From 0827edeace3fbc5de0d944688a5cc424e6011dd1 Mon Sep 17 00:00:00 2001 From: Nick Terrell Date: Mon, 1 Apr 2019 18:43:32 -0700 Subject: [PATCH 1/4] [libzstd] Bump the library version to 1.4.0 Bumps the library version to 1.4.0 in preparation to stabilize the advanced API. --- lib/zstd.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/zstd.h b/lib/zstd.h index acc535cff..667d8142d 100644 --- a/lib/zstd.h +++ b/lib/zstd.h @@ -70,8 +70,8 @@ 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 0 #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 */ From d7d89513d6a216cfa920208ce82f9128616bab7c Mon Sep 17 00:00:00 2001 From: Nick Terrell Date: Thu, 28 Mar 2019 19:04:32 -0600 Subject: [PATCH 2/4] Stabilize advance API This commit moves the candidate advanced API to the stable section. It makes some minor whitespace changes, but it doesn't change any of the wording of the documentation. I'll put up a separate PR that tweaks some of the documentation once this lands, so that it is easier to review. NOTE: Even though these functions are now in stable, they aren't stable until the next release (in under 1 month). It is possible that they change until then. --- lib/zstd.h | 486 +++++++++++++++++++++++++---------------------------- 1 file changed, 228 insertions(+), 258 deletions(-) diff --git a/lib/zstd.h b/lib/zstd.h index 667d8142d..91956a739 100644 --- a/lib/zstd.h +++ b/lib/zstd.h @@ -89,6 +89,21 @@ ZSTDLIB_API const char* ZSTD_versionString(void); /* requires v1.3.0+ */ # 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<= 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 */ @@ -273,216 +297,6 @@ ZSTDLIB_API size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx, 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 =====*/ -/** - * 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 number of bytes left to flush (if non-zero and not an error). - */ -ZSTDLIB_API size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input); -/** Equivalent to ZSTD_compressStream2(zcs, output, &emptyInput, ZSTD_e_flush). */ -ZSTDLIB_API size_t ZSTD_flushStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output); -/** Equivalent to ZSTD_compressStream2(zcs, output, &emptyInput, ZSTD_e_end). */ -ZSTDLIB_API size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output); - -ZSTDLIB_API size_t ZSTD_CStreamInSize(void); /**< recommended size for input buffer */ -ZSTDLIB_API size_t ZSTD_CStreamOutSize(void); /**< recommended size for output buffer. Guarantee to successfully flush at least one complete compressed block in all circumstances. */ - - - -/*-*************************************************************************** -* Streaming decompression - HowTo -* -* 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<= 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 ***************************************/ @@ -655,7 +469,6 @@ typedef enum { ZSTD_c_experimentalParam5=1002, } ZSTD_cParameter; - typedef struct { size_t error; int lowerBound; @@ -755,7 +568,6 @@ ZSTDLIB_API size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict); 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, @@ -778,8 +590,6 @@ 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. @@ -794,48 +604,10 @@ ZSTDLIB_API size_t ZSTD_compress2( ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); -typedef enum { - ZSTD_e_continue=0, /* collect more data, encoder decides when to output compressed result, for optimal compression ratio */ - ZSTD_e_flush=1, /* flush any data provided so far, - * it creates (at least) one new block, that can be decoded immediately on reception; - * frame will continue: any future data can still reference previously compressed data, improving compression. */ - ZSTD_e_end=2 /* flush any remaining data _and_ close current frame. - * 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). */ -} 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. - * - When nbWorkers==0 (default), function is blocking : it completes its job before returning to caller. - * - When nbWorkers>=1, function is non-blocking : it just acquires a copy of input, and distributes jobs to internal worker threads, flush whatever is available, - * and then immediately returns, just indicating that there is some data remaining to be flushed. - * The function nonetheless guarantees forward progress : it will return only after it reads or write at least 1+ byte. - * - Exception : if the first call requests a ZSTD_e_end directive and provides enough dstCapacity, the function delegates to ZSTD_compress2() which is always blocking. - * - @return provides a minimum amount of data remaining to be flushed from internal buffers - * or an error code, which can be tested using ZSTD_isError(). - * if @return != 0, flush is not fully completed, there is still some data left within internal buffers. - * This is useful for ZSTD_e_flush, since in this case more flushes are necessary to empty all buffers. - * For ZSTD_e_end, @return == 0 when internal buffers are fully flushed and frame is completed. - * - after a ZSTD_e_end directive, if internal buffer is not fully flushed (@return != 0), - * only ZSTD_e_end or ZSTD_e_flush operations are allowed. - * Before starting a new compression job, or changing compression parameters, - * it is required to fully flush internal buffers. - */ -ZSTDLIB_API size_t ZSTD_compressStream2( ZSTD_CCtx* cctx, - ZSTD_outBuffer* output, - ZSTD_inBuffer* input, - ZSTD_EndDirective endOp); - - - -/* ============================== */ -/* Advanced decompression API */ -/* ============================== */ +/*************************************** +* 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 @@ -845,7 +617,6 @@ ZSTDLIB_API size_t ZSTD_compressStream2( ZSTD_CCtx* cctx, * Therefore, no new decompression function is necessary. */ - typedef enum { ZSTD_d_windowLogMax=100, /* Select a size limit (in power of 2) beyond which @@ -866,7 +637,6 @@ typedef enum { } 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. @@ -885,7 +655,6 @@ ZSTDLIB_API ZSTD_bounds ZSTD_dParam_getBounds(ZSTD_dParameter dParam); */ ZSTDLIB_API size_t ZSTD_DCtx_setParameter(ZSTD_DCtx* dctx, ZSTD_dParameter param, int value); - /*! ZSTD_DCtx_loadDictionary() : * Create an internal DDict from dict buffer, * to be used to decompress next frames. @@ -942,6 +711,207 @@ ZSTDLIB_API size_t ZSTD_DCtx_refPrefix(ZSTD_DCtx* dctx, 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_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 =====*/ +typedef enum { + ZSTD_e_continue=0, /* collect more data, encoder decides when to output compressed result, for optimal compression ratio */ + ZSTD_e_flush=1, /* flush any data provided so far, + * it creates (at least) one new block, that can be decoded immediately on reception; + * frame will continue: any future data can still reference previously compressed data, improving compression. */ + ZSTD_e_end=2 /* flush any remaining data _and_ close current frame. + * 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). */ +} 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. + * - When nbWorkers==0 (default), function is blocking : it completes its job before returning to caller. + * - When nbWorkers>=1, function is non-blocking : it just acquires a copy of input, and distributes jobs to internal worker threads, flush whatever is available, + * and then immediately returns, just indicating that there is some data remaining to be flushed. + * The function nonetheless guarantees forward progress : it will return only after it reads or write at least 1+ byte. + * - Exception : if the first call requests a ZSTD_e_end directive and provides enough dstCapacity, the function delegates to ZSTD_compress2() which is always blocking. + * - @return provides a minimum amount of data remaining to be flushed from internal buffers + * or an error code, which can be tested using ZSTD_isError(). + * if @return != 0, flush is not fully completed, there is still some data left within internal buffers. + * This is useful for ZSTD_e_flush, since in this case more flushes are necessary to empty all buffers. + * For ZSTD_e_end, @return == 0 when internal buffers are fully flushed and frame is completed. + * - after a ZSTD_e_end directive, if internal buffer is not fully flushed (@return != 0), + * only ZSTD_e_end or ZSTD_e_flush operations are allowed. + * Before starting a new compression job, or changing compression parameters, + * it is required to fully flush internal buffers. + */ +ZSTDLIB_API size_t ZSTD_compressStream2( ZSTD_CCtx* cctx, + ZSTD_outBuffer* output, + ZSTD_inBuffer* input, + ZSTD_EndDirective endOp); + +/** + * 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 number of bytes left to flush (if non-zero and not an error). + */ +ZSTDLIB_API size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input); +/** Equivalent to ZSTD_compressStream2(zcs, output, &emptyInput, ZSTD_e_flush). */ +ZSTDLIB_API size_t ZSTD_flushStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output); +/** Equivalent to ZSTD_compressStream2(zcs, output, &emptyInput, ZSTD_e_end). */ +ZSTDLIB_API size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output); + +ZSTDLIB_API size_t ZSTD_CStreamInSize(void); /**< recommended size for input buffer */ +ZSTDLIB_API size_t ZSTD_CStreamOutSize(void); /**< recommended size for output buffer. Guarantee to successfully flush at least one complete compressed block in all circumstances. */ + + +/*-*************************************************************************** +* Streaming decompression - HowTo +* +* 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. */ + +/* === 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) From cf7d601bf583e56baff75f624753a586a9498250 Mon Sep 17 00:00:00 2001 From: Nick Terrell Date: Wed, 3 Apr 2019 19:01:51 -0700 Subject: [PATCH 3/4] Move the dictionary API and mark the legacy API * Move the dictionary API below