1 /*-
2 * Copyright (c) 1990, 1993
3 * The Regents of the University of California. All rights reserved.
4 *
5 * This code is derived from software contributed to Berkeley by
6 * Margo Seltzer.
7 *
8 * Redistribution and use in source and binary forms, with or without
9 * modification, are permitted provided that the following conditions
10 * are met:
11 * 1. Redistributions of source code must retain the above copyright
12 * notice, this list of conditions and the following disclaimer.
13 * 2. Redistributions in binary form must reproduce the above copyright
14 * notice, this list of conditions and the following disclaimer in the
15 * documentation and/or other materials provided with the distribution.
16 * 3. All advertising materials mentioning features or use of this software
17 * must display the following acknowledgement:
18 * This product includes software developed by the University of
19 * California, Berkeley and its contributors.
20 * 4. Neither the name of the University nor the names of its contributors
21 * may be used to endorse or promote products derived from this software
22 * without specific prior written permission.
23 *
24 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
25 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
26 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
27 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
28 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
29 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
30 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
31 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
32 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
33 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
34 * SUCH DAMAGE.
35 */
36
37 #if defined(LIBC_SCCS) && !defined(lint)
38 static char sccsid[] = "@(#)hash_func.c 8.4 (Berkeley) 11/7/95";
39 #endif /* LIBC_SCCS and not lint */
40
41 #include <sys/types.h>
42
43 #include "db-int.h"
44 #include "hash.h"
45 #include "page.h"
46 #include "extern.h"
47
48 #if 0
49 static u_int32_t hash1 __P((const void *, size_t));
50 static u_int32_t hash2 __P((const void *, size_t));
51 static u_int32_t hash3 __P((const void *, size_t));
52 #endif
53 static u_int32_t hash4 __P((const void *, size_t));
54
55 /* Default hash function. */
56 u_int32_t (*__default_hash) __P((const void *, size_t)) = hash4;
57
58 /*
59 * Assume that we've already split the bucket to which this key hashes,
60 * calculate that bucket, and check that in fact we did already split it.
61 *
62 * EJB's original hsearch hash.
63 */
64 #define PRIME1 37
65 #define PRIME2 1048583
66
67 #if 0
68 static u_int32_t
69 hash1(const void *key, size_t len)
70 {
71 u_int32_t h;
72 u_int8_t *k;
73
74 h = 0;
75 k = (u_int8_t *)key;
76 /* Convert string to integer */
77 while (len--)
78 h = h * PRIME1 ^ (*k++ - ' ');
79 h %= PRIME2;
80 return (h);
81 }
82
83 /*
84 * Phong Vo's linear congruential hash
85 */
86 #define dcharhash(h, c) ((h) = 0x63c63cd9*(h) + 0x9c39c33d + (c))
87
88 static u_int32_t
89 hash2(const void *key, size_t len)
90 {
91 u_int32_t h;
92 u_int8_t *e, c, *k;
93
94 k = (u_int8_t *)key;
95 e = k + len;
96 for (h = 0; k != e;) {
97 c = *k++;
98 if (!c && k > e)
99 break;
100 dcharhash(h, c);
101 }
102 return (h);
103 }
104
105 /*
106 * This is INCREDIBLY ugly, but fast. We break the string up into 8 byte
107 * units. On the first time through the loop we get the "leftover bytes"
108 * (strlen % 8). On every other iteration, we perform 8 HASHC's so we handle
109 * all 8 bytes. Essentially, this saves us 7 cmp & branch instructions. If
110 * this routine is heavily used enough, it's worth the ugly coding.
111 *
112 * Ozan Yigit's original sdbm hash.
113 */
114 static u_int32_t
115 hash3(const void *key, size_t len)
116 {
117 u_int32_t n, loop;
118 u_int8_t *k;
119
120 #define HASHC n = *k++ + 65599 * n
121
122 n = 0;
123 k = (u_int8_t *)key;
124 if (len > 0) {
125 loop = (len + 8 - 1) >> 3;
126
127 switch (len & (8 - 1)) {
128 case 0:
129 do { /* All fall throughs */
130 HASHC;
131 case 7:
132 HASHC;
133 case 6:
134 HASHC;
135 case 5:
136 HASHC;
137 case 4:
138 HASHC;
139 case 3:
140 HASHC;
141 case 2:
142 HASHC;
143 case 1:
144 HASHC;
145 } while (--loop);
146 }
147
148 }
149 return (n);
150 }
151 #endif
152
153
154 /* Chris Torek's hash function. */
155 static u_int32_t
hash4(const void * key,size_t len)156 hash4(const void *key, size_t len)
157 {
158 u_int32_t h, loop;
159 const u_int8_t *k;
160
161 #define HASH4a h = (h << 5) - h + *k++;
162 #define HASH4b h = (h << 5) + h + *k++;
163 #define HASH4 HASH4b
164
165 h = 0;
166 k = (const u_int8_t *)key;
167 if (len > 0) {
168 loop = (len + 8 - 1) >> 3;
169
170 switch (len & (8 - 1)) {
171 case 0:
172 do { /* All fall throughs */
173 HASH4;
174 case 7:
175 HASH4;
176 case 6:
177 HASH4;
178 case 5:
179 HASH4;
180 case 4:
181 HASH4;
182 case 3:
183 HASH4;
184 case 2:
185 HASH4;
186 case 1:
187 HASH4;
188 } while (--loop);
189 }
190
191 }
192 return (h);
193 }
194