diff options
Diffstat (limited to 'Utilities/cmzstd/lib/zstd.h')
| -rw-r--r-- | Utilities/cmzstd/lib/zstd.h | 1298 |
1 files changed, 811 insertions, 487 deletions
diff --git a/Utilities/cmzstd/lib/zstd.h b/Utilities/cmzstd/lib/zstd.h index b18fc8a..8c6fc6a 100644 --- a/Utilities/cmzstd/lib/zstd.h +++ b/Utilities/cmzstd/lib/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 */ @@ -70,8 +71,8 @@ extern "C" { /*------ Version ------*/ #define ZSTD_VERSION_MAJOR 1 -#define ZSTD_VERSION_MINOR 3 -#define ZSTD_VERSION_RELEASE 8 +#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); /**< to check runtime library version */ @@ -82,13 +83,28 @@ ZSTDLIB_API unsigned ZSTD_versionNumber(void); /**< to check runtime library v #define ZSTD_VERSION_STRING ZSTD_EXPAND_AND_QUOTE(ZSTD_LIB_VERSION) ZSTDLIB_API const char* ZSTD_versionString(void); /* requires v1.3.0+ */ -/*************************************** -* Default constant -***************************************/ +/* ************************************* + * 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) + + + /*************************************** * Simple API ***************************************/ @@ -145,12 +161,21 @@ ZSTDLIB_API unsigned long long ZSTD_getFrameContentSize(const void *src, size_t * @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 ======*/ #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 */ @@ -159,17 +184,26 @@ ZSTDLIB_API int ZSTD_maxCLevel(void); /*!< maximum compres ***************************************/ /*= 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(), using an explicit ZSTD_CCtx - * The function will compress at requested compression level, - * ignoring any other parameter */ + * 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, @@ -195,279 +229,6 @@ ZSTDLIB_API size_t ZSTD_decompressDCtx(ZSTD_DCtx* dctx, const void* src, size_t srcSize); -/************************** -* 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); - - -/*********************************** - * Bulk processing dictionary API - **********************************/ -typedef struct ZSTD_CDict_s ZSTD_CDict; - -/*! ZSTD_createCDict() : - * When compressing multiple messages / blocks using the same dictionary, it's recommended to load it only once. - * ZSTD_createCDict() will create a digested dictionary, ready to start future compression operations without 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. - * Consider experimental function `ZSTD_createCDict_byReference()` if you prefer to not duplicate `dictBuffer` content. - * Note : A ZSTD_CDict can be created from an empty dictBuffer, but it is inefficient when used to compress small data. */ -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); - - -/**************************** -* Streaming -****************************/ - -typedef struct ZSTD_inBuffer_s { - const void* src; /**< start of input buffer */ - size_t size; /**< size of input buffer */ - size_t pos; /**< position where reading stopped. Will be updated. Necessarily 0 <= pos <= size */ -} ZSTD_inBuffer; - -typedef struct ZSTD_outBuffer_s { - void* dst; /**< start of output buffer */ - size_t size; /**< size of output buffer */ - size_t pos; /**< position where writing stopped. Will be updated. Necessarily 0 <= pos <= size */ -} ZSTD_outBuffer; - - - -/*-*********************************************************************** -* Streaming compression - HowTo -* -* 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 since it will play nicer with system's memory, by re-using already allocated memory. -* -* For parallel execution, use one separate ZSTD_CStream per thread. -* -* note : since v1.3.0, ZSTD_CStream and ZSTD_CCtx are the same thing. -* -* 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_initCStream() to set the parameter to a selected compression level. -* Use advanced API (ZSTD_CCtx_setParameter(), etc.) to set more specific parameters. -* -* Use ZSTD_compressStream() 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. -* @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 value will work fine. -* Note 2 : size hint is guaranteed to be <= ZSTD_CStreamInSize() -* -* At any moment, it's possible to flush whatever data might remain stuck within internal buffer, -* using ZSTD_flushStream(). `output->pos` will be updated. -* Note that, if `output->size` is too small, a single invocation of ZSTD_flushStream() might not be enough (return code > 0). -* In which case, make some room to receive more compressed data, and call again ZSTD_flushStream(). -* @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. -* It will perform a flush and write frame epilogue. -* The epilogue is required for decoders to consider a frame completed. -* flush() operation is the same, and follows same rules as ZSTD_flushStream(). -* @return : 0 if frame fully completed and fully 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(). -* -* *******************************************************************/ - -typedef ZSTD_CCtx ZSTD_CStream; /**< CCtx and CStream are now effectively same object (>= v1.3.0) */ - /* 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 =====*/ -ZSTDLIB_API size_t ZSTD_initCStream(ZSTD_CStream* zcs, int compressionLevel); -ZSTDLIB_API size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input); -ZSTDLIB_API size_t ZSTD_flushStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output); -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 -* -* A ZSTD_DStream object is required to track streaming operations. -* 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. -* @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. -* 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) */ - /* 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 =====*/ -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 */ - - - - -/**************************************************************************************** - * 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 - - -/**************************************************************************************** - * Candidate API for promotion to stable status - **************************************************************************************** - * The following symbols and constants form the "staging area" : - * they are considered to join "stable API" by v1.4.0. - * The proposal is written so that it can be made stable "as is", - * though it's still possible to suggest improvements. - * Staging is in fact last chance for changes, - * the API is locked once reaching "stable" status. - * ***************************************************************************************/ - - -/* === 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) - - -/* === query limits === */ - -ZSTDLIB_API int ZSTD_minCLevel(void); /*!