1 /* gunicode.h - Unicode manipulation functions
3 * Copyright (C) 1999, 2000 Tom Tromey
4 * Copyright 2000, 2005 Red Hat, Inc.
6 * The Gnome Library is free software; you can redistribute it and/or
7 * modify it under the terms of the GNU Lesser General Public License as
8 * published by the Free Software Foundation; either version 2 of the
9 * License, or (at your option) any later version.
11 * The Gnome Library is distributed in the hope that it will be useful,
12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
14 * Lesser General Public License for more details.
16 * You should have received a copy of the GNU Lesser General Public
17 * License along with the Gnome Library; see the file COPYING.LIB. If not,
18 * write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
19 * Boston, MA 02111-1307, USA.
22 #ifndef __G_UNICODE_H__
23 #define __G_UNICODE_H__
25 #include <glib/gerror.h>
26 #include <glib/gtypes.h>
30 typedef guint32 gunichar;
31 typedef guint16 gunichar2;
33 /* These are the possible character classifications.
34 * See http://www.unicode.org/Public/UNIDATA/UCD.html#General_Category_Values
41 G_UNICODE_PRIVATE_USE,
43 G_UNICODE_LOWERCASE_LETTER,
44 G_UNICODE_MODIFIER_LETTER,
45 G_UNICODE_OTHER_LETTER,
46 G_UNICODE_TITLECASE_LETTER,
47 G_UNICODE_UPPERCASE_LETTER,
48 G_UNICODE_COMBINING_MARK,
49 G_UNICODE_ENCLOSING_MARK,
50 G_UNICODE_NON_SPACING_MARK,
51 G_UNICODE_DECIMAL_NUMBER,
52 G_UNICODE_LETTER_NUMBER,
53 G_UNICODE_OTHER_NUMBER,
54 G_UNICODE_CONNECT_PUNCTUATION,
55 G_UNICODE_DASH_PUNCTUATION,
56 G_UNICODE_CLOSE_PUNCTUATION,
57 G_UNICODE_FINAL_PUNCTUATION,
58 G_UNICODE_INITIAL_PUNCTUATION,
59 G_UNICODE_OTHER_PUNCTUATION,
60 G_UNICODE_OPEN_PUNCTUATION,
61 G_UNICODE_CURRENCY_SYMBOL,
62 G_UNICODE_MODIFIER_SYMBOL,
63 G_UNICODE_MATH_SYMBOL,
64 G_UNICODE_OTHER_SYMBOL,
65 G_UNICODE_LINE_SEPARATOR,
66 G_UNICODE_PARAGRAPH_SEPARATOR,
67 G_UNICODE_SPACE_SEPARATOR
70 /* These are the possible line break classifications.
71 * Note that new types may be added in the future.
72 * Implementations may regard unknown values like G_UNICODE_BREAK_UNKNOWN
73 * See http://www.unicode.org/unicode/reports/tr14/
77 G_UNICODE_BREAK_MANDATORY,
78 G_UNICODE_BREAK_CARRIAGE_RETURN,
79 G_UNICODE_BREAK_LINE_FEED,
80 G_UNICODE_BREAK_COMBINING_MARK,
81 G_UNICODE_BREAK_SURROGATE,
82 G_UNICODE_BREAK_ZERO_WIDTH_SPACE,
83 G_UNICODE_BREAK_INSEPARABLE,
84 G_UNICODE_BREAK_NON_BREAKING_GLUE,
85 G_UNICODE_BREAK_CONTINGENT,
86 G_UNICODE_BREAK_SPACE,
87 G_UNICODE_BREAK_AFTER,
88 G_UNICODE_BREAK_BEFORE,
89 G_UNICODE_BREAK_BEFORE_AND_AFTER,
90 G_UNICODE_BREAK_HYPHEN,
91 G_UNICODE_BREAK_NON_STARTER,
92 G_UNICODE_BREAK_OPEN_PUNCTUATION,
93 G_UNICODE_BREAK_CLOSE_PUNCTUATION,
94 G_UNICODE_BREAK_QUOTATION,
95 G_UNICODE_BREAK_EXCLAMATION,
96 G_UNICODE_BREAK_IDEOGRAPHIC,
97 G_UNICODE_BREAK_NUMERIC,
98 G_UNICODE_BREAK_INFIX_SEPARATOR,
99 G_UNICODE_BREAK_SYMBOL,
100 G_UNICODE_BREAK_ALPHABETIC,
101 G_UNICODE_BREAK_PREFIX,
102 G_UNICODE_BREAK_POSTFIX,
103 G_UNICODE_BREAK_COMPLEX_CONTEXT,
