string/strcasestr.c

   1 /* Return the offset of one string within another.
   2    Copyright (C) 1994, 1996-2000, 2004, 2008, 2009
   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, write to the Free
  18    Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
  19    02111-1307 USA.  */
  20
  21 /*
  22  * My personal strstr() implementation that beats most other algorithms.
  23  * Until someone tells me otherwise, I assume that this is the
  24  * fastest implementation of strstr() in C.
  25  * I deliberately chose not to comment it.  You should have at least
  26  * as much fun trying to understand it, as I had to write it :-).
  27  *
  28  * Stephen R. van den Berg, berg@pool.informatik.rwth-aachen.de */
  29
  30 #if HAVE_CONFIG_H
  31 # include <config.h>
  32 #endif
  33
  34 /* Specification.  */
  35 #include <string.h>
  36
  37 #include <ctype.h>
  38 #include <stdbool.h>
  39 #include <strings.h>
  40
  41 #define TOLOWER(Ch) (isupper (Ch) ? tolower (Ch) : (Ch))
  42
  43 /* Two-Way algorithm.  */
  44 #define RETURN_TYPE char *
  45 #define AVAILABLE(h, h_l, j, n_l)                       \
  46   (!memchr ((h) + (h_l), '\0', (j) + (n_l) - (h_l))     \
  47    && ((h_l) = (j) + (n_l)))
  48 #define CANON_ELEMENT(c) TOLOWER (c)
  49 #define CMP_FUNC(p1, p2, l)                             \
  50   __strncasecmp ((const char *) (p1), (const char *) (p2), l)
  51 #include "str-two-way.h"
  52
  53 #undef strcasestr
  54 #undef __strcasestr
  55
  56 #ifndef STRCASESTR
  57 #define STRCASESTR __strcasestr
  58 #endif
  59
  60
  61 /* Find the first occurrence of NEEDLE in HAYSTACK, using
  62    case-insensitive comparison.  This function gives unspecified
  63    results in multibyte locales.  */
  64 char *
  65 STRCASESTR (const char *haystack_start, const char *needle_start)
  66 {
  67   const char *haystack = haystack_start;
  68   const char *needle = needle_start;
  69   size_t needle_len; /* Length of NEEDLE.  */
  70   size_t haystack_len; /* Known minimum length of HAYSTACK.  */
  71   bool ok = true; /* True if NEEDLE is prefix of HAYSTACK.  */
  72
  73   /* Determine length of NEEDLE, and in the process, make sure
  74      HAYSTACK is at least as long (no point processing all of a long
  75      NEEDLE if HAYSTACK is too short).  */
  76   while (*haystack && *needle)
  77     {
  78       ok &= (TOLOWER ((unsigned char) *haystack)
  79              == TOLOWER ((unsigned char) *needle));
  80       haystack++;
  81       needle++;
  82     }
  83   if (*needle)
  84     return NULL;
  85   if (ok)
  86     return (char *) haystack_start;
  87   needle_len = needle - needle_start;
  88   haystack = haystack_start + 1;
  89   haystack_len = needle_len - 1;
  90
  91   /* Perform the search.  Abstract memory is considered to be an array
  92      of 'unsigned char' values, not an array of 'char' values.  See
  93      ISO C 99 section 6.2.6.1.  */
  94   if (needle_len < LONG_NEEDLE_THRESHOLD)
  95     return two_way_short_needle ((const unsigned char *) haystack,
  96                                  haystack_len,
  97                                  (const unsigned char *) needle_start,
  98                                  needle_len);
  99   return two_way_long_needle ((const unsigned char *) haystack, haystack_len,
 100                               (const unsigned char *) needle_start,
 101                               needle_len);
 102 }
 103
 104 #undef LONG_NEEDLE_THRESHOLD
 105
 106 weak_alias (__strcasestr, strcasestr)