xxhash.h (13466B)
1 /* 2 xxHash - Extremely Fast Hash algorithm 3 Header File 4 Copyright (C) 2012-2016, 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 You can contact the author at : 32 - xxHash source repository : https://github.com/Cyan4973/xxHash 33 */ 34 35 /* Notice extracted from xxHash homepage : 36 37 xxHash is an extremely fast Hash algorithm, running at RAM speed limits. 38 It also successfully passes all tests from the SMHasher suite. 39 40 Comparison (single thread, Windows Seven 32 bits, using SMHasher on a Core 2 Duo @3GHz) 41 42 Name Speed Q.Score Author 43 xxHash 5.4 GB/s 10 44 CrapWow 3.2 GB/s 2 Andrew 45 MumurHash 3a 2.7 GB/s 10 Austin Appleby 46 SpookyHash 2.0 GB/s 10 Bob Jenkins 47 SBox 1.4 GB/s 9 Bret Mulvey 48 Lookup3 1.2 GB/s 9 Bob Jenkins 49 SuperFastHash 1.2 GB/s 1 Paul Hsieh 50 CityHash64 1.05 GB/s 10 Pike & Alakuijala 51 FNV 0.55 GB/s 5 Fowler, Noll, Vo 52 CRC32 0.43 GB/s 9 53 MD5-32 0.33 GB/s 10 Ronald L. Rivest 54 SHA1-32 0.28 GB/s 10 55 56 Q.Score is a measure of quality of the hash function. 57 It depends on successfully passing SMHasher test set. 58 10 is a perfect score. 59 60 A 64-bit version, named XXH64, is available since r35. 61 It offers much better speed, but for 64-bit applications only. 62 Name Speed on 64 bits Speed on 32 bits 63 XXH64 13.8 GB/s 1.9 GB/s 64 XXH32 6.8 GB/s 6.0 GB/s 65 */ 66 67 #ifndef XXHASH_H_5627135585666179 68 #define XXHASH_H_5627135585666179 1 69 70 #if defined (__cplusplus) 71 extern "C" { 72 #endif 73 74 75 /* **************************** 76 * Definitions 77 ******************************/ 78 #include <stddef.h> /* size_t */ 79 typedef enum { XXH_OK=0, XXH_ERROR } XXH_errorcode; 80 81 82 /* **************************** 83 * API modifier 84 ******************************/ 85 /** XXH_INLINE_ALL (and XXH_PRIVATE_API) 86 * This is useful to include xxhash functions in `static` mode 87 * in order to inline them, and remove their symbol from the public list. 88 * Inlining can offer dramatic performance improvement on small keys. 89 * Methodology : 90 * #define XXH_INLINE_ALL 91 * #include "xxhash.h" 92 * `xxhash.c` is automatically included. 93 * It's not useful to compile and link it as a separate module. 94 */ 95 #if defined(XXH_INLINE_ALL) || defined(XXH_PRIVATE_API) 96 # ifndef XXH_STATIC_LINKING_ONLY 97 # define XXH_STATIC_LINKING_ONLY 98 # endif 99 # if defined(__GNUC__) 100 # define XXH_PUBLIC_API static __inline __attribute__((unused)) 101 # elif defined (__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */) 102 # define XXH_PUBLIC_API static inline 103 # elif defined(_MSC_VER) 104 # define XXH_PUBLIC_API static __inline 105 # else 106 /* this version may generate warnings for unused static functions */ 107 # define XXH_PUBLIC_API static 108 # endif 109 #else 110 # define XXH_PUBLIC_API /* do nothing */ 111 #endif /* XXH_INLINE_ALL || XXH_PRIVATE_API */ 112 113 /*! XXH_NAMESPACE, aka Namespace Emulation : 114 * 115 * If you want to include _and expose_ xxHash functions from within your own library, 116 * but also want to avoid symbol collisions with other libraries which may also include xxHash, 117 * 118 * you can use XXH_NAMESPACE, to automatically prefix any public symbol from xxhash library 119 * with the value of XXH_NAMESPACE (therefore, avoid NULL and numeric values). 120 * 121 * Note that no change is required within the calling program as long as it includes `xxhash.h` : 122 * regular symbol name will be automatically translated by this header. 123 */ 124 #ifdef XXH_NAMESPACE 125 # define XXH_CAT(A,B) A##B 126 # define XXH_NAME2(A,B) XXH_CAT(A,B) 127 # define XXH_versionNumber XXH_NAME2(XXH_NAMESPACE, XXH_versionNumber) 128 # define XXH32 XXH_NAME2(XXH_NAMESPACE, XXH32) 129 # define XXH32_createState XXH_NAME2(XXH_NAMESPACE, XXH32_createState) 130 # define XXH32_freeState XXH_NAME2(XXH_NAMESPACE, XXH32_freeState) 131 # define XXH32_reset XXH_NAME2(XXH_NAMESPACE, XXH32_reset) 132 # define XXH32_update XXH_NAME2(XXH_NAMESPACE, XXH32_update) 133 # define XXH32_digest XXH_NAME2(XXH_NAMESPACE, XXH32_digest) 134 # define XXH32_copyState XXH_NAME2(XXH_NAMESPACE, XXH32_copyState) 135 # define XXH32_canonicalFromHash