter() (rather than ZSTD_setCDictParameter()) - * ZSTD_DCtx_setParameter() (rather than ZSTD_setDCtxParameter() ) - * Left variant feels easier to distinguish. - */ - -/* note on enum design : - * All enum will be manually set to explicit values before reaching "stable API" status */ - -typedef enum { - /* 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 "do not change cLevel". */ - ZSTD_p_windowLog, /* 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 "do not change windowLog". */ - ZSTD_p_hashLog, /* Size of the probe table, as a power of 2. - * Resulting table size is (1 << (hashLog+2)). - * Must be clamped between ZSTD_HASHLOG_MIN and ZSTD_HASHLOG_MAX. - * Larger tables improve compression ratio of strategies <= dFast, - * and improve speed of strategies > dFast. - * Special: value 0 means "do not change hashLog". */ - ZSTD_p_chainLog, /* Size of the full-search table, as a power of 2. - * Resulting table size is (1 << (chainLog+2)). - * Larger tables result in better and slower compression. - * This parameter is useless when using "fast" strategy. - * Special: value 0 means "do not change chainLog". */ - ZSTD_p_searchLog, /* 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 "do not change searchLog". */ - ZSTD_p_minMatch, /* 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. - * Note that currently, for all strategies > fast, effective maximum is 6. - * Special: value 0 means "do not change minMatchLength". */ - ZSTD_p_targetLength, /* Only useful for strategies >= btopt. - * Length of Match considered "good enough" to stop search. - * Larger values make compression stronger and slower. - * Special: value 0 means "do not change targetLength". */ - ZSTD_p_compressionStrategy, /* 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 "do not change strategy". */ - - /* frame parameters */ - ZSTD_p_contentSizeFlag=200, /* Content size is written into frame header _whenever known_ (default:1) - * note that content size must be known at the beginning, - * it is sent using ZSTD_CCtx_setPledgedSrcSize() */ - 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) */ - - /* multi-threading parameters */ - ZSTD_p_nbThreads=400, /* Select how many threads a compression job can spawn (default:1) - * More threads improve speed, but also increase memory usage. - * Can only receive a value > 1 if ZSTD_MULTITHREAD is enabled. - * Special: value 0 means "do not change nbThreads" */ - ZSTD_p_jobSize, /* Size of a compression job. Each compression job is completed in parallel. - * 0 means default, which is dynamically determined based on compression parameters. - * Job size must be a minimum of overlapSize, or 1 KB, whichever is largest - * The minimum size is automatically and transparently enforced */ - ZSTD_p_overlapSizeLog, /* Size of previous input reloaded at the beginning of each job. - * 0 => no overlap, 6(default) => use 1/8th of windowSize, >=9 => use full windowSize */ - - /* advanced parameters - may not remain available after API update */ - ZSTD_p_forceMaxWindow=1100, /* Force back-reference distances to remain < windowSize, - * even when referencing into Dictionary content (default:0) */ - ZSTD_p_enableLongDistanceMatching=1200, /* Enable long distance matching. - * This parameter is designed to improve the compression - * ratio for large inputs with long distance matches. - * This increases the memory usage as well as window size. - * Note: setting this parameter sets all the LDM parameters - * as well as ZSTD_p_windowLog. It should be set after - * ZSTD_p_compressionLevel and before ZSTD_p_windowLog and - * other LDM parameters. Setting the compression level - * after this parameter overrides the window log, though LDM - * will remain enabled until explicitly disabled. */ - ZSTD_p_ldmHashLog, /* 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: 20). */ - ZSTD_p_ldmMinMatch, /* Minimum size of searched matches 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 (default: 64). */ - ZSTD_p_ldmBucketSizeLog, /* Log size of each bucket in the LDM hash table for collision resolution. - * Larger values usually improve collision resolution but may decrease - * compression speed. - * The maximum value is ZSTD_LDM_BUCKETSIZELOG_MAX (default: 3). */ - ZSTD_p_ldmHashEveryLog, /* Frequency