hashlib.c 10 KB
Newer Older
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
/* hashlib.c -- functions to manage and access hash tables for bash. */

/* Copyright (C) 1987,1989,1991,1995,1998,2001,2003,2005,2006,2008,2009 Free Software Foundation, Inc.

   This file is part of GNU Bash, the Bourne Again SHell.

   Bash 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 3 of the License, or
   (at your option) any later version.

   Bash 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 Bash.  If not, see <http://www.gnu.org/licenses/>.
*/

#include <config.h>

#include "bashansi.h"

#if defined (HAVE_UNISTD_H)
#  ifdef _MINIX
#    include <sys/types.h>
#  endif
#  include <unistd.h>
#endif

#include <stdio.h>

#include "shell.h"
#include "hashlib.h"

/* Rely on properties of unsigned division (unsigned/int -> unsigned) and
   don't discard the upper 32 bits of the value, if present. */
#define HASH_BUCKET(s, t, h) (((h) = hash_string (s)) & ((t)->nbuckets - 1))

static BUCKET_CONTENTS *copy_bucket_array __P((BUCKET_CONTENTS *, sh_string_func_t *));

/* Make a new hash table with BUCKETS number of buckets.  Initialize
   each slot in the table to NULL. */
HASH_TABLE *
hash_create (buckets)
     int buckets;
{
  HASH_TABLE *new_table;
  register int i;

  new_table = (HASH_TABLE *)xmalloc (sizeof (HASH_TABLE));
  if (buckets == 0)
    buckets = DEFAULT_HASH_BUCKETS;

  new_table->bucket_array =
    (BUCKET_CONTENTS **)xmalloc (buckets * sizeof (BUCKET_CONTENTS *));
  new_table->nbuckets = buckets;
  new_table->nentries = 0;

  for (i = 0; i < buckets; i++)
    new_table->bucket_array[i] = (BUCKET_CONTENTS *)NULL;

  return (new_table);
}

int
hash_size (table)
     HASH_TABLE *table;
{
  return (HASH_ENTRIES(table));
}

static BUCKET_CONTENTS *
copy_bucket_array (ba, cpdata)
     BUCKET_CONTENTS *ba;
     sh_string_func_t *cpdata;	/* data copy function */
{
  BUCKET_CONTENTS *new_bucket, *n, *e;

  if (ba == 0)
    return ((BUCKET_CONTENTS *)0);

  for (n = (BUCKET_CONTENTS *)0, e = ba; e; e = e->next)
    {
      if (n == 0)
        {
          new_bucket = (BUCKET_CONTENTS *)xmalloc (sizeof (BUCKET_CONTENTS));
          n = new_bucket;
        }
      else
        {
          n->next = (BUCKET_CONTENTS *)xmalloc (sizeof (BUCKET_CONTENTS));
          n = n->next;
        }

      n->key = savestring (e->key);
      n->data = e->data ? (cpdata ? (*cpdata) (e->data) : savestring (e->data))
			: NULL;
      n->khash = e->khash;
      n->times_found = e->times_found;
      n->next = (BUCKET_CONTENTS *)NULL;
    }

  return new_bucket;  
}

HASH_TABLE *
hash_copy (table, cpdata)
     HASH_TABLE *table;
     sh_string_func_t *cpdata;
{
  HASH_TABLE *new_table;
  int i;

  if (table == 0)
    return ((HASH_TABLE *)NULL);

  new_table = hash_create (table->nbuckets);

  for (i = 0; i < table->nbuckets; i++)
    new_table->bucket_array[i] = copy_bucket_array (table->bucket_array[i], cpdata);

  new_table->nentries = table->nentries;
  return new_table;
}

128 129 130 131 132 133 134 135 136 137 138 139 140 141
/* This is the best 32-bit string hash function I found. It's one of the
   Fowler-Noll-Vo family (FNV-1).

