Mercurial > public > mercurial-scm > hg
diff contrib/python-zstandard/zstd/dictBuilder/zdict.h @ 37495:b1fb341d8a61
zstandard: vendor python-zstandard 0.9.0
This was just released. It features a number of goodies. More info at
https://gregoryszorc.com/blog/2018/04/09/release-of-python-zstandard-0.9/.
The clang-format ignore list was updated to reflect the new source
of files.
The project contains a vendored copy of zstandard 1.3.4. The old
version was 1.1.3. One of the changes between those versions is that
zstandard is now dual licensed BSD + GPLv2 and the patent rights grant
has been removed. Good riddance.
The API should be backwards compatible. So no changes in core
should be needed. However, there were a number of changes in the
library that we'll want to adapt to. Those will be addressed in
subsequent commits.
Differential Revision: https://phab.mercurial-scm.org/D3198
author | Gregory Szorc <gregory.szorc@gmail.com> |
---|---|
date | Mon, 09 Apr 2018 10:13:29 -0700 |
parents | c32454d69b85 |
children | 73fef626dae3 |
line wrap: on
line diff
--- a/contrib/python-zstandard/zstd/dictBuilder/zdict.h Sun Apr 08 01:08:43 2018 +0200 +++ b/contrib/python-zstandard/zstd/dictBuilder/zdict.h Mon Apr 09 10:13:29 2018 -0700 @@ -1,10 +1,11 @@ -/** +/* * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. * All rights reserved. * - * This source code is licensed under the BSD-style license found in the - * LICENSE file in the root directory of this source tree. An additional grant - * of patent rights can be found in the PATENTS file in the same directory. + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. */ #ifndef DICTBUILDER_H_001 @@ -20,10 +21,12 @@ /* ===== ZDICTLIB_API : control library symbols visibility ===== */ -#if defined(__GNUC__) && (__GNUC__ >= 4) -# define ZDICTLIB_VISIBILITY __attribute__ ((visibility ("default"))) -#else -# define ZDICTLIB_VISIBILITY +#ifndef ZDICTLIB_VISIBILITY +# if defined(__GNUC__) && (__GNUC__ >= 4) +# define ZDICTLIB_VISIBILITY __attribute__ ((visibility ("default"))) +# else +# define ZDICTLIB_VISIBILITY +# endif #endif #if defined(ZSTD_DLL_EXPORT) && (ZSTD_DLL_EXPORT==1) # define ZDICTLIB_API __declspec(dllexport) ZDICTLIB_VISIBILITY @@ -34,20 +37,22 @@ #endif -/*! ZDICT_trainFromBuffer() : - Train a dictionary from an array of samples. - Samples must be stored concatenated in a single flat buffer `samplesBuffer`, - supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order. - The resulting dictionary will be saved into `dictBuffer`. - @return : size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`) - or an error code, which can be tested with ZDICT_isError(). - Tips : In general, a reasonable dictionary has a size of ~ 100 KB. - It's obviously possible to target smaller or larger ones, just by specifying different `dictBufferCapacity`. - In general, it's recommended to provide a few thousands samples, but this can vary a lot. - It's recommended that total size of all samples be about ~x100 times the target size of dictionary. -*/ +/*! ZDICT_trainFromBuffer(): + * Train a dictionary from an array of samples. + * Redirect towards ZDICT_optimizeTrainFromBuffer_cover() single-threaded, with d=8 and steps=4. + * Samples must be stored concatenated in a single flat buffer `samplesBuffer`, + * supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order. + * The resulting dictionary will be saved into `dictBuffer`. + * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`) + * or an error code, which can be tested with ZDICT_isError(). + * Note: ZDICT_trainFromBuffer() requires about 9 bytes of memory for each input byte. + * Tips: In general, a reasonable dictionary has a size of ~ 100 KB. + * It's possible to select smaller or larger size, just by specifying `dictBufferCapacity`. + * In general, it's recommended to provide a few thousands samples, though this can vary a lot. + * It's recommended that total size of all samples be about ~x100 times the target size of dictionary. + */ ZDICTLIB_API size_t ZDICT_trainFromBuffer(void* dictBuffer, size_t dictBufferCapacity, - const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples); + const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples); /*====== Helper functions ======*/ @@ -67,102 +72,108 @@ * ==================================================================================== */ typedef struct { - unsigned selectivityLevel; /* 0 means default; larger => select more => larger dictionary */ - int compressionLevel; /* 0 means default; target a specific zstd compression level */ - unsigned notificationLevel; /* Write to stderr; 0 = none (default); 1 = errors; 2 = progression; 3 = details; 4 = debug; */ - unsigned dictID; /* 0 means auto mode (32-bits random value); other : force dictID value */ - unsigned reserved[2]; /* reserved space for future parameters */ + int compressionLevel; /* optimize for a specific zstd compression level; 0 means default */ + unsigned notificationLevel; /* Write log to stderr; 0 = none (default); 1 = errors; 2 = progression; 3 = details; 4 = debug; */ + unsigned dictID; /* force dictID value; 0 means auto mode (32-bits random value) */ } ZDICT_params_t; - -/*! ZDICT_trainFromBuffer_advanced() : - Same