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_General_Category cat(uint32_t c) {
43 if(c < UNICODE_NCHARS) {
44 const struct unidata *const ud = &unidata[c / UNICODE_MODULUS][c % UNICODE_MODULUS];
45 return ud->general_category;
47 return unicode_General_Category_Cn;
50 /* XXX this is a bit kludgy */
52 char **words(const char *s, int *nvecp) {
62 PARSE_UTF8(s, c, return 0);
63 /* special cases first */
74 /* do the rest on category */
76 case unicode_General_Category_Ll:
77 case unicode_General_Category_Lm:
78 case unicode_General_Category_Lo:
79 case unicode_General_Category_Lt:
80 case unicode_General_Category_Lu:
81 case unicode_General_Category_Nd:
82 case unicode_General_Category_Nl:
83 case unicode_General_Category_No:
84 case unicode_General_Category_Sc:
85 case unicode_General_Category_Sk:
86 case unicode_General_Category_Sm:
87 case unicode_General_Category_So:
88 /* letters, digits and symbols are considered to be part of
94 dynstr_append_bytes(&d, start, s - start);
97 case unicode_General_Category_Cc:
98 case unicode_General_Category_Cf:
99 case unicode_General_Category_Co:
100 case unicode_General_Category_Cs:
101 case unicode_General_Category_Zl:
102 case unicode_General_Category_Zp:
103 case unicode_General_Category_Zs:
104 case unicode_General_Category_Pe:
105 case unicode_General_Category_Ps:
108 dynstr_terminate(&d);
109 vector_append(&v, d.vec);
114 case unicode_General_Category_Mc:
115 case unicode_General_Category_Me:
116 case unicode_General_Category_Mn:
117 case unicode_General_Category_Pc:
118 case unicode_General_Category_Pd:
119 case unicode_General_Category_Pf:
120 case unicode_General_Category_Pi:
121 case unicode_General_Category_Po:
122 case unicode_General_Category_Cn:
123 /* control and punctuation is completely ignored */
129 /* pick up the final word */
130 dynstr_terminate(&d);
131 vector_append(&v, d.vec);
133 vector_terminate(&v);