Commit | Line | Data |
---|---|---|
e5a5a138 RK |
1 | /* |
2 | * This file is part of DisOrde | |
3 | * Copyright (C) 2007 Richard Kettlewell | |
4 | * | |
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. | |
9 | * | |
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. | |
14 | * | |
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 | |
18 | * USA | |
19 | */ | |
20 | /** @file lib/unicode.h | |
21 | * @brief Unicode support functions | |
22 | */ | |
23 | ||
24 | #ifndef UNICODE_H | |
25 | #define UNICODE_H | |
26 | ||
092f426f RK |
27 | /** @brief Smart pointer into a string |
28 | * | |
29 | * Iterators can be efficiently moved either forwards or back to the start of | |
30 | * the string. They cannot (currently) efficiently be moved backwards. Their | |
31 | * advantage is that they remember internal state to speed up boundary | |
32 | * detection. | |
33 | * | |
34 | * Iterators can point to any code point of the string, or to a hypothetical | |
35 | * post-final code point of value 0, but not outside the string. | |
36 | */ | |
37 | typedef struct utf32_iterator_data *utf32_iterator; | |
38 | ||
c85b7022 RK |
39 | /** @brief Property tailor function |
40 | * @param c Code point | |
41 | * @return Tailored property or -1 to use standard value | |
42 | * | |
43 | * See also utf32_iterator_tailor_word_break(). | |
44 | */ | |
45 | typedef int unicode_property_tailor(uint32_t c); | |
46 | ||
e5a5a138 RK |
47 | char *utf32_to_utf8(const uint32_t *s, size_t ns, size_t *nd); |
48 | uint32_t *utf8_to_utf32(const char *s, size_t ns, size_t *nd); | |
18cda350 | 49 | int utf8_valid(const char *s, size_t ns); |
e5a5a138 | 50 | |
3c82b504 RK |
51 | int utf32_combining_class(uint32_t c); |
52 | ||
e5a5a138 RK |
53 | size_t utf32_len(const uint32_t *s); |
54 | int utf32_cmp(const uint32_t *a, const uint32_t *b); | |
55 | ||
56 | uint32_t *utf32_decompose_canon(const uint32_t *s, size_t ns, size_t *ndp); | |
57 | char *utf8_decompose_canon(const char *s, size_t ns, size_t *ndp); | |
58 | ||
59 | uint32_t *utf32_decompose_compat(const uint32_t *s, size_t ns, size_t *ndp); | |
60 | char *utf8_decompose_compat(const char *s, size_t ns, size_t *ndp); | |
61 | ||
16506c9d RK |
62 | uint32_t *utf32_compose_canon(const uint32_t *s, size_t ns, size_t *ndp); |
63 | char *utf8_compose_canon(const char *s, size_t ns, size_t *ndp); | |
64 | ||
65 | uint32_t *utf32_compose_compat(const uint32_t *s, size_t ns, size_t *ndp); | |
66 | char *utf8_compose_compat(const char *s, size_t ns, size_t *ndp); | |
67 | ||
e5a5a138 RK |
68 | uint32_t *utf32_casefold_canon(const uint32_t *s, size_t ns, size_t *ndp); |
69 | char *utf8_casefold_canon(const char *s, size_t ns, size_t *ndp); | |
70 | ||
71 | uint32_t *utf32_casefold_compat(const uint32_t *s, size_t ns, size_t *ndp); | |
72 | char *utf8_casefold_compat(const char *s, size_t ns, size_t *ndp); | |
73 | ||
1625e11a | 74 | int utf32_is_grapheme_boundary(const uint32_t *s, size_t ns, size_t n); |
0b7052da | 75 | int utf32_is_word_boundary(const uint32_t *s, size_t ns, size_t n); |
e5a5a138 | 76 | |
092f426f RK |
77 | utf32_iterator utf32_iterator_new(const uint32_t *s, size_t ns); |
78 | void utf32_iterator_destroy(utf32_iterator it); | |
79 | ||
80 | size_t utf32_iterator_where(utf32_iterator it); | |
81 | int utf32_iterator_set(utf32_iterator it, size_t n); | |
82 | int utf32_iterator_advance(utf32_iterator it, size_t n); | |
83 | uint32_t utf32_iterator_code(utf32_iterator it); | |
84 | int utf32_iterator_grapheme_boundary(utf32_iterator it); | |
85 | int utf32_iterator_word_boundary(utf32_iterator it); | |
c85b7022 RK |
86 | void utf32_iterator_tailor_word_break(utf32_iterator it, |
87 | unicode_property_tailor *pt); | |
092f426f | 88 | |
c85b7022 RK |
89 | uint32_t **utf32_word_split(const uint32_t *s, size_t ns, size_t *nwp, |
90 | unicode_property_tailor *wbreak); | |
91 | char **utf8_word_split(const char *s, size_t ns, size_t *nwp, | |
92 | unicode_property_tailor *wbreak); | |
8818b7fc | 93 | |
caecd4f4 RK |
94 | /** @brief Convert 0-terminated UTF-32 to UTF-8 |
95 | * @param s 0-terminated UTF-32 string | |
96 | * @return 0-terminated UTF-8 string or 0 on error | |
97 | * | |
98 | * See utf32_to_utf8() for possible causes of errors. | |
99 | */ | |
100 | static inline char *utf32nt_to_utf8(const uint32_t *s) { | |
101 | return utf32_to_utf8(s, utf32_len(s), 0); | |
102 | } | |
103 | ||
104 | /** @brief Convert 0-terminated UTF-8 to UTF-32 | |
105 | * @param s 0-terminated UTF-8 string | |
106 | * @return 0-terminated UTF-32 string or 0 on error | |
107 | * | |
108 | * See utf8_to_utf32() for possible causes of errors. | |
109 | */ | |
110 | static inline uint32_t *utf8nt_to_utf32(const char *s) { | |
111 | return utf8_to_utf32(s, strlen(s), 0); | |
112 | } | |
113 | ||
e5a5a138 RK |
114 | #endif /* UNICODE_H */ |
115 | ||
116 | /* | |
117 | Local Variables: | |
118 | c-basic-offset:2 | |
119 | comment-column:40 | |
120 | fill-column:79 | |
121 | indent-tabs-mode:nil | |
122 | End: | |
123 | */ |