as ZDICT_trainFromBuffer() with control over more parameters. - `parameters` is optional and can be provided with values set to 0 to mean "default". - @return : size of dictionary stored into `dictBuffer` (<= `dictBufferSize`), - or an error code, which can be tested by ZDICT_isError(). - note : ZDICT_trainFromBuffer_advanced() will send notifications into stderr if instructed to, using notificationLevel>0. -*/ -ZDICTLIB_API size_t ZDICT_trainFromBuffer_advanced(void* dictBuffer, size_t dictBufferCapacity, - const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples, - ZDICT_params_t parameters); - -/*! COVER_params_t : - For all values 0 means default. - kMin and d are the only required parameters. -*/ +/*! ZDICT_cover_params_t: + * k and d are the only required parameters. + * For others, value 0 means default. + */ typedef struct { unsigned k; /* Segment size : constraint: 0 < k : Reasonable range [16, 2048+] */ unsigned d; /* dmer size : constraint: 0 < d <= k : Reasonable range [6, 16] */ unsigned steps; /* Number of steps : Only used for optimization : 0 means default (32) : Higher means more parameters checked */ - unsigned nbThreads; /* Number of threads : constraint: 0 < nbThreads : 1 means single-threaded : Only used for optimization : Ignored if ZSTD_MULTITHREAD is not defined */ - unsigned notificationLevel; /* Write to stderr; 0 = none (default); 1 = errors; 2 = progression; 3 = details; 4 = debug; */ - unsigned dictID; /* 0 means auto mode (32-bits random value); other : force dictID value */ - int compressionLevel; /* 0 means default; target a specific zstd compression level */ -} COVER_params_t; + ZDICT_params_t zParams; +} ZDICT_cover_params_t; -/*! COVER_trainFromBuffer() : - Train a dictionary from an array of samples using the COVER algorithm. - Samples must be stored concatenated in a single flat buffer `samplesBuffer`, - supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order. - The resulting dictionary will be saved into `dictBuffer`. - @return : size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`) - or an error code, which can be tested with ZDICT_isError(). - Note : COVER_trainFromBuffer() requires about 9 bytes of memory for each input byte. - Tips : In general, a reasonable dictionary has a size of ~ 100 KB. - It's obviously possible to target smaller or larger ones, just by specifying different `dictBufferCapacity`. - In general, it's recommended to provide a few thousands samples, but this can vary a lot. - It's recommended that total size of all samples be about ~x100 times the target size of dictionary. -*/ -ZDICTLIB_API size_t COVER_trainFromBuffer(void* dictBuffer, size_t dictBufferCapacity, - const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples, - COVER_params_t parameters); - -/*! COVER_optimizeTrainFromBuffer() : - The same requirements as above hold for all the parameters except `parameters`. - This function tries many parameter combinations and picks the best parameters. - `*parameters` is filled with the best parameters found, and the dictionary - constructed with those parameters is stored in `dictBuffer`. - - All of the parameters d, k, steps are optional. - If d is non-zero then we don't check multiple values of d, otherwise we check d = {6, 8, 10, 12, 14, 16}. - if steps is zero it defaults to its default value. - If k is non-zero then we don't check multiple values of k, otherwise we check steps values in [16, 2048]. +/*! ZDICT_trainFromBuffer_cover(): + * Train a dictionary from an array of samples using the COVER algorithm. + * Samples must be stored concatenated in a single flat buffer `samplesBuffer`, + * supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order. + * The resulting dictionary will be saved into `dictBuffer`. + * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`) + * or an error code, which can be tested with ZDICT_isError(). + * Note: ZDICT_trainFromBuffer_cover() requires about 9 bytes of memory for each input byte. + * Tips: In general, a reasonable dictionary has a size of ~ 100 KB. + * It's possible to select smaller or larger size, just by specifying `dictBufferCapacity`. + * In general, it's recommended to provide a few thousands samples, though this can vary a lot. + * It's recommended that total size of all samples be about ~x100 times the target size of dictionary. + */ +ZDICTLIB_API size_t ZDICT_trainFromBuffer_cover( + void *dictBuffer, size_t dictBufferCapacity, + const void *samplesBuffer, const size_t *samplesSizes, unsigned nbSamples, + ZDICT_cover_params_t parameters); - @return : size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`) - or an error code, which can be tested with ZDICT_isError(). - On success `*parameters` contains the parameters selected. - Note : COVER_optimizeTrainFromBuffer() requires about 8 bytes of memory for each input byte and additionally another 5 bytes of memory for each byte of memory for each thread. -*/ -ZDICTLIB_API size_t COVER_optimizeTrainFromBuffer(void* dictBuffer, size_t dictBufferCapacity, - const void* samplesBuffer, const size_t *samplesSizes, unsigned nbSamples, - COVER_params_t *parameters); - -/*! ZDICT_finalizeDictionary() : - - Given