< minimum negative compression level allowed */ - - -/* === frame size === */ - -/*! 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); - - -/* === 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); - - /*************************************** * Advanced compression API ***************************************/ @@ -477,7 +238,7 @@ ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict); * 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() + * __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(). * @@ -503,17 +264,31 @@ typedef enum { ZSTD_fast=1, typedef enum { - /* compression parameters */ - ZSTD_c_compressionLevel=100, /* Update all compression parameters according to pre-defined cLevel table + /* 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 sets all default values of other compression parameters */ + * 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 window size at decompression stage if using streaming. */ + * 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. @@ -524,13 +299,13 @@ typedef enum { * 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 when using "fast" strategy. + * 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 when using "fast" and "dFast" strategies. + * 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, @@ -585,7 +360,7 @@ typedef enum { 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 variants, content size must be provided with ZSTD_CCtx_setPledgedSrcSize() */ + * 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) */ @@ -604,7 +379,7 @@ typedef enum { * 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 */ + * 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. @@ -625,6 +400,9 @@ typedef enum { * 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. @@ -632,10 +410,12 @@ typedef enum { ZSTD_c_experimentalParam1=500, ZSTD_c_experimentalParam2=10, ZSTD_c_experimentalParam3=1000, - ZSTD_c_experimentalParam4=1001 + ZSTD_c_experimentalParam4=1001, + ZSTD_c_experimentalParam5=1002, + ZSTD_c_experimentalParam6=1003, + ZSTD_c_experimentalParam7=1004 } ZSTD_cParameter; - typedef struct { size_t error; int lowerBound; @@ -677,63 +457,10 @@ ZSTDLIB_API size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param * 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 overriden by srcSize instead. + * this value is automatically overridden 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 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 supercede any compression parameter previously set within CCtx. - * 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_dm_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); - - typedef enum { ZSTD_reset_session_only = 1, ZSTD_reset_parameters = 2, @@ -756,8 +483,6 @@ typedef enum { */ 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. @@ -772,23 +497,173 @@ ZSTDLIB_API size_t ZSTD_compress2( ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); + +/*************************************** +* 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); + + +/**************************** +* Streaming +****************************/ + +typedef struct ZSTD_inBuffer_s { + const void* src; /**< start of input buffer */ + size_t size; /**< size of input buffer */ + size_t pos; /**< position where reading stopped. Will be updated. Necessarily 0 <= pos <= size */ +} ZSTD_inBuffer; + +typedef struct ZSTD_outBuffer_s { + void* dst; /**< start of output buffer */ + size_t size; /**< size of output buffer */ + size_t pos; /**< position where writing stopped. Will be updated. Necessarily 0 <= pos <= size */ +} ZSTD_outBuffer; + + + +/*-*********************************************************************** +* Streaming compression - HowTo +* +* 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 since it will play nicer with system's memory, by re-using already allocated memory. +* +* For parallel execution, use one separate ZSTD_CStream per thread. +* +* note : since v1.3.0, ZSTD_CStream and ZSTD_CCtx are the same thing. +* +* 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(). +* +* 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. +* 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, +* >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 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. */ + * 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 : 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) - * - outpot->pos must be <= dstCapacity, input->pos must be <= srcSize - * - outpot->pos and input->pos will be updated. They are guaranteed to remain below their respective limit. + * - 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. @@ -810,58 +685,275 @@ ZSTDLIB_API size_t ZSTD_compressStream2( ZSTD_CCtx* cctx, 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. */ -/* ============================== */ -/* 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. +/* ***************************************************************************** + * 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); -typedef enum { +/*-*************************************************************************** +* Streaming decompression - HowTo +* +* A ZSTD_DStream object is required to track streaming operations. +* 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. +* @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. +* 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. +* *******************************************************************************/ - 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) */ +typedef ZSTD_DCtx ZSTD_DStream; /**< DCtx and DStream are now effectively same object (>= v1.3.0) */ + /* 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); - /* note : additional experimental parameters are also available - * within the experimental section of the API. - * At the time of this writing, they include : - * ZSTD_c_format - * 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 +/*===== Streaming decompression functions =====*/ -} ZSTD_dParameter; +/* 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); -/*! 