string/strchr.c

   1 /* Copyright (C) 1991-2013 Free Software Foundation, Inc.
   2    This file is part of the GNU C Library.
   3    Based on strlen implementation by Torbjorn Granlund (tege@sics.se),
   4    with help from Dan Sahlin (dan@sics.se) and
   5    bug fix and commentary by Jim Blandy (jimb@ai.mit.edu);
   6    adaptation to strchr suggested by Dick Karpinski (dick@cca.ucsf.edu),
   7    and implemented by Roland McGrath (roland@ai.mit.edu).
   8
   9    The GNU C Library is free software; you can redistribute it and/or
  10    modify it under the terms of the GNU Lesser General Public
  11    License as published by the Free Software Foundation; either
  12    version 2.1 of the License, or (at your option) any later version.
  13
  14    The GNU C Library is distributed in the hope that it will be useful,
  15    but WITHOUT ANY WARRANTY; without even the implied warranty of
  16    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  17    Lesser General Public License for more details.
  18
  19    You should have received a copy of the GNU Lesser General Public
  20    License along with the GNU C Library; if not, see
  21    <http://www.gnu.org/licenses/>.  */
  22
  23 #include <string.h>
  24 #include <memcopy.h>
  25 #include <stdlib.h>
  26
  27 #undef strchr
  28
  29 /* Find the first occurrence of C in S.  */
  30 char *
  31 strchr (s, c_in)
  32      const char *s;
  33      int c_in;
  34 {
  35   const unsigned char *char_ptr;
  36   const unsigned long int *longword_ptr;
  37   unsigned long int longword, magic_bits, charmask;
  38   unsigned char c;
  39
  40   c = (unsigned char) c_in;
  41
  42   /* Handle the first few characters by reading one character at a time.
  43      Do this until CHAR_PTR is aligned on a longword boundary.  */
  44   for (char_ptr = (const unsigned char *) s;
  45        ((unsigned long int) char_ptr & (sizeof (longword) - 1)) != 0;
  46        ++char_ptr)
  47     if (*char_ptr == c)
  48       return (void *) char_ptr;
  49     else if (*char_ptr == '\0')
  50       return NULL;
  51
  52   /* All these elucidatory comments refer to 4-byte longwords,
  53      but the theory applies equally well to 8-byte longwords.  */
  54
  55   longword_ptr = (unsigned long int *) char_ptr;
  56
  57   /* Bits 31, 24, 16, and 8 of this number are zero.  Call these bits
  58      the "holes."  Note that there is a hole just to the left of
  59      each byte, with an extra at the end:
  60
  61      bits:  01111110 11111110 11111110 11111111
  62      bytes: AAAAAAAA BBBBBBBB CCCCCCCC DDDDDDDD
  63
  64      The 1-bits make sure that carries propagate to the next 0-bit.
  65      The 0-bits provide holes for carries to fall into.  */
  66   switch (sizeof (longword))
  67     {
  68     case 4: magic_bits = 0x7efefeffL; break;
  69     case 8: magic_bits = ((0x7efefefeL << 16) << 16) | 0xfefefeffL; break;
  70     default:
  71       abort ();
  72     }
  73
  74   /* Set up a longword, each of whose bytes is C.  */
  75   charmask = c | (c << 8);
  76   charmask |= charmask << 16;
  77   if (sizeof (longword) > 4)
  78     /* Do the shift in two steps to avoid a warning if long has 32 bits.  */
  79     charmask |= (charmask << 16) << 16;
  80   if (sizeof (longword) > 8)
  81     abort ();
  82
  83   /* Instead of the traditional loop which tests each character,
  84      we will test a longword at a time.  The tricky part is testing
  85      if *any of the four* bytes in the longword in question are zero.  */
  86   for (;;)
  87     {
  88       /* We tentatively exit the loop if adding MAGIC_BITS to
  89          LONGWORD fails to change any of the hole bits of LONGWORD.
  90
  91          1) Is this safe?  Will it catch all the zero bytes?
  92          Suppose there is a byte with all zeros.  Any carry bits
  93          propagating from its left will fall into the hole at its
  94          least significant bit and stop.  Since there will be no
  95          carry from its most significant bit, the LSB of the
  96          byte to the left will be unchanged, and the zero will be
  97          detected.
  98
  99          2) Is this worthwhile?  Will it ignore everything except
 100          zero bytes?  Suppose every byte of LONGWORD has a bit set
 101          somewhere.  There will be a carry into bit 8.  If bit 8
 102          is set, this will carry into bit 16.  If bit 8 is clear,
 103          one of bits 9-15 must be set, so there will be a carry
 104          into bit 16.  Similarly, there will be a carry into bit
 105          24.  If one of bits 24-30 is set, there will be a carry
 106          into bit 31, so all of the hole bits will be changed.
 107
 108          The one misfire occurs when bits 24-30 are clear and bit
 109          31 is set; in this case, the hole at bit 31 is not
 110          changed.  If we had access to the processor carry flag,
 111          we could close this loophole by putting the fourth hole
 112          at bit 32!
 113
 114          So it ignores everything except 128's, when they're aligned
 115          properly.
 116
 117          3) But wait!  Aren't we looking for C as well as zero?
 118          Good point.  So what we do is XOR LONGWORD with a longword,
 119          each of whose bytes is C.  This turns each byte that is C
 120          into a zero.  */
 121
 122       longword = *longword_ptr++;
 123
 124       /* Add MAGIC_BITS to LONGWORD.  */
 125       if ((((longword + magic_bits)
 126
 127             /* Set those bits that were unchanged by the addition.  */
 128             ^ ~longword)
 129
 130            /* Look at only the hole bits.  If any of the hole bits
 131               are unchanged, most likely one of the bytes was a
 132               zero.  */
 133            & ~magic_bits) != 0 ||
 134
 135           /* That caught zeroes.  Now test for C.  */
 136           ((((longword ^ charmask) + magic_bits) ^ ~(longword ^ charmask))
 137            & ~magic_bits) != 0)
 138         {
 139           /* Which of the bytes was C or zero?
 140              If none of them were, it was a misfire; continue the search.  */
 141
 142           const unsigned char *cp = (const unsigned char *) (longword_ptr - 1);
 143
 144           if (*cp == c)
 145             return (char *) cp;
 146           else if (*cp == '\0')
 147             return NULL;
 148           if (*++cp == c)
 149             return (char *) cp;
 150           else if (*cp == '\0')
 151             return NULL;
 152           if (*++cp == c)
 153             return (char *) cp;
 154           else if (*cp == '\0')
 155             return NULL;
 156           if (*++cp == c)
 157             return (char *) cp;
 158           else if (*cp == '\0')
 159             return NULL;
 160           if (sizeof (longword) > 4)
 161             {
 162               if (*++cp == c)
 163                 return (char *) cp;
 164               else if (*cp == '\0')
 165                 return NULL;
 166               if (*++cp == c)
 167                 return (char *) cp;
 168               else if (*cp == '\0')
 169                 return NULL;
 170               if (*++cp == c)
 171                 return (char *) cp;
 172               else if (*cp == '\0')
 173                 return NULL;
 174               if (*++cp == c)
 175                 return (char *) cp;
 176               else if (*cp == '\0')
 177                 return NULL;
 178             }
 179         }
 180     }
 181
 182   return NULL;
 183 }
 184
 185 #ifdef weak_alias
 186 #undef index
 187 weak_alias (strchr, index)
 188 #endif
 189 libc_hidden_builtin_def (strchr)