2 * This file is part of DisOrde
3 * Copyright (C) 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
20 /** @file lib/unicode.h
21 * @brief Unicode support functions
27 /** @brief Smart pointer into a string
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
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.
37 typedef struct utf32_iterator_data *utf32_iterator;
39 /** @brief Property tailor function
41 * @return Tailored property or -1 to use standard value
43 * See also utf32_iterator_tailor_word_break().
45 typedef int unicode_property_tailor(uint32_t c);
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);
49 int utf8_valid(const char *s, size_t ns);
51 int utf32_combining_class(uint32_t c);
53 size_t utf32_len(const uint32_t *s);
54 int utf32_cmp(const uint32_t *a, const uint32_t *b);
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);
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);
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);
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);
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);
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);
74 int utf32_is_grapheme_boundary(const uint32_t *s, size_t ns, size_t n);
75 int utf32_is_word_boundary(const uint32_t *s, size_t ns, size_t n);
77 utf32_iterator utf32_iterator_new(const uint32_t *s, size_t ns);
78 void utf32_iterator_destroy(utf32_iterator it);
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);
86 void utf32_iterator_tailor_word_break(utf32_iterator it,
87 unicode_property_tailor *pt);
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);
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
98 * See utf32_to_utf8() for possible causes of errors.
100 static inline char *utf32nt_to_utf8(const uint32_t *s) {
101 return utf32_to_utf8(s, utf32_len(s), 0);
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
108 * See utf8_to_utf32() for possible causes of errors.
110 static inline uint32_t *utf8nt_to_utf32(const char *s) {
111 return utf8_to_utf32(s, strlen(s), 0);
114 #endif /* UNICODE_H */