summaryrefslogtreecommitdiffstats
path: root/source/lib/hash.c
blob: ccaf65b55a0e867fdf4dc2a737306d013733bdf3 (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
317
318
319
320
/*
   Unix SMB/Netbios implementation.
   Version 2.0

   Copyright (C) Ying Chen 2000.
   Copyright (C) Jeremy Allison 2000.
                 - added some defensive programming.

   This program is free software; you can redistribute it and/or modify
   it under the terms of the GNU General Public License as published by
   the Free Software Foundation; either version 2 of the License, or
   (at your option) any later version.

   This program is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
   GNU General Public License for more details.

   You should have received a copy of the GNU General Public License
   along with this program; if not, write to the Free Software
   Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/

/*
 * NB. We may end up replacing this functionality in a future 2.x 
 * release to reduce the number of hashing/lookup methods we support. JRA.
 */

#include "includes.h"

extern int DEBUGLEVEL;

#define NUM_PRIMES 11

static BOOL enlarge_hash_table(hash_table *table);
static int primes[NUM_PRIMES] = 
        {17, 37, 67, 131, 257, 521, 1031, 2053, 4099, 8209, 16411};

/****************************************************************************
 *      This function initializes the hash table.
 *      This hash function hashes on string keys.
 *      This number of hash buckets is always rounded up to a power of 
 *      2 first, then to a prime number that is large than the power of two. 
 *      Input:
 *              table -- the hash table pointer.
 *              num_buckets -- the number of buckets to be allocated. This
 *              hash function can dynamically increase its size when the 
 *              the hash table size becomes small. There is a MAX hash table
 *              size defined in hash.h.
 *              compare_func -- the function pointer to a comparison function
 *              used by the hash key comparison.
 ****************************************************************************
 */

BOOL hash_table_init(hash_table *table, int num_buckets, compare_function compare_func)
{
	int 	i;
	ubi_dlList 	*bucket;

	table->num_elements = 0;
	table->size = 2;
	table->comp_func = compare_func;
	while (table->size < num_buckets) 
	table->size <<= 1;
	for (i = 0; i < NUM_PRIMES; i++) {
		if (primes[i] > table->size) {
			table->size = primes[i];
			break;
		}
	}

	DEBUG(5, ("Hash size = %d.\n", table->size));

	if(!(table->buckets = (ubi_dlList *) malloc(sizeof(ubi_dlList) * table->size))) {
		DEBUG(0,("hash_table_init: malloc fail !\n"));
		return False;
	}
	ubi_dlInitList(&(table->lru_chain));
	for (i=0, bucket = table->buckets; i < table->size; i++, bucket++) 
		ubi_dlInitList(bucket);

	return True;
}

/*
 **************************************************************
 *	Compute a hash value based on a string key value.
 *	Make the string key into an array of int's if possible.
 *	For the last few chars that cannot be int'ed, use char instead.
 *	The function returns the bucket index number for the hashed 
 *	key.
 **************************************************************
 */

int string_hash(int hash_size, const char *key)
{
	int j=0;
	while (*key)
		j = j*10 + *key++;
	return(((j>=0)?j:(-j)) % hash_size);
}

/* *************************************************************************
 * 	Search the hash table for the entry in the hash chain.
 *	The function returns the pointer to the 
 *	element found in the chain or NULL if none is found. 
 *	If the element is found, the element is also moved to 
 *	the head of the LRU list.
 *
 *	Input:
 *              table -- The hash table where the element is stored in.
 *              hash_chain -- The pointer to the bucket that stores the 
 *              element to be found.
 *              key -- The hash key to be found. 
 ***************************************************************************
 */

static hash_element *hash_chain_find(hash_table *table, ubi_dlList *hash_chain, char *key)
{
	hash_element *hash_elem;
	ubi_dlNodePtr lru_item;
	int	i = 0;

	for (hash_elem = (hash_element *)(ubi_dlFirst(hash_chain)); i < hash_chain->count; 
		i++, hash_elem = (hash_element *)(ubi_dlNext(hash_elem))) {
		if ((table->comp_func)(hash_elem->key, key) == 0) {
			/* Move to the head of the lru List. */
			lru_item = ubi_dlRemove(&(table->lru_chain), &(hash_elem->lru_link.lru_link));
			ubi_dlAddHead(&(table->lru_chain), lru_item);
			return(hash_elem);
		}
	}
	return ((hash_element *) NULL);
}

/* ***************************************************************************
 *
 * 	Lookup a hash table for an element with key.  
 *      The function returns a pointer to the hash element.
 *	If no element is found, the function returns NULL.
 *
 *      Input:
 *              table -- The hash table to be searched on.
 *              key -- The key to be found.
 *****************************************************************************
 */

hash_element *hash_lookup(hash_table *table, char *key)
{
	return (hash_chain_find(table, &(table->buckets[string_hash(table->size, key)]), key));
}

/* ***************************************************************
 *
 *	This function first checks if an element with key "key"
 *	exists in the hash table. If so, the function moves the 
 *	element to the front of the LRU list. Otherwise, a new 
 *	hash element corresponding to "value" and "key" is allocated
 *	and inserted into the hash table. The new elements are
 *	always inserted in the LRU order to the LRU list as well.
 *
 *      Input:
 *              table -- The hash table to be inserted in.
 *              value -- The content of the element to be inserted.
 *              key -- The key of the new element to be inserted.
 *
 ****************************************************************
 */

hash_element *hash_insert(hash_table *table, char *value, char *key)
{
	hash_element	*hash_elem;
	ubi_dlNodePtr lru_item;
	ubi_dlList *bucket; 

