string/strlen.c

   1 /* Copyright (C) 1991-2023 Free Software Foundation, Inc.
   2    This file is part of the GNU C Library.
   3
   4    The GNU C Library is free software; you can redistribute it and/or
   5    modify it under the terms of the GNU Lesser General Public
   6    License as published by the Free Software Foundation; either
   7    version 2.1 of the License, or (at your option) any later version.
   8
   9    The GNU C Library is distributed in the hope that it will be useful,
  10    but WITHOUT ANY WARRANTY; without even the implied warranty of
  11    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  12    Lesser General Public License for more details.
  13
  14    You should have received a copy of the GNU Lesser General Public
  15    License along with the GNU C Library; if not, see
  16    <https://www.gnu.org/licenses/>.  */
  17
  18 #include <string.h>
  19 #include <stdlib.h>
  20
  21 #undef strlen
  22
  23 #ifndef STRLEN
  24 # define STRLEN strlen
  25 #endif
  26
  27 /* Return the length of the null-terminated string STR.  Scan for
  28    the null terminator quickly by testing four bytes at a time.  */
  29 size_t
  30 STRLEN (const char *str)
  31 {
  32   const char *char_ptr;
  33   const unsigned long int *longword_ptr;
  34   unsigned long int longword, himagic, lomagic;
  35
  36   /* Handle the first few characters by reading one character at a time.
  37      Do this until CHAR_PTR is aligned on a longword boundary.  */
  38   for (char_ptr = str; ((unsigned long int) char_ptr
  39                         & (sizeof (longword) - 1)) != 0;
  40        ++char_ptr)
  41     if (*char_ptr == '\0')
  42       return char_ptr - str;
  43
  44   /* All these elucidatory comments refer to 4-byte longwords,
  45      but the theory applies equally well to 8-byte longwords.  */
  46
  47   longword_ptr = (unsigned long int *) char_ptr;
  48
  49   /* Computing (longword - lomagic) sets the high bit of any corresponding
  50      byte that is either zero or greater than 0x80.  The latter case can be
  51      filtered out by computing (~longword & himagic).  The final result
  52      will always be non-zero if one of the bytes of longword is zero.  */
  53   himagic = 0x80808080L;
  54   lomagic = 0x01010101L;
  55   if (sizeof (longword) > 4)
  56     {
  57       /* 64-bit version of the magic.  */
  58       /* Do the shift in two steps to avoid a warning if long has 32 bits.  */
  59       himagic = ((himagic << 16) << 16) | himagic;
  60       lomagic = ((lomagic << 16) << 16) | lomagic;
  61     }
  62   if (sizeof (longword) > 8)
  63     abort ();
  64
  65   /* Instead of the traditional loop which tests each character,
  66      we will test a longword at a time.  The tricky part is testing
  67      if *any of the four* bytes in the longword in question are zero.  */
  68   for (;;)
  69     {
  70       longword = *longword_ptr++;
  71
  72       if (((longword - lomagic) & ~longword & himagic) != 0)
  73         {
  74           /* Which of the bytes was the zero?  */
  75
  76           const char *cp = (const char *) (longword_ptr - 1);
  77
  78           if (cp[0] == 0)
  79             return cp - str;
  80           if (cp[1] == 0)
  81             return cp - str + 1;
  82           if (cp[2] == 0)
  83             return cp - str + 2;
  84           if (cp[3] == 0)
  85             return cp - str + 3;
  86           if (sizeof (longword) > 4)
  87             {
  88               if (cp[4] == 0)
  89                 return cp - str + 4;
  90               if (cp[5] == 0)
  91                 return cp - str + 5;
  92               if (cp[6] == 0)
  93                 return cp - str + 6;
  94               if (cp[7] == 0)
  95                 return cp - str + 7;
  96             }
  97         }
  98     }
  99 }
 100 libc_hidden_builtin_def (strlen)