1 /* ****************************************************************** 2 huff0 huffman codec, 3 part of Finite State Entropy library 4 Copyright (C) 2013-present, 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 You can contact the author at : 32 - Source repository : https://github.com/Cyan4973/FiniteStateEntropy 33 ****************************************************************** */ 34 35 #if defined (__cplusplus) 36 extern "C" { 37 #endif 38 39 #ifndef HUF_H_298734234 40 #define HUF_H_298734234 41 42 /* *** Dependencies *** */ 43 #include <stddef.h> /* size_t */ 44 45 46 /* *** library symbols visibility *** */ 47 /* Note : when linking with -fvisibility=hidden on gcc, or by default on Visual, 48 * HUF symbols remain "private" (internal symbols for library only). 49 * Set macro FSE_DLL_EXPORT to 1 if you want HUF symbols visible on DLL interface */ 50 #if defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1) && defined(__GNUC__) && (__GNUC__ >= 4) 51 # define HUF_PUBLIC_API __attribute__ ((visibility ("default"))) 52 #elif defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1) /* Visual expected */ 53 # define HUF_PUBLIC_API __declspec(dllexport) 54 #elif defined(FSE_DLL_IMPORT) && (FSE_DLL_IMPORT==1) 55 # define HUF_PUBLIC_API __declspec(dllimport) /* not required, just to generate faster code (saves a function pointer load from IAT and an indirect jump) */ 56 #else 57 # define HUF_PUBLIC_API 58 #endif 59 60 61 /* ========================== */ 62 /* *** simple functions *** */ 63 /* ========================== */ 64 65 /** HUF_compress() : 66 * Compress content from buffer 'src', of size 'srcSize', into buffer 'dst'. 67 * 'dst' buffer must be already allocated. 68 * Compression runs faster if `dstCapacity` >= HUF_compressBound(srcSize). 69 * `srcSize` must be <= `HUF_BLOCKSIZE_MAX` == 128 KB. 70 * @return : size of compressed data (<= `dstCapacity`). 71 * Special values : if return == 0, srcData is not compressible => Nothing is stored within dst !!! 72 * if HUF_isError(return), compression failed (more details using HUF_getErrorName()) 73 */ 74 HUF_PUBLIC_API size_t HUF_compress(void* dst, size_t dstCapacity, 75 const void* src, size_t srcSize); 76 77 /** HUF_decompress() : 78 * Decompress HUF data from buffer 'cSrc', of size 'cSrcSize', 79 * into already allocated buffer 'dst', of minimum size 'dstSize'. 80 * `originalSize` : **must** be the ***exact*** size of original (uncompressed) data. 81 * Note : in contrast with FSE, HUF_decompress can regenerate 82 * RLE (cSrcSize==1) and uncompressed (cSrcSize==dstSize) data, 83 * because it knows size to regenerate (originalSize). 84 * @return : size of regenerated data (== originalSize), 85 * or an error code, which can be tested using HUF_isError() 86 */ 87 HUF_PUBLIC_API size_t HUF_decompress(void* dst, size_t originalSize, 88 const void* cSrc, size_t cSrcSize); 89 90 91 /* *** Tool functions *** */ 92 #define HUF_BLOCKSIZE_MAX (128 * 1024) /**< maximum input size for a single block compressed with HUF_compress */ 93 HUF_PUBLIC_API size_t HUF_compressBound(size_t size); /**< maximum compressed size (worst case) */ 94 95 /* Error Management */ 96 HUF_PUBLIC_API unsigned HUF_isError(size_t code); /**< tells if a return value is an error code */ 97 HUF_PUBLIC_API const char* HUF_getErrorName(size_t code); /**< provides error code string (useful for debugging) */ 98 99 100 /* *** Advanced function *** */ 101 102 /** HUF_compress2() : 103 * Same as HUF_compress(), but offers control over `maxSymbolValue` and `tableLog`. 104 * `maxSymbolValue` must be <= HUF_SYMBOLVALUE_MAX . 105 * `tableLog` must be `<= HUF_TABLELOG_MAX` . */ 106 HUF_PUBLIC_API size_t HUF_compress2 (void* dst, size_t dstCapacity, 107 const void* src, size_t srcSize, 108 unsigned maxSymbolValue, unsigned tableLog); 109 110 /** HUF_compress4X_wksp() : 111 * Same as HUF_compress2(), but uses externally allocated `workSpace`. 112 * `workspace` must have minimum alignment of 4, and be at least as large as HUF_WORKSPACE_SIZE */ 113 #define HUF_WORKSPACE_SIZE (6 << 10) 114 #define HUF_WORKSPACE_SIZE_U32 (HUF_WORKSPACE_SIZE / sizeof(U32)) 115 HUF_PUBLIC_API size_t HUF_compress4X_wksp (void* dst, size_t dstCapacity, 116 const void* src, size_t srcSize, 117 unsigned maxSymbolValue, unsigned tableLog, 118 void* workSpace, size_t wkspSize); 119 120 #endif /* HUF_H_298734234 */ 121 122 /* ****************************************************************** 123 * WARNING !! 