string/strcasestr.c

   1 /* Return the offset of one string within another.
   2    Copyright (C) 1994-2012 Free Software Foundation, Inc.
   3    This file is part of the GNU C Library.
   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    <http://www.gnu.org/licenses/>.  */
  18
  19 /*
  20  * My personal strstr() implementation that beats most other algorithms.
  21  * Until someone tells me otherwise, I assume that this is the
  22  * fastest implementation of strstr() in C.
  23  * I deliberately chose not to comment it.  You should have at least
  24  * as much fun trying to understand it, as I had to write it :-).
  25  *
  26  * Stephen R. van den Berg, berg@pool.informatik.rwth-aachen.de */
  27
  28 #if HAVE_CONFIG_H
  29 # include <config.h>
  30 #endif
  31
  32 /* Specification.  */
  33 #include <string.h>
  34
  35 #include <ctype.h>
  36 #include <stdbool.h>
  37 #include <strings.h>
  38
  39 #define TOLOWER(Ch) tolower (Ch)
  40
  41 /* Two-Way algorithm.  */
  42 #define RETURN_TYPE char *
  43 #define AVAILABLE(h, h_l, j, n_l)                       \
  44   (!memchr ((h) + (h_l), '\0', (j) + (n_l) - (h_l))     \
  45    && ((h_l) = (j) + (n_l)))
  46 #define AVAILABLE1(h, h_l, j, n_l) (true)
  47 #define AVAILABLE2(h, h_l, j, n_l) AVAILABLE (h, h_l, j, n_l)
  48 #define RET0_IF_0(a) if (!a) goto ret0
  49 #define AVAILABLE1_USES_J (0)
  50 #define CANON_ELEMENT(c) TOLOWER (c)
  51 #define CMP_FUNC(p1, p2, l)                             \
  52   __strncasecmp ((const char *) (p1), (const char *) (p2), l)
  53 #include "str-two-way.h"
  54
  55 #undef strcasestr
  56 #undef __strcasestr
  57
  58 #ifndef STRCASESTR
  59 #define STRCASESTR __strcasestr
  60 #endif
  61
  62
  63 /* Find the first occurrence of NEEDLE in HAYSTACK, using
  64    case-insensitive comparison.  This function gives unspecified
  65    results in multibyte locales.  */
  66 char *
  67 STRCASESTR (const char *haystack_start, const char *needle_start)
  68 {
  69   const char *haystack = haystack_start;
  70   const char *needle = needle_start;
  71   size_t needle_len; /* Length of NEEDLE.  */
  72   size_t haystack_len; /* Known minimum length of HAYSTACK.  */
  73   bool ok = true; /* True if NEEDLE is prefix of HAYSTACK.  */
  74
  75   /* Determine length of NEEDLE, and in the process, make sure
  76      HAYSTACK is at least as long (no point processing all of a long
  77      NEEDLE if HAYSTACK is too short).  */
  78   while (*haystack && *needle)
  79     {
  80       ok &= (TOLOWER ((unsigned char) *haystack)
  81              == TOLOWER ((unsigned char) *needle));
  82       haystack++;
  83       needle++;
  84     }
  85   if (*needle)
  86     return NULL;
  87   if (ok)
  88     return (char *) haystack_start;
  89   needle_len = needle - needle_start;
  90   haystack = haystack_start + 1;
  91   haystack_len = needle_len - 1;
  92
  93   /* Perform the search.  Abstract memory is considered to be an array
  94      of 'unsigned char' values, not an array of 'char' values.  See
  95      ISO C 99 section 6.2.6.1.  */
  96   if (needle_len < LONG_NEEDLE_THRESHOLD)
  97     return two_way_short_needle ((const unsigned char *) haystack,
  98                                  haystack_len,
  99                                  (const unsigned char *) needle_start,
 100                                  needle_len);
 101   return two_way_long_needle ((const unsigned char *) haystack, haystack_len,
 102                               (const unsigned char *) needle_start,
 103                               needle_len);
 104 }
 105
 106 #undef LONG_NEEDLE_THRESHOLD
 107
 108 #ifndef NO_ALIAS
 109 weak_alias (__strcasestr, strcasestr)
 110 #endif