1 /* $NetBSD: hash.c,v 1.64 2021/04/11 12:46:54 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 1.64 2021/04/11 12:46:54 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_String(const char *key, size_t *out_keylen)
93 for (p = key; *p != '\0'; p++)
94 h = 31 * h + (unsigned char)*p;
96 if (out_keylen != NULL)
97 *out_keylen = (size_t)(p - key);
101 /* This hash function matches Gosling's Emacs and java.lang.String. */
103 Hash_Substring(Substring key)
109 for (p = key.start; p != key.end; p++)
110 h = 31 * h + (unsigned char)*p;
115 HashTable_Find(HashTable *t, unsigned int h, const char *key)
118 unsigned int chainlen = 0;
120 #ifdef DEBUG_HASH_LOOKUP
121 DEBUG4(HASH, "%s: %p h=%08x key=%s\n", __func__, t, h, key);
124 for (e = t->buckets[h & t->bucketsMask]; e != NULL; e = e->next) {
126 if (e->key_hash == h && strcmp(e->key, key) == 0)
130 if (chainlen > t->maxchain)
131 t->maxchain = chainlen;
137 HashEntry_KeyEquals(const HashEntry *he, Substring key)
139 const char *heKey, *p;
142 for (p = key.start; p != key.end; p++, heKey++)
143 if (*p != *heKey || *heKey == '\0')
145 return *heKey == '\0';
149 HashTable_FindEntryBySubstring(HashTable *t, Substring key, unsigned int h)
152 unsigned int chainlen = 0;
154 #ifdef DEBUG_HASH_LOOKUP
155 DEBUG4(HASH, "%s: %p h=%08x key=%.*s\n", __func__, t, h,
156 (int)Substring_Length(key), key.start);
159 for (e = t->buckets[h & t->bucketsMask]; e != NULL; e = e->next) {
161 if (e->key_hash == h && HashEntry_KeyEquals(e, key))
165 if (chainlen > t->maxchain)
166 t->maxchain = chainlen;
171 /* Set up the hash table. */
173 HashTable_Init(HashTable *t)
175 unsigned int n = 16, i;
176 HashEntry **buckets = bmake_malloc(sizeof *buckets * n);
177 for (i = 0; i < n; i++)
180 t->buckets = buckets;
183 t->bucketsMask = n - 1;
188 * Remove everything from the hash table and free up the memory for the keys
189 * of the hash table, but not for the values associated to these keys.
192 HashTable_Done(HashTable *t)
194 HashEntry **buckets = t->buckets;
195 size_t i, n = t->bucketsSize;
197 for (i = 0; i < n; i++) {
198 HashEntry *he = buckets[i];
200 HashEntry *next = he->next;
212 /* Find the entry corresponding to the key, or return NULL. */
214 HashTable_FindEntry(HashTable *t, const char *key)
216 unsigned int h = Hash_String(key, NULL);
217 return HashTable_Find(t, h, key);
220 /* Find the value corresponding to the key, or return NULL. */
222 HashTable_FindValue(HashTable *t, const char *key)
224 HashEntry *he = HashTable_FindEntry(t, key);
225 return he != NULL ? he->value : NULL;
229 * Find the value corresponding to the key and the precomputed hash,
233 HashTable_FindValueBySubstringHash(HashTable *t, Substring key, unsigned int h)
235 HashEntry *he = HashTable_FindEntryBySubstring(t, key, h);
236 return he != NULL ? he->value : NULL;
240 * Make the hash table larger. Any bucket numbers from the old table become
241 * invalid; the hash codes stay valid though.
244 HashTable_Enlarge(HashTable *t)
246 unsigned int oldSize = t->bucketsSize;
247 HashEntry **oldBuckets = t->buckets;
248 unsigned int newSize = 2 * oldSize;
249 unsigned int newMask = newSize - 1;
250 HashEntry **newBuckets = bmake_malloc(sizeof *newBuckets * newSize);
253 for (i = 0; i < newSize; i++)
254 newBuckets[i] = NULL;
256 for (i = 0; i < oldSize; i++) {
257 HashEntry *he = oldBuckets[i];
259 HashEntry *next = he->next;
260 he->next = newBuckets[he->key_hash & newMask];
261 newBuckets[he->key_hash & newMask] = he;
268 t->bucketsSize = newSize;
269 t->bucketsMask = newMask;
270 t->buckets = newBuckets;
271 DEBUG5(HASH, "%s: %p size=%d entries=%d maxchain=%d\n",
272 __func__, (void *)t, t->bucketsSize, t->numEntries, t->maxchain);
277 * Find or create an entry corresponding to the key.
278 * Return in out_isNew whether a new entry has been created.
281 HashTable_CreateEntry(HashTable *t, const char *key, bool *out_isNew)
284 unsigned int h = Hash_String(key, &keylen);
285 HashEntry *he = HashTable_Find(t, h, key);
288 if (out_isNew != NULL)
293 if (t->numEntries >= rebuildLimit * t->bucketsSize)
294 HashTable_Enlarge(t);
296 he = bmake_malloc(sizeof *he + keylen);
299 memcpy(he->key, key, keylen + 1);
301 he->next = t->buckets[h & t->bucketsMask];
302 t->buckets[h & t->bucketsMask] = he;
305 if (out_isNew != NULL)
311 HashTable_Set(HashTable *t, const char *key, void *value)
313 HashEntry *he = HashTable_CreateEntry(t, key, NULL);
314 HashEntry_Set(he, value);
318 /* Delete the entry from the table and free the associated memory. */
320 HashTable_DeleteEntry(HashTable *t, HashEntry *he)
322 HashEntry **ref = &t->buckets[he->key_hash & t->bucketsMask];
325 for (; (p = *ref) != NULL; ref = &p->next) {
336 /* Set things up for iterating over all entries in the hash table. */
338 HashIter_Init(HashIter *hi, HashTable *t)
346 * Return the next entry in the hash table, or NULL if the end of the table
350 HashIter_Next(HashIter *hi)
352 HashTable *t = hi->table;
353 HashEntry *he = hi->entry;
354 HashEntry **buckets = t->buckets;
355 unsigned int bucketsSize = t->bucketsSize;
358 he = he->next; /* skip the most recently returned entry */
360 while (he == NULL) { /* find the next nonempty chain */
361 if (hi->nextBucket >= bucketsSize)
363 he = buckets[hi->nextBucket++];
370 HashTable_DebugStats(HashTable *t, const char *name)
372 DEBUG4(HASH, "HashTable %s: size=%u numEntries=%u maxchain=%u\n",
373 name, t->bucketsSize, t->numEntries, t->maxchain);