124 * The following section contains advanced and experimental definitions 125 * which shall never be used in the context of a dynamic library, 126 * because they are not guaranteed to remain stable in the future. 127 * Only consider them in association with static linking. 128 * *****************************************************************/ 129 #if defined(HUF_STATIC_LINKING_ONLY) && !defined(HUF_H_HUF_STATIC_LINKING_ONLY) 130 #define HUF_H_HUF_STATIC_LINKING_ONLY 131 132 /* *** Dependencies *** */ 133 #include "mem.h" /* U32 */ 134 135 136 /* *** Constants *** */ 137 #define HUF_TABLELOG_MAX 12 /* max runtime value of tableLog (due to static allocation); can be modified up to HUF_ABSOLUTEMAX_TABLELOG */ 138 #define HUF_TABLELOG_DEFAULT 11 /* default tableLog value when none specified */ 139 #define HUF_SYMBOLVALUE_MAX 255 140 141 #define HUF_TABLELOG_ABSOLUTEMAX 15 /* absolute limit of HUF_MAX_TABLELOG. Beyond that value, code does not work */ 142 #if (HUF_TABLELOG_MAX > HUF_TABLELOG_ABSOLUTEMAX) 143 # error "HUF_TABLELOG_MAX is too large !" 144 #endif 145 146 147 /* **************************************** 148 * Static allocation 149 ******************************************/ 150 /* HUF buffer bounds */ 151 #define HUF_CTABLEBOUND 129 152 #define HUF_BLOCKBOUND(size) (size + (size>>8) + 8) /* only true when incompressible is pre-filtered with fast heuristic */ 153 #define HUF_COMPRESSBOUND(size) (HUF_CTABLEBOUND + HUF_BLOCKBOUND(size)) /* Macro version, useful for static allocation */ 154 155 /* static allocation of HUF's Compression Table */ 156 #define HUF_CTABLE_SIZE_U32(maxSymbolValue) ((maxSymbolValue)+1) /* Use tables of U32, for proper alignment */ 157 #define HUF_CTABLE_SIZE(maxSymbolValue) (HUF_CTABLE_SIZE_U32(maxSymbolValue) * sizeof(U32)) 158 #define HUF_CREATE_STATIC_CTABLE(name, maxSymbolValue) \ 159 U32 name##hb[HUF_CTABLE_SIZE_U32(maxSymbolValue)]; \ 160 void* name##hv = &(name##hb); \ 161 HUF_CElt* name = (HUF_CElt*)(name##hv) /* no final ; */ 162 163 /* static allocation of HUF's DTable */ 164 typedef U32 HUF_DTable; 165 #define HUF_DTABLE_SIZE(maxTableLog) (1 + (1<<(maxTableLog))) 166 #define HUF_CREATE_STATIC_DTABLEX1(DTable, maxTableLog) \ 167 HUF_DTable DTable[HUF_DTABLE_SIZE((maxTableLog)-1)] = { ((U32)((maxTableLog)-1) * 0x01000001) } 168 #define HUF_CREATE_STATIC_DTABLEX2(DTable, maxTableLog) \ 169 HUF_DTable DTable[HUF_DTABLE_SIZE(maxTableLog)] = { ((U32)(maxTableLog) * 0x01000001) } 170 171 172 /* **************************************** 173 * Advanced decompression functions 174 ******************************************/ 175 size_t HUF_decompress4X1 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< single-symbol decoder */ 176 #ifndef HUF_FORCE_DECOMPRESS_X1 177 size_t HUF_decompress4X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< double-symbols decoder */ 178 #endif 179 180 size_t HUF_decompress4X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< decodes RLE and uncompressed */ 181 size_t HUF_decompress4X_hufOnly(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< considers RLE and uncompressed as errors */ 182 size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /**< considers RLE and uncompressed as errors */ 183 size_t HUF_decompress4X1_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< single-symbol decoder */ 184 size_t HUF_decompress4X1_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /**< single-symbol decoder */ 185 #ifndef HUF_FORCE_DECOMPRESS_X1 186 size_t HUF_decompress4X2_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< double-symbols decoder */ 187 size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /**< double-symbols decoder */ 188 #endif 189 190 191 /* **************************************** 192 * HUF detailed API 193 * ****************************************/ 194 195 /*! HUF_compress() does the following: 196 * 1. count symbol occurrence from source[] into table count[] using FSE_count() (exposed within "fse.h") 197 * 2. (optional) refine tableLog using HUF_optimalTableLog() 198 * 3. build Huffman table from count using HUF_buildCTable() 199 * 4. save Huffman table to memory buffer using HUF_writeCTable() 200 * 5. encode the data stream using HUF_compress4X_usingCTable() 201 * 202 * The following API allows targeting specific sub-functions for advanced tasks. 