| 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 3 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, |
| 11 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 12 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 13 | * GNU 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, see <http://www.gnu.org/licenses/>. |
| 17 | */ |
| 18 | /** @file lib/unicode.h |
| 19 | * @brief Unicode support functions |
| 20 | */ |
| 21 | |
| 22 | #ifndef UNICODE_H |
| 23 | #define UNICODE_H |
| 24 | |
| 25 | /** @brief Smart pointer into a string |
| 26 | * |
| 27 | * Iterators can be efficiently moved either forwards or back to the start of |
| 28 | * the string. They cannot (currently) efficiently be moved backwards. Their |
| 29 | * advantage is that they remember internal state to speed up boundary |
| 30 | * detection. |
| 31 | * |
| 32 | * Iterators can point to any code point of the string, or to a hypothetical |
| 33 | * post-final code point of value 0, but not outside the string. |
| 34 | */ |
| 35 | typedef struct utf32_iterator_data *utf32_iterator; |
| 36 | |
| 37 | /** @brief Property tailor function |
| 38 | * @param c Code point |
| 39 | * @return Tailored property or -1 to use standard value |
| 40 | * |
| 41 | * See also utf32_iterator_tailor_word_break(). |
| 42 | */ |
| 43 | typedef int unicode_property_tailor(uint32_t c); |
| 44 | |
| 45 | char *utf32_to_utf8(const uint32_t *s, size_t ns, size_t *nd); |
| 46 | uint32_t *utf8_to_utf32(const char *s, size_t ns, size_t *nd); |
| 47 | int utf8_valid(const char *s, size_t ns); |
| 48 | |
| 49 | int utf32_combining_class(uint32_t c); |
| 50 | |
| 51 | size_t utf32_len(const uint32_t *s); |
| 52 | int utf32_cmp(const uint32_t *a, const uint32_t *b); |
| 53 | |
| 54 | uint32_t *utf32_decompose_canon(const uint32_t *s, size_t ns, size_t *ndp); |
| 55 | char *utf8_decompose_canon(const char *s, size_t ns, size_t *ndp); |
| 56 | |
| 57 | uint32_t *utf32_decompose_compat(const uint32_t *s, size_t ns, size_t *ndp); |
| 58 | char *utf8_decompose_compat(const char *s, size_t ns, size_t *ndp); |
| 59 | |
| 60 | uint32_t *utf32_compose_canon(const uint32_t *s, size_t ns, size_t *ndp); |
| 61 | char *utf8_compose_canon(const char *s, size_t ns, size_t *ndp); |
| 62 | |
| 63 | uint32_t *utf32_compose_compat(const uint32_t *s, size_t ns, size_t *ndp); |
| 64 | char *utf8_compose_compat(const char *s, size_t ns, size_t *ndp); |
| 65 | |
| 66 | uint32_t *utf32_casefold_canon(const uint32_t *s, size_t ns, size_t *ndp); |
| 67 | char *utf8_casefold_canon(const char *s, size_t ns, size_t *ndp); |
| 68 | |
| 69 | uint32_t *utf32_casefold_compat(const uint32_t *s, size_t ns, size_t *ndp); |
| 70 | char *utf8_casefold_compat(const char *s, size_t ns, size_t *ndp); |
| 71 | |
| 72 | int utf32_is_grapheme_boundary(const uint32_t *s, size_t ns, size_t n); |
| 73 | int utf32_is_word_boundary(const uint32_t *s, size_t ns, size_t n); |
| 74 | |
| 75 | utf32_iterator utf32_iterator_new(const uint32_t *s, size_t ns); |
| 76 | void utf32_iterator_destroy(utf32_iterator it); |
| 77 | |
| 78 | size_t utf32_iterator_where(utf32_iterator it); |
| 79 | int utf32_iterator_set(utf32_iterator it, size_t n); |
| 80 | int utf32_iterator_advance(utf32_iterator it, size_t n); |
| 81 | uint32_t utf32_iterator_code(utf32_iterator it); |
| 82 | int utf32_iterator_grapheme_boundary(utf32_iterator it); |
| 83 | int utf32_iterator_word_boundary(utf32_iterator it); |
| 84 | void utf32_iterator_tailor_word_break(utf32_iterator it, |
| 85 | unicode_property_tailor *pt); |
| 86 | |
| 87 | uint32_t **utf32_word_split(const uint32_t *s, size_t ns, size_t *nwp, |
| 88 | unicode_property_tailor *wbreak); |
| 89 | char **utf8_word_split(const char *s, size_t ns, size_t *nwp, |
| 90 | unicode_property_tailor *wbreak); |
| 91 | |
| 92 | /** @brief Convert 0-terminated UTF-32 to UTF-8 |
| 93 | * @param s 0-terminated UTF-32 string |
| 94 | * @return 0-terminated UTF-8 string or 0 on error |
| 95 | * |
| 96 | * See utf32_to_utf8() for possible causes of errors. |
| 97 | */ |
| 98 | static inline char *utf32nt_to_utf8(const uint32_t *s) { |
| 99 | return utf32_to_utf8(s, utf32_len(s), 0); |
| 100 | } |
| 101 | |
| 102 | /** @brief Convert 0-terminated UTF-8 to UTF-32 |
| 103 | * @param s 0-terminated UTF-8 string |
| 104 | * @return 0-terminated UTF-32 string or 0 on error |
| 105 | * |
| 106 | * See utf8_to_utf32() for possible causes of errors. |
| 107 | */ |
| 108 | static inline uint32_t *utf8nt_to_utf32(const char *s) { |
| 109 | return utf8_to_utf32(s, strlen(s), 0); |
| 110 | } |
| 111 | |
| 112 | #endif /* UNICODE_H */ |
| 113 | |
| 114 | /* |
| 115 | Local Variables: |
| 116 | c-basic-offset:2 |
| 117 | comment-column:40 |
| 118 | fill-column:79 |
| 119 | indent-tabs-mode:nil |
| 120 | End: |
| 121 | */ |