string/strcasestr.c

   1 /* Return the offset of one string within another.
   2    Copyright (C) 1994-2017 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 /* Specification.  */
  29 #include <string.h>
  30
  31 #include <ctype.h>
  32 #include <stdbool.h>
  33 #include <strings.h>
  34
  35 #define TOLOWER(Ch) tolower (Ch)
  36
  37 /* Two-Way algorithm.  */
  38 #define RETURN_TYPE char *
  39 #define AVAILABLE(h, h_l, j, n_l)                       \
  40   (!memchr ((h) + (h_l), '\0', (j) + (n_l) - (h_l))     \
  41    && ((h_l) = (j) + (n_l)))
  42 #define CHECK_EOL (1)
  43 #define RET0_IF_0(a) if (!a) goto ret0
  44 #define CANON_ELEMENT(c) TOLOWER (c)
  45 #define CMP_FUNC(p1, p2, l)                             \
  46   __strncasecmp ((const char *) (p1), (const char *) (p2), l)
  47 #include "str-two-way.h"
  48
  49 #undef strcasestr
  50 #undef __strcasestr
  51
  52 #ifndef STRCASESTR
  53 #define STRCASESTR __strcasestr
  54 #endif
  55
  56
  57 /* Find the first occurrence of NEEDLE in HAYSTACK, using
  58    case-insensitive comparison.  This function gives unspecified
  59    results in multibyte locales.  */
  60 char *
  61 STRCASESTR (const char *haystack_start, const char *needle_start)
  62 {
  63   const char *haystack = haystack_start;
  64   const char *needle = needle_start;
  65   size_t needle_len; /* Length of NEEDLE.  */
  66   size_t haystack_len; /* Known minimum length of HAYSTACK.  */
  67   bool ok = true; /* True if NEEDLE is prefix of HAYSTACK.  */
  68
  69   /* Determine length of NEEDLE, and in the process, make sure
  70      HAYSTACK is at least as long (no point processing all of a long
  71      NEEDLE if HAYSTACK is too short).  */
  72   while (*haystack && *needle)
  73     {
  74       ok &= (TOLOWER ((unsigned char) *haystack)
  75              == TOLOWER ((unsigned char) *needle));
  76       haystack++;
  77       needle++;
  78     }
  79   if (*needle)
  80     return NULL;
  81   if (ok)
  82     return (char *) haystack_start;
  83   needle_len = needle - needle_start;
  84   haystack = haystack_start + 1;
  85   haystack_len = needle_len - 1;
  86
  87   /* Perform the search.  Abstract memory is considered to be an array
  88      of 'unsigned char' values, not an array of 'char' values.  See
  89      ISO C 99 section 6.2.6.1.  */
  90   if (needle_len < LONG_NEEDLE_THRESHOLD)
  91     return two_way_short_needle ((const unsigned char *) haystack,
  92                                  haystack_len,
  93                                  (const unsigned char *) needle_start,
  94                                  needle_len);
  95   return two_way_long_needle ((const unsigned char *) haystack, haystack_len,
  96                               (const unsigned char *) needle_start,
  97                               needle_len);
  98 }
  99
 100 #undef LONG_NEEDLE_THRESHOLD
 101
 102 #ifndef NO_ALIAS
 103 weak_alias (__strcasestr, strcasestr)
 104 #endif