PHP源码中HashTable的简单示例 前些日子看了那篇对hasttable的介绍，于是也想自己运行一下，可是对于源码的调试不是太在行。 所以想了个办法：自己把PHP源码中的一些简单操作提取出来，自己运行一下，查看输出或调试。 于是花费了三天的空闲时间把一些相关的东西提取出来，主要是Zend目录下的zend_alloc.c,zend_alloc.h,zend_hash.c,zend_hash.h四个文件。 将与PHP相关的内存分配去掉，默认使用系统自带的内存分配方式。 另外：一些注释是http://www.phppan.com/2009/12/zend-hashtable/中所引用文章中的相关信息。 作者地址：http://www.phpinternals.com 下面的代码是一个可以运行的C程序，它初始化一个容量为50的hashtable（实际上分配了64个），然后将30到68，写入hash table，并将这个hash table 打印出来。 相信这会给一些想学习源码的童鞋一些帮助。 源代码如下：
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 | <!-- #include <stdio.h--> #include #include typedef unsigned long ulong; typedef unsigned int uint; typedef unsigned char zend_bool; typedef unsigned int size_t; typedef void (*dtor_func_t)(void *pDest); typedef ulong (*hash_func_t)(char *arKey, uint nKeyLength); #define SUCCESS 0 #define FAILURE -1 /* this MUST stay a negative number, or it may affect functions! */ #define HASH_UPDATE (1<<0) #define HASH_ADD (1<<1) #define HASH_NEXT_INSERT (1<<2) #define HASH_DEL_KEY 0 #define perealloc_recoverable(ptr, size, persistent) (__zend_realloc((ptr), (size))) #define pefree_rel(ptr, persistent) (free(ptr)) // 此处省略了使用PHP的内存分配函数 #define pemalloc_rel(size, persistent) (__zend_malloc(size)) #define perealloc_rel(ptr, size, persistent) (__zend_realloc((ptr), (size))) #define pemalloc(size, persistent) (__zend_malloc(size)) #define pefree(ptr, persistent) (free(ptr)) inline static void * __zend_malloc(size_t len) { void *tmp = malloc(len); if (tmp) { return tmp; } fprintf(stderr, "Out of memory\n"); exit(1); } inline static void * __zend_realloc(void *p, size_t len) { p = realloc(p, len); if (p) { return p; } fprintf(stderr, "Out of memory\n"); exit(1); } typedef struct bucket { ulong h; /* Used for numeric indexing */ uint nKeyLength; /* key 长度 */ void *pData; /* 指向Bucket中保存的数据的指针 */ void *pDataPtr; /* 指针数据 */ struct bucket *pListNext; /* 指向HashTable桶列中下一个元素 */ struct bucket *pListLast; /* 指向HashTable桶列中前一个元素 */ struct bucket *pNext; /* 指向具有同一个hash值的桶列的后一个元素 */ struct bucket *pLast; /* 指向具有同一个hash值的桶列的前一个元素 */ char arKey[1]; /* 必须是最后一个成员，key名称*/ } Bucket; typedef struct _hashtable { uint nTableSize; /*指定了HashTable的大小，同时它限定了HashTable中能保存Bucket的最大数量 此 数越大，系统为HashTable分配的内存就越多。为了提高计算效率， 系统自动会将nTableSize调整到最小一个不小于nTableSize的2 的整数次方*/ uint nTableMask; /*nTableMask的值永远是nTableSize – 1，引入这个字段的主要目的是为了提高计算效率*/ uint nNumOfElements; /*记录HashTable当前保存的数据元素的个数*/ ulong nNextFreeElement; /*记录HashTable中下一个可用于插入数据元素的arBuckets的索引*/ Bucket *pInternalPointer; /* Used for element traversal */ Bucket *pListHead; /*Bucket双向链表的第一个元素*/ Bucket *pListTail; /*Bucket双向链表的最后一元素*/ Bucket **arBuckets; /*存储Bucket双向链表*/ dtor_func_t pDestructor; /*函数指针，在HashTable的增加、修改、删除Bucket时自动调用，用于处理相关数据的清理工作*/ zend_bool persistent; /*指出了Bucket内存分配的方式。如果persisient为TRUE，则使用操作系统本身的内存分配函数为Bucket分配内存，否则使用PHP的内存分配函数。*/ unsigned char nApplyCount; /*nApplyCount与bApplyProtection结合提供了一个防止在遍历HashTable时进入递归循环时的一种机制*/ zend_bool bApplyProtection; } HashTable; typedef struct _zend_hash_key { char *arKey; uint nKeyLength; ulong h; } zend_hash_key; typedef zend_bool (*merge_checker_func_t)(HashTable *target_ht, void *source_data, zend_hash_key *hash_key, void *pParam); #define CONNECT_TO_BUCKET_DLLIST(element, list_head) \ (element)->pNext = (list_head); \ (element)->pLast = NULL; \ if ((element)->pNext) { \ (element)->pNext->pLast = (element); \ } #define CONNECT_TO_GLOBAL_DLLIST(element, ht) \ (element)->pListLast = (ht)->pListTail; \ (ht)->pListTail = (element); \ (element)->pListNext = NULL; \ if ((element)->pListLast != NULL) { \ (element)->pListLast->pListNext = (element); \ } \ if (!