string/strcasestr.c

   1 /* Return the offset of one string within another.
   2    Copyright (C) 1994, 1996-2000, 2004, 2008, 2009, 2010
   3    Free Software Foundation, Inc.
   4    This file is part of the GNU C Library.
   5
   6    The GNU C Library is free software; you can redistribute it and/or
   7    modify it under the terms of the GNU Lesser General Public
   8    License as published by the Free Software Foundation; either
   9    version 2.1 of the License, or (at your option) any later version.
  10
  11    The GNU C Library is distributed in the hope that it will be useful,
  12    but WITHOUT ANY WARRANTY; without even the implied warranty of
  13    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  14    Lesser General Public License for more details.
  15
  16    You should have received a copy of the GNU Lesser General Public
  17    License along with the GNU C Library; if not, see
  18    <http://www.gnu.org/licenses/>.  */
  19
  20 /*
  21  * My personal strstr() implementation that beats most other algorithms.
  22  * Until someone tells me otherwise, I assume that this is the
  23  * fastest implementation of strstr() in C.
  24  * I deliberately chose not to comment it.  You should have at least
  25  * as much fun trying to understand it, as I had to write it :-).
  26  *
  27  * Stephen R. van den Berg, berg@pool.informatik.rwth-aachen.de */
  28
  29 #if HAVE_CONFIG_H
  30 # include <config.h>
  31 #endif
  32
  33 /* Specification.  */
  34 #include <string.h>
  35
  36 #include <ctype.h>
  37 #include <stdbool.h>
  38 #include <strings.h>
  39
  40 #define TOLOWER(Ch) (isupper (Ch) ? tolower (Ch) : (Ch))
  41
  42 /* Two-Way algorithm.  */
  43 #define RETURN_TYPE char *
  44 #define AVAILABLE(h, h_l, j, n_l)                       \
  45   (!memchr ((h) + (h_l), '\0', (j) + (n_l) - (h_l))     \
  46    && ((h_l) = (j) + (n_l)))
  47 #define CANON_ELEMENT(c) TOLOWER (c)
  48 #define CMP_FUNC(p1, p2, l)                             \
  49   __strncasecmp ((const char *) (p1), (const char *) (p2), l)
  50 #include "str-two-way.h"
  51
  52 #undef strcasestr
  53 #undef __strcasestr
  54
  55 #ifndef STRCASESTR
  56 #define STRCASESTR __strcasestr
  57 #endif
  58
  59
  60 /* Find the first occurrence of NEEDLE in HAYSTACK, using
  61    case-insensitive comparison.  This function gives unspecified
  62    results in multibyte locales.  */
  63 char *
  64 STRCASESTR (const char *haystack_start, const char *needle_start)
  65 {
  66   const char *haystack = haystack_start;
  67   const char *needle = needle_start;
  68   size_t needle_len; /* Length of NEEDLE.  */
  69   size_t haystack_len; /* Known minimum length of HAYSTACK.  */
  70   bool ok = true; /* True if NEEDLE is prefix of HAYSTACK.  */
  71
  72   /* Determine length of NEEDLE, and in the process, make sure
  73      HAYSTACK is at least as long (no point processing all of a long
  74      NEEDLE if HAYSTACK is too short).  */
  75   while (*haystack && *needle)
  76     {
  77       ok &= (TOLOWER ((unsigned char) *haystack)
  78              == TOLOWER ((unsigned char) *needle));
  79       haystack++;
  80       needle++;
  81     }
  82   if (*needle)
  83     return NULL;
  84   if (ok)
  85     return (char *) haystack_start;
  86   needle_len = needle - needle_start;
  87   haystack = haystack_start + 1;
  88   haystack_len = needle_len - 1;
  89
  90   /* Perform the search.  Abstract memory is considered to be an array
  91      of 'unsigned char' values, not an array of 'char' values.  See
  92      ISO C 99 section 6.2.6.1.  */
  93   if (needle_len < LONG_NEEDLE_THRESHOLD)
  94     return two_way_short_needle ((const unsigned char *) haystack,
  95                                  haystack_len,
  96                                  (const unsigned char *) needle_start,
  97                                  needle_len);
  98   return two_way_long_needle ((const unsigned char *) haystack, haystack_len,
  99                               (const unsigned char *) needle_start,
 100                               needle_len);
 101 }
 102
 103 #undef LONG_NEEDLE_THRESHOLD
 104
 105 #ifndef NO_ALIAS
 106 weak_alias (__strcasestr, strcasestr)
 107 #endif