1/* gunicode.h - Unicode manipulation functions
2 *
3 * Copyright (C) 1999, 2000 Tom Tromey
4 * Copyright 2000, 2005 Red Hat, Inc.
5 *
6 * SPDX-License-Identifier: LGPL-2.1-or-later
7 *
8 * This library is free software; you can redistribute it and/or
9 * modify it under the terms of the GNU Lesser General Public
10 * License as published by the Free Software Foundation; either
11 * version 2.1 of the License, or (at your option) any later version.
12 *
13 * This library is distributed in the hope that it will be useful,
14 * but WITHOUT ANY WARRANTY; without even the implied warranty of
15 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
16 * Lesser General Public License for more details.
17 *
18 * You should have received a copy of the GNU Lesser General Public License
19 * along with this library; if not, see <http://www.gnu.org/licenses/>.
20 */
21
22#ifndef __G_UNICODE_H__
23#define __G_UNICODE_H__
24
25#if !defined (__GLIB_H_INSIDE__) && !defined (GLIB_COMPILATION)
26#error "Only <glib.h> can be included directly."
27#endif
28
29#include <glib/gerror.h>
30#include <glib/gtypes.h>
31
32G_BEGIN_DECLS
33
34/**
35 * gunichar:
36 *
37 * A type which can hold any UTF-32 or UCS-4 character code,
38 * also known as a Unicode code point.
39 *
40 * If you want to produce the UTF-8 representation of a #gunichar,
41 * use g_ucs4_to_utf8(). See also g_utf8_to_ucs4() for the reverse
42 * process.
43 *
44 * To print/scan values of this type as integer, use
45 * %G_GINT32_MODIFIER and/or %G_GUINT32_FORMAT.
46 *
47 * The notation to express a Unicode code point in running text is
48 * as a hexadecimal number with four to six digits and uppercase
49 * letters, prefixed by the string "U+". Leading zeros are omitted,
50 * unless the code point would have fewer than four hexadecimal digits.
51 * For example, "U+0041 LATIN CAPITAL LETTER A". To print a code point
52 * in the U+-notation, use the format string "U+\%04"G_GINT32_FORMAT"X".
53 * To scan, use the format string "U+\%06"G_GINT32_FORMAT"X".
54 *
55 * |[
56 * gunichar c;
57 * sscanf ("U+0041", "U+%06"G_GINT32_FORMAT"X", &amp;c)
58 * g_print ("Read U+%04"G_GINT32_FORMAT"X", c);
59 * ]|
60 */
61typedef guint32 gunichar;
62
63/**
64 * gunichar2:
65 *
66 * A type which can hold any UTF-16 code
67 * point<footnote id="utf16_surrogate_pairs">UTF-16 also has so called
68 * <firstterm>surrogate pairs</firstterm> to encode characters beyond
69 * the BMP as pairs of 16bit numbers. Surrogate pairs cannot be stored
70 * in a single gunichar2 field, but all GLib functions accepting gunichar2
71 * arrays will correctly interpret surrogate pairs.</footnote>.
72 *
73 * To print/scan values of this type to/from text you need to convert
74 * to/from UTF-8, using g_utf16_to_utf8()/g_utf8_to_utf16().
75 *
76 * To print/scan values of this type as integer, use
77 * %G_GINT16_MODIFIER and/or %G_GUINT16_FORMAT.
