├── License.md ├── README ├── hashmap.c ├── hashmap.h └── main.c /License.md: -------------------------------------------------------------------------------- 1 |

2 | 4 | CC0 5 | 6 |
7 | To the extent possible under law, 8 | 10 | Pete Warden 11 | has waived all copyright and related or neighboring rights to 12 | C hashmap. 13 |

14 | -------------------------------------------------------------------------------- /README: -------------------------------------------------------------------------------- 1 | This is a simple C hashmap, using strings for the keys. 2 | 3 | Originally based on code by Eliot Back at http://elliottback.com/wp/hashmap-implementation-in-c/ 4 | Reworked by Pete Warden - http://petewarden.typepad.com/searchbrowser/2010/01/c-hashmap.html 5 | 6 | This version is now deprecated, since it's unmaintained. @sheredom has a newer version at 7 | https://github.com/sheredom/hashmap.h 8 | 9 | main.c contains an example that tests the functionality of the hashmap module. 10 | To compile it, run something like this on your system: 11 | gcc main.c hashmap.c -o hashmaptest 12 | 13 | There are no restrictions on how you reuse this code. 14 | -------------------------------------------------------------------------------- /hashmap.c: -------------------------------------------------------------------------------- 1 | /* 2 | * Generic map implementation. 3 | */ 4 | #include "hashmap.h" 5 | 6 | #include 7 | #include 8 | #include 9 | 10 | #define INITIAL_SIZE (256) 11 | #define MAX_CHAIN_LENGTH (8) 12 | 13 | /* We need to keep keys and values */ 14 | typedef struct _hashmap_element{ 15 | char* key; 16 | int in_use; 17 | any_t data; 18 | } hashmap_element; 19 | 20 | /* A hashmap has some maximum size and current size, 21 | * as well as the data to hold. */ 22 | typedef struct _hashmap_map{ 23 | int table_size; 24 | int size; 25 | hashmap_element *data; 26 | } hashmap_map; 27 | 28 | /* 29 | * Return an empty hashmap, or NULL on failure. 30 | */ 31 | map_t hashmap_new() { 32 | hashmap_map* m = (hashmap_map*) malloc(sizeof(hashmap_map)); 33 | if(!m) goto err; 34 | 35 | m->data = (hashmap_element*) calloc(INITIAL_SIZE, sizeof(hashmap_element)); 36 | if(!m->data) goto err; 37 | 38 | m->table_size = INITIAL_SIZE; 39 | m->size = 0; 40 | 41 | return m; 42 | err: 43 | if (m) 44 | hashmap_free(m); 45 | return NULL; 46 | } 47 | 48 | /* The implementation here was originally done by Gary S. Brown. I have 49 | borrowed the tables directly, and made some minor changes to the 50 | crc32-function (including changing the interface). //ylo */ 51 | 52 | /* ============================================================= */ 53 | /* COPYRIGHT (C) 1986 Gary S. Brown. You may use this program, or */ 54 | /* code or tables extracted from it, as desired without restriction. */ 55 | /* */ 56 | /* First, the polynomial itself and its table of feedback terms. The */ 57 | /* polynomial is */ 58 | /* X^32+X^26+X^23+X^22+X^16+X^12+X^11+X^10+X^8+X^7+X^5+X^4+X^2+X^1+X^0 */ 59 | /* */ 60 | /* Note that we take it "backwards" and put the highest-order term in */ 61 | /* the lowest-order bit. The X^32 term is "implied"; the LSB is the */ 62 | /* X^31 term, etc. The X^0 term (usually shown as "+1") results in */ 63 | /* the MSB being 1. */ 64 | /* */ 65 | /* Note that the usual hardware shift register implementation, which */ 66 | /* is what we're using (we're merely optimizing it by doing eight-bit */ 67 | /* chunks at a time) shifts bits into the lowest-order term. In our */ 68 | /* implementation, that means shifting towards the right. Why do we */ 69 | /* do it this way? Because the calculated CRC must be transmitted in */ 70 | /* order from highest-order term to lowest-order term. UARTs transmit */ 71 | /* characters in order from LSB to MSB. By storing the CRC this way, */ 72 | /* we hand it to the UART in the order low-byte to high-byte; the UART */ 73 | /* sends each low-bit to hight-bit; and the result is transmission bit */ 74 | /* by bit from highest- to lowest-order term without requiring any bit */ 75 | /* shuffling on our part. Reception works similarly. */ 76 | /* */ 77 | /* The feedback terms table consists of 256, 32-bit entries. Notes: */ 78 | /* */ 79 | /* The table can be generated at runtime if desired; code to do so */ 80 | /* is shown later. It might not be obvious, but the feedback */ 81 | /* terms simply represent the results of eight shift/xor opera- */ 82 | /* tions for all combinations of data and CRC register values. */ 83 | /* */ 84 | /* The values must be right-shifted by eight bits by the "updcrc" */ 85 | /* logic; the shift must be unsigned (bring in zeroes). On some */ 86 | /* hardware you could probably optimize the shift in assembler by */ 87 | /* using byte-swap instructions. */ 88 | /* polynomial $edb88320 */ 89 | /* */ 90 | /* -------------------------------------------------------------------- */ 91 | 92 | static unsigned long crc32_tab[] = { 93 | 0x00000000L, 0x77073096L, 0xee0e612cL, 0x990951baL, 0x076dc419L, 94 | 0x706af48fL, 0xe963a535L, 0x9e6495a3L, 0x0edb8832L, 0x79dcb8a4L, 95 | 0xe0d5e91eL, 0x97d2d988L, 0x09b64c2bL, 0x7eb17cbdL, 0xe7b82d07L, 96 | 0x90bf1d91L, 0x1db71064L, 0x6ab020f2L, 0xf3b97148L, 0x84be41deL, 97 | 0x1adad47dL, 0x6ddde4ebL, 0xf4d4b551L, 0x83d385c7L, 0x136c9856L, 98 | 0x646ba8c0L, 0xfd62f97aL, 0x8a65c9ecL, 0x14015c4fL, 0x63066cd9L, 99 | 0xfa0f3d63L, 0x8d080df5L, 0x3b6e20c8L, 0x4c69105eL, 0xd56041e4L, 100 | 0xa2677172L, 0x3c03e4d1L, 0x4b04d447L, 0xd20d85fdL, 0xa50ab56bL, 101 | 0x35b5a8faL, 0x42b2986cL, 0xdbbbc9d6L, 0xacbcf940L, 0x32d86ce3L, 102 | 0x45df5c75L, 0xdcd60dcfL, 0xabd13d59L, 0x26d930acL, 0x51de003aL, 103 | 0xc8d75180L, 0xbfd06116L, 0x21b4f4b5L, 0x56b3c423L, 0xcfba9599L, 104 | 0xb8bda50fL, 0x2802b89eL, 0x5f058808L, 0xc60cd9b2L, 0xb10be924L, 105 | 0x2f6f7c87L, 0x58684c11L, 0xc1611dabL, 0xb6662d3dL, 0x76dc4190L, 106 | 0x01db7106L, 0x98d220bcL, 0xefd5102aL, 0x71b18589L, 0x06b6b51fL, 107 | 0x9fbfe4a5L, 0xe8b8d433L, 0x7807c9a2L, 0x0f00f934L, 0x9609a88eL, 108 | 0xe10e9818L, 0x7f6a0dbbL, 0x086d3d2dL, 0x91646c97L, 0xe6635c01L, 109 | 0x6b6b51f4L, 0x1c6c6162L, 0x856530d8L, 0xf262004eL, 0x6c0695edL, 110 | 0x1b01a57bL, 0x8208f4c1L, 0xf50fc457L, 0x65b0d9c6L, 0x12b7e950L, 111 | 0x8bbeb8eaL, 0xfcb9887cL, 0x62dd1ddfL, 0x15da2d49L, 