summaryrefslogtreecommitdiff
path: root/tables/apr_hash.c
blob: f8ab43fa27a8dd07ae13aea19c45b85e2149b70c (plain)
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
/* ====================================================================
 * The Apache Software License, Version 1.1
 *
 * Copyright (c) 2000 The Apache Software Foundation.  All rights
 * reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 *
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in
 *    the documentation and/or other materials provided with the
 *    distribution.
 *
 * 3. The end-user documentation included with the redistribution,
 *    if any, must include the following acknowledgment:
 *       "This product includes software developed by the
 *        Apache Software Foundation (http://www.apache.org/)."
 *    Alternately, this acknowledgment may appear in the software itself,
 *    if and wherever such third-party acknowledgments normally appear.
 *
 * 4. The names "Apache" and "Apache Software Foundation" must
 *    not be used to endorse or promote products derived from this
 *    software without prior written permission. For written
 *    permission, please contact apache@apache.org.
 *
 * 5. Products derived from this software may not be called "Apache",
 *    nor may "Apache" appear in their name, without prior written
 *    permission of the Apache Software Foundation.
 *
 * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
 * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 * DISCLAIMED.  IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
 * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
 * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
 * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
 * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 * ====================================================================
 *
 * This software consists of voluntary contributions made by many
 * individuals on behalf of the Apache Software Foundation.  For more
 * information on the Apache Software Foundation, please see
 * <http://www.apache.org/>.
 *
 * Portions of this software are based upon public domain software
 * originally written at the National Center for Supercomputing Applications,
 * University of Illinois, Urbana-Champaign.
 */

#include "apr_private.h"

#include "apr_general.h"
#include "apr_pools.h"

#include "apr_hash.h"

#ifdef HAVE_STDLIB_H
#include <stdlib.h>
#endif
#ifdef HAVE_STDLIB_H
#include <string.h>
#endif


/*
 * The internal form of a hash table.
 *
 * The table is an array indexed by the hash of the key; collisions
 * are resolved by hanging a linked list of hash entries off each
 * element of the array. Although this is a really simple design it
 * isn't too bad given that pools have a low allocation overhead.
 */

typedef struct apr_hash_entry_t apr_hash_entry_t;

struct apr_hash_entry_t {
    apr_hash_entry_t	*next;
    int			 hash;
    const void		*key;
    apr_size_t		 klen;
    const void		*val;
};

/*
 * The size of the array is always a power of two. We use the maximum
 * index rather than the size so that we can use bitwise-AND for
 * modular arithmetic.
 * The count of hash entries may be greater depending on the chosen
 * collision rate.
 */
struct apr_hash_t {
    apr_pool_t		*pool;
    apr_hash_entry_t   **array;
    apr_size_t		 count, max;
};
#define INITIAL_MAX 15 /* tunable == 2^n - 1 */

/*
 * Data structure for iterating through a hash table.
 *
 * We keep a pointer to the next hash entry here to allow the current
 * hash entry to be freed or otherwise mangled between calls to
 * apr_hash_next().
 */
struct apr_hash_index_t {
    apr_hash_t	       *ht;
    apr_hash_entry_t   *this, *next;
    apr_size_t		index;
};


/*
 * Hash creation functions.
 */

static apr_hash_entry_t **alloc_array(apr_hash_t *ht, apr_size_t max)
{
   return apr_pcalloc(ht->pool, sizeof(*ht->array) * (max + 1));
}

APR_DECLARE(apr_hash_t *) apr_make_hash(apr_pool_t *pool)
{
    apr_hash_t *ht;
    ht = apr_palloc(pool, sizeof(apr_hash_t));
    ht->pool = pool;
    ht->count = 0;
    ht->max = INITIAL_MAX;
    ht->array = alloc_array(ht, ht->max);
    return ht;
}


/*
 * Hash iteration functions.
 */

APR_DECLARE(apr_hash_index_t *) apr_hash_next(apr_hash_index_t *hi)
{
    hi->this = hi->next;
    while (!hi->this) {
	if (hi->index > hi->ht->max)
	    return NULL;
	hi->this = hi->ht->array[hi->index++];
    }
    hi->next = hi->this->next;
    return hi;
}

APR_DECLARE(apr_hash_index_t *) apr_hash_first(apr_hash_t *ht)
{
    apr_hash_index_t *hi;
    hi = apr_palloc(ht->pool, sizeof(*hi));
    hi->ht = ht;
    hi->index = 0;
    hi->this = NULL;
    hi->next = NULL;
    return apr_hash_next(hi);
}

