summaryrefslogtreecommitdiff
path: root/common/hash.c
blob: 5f3308cb087218a3d95c30e45d844aa21ef61db9 (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
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
/*
 * Originally from apache 2.0
 * Modifications for general use by <nielsen@memberwebs.com>
 */

/* Copyright 2000-2004 The Apache Software Foundation
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

#include <sys/types.h>
#include <stdlib.h>
#include "hash.h"

#ifdef HSH_TIMESTAMP
#include <time.h>
#endif

#ifdef HSH_COPYKEYS
  #define KEY_DATA(he) (void*)(((unsigned char*)(he)) + sizeof(*(he)))
#else
  #define KEY_DATA(he)  ((he)->key)
#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 hsh_entry_t hsh_entry_t;

struct hsh_entry_t
{
  hsh_entry_t* next;
  unsigned int hash;
#ifndef HSH_COPYKEYS
  const void* key;
  size_t klen;
#endif
  const void* val;
#ifdef HSH_TIMESTAMP
  time_t stamp;
#endif
};

/*
 * 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
 * hsh_next().
 */
struct hsh_index_t
{
  hsh_t* ht;
  hsh_entry_t* ths;
  hsh_entry_t* next;
  unsigned int index;
};

/*
 * 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 hsh_t
{
  hsh_entry_t** array;
  hsh_index_t iterator;  /* For hsh_first(...) */
  unsigned int count;
  unsigned int max;
#ifdef HSH_COPYKEYS
  unsigned int klen;
#endif
#ifdef HSH_CALLBACKS
  hsh_table_calls_t calls;
#endif
};


#define INITIAL_MAX 15 /* tunable == 2^n - 1 */

#ifdef HSH_CALLBACKS

/* A copy of the memory call table we've been set to */
static hsh_memory_calls_t g_memory_calls_cpy;

/* Pointer to above. This indicates when we actually are set */
static hsh_memory_calls_t* g_memory_calls = NULL;

static void* int_malloc(size_t len)
{
  if(g_memory_calls)
    return (g_memory_calls->f_alloc)(g_memory_calls->arg, len);
  else
    return malloc(len);
}

static void* int_calloc(size_t len)
{
  void* p = int_malloc(len);
  memset(p, 0, len);
  return p;
}

static void int_free(void* ptr)
{
  if(g_memory_calls)
  {
    /* We allow for gc type memory allocation with a null free */
    if(g_memory_calls->f_free)
      (g_memory_calls->f_free)(g_memory_calls->arg, ptr);
  }
  else
    free(ptr);
}

void hsh_set_memory_calls(hsh_memory_calls_t* hmc)
{
  if(hmc == NULL)
  {
    g_memory_calls = NULL;
  }
  else
  {
    memcpy(&g_memory_calls_cpy, hmc, sizeof(g_memory_calls_cpy));
    g_memory_calls = &g_memory_calls_cpy;
  }
}

void hsh_set_table_calls(hsh_t* ht, hsh_table_calls_t* htc)
{
  memcpy(&(ht->calls), htc, sizeof(ht->calls));
}

#else

#define int_malloc malloc
#define int_free free

#endif


/*
 * Hash creation functions.
 */

static hsh_entry_t** alloc_array(hsh_t* ht, unsigned int max)
{
  return int_calloc(sizeof(*(ht->array)) * (max + 1));
}

#ifdef HSH_COPYKEYS
hsh_t* hsh_create(size_t klen)
#else
hsh_t* hsh_create()
#endif
{
  hsh_t* ht = int_malloc(sizeof(hsh_t));
  if(ht)
  {
    ht->count = 0;
    ht->max = INITIAL_MAX;
    ht->array = alloc_array(ht, ht->max);
#ifdef HSH_COPYKEYS
    ht->klen = klen;
#endif
    if(!ht->array)
    {
      int_free(ht);
      return NULL;
    }
  }
  return ht;
}

void hsh_free(hsh_t* ht)
{
  hsh_index_t* hi;

  for(hi = hsh_first(ht); hi; hi = hsh_next(hi))
  {
#ifdef HSH_CALLBACKS
    if(hi->ths->val && ht->calls.f_freeval)
      (ht->calls.f_freeval)(ht->calls.arg, (void*)hi->ths->val);
#endif
    int_free(hi->ths);
  }

  if(ht->array)
    int_free(ht->array);

  int_free(ht);
}

/*
 * Hash iteration functions.
 */

hsh_index_t* hsh_next(hsh_index_t* hi)
{
  hi->ths = hi->next;
  while(!hi->ths)
  {
    if(hi->index > hi->ht->max)
      return NULL;

    hi->ths = hi->ht->array[hi->index++];
  }
  hi->next = hi->ths->next;
  return hi;
}

hsh_index_t* hsh_first(hsh_t* ht)
{
  hsh_index_t* hi = &ht->iterator;

  hi->ht = ht;
  hi->index = 0;
  hi->ths = NULL;
  hi->next = NULL;
  return hsh_next(hi);
}

#ifdef HSH_COPYKEYS
void* hsh_this(hsh_index_t* hi, const void** key)
#else
void* hsh_this(hsh_index_t* hi, const void** key, size_t* klen)
#endif
{
  if(key)
    *key = KEY_DATA(hi->ths);

#ifndef HSH_COPYKEYS
  if(klen)
    *klen = hi->ths->klen;
#endif

  return (void*)hi->ths->val;
}


/*
 * Expanding a hash table
 */

static int expand_array(hsh_t* ht)
{
  hsh_index_t* hi;
  hsh_entry_t** new_array;
  unsigned int new_max;

  new_max = ht->max * 2 + 1;
  new_array = alloc_array(ht, new_max);

  if(!new_array)
    return 0;

  for(hi = hsh_first(ht); hi; hi = hsh_next(hi))
  {
    unsigned int i = hi->ths->hash & new_max;
    hi->ths->next = new_array[i];
    new_array[i] = hi->ths;
  }

  if(ht->array)
    free(ht->array);

  ht->array = new_array;
  ht->max = new_max;
  return 1;
}

/*
 * 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.
 */

#ifdef HSH_COPYKEYS
static hsh_entry_t** find_entry(hsh_t* ht, const void* key, const void* val)
#else
static hsh_entry_t** find_entry(hsh_t* ht, const void* key, size_t klen, const void* val)
#endif
{
  hsh_entry_t** hep;
  hsh_entry_t* he;
  const unsigned char* p;
  unsigned int hash;
  size_t i;

#ifdef HSH_COPYKEYS
  size_t klen = ht->klen;
#endif

  /*
   * This is the popular `times 33' hash algorithm which is used by
   * perl and also appears in Berkeley DB. This is one of the best
   * known hash functions for strings because it is both computed
   * very fast and distributes very well.
   *
   * The originator may be Dan Bernstein but the code in Berkeley DB
   * cites Chris Torek as the source. The best citation I have found
   * is "Chris Torek, Hash function for text in C, Usenet message
   * <27038@mimsy.umd.edu> in comp.lang.c , October, 1990." in Rich
   * Salz's USENIX 1992 paper about INN which can be found at
   * <http://citeseer.nj.nec.com/salz92internetnews.html>.
   *
   * 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.
   *
   *                  -- Ralf S. Engelschall <rse@engelschall.com>
   */
  hash = 0;

#ifndef HSH_COPYKEYS
  if(klen == HSH_KEY_STRING)
  {
    for(p = key; *p; p++)
      hash = hash * 33 + *p;

    klen = p - (const unsigned char *)key;
  }
  else
#endif
  {
    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 &&
#ifndef HSH_COPYKEYS
      he->klen == klen &&
#endif
      memcmp(KEY_DATA(he), key, klen) == 0)
     break;
  }

  if(he || !val)
    return hep;

  /* add a new entry for non-NULL val */
#ifdef HSH_COPYKEYS
  he = int_malloc(sizeof(*he) + klen);
#else
  he = int_malloc(sizeof(*he));
#endif

  if(he)
  {
#ifdef HSH_COPYKEYS
    /* Key data points past end of entry */
    memcpy(KEY_DATA(he), key, klen);
#else
    /* Key points to external data */
    he->key = key;
    he->klen = klen;
#endif

    he->next = NULL;
    he->hash = hash;
    he->val  = val;