0x8cd37cf3L, 112 | 0xfbd44c65L, 0x4db26158L, 0x3ab551ceL, 0xa3bc0074L, 0xd4bb30e2L, 113 | 0x4adfa541L, 0x3dd895d7L, 0xa4d1c46dL, 0xd3d6f4fbL, 0x4369e96aL, 114 | 0x346ed9fcL, 0xad678846L, 0xda60b8d0L, 0x44042d73L, 0x33031de5L, 115 | 0xaa0a4c5fL, 0xdd0d7cc9L, 0x5005713cL, 0x270241aaL, 0xbe0b1010L, 116 | 0xc90c2086L, 0x5768b525L, 0x206f85b3L, 0xb966d409L, 0xce61e49fL, 117 | 0x5edef90eL, 0x29d9c998L, 0xb0d09822L, 0xc7d7a8b4L, 0x59b33d17L, 118 | 0x2eb40d81L, 0xb7bd5c3bL, 0xc0ba6cadL, 0xedb88320L, 0x9abfb3b6L, 119 | 0x03b6e20cL, 0x74b1d29aL, 0xead54739L, 0x9dd277afL, 0x04db2615L, 120 | 0x73dc1683L, 0xe3630b12L, 0x94643b84L, 0x0d6d6a3eL, 0x7a6a5aa8L, 121 | 0xe40ecf0bL, 0x9309ff9dL, 0x0a00ae27L, 0x7d079eb1L, 0xf00f9344L, 122 | 0x8708a3d2L, 0x1e01f268L, 0x6906c2feL, 0xf762575dL, 0x806567cbL, 123 | 0x196c3671L, 0x6e6b06e7L, 0xfed41b76L, 0x89d32be0L, 0x10da7a5aL, 124 | 0x67dd4accL, 0xf9b9df6fL, 0x8ebeeff9L, 0x17b7be43L, 0x60b08ed5L, 125 | 0xd6d6a3e8L, 0xa1d1937eL, 0x38d8c2c4L, 0x4fdff252L, 0xd1bb67f1L, 126 | 0xa6bc5767L, 0x3fb506ddL, 0x48b2364bL, 0xd80d2bdaL, 0xaf0a1b4cL, 127 | 0x36034af6L, 0x41047a60L, 0xdf60efc3L, 0xa867df55L, 0x316e8eefL, 128 | 0x4669be79L, 0xcb61b38cL, 0xbc66831aL, 0x256fd2a0L, 0x5268e236L, 129 | 0xcc0c7795L, 0xbb0b4703L, 0x220216b9L, 0x5505262fL, 0xc5ba3bbeL, 130 | 0xb2bd0b28L, 0x2bb45a92L, 0x5cb36a04L, 0xc2d7ffa7L, 0xb5d0cf31L, 131 | 0x2cd99e8bL, 0x5bdeae1dL, 0x9b64c2b0L, 0xec63f226L, 0x756aa39cL, 132 | 0x026d930aL, 0x9c0906a9L, 0xeb0e363fL, 0x72076785L, 0x05005713L, 133 | 0x95bf4a82L, 0xe2b87a14L, 0x7bb12baeL, 0x0cb61b38L, 0x92d28e9bL, 134 | 0xe5d5be0dL, 0x7cdcefb7L, 0x0bdbdf21L, 0x86d3d2d4L, 0xf1d4e242L, 135 | 0x68ddb3f8L, 0x1fda836eL, 0x81be16cdL, 0xf6b9265bL, 0x6fb077e1L, 136 | 0x18b74777L, 0x88085ae6L, 0xff0f6a70L, 0x66063bcaL, 0x11010b5cL, 137 | 0x8f659effL, 0xf862ae69L, 0x616bffd3L, 0x166ccf45L, 0xa00ae278L, 138 | 0xd70dd2eeL, 0x4e048354L, 0x3903b3c2L, 0xa7672661L, 0xd06016f7L, 139 | 0x4969474dL, 0x3e6e77dbL, 0xaed16a4aL, 0xd9d65adcL, 0x40df0b66L, 140 | 0x37d83bf0L, 0xa9bcae53L, 0xdebb9ec5L, 0x47b2cf7fL, 0x30b5ffe9L, 141 | 0xbdbdf21cL, 0xcabac28aL, 0x53b39330L, 0x24b4a3a6L, 0xbad03605L, 142 | 0xcdd70693L, 0x54de5729L, 0x23d967bfL, 0xb3667a2eL, 0xc4614ab8L, 143 | 0x5d681b02L, 0x2a6f2b94L, 0xb40bbe37L, 0xc30c8ea1L, 0x5a05df1bL, 144 | 0x2d02ef8dL 145 | }; 146 | 147 | /* Return a 32-bit CRC of the contents of the buffer. */ 148 | 149 | unsigned long crc32(const unsigned char *s, unsigned int len) 150 | { 151 | unsigned int i; 152 | unsigned long crc32val; 153 | 154 | crc32val = 0; 155 | for (i = 0; i < len; i ++) 156 | { 157 | crc32val = 158 | crc32_tab[(crc32val ^ s[i]) & 0xff] ^ 159 | (crc32val >> 8); 160 | } 161 | return crc32val; 162 | } 163 | 164 | /* 165 | * Hashing function for a string 166 | */ 167 | unsigned int hashmap_hash_int(hashmap_map * m, char* keystring){ 168 | 169 | unsigned long key = crc32((unsigned char*)(keystring), strlen(keystring)); 170 | 171 | /* Robert Jenkins' 32 bit Mix Function */ 172 | key += (key << 12); 173 | key ^= (key >> 22); 174 | key += (key << 4); 175 | key ^= (key >> 9); 176 | key += (key << 10); 177 | key ^= (key >> 2); 178 | key += (key << 7); 179 | key ^= (key >> 12); 180 | 181 | /* Knuth's Multiplicative Method */ 182 | key = (key >> 3) * 2654435761; 183 | 184 | return key % m->table_size; 185 | } 186 | 187 | /* 188 | * Return the integer of the location in data 189 | * to store the point to the item, or MAP_FULL. 190 | */ 191 | int hashmap_hash(map_t in, char* key){ 192 | int curr; 193 | int i; 194 | 195 | /* Cast the hashmap */ 196 | hashmap_map* m = (hashmap_map *) in; 197 | 198 | /* If full, return immediately */ 199 | if(m->size >= (m->table_size/2)) return MAP_FULL; 200 | 201 | /* Find the best index */ 202 | curr = hashmap_hash_int(m, key); 203 | 204 | /* Linear probing */ 205 | for(i = 0; i< MAX_CHAIN_LENGTH; i++){ 206 | if(m->data[curr].in_use == 0) 207 | return curr; 208 | 209 | if(m->data[curr].in_use == 1 && (strcmp(m->data[curr].key,key)==0)) 210 | return curr; 211 | 212 | curr = (curr + 1) % m->table_size; 213 | } 214 | 215 | return MAP_FULL; 216 | } 217 | 218 | /* 219 | * Doubles the size of the hashmap, and rehashes all the elements 220 | */ 221 | int hashmap_rehash(map_t in){ 222 | int i; 223 | int old_size; 224 | hashmap_element* curr; 225 | 226 | /* Setup the new elements */ 227 | hashmap_map *m = (hashmap_map *) in; 228 | hashmap_element* temp = (hashmap_element *) 229 | calloc(2 * m->table_size, sizeof(hashmap_element)); 230 | if(!temp) return MAP_OMEM; 231 | 232 | /* Update the array */ 233 | curr = m->data; 234 | m->data = temp; 235 | 236 | /* Update the size */ 237 | old_size = m->table_size; 238 | m->table_size = 2 * m->table_size; 239 | m->size = 0; 240 | 241 | /* Rehash the elements */ 242 | for(i = 0; i < old_size; i++){ 243 | int status; 244 | 245 | if (curr[i].in_use == 0) 246 | continue; 247 | 248 | status = hashmap_put(m, curr[i].key, curr[i].data); 249 | if (status != MAP_OK) 250 | return status; 251 | } 252 | 253 | free(curr); 254 | 255 | return MAP_OK; 256 | } 257 | 258 | /* 259 | * Add a pointer to the hashmap with some key 260 | */ 261 | int hashmap_put(map_t in, char* key, any_t value){ 262 | int index; 263 | hashmap_map* m; 264 | 265 | /* Cast the hashmap */ 266 | m = (hashmap_map *) in; 267 | 268 | /* Find a place to put our value */ 269 | index = hashmap_hash(in, key); 270 | while(index == MAP_FULL){ 271 | if (hashmap_rehash(in) == MAP_OMEM) { 272 | return MAP_OMEM; 273 | } 274 | index = hashmap_hash(in, key); 275 | } 276 | 277 | /* Set the data */ 278 | m->data[index].data = value; 279 | m->data[index].key = key; 280 | m->data[index].in_use = 1; 281 | m->size++; 282 | 283 | return MAP_OK; 284 | } 285 | 286 | /* 287 | * Get your pointer out of the hashmap with a key 288 | */ 289 | int hashmap_get(map_t in, char* key, any_t *arg){ 290 | int curr; 291 | int i; 292 | hashmap_map* m; 293 | 294 | /* Cast the hashmap */ 295 | m = (hashmap_map *) in; 296 | 297 | /* Find data location */ 298 | curr = hashmap_hash_int(m, key); 299 | 300 | /* Linear probing, if necessary */ 301 | for(i = 0; idata[curr].in_use; 304 | if (in_use == 1){ 305 | if (strcmp(m->data[curr].key,key)==0){ 306 | *arg = (m->data[curr].data); 307 | return MAP_OK; 308 | } 309 | } 310 | 311 | curr = (curr + 1) % m->table_size; 312 | } 313 | 314 | *arg = NULL; 315 | 316 | /* Not found */ 317 | return MAP_MISSING; 318 | } 319 | 320 | /* 321 | * Iterate the function parameter over each element in the hashmap. The 322 | * additional any_t argument is passed to the function as its first 323 | * argument and the hashmap element is the second. 