(ht)->pListHead) { \ (ht)->pListHead = (element); \ } \ if ((ht)->pInternalPointer == NULL) { \ (ht)->pInternalPointer = (element); \ } #define ZEND_HASH_IF_FULL_DO_RESIZE(ht) \ if ((ht)->nNumOfElements > (ht)->nTableSize) { \ zend_hash_do_resize(ht); \ } int zend_hash_rehash(HashTable *ht) { Bucket *p; uint nIndex; memset(ht->arBuckets, 0, ht->nTableSize * sizeof(Bucket *)); p = ht->pListHead; while (p != NULL) { nIndex = p->h & ht->nTableMask; CONNECT_TO_BUCKET_DLLIST(p, ht->arBuckets[nIndex]); ht->arBuckets[nIndex] = p; p = p->pListNext; } return SUCCESS; } static int zend_hash_do_resize(HashTable *ht) { Bucket **t; if ((ht->nTableSize << 1) > 0) { /* Let's double the table size */ t = (Bucket **) perealloc_recoverable(ht->arBuckets, (ht->nTableSize << 1) * sizeof(Bucket *), ht->persistent); if (t) { ht->arBuckets = t; ht->nTableSize = (ht->nTableSize << 1); ht->nTableMask = ht->nTableSize - 1; zend_hash_rehash(ht); return SUCCESS; } return FAILURE; } return SUCCESS; } #define UPDATE_DATA(ht, p, pData, nDataSize) \ if (nDataSize == sizeof(void*)) { \ if ((p)->pData != &(p)->pDataPtr) { \ pefree_rel((p)->pData, (ht)->persistent); \ } \ memcpy(&(p)->pDataPtr, pData, sizeof(void *)); \ (p)->pData = &(p)->pDataPtr; \ } else { \ if ((p)->pData == &(p)->pDataPtr) { \ (p)->pData = (void *) pemalloc_rel(nDataSize, (ht)->persistent); \ (p)->pDataPtr=NULL; \ } else { \ (p)->pData = (void *) perealloc_rel((p)->pData, nDataSize, (ht)->persistent); \ /* (p)->pDataPtr is already NULL so no need to initialize it */ \ } \ memcpy((p)->pData, pData, nDataSize); \ } #define INIT_DATA(ht, p, pData, nDataSize); \ if (nDataSize == sizeof(void*)) { \ memcpy(&(p)->pDataPtr, pData, sizeof(void *)); \ (p)->pData = &(p)->pDataPtr; \ } else { \ (p)->pData = (void *) pemalloc_rel(nDataSize, (ht)->persistent);\ if (!(p)->pData) { \ pefree_rel(p, (ht)->persistent); \ return FAILURE; \ } \ memcpy((p)->pData, pData, nDataSize); \ (p)->pDataPtr=NULL; \ } static inline ulong zend_inline_hash_func(char *arKey, uint nKeyLength) { register ulong hash = 5381; /* variant with the hash unrolled eight times */ for (; nKeyLength >= 8; nKeyLength -= 8) { hash = ((hash << 5) + hash) + *arKey++; hash = ((hash << 5) + hash) + *arKey++; hash = ((hash << 5) + hash) + *arKey++; hash = ((hash << 5) + hash) + *arKey++; hash = ((hash << 5) + hash) + *arKey++; hash = ((hash << 5) + hash) + *arKey++; hash = ((hash << 5) + hash) + *arKey++; hash = ((hash << 5) + hash) + *arKey++; } switch (nKeyLength) { case 7: hash = ((hash << 5) + hash) + *arKey++; /* fallthrough... */ case 6: hash = ((hash << 5) + hash) + *arKey++; /* fallthrough... */ case 5: hash = ((hash << 5) + hash) + *arKey++; /* fallthrough... */ case 4: hash = ((hash << 5) + hash) + *arKey++; /* fallthrough... */ case 3: hash = ((hash << 5) + hash) + *arKey++; /* fallthrough... */ case 2: hash = ((hash << 5) + hash) + *arKey++; /* fallthrough... */ case 1: hash = ((hash << 5) + hash) + *arKey++; break; case 0: break; } return hash; } ulong zend_hash_func(char *arKey, uint nKeyLength) { return zend_inline_hash_func(arKey, nKeyLength); } // 省略了 int zend_hash_init(HashTable *ht, uint nSize, hash_func_t