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); +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. */ + + +/************************** +* 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); + + +/*********************************** + * 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); -/*! 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); +/******************************** + * 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, @@ -902,7 +994,7 @@ ZSTDLIB_API size_t ZSTD_DCtx_refDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict); * 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_dm_rawContent). + * 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. @@ -910,16 +1002,33 @@ ZSTDLIB_API size_t ZSTD_DCtx_refDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict); ZSTDLIB_API size_t ZSTD_DCtx_refPrefix(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSize); -/*! ZSTD_DCtx_reset() : - * Return a DCtx to clean state. - * 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); +/* === 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 + /**************************************************************************************** * experimental API (static linking only) **************************************************************************************** @@ -930,8 +1039,8 @@ ZSTDLIB_API size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset); * Some of them might be removed in the future (especially when redundant with existing stable functions) * ***************************************************************************************/ -#define ZSTD_FRAMEHEADERSIZE_PREFIX 5 /* minimum input size required to query frame header size */ -#define ZSTD_FRAMEHEADERSIZE_MIN 6 +#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 @@ -962,7 +1071,7 @@ ZSTDLIB_API size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset); #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 overriden using ZSTD_DCtx_setParameter(,ZSTD_d_windowLogMax,). + * 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 */ @@ -976,6 +1085,12 @@ ZSTDLIB_API size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset); #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 @@ -985,6 +1100,24 @@ ZSTDLIB_API size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset); 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 */ @@ -1013,21 +1146,12 @@ typedef enum { 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_dlm_byRef = 1 /**< Reference dictionary content -- the dictionary buffer must outlive its users. */ } ZSTD_dictLoadMethod_e; typedef enum { - /* Opened question : should we have a format ZSTD_f_auto ? - * Today, it would mean exactly the same as ZSTD_f_zstd1. - * But, in the future, should several formats become supported, - * on the compression side, it would mean "default format". - * On the decompression side, it would mean "automatic format detection", - * so that ZSTD_f_zstd1 would mean "accept *only* zstd frames". - * Since meaning is a little different, another option could be to define different enums for compression and decompression. - * This question could be kept for later, when there are actually multiple formats to support, - * but there is also the question of pinning enum values, and pinning value `0` is especially important */ 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. + 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; @@ -1038,7 +1162,7 @@ typedef enum { * to evolve and should be considered only in the context of extremely * advanced performance tuning. * - * Zstd currently supports the use of a CDict in two ways: + * 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 @@ -1054,6 +1178,12 @@ typedef enum { * 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 @@ -1062,17 +1192,27 @@ typedef 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_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 @@ -1092,12 +1232,36 @@ typedef enum { * 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() : * 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); + /*************************************** * Memory management @@ -1106,12 +1270,26 @@ ZSTDLIB_API size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize); /*! ZSTD_estimate*() : * These functions make it possible to estimate memory usage * of a future {D,C}Ctx, before its creation. - * ZSTD_estimateCCtxSize() will provide a budget large enough for any compression level up to selected one. - * It will also consider src size to be arbitrarily "large", which is worst case. - * If srcSize is known to always be small, ZSTD_estimateCCtxSize_usingCParams() can provide a tighter estimation. - * ZSTD_estimateCCtxSize_usingCParams() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel. - * ZSTD_estimateCCtxSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParam_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1. - * Note : CCtx size 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_usingCParams(ZSTD_compressionParameters cParams); ZSTDLIB_API size_t ZSTD_estimateCCtxSize_usingCCtxParams(const ZSTD_CCtx_params* params); @@ -1122,7 +1300,7 @@ ZSTDLIB_API size_t ZSTD_estimateDCtxSize(void); * It will also consider src size to be arbitrarily "large", which is worst case. * If srcSize is known to always be