string/strcasestr.c

   1 /* Return the offset of one string within another.
   2    Copyright (C) 1994, 1996-2000, 2004, 2008 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, write to the Free
  17    Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
  18    02111-1307 USA.  */
  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 /* Find the first occurrence of NEEDLE in HAYSTACK, using
  56    case-insensitive comparison.  This function gives unspecified
  57    results in multibyte locales.  */
  58 char *
  59 __strcasestr (const char *haystack_start, const char *needle_start)
  60 {
  61   const char *haystack = haystack_start;
  62   const char *needle = needle_start;
  63   size_t needle_len; /* Length of NEEDLE.  */
  64   size_t haystack_len; /* Known minimum length of HAYSTACK.  */
  65   bool ok = true; /* True if NEEDLE is prefix of HAYSTACK.  */
  66
  67   /* Determine length of NEEDLE, and in the process, make sure
  68      HAYSTACK is at least as long (no point processing all of a long
  69      NEEDLE if HAYSTACK is too short).  */
  70   while (*haystack && *needle)
  71     {
  72       ok &= (TOLOWER ((unsigned char) *haystack)
  73              == TOLOWER ((unsigned char) *needle));
  74       haystack++;
  75       needle++;
  76     }
  77   if (*needle)
  78     return NULL;
  79   if (ok)
  80     return (char *) haystack_start;
  81   needle_len = needle - needle_start;
  82   haystack = haystack_start + 1;
  83   haystack_len = needle_len - 1;
  84
  85   /* Perform the search.  Abstract memory is considered to be an array
  86      of 'unsigned char' values, not an array of 'char' values.  See
  87      ISO C 99 section 6.2.6.1.  */
  88   if (needle_len < LONG_NEEDLE_THRESHOLD)
  89     return two_way_short_needle ((const unsigned char *) haystack,
  90                                  haystack_len,
  91                                  (const unsigned char *) needle_start,
  92                                  needle_len);
  93   return two_way_long_needle ((const unsigned char *) haystack, haystack_len,
  94                               (const unsigned char *) needle_start,
  95                               needle_len);
  96 }
  97
  98 #undef LONG_NEEDLE_THRESHOLD
  99
 100 weak_alias (__strcasestr, strcasestr)