Source

xemacs-beta / src / hash.c

Full commit
  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
/* Hash tables.
   Copyright (C) 1992, 1993, 1994 Free Software Foundation, Inc.
   Copyright (C) 2003, 2004, 2010 Ben Wing.

This file is part of XEmacs.

XEmacs 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, or (at your option) any
later version.

XEmacs 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 XEmacs; see the file COPYING.  If not, write to
the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
Boston, MA 02111-1307, USA.  */

/* Synched up with: Not in FSF. */

/* Author: Lost in the mists of history.  At least back to Lucid 19.3,
   circa Sep 1992. */

#include <config.h>
#include "lisp.h"
#include "hash.h"

#define NULL_ENTRY ((void *) 0xDEADBEEF) /* -559038737 base 10 */

#define COMFORTABLE_SIZE(size) (21 * (size) / 16)

#define KEYS_DIFFER_P(old, new_, testfun) \
  (((old) != (new_)) && (!(testfun) || !(testfun) ((old),(new_))))

static void rehash (hentry *harray, struct hash_table *ht, Elemcount size);

Hashcode
memory_hash (const void *xv, Bytecount size)
{
  Hashcode h = 0;
  unsigned const char *x = (unsigned const char *) xv;

  if (!x) return 0;

  while (size--)
    {
      Hashcode g;
      h = (h << 4) + *x++;
      if ((g = h & 0xf0000000) != 0)
	h = (h ^ (g >> 24)) ^ g;
    }

  return h;
}

static int
string_equal (const void *st1, const void *st2)
{
  if (!st1)
    return st2 ? 0 : 1;
  else if (!st2)
    return 0;
  else
    return !strcmp ((const char *) st1, (const char *) st2);
}

static Hashcode
string_hash (const void *xv)
{
  Hashcode h = 0;
  unsigned const char *x = (unsigned const char *) xv;

  if (!x) return 0;

  while (*x)
    {
      Hashcode g;
      h = (h << 4) + *x++;
      if ((g = h & 0xf0000000) != 0)
	h = (h ^ (g >> 24)) ^ g;
    }

  return h;
}

/* Return a suitable size for a hash table, with at least SIZE slots. */
static Elemcount
hash_table_size (Elemcount requested_size)
{
  /* Return some prime near, but greater than or equal to, SIZE.
     Decades from the time of writing, someone will have a system large
     enough that the list below will be too short... */
  static const Elemcount primes [] =
  {
    19, 29, 41, 59, 79, 107, 149, 197, 263, 347, 457, 599, 787, 1031,
    1361, 1777, 2333, 3037, 3967, 5167, 6719, 8737, 11369, 14783,
    19219, 24989, 32491, 42257, 54941, 71429, 92861, 120721, 156941,
    204047, 265271, 344857, 448321, 582821, 757693, 985003, 1280519,
    1664681, 2164111, 2813353, 3657361, 4754591, 6180989, 8035301,
    10445899, 13579681, 17653589, 22949669, 29834603, 38784989,
    50420551, 65546729, 85210757, 110774011, 144006217, 187208107,
    243370577, 316381771, 411296309, 534685237, 695090819, 903618083,
    1174703521, 1527114613, 1985248999 /* , 2580823717UL, 3355070839UL */
  };
  /* We've heard of binary search. */
  int low, high;
  for (low = 0, high = countof (primes) - 1; high - low > 1;)
    {
      /* Loop Invariant: size < primes [high] */
      int mid = (low + high) / 2;
      if (primes [mid] < requested_size)
	low = mid;
      else
	high = mid;
    }
  return primes [high];
}

const void *
gethash (const void *key, struct hash_table *hash_table, const void **ret_value)
{
  if (!key)
    {
      *ret_value = hash_table->zero_entry;
      return (void *) hash_table->zero_set;
    }
  else
    {
      hentry *harray = hash_table->harray;
      hash_table_test_function test_function = hash_table->test_function;
      Elemcount size = hash_table->size;
      Hashcode hcode_initial =
	hash_table->hash_function ?
	hash_table->hash_function (key) :
	(Hashcode) key;
      Elemcount hcode = (Elemcount) (hcode_initial % size);
      hentry *e = &harray [hcode];
      const void *e_key = e->key;