small, ZSTD_estimateCStreamSize_usingCParams() can provide a tighter estimation. * ZSTD_estimateCStreamSize_usingCParams() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel. - * ZSTD_estimateCStreamSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParam_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1. + * 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, @@ -1222,30 +1400,37 @@ ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_advanced(const void* dict, size_t dictS * 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. */ + * 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 : contentSize=1, checksum=0, noDictID=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 compression parameters (by structure) */ + * 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, @@ -1253,7 +1438,9 @@ ZSTDLIB_API size_t ZSTD_compress_advanced(ZSTD_CCtx* cctx, 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, @@ -1314,6 +1501,23 @@ ZSTDLIB_API size_t ZSTD_CCtx_refPrefix_advanced(ZSTD_CCtx* cctx, const void* pre * 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. @@ -1325,10 +1529,10 @@ ZSTDLIB_API size_t ZSTD_CCtx_getParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param /*! ZSTD_CCtx_params : * Quick howto : * - 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_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 @@ -1359,20 +1563,20 @@ ZSTDLIB_API size_t ZSTD_CCtxParams_init(ZSTD_CCtx_params* cctxParams, int compre */ ZSTDLIB_API size_t ZSTD_CCtxParams_init_advanced(ZSTD_CCtx_params* cctxParams, ZSTD_parameters params); -/*! ZSTD_CCtxParam_setParameter() : +/*! 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_CCtxParam_setParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int value); +ZSTDLIB_API size_t ZSTD_CCtxParams_setParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int value); -/*! ZSTD_CCtxParam_getParameter() : +/*! 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_CCtxParam_getParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int* value); +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. @@ -1415,31 +1619,6 @@ ZSTDLIB_API unsigned ZSTD_isFrame(const void* buffer, size_t size); * it must remain read accessible throughout the lifetime of DDict */ ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, size_t dictSize); - -/*! 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); - /*! ZSTD_DCtx_loadDictionary_byReference() : * Same as ZSTD_DCtx_loadDictionary(), * but references `dict` content instead of copying it into `dctx`. @@ -1473,6 +1652,37 @@ ZSTDLIB_API size_t ZSTD_DCtx_setMaxWindowSize(ZSTD_DCtx* dctx, size_t maxWindowS * 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_DCtx_setFormat() : * Instruct the decoder context about what kind of data to decode next. @@ -1501,14 +1711,97 @@ ZSTDLIB_API size_t ZSTD_decompressStream_simpleArgs ( ********************************************************************/ /*===== Advanced Streaming compression functions =====*/ -ZSTDLIB_API size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize); /**< pledgedSrcSize must be correct. If it is not known at init time, use ZSTD_CONTENTSIZE_UNKNOWN. Note that, for compatibility with older programs, "0" also disables frame content size field. It may be enabled in the future. */ -ZSTDLIB_API size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel); /**< creates of an internal CDict (incompatible with static CCtx), except if dict == NULL or dictSize < 8, in which case no dict is used. Note: dict is loaded with ZSTD_dm_auto (treated as a full zstd dictionary if it begins with ZSTD_MAGIC_DICTIONARY, else as raw content) and ZSTD_dlm_byCopy.*/ -ZSTDLIB_API size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, const void* dict, size_t dictSize, - ZSTD_parameters params, unsigned long long pledgedSrcSize); /**< pledgedSrcSize must be correct. If srcSize is not known at init time, use value ZSTD_CONTENTSIZE_UNKNOWN. dict is loaded with ZSTD_dm_auto and ZSTD_dlm_byCopy. */ -ZSTDLIB_API size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict); /**< note : cdict will just be referenced, and must outlive compression session */ -ZSTDLIB_API size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict* cdict, ZSTD_frameParameters fParams, unsigned long long pledgedSrcSize); /**< same as ZSTD_initCStream_usingCDict(), with control over frame parameters. pledgedSrcSize must be correct. If srcSize is not known at init time, use value ZSTD_CONTENTSIZE_UNKNOWN. */ +/**! 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() : + * 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(). @@ -1517,6 +1810,7 @@ ZSTDLIB_API size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const * 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); @@ -1555,9 +1849,37 @@ ZSTDLIB_API size_t ZSTD_toFlushNow(ZSTD_CCtx* cctx); /*===== Advanced Streaming decompression functions =====*/ -ZSTDLIB_API size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize); /**< note: no dictionary will be used if dict == NULL or dictSize < 8 */ -ZSTDLIB_API size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* zds, const ZSTD_DDict* ddict); /**< note : ddict is referenced, it must outlive decompression session */ -ZSTDLIB_API size_t ZSTD_resetDStream(ZSTD_DStream* zds); /**< re-use decompression parameters from previous init; saves dictionary loading */ +/** + * 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); /********************************************************************* @@ -1696,7 +2018,7 @@ typedef struct { unsigned checksumFlag; } ZSTD_frameHeader; -/** ZSTD_getFrameHeader() : +/*! 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, @@ -1729,8 +2051,8 @@ ZSTDLIB_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx); /*! 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 @@ -1741,12 +2063,14 @@ ZSTDLIB_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx); + copyCCtx() and copyDCtx() can be used too - 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, really consider using 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. |