78 */
79typedef guint16 gunichar2;
80
81/**
82 * GUnicodeType:
83 * @G_UNICODE_CONTROL: General category "Other, Control" (Cc)
84 * @G_UNICODE_FORMAT: General category "Other, Format" (Cf)
85 * @G_UNICODE_UNASSIGNED: General category "Other, Not Assigned" (Cn)
86 * @G_UNICODE_PRIVATE_USE: General category "Other, Private Use" (Co)
87 * @G_UNICODE_SURROGATE: General category "Other, Surrogate" (Cs)
88 * @G_UNICODE_LOWERCASE_LETTER: General category "Letter, Lowercase" (Ll)
89 * @G_UNICODE_MODIFIER_LETTER: General category "Letter, Modifier" (Lm)
90 * @G_UNICODE_OTHER_LETTER: General category "Letter, Other" (Lo)
91 * @G_UNICODE_TITLECASE_LETTER: General category "Letter, Titlecase" (Lt)
92 * @G_UNICODE_UPPERCASE_LETTER: General category "Letter, Uppercase" (Lu)
93 * @G_UNICODE_SPACING_MARK: General category "Mark, Spacing" (Mc)
94 * @G_UNICODE_ENCLOSING_MARK: General category "Mark, Enclosing" (Me)
95 * @G_UNICODE_NON_SPACING_MARK: General category "Mark, Nonspacing" (Mn)
96 * @G_UNICODE_DECIMAL_NUMBER: General category "Number, Decimal Digit" (Nd)
97 * @G_UNICODE_LETTER_NUMBER: General category "Number, Letter" (Nl)
98 * @G_UNICODE_OTHER_NUMBER: General category "Number, Other" (No)
99 * @G_UNICODE_CONNECT_PUNCTUATION: General category "Punctuation, Connector" (Pc)
100 * @G_UNICODE_DASH_PUNCTUATION: General category "Punctuation, Dash" (Pd)
101 * @G_UNICODE_CLOSE_PUNCTUATION: General category "Punctuation, Close" (Pe)
102 * @G_UNICODE_FINAL_PUNCTUATION: General category "Punctuation, Final quote" (Pf)
103 * @G_UNICODE_INITIAL_PUNCTUATION: General category "Punctuation, Initial quote" (Pi)
104 * @G_UNICODE_OTHER_PUNCTUATION: General category "Punctuation, Other" (Po)
105 * @G_UNICODE_OPEN_PUNCTUATION: General category "Punctuation, Open" (Ps)
106 * @G_UNICODE_CURRENCY_SYMBOL: General category "Symbol, Currency" (Sc)
107 * @G_UNICODE_MODIFIER_SYMBOL: General category "Symbol, Modifier" (Sk)
108 * @G_UNICODE_MATH_SYMBOL: General category "Symbol, Math" (Sm)
109 * @G_UNICODE_OTHER_SYMBOL: General category "Symbol, Other" (So)
110 * @G_UNICODE_LINE_SEPARATOR: General category "Separator, Line" (Zl)
111 * @G_UNICODE_PARAGRAPH_SEPARATOR: General category "Separator, Paragraph" (Zp)
112 * @G_UNICODE_SPACE_SEPARATOR: General category "Separator, Space" (Zs)
113 *
114 * These are the possible character classifications from the
115 * Unicode specification.
116 * See [Unicode Character Database](http://www.unicode.org/reports/tr44/#General_Category_Values).
117 */
118typedef enum
119{
120 G_UNICODE_CONTROL,
121 G_UNICODE_FORMAT,
122 G_UNICODE_UNASSIGNED,
123 G_UNICODE_PRIVATE_USE,
124 G_UNICODE_SURROGATE,
125 G_UNICODE_LOWERCASE_LETTER,
126 G_UNICODE_MODIFIER_LETTER,
127 G_UNICODE_OTHER_LETTER,
128 G_UNICODE_TITLECASE_LETTER,
129 G_UNICODE_UPPERCASE_LETTER,
130 G_UNICODE_SPACING_MARK,
131 G_UNICODE_ENCLOSING_MARK,
132 G_UNICODE_NON_SPACING_MARK,
133 G_UNICODE_DECIMAL_NUMBER,
134 G_UNICODE_LETTER_NUMBER,
135 G_UNICODE_OTHER_NUMBER,
136 G_UNICODE_CONNECT_PUNCTUATION,
137 G_UNICODE_DASH_PUNCTUATION,
138 G_UNICODE_CLOSE_PUNCTUATION,
139 G_UNICODE_FINAL_PUNCTUATION,
140 G_UNICODE_INITIAL_PUNCTUATION,
141 G_UNICODE_OTHER_PUNCTUATION,
142 G_UNICODE_OPEN_PUNCTUATION,
143 G_UNICODE_CURRENCY_SYMBOL,
144 G_UNICODE_MODIFIER_SYMBOL,
145 G_UNICODE_MATH_SYMBOL,
146 G_UNICODE_OTHER_SYMBOL,
147 G_UNICODE_LINE_SEPARATOR,
148 G_UNICODE_PARAGRAPH_SEPARATOR,
149 G_UNICODE_SPACE_SEPARATOR
150} GUnicodeType;
151
152/**
153 * G_UNICODE_COMBINING_MARK:
154 *
155 * Older name for %G_UNICODE_SPACING_MARK.
