lib/zstd/huf.h

   1 /*
   2  * Huffman coder, part of New Generation Entropy library
   3  * header file
   4  * Copyright (C) 2013-2016, Yann Collet.
   5  *
   6  * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
   7  *
   8  * Redistribution and use in source and binary forms, with or without
   9  * modification, are permitted provided that the following conditions are
  10  * met:
  11  *
  12  *   * Redistributions of source code must retain the above copyright
  13  * notice, this list of conditions and the following disclaimer.
  14  *   * Redistributions in binary form must reproduce the above
  15  * copyright notice, this list of conditions and the following disclaimer
  16  * in the documentation and/or other materials provided with the
  17  * distribution.
  18  *
  19  * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
  20  * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
  21  * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
  22  * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
  23  * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
  24  * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
  25  * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
  26  * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
  27  * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
  28  * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
  29  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  30  *
  31  * This program is free software; you can redistribute it and/or modify it under
  32  * the terms of the GNU General Public License version 2 as published by the
  33  * Free Software Foundation. This program is dual-licensed; you may select
  34  * either version 2 of the GNU General Public License ("GPL") or BSD license
  35  * ("BSD").
  36  *
  37  * You can contact the author at :
  38  * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
  39  */
  40 #ifndef HUF_H_298734234
  41 #define HUF_H_298734234
  42
  43 /* *** Dependencies *** */
  44 #include <linux/types.h> /* size_t */
  45
  46 /* ***   Tool functions *** */
  47 #define HUF_BLOCKSIZE_MAX (128 * 1024) /**< maximum input size for a single block compressed with HUF_compress */
  48 size_t HUF_compressBound(size_t size); /**< maximum compressed size (worst case) */
  49
  50 /* Error Management */
  51 unsigned HUF_isError(size_t code); /**< tells if a return value is an error code */
  52
  53 /* ***   Advanced function   *** */
  54
  55 /** HUF_compress4X_wksp() :
  56 *   Same as HUF_compress2(), but uses externally allocated `workSpace`, which must be a table of >= 1024 unsigned */
  57 size_t HUF_compress4X_wksp(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void *workSpace,
  58                            size_t wkspSize); /**< `workSpace` must be a table of at least HUF_COMPRESS_WORKSPACE_SIZE_U32 unsigned */
  59
  60 /* *** Dependencies *** */
  61 #include "mem.h" /* U32 */
  62
  63 /* *** Constants *** */
  64 #define HUF_TABLELOG_MAX 12     /* max configured tableLog (for static allocation); can be modified up to HUF_ABSOLUTEMAX_TABLELOG */
  65 #define HUF_TABLELOG_DEFAULT 11 /* tableLog by default, when not specified */
  66 #define HUF_SYMBOLVALUE_MAX 255
  67
  68 #define HUF_TABLELOG_ABSOLUTEMAX 15 /* absolute limit of HUF_MAX_TABLELOG. Beyond that value, code does not work */
  69 #if (HUF_TABLELOG_MAX > HUF_TABLELOG_ABSOLUTEMAX)
  70 #error "HUF_TABLELOG_MAX is too large !"