a custom content as a basis for dictionary, and a set of samples, - finalize dictionary by adding headers and statistics. +/*! ZDICT_optimizeTrainFromBuffer_cover(): + * The same requirements as above hold for all the parameters except `parameters`. + * This function tries many parameter combinations and picks the best parameters. + * `*parameters` is filled with the best parameters found, + * dictionary constructed with those parameters is stored in `dictBuffer`. + * + * All of the parameters d, k, steps are optional. + * If d is non-zero then we don't check multiple values of d, otherwise we check d = {6, 8, 10, 12, 14, 16}. + * if steps is zero it defaults to its default value. + * If k is non-zero then we don't check multiple values of k, otherwise we check steps values in [16, 2048]. + * + * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`) + * or an error code, which can be tested with ZDICT_isError(). + * On success `*parameters` contains the parameters selected. + * Note: ZDICT_optimizeTrainFromBuffer_cover() requires about 8 bytes of memory for each input byte and additionally another 5 bytes of memory for each byte of memory for each thread. + */ +ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_cover( + void* dictBuffer, size_t dictBufferCapacity, + const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples, + ZDICT_cover_params_t* parameters); - Samples must be stored concatenated in a flat buffer `samplesBuffer`, - supplied with an array of sizes `samplesSizes`, providing the size of each sample in order. - - dictContentSize must be > ZDICT_CONTENTSIZE_MIN bytes. - maxDictSize must be >= dictContentSize, and must be > ZDICT_DICTSIZE_MIN bytes. - - @return : size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`), - or an error code, which can be tested by ZDICT_isError(). - note : ZDICT_finalizeDictionary() will push notifications into stderr if instructed to, using notificationLevel>0. - note 2 : dictBuffer and customDictContent can overlap -*/ -#define ZDICT_CONTENTSIZE_MIN 256 -#define ZDICT_DICTSIZE_MIN 512 +/*! ZDICT_finalizeDictionary(): + * Given a custom content as a basis for dictionary, and a set of samples, + * finalize dictionary by adding headers and statistics. + * + * Samples must be stored concatenated in a flat buffer `samplesBuffer`, + * supplied with an array of sizes `samplesSizes`, providing the size of each sample in order. + * + * dictContentSize must be >= ZDICT_CONTENTSIZE_MIN bytes. + * maxDictSize must be >= dictContentSize, and must be >= ZDICT_DICTSIZE_MIN bytes. + * + * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`), + * or an error code, which can be tested by ZDICT_isError(). + * Note: ZDICT_finalizeDictionary() will push notifications into stderr if instructed to, using notificationLevel>0. + * Note 2: dictBuffer and dictContent can overlap + */ +#define ZDICT_CONTENTSIZE_MIN 128 +#define ZDICT_DICTSIZE_MIN 256 ZDICTLIB_API size_t ZDICT_finalizeDictionary(void* dictBuffer, size_t dictBufferCapacity, - const void* customDictContent, size_t dictContentSize, + const void* dictContent, size_t dictContentSize, const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples, ZDICT_params_t parameters); +typedef struct { + unsigned selectivityLevel; /* 0 means default; larger => select more => larger dictionary */ + ZDICT_params_t zParams; +} ZDICT_legacy_params_t; +/*! ZDICT_trainFromBuffer_legacy(): + * Train a dictionary from an array of samples. + * Samples must be stored concatenated in a single flat buffer `samplesBuffer`, + * supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order. + * The resulting dictionary will be saved into `dictBuffer`. + * `parameters` is optional and can be provided with values set to 0 to mean "default". + * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`) + * or an error code, which can be tested with ZDICT_isError(). + * Tips: In general, a reasonable dictionary has a size of ~ 100 KB. + * It's possible to select smaller or larger size, just by specifying `dictBufferCapacity`. + * In general, it's recommended to provide a few thousands samples, though this can vary a lot. + * It's recommended that total size of all samples be about ~x100 times the target size of dictionary. + * Note: ZDICT_trainFromBuffer_legacy() will send notifications into stderr if instructed to, using notificationLevel>0. + */ +ZDICTLIB_API size_t ZDICT_trainFromBuffer_legacy( + void *dictBuffer, size_t dictBufferCapacity, + const void *samplesBuffer, const size_t *samplesSizes, unsigned nbSamples, + ZDICT_legacy_params_t parameters); /* Deprecation warnings */ /* It is generally possible to disable deprecation warnings from compiler, @@ -174,7 +185,7 @@ #else # define ZDICT_GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__) # if defined (__cplusplus) && (__cplusplus >= 201402) /* C++14 or greater */ -# define ZDICT_DEPRECATED(message) ZDICTLIB_API [[deprecated(message)]] +# define ZDICT_DEPRECATED(message) [[deprecated(message)]] ZDICTLIB_API # elif (ZDICT_GCC_VERSION >= 405) || defined(__clang__) # define ZDICT_DEPRECATED(message) ZDICTLIB_API __attribute__((deprecated(message))) # elif (ZDICT_GCC_VERSION >= 301)