156 *
157 * Deprecated: 2.30: Use %G_UNICODE_SPACING_MARK.
158 */
159#define G_UNICODE_COMBINING_MARK G_UNICODE_SPACING_MARK GLIB_DEPRECATED_MACRO_IN_2_30_FOR(G_UNICODE_SPACING_MARK)
160
161/**
162 * GUnicodeBreakType:
163 * @G_UNICODE_BREAK_MANDATORY: Mandatory Break (BK)
164 * @G_UNICODE_BREAK_CARRIAGE_RETURN: Carriage Return (CR)
165 * @G_UNICODE_BREAK_LINE_FEED: Line Feed (LF)
166 * @G_UNICODE_BREAK_COMBINING_MARK: Attached Characters and Combining Marks (CM)
167 * @G_UNICODE_BREAK_SURROGATE: Surrogates (SG)
168 * @G_UNICODE_BREAK_ZERO_WIDTH_SPACE: Zero Width Space (ZW)
169 * @G_UNICODE_BREAK_INSEPARABLE: Inseparable (IN)
170 * @G_UNICODE_BREAK_NON_BREAKING_GLUE: Non-breaking ("Glue") (GL)
171 * @G_UNICODE_BREAK_CONTINGENT: Contingent Break Opportunity (CB)
172 * @G_UNICODE_BREAK_SPACE: Space (SP)
173 * @G_UNICODE_BREAK_AFTER: Break Opportunity After (BA)
174 * @G_UNICODE_BREAK_BEFORE: Break Opportunity Before (BB)
175 * @G_UNICODE_BREAK_BEFORE_AND_AFTER: Break Opportunity Before and After (B2)
176 * @G_UNICODE_BREAK_HYPHEN: Hyphen (HY)
177 * @G_UNICODE_BREAK_NON_STARTER: Nonstarter (NS)
178 * @G_UNICODE_BREAK_OPEN_PUNCTUATION: Opening Punctuation (OP)
179 * @G_UNICODE_BREAK_CLOSE_PUNCTUATION: Closing Punctuation (CL)
180 * @G_UNICODE_BREAK_QUOTATION: Ambiguous Quotation (QU)
181 * @G_UNICODE_BREAK_EXCLAMATION: Exclamation/Interrogation (EX)
182 * @G_UNICODE_BREAK_IDEOGRAPHIC: Ideographic (ID)
183 * @G_UNICODE_BREAK_NUMERIC: Numeric (NU)
184 * @G_UNICODE_BREAK_INFIX_SEPARATOR: Infix Separator (Numeric) (IS)
185 * @G_UNICODE_BREAK_SYMBOL: Symbols Allowing Break After (SY)
186 * @G_UNICODE_BREAK_ALPHABETIC: Ordinary Alphabetic and Symbol Characters (AL)
187 * @G_UNICODE_BREAK_PREFIX: Prefix (Numeric) (PR)
188 * @G_UNICODE_BREAK_POSTFIX: Postfix (Numeric) (PO)
189 * @G_UNICODE_BREAK_COMPLEX_CONTEXT: Complex Content Dependent (South East Asian) (SA)
190 * @G_UNICODE_BREAK_AMBIGUOUS: Ambiguous (Alphabetic or Ideographic) (AI)
191 * @G_UNICODE_BREAK_UNKNOWN: Unknown (XX)
192 * @G_UNICODE_BREAK_NEXT_LINE: Next Line (NL)
193 * @G_UNICODE_BREAK_WORD_JOINER: Word Joiner (WJ)
194 * @G_UNICODE_BREAK_HANGUL_L_JAMO: Hangul L Jamo (JL)
195 * @G_UNICODE_BREAK_HANGUL_V_JAMO: Hangul V Jamo (JV)
196 * @G_UNICODE_BREAK_HANGUL_T_JAMO: Hangul T Jamo (JT)
197 * @G_UNICODE_BREAK_HANGUL_LV_SYLLABLE: Hangul LV Syllable (H2)
198 * @G_UNICODE_BREAK_HANGUL_LVT_SYLLABLE: Hangul LVT Syllable (H3)
199 * @G_UNICODE_BREAK_CLOSE_PARANTHESIS: Closing Parenthesis (CP). Since 2.28. Deprecated: 2.70: Use %G_UNICODE_BREAK_CLOSE_PARENTHESIS instead.