104 G_UNICODE_BREAK_AMBIGUOUS,
105 G_UNICODE_BREAK_UNKNOWN,
106 G_UNICODE_BREAK_NEXT_LINE,
107 G_UNICODE_BREAK_WORD_JOINER,
108 G_UNICODE_BREAK_HANGUL_L_JAMO,
109 G_UNICODE_BREAK_HANGUL_V_JAMO,
110 G_UNICODE_BREAK_HANGUL_T_JAMO,
111 G_UNICODE_BREAK_HANGUL_LV_SYLLABLE,
112 G_UNICODE_BREAK_HANGUL_LVT_SYLLABLE
115 /* Returns TRUE if current locale uses UTF-8 charset. If CHARSET is
116 * not null, sets *CHARSET to the name of the current locale's
117 * charset. This value is statically allocated, and should be copied
118 * in case the locale's charset will be changed later using setlocale()
119 * or in some other way.
121 gboolean g_get_charset (G_CONST_RETURN char **charset);
123 /* These are all analogs of the <ctype.h> functions.
125 gboolean g_unichar_isalnum (gunichar c) G_GNUC_CONST;
126 gboolean g_unichar_isalpha (gunichar c) G_GNUC_CONST;
127 gboolean g_unichar_iscntrl (gunichar c) G_GNUC_CONST;
128 gboolean g_unichar_isdigit (gunichar c) G_GNUC_CONST;
129 gboolean g_unichar_isgraph (gunichar c) G_GNUC_CONST;
130 gboolean g_unichar_islower (gunichar c) G_GNUC_CONST;
131 gboolean g_unichar_isprint (gunichar c) G_GNUC_CONST;
132 gboolean g_unichar_ispunct (gunichar c) G_GNUC_CONST;
133 gboolean g_unichar_isspace (gunichar c) G_GNUC_CONST;
134 gboolean g_unichar_isupper (gunichar c) G_GNUC_CONST;
135 gboolean g_unichar_isxdigit (gunichar c) G_GNUC_CONST;
136 gboolean g_unichar_istitle (gunichar c) G_GNUC_CONST;
137 gboolean g_unichar_isdefined (gunichar c) G_GNUC_CONST;
138 gboolean g_unichar_iswide (gunichar c) G_GNUC_CONST;
139 gboolean g_unichar_iswide_cjk(gunichar c) G_GNUC_CONST;
141 /* More <ctype.h> functions. These convert between the three cases.
142 * See the Unicode book to understand title case. */
143 gunichar g_unichar_toupper (gunichar c) G_GNUC_CONST;
144 gunichar g_unichar_tolower (gunichar c) G_GNUC_CONST;
145 gunichar g_unichar_totitle (gunichar c) G_GNUC_CONST;
147 /* If C is a digit (according to `g_unichar_isdigit'), then return its
148 numeric value. Otherwise return -1. */
149 gint g_unichar_digit_value (gunichar c) G_GNUC_CONST;
151 gint g_unichar_xdigit_value (gunichar c) G_GNUC_CONST;
153 /* Return the Unicode character type of a given character. */
154 GUnicodeType g_unichar_type (gunichar c) G_GNUC_CONST;
156 /* Return the line break property for a given character */
157 GUnicodeBreakType g_unichar_break_type (gunichar c) G_GNUC_CONST;
160 /* Compute canonical ordering of a string in-place. This rearranges
161 decomposed characters in the string according to their combining
162 classes. See the Unicode manual for more information. */
163 void g_unicode_canonical_ordering (gunichar *string,
166 /* Compute canonical decomposition of a character. Returns g_malloc()d
167 string of Unicode characters. RESULT_LEN is set to the resulting
168 length of the string. */
169 gunichar *g_unicode_canonical_decomposition (gunichar ch,
170 gsize *result_len) G_GNUC_MALLOC;
172 /* Array of skip-bytes-per-initial character.