	/* 
	 * If the hash table size has not reached the MAX_HASH_TABLE_SIZE,
	 * the hash table may be enlarged if the current hash table is full.
	 * If the hash table size has reached the MAX_HASH_TABLE_SIZE, 
	 * use LRU to remove the oldest element from the hash table.
	 */

	if ((table->num_elements >= table->size) &&  
		(table->num_elements < MAX_HASH_TABLE_SIZE)) {
		if(!enlarge_hash_table(table))
			return (hash_element *)NULL;
		table->num_elements += 1;
	} else if (table->num_elements >= MAX_HASH_TABLE_SIZE) {
		/* Do an LRU replacement. */
		lru_item = ubi_dlLast(&(table->lru_chain));
		hash_elem = (hash_element *)(((lru_node *)lru_item)->hash_elem);
		bucket = hash_elem->bucket;
		ubi_dlRemThis(&(table->lru_chain), &(hash_elem->lru_link.lru_link));
		ubi_dlRemThis(bucket, (ubi_dlNodePtr)hash_elem);
		free((char*)(hash_elem->value));
		free(hash_elem);
	}  else  {
		table->num_elements += 1;
	}

	bucket = &(table->buckets[string_hash(table->size, key)]);

	/* Since we only have 1-byte for the key string, we need to 
	 * allocate extra space in the hash_element to store the entire key
	 * string.
	 */

	if(!(hash_elem = (hash_element *) malloc(sizeof(hash_element) + strlen(key)))) {
		DEBUG(0,("hash_insert: malloc fail !\n"));
		return (hash_element *)NULL;
	}

	safe_strcpy((char *) hash_elem->key, key, strlen(key)+1);

	hash_elem->value = (char *)value;
	hash_elem->bucket = bucket;
	/* Insert in front of the lru list and the bucket list. */
	ubi_dlAddHead(bucket, hash_elem);
	hash_elem->lru_link.hash_elem = hash_elem;
	ubi_dlAddHead(&(table->lru_chain), &(hash_elem->lru_link.lru_link));

	return(hash_elem);
}

/* **************************************************************************
 *
 * 	Remove a hash element from the hash table. The hash element is 
 * 	removed from both the LRU list and the hash bucket chain.
 *
 *      Input:
 *              table -- the hash table to be manipulated on.
 *              hash_elem -- the element to be removed.
 **************************************************************************
 */

void hash_remove(hash_table *table, hash_element *hash_elem)
{
	if (hash_elem) { 
		ubi_dlRemove(&(table->lru_chain), &(hash_elem->lru_link.lru_link));
		ubi_dlRemove(hash_elem->bucket, (ubi_dlNodePtr) hash_elem);
		if(hash_elem->value)
			free((char *)(hash_elem->value));
		if(hash_elem)
			free((char *) hash_elem);
		table->num_elements--;
	}
}

/* ******************************************************************
 *	Increase the hash table size if it is too small. 
 *	The hash table size is increased by the HASH_TABLE_INCREMENT
 *	ratio.
 *      Input:
 *              table -- the hash table to be enlarged.
 ******************************************************************
 */

static BOOL enlarge_hash_table(hash_table *table)
{
	hash_element  	*hash_elem;
	int size, hash_value;
	ubi_dlList	*buckets;
	ubi_dlList	*old_bucket;
	ubi_dlList	*bucket;
	ubi_dlList  lru_chain;

	buckets = table->buckets;
	lru_chain = table->lru_chain;
	size = table->size;

	/* Reinitialize the hash table. */
	if(!hash_table_init(table, table->size * HASH_TABLE_INCREMENT, table->comp_func))
		return False;

	for (old_bucket = buckets; size > 0; size--, old_bucket++) {
		while (old_bucket->count != 0) {
			hash_elem = (hash_element *) ubi_dlRemHead(old_bucket);
			ubi_dlRemove(&lru_chain, &(hash_elem->lru_link.lru_link));
			hash_value = string_hash(table->size, (char *) hash_elem->key);
			bucket = &(table->buckets[hash_value]);
			ubi_dlAddHead(bucket, hash_elem);
			ubi_dlAddHead(&(table->lru_chain), &(hash_elem->lru_link.lru_link));
			hash_elem->bucket = bucket;
			hash_elem->lru_link.hash_elem = hash_elem;
			table->num_elements++;
		}
	}
	if(buckets)
		free((char *) buckets);

	return True;
}

/* **********************************************************************
 *
 *	Remove everything from a hash table and free up the memory it 
 *	occupies. 
 *      Input: 
 *              table -- the hash table to be cleared.
 *
 *************************************************************************
 */

void hash_clear(hash_table *table)
{
	int i;
	ubi_dlList	*bucket = table->buckets;
	hash_element    *hash_elem;
	for (i = 0; i < table->size; bucket++, i++) {
		while (bucket->count != 0) {
			hash_elem = (hash_element *) ubi_dlRemHead(bucket);
			if(hash_elem->value)
				free((char *)(hash_elem->value));
			if(hash_elem)
				free((char *)hash_elem);
		}
	}
	if(table->buckets)
		free((char *) table->buckets);
}