200 * @G_UNICODE_BREAK_CLOSE_PARENTHESIS: Closing Parenthesis (CP). Since 2.70
201 * @G_UNICODE_BREAK_CONDITIONAL_JAPANESE_STARTER: Conditional Japanese Starter (CJ). Since: 2.32
202 * @G_UNICODE_BREAK_HEBREW_LETTER: Hebrew Letter (HL). Since: 2.32
203 * @G_UNICODE_BREAK_REGIONAL_INDICATOR: Regional Indicator (RI). Since: 2.36
204 * @G_UNICODE_BREAK_EMOJI_BASE: Emoji Base (EB). Since: 2.50
205 * @G_UNICODE_BREAK_EMOJI_MODIFIER: Emoji Modifier (EM). Since: 2.50
206 * @G_UNICODE_BREAK_ZERO_WIDTH_JOINER: Zero Width Joiner (ZWJ). Since: 2.50
207 * @G_UNICODE_BREAK_AKSARA: Aksara (AK). Since: 2.80
208 * @G_UNICODE_BREAK_AKSARA_PRE_BASE (AP). Since: 2.80
209 * @G_UNICODE_BREAK_AKSARA_START (AS). Since: 2.80
210 * @G_UNICODE_BREAK_VIRAMA_FINAL (VF). Since: 2.80
211 * @G_UNICODE_BREAK_VIRAMA (VI). Since: 2.80
212 *
213 * These are the possible line break classifications.
214 *
215 * Since new Unicode versions may add new types here, applications should be ready
216 * to handle unknown values. They may be regarded as %G_UNICODE_BREAK_UNKNOWN.
217 *
218 * See [Unicode Line Breaking Algorithm](https://www.unicode.org/reports/tr14/).
219 */
220typedef enum
221{
222 G_UNICODE_BREAK_MANDATORY,
223 G_UNICODE_BREAK_CARRIAGE_RETURN,
224 G_UNICODE_BREAK_LINE_FEED,
225 G_UNICODE_BREAK_COMBINING_MARK,
226 G_UNICODE_BREAK_SURROGATE,
227 G_UNICODE_BREAK_ZERO_WIDTH_SPACE,
228 G_UNICODE_BREAK_INSEPARABLE,
229 G_UNICODE_BREAK_NON_BREAKING_GLUE,
230 G_UNICODE_BREAK_CONTINGENT,
231 G_UNICODE_BREAK_SPACE,
232 G_UNICODE_BREAK_AFTER,
233 G_UNICODE_BREAK_BEFORE,
234 G_UNICODE_BREAK_BEFORE_AND_AFTER,
235 G_UNICODE_BREAK_HYPHEN,
236 G_UNICODE_BREAK_NON_STARTER,
237 G_UNICODE_BREAK_OPEN_PUNCTUATION,
238 G_UNICODE_BREAK_CLOSE_PUNCTUATION,
239 G_UNICODE_BREAK_QUOTATION,
240 G_UNICODE_BREAK_EXCLