1 /* $NetBSD: hash.c,v 1.57 2020/11/14 21:29:44 rillig Exp $ */
4 * Copyright (c) 1988, 1989, 1990 The Regents of the University of California.
7 * This code is derived from software contributed to Berkeley by
10 * Redistribution and use in source and binary forms, with or without
11 * modification, are permitted provided that the following conditions
13 * 1. Redistributions of source code must retain the above copyright
14 * notice, this list of conditions and the following disclaimer.
15 * 2. Redistributions in binary form must reproduce the above copyright
16 * notice, this list of conditions and the following disclaimer in the
17 * documentation and/or other materials provided with the distribution.
18 * 3. Neither the name of the University nor the names of its contributors
19 * may be used to endorse or promote products derived from this software
20 * without specific prior written permission.
22 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
23 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
24 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
25 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
26 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
27 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
28 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
29 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
30 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
31 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
36 * Copyright (c) 1988, 1989 by Adam de Boor
37 * Copyright (c) 1989 by Berkeley Softworks
38 * All rights reserved.
40 * This code is derived from software contributed to Berkeley by
43 * Redistribution and use in source and binary forms, with or without
44 * modification, are permitted provided that the following conditions
46 * 1. Redistributions of source code must retain the above copyright
47 * notice, this list of conditions and the following disclaimer.
48 * 2. Redistributions in binary form must reproduce the above copyright
49 * notice, this list of conditions and the following disclaimer in the
50 * documentation and/or other materials provided with the distribution.
51 * 3. All advertising materials mentioning features or use of this software
52 * must display the following acknowledgement:
53 * This product includes software developed by the University of
54 * California, Berkeley and its contributors.
55 * 4. Neither the name of the University nor the names of its contributors
56 * may be used to endorse or promote products derived from this software
57 * without specific prior written permission.
59 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
60 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
61 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
62 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
63 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
64 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
65 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
66 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
67 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
68 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
72 /* Hash tables with string keys. */
76 /* "@(#)hash.c 8.1 (Berkeley) 6/6/93" */
77 MAKE_RCSID("$NetBSD: hash.c,v 1.57 2020/11/14 21:29:44 rillig Exp $");
80 * The ratio of # entries to # buckets at which we rebuild the table to
83 #define rebuildLimit 3
85 /* This hash function matches Gosling's emacs and java.lang.String. */
87 hash(const char *key, size_t *out_keylen)
92 h = (h << 5) - h + (unsigned char)*p++;
93 if (out_keylen != NULL)
94 *out_keylen = (size_t)(p - key);
99 Hash_Hash(const char *key)
101 return hash(key, NULL);
105 HashTable_Find(HashTable *t, unsigned int h, const char *key)
108 unsigned int chainlen = 0;
110 #ifdef DEBUG_HASH_LOOKUP
111 DEBUG4(HASH, "%s: %p h=%08x key=%s\n", __func__, t, h, key);
114 for (e = t->buckets[h & t->bucketsMask]; e != NULL; e = e->next) {
116 if (e->key_hash == h && strcmp(e->key, key) == 0)
120 if (chainlen > t->maxchain)
121 t->maxchain = chainlen;
126 /* Set up the hash table. */
128 HashTable_Init(HashTable *t)
130 unsigned int n = 16, i;
131 HashEntry **buckets = bmake_malloc(sizeof *buckets * n);
132 for (i = 0; i < n; i++)
135 t->buckets = buckets;
138 t->bucketsMask = n - 1;
142 /* Remove everything from the hash table and frees up the memory. */
144 HashTable_Done(HashTable *t)
146 HashEntry **buckets = t->buckets;
147 size_t i, n = t->bucketsSize;
149 for (i = 0; i < n; i++) {
150 HashEntry *he = buckets[i];
152 HashEntry *next = he->next;
164 /* Find the entry corresponding to the key, or return NULL. */
166 HashTable_FindEntry(HashTable *t, const char *key)
168 unsigned int h = hash(key, NULL);
169 return HashTable_Find(t, h, key);
172 /* Find the value corresponding to the key, or return NULL. */
174 HashTable_FindValue(HashTable *t, const char *key)
176 HashEntry *he = HashTable_FindEntry(t, key);
177 return he != NULL ? he->value : NULL;
180 /* Find the value corresponding to the key and the precomputed hash,
183 HashTable_FindValueHash(HashTable *t, const char *key, unsigned int h)
185 HashEntry *he = HashTable_Find(t, h, key);
186 return he != NULL ? he->value : NULL;
189 /* Make the hash table larger. Any bucket numbers from the old table become
190 * invalid; the hash codes stay valid though. */
192 HashTable_Enlarge(HashTable *t)
194 unsigned int oldSize = t->bucketsSize;
195 HashEntry **oldBuckets = t->buckets;
196 unsigned int newSize = 2 * oldSize;
197 unsigned int newMask = newSize - 1;
198 HashEntry **newBuckets = bmake_malloc(sizeof *newBuckets * newSize);
201 for (i = 0; i < newSize; i++)
202 newBuckets[i] = NULL;
204 for (i = 0; i < oldSize; i++) {
205 HashEntry *he = oldBuckets[i];
207 HashEntry *next = he->next;
208 he->next = newBuckets[he->key_hash & newMask];
209 newBuckets[he->key_hash & newMask] = he;
216 t->bucketsSize = newSize;
217 t->bucketsMask = newMask;
218 t->buckets = newBuckets;
219 DEBUG5(HASH, "%s: %p size=%d entries=%d maxchain=%d\n",
220 __func__, t, t->bucketsSize, t->numEntries, t->maxchain);
224 /* Find or create an entry corresponding to the key.
225 * Return in out_isNew whether a new entry has been created. */
227 HashTable_CreateEntry(HashTable *t, const char *key, Boolean *out_isNew)
230 unsigned int h = hash(key, &keylen);
231 HashEntry *he = HashTable_Find(t, h, key);
234 if (out_isNew != NULL)
239 if (t->numEntries >= rebuildLimit * t->bucketsSize)
240 HashTable_Enlarge(t);
242 he = bmake_malloc(sizeof *he + keylen);
245 memcpy(he->key, key, keylen + 1);
247 he->next = t->buckets[h & t->bucketsMask];
248 t->buckets[h & t->bucketsMask] = he;
251 if (out_isNew != NULL)
257 HashTable_Set(HashTable *t, const char *key, void *value)
259 HashEntry *he = HashTable_CreateEntry(t, key, NULL);
260 HashEntry_Set(he, value);
264 /* Delete the entry from the table and free the associated memory. */
266 HashTable_DeleteEntry(HashTable *t, HashEntry *he)
268 HashEntry **ref = &t->buckets[he->key_hash & t->bucketsMask];
271 for (; (p = *ref) != NULL; ref = &p->next) {
282 /* Set things up for iterating over all entries in the hash table. */
284 HashIter_Init(HashIter *hi, HashTable *t)
291 /* Return the next entry in the hash table, or NULL if the end of the table
294 HashIter_Next(HashIter *hi)
296 HashTable *t = hi->table;
297 HashEntry *he = hi->entry;
298 HashEntry **buckets = t->buckets;
299 unsigned int bucketsSize = t->bucketsSize;
302 he = he->next; /* skip the most recently returned entry */
304 while (he == NULL) { /* find the next nonempty chain */
305 if (hi->nextBucket >= bucketsSize)
307 he = buckets[hi->nextBucket++];
314 HashTable_DebugStats(HashTable *t, const char *name)
316 DEBUG4(HASH, "HashTable %s: size=%u numEntries=%u maxchain=%u\n",
317 name, t->bucketsSize, t->numEntries, t->maxchain);