the streaming API * Mark the legacy streaming API as redundant --- lib/zstd.h | 382 ++++++++++++++++++++++++++++------------------------- 1 file changed, 200 insertions(+), 182 deletions(-) diff --git a/lib/zstd.h b/lib/zstd.h index 91956a739..4e6791560 100644 --- a/lib/zstd.h +++ b/lib/zstd.h @@ -219,84 +219,6 @@ 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); - - /*************************************** * Advanced compression API ***************************************/ @@ -514,60 +436,6 @@ ZSTDLIB_API size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param */ 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 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_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, @@ -655,53 +523,6 @@ ZSTDLIB_API ZSTD_bounds ZSTD_dParam_getBounds(ZSTD_dParameter dParam); */ ZSTDLIB_API size_t ZSTD_DCtx_setParameter(ZSTD_DCtx* dctx, ZSTD_dParameter param, int value); -/*! ZSTD_DCtx_loadDictionary() : - * Create an internal DDict from dict buffer, - * to be used to decompress next frames. - * The dictionary remains valid for all future frames, until explicitly invalidated. - * @result : 0, or an error code (which can be tested with ZSTD_isError()). - * Special : Adding a NULL (or 0-size) dictionary invalidates any previous dictionary, - * meaning "return to no-dictionary mode". - * Note 1 : Loading a dictionary involves building tables, - * which has a non-negligible impact on CPU usage and latency. - * It's recommended to "load once, use many times", to amortize the cost - * Note 2 :`dict` content will be copied internally, so `dict` can be released after loading. - * Use ZSTD_DCtx_loadDictionary_byReference() to reference dictionary content instead. - * Note 3 : Use ZSTD_DCtx_loadDictionary_advanced() to take control of - * how dictionary content is loaded and interpreted. - */ -ZSTDLIB_API size_t ZSTD_DCtx_loadDictionary(ZSTD_DCtx* dctx, const void* dict, size_t dictSize); - -/*! ZSTD_DCtx_refDDict() : - * Reference a prepared dictionary, to be used to decompress next frames. - * The dictionary remains active for decompression of future frames using same DCtx. - * @result : 0, or an error code (which can be tested with ZSTD_isError()). - * Note 1 : Currently, only one dictionary can be managed. - * Referencing a new dictionary effectively "discards" any previous one. - * Special: referencing a NULL DDict means "return to no-dictionary mode". - * Note 2 : DDict is just referenced, its lifetime must outlive its usage from DCtx. - */ -ZSTDLIB_API size_t ZSTD_DCtx_refDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict); - -/*! ZSTD_DCtx_refPrefix() : - * Reference a prefix (single-usage dictionary) to decompress next frame. - * This is the reverse operation of ZSTD_CCtx_refPrefix(), - * and must use the same prefix as the one used during compression. - * Prefix is **only used once**. Reference is discarded at end of frame. - * End of frame is reached when ZSTD_decompressStream() returns 0. - * @result : 0, or an error code (which can be tested with ZSTD_isError()). - * Note 1 : Adding any prefix (including NULL) invalidates any previously set prefix or dictionary - * Note 2 : Prefix buffer is referenced. It **must** outlive decompression. - * Prefix buffer must remain unmodified up to the end of frame, - * reached when ZSTD_decompressStream() returns 0. - * Note 3 : By default, the prefix is treated as raw content (ZSTD_dm_rawContent). - * Use ZSTD_CCtx_refPrefix_advanced() to alter dictMode (Experimental section) - * Note 4 : Referencing a raw content prefix has almost no cpu nor memory cost. - * A full dictionary is more costly, as it requires building tables. - */ -ZSTDLIB_API size_t ZSTD_DCtx_refPrefix(ZSTD_DCtx* dctx, - const void* prefix, size_t prefixSize); - /*! ZSTD_DCtx_reset() : * Return a DCtx to clean state. * Session and parameters can be reset jointly or separately. @@ -822,6 +643,16 @@ ZSTDLIB_API size_t ZSTD_compressStream2( ZSTD_CCtx* cctx, ZSTD_inBuffer* input, ZSTD_EndDirective endOp); +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. */ + +/******************************************************************************* + * This is a legacy streaming API, and can be replaced by ZSTD_CCtx_reset() and + * ZSTD_compressStream2(). It is redundent, but is still fully supported. + * Advanced parameters and dictionary compression can only be used through the + * new API. + ******************************************************************************/ + /** * Equivalent to: * @@ -842,9 +673,6 @@ ZSTDLIB_API size_t ZSTD_flushStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output); /** Equivalent to ZSTD_compressStream2(zcs, output, &emptyInput, ZSTD_e_end). */ ZSTDLIB_API size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output); -ZSTDLIB_API size_t ZSTD_CStreamInSize(void); /**< recommended size for input buffer */ -ZSTDLIB_API size_t ZSTD_CStreamOutSize(void); /**< recommended size for output