of inserting/looking up entries in the LDM hash table. - * The default is MAX(0, (windowLog - ldmHashLog)) to - * optimize hash table usage. - * Larger values improve compression speed. Deviating far from the - * default value will likely result in a decrease in compression ratio. - * Must be clamped between 0 and ZSTD_WINDOWLOG_MAX - ZSTD_HASHLOG_MIN. */ - -} ZSTD_cParameter; - - -/*! ZSTD_CCtx_setParameter() : - * Set one compression parameter, selected by enum ZSTD_cParameter. - * Note : when `value` is an enum, cast it to unsigned for proper type checking. - * @result : 0, 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_CCtx_setPledgedSrcSize() : - * Total input data size to be compressed as a single frame. - * This value will be controlled at the end, and result in 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. - * Note that ZSTD_CONTENTSIZE_UNKNOWN is default value for new compression jobs. - * Note 2 : If all data is provided and consumed in a single round, - * this value is overriden by srcSize instead. */ -ZSTDLIB_API size_t ZSTD_CCtx_setPledgedSrcSize(ZSTD_CCtx* cctx, unsigned long long pledgedSrcSize); -/*! ZSTD_CCtx_loadDictionary() : - * Create an internal CDict from dict buffer. - * Decompression will have to use same buffer. - * @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 : `dict` content will be copied internally. Use - * ZSTD_CCtx_loadDictionary_byReference() to reference dictionary - * content instead. The dictionary buffer must then outlive its - * users. - * 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-heavy operation, with non-negligible impact on latency. - * Note 3 : Dictionary will be used for all future compression jobs. - * To return to "no-dictionary" situation, load a NULL dictionary - * Note 5 : Use ZSTD_CCtx_loadDictionary_advanced() to select how dictionary - * content will be interpreted. - */ -ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, size_t dictSize); -ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary_byReference(ZSTD_CCtx* cctx, const void* dict, size_t dictSize); -ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary_advanced(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod, ZSTD_dictMode_e dictMode); - - -/*! 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 supersede 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_CCtx_refPrefix() : - * 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 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. - * Note 3 : By default, the prefix is treated as raw content - * (ZSTD_dm_rawContent). Use ZSTD_CCtx_refPrefix_advanced() to alter - * dictMode. */ -ZSTDLIB_API size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize); -ZSTDLIB_API size_t ZSTD_CCtx_refPrefix_advanced(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize, ZSTD_dictMode_e dictMode); - - - -typedef enum { - ZSTD_e_continue=0, /* collect more data, encoder transparently decides when to output result, for optimal conditions */ - ZSTD_e_flush, /* flush any data provided so far - frame will continue, future data can still reference previous data for better compression */ - ZSTD_e_end /* flush any remaining data and ends current frame. Any future compression starts a new frame. */ -} ZSTD_EndDirective; - -/*! ZSTD_compress_generic() : - * Behave about the same as ZSTD_compressStream. To note : - * - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_setParameter() - * - Compression parameters cannot be changed once compression is started. - * - *dstPos must be <= dstCapacity, *srcPos must be <= srcSize - * - *dspPos and *srcPos will be updated. They are guaranteed to remain below their respective limit. - * - @return provides the minimum amount of data still to flush from internal buffers - * or an error code, which can be tested using ZSTD_isError(). - * if @return != 0, flush is not fully completed, there is some data left within internal buffers. - * - after a ZSTD_e_end directive, if internal buffer is not fully flushed, - * only ZSTD_e_end or ZSTD_e_flush operations are allowed. - * It is necessary to fully flush internal buffers - * before starting a new compression job, or changing compression parameters. - */ -ZSTDLIB_API size_t ZSTD_compress_generic (ZSTD_CCtx* cctx, - ZSTD_outBuffer* output, - ZSTD_inBuffer* input, - ZSTD_EndDirective endOp); - -/*! ZSTD_CCtx_reset() : - * Return a CCtx to clean state. - * Useful after an error, or to interrupt an ongoing compression job and start a new one. - * Any internal data not yet flushed is cancelled. - * Dictionary (if any) is dropped. - * It's possible to modify compression parameters after a reset. - */ -ZSTDLIB_API void ZSTD_CCtx_reset(ZSTD_CCtx* cctx); /* Not ready yet ! */ - - -/*! ZSTD_compress_generic_simpleArgs() : - * Same as ZSTD_compress_generic(), - * but using only integral types as arguments. - * Argument list is larger and less expressive than ZSTD_{in,out}Buffer, - * but can be helpful for binders from dynamic languages - * which have troubles handling structures containing memory pointers. - */ -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); - - -/** ZSTD_CCtx_params - * - * - ZSTD_createCCtxParams() : Create a ZSTD_CCtx_params structure - * - ZSTD_CCtxParam_setParameter() : Push parameters one by one into an - * existing ZSTD_CCtx_params structure. This is similar to - * ZSTD_CCtx_setParameter(). - * - ZSTD_CCtx_setParametersUsingCCtxParams() : Apply parameters to an existing CCtx. These - * parameters will be applied to all subsequent compression jobs. - * - ZSTD_compress_generic() : Do compression using the CCtx. - * - ZSTD_freeCCtxParams() : Free the memory. - * - * This can be used with ZSTD_estimateCCtxSize_opaque() for static allocation - * for single-threaded compression. - */ -ZSTDLIB_API ZSTD_CCtx_params* ZSTD_createCCtxParams(void); - -/*! ZSTD_resetCCtxParams() : - * Reset params to default, with the default compression level. - */ -ZSTDLIB_API size_t ZSTD_resetCCtxParams(ZSTD_CCtx_params* params); - -/*! ZSTD_initCCtxParams() : - * Initializes the compression parameters of cctxParams according to - * compression level. All other parameters are reset to their default values. - */ -ZSTDLIB_API size_t ZSTD_initCCtxParams(ZSTD_CCtx_params* cctxParams, int compressionLevel); - -/*! ZSTD_initCCtxParams_advanced() : - * Initializes the compression and frame parameters of cctxParams according to - * params. All other parameters are reset to their default values. - */ -ZSTDLIB_API size_t ZSTD_initCCtxParams_advanced(ZSTD_CCtx_params* cctxParams, ZSTD_parameters params); - -ZSTDLIB_API size_t ZSTD_freeCCtxParams(ZSTD_CCtx_params* params); - -/*! ZSTD_CCtxParam_setParameter() : - * Similar to ZSTD_CCtx_setParameter. - * Set one compression parameter, selected by enum ZSTD_cParameter. - * Parameters must be applied to a ZSTD_CCtx using ZSTD_CCtx_setParametersUsingCCtxParams(). - * Note : when `value` is an enum, cast it to unsigned for proper type checking. - * @result : 0, or an error code (which can be tested with ZSTD_isError()). - */ -ZSTDLIB_API size_t ZSTD_CCtxParam_setParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, unsigned value); - -/*! ZSTD_CCtx_setParametersUsingCCtxParams() : - * Apply a set of ZSTD_CCtx_params to the compression context. - * This must be done before the dictionary is loaded. - * The pledgedSrcSize is treated as unknown. - * Multithreading parameters are applied only if nbThreads > 1. - */ -ZSTDLIB_API size_t ZSTD_CCtx_setParametersUsingCCtxParams( - ZSTD_CCtx* cctx, const ZSTD_CCtx_params* params); - -/** - Block functions +/* ============================ */ +/** Block level API */ +/* ============================ */ +/*! Block functions produce and decode raw zstd blocks, without frame metadata. - Frame metadata cost is typically ~18 bytes, which can be non-negligible for very small blocks (< 100 bytes). - User will have to take in charge required information to regenerate data, such as compressed and content sizes. + Frame metadata cost is typically ~12 bytes, which can be non-negligible for very small blocks (< 100 bytes). + But users will have to take in charge needed metadata to regenerate data, such as compressed and content sizes. A few rules to respect : - Compressing and decompressing require a context structure @@ -1216,26 +2061,26 @@ ZSTDLIB_API size_t ZSTD_CCtx_setParametersUsingCCtxParams( + compression : any ZSTD_compressBegin*() variant, including with dictionary + decompression : any ZSTD_decompressBegin*() variant, including with dictionary + copyCCtx() and copyDCtx() can be used too - - Block size is limited, it must be <= ZSTD_getBlockSize() <= ZSTD_BLOCKSIZE_MAX + - Block size is limited, it must be <= ZSTD_getBlockSize() <= ZSTD_BLOCKSIZE_MAX == 128 KB + If input is larger than a block size, it's necessary to split input data into multiple blocks - + For inputs larger than a single block size, consider using the regular ZSTD_compress() instead. - Frame metadata is not that costly, and quickly becomes negligible as source size grows larger. - - When a block is considered not compressible enough, ZSTD_compressBlock() result will be zero. - In which case, nothing is produced into `dst`. - + User must test for such outcome and deal directly with uncompressed data - + ZSTD_decompressBlock() doesn't accept uncompressed data as input !!! + + For inputs larger than a single block, consider using regular ZSTD_compress() instead. + Frame metadata is not that costly, and quickly becomes negligible as source size grows larger than a block. + - When a block is considered not compressible enough, ZSTD_compressBlock() result will be 0 (zero) ! + ===> In which case, nothing is produced into `dst` ! + + User __must__ test for such outcome and deal directly with uncompressed data + + A block cannot be declared incompressible if ZSTD_compressBlock() return value was != 0. + Doing so would mess up with statistics history, leading to potential data corruption. + + ZSTD_decompressBlock() _doesn't accept uncompressed data as input_ !! + In case of multiple successive blocks, should some of them be uncompressed, decoder must be informed of their existence in order to follow proper history. Use ZSTD_insertBlock() for such a case. */ -#define ZSTD_BLOCKSIZELOG_MAX 17 -#define ZSTD_BLOCKSIZE_MAX (1<<ZSTD_BLOCKSIZELOG_MAX) /* define, for static allocation */ /*===== Raw zstd block functions =====*/ ZSTDLIB_API size_t ZSTD_getBlockSize (const ZSTD_CCtx* cctx); ZSTDLIB_API size_t ZSTD_compressBlock (ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); ZSTDLIB_API size_t ZSTD_decompressBlock(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); -ZSTDLIB_API size_t ZSTD_insertBlock(ZSTD_DCtx* dctx, const void* blockStart, size_t blockSize); /**< insert uncompressed block into `dctx` history. Useful for multi-blocks decompression */ +ZSTDLIB_API size_t ZSTD_insertBlock (ZSTD_DCtx* dctx, const void* blockStart, size_t blockSize); /**< insert uncompressed block into `dctx` history. Useful for multi-blocks decompression. */ #endif /* ZSTD_H_ZSTD_STATIC_LINKING_ONLY */ diff --git a/contrib/zstd/zstd_compress_superblock.h b/contrib/zstd/zstd_compress_superblock.h index 07f4cb1dc..35d207299 100644 --- a/contrib/zstd/zstd_compress_superblock.h +++ b/contrib/zstd/zstd_compress_superblock.h @@ -15,7 +15,7 @@ * Dependencies ***************************************/ -#include "../zstd.h" /* ZSTD_CCtx */ +#include "zstd.h" /* ZSTD_CCtx */ /*-************************************* * Target Compressed Block Size diff --git a/contrib/zstd/zstd_ddict.h b/contrib/zstd/zstd_ddict.h index af307efd3..3ab7532ee 100644 --- a/contrib/zstd/zstd_ddict.h +++ b/contrib/zstd/zstd_ddict.h @@ -16,7 +16,7 @@ * Dependencies *********************************************************/ #include <stddef.h> /* size_t */ -#include "../zstd.h" /* ZSTD_DDict, and several public functions */ +#include "zstd.h" /* ZSTD_DDict, and several public functions */ /*-******************************************************* diff --git a/contrib/zstd/zstd_internal.h b/contrib/zstd/zstd_internal.h index ea3d61837..d45e88257 100644 --- a/contrib/zstd/zstd_internal.h +++ b/contrib/zstd/zstd_internal.h @@ -29,7 +29,7 @@ #ifndef ZSTD_STATIC_LINKING_ONLY #define ZSTD_STATIC_LINKING_ONLY #endif -#include "../zstd.h" +#include "zstd.h" #define FSE_STATIC_LINKING_ONLY #include "fse.h" #define HUF_STATIC_LINKING_ONLY diff --git a/contrib/zstd/zstd_ldm.h b/contrib/zstd/zstd_ldm.h index 229ea05a9..aa2b6c52e 100644 --- a/contrib/zstd/zstd_ldm.h +++ b/contrib/zstd/zstd_ldm.h @@ -16,7 +16,7 @@ extern "C" { #endif #include "zstd_compress_internal.h" /* ldmParams_t, U32 */ -#include "../zstd.h" /* ZSTD_CCtx, size_t */ +#include "zstd.h" /* ZSTD_CCtx, size_t */ /*-************************************* * Long distance matching |