  71 #endif
  72
  73 /* ****************************************
  74 *  Static allocation
  75 ******************************************/
  76 /* HUF buffer bounds */
  77 #define HUF_CTABLEBOUND 129
  78 #define HUF_BLOCKBOUND(size) (size + (size >> 8) + 8)                    /* only true if incompressible pre-filtered with fast heuristic */
  79 #define HUF_COMPRESSBOUND(size) (HUF_CTABLEBOUND + HUF_BLOCKBOUND(size)) /* Macro version, useful for static allocation */
  80
  81 /* static allocation of HUF's Compression Table */
  82 #define HUF_CREATE_STATIC_CTABLE(name, maxSymbolValue) \
  83         U32 name##hb[maxSymbolValue + 1];              \
  84         void *name##hv = &(name##hb);                  \
  85         HUF_CElt *name = (HUF_CElt *)(name##hv) /* no final ; */
  86
  87 /* static allocation of HUF's DTable */
  88 typedef U32 HUF_DTable;
  89 #define HUF_DTABLE_SIZE(maxTableLog) (1 + (1 << (maxTableLog)))
  90 #define HUF_CREATE_STATIC_DTABLEX2(DTable, maxTableLog) HUF_DTable DTable[HUF_DTABLE_SIZE((maxTableLog)-1)] = {((U32)((maxTableLog)-1) * 0x01000001)}
  91 #define HUF_CREATE_STATIC_DTABLEX4(DTable, maxTableLog) HUF_DTable DTable[HUF_DTABLE_SIZE(maxTableLog)] = {((U32)(maxTableLog)*0x01000001)}
  92
  93 /* The workspace must have alignment at least 4 and be at least this large */
  94 #define HUF_COMPRESS_WORKSPACE_SIZE (6 << 10)
  95 #define HUF_COMPRESS_WORKSPACE_SIZE_U32 (HUF_COMPRESS_WORKSPACE_SIZE / sizeof(U32))
  96
  97 /* The workspace must have alignment at least 4 and be at least this large */
  98 #define HUF_DECOMPRESS_WORKSPACE_SIZE (3 << 10)
  99 #define HUF_DECOMPRESS_WORKSPACE_SIZE_U32 (HUF_DECOMPRESS_WORKSPACE_SIZE / sizeof(U32))
 100
 101 /* ****************************************
 102 *  Advanced decompression functions
 103 ******************************************/
 104 size_t HUF_decompress4X_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize); /**< decodes RLE and uncompressed */
 105 size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace,
 106                                 size_t workspaceSize);                                                         /**< considers RLE and uncompressed as errors */
 107 size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace,
 108                                    size_t workspaceSize); /**< single-symbol decoder */
 109 size_t HUF_decompress4X4_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace,
 110                                    size_t workspaceSize); /**< double-symbols decoder */
 111
 112 /* ****************************************
 113 *  HUF detailed API
 114 ******************************************/
 115 /*!
 116 HUF_compress() does the following:
 117 1. count symbol occurrence from source[] into table count[] using FSE_count()
 118 2. (optional) refine tableLog using HUF_optimalTableLog()
 119 3. build Huffman table from count using HUF_buildCTable()
 120 4. save Huffman table to memory buffer using HUF_writeCTable_wksp()
 121 5. encode the data stream using HUF_compress4X_usingCTable()
 122
 123 The following API allows targeting specific sub-functions for advanced tasks.
 124 For example, it's possible to compress several blocks using the same 'CTable',
 125 or to save and regenerate 'CTable' using external methods.
 126 */
 127 /* FSE_count() : find it within "fse.h" */
 128 unsigned HUF_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue);
 129 typedef struct HUF_CElt_s HUF_CElt; /* incomplete type */
 130 size_t HUF_writeCTable_wksp(void *dst, size_t maxDstSize, const HUF_CElt *CTable, unsigned maxSymbolValue, unsigned huffLog, void *workspace, size_t workspaceSize);
 131 size_t HUF_compress4X_usingCTable(void *dst, size_t dstSize, const void *src, size_t srcSize, const HUF_CElt *CTable);
 132
 133 typedef enum {
 134         HUF_repeat_none,  /**< Cannot use the previous table */
 135         HUF_repeat_check, /**< Can use the previous table but it must be checked. Note : The previous table must have been constructed by HUF_compress{1,
 136                              4}X_repeat */
 137         HUF_repeat_valid  /**< Can use the previous table and it is asumed to be valid */
 138 } HUF_repeat;
 139 /** HUF_compress4X_repeat() :
 140 *   Same as HUF_compress4X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none.
 141 *   If it uses hufTable it does not modify hufTable or repeat.
 142 *   If it doesn't, it sets *repeat = HUF_repeat_none, and it sets hufTable to the table used.
 143 *   If preferRepeat then the old table will always be used if valid. */
 144 size_t HUF_compress4X_repeat(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void *workSpace,
 145                              size_t wkspSize, HUF_CElt *hufTable, HUF_repeat *repeat,
 146                              int preferRepeat); /**< `workSpace` must be a table of at least HUF_COMPRESS_WORKSPACE_SIZE_U32 unsigned */
 147
 148 /** HUF_buildCTable_wksp() :
 149  *  Same as HUF_buildCTable(), but using externally allocated scratch buffer.