      if (e_key ?
	  KEYS_DIFFER_P (e_key, key, test_function) :
	  e->contents == NULL_ENTRY)
	{
	  Elemcount h2 = size - 2;
	  Elemcount incr = (Elemcount) (1 + (hcode_initial % h2));
	  do
	    {
	      hcode += incr; if (hcode >= size) hcode -= size;
	      e = &harray [hcode];
	      e_key = e->key;
	    }
	  while (e_key ?
		 KEYS_DIFFER_P (e_key, key, test_function) :
		 e->contents == NULL_ENTRY);
	}

      *ret_value = e->contents;
      return e->key;
    }
}

void
clrhash (struct hash_table *hash_table)
{
  memset (hash_table->harray, 0, sizeof (hentry) * hash_table->size);
  hash_table->zero_entry = 0;
  hash_table->zero_set   = 0;
  hash_table->fullness   = 0;
}

void
free_hash_table (struct hash_table *hash_table)
{
  xfree (hash_table->harray);
  xfree (hash_table);
}

struct hash_table *
make_hash_table (Elemcount size)
{
  struct hash_table *hash_table = xnew_and_zero (struct hash_table);
  hash_table->size = hash_table_size (COMFORTABLE_SIZE (size));
  hash_table->harray = xnew_array (hentry, hash_table->size);
  clrhash (hash_table);
  return hash_table;
}

struct hash_table *
make_string_hash_table (Elemcount size)
{
  return make_general_hash_table (size, string_hash, string_equal);
}

struct hash_table *
make_general_hash_table (Elemcount size,
			hash_table_hash_function hash_function,
			hash_table_test_function test_function)
{
  struct hash_table* hash_table = make_hash_table (size);
  hash_table->hash_function = hash_function;
  hash_table->test_function = test_function;
  return hash_table;
}

static void
grow_hash_table (struct hash_table *hash_table, Elemcount new_size)
{
  Elemcount old_size   = hash_table->size;
  hentry     *old_harray = hash_table->harray;

  hash_table->size   = hash_table_size (new_size);
  hash_table->harray = xnew_array (hentry, hash_table->size);

  /* do the rehash on the "grown" table */
  {
    long old_zero_set    = hash_table->zero_set;
    void *old_zero_entry = hash_table->zero_entry;
    clrhash (hash_table);
    hash_table->zero_set   = old_zero_set;
    hash_table->zero_entry = old_zero_entry;
    rehash (old_harray, hash_table, old_size);
  }

  xfree (old_harray);
}

void
pregrow_hash_table_if_necessary (struct hash_table *hash_table,
				 Elemcount breathing_room)
{
  Elemcount comfortable_size = COMFORTABLE_SIZE (hash_table->fullness);
  if (hash_table->size < comfortable_size - breathing_room)
    grow_hash_table (hash_table, comfortable_size + 1);
}

void
puthash (const void *key, void *contents, struct hash_table *hash_table)
{
  if (!key)
    {
      hash_table->zero_entry = contents;
      hash_table->zero_set = 1;
    }
  else
    {
      hash_table_test_function test_function = hash_table->test_function;
      Elemcount size = hash_table->size;
      hentry *harray   = hash_table->harray;
      Hashcode hcode_initial =
	hash_table->hash_function ?
	hash_table->hash_function (key) :
	(Hashcode) key;
      Elemcount hcode = (Elemcount) (hcode_initial % size);
      Elemcount h2 = size - 2;
      Elemcount incr = (Elemcount) (1 + (hcode_initial % h2));
      const void *e_key = harray [hcode].key;
      const void *oldcontents;

