string/strchr.c

   1 /* Copyright (C) 1991-2015 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 <stdlib.h>
  25
  26 #undef strchr
  27
  28 /* Find the first occurrence of C in S.  */
  29 char *
  30 strchr (const char *s, int c_in)
  31 {
  32   const unsigned char *char_ptr;
  33   const unsigned long int *longword_ptr;
  34   unsigned long int longword, magic_bits, charmask;
  35   unsigned char c;
  36
  37   c = (unsigned char) c_in;
  38
  39   /* Handle the first few characters by reading one character at a time.
  40      Do this until CHAR_PTR is aligned on a longword boundary.  */
  41   for (char_ptr = (const unsigned char *) s;
  42        ((unsigned long int) char_ptr & (sizeof (longword) - 1)) != 0;
  43        ++char_ptr)
  44     if (*char_ptr == c)
  45       return (void *) char_ptr;
  46     else if (*char_ptr == '\0')
  47       return NULL;
  48
  49   /* All these elucidatory comments refer to 4-byte longwords,
  50      but the theory applies equally well to 8-byte longwords.  */
  51
  52   longword_ptr = (unsigned long int *) char_ptr;
  53
  54   /* Bits 31, 24, 16, and 8 of this number are zero.  Call these bits
  55      the "holes."  Note that there is a hole just to the left of
  56      each byte, with an extra at the end:
  57
  58      bits:  01111110 11111110 11111110 11111111
  59      bytes: AAAAAAAA BBBBBBBB CCCCCCCC DDDDDDDD
  60
  61      The 1-bits make sure that carries propagate to the next 0-bit.
  62      The 0-bits provide holes for carries to fall into.  */
  63   switch (sizeof (longword))
  64     {
  65     case 4: magic_bits = 0x7efefeffL; break;
  66     case 8: magic_bits = ((0x7efefefeL << 16) << 16) | 0xfefefeffL; break;
  67     default:
  68       abort ();
  69     }
  70
  71   /* Set up a longword, each of whose bytes is C.  */
  72   charmask = c | (c << 8);
  73   charmask |= charmask << 16;
  74   if (sizeof (longword) > 4)
  75     /* Do the shift in two steps to avoid a warning if long has 32 bits.  */
  76     charmask |= (charmask << 16) << 16;
  77   if (sizeof (longword) > 8)
  78     abort ();
  79
  80   /* Instead of the traditional loop which tests each character,
  81      we will test a longword at a time.  The tricky part is testing
  82      if *any of the four* bytes in the longword in question are zero.  */
  83   for (;;)
  84     {
  85       /* We tentatively exit the loop if adding MAGIC_BITS to
  86          LONGWORD fails to change any of the hole bits of LONGWORD.
  87
  88          1) Is this safe?  Will it catch all the zero bytes?
  89          Suppose there is a byte with all zeros.  Any carry bits
  90          propagating from its left will fall into the hole at its
  91          least significant bit and stop.  Since there will be no
  92          carry from its most significant bit, the LSB of the
  93          byte to the left will be unchanged, and the zero will be
  94          detected.
  95
  96          2) Is this worthwhile?  Will it ignore everything except
  97          zero bytes?  Suppose every byte of LONGWORD has a bit set
  98          somewhere.  There will be a carry into bit 8.  If bit 8
  99          is set, this will carry into bit 16.  If bit 8 is clear,
 100          one of bits 9-15 must be set, so there will be a carry
 101          into bit 16.  Similarly, there will be a carry into bit
 102          24.  If one of bits 24-30 is set, there will be a carry
 103          into bit 31, so all of the hole bits will be changed.
 104
 105          The one misfire occurs when bits 24-30 are clear and bit
 106          31 is set; in this case, the hole at bit 31 is not
 107          changed.  If we had access to the processor carry flag,
 108          we could close this loophole by putting the fourth hole
 109          at bit 32!
 110
 111          So it ignores everything except 128's, when they're aligned
 112          properly.
 113
 114          3) But wait!  Aren't we looking for C as well as zero?
 115          Good point.  So what we do is XOR LONGWORD with a longword,
 116          each of whose bytes is C.  This turns each byte that is C
 117          into a zero.  */
 118
 119       longword = *longword_ptr++;
 120
 121       /* Add MAGIC_BITS to LONGWORD.  */
 122       if ((((longword + magic_bits)
 123
 124             /* Set those bits that were unchanged by the addition.  */
 125             ^ ~longword)
 126
 127            /* Look at only the hole bits.  If any of the hole bits
 128               are unchanged, most likely one of the bytes was a
 129               zero.  */
 130            & ~magic_bits) != 0 ||
 131
 132           /* That caught zeroes.  Now test for C.  */
 133           ((((longword ^ charmask) + magic_bits) ^ ~(longword ^ charmask))
 134            & ~magic_bits) != 0)
 135         {
 136           /* Which of the bytes was C or zero?
 137              If none of them were, it was a misfire; continue the search.  */
 138
 139           const unsigned char *cp = (const unsigned char *) (longword_ptr - 1);
 140
 141           if (*cp == c)
 142             return (char *) cp;
 143           else if (*cp == '\0')
 144             return NULL;
 145           if (*++cp == c)
 146             return (char *) cp;
 147           else if (*cp == '\0')
 148             return NULL;
 149           if (*++cp == c)
 150             return (char *) cp;
 151           else if (*cp == '\0')
 152             return NULL;
 153           if (*++cp == c)
 154             return (char *) cp;
 155           else if (*cp == '\0')
 156             return NULL;
 157           if (sizeof (longword) > 4)
 158             {
 159               if (*++cp == c)
 160                 return (char *) cp;
 161               else if (*cp == '\0')
 162                 return NULL;
 163               if (*++cp == c)
 164                 return (char *) cp;
 165               else if (*cp == '\0')
 166                 return NULL;
 167               if (*++cp == c)
 168                 return (char *) cp;
 169               else if (*cp == '\0')
 170                 return NULL;
 171               if (*++cp == c)
 172                 return (char *) cp;
 173               else if (*cp == '\0')
 174                 return NULL;
 175             }
 176         }
 177     }
 178
 179   return NULL;
 180 }
 181
 182 #ifdef weak_alias
 183 #undef index
 184 weak_alias (strchr, index)
 185 #endif
 186 libc_hidden_builtin_def (strchr)