string/strcasestr.c

   1 /* Return the offset of one string within another.
   2    Copyright (C) 1994-2023 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    <https://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   (((j) + (n_l) <= (h_l)) \
  41    || ((h_l) += __strnlen ((void*)((h) + (h_l)), (n_l) + 512), \
  42        (j) + (n_l) <= (h_l)))
  43 #define CHECK_EOL (1)
  44 #define RET0_IF_0(a) if (!a) goto ret0
  45 #define CANON_ELEMENT(c) TOLOWER (c)
  46 #define CMP_FUNC(p1, p2, l)                             \
  47   __strncasecmp ((const char *) (p1), (const char *) (p2), l)
  48 #include "str-two-way.h"
  49
  50 #undef strcasestr
  51 #undef __strcasestr
  52
  53 #ifndef STRCASESTR
  54 #define STRCASESTR __strcasestr
  55 #endif
  56
  57
  58 /* Find the first occurrence of NEEDLE in HAYSTACK, using
  59    case-insensitive comparison.  This function gives unspecified
  60    results in multibyte locales.  */
  61 char *
  62 STRCASESTR (const char *haystack, const char *needle)
  63 {
  64   size_t needle_len; /* Length of NEEDLE.  */
  65   size_t haystack_len; /* Known minimum length of HAYSTACK.  */
  66
  67   /* Handle empty NEEDLE special case.  */
  68   if (needle[0] == '\0')
  69     return (char *) haystack;
  70
  71   /* Ensure HAYSTACK length is at least as long as NEEDLE length.
  72      Since a match may occur early on in a huge HAYSTACK, use strnlen
  73      and read ahead a few cachelines for improved performance.  */
  74   needle_len = strlen (needle);
  75   haystack_len = __strnlen (haystack, needle_len + 256);
  76   if (haystack_len < needle_len)
  77     return NULL;
  78
  79   /* Perform the search.  Abstract memory is considered to be an array
  80      of 'unsigned char' values, not an array of 'char' values.  See
  81      ISO C 99 section 6.2.6.1.  */
  82   if (needle_len < LONG_NEEDLE_THRESHOLD)
  83     return two_way_short_needle ((const unsigned char *) haystack,
  84                                  haystack_len,
  85                                  (const unsigned char *) needle,
  86                                  needle_len);
  87   return two_way_long_needle ((const unsigned char *) haystack, haystack_len,
  88                               (const unsigned char *) needle,
  89                               needle_len);
  90 }
  91
  92 #undef LONG_NEEDLE_THRESHOLD
  93
  94 #ifndef NO_ALIAS
  95 weak_alias (__strcasestr, strcasestr)
  96 #endif