#ifdef HSH_TIMESTAMP
    he->stamp = 0;
#endif

    *hep = he;
    ht->count++;
  }

  return hep;
}

#ifdef HSH_COPYKEYS
void* hsh_get(hsh_t* ht, const void *key)
{
    hsh_entry_t** he = find_entry(ht, key, NULL);
#else
void* hsh_get(hsh_t* ht, const void *key, size_t klen)
{
    hsh_entry_t** he = find_entry(ht, key, klen, NULL);
#endif

    if(he && *he)
      return (void*)((*he)->val);
    else
      return NULL;
}

#ifdef HSH_COPYKEYS
int hsh_set(hsh_t* ht, const void* key, void* val)
{
  hsh_entry_t** hep = find_entry(ht, key, val);
#else
int hsh_set(hsh_t* ht, const void* key, size_t klen, void* val)
{
  hsh_entry_t** hep = find_entry(ht, key, klen, val);
#endif

  if(hep && *hep)
  {
#ifdef HSH_CALLBACKS
    if((*hep)->val && (*hep)->val != val && ht->calls.f_freeval)
      (ht->calls.f_freeval)(ht->calls.arg, (void*)((*hep)->val));
#endif

    /* replace entry */
    (*hep)->val = val;

#ifdef HSH_TIMESTAMP
    /* Update or set the timestamp */
    (*hep)->stamp = time(NULL);
#endif

    /* check that the collision rate isn't too high */
    if(ht->count > ht->max)
    {
      if(!expand_array(ht))
        return 0;
    }

    return 1;
  }

  return 0;
}

#ifdef HSH_COPYKEYS
void* hsh_rem(hsh_t* ht, const void* key)
{
  hsh_entry_t** hep = find_entry(ht, key, NULL);
#else
void* hsh_rem(hsh_t* ht, const void* key, size_t klen)
{
  hsh_entry_t** hep = find_entry(ht, key, klen, NULL);
#endif
  void* val = NULL;

  if(hep && *hep)
  {
    hsh_entry_t* old = *hep;
    *hep = (*hep)->next;
    --ht->count;
    val = (void*)old->val;
    free(old);
  }

  return val;
}

unsigned int hsh_count(hsh_t* ht)
{
  return ht->count;
}

#ifdef HSH_TIMESTAMP
int hsh_purge(hsh_t* ht, time_t stamp)
{
  hsh_index_t* hi;
  int r = 0;
  void* val;

  for(hi = hsh_first(ht); hi; hi = hsh_next(hi))
  {
    if(hi->ths->stamp < stamp)
    {
      /* No need to check for errors as we're deleting */
#ifdef HSH_COPYKEYS
      val = hsh_rem(ht, KEY_DATA(hi->ths));
#else
      val = hsh_rem(ht, hi->ths->key, hi->ths->klen);
#endif

#ifdef HSH_CALLBACKS
      if(val && ht->calls.f_freeval)
        (ht->calls.f_freeval)(ht->calls.arg, val);
#endif

      r++;
    }
  }

  return r;
}

#ifdef HSH_COPYKEYS
void hsh_touch(hsh_t* ht, const void* key)
{
  hsh_entry_t** hep = find_entry(ht, key, NULL);
#else
void hsh_touch(hsh_t* ht, const void* key, size_t* klen)
{
  hsh_entry_t** hep = find_entry(ht, key, klen, NULL);
#endif

  if(hep && *hep)
    ((*hep)->stamp) = time(NULL);
}

int hsh_bump(hsh_t* ht)
{
  hsh_index_t* hi;
  void* key = NULL;
  void* val = NULL;
  time_t least = 0;
#ifndef HSH_COPYKEYS
  size_t klen = 0;
#endif

  for(hi = hsh_first(ht); hi; hi = hsh_next(hi))
  {
    if(least == 0 || hi->ths->stamp < least)
    {
      least = hi->ths->stamp;
      key = KEY_DATA(hi->ths);
#ifndef HSH_COPYKEYS
      klen = hi->this->klen;
#endif
    }
  }

  if(key)
  {
#ifdef HSH_COPYKEYS
    val = hsh_rem(ht, key);
#else
    val = hsh_rem(ht, key, klen);
#endif

#ifdef HSH_CALLBACKS
    if(val && ht->calls.f_freeval)
      (ht->calls.f_freeval)(ht->calls.arg, (void*)val);
#endif

    return 1;
  }

  return 0;
}

#endif /* HSH_TIMESTAMP */