203 * For example, it's possible to compress several blocks using the same 'CTable', 204 * or to save and regenerate 'CTable' using external methods. 205 */ 206 unsigned HUF_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue); 207 typedef struct HUF_CElt_s HUF_CElt; /* incomplete type */ 208 size_t HUF_buildCTable (HUF_CElt* CTable, const unsigned* count, unsigned maxSymbolValue, unsigned maxNbBits); /* @return : maxNbBits; CTable and count can overlap. In which case, CTable will overwrite count content */ 209 size_t HUF_writeCTable (void* dst, size_t maxDstSize, const HUF_CElt* CTable, unsigned maxSymbolValue, unsigned huffLog); 210 size_t HUF_compress4X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable); 211 212 typedef enum { 213 HUF_repeat_none, /**< Cannot use the previous table */ 214 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, 4}X_repeat */ 215 HUF_repeat_valid /**< Can use the previous table and it is assumed to be valid */ 216 } HUF_repeat; 217 /** HUF_compress4X_repeat() : 218 * Same as HUF_compress4X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none. 219 * If it uses hufTable it does not modify hufTable or repeat. 220 * If it doesn't, it sets *repeat = HUF_repeat_none, and it sets hufTable to the table used. 221 * If preferRepeat then the old table will always be used if valid. */ 222 size_t HUF_compress4X_repeat(void* dst, size_t dstSize, 223 const void* src, size_t srcSize, 224 unsigned maxSymbolValue, unsigned tableLog, 225 void* workSpace, size_t wkspSize, /**< `workSpace` must be aligned on 4-bytes boundaries, `wkspSize` must be >= HUF_WORKSPACE_SIZE */ 226 HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat, int bmi2); 227 228 /** HUF_buildCTable_wksp() : 229 * Same as HUF_buildCTable(), but using externally allocated scratch buffer. 230 * `workSpace` must be aligned on 4-bytes boundaries, and its size must be >= HUF_CTABLE_WORKSPACE_SIZE. 231 */ 232 #define HUF_CTABLE_WORKSPACE_SIZE_U32 (2*HUF_SYMBOLVALUE_MAX +1 +1) 233 #define HUF_CTABLE_WORKSPACE_SIZE (HUF_CTABLE_WORKSPACE_SIZE_U32 * sizeof(unsigned)) 234 size_t HUF_buildCTable_wksp (HUF_CElt* tree, 235 const unsigned* count, U32 maxSymbolValue, U32 maxNbBits, 236 void* workSpace, size_t wkspSize); 237 238 /*! HUF_readStats() : 239 * Read compact Huffman tree, saved by HUF_writeCTable(). 240 * `huffWeight` is destination buffer. 241 * @return : size read from `src` , or an error Code . 242 * Note : Needed by HUF_readCTable() and HUF_readDTableXn() . */ 243 size_t HUF_readStats(BYTE* huffWeight, size_t hwSize, 244 U32* rankStats, U32* nbSymbolsPtr, U32* tableLogPtr, 245 const void* src, size_t srcSize); 246 247 /** HUF_readCTable() : 248 * Loading a CTable saved with HUF_writeCTable() */ 249 size_t HUF_readCTable (HUF_CElt* CTable, unsigned* maxSymbolValuePtr, const void* src, size_t srcSize); 250 251 /** HUF_getNbBits() : 252 * Read nbBits from CTable symbolTable, for symbol `symbolValue` presumed <= HUF_SYMBOLVALUE_MAX 253 * Note 1 : is not inlined, as HUF_CElt definition is private 254 * Note 2 : const void* used, so that it can provide a statically allocated table as argument (which uses type U32) */ 255 U32 HUF_getNbBits(const void* symbolTable, U32 symbolValue); 256 257 /* 258 * HUF_decompress() does the following: 259 * 1. select the decompression algorithm (X1, X2) based on pre-computed heuristics 260 * 2. build Huffman table from save, using HUF_readDTableX?() 261 * 3. decode 1 or 4 segments in parallel using HUF_decompress?X?_usingDTable() 262 */ 263 264 /** HUF_selectDecoder() : 265 * Tells which decoder is likely to decode faster, 266 * based on a set of pre-computed metrics. 267 * @return : 0==HUF_decompress4X1, 1==HUF_decompress4X2 . 268 * Assumption : 0 < dstSize <= 128 KB */ 269 U32 HUF_selectDecoder (size_t dstSize, size_t cSrcSize); 270 271 /** 272 * The minimum workspace size for the `workSpace` used in 273 * HUF_readDTableX1_wksp() and HUF_readDTableX2_wksp(). 274 * 275 * The space used depends on HUF_TABLELOG_MAX, ranging from ~1500 bytes when 276 * HUF_TABLE_LOG_MAX=12 to ~1850 bytes when HUF_TABLE_LOG_MAX=15. 