misc/hsearch_r.c

   1 /* Copyright (C) 1993-2020 Free Software Foundation, Inc.
   2    This file is part of the GNU C Library.
   3    Contributed by Ulrich Drepper <drepper@gnu.ai.mit.edu>, 1993.
   4
   5    The GNU C Library is free software; you can redistribute it and/or
   6    modify it under the terms of the GNU Lesser General Public
   7    License as published by the Free Software Foundation; either
   8    version 2.1 of the License, or (at your option) any later version.
   9
  10    The GNU C Library is distributed in the hope that it will be useful,
  11    but WITHOUT ANY WARRANTY; without even the implied warranty of
  12    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  13    Lesser General Public License for more details.
  14
  15    You should have received a copy of the GNU Lesser General Public
  16    License along with the GNU C Library; if not, see
  17    <https://www.gnu.org/licenses/>.  */
  18
  19 #include <errno.h>
  20 #include <malloc.h>
  21 #include <string.h>
  22 #include <stdint.h>
  23 #include <search.h>
  24 #include <limits.h>
  25
  26 /* [Aho,Sethi,Ullman] Compilers: Principles, Techniques and Tools, 1986
  27    [Knuth]            The Art of Computer Programming, part 3 (6.4)  */
  28
  29
  30 /* The reentrant version has no static variables to maintain the state.
  31    Instead the interface of all functions is extended to take an argument
  32    which describes the current status.  */
  33 typedef struct _ENTRY
  34 {
  35   unsigned int used;
  36   ENTRY entry;
  37 }
  38 _ENTRY;
  39
  40
  41 /* For the used double hash method the table size has to be a prime. To
  42    correct the user given table size we need a prime test.  This trivial
  43    algorithm is adequate because
  44    a)  the code is (most probably) called a few times per program run and
  45    b)  the number is small because the table must fit in the core  */
  46 static int
  47 isprime (unsigned int number)
  48 {
  49   /* no even number will be passed */
  50   for (unsigned int div = 3; div <= number / div; div += 2)
  51     if (number % div == 0)
  52       return 0;
  53   return 1;
  54 }
  55
  56 /* Before using the hash table we must allocate memory for it.
  57    Test for an existing table are done. We allocate one element
  58    more as the found prime number says. This is done for more effective
  59    indexing as explained in the comment for the hsearch function.
  60    The contents of the table is zeroed, especially the field used
  61    becomes zero.  */
  62 int
  63 __hcreate_r (size_t nel, struct hsearch_data *htab)
  64 {
  65   /* Test for correct arguments.  */
  66   if (htab == NULL)
  67     {
  68       __set_errno (EINVAL);
  69       return 0;
  70     }
  71
  72   /* There is still another table active. Return with error. */
  73   if (htab->table != NULL)
  74     return 0;
  75
  76   /* We need a size of at least 3.  Otherwise the hash functions we
  77      use will not work.  */
  78   if (nel < 3)
  79     nel = 3;
  80
  81   /* Change nel to the first prime number in the range [nel, UINT_MAX - 2],
  82      The '- 2' means 'nel += 2' cannot overflow.  */
  83   for (nel |= 1; ; nel += 2)
  84     {
  85       if (UINT_MAX - 2 < nel)
  86         {
  87           __set_errno (ENOMEM);
  88           return 0;
  89         }
  90       if (isprime (nel))
  91         break;
  92     }
  93
  94   htab->size = nel;
  95   htab->filled = 0;
  96
  97   /* allocate memory and zero out */
  98   htab->table = (_ENTRY *) calloc (htab->size + 1, sizeof (_ENTRY));
  99   if (htab->table == NULL)
 100     return 0;
 101
 102   /* everything went alright */
 103   return 1;
 104 }
 105 libc_hidden_def (__hcreate_r)
 106 weak_alias (__hcreate_r, hcreate_r)
 107
 108
 109 /* After using the hash table it has to be destroyed. The used memory can
 110    be freed and the local static variable can be marked as not used.  */
 111 void
 112 __hdestroy_r (struct hsearch_data *htab)
 113 {
 114   /* Test for correct arguments.  */
 115   if (htab == NULL)
 116     {
 117       __set_errno (EINVAL);
 118       return;
 119     }
 120
 121   /* Free used memory.  */
 122   free (htab->table);
 123
 124   /* the sign for an existing table is an value != NULL in htable */
 125   htab->table = NULL;
 126 }
 127 libc_hidden_def (__hdestroy_r)
 128 weak_alias (__hdestroy_r, hdestroy_r)
 129
 130
 131 /* This is the search function. It uses double hashing with open addressing.