324 | */ 325 | int hashmap_iterate(map_t in, PFany f, any_t item) { 326 | int i; 327 | 328 | /* Cast the hashmap */ 329 | hashmap_map* m = (hashmap_map*) in; 330 | 331 | /* On empty hashmap, return immediately */ 332 | if (hashmap_length(m) <= 0) 333 | return MAP_MISSING; 334 | 335 | /* Linear probing */ 336 | for(i = 0; i< m->table_size; i++) 337 | if(m->data[i].in_use != 0) { 338 | any_t data = (any_t) (m->data[i].data); 339 | int status = f(item, data); 340 | if (status != MAP_OK) { 341 | return status; 342 | } 343 | } 344 | 345 | return MAP_OK; 346 | } 347 | 348 | /* 349 | * Remove an element with that key from the map 350 | */ 351 | int hashmap_remove(map_t in, char* key){ 352 | int i; 353 | int curr; 354 | hashmap_map* m; 355 | 356 | /* Cast the hashmap */ 357 | m = (hashmap_map *) in; 358 | 359 | /* Find key */ 360 | curr = hashmap_hash_int(m, key); 361 | 362 | /* Linear probing, if necessary */ 363 | for(i = 0; idata[curr].in_use; 366 | if (in_use == 1){ 367 | if (strcmp(m->data[curr].key,key)==0){ 368 | /* Blank out the fields */ 369 | m->data[curr].in_use = 0; 370 | m->data[curr].data = NULL; 371 | m->data[curr].key = NULL; 372 | 373 | /* Reduce the size */ 374 | m->size--; 375 | return MAP_OK; 376 | } 377 | } 378 | curr = (curr + 1) % m->table_size; 379 | } 380 | 381 | /* Data not found */ 382 | return MAP_MISSING; 383 | } 384 | 385 | /* Deallocate the hashmap */ 386 | void hashmap_free(map_t in){ 387 | hashmap_map* m = (hashmap_map*) in; 388 | free(m->data); 389 | free(m); 390 | } 391 | 392 | /* Return the length of the hashmap */ 393 | int hashmap_length(map_t in){ 394 | hashmap_map* m = (hashmap_map *) in; 395 | if(m != NULL) return m->size; 396 | else return 0; 397 | } -------------------------------------------------------------------------------- /hashmap.h: -------------------------------------------------------------------------------- 1 | /* 2 | * Generic hashmap manipulation functions 3 | * 4 | * Originally by Elliot C Back - http://elliottback.com/wp/hashmap-implementation-in-c/ 5 | * 6 | * Modified by Pete Warden to fix a serious performance problem, support strings as keys 7 | * and removed thread synchronization - http://petewarden.typepad.com 8 | */ 9 | #ifndef __HASHMAP_H__ 10 | #define __HASHMAP_H__ 11 | 12 | #define MAP_MISSING -3 /* No such element */ 13 | #define MAP_FULL -2 /* Hashmap is full */ 14 | #define MAP_OMEM -1 /* Out of Memory */ 15 | #define MAP_OK 0 /* OK */ 16 | 17 | /* 18 | * any_t is a pointer. This allows you to put arbitrary structures in 19 | * the hashmap. 20 | */ 21 | typedef void *any_t; 22 | 23 | /* 24 | * PFany is a pointer to a function that can take two any_t arguments 25 | * and return an integer. Returns status code.. 26 | */ 27 | typedef int (*PFany)(any_t, any_t); 28 | 29 | /* 30 | * map_t is a pointer to an internally maintained data structure. 