      if (e_key && KEYS_DIFFER_P (e_key, key, test_function))
	{
	  do
	    {
	      hcode += incr; if (hcode >= size) hcode -= size;
	      e_key = harray [hcode].key;
	    }
	  while (e_key && KEYS_DIFFER_P (e_key, key, test_function));
	}
      oldcontents = harray [hcode].contents;
      harray [hcode].key = key;
      harray [hcode].contents = contents;
      /* If the entry that we used was a deleted entry,
	 check for a non deleted entry of the same key,
	 then delete it. */
      if (!e_key && oldcontents == NULL_ENTRY)
	{
	  hentry *e;

	  do
	    {
	      hcode += incr; if (hcode >= size) hcode -= size;
	      e = &harray [hcode];
	      e_key = e->key;
	    }
	  while (e_key ?
		 KEYS_DIFFER_P (e_key, key, test_function):
		 e->contents == NULL_ENTRY);

	  if (e_key)
	    {
	      e->key = 0;
	      e->contents = NULL_ENTRY;
	    }
	}

      /* only increment the fullness when we used up a new hentry */
      if (!e_key || KEYS_DIFFER_P (e_key, key, test_function))
	{
	  Elemcount comfortable_size = COMFORTABLE_SIZE (++(hash_table->fullness));
	  if (hash_table->size < comfortable_size)
	    grow_hash_table (hash_table, comfortable_size + 1);
	}
    }
}

static void
rehash (hentry *harray, struct hash_table *hash_table, Elemcount size)
{
  hentry *limit = harray + size;
  hentry *e;
  for (e = harray; e < limit; e++)
    {
      if (e->key)
	puthash (e->key, e->contents, hash_table);
    }
}

void
remhash (const void *key, struct hash_table *hash_table)
{
  if (!key)
    {
      hash_table->zero_entry = 0;
      hash_table->zero_set = 0;
    }
  else
    {
      hentry *harray = hash_table->harray;
      hash_table_test_function test_function = hash_table->test_function;
      Elemcount size = hash_table->size;
      Hashcode hcode_initial =
	(hash_table->hash_function) ?
	(hash_table->hash_function (key)) :
	((Hashcode) key);
      Elemcount hcode = (Elemcount) (hcode_initial % size);
      hentry *e = &harray [hcode];
      const void *e_key = e->key;

      if (e_key ?
	  KEYS_DIFFER_P (e_key, key, test_function) :
	  e->contents == NULL_ENTRY)
	{
	  Elemcount h2 = size - 2;
	  Elemcount incr = (Elemcount) (1 + (hcode_initial % h2));
	  do
	    {
	      hcode += incr; if (hcode >= size) hcode -= size;
	      e = &harray [hcode];
	      e_key = e->key;
	    }
	  while (e_key?
		 KEYS_DIFFER_P (e_key, key, test_function):
		 e->contents == NULL_ENTRY);
	}
      if (e_key)
	{
	  e->key = 0;
	  e->contents = NULL_ENTRY;
	  /* Note: you can't do fullness-- here, it breaks the world. */
	}
    }
}

void
maphash (maphash_function mf, struct hash_table *hash_table, void *arg)
{
  hentry *e;
  hentry *limit;

  if (hash_table->zero_set)
    {
      if (mf (0, hash_table->zero_entry, arg))
	return;
    }

  for (e = hash_table->harray, limit = e + hash_table->size; e < limit; e++)
    {
      if (e->key && mf (e->key, e->contents, arg))
	return;
    }
}

void
map_remhash (remhash_predicate predicate, struct hash_table *hash_table, void *arg)
{
  hentry *e;
  hentry *limit;

  if (hash_table->zero_set && predicate (0, hash_table->zero_entry, arg))
    {
      hash_table->zero_set = 0;
      hash_table->zero_entry = 0;
    }

  for (e = hash_table->harray, limit = e + hash_table->size; e < limit; e++)
    if (predicate (e->key, e->contents, arg))
      {
        e->key = 0;
        e->contents = NULL_ENTRY;
      }
}