buffer. Guarantee to successfully flush at least one complete compressed block in all circumstances. */ - /*-*************************************************************************** * Streaming decompression - HowTo @@ -886,6 +714,196 @@ ZSTDLIB_API size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* outp 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 / 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); + + +/******************************************************************************* + * 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_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); + +/*! ZSTD_DCtx_loadDictionary() : + * Create an internal DDict from dict buffer, + * to be used to decompress next frames. + * The dictionary remains valid for all future frames, until explicitly invalidated. + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + * Special : Adding a NULL (or 0-size) dictionary invalidates any previous dictionary, + * meaning "return to no-dictionary mode". + * Note 1 : Loading a dictionary involves building tables, + * which has a non-negligible impact on CPU usage and latency. + * It's recommended to "load once, use many times", to amortize the cost + * Note 2 :`dict` content will be copied internally, so `dict` can be released after loading. + * Use ZSTD_DCtx_loadDictionary_byReference() to reference dictionary content instead. + * Note 3 : Use ZSTD_DCtx_loadDictionary_advanced() to take control of + * how dictionary content is loaded and interpreted. + */ +ZSTDLIB_API size_t ZSTD_DCtx_loadDictionary(ZSTD_DCtx* dctx, const void* dict, size_t dictSize); + +/*! ZSTD_DCtx_refDDict() : + * Reference a prepared dictionary, to be used to decompress next frames. + * The dictionary remains active for decompression of future frames using same DCtx. + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + * Note 1 : Currently, only one dictionary can be managed. + * Referencing a new dictionary effectively "discards" any previous one. + * Special: referencing a NULL DDict means "return to no-dictionary mode". + * Note 2 : DDict is just referenced, its lifetime must outlive its usage from DCtx. + */ +ZSTDLIB_API size_t ZSTD_DCtx_refDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict); + +/*! ZSTD_DCtx_refPrefix() : + * Reference a prefix (single-usage dictionary) to decompress next frame. + * This is the reverse operation of ZSTD_CCtx_refPrefix(), + * and must use the same prefix as the one used during compression. + * Prefix is **only used once**. Reference is discarded at end of frame. + * End of frame is reached when ZSTD_decompressStream() returns 0. + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + * Note 1 : Adding any prefix (including NULL) invalidates any previously set prefix or dictionary + * Note 2 : Prefix buffer is referenced. It **must** outlive decompression. + * Prefix buffer must remain unmodified up to the end of frame, + * reached when ZSTD_decompressStream() returns 0. + * Note 3 : By default, the prefix is treated as raw content (ZSTD_dm_rawContent). + * Use ZSTD_CCtx_refPrefix_advanced() to alter dictMode (Experimental section) + * Note 4 : Referencing a raw content prefix has almost no cpu nor memory cost. + * A full dictionary is more costly, as it requires building tables. + */ +ZSTDLIB_API size_t ZSTD_DCtx_refPrefix(ZSTD_DCtx* dctx, + const void* prefix, size_t prefixSize); + /* === Memory management === */ /*! ZSTD_sizeof_*() : From 7231ea72a8b52b5942e6ec4b5ca43f3352eb4e2a Mon Sep 17 00:00:00 2001 From: Nick Terrell Date: Wed, 3 Apr 2019 19:21:05 -0700 Subject: [PATCH 4/4] [libzstd] Reword the streaming docs for the new API --- lib/zstd.h | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-) diff --git a/lib/zstd.h b/lib/zstd.h index 4e6791560..e7023361f 100644 --- a/lib/zstd.h +++ b/lib/zstd.h @@ -565,14 +565,15 @@ typedef struct ZSTD_outBuffer_s { * 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_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_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`. +* 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. @@ -582,17 +583,21 @@ typedef struct ZSTD_outBuffer_s { * 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(). +* 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. * @return : 0 if internal buffers are entirely flushed, * >0 if some data still present within internal buffer (the value is minimal estimation of remaining size), * or an error code, which can be tested using ZSTD_isError(). * -* ZSTD_endStream() instructs to finish a frame. +* Calling ZSTD_compressStream2() with ZSTD_e_end instructs to finish a frame. * It will perform a flush and write frame epilogue. * The epilogue is required for decoders to consider a frame completed. -* flush() operation is the same, and follows same rules as ZSTD_flushStream(). +* 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. * @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().