APR_DECLARE(void) apr_hash_this(apr_hash_index_t *hi,
			       const void **key,
			       apr_size_t *klen,
			       void **val)
{
    if (key)  *key  = hi->this->key;
    if (klen) *klen = hi->this->klen;
    if (val)  *val  = (void *)hi->this->val;
}


/*
 * Expanding a hash table
 */

static void expand_array(apr_hash_t *ht)
{
    apr_hash_index_t *hi;
    apr_hash_entry_t **new_array;
    apr_size_t new_max;
    int i;

    new_max = ht->max * 2 + 1;
    new_array = alloc_array(ht, new_max);
    for (hi = apr_hash_first(ht); hi; hi = apr_hash_next(hi)) {
	i = hi->this->hash & new_max;
	hi->this->next = new_array[i];
	new_array[i] = hi->this;
    }	       
    ht->array = new_array;
    ht->max = new_max;
}

/*
 * This is where we keep the details of the hash function and control
 * the maximum collision rate.
 *
 * If val is non-NULL it creates and initializes a new hash entry if
 * there isn't already one there; it returns an updatable pointer so
 * that hash entries can be removed.
 */

static apr_hash_entry_t **find_entry(apr_hash_t *ht,
				    const void *key,
				    apr_ssize_t klen,
				    const void *val)
{
    apr_hash_entry_t **hep, *he;
    const unsigned char *p;
    int hash;
    int i;

    if (klen == APR_HASH_KEY_STRING)
	klen = strlen(key);

    /*
     * This is Daniel J. Bernstein's popular `times 33' hash function
     * as posted by him years ago on comp.lang.c and used by perl.
     * This is one of the best known hash functions for strings
     * because it is both computed very fast and distributes very
     * well.
     *
     * The magic of number 33, i.e. why it works better than many other
     * constants, prime or not, has never been adequately explained by
     * anyone. So I try an explanation: if one experimentally tests all
     * multipliers between 1 and 256 (as I did while writing a low-level
     * data structure library some time ago) one detects that even
     * numbers are not useable at all. The remaining 128 odd numbers
     * (except for the number 1) work more or less all equally well.
     * They all distribute in an acceptable way and this way fill a hash
     * table with an average percent of approx. 86%.
     *
     * If one compares the chi^2 values of the variants (see
     * Bob Jenkins ``Hashing Frequently Asked Questions'' at
     * http://burtleburtle.net/bob/hash/hashfaq.html for a description
     * of chi^2), the number 33 not even has the best value. But the
     * number 33 and a few other equally good numbers like 17, 31, 63,
     * 127 and 129 have nevertheless a great advantage to the remaining
     * numbers in the large set of possible multipliers: their multiply
     * operation can be replaced by a faster operation based on just one
     * shift plus either a single addition or subtraction operation. And
     * because a hash function has to both distribute good _and_ has to
     * be very fast to compute, those few numbers should be preferred
     * and seems to be the reason why Daniel J. Bernstein also preferred
     * it.
     *                  -- Ralf S. Engelschall <rse@engelschall.com>
     */
    hash = 0;
    for (p = key, i = klen; i; i--, p++)
	hash = hash * 33 + *p;
    
    /* scan linked list */
    for (hep = &ht->array[hash & ht->max], he = *hep;
	 he;
	 hep = &he->next, he = *hep) {
	if (he->hash == hash &&
	    he->klen == klen &&
	    memcmp(he->key, key, klen) == 0)
	    break;
    }
    if (he || !val)
	return hep;
    /* add a new entry for non-NULL values */
    he = apr_pcalloc(ht->pool, sizeof(*he));
    he->hash = hash;
    he->key  = key;
    he->klen = klen;
    he->val  = val;
    *hep = he;
    /* check that the collision rate isn't too high */
    if (++ht->count > ht->max) {
	expand_array(ht);
    }
    return hep;
}

APR_DECLARE(void *) apr_hash_get(apr_hash_t *ht,
			       const void *key,
			       apr_ssize_t klen)
{
    apr_hash_entry_t *he;
    he = *find_entry(ht, key, klen, NULL);
    if (he)
	return (void *)he->val;
    else
	return NULL;
}

APR_DECLARE(void) apr_hash_set(apr_hash_t *ht,
			     const void *key,
			     apr_ssize_t klen,
			     const void *val)
{
    apr_hash_entry_t **hep;
    hep = find_entry(ht, key, klen, val);
    if (*hep) {
        if (!val) {
            /* delete entry */
            *hep = (*hep)->next;
            --ht->count;
        }
        else {
            /* replace entry */
            (*hep)->val = val;
        }
    }
    /* else key not present and val==NULL */
}