 150  *  `workSpace` must be aligned on 4-bytes boundaries, and be at least as large as a table of 1024 unsigned.
 151  */
 152 size_t HUF_buildCTable_wksp(HUF_CElt *tree, const U32 *count, U32 maxSymbolValue, U32 maxNbBits, void *workSpace, size_t wkspSize);
 153
 154 /*! HUF_readStats() :
 155         Read compact Huffman tree, saved by HUF_writeCTable().
 156         `huffWeight` is destination buffer.
 157         @return : size read from `src` , or an error Code .
 158         Note : Needed by HUF_readCTable() and HUF_readDTableXn() . */
 159 size_t HUF_readStats_wksp(BYTE *huffWeight, size_t hwSize, U32 *rankStats, U32 *nbSymbolsPtr, U32 *tableLogPtr, const void *src, size_t srcSize,
 160                           void *workspace, size_t workspaceSize);
 161
 162 /** HUF_readCTable() :
 163 *   Loading a CTable saved with HUF_writeCTable() */
 164 size_t HUF_readCTable_wksp(HUF_CElt *CTable, unsigned maxSymbolValue, const void *src, size_t srcSize, void *workspace, size_t workspaceSize);
 165
 166 /*
 167 HUF_decompress() does the following:
 168 1. select the decompression algorithm (X2, X4) based on pre-computed heuristics
 169 2. build Huffman table from save, using HUF_readDTableXn()
 170 3. decode 1 or 4 segments in parallel using HUF_decompressSXn_usingDTable
 171 */
 172
 173 /** HUF_selectDecoder() :
 174 *   Tells which decoder is likely to decode faster,
 175 *   based on a set of pre-determined metrics.
 176 *   @return : 0==HUF_decompress4X2, 1==HUF_decompress4X4 .
 177 *   Assumption : 0 < cSrcSize < dstSize <= 128 KB */
 178 U32 HUF_selectDecoder(size_t dstSize, size_t cSrcSize);
 179
 180 size_t HUF_readDTableX2_wksp(HUF_DTable *DTable, const void *src, size_t srcSize, void *workspace, size_t workspaceSize);
 181 size_t HUF_readDTableX4_wksp(HUF_DTable *DTable, const void *src, size_t srcSize, void *workspace, size_t workspaceSize);
 182
 183 size_t HUF_decompress4X_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable);
 184 size_t HUF_decompress4X2_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable);
 185 size_t HUF_decompress4X4_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable);
 186
 187 /* single stream variants */
 188
 189 size_t HUF_compress1X_wksp(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void *workSpace,
 190                            size_t wkspSize); /**< `workSpace` must be a table of at least HUF_COMPRESS_WORKSPACE_SIZE_U32 unsigned */
 191 size_t HUF_compress1X_usingCTable(void *dst, size_t dstSize, const void *src, size_t srcSize, const HUF_CElt *CTable);
 192 /** HUF_compress1X_repeat() :
 193 *   Same as HUF_compress1X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none.
 194 *   If it uses hufTable it does not modify hufTable or repeat.
 195 *   If it doesn't, it sets *repeat = HUF_repeat_none, and it sets hufTable to the table used.
 196 *   If preferRepeat then the old table will always be used if valid. */
 197 size_t HUF_compress1X_repeat(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void *workSpace,
 198                              size_t wkspSize, HUF_CElt *hufTable, HUF_repeat *repeat,
 199                              int preferRepeat); /**< `workSpace` must be a table of at least HUF_COMPRESS_WORKSPACE_SIZE_U32 unsigned */
 200
 201 size_t HUF_decompress1X_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize);
 202 size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace,
 203                                    size_t workspaceSize); /**< single-symbol decoder */
 204 size_t HUF_decompress1X4_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace,
 205                                    size_t workspaceSize); /**< double-symbols decoder */
 206
 207 size_t HUF_decompress1X_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize,
 208                                     const HUF_DTable *DTable); /**< automatic selection of sing or double symbol decoder, based on DTable */
 209 size_t HUF_decompress1X2_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable);
 210 size_t HUF_decompress1X4_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable);
 211
 212 #endif /* HUF_H_298734234 */