Mercurial > hg > octave-kai > gnulib-hg
annotate lib/mbscasecmp.c @ 8091:ebf2b19b5684
New module 'mbscasecmp'. strcasecmp is not expected to work with multibyte
strings.
| author | Bruno Haible <bruno@clisp.org> |
|---|---|
| date | Mon, 05 Feb 2007 01:57:07 +0000 |
| parents | 6a02aa86f4b4 |
| children | bbbbbf4cd1c5 |
| rev | line source |
|---|---|
| 8089 | 1 /* Case-insensitive string comparison function. |
| 2 Copyright (C) 1998-1999, 2005-2007 Free Software Foundation, Inc. | |
| 3 Written by Bruno Haible <bruno@clisp.org>, 2005, | |
| 4 based on earlier glibc code. | |
| 5 | |
| 6 This program is free software; you can redistribute it and/or modify | |
| 7 it under the terms of the GNU General Public License as published by | |
| 8 the Free Software Foundation; either version 2, or (at your option) | |
| 9 any later version. | |
| 10 | |
| 11 This program 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 | |
| 14 GNU General Public License for more details. | |
| 15 | |
| 16 You should have received a copy of the GNU General Public License | |
| 17 along with this program; if not, write to the Free Software Foundation, | |
| 18 Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */ | |
| 19 | |
| 20 #include <config.h> | |
| 21 | |
| 22 /* Specification. */ | |
| 23 #include <string.h> | |
| 24 | |
| 25 #include <ctype.h> | |
| 26 #include <limits.h> | |
| 27 | |
| 28 #if HAVE_MBRTOWC | |
| 29 # include "mbuiter.h" | |
| 30 #endif | |
| 31 | |
| 32 #define TOLOWER(Ch) (isupper (Ch) ? tolower (Ch) : (Ch)) | |
| 33 | |
|
8091
ebf2b19b5684
New module 'mbscasecmp'. strcasecmp is not expected to work with multibyte
Bruno Haible <bruno@clisp.org>
parents:
8089
diff
changeset
|
34 /* Compare the character strings S1 and S2, ignoring case, returning less than, |
|
ebf2b19b5684
New module 'mbscasecmp'. strcasecmp is not expected to work with multibyte
Bruno Haible <bruno@clisp.org>
parents:
8089
diff
changeset
|
35 equal to or greater than zero if S1 is lexicographically less than, equal to |
|
ebf2b19b5684
New module 'mbscasecmp'. strcasecmp is not expected to work with multibyte
Bruno Haible <bruno@clisp.org>
parents:
8089
diff
changeset
|
36 or greater than S2. |
| 8089 | 37 Note: This function may, in multibyte locales, return 0 for strings of |
| 38 different lengths! */ | |
| 39 int | |
|
8091
ebf2b19b5684
New module 'mbscasecmp'. strcasecmp is not expected to work with multibyte
Bruno Haible <bruno@clisp.org>
parents:
8089
diff
changeset
|
40 mbscasecmp (const char *s1, const char *s2) |
| 8089 | 41 { |
| 42 if (s1 == s2) | |
| 43 return 0; | |
| 44 | |
| 45 /* Be careful not to look at the entire extent of s1 or s2 until needed. | |
| 46 This is useful because when two strings differ, the difference is | |
| 47 most often already in the very few first characters. */ | |
| 48 #if HAVE_MBRTOWC | |
| 49 if (MB_CUR_MAX > 1) | |
| 50 { | |
| 51 mbui_iterator_t iter1; | |
| 52 mbui_iterator_t iter2; | |
| 53 | |
| 54 mbui_init (iter1, s1); | |
| 55 mbui_init (iter2, s2); | |
| 56 | |
| 57 while (mbui_avail (iter1) && mbui_avail (iter2)) | |
| 58 { | |
| 59 int cmp = mb_casecmp (mbui_cur (iter1), mbui_cur (iter2)); | |
| 60 | |
| 61 if (cmp != 0) | |
| 62 return cmp; | |
| 63 | |
| 64 mbui_advance (iter1); | |
| 65 mbui_advance (iter2); | |
| 66 } | |
| 67 if (mbui_avail (iter1)) | |
| 68 /* s2 terminated before s1. */ | |
| 69 return 1; | |
| 70 if (mbui_avail (iter2)) | |
| 71 /* s1 terminated before s2. */ | |
| 72 return -1; | |
| 73 return 0; | |
| 74 } | |
| 75 else | |
| 76 #endif | |
| 77 { | |
| 78 const unsigned char *p1 = (const unsigned char *) s1; | |
| 79 const unsigned char *p2 = (const unsigned char *) s2; | |
| 80 unsigned char c1, c2; | |
| 81 | |
| 82 do | |
| 83 { | |
| 84 c1 = TOLOWER (*p1); | |
| 85 c2 = TOLOWER (*p2); | |
| 86 | |
| 87 if (c1 == '\0') | |
| 88 break; | |
| 89 | |
| 90 ++p1; | |
| 91 ++p2; | |
| 92 } | |
| 93 while (c1 == c2); | |
| 94 | |
| 95 if (UCHAR_MAX <= INT_MAX) | |
| 96 return c1 - c2; | |
| 97 else | |
| 98 /* On machines where 'char' and 'int' are types of the same size, the | |
| 99 difference of two 'unsigned char' values - including the sign bit - | |
| 100 doesn't fit in an 'int'. */ | |
| 101 return (c1 > c2 ? 1 : c1 < c2 ? -1 : 0); | |
| 102 } | |
| 103 } |