XXH_NAME2(XXH_NAMESPACE, XXH32_canonicalFromHash) 136 # define XXH32_hashFromCanonical XXH_NAME2(XXH_NAMESPACE, XXH32_hashFromCanonical) 137 # define XXH64 XXH_NAME2(XXH_NAMESPACE, XXH64) 138 # define XXH64_createState XXH_NAME2(XXH_NAMESPACE, XXH64_createState) 139 # define XXH64_freeState XXH_NAME2(XXH_NAMESPACE, XXH64_freeState) 140 # define XXH64_reset XXH_NAME2(XXH_NAMESPACE, XXH64_reset) 141 # define XXH64_update XXH_NAME2(XXH_NAMESPACE, XXH64_update) 142 # define XXH64_digest XXH_NAME2(XXH_NAMESPACE, XXH64_digest) 143 # define XXH64_copyState XXH_NAME2(XXH_NAMESPACE, XXH64_copyState) 144 # define XXH64_canonicalFromHash XXH_NAME2(XXH_NAMESPACE, XXH64_canonicalFromHash) 145 # define XXH64_hashFromCanonical XXH_NAME2(XXH_NAMESPACE, XXH64_hashFromCanonical) 146 #endif 147 148 149 /* ************************************* 150 * Version 151 ***************************************/ 152 #define XXH_VERSION_MAJOR 0 153 #define XXH_VERSION_MINOR 6 154 #define XXH_VERSION_RELEASE 5 155 #define XXH_VERSION_NUMBER (XXH_VERSION_MAJOR *100*100 + XXH_VERSION_MINOR *100 + XXH_VERSION_RELEASE) 156 XXH_PUBLIC_API unsigned XXH_versionNumber (void); 157 158 159 /*-********************************************************************** 160 * 32-bit hash 161 ************************************************************************/ 162 typedef unsigned int XXH32_hash_t; 163 164 /*! XXH32() : 165 Calculate the 32-bit hash of sequence "length" bytes stored at memory address "input". 166 The memory between input & input+length must be valid (allocated and read-accessible). 167 "seed" can be used to alter the result predictably. 168 Speed on Core 2 Duo @ 3 GHz (single thread, SMHasher benchmark) : 5.4 GB/s */ 169 XXH_PUBLIC_API XXH32_hash_t XXH32 (const void* input, size_t length, unsigned int seed); 170 171 /*====== Streaming ======*/ 172 typedef struct XXH32_state_s XXH32_state_t; /* incomplete type */ 173 XXH_PUBLIC_API XXH32_state_t* XXH32_createState(void); 174 XXH_PUBLIC_API XXH_errorcode XXH32_freeState(XXH32_state_t* statePtr); 175 XXH_PUBLIC_API void XXH32_copyState(XXH32_state_t* dst_state, const XXH32_state_t* src_state); 176 177 XXH_PUBLIC_API XXH_errorcode XXH32_reset (XXH32_state_t* statePtr, unsigned int seed); 178 XXH_PUBLIC_API XXH_errorcode XXH32_update (XXH32_state_t* statePtr, const void* input, size_t length); 179 XXH_PUBLIC_API XXH32_hash_t XXH32_digest (const XXH32_state_t* statePtr); 180 181 /* 182 * Streaming functions generate the xxHash of an input provided in multiple segments. 183 * Note that, for small input, they are slower than single-call functions, due to state management. 184 * For small inputs, prefer `XXH32()` and `XXH64()`, which are better optimized. 185 * 186 * XXH state must first be allocated, using XXH*_createState() . 187 * 188 * Start a new hash by initializing state with a seed, using XXH*_reset(). 189 * 190 * Then, feed the hash state by calling XXH*_update() as many times as necessary. 191 * The function returns an error code, with 0 meaning OK, and any other value meaning there is an error. 192 * 193 * Finally, a hash value can be produced anytime, by using XXH*_digest(). 194 * This function returns the nn-bits hash as an int or long long. 195 * 196 * It's still possible to continue inserting input into the hash state after a digest, 197 * and generate some new hashes later on, by calling again XXH*_digest(). 198 * 199 * When done, free XXH state space if it was allocated dynamically. 200 */ 201 202 /*====== Canonical representation ======*/ 203 204 typedef struct { unsigned char digest[4]; } XXH32_canonical_t; 205 XXH_PUBLIC_API void XXH32_canonicalFromHash(XXH32_canonical_t* dst, XXH32_hash_t hash); 206 XXH_PUBLIC_API XXH32_hash_t XXH32_hashFromCanonical(const XXH32_canonical_t* src); 207 208 /* Default result type for XXH functions are primitive unsigned 32 and 64 bits. 209 * The canonical representation uses human-readable write convention, aka big-endian (large digits first). 210 * These functions allow transformation of hash result into and from its canonical format. 211 * This way, hash values can be written into a file / memory, and remain comparable on different systems and programs. 