pHashFunction, dtor_func_t pDestructor) { uint i = 3; Bucket **tmp; zend_bool persistent = 1; if (nSize >= 0x80000000) { /* prevent overflow */ ht->nTableSize = 0x80000000; } else { while ((1U << i) < nSize) { i++; } ht->nTableSize = 1 << i; } ht->nTableMask = ht->nTableSize - 1; ht->pDestructor = pDestructor; ht->arBuckets = NULL; ht->pListHead = NULL; ht->pListTail = NULL; ht->nNumOfElements = 0; ht->nNextFreeElement = 0; ht->pInternalPointer = NULL; ht->persistent = persistent; ht->nApplyCount = 0; ht->bApplyProtection = 1; tmp = (Bucket **) calloc(ht->nTableSize, sizeof(Bucket *)); if (!tmp) { return FAILURE; } ht->arBuckets = tmp; return SUCCESS; } int zend_hash_add_or_update(HashTable *ht, char *arKey, uint nKeyLength, void *pData, uint nDataSize, void **pDest, int flag) { ulong h; uint nIndex; Bucket *p; if (nKeyLength <= 0) { return FAILURE; } h = zend_inline_hash_func(arKey, nKeyLength); nIndex = h & ht->nTableMask; p = ht->arBuckets[nIndex]; while (p != NULL) { if ((p->h == h) && (p->nKeyLength == nKeyLength)) { if (!memcmp(p->arKey, arKey, nKeyLength)) { if (flag & HASH_ADD) { return FAILURE; } if (ht->pDestructor) { ht->pDestructor(p->pData); } UPDATE_DATA(ht, p, pData, nDataSize); if (pDest) { *pDest = p->pData; } return SUCCESS; } } p = p->pNext; } p = (Bucket *) pemalloc(sizeof(Bucket) - 1 + nKeyLength, ht->persistent); if (!p) { return FAILURE; } memcpy(p->arKey, arKey, nKeyLength); p->nKeyLength = nKeyLength; INIT_DATA(ht, p, pData, nDataSize); p->h = h; CONNECT_TO_BUCKET_DLLIST(p, ht->arBuckets[nIndex]); if (pDest) { *pDest = p->pData; } CONNECT_TO_GLOBAL_DLLIST(p, ht); ht->arBuckets[nIndex] = p; ht->nNumOfElements++; ZEND_HASH_IF_FULL_DO_RESIZE(ht); /* If the Hash table is full, resize it */ return SUCCESS; } void zend_hash_destroy(HashTable *ht) { Bucket *p, *q; p = ht->pListHead; while (p != NULL) { q = p; p = p->pListNext; if (ht->pDestructor) { ht->pDestructor(q->pData); } if (q->pData != &q->pDataPtr) { pefree(q->pData, ht->persistent); } pefree(q, ht->persistent); } pefree(ht->arBuckets, ht->persistent); } int zend_hash_find(HashTable *ht, char *arKey, uint nKeyLength, void **pData) { ulong h; uint nIndex; Bucket *p; h = zend_inline_hash_func(arKey, nKeyLength); nIndex = h & ht->nTableMask; p = ht->arBuckets[nIndex]; while (p != NULL) { if ((p->h == h) && (p->nKeyLength == nKeyLength)) { if (!memcmp(p->arKey, arKey, nKeyLength)) { *pData = p->pData; return SUCCESS; } } p = p->pNext; } return FAILURE; } void zend_hash_display(HashTable *ht) { Bucket *p; uint i; int flag = 0 ; for (i = 0; i < ht->nTableSize; i++) { p = ht->arBuckets[i]; flag = 0; while (p != NULL) { printf("(%d %s <==> 0x%lX %d) ", i, p->arKey, p->h, p->pNext); p = p->pNext; flag = 1; } if (flag == 1) { printf("\n"); } } p = ht->pListTail; while (p != NULL) { printf("%s <==> 0x%lX\n", p->arKey, p->h); p = p->pListLast; } } int main() { int i; char ch[20]; HashTable ht; zend_hash_init(&ht, 50, NULL, NULL); for (i = 30; i < 68; i++) { sprintf(ch, "%d", i); ch[strlen(ch) + 1] = '\0'; zend_hash_add_or_update(&ht, ch, strlen(ch) + 1, NULL, 0, NULL, 0); } zend_hash_display(&ht); zend_hash_destroy(&ht); return 0; } ?> |
Pingback引用通告： PHP源码阅读笔记四：count函数 | 胖子的空间
Pingback引用通告： PHP源码阅读笔记十：array_keys,array_values函数 | 胖子的空间
Pingback引用通告： PHP源码阅读笔记二十：array_flip,array_reverse函数 | 胖子的空间
呵呵，不错哦。
谢谢！呵
源代码上那个大大的<?PHP 一下刺激了我的眼睛。
多谢，已修复
再多一点注释就好了，后面摸索了好久才看懂，呜呜