31 | * Clients of this package do not need to know how hashmaps are 32 | * represented. They see and manipulate only map_t's. 33 | */ 34 | typedef any_t map_t; 35 | 36 | /* 37 | * Return an empty hashmap. Returns NULL if empty. 38 | */ 39 | extern map_t hashmap_new(); 40 | 41 | /* 42 | * Iteratively call f with argument (item, data) for 43 | * each element data in the hashmap. The function must 44 | * return a map status code. If it returns anything other 45 | * than MAP_OK the traversal is terminated. f must 46 | * not reenter any hashmap functions, or deadlock may arise. 47 | */ 48 | extern int hashmap_iterate(map_t in, PFany f, any_t item); 49 | 50 | /* 51 | * Add an element to the hashmap. Return MAP_OK or MAP_OMEM. 52 | */ 53 | extern int hashmap_put(map_t in, char* key, any_t value); 54 | 55 | /* 56 | * Get an element from the hashmap. Return MAP_OK or MAP_MISSING. 57 | */ 58 | extern int hashmap_get(map_t in, char* key, any_t *arg); 59 | 60 | /* 61 | * Remove an element from the hashmap. Return MAP_OK or MAP_MISSING. 62 | */ 63 | extern int hashmap_remove(map_t in, char* key); 64 | 65 | /* 66 | * Get any element. Return MAP_OK or MAP_MISSING. 67 | * remove - should the element be removed from the hashmap 68 | */ 69 | extern int hashmap_get_one(map_t in, any_t *arg, int remove); 70 | 71 | /* 72 | * Free the hashmap 73 | */ 74 | extern void hashmap_free(map_t in); 75 | 76 | /* 77 | * Get the current size of a hashmap 78 | */ 79 | extern int hashmap_length(map_t in); 80 | 81 | #endif __HASHMAP_H__ -------------------------------------------------------------------------------- /main.c: -------------------------------------------------------------------------------- 1 | /* 2 | * A unit test and example of how to use the simple C hashmap 3 | */ 4 | 5 | #include 6 | #include 7 | #include 8 | 9 | #include "hashmap.h" 10 | 11 | #define KEY_MAX_LENGTH (256) 12 | #define KEY_PREFIX ("somekey") 13 | #define KEY_COUNT (1024*1024) 14 | 15 | typedef struct data_struct_s 16 | { 17 | char key_string[KEY_MAX_LENGTH]; 18 | int number; 19 | } data_struct_t; 20 | 21 | int main(char* argv, int argc) 22 | { 23 | int index; 24 | int error; 25 | map_t mymap; 26 | char key_string[KEY_MAX_LENGTH]; 27 | data_struct_t* value; 28 | 29 | mymap = hashmap_new(); 30 | 31 | /* First, populate the hash map with ascending values */ 32 | for (index=0; indexkey_string, KEY_MAX_LENGTH, "%s%d", KEY_PREFIX, index); 37 | value->number = index; 38 | 39 | error = hashmap_put(mymap, value->key_string, value); 40 | assert(error==MAP_OK); 41 | } 42 | 43 | /* Now, check all of the expected values are there */ 44 | for (index=0; indexnumber==index); 53 | } 54 | 55 | /* Make sure that a value that wasn't in the map can't be found */ 56 | snprintf(key_string, KEY_MAX_LENGTH, "%s%d", KEY_PREFIX, KEY_COUNT); 57 | 58 | error = hashmap_get(mymap, key_string, (void**)(&value)); 59 | 60 | /* Make sure the value was not found */ 61 | assert(error==MAP_MISSING); 62 | 63 | /* Free all of the values we allocated and remove them from the map */ 64 | for (index=0; index