174 GLIB_VAR const gchar * const g_utf8_skip;
176 #define g_utf8_next_char(p) (char *)((p) + g_utf8_skip[*(guchar *)(p)])
178 gunichar g_utf8_get_char (const gchar *p);
179 gunichar g_utf8_get_char_validated (const gchar *p,
182 gchar* g_utf8_offset_to_pointer (const gchar *str,
184 glong g_utf8_pointer_to_offset (const gchar *str,
186 gchar* g_utf8_prev_char (const gchar *p);
187 gchar* g_utf8_find_next_char (const gchar *p,
189 gchar* g_utf8_find_prev_char (const gchar *str,
192 glong g_utf8_strlen (const gchar *p,
195 /* Copies n characters from src to dest */
196 gchar* g_utf8_strncpy (gchar *dest,
200 /* Find the UTF-8 character corresponding to ch, in string p. These
201 functions are equivalants to strchr and strrchr */
202 gchar* g_utf8_strchr (const gchar *p,
205 gchar* g_utf8_strrchr (const gchar *p,
208 gchar* g_utf8_strreverse (const gchar *str,
211 gunichar2 *g_utf8_to_utf16 (const gchar *str,
214 glong *items_written,
215 GError **error) G_GNUC_MALLOC;
216 gunichar * g_utf8_to_ucs4 (const gchar *str,
219 glong *items_written,
220 GError **error) G_GNUC_MALLOC;
221 gunichar * g_utf8_to_ucs4_fast (const gchar *str,
223 glong *items_written) G_GNUC_MALLOC;
224 gunichar * g_utf16_to_ucs4 (const gunichar2 *str,
227 glong *items_written,
228 GError **error) G_GNUC_MALLOC;
229 gchar* g_utf16_to_utf8 (const gunichar2 *str,
232 glong *items_written,
233 GError **error) G_GNUC_MALLOC;
234 gunichar2 *g_ucs4_to_utf16 (const gunichar *str,
237 glong *items_written,
238 GError **error) G_GNUC_MALLOC;
239 gchar* g_ucs4_to_utf8 (const gunichar *str,
242 glong *items_written,
243 GError **error) G_GNUC_MALLOC;
245 /* Convert a single character into UTF-8. outbuf must have at
246 * least 6 bytes of space. Returns the number of bytes in the
249 gint g_unichar_to_utf8 (gunichar c,
252 /* Validate a UTF8 string, return TRUE if valid, put pointer to
253 * first invalid char in **end
256 gboolean g_utf8_validate (const gchar *str,
260 /* Validate a Unicode character */
261 gboolean g_unichar_validate (gunichar ch);
263 gchar *g_utf8_strup (const gchar *str,
264 gssize len) G_GNUC_MALLOC;
265 gchar *g_utf8_strdown (const gchar *str,
266 gssize len) G_GNUC_MALLOC;
267 gchar *g_utf8_casefold (const gchar *str,
268 gssize len) G_GNUC_MALLOC;
272 G_NORMALIZE_NFD = G_NORMALIZE_DEFAULT,
273 G_NORMALIZE_DEFAULT_COMPOSE,
274 G_NORMALIZE_NFC = G_NORMALIZE_DEFAULT_COMPOSE,
276 G_NORMALIZE_NFKD = G_NORMALIZE_ALL,
277 G_NORMALIZE_ALL_COMPOSE,
278 G_NORMALIZE_NFKC = G_NORMALIZE_ALL_COMPOSE
281 gchar *g_utf8_normalize (const gchar *str,
283 GNormalizeMode mode) G_GNUC_MALLOC;
285 gint g_utf8_collate (const gchar *str1,
287 gchar *g_utf8_collate_key (const gchar *str,
288 gssize len) G_GNUC_MALLOC;
289 gchar *g_utf8_collate_key_for_filename (const gchar *str,
290 gssize len) G_GNUC_MALLOC;
292 gboolean g_unichar_get_mirror_char (gunichar ch,
293 gunichar *mirrored_ch);
297 gchar *_g_utf8_make_valid (const gchar *name);
302 #endif /* __G_UNICODE_H__ */