212 */ 213 214 215 #ifndef XXH_NO_LONG_LONG 216 /*-********************************************************************** 217 * 64-bit hash 218 ************************************************************************/ 219 typedef unsigned long long XXH64_hash_t; 220 221 /*! XXH64() : 222 Calculate the 64-bit hash of sequence of length "len" stored at memory address "input". 223 "seed" can be used to alter the result predictably. 224 This function runs faster on 64-bit systems, but slower on 32-bit systems (see benchmark). 225 */ 226 XXH_PUBLIC_API XXH64_hash_t XXH64 (const void* input, size_t length, unsigned long long seed); 227 228 /*====== Streaming ======*/ 229 typedef struct XXH64_state_s XXH64_state_t; /* incomplete type */ 230 XXH_PUBLIC_API XXH64_state_t* XXH64_createState(void); 231 XXH_PUBLIC_API XXH_errorcode XXH64_freeState(XXH64_state_t* statePtr); 232 XXH_PUBLIC_API void XXH64_copyState(XXH64_state_t* dst_state, const XXH64_state_t* src_state); 233 234 XXH_PUBLIC_API XXH_errorcode XXH64_reset (XXH64_state_t* statePtr, unsigned long long seed); 235 XXH_PUBLIC_API XXH_errorcode XXH64_update (XXH64_state_t* statePtr, const void* input, size_t length); 236 XXH_PUBLIC_API XXH64_hash_t XXH64_digest (const XXH64_state_t* statePtr); 237 238 /*====== Canonical representation ======*/ 239 typedef struct { unsigned char digest[8]; } XXH64_canonical_t; 240 XXH_PUBLIC_API void XXH64_canonicalFromHash(XXH64_canonical_t* dst, XXH64_hash_t hash); 241 XXH_PUBLIC_API XXH64_hash_t XXH64_hashFromCanonical(const XXH64_canonical_t* src); 242 #endif /* XXH_NO_LONG_LONG */ 243 244 245 246 #ifdef XXH_STATIC_LINKING_ONLY 247 248 /* ================================================================================================ 249 This section contains declarations which are not guaranteed to remain stable. 250 They may change in future versions, becoming incompatible with a different version of the library. 251 These declarations should only be used with static linking. 252 Never use them in association with dynamic linking ! 253 =================================================================================================== */ 254 255 /* These definitions are only present to allow 256 * static allocation of XXH state, on stack or in a struct for example. 257 * Never **ever** use members directly. */ 258 259 #if !defined (__VMS) \ 260 && (defined (__cplusplus) \ 261 || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */) ) 262 # include <stdint.h> 263 264 struct XXH32_state_s { 265 uint32_t total_len_32; 266 uint32_t large_len; 267 uint32_t v1; 268 uint32_t v2; 269 uint32_t v3; 270 uint32_t v4; 271 uint32_t mem32[4]; 272 uint32_t memsize; 273 uint32_t reserved; /* never read nor write, might be removed in a future version */ 274 }; /* typedef'd to XXH32_state_t */ 275 276 struct XXH64_state_s { 277 uint64_t total_len; 278 uint64_t v1; 279 uint64_t v2; 280 uint64_t v3; 281 uint64_t v4; 282 uint64_t mem64[4]; 283 uint32_t memsize; 284 uint32_t reserved[2]; /* never read nor write, might be removed in a future version */ 285 }; /* typedef'd to XXH64_state_t */ 286 287 # else 288 289 struct XXH32_state_s { 290 unsigned total_len_32; 291 unsigned large_len; 292 unsigned v1; 293 unsigned v2; 294 unsigned v3; 295 unsigned v4; 296 unsigned mem32[4]; 297 unsigned memsize; 298 unsigned reserved; /* never read nor write, might be removed in a future version */ 299 }; /* typedef'd to XXH32_state_t */ 300 301 # ifndef XXH_NO_LONG_LONG /* remove 64-bit support */ 302 struct XXH64_state_s { 303 unsigned long long total_len; 304 unsigned long long v1; 305 unsigned long long v2; 306 unsigned long long v3; 307 unsigned long long v4; 308 unsigned long long mem64[4]; 309 unsigned memsize; 310 unsigned reserved[2]; /* never read nor write, might be removed in a future version */ 311 }; /* typedef'd to XXH64_state_t */ 312 # endif 313 314 # endif 315 316 317 #if defined(XXH_INLINE_ALL) || defined(XXH_PRIVATE_API) 318 # include "xxhash.c" /* include xxhash function bodies as `static`, for inlining */ 319 #endif 320 321 #endif /* XXH_STATIC_LINKING_ONLY */ 322 323 324 #if defined (__cplusplus) 325 } 326 #endif 327 328 #endif /* XXHASH_H_5627135585666179 */