277 * Buffer overflow errors may potentially occur if code modifications result in 278 * a required workspace size greater than that specified in the following 279 * macro. 280 */ 281 #define HUF_DECOMPRESS_WORKSPACE_SIZE (2 << 10) 282 #define HUF_DECOMPRESS_WORKSPACE_SIZE_U32 (HUF_DECOMPRESS_WORKSPACE_SIZE / sizeof(U32)) 283 284 #ifndef HUF_FORCE_DECOMPRESS_X2 285 size_t HUF_readDTableX1 (HUF_DTable* DTable, const void* src, size_t srcSize); 286 size_t HUF_readDTableX1_wksp (HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize); 287 #endif 288 #ifndef HUF_FORCE_DECOMPRESS_X1 289 size_t HUF_readDTableX2 (HUF_DTable* DTable, const void* src, size_t srcSize); 290 size_t HUF_readDTableX2_wksp (HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize); 291 #endif 292 293 size_t HUF_decompress4X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable); 294 #ifndef HUF_FORCE_DECOMPRESS_X2 295 size_t HUF_decompress4X1_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable); 296 #endif 297 #ifndef HUF_FORCE_DECOMPRESS_X1 298 size_t HUF_decompress4X2_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable); 299 #endif 300 301 302 /* ====================== */ 303 /* single stream variants */ 304 /* ====================== */ 305 306 size_t HUF_compress1X (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog); 307 size_t HUF_compress1X_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize); /**< `workSpace` must be a table of at least HUF_WORKSPACE_SIZE_U32 unsigned */ 308 size_t HUF_compress1X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable); 309 /** HUF_compress1X_repeat() : 310 * Same as HUF_compress1X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none. 311 * If it uses hufTable it does not modify hufTable or repeat. 312 * If it doesn't, it sets *repeat = HUF_repeat_none, and it sets hufTable to the table used. 313 * If preferRepeat then the old table will always be used if valid. */ 314 size_t HUF_compress1X_repeat(void* dst, size_t dstSize, 315 const void* src, size_t srcSize, 316 unsigned maxSymbolValue, unsigned tableLog, 317 void* workSpace, size_t wkspSize, /**< `workSpace` must be aligned on 4-bytes boundaries, `wkspSize` must be >= HUF_WORKSPACE_SIZE */ 318 HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat, int bmi2); 319 320 size_t HUF_decompress1X1 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /* single-symbol decoder */ 321 #ifndef HUF_FORCE_DECOMPRESS_X1 322 size_t HUF_decompress1X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /* double-symbol decoder */ 323 #endif 324 325 size_t HUF_decompress1X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); 326 size_t HUF_decompress1X_DCtx_wksp (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); 327 #ifndef HUF_FORCE_DECOMPRESS_X2 328 size_t HUF_decompress1X1_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< single-symbol decoder */ 329 size_t HUF_decompress1X1_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /**< single-symbol decoder */ 330 #endif 331 #ifndef HUF_FORCE_DECOMPRESS_X1 332 size_t HUF_decompress1X2_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< double-symbols decoder */ 333 size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /**< double-symbols decoder */ 334 #endif 335 336 size_t HUF_decompress1X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable); /**< automatic selection of sing or double symbol decoder, based on DTable */ 337 #ifndef HUF_FORCE_DECOMPRESS_X2 338 size_t HUF_decompress1X1_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable); 339 #endif 340 #ifndef HUF_FORCE_DECOMPRESS_X1 341 size_t HUF_decompress1X2_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable); 342 #endif 343 344 /* BMI2 variants. 345 * If the CPU has BMI2 support, pass bmi2=1, otherwise pass bmi2=0. 346 */ 347 size_t HUF_decompress1X_usingDTable_bmi2(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int bmi2); 348 #ifndef HUF_FORCE_DECOMPRESS_X2 349 size_t HUF_decompress1X1_DCtx_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int bmi2); 350 #endif 351 size_t HUF_decompress4X_usingDTable_bmi2(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int bmi2); 352 size_t HUF_decompress4X_hufOnly_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int bmi2); 353 354 #endif /* HUF_STATIC_LINKING_ONLY */ 355 356 #if defined (__cplusplus) 357 } 358 #endif 359