   The magic is in the interesting relationship between the special prime
   16777619 (2^24 + 403) and 2^32 and 2^8. */

#define FNV_OFFSET 2166136261
#define FNV_PRIME 16777619

/* If you want to use 64 bits, use
FNV_OFFSET	14695981039346656037
FNV_PRIMT	1099511628211
*/

142 143 144 145 146 147 148 149
/* The `khash' check below requires that strings that compare equally with
   strcmp hash to the same value. */
unsigned int
hash_string (s)
     const char *s;
{
  register unsigned int i;

150
  for (i = FNV_OFFSET; *s; s++)
151
    {
152
      i *= FNV_PRIME;
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
      i ^= *s;
    }

  return i;
}

/* Return the location of the bucket which should contain the data
   for STRING.  TABLE is a pointer to a HASH_TABLE. */

int
hash_bucket (string, table)
     const char *string;
     HASH_TABLE *table;
{
  unsigned int h;

  return (HASH_BUCKET (string, table, h));
}

/* Return a pointer to the hashed item.  If the HASH_CREATE flag is passed,
   create a new hash table entry for STRING, otherwise return NULL. */
BUCKET_CONTENTS *
hash_search (string, table, flags)
     const char *string;
     HASH_TABLE *table;
     int flags;
{
  BUCKET_CONTENTS *list;
  int bucket;
  unsigned int hv;

  if (table == 0 || ((flags & HASH_CREATE) == 0 && HASH_ENTRIES (table) == 0))
    return (BUCKET_CONTENTS *)NULL;

  bucket = HASH_BUCKET (string, table, hv);

  for (list = table->bucket_array ? table->bucket_array[bucket] : 0; list; list = list->next)
    {
191
      /* This is the comparison function */
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
      if (hv == list->khash && STREQ (list->key, string))
	{
	  list->times_found++;
	  return (list);
	}
    }

  if (flags & HASH_CREATE)
    {
      list = (BUCKET_CONTENTS *)xmalloc (sizeof (BUCKET_CONTENTS));
      list->next = table->bucket_array[bucket];
      table->bucket_array[bucket] = list;

      list->data = NULL;
      list->key = (char *)string;	/* XXX fix later */
      list->khash = hv;
      list->times_found = 0;

      table->nentries++;
      return (list);
    }
      
  return (BUCKET_CONTENTS *)NULL;
}

/* Remove the item specified by STRING from the hash table TABLE.
   The item removed is returned, so you can free its contents.  If
   the item isn't in this table NULL is returned. */
BUCKET_CONTENTS *
hash_remove (string, table, flags)
     const char *string;
     HASH_TABLE *table;
     int flags;
{
  int bucket;
  BUCKET_CONTENTS *prev, *temp;
  unsigned int hv;

  if (table == 0 || HASH_ENTRIES (table) == 0)
    return (BUCKET_CONTENTS *)NULL;

  bucket = HASH_BUCKET (string, table, hv);
  prev = (BUCKET_CONTENTS *)NULL;
  for (temp = table->bucket_array[bucket]; temp; temp = temp->next)
    {
      if (hv == temp->khash && STREQ (temp->key, string))
	{
	  if (prev)
	    prev->next = temp->next;
	  else
	    table->bucket_array[bucket] = temp->next;

	  table->nentries--;
	  return (temp);
	}
      prev = temp;
    }
  return ((BUCKET_CONTENTS *) NULL);
}

/* Create an entry for STRING, in TABLE.  If the entry already
   exists, then return it (unless the HASH_NOSRCH flag is set). */
BUCKET_CONTENTS *
hash_insert (string, table, flags)
     char *string;
     HASH_TABLE *table;
     int flags;
{
  BUCKET_CONTENTS *item;
  int bucket;
  unsigned int hv;

  if (table == 0)
    table = hash_create (0);

  item = (flags & HASH_NOSRCH) ? (BUCKET_CONTENTS *)NULL
  			       : hash_search (string, table, 0);

  if (item == 0)
    {
      bucket = HASH_BUCKET (string, table, hv);

      item = (BUCKET_CONTENTS *)xmalloc (sizeof (BUCKET_CONTENTS));
      item->next = table->bucket_array[bucket];
      table->bucket_array[bucket] = item;

      item->data = NULL;
      item->key = string;
      item->khash = hv;
      item->times_found = 0;

      table->nentries++;
    }

  return (item);
}

/* Remove and discard all entries in TABLE.  If FREE_DATA is non-null, it
   is a function to call to dispose of a hash item's data.  Otherwise,
   free() is called. */
void
hash_flush (table, free_data)
     HASH_TABLE *table;
     sh_free_func_t *free_data;
{
  int i;
  register BUCKET_CONTENTS *bucket, *item;

  if (table == 0 || HASH_ENTRIES (table) == 0)
    return;

  for (i = 0; i < table->nbuckets; i++)
    {
      bucket = table->bucket_array[i];

      while (bucket)
	{
	  item = bucket;
	  bucket = bucket->next;

	  if (free_data)
	    (*free_data) (item->data);
	  else
	    free (item->data);
	  free (item->key);
	  free (item);
	}
      table->bucket_array[i] = (BUCKET_CONTENTS *)NULL;
    }

  table->nentries = 0;
}

/* Free the hash table pointed to by TABLE. */
void
hash_dispose (table)
     HASH_TABLE *table;
{
  free (table->bucket_array);
  free (table);
}

void
hash_walk (table, func)
     HASH_TABLE *table;
     hash_wfunc *func;
{
  register int i;
  BUCKET_CONTENTS *item;

  if (table == 0 || HASH_ENTRIES (table) == 0)
    return;

  for (i = 0; i < table->nbuckets; i++)
    {
      for (item = hash_items (i, table); item; item = item->next)
	if ((*func) (item) < 0)
	  return;
    }
}

#if defined (DEBUG) || defined (TEST_HASHING)
void
hash_pstats (table, name)
     HASH_TABLE *table;
     char *name;
{
  register int slot, bcount;
  register BUCKET_CONTENTS *bc;

  if (name == 0)
    name = "unknown hash table";

  fprintf (stderr, "%s: %d buckets; %d items\n", name, table->nbuckets, table->nentries);

  /* Print out a count of how many strings hashed to each bucket, so we can
     see how even the distribution is. */
  for (slot = 0; slot < table->nbuckets; slot++)
    {
      bc = hash_items (slot, table);

      fprintf (stderr, "\tslot %3d: ", slot);
      for (bcount = 0; bc; bc = bc->next)
	bcount++;

      fprintf (stderr, "%d\n", bcount);
    }
}
#endif

#ifdef TEST_HASHING

/* link with xmalloc.o and lib/malloc/libmalloc.a */
#undef NULL
#include <stdio.h>

#ifndef NULL
#define NULL 0
#endif

HASH_TABLE *table, *ntable;

int interrupt_immediately = 0;

int
signal_is_trapped (s)
     int s;
{
  return (0);
}

void
programming_error (const char *format, ...)
{
  abort();
}

void
fatal_error (const char *format, ...)
{
  abort();
}

415 416 417 418 419
void
internal_warning (const char *format, ...)
{
}

420 421 422 423 424 425
main ()
{
  char string[256];
  int count = 0;
  BUCKET_CONTENTS *tt;

426 427 428
#if defined (TEST_NBUCKETS)
  table = hash_create (TEST_NBUCKETS);
#else
429
  table = hash_create (0);
430
#endif
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

  for (;;)
    {
      char *temp_string;
      if (fgets (string, sizeof (string), stdin) == 0)
	break;
      if (!*string)
	break;
      temp_string = savestring (string);
      tt = hash_insert (temp_string, table, 0);
      if (tt->times_found)
	{
	  fprintf (stderr, "You have already added item `%s'\n", string);
	  free (temp_string);
	}
      else
	{
	  count++;
	}
    }

  hash_pstats (table, "hash test");

  ntable = hash_copy (table, (sh_string_func_t *)NULL);
  hash_flush (table, (sh_free_func_t *)NULL);
  hash_pstats (ntable, "hash copy test");

  exit (0);
}

#endif /* TEST_HASHING */