2 * This file is part of DisOrder
3 * Copyright (C) 2004, 2007 Richard Kettlewell
5 * This program is free software; you can redistribute it and/or modify
6 * it under the terms of the GNU General Public License as published by
7 * the Free Software Foundation; either version 2 of the License, or
8 * (at your option) any later version.
10 * This program is distributed in the hope that it will be useful, but
11 * WITHOUT ANY WARRANTY; without even the implied warranty of
12 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
13 * General Public License for more details.
15 * You should have received a copy of the GNU General Public License
16 * along with this program; if not, write to the Free Software
17 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
38 const char *casefold(const char *ptr
) {
39 return utf8_casefold_canon(ptr
, strlen(ptr
), 0);
42 static enum unicode_gc_cat
cat(uint32_t c
) {
43 if(c
< UNICODE_NCHARS
) {
44 /* If this a known character, convert it to lower case */
45 const struct unidata
*const ud
= &unidata
[c
/ UNICODE_MODULUS
][c
% UNICODE_MODULUS
];
51 /* XXX this is a bit kludgy */
53 char **words(const char *s
, int *nvecp
) {
63 PARSE_UTF8(s
, c
, return 0);
64 /* special cases first */
75 /* do the rest on category */
89 /* letters, digits and symbols are considered to be part of
95 dynstr_append_bytes(&d
, start
, s
- start
);
109 dynstr_terminate(&d
);
110 vector_append(&v
, d
.vec
);
124 /* control and punctuation is completely ignored */
130 /* pick up the final word */
131 dynstr_terminate(&d
);
132 vector_append(&v
, d
.vec
);
134 vector_terminate(&v
);