 132    The argument item.key has to be a pointer to an zero terminated, most
 133    probably strings of chars. The function for generating a number of the
 134    strings is simple but fast. It can be replaced by a more complex function
 135    like ajw (see [Aho,Sethi,Ullman]) if the needs are shown.
 136
 137    We use an trick to speed up the lookup. The table is created by hcreate
 138    with one more element available. This enables us to use the index zero
 139    special. This index will never be used because we store the first hash
 140    index in the field used where zero means not used. Every other value
 141    means used. The used field can be used as a first fast comparison for
 142    equality of the stored and the parameter value. This helps to prevent
 143    unnecessary expensive calls of strcmp.  */
 144 int
 145 __hsearch_r (ENTRY item, ACTION action, ENTRY **retval,
 146              struct hsearch_data *htab)
 147 {
 148   unsigned int hval;
 149   unsigned int count;
 150   unsigned int len = strlen (item.key);
 151   unsigned int idx;
 152
 153   /* Compute an value for the given string. Perhaps use a better method. */
 154   hval = len;
 155   count = len;
 156   while (count-- > 0)
 157     {
 158       hval <<= 4;
 159       hval += item.key[count];
 160     }
 161   if (hval == 0)
 162     ++hval;
 163
 164   /* First hash function: simply take the modul but prevent zero. */
 165   idx = hval % htab->size + 1;
 166
 167   if (htab->table[idx].used)
 168     {
 169       /* Further action might be required according to the action value. */
 170       if (htab->table[idx].used == hval
 171           && strcmp (item.key, htab->table[idx].entry.key) == 0)
 172         {
 173           *retval = &htab->table[idx].entry;
 174           return 1;
 175         }
 176
 177       /* Second hash function, as suggested in [Knuth] */
 178       unsigned int hval2 = 1 + hval % (htab->size - 2);
 179       unsigned int first_idx = idx;
 180
 181       do
 182         {
 183           /* Because SIZE is prime this guarantees to step through all
 184              available indeces.  */
 185           if (idx <= hval2)
 186             idx = htab->size + idx - hval2;
 187           else
 188             idx -= hval2;
 189
 190           /* If we visited all entries leave the loop unsuccessfully.  */
 191           if (idx == first_idx)
 192             break;
 193
 194             /* If entry is found use it. */
 195           if (htab->table[idx].used == hval
 196               && strcmp (item.key, htab->table[idx].entry.key) == 0)
 197             {
 198               *retval = &htab->table[idx].entry;
 199               return 1;
 200             }
 201         }
 202       while (htab->table[idx].used);
 203     }
 204
 205   /* An empty bucket has been found. */
 206   if (action == ENTER)
 207     {
 208       /* If table is full and another entry should be entered return
 209          with error.  */
 210       if (htab->filled == htab->size)
 211         {
 212           __set_errno (ENOMEM);
 213           *retval = NULL;
 214           return 0;
 215         }
 216
 217       htab->table[idx].used  = hval;
 218       htab->table[idx].entry = item;
 219
 220       ++htab->filled;
 221
 222       *retval = &htab->table[idx].entry;
 223       return 1;
 224     }
 225
 226   __set_errno (ESRCH);
 227   *retval = NULL;
 228   return 0;
 229 }
 230 libc_hidden_def (__hsearch_r)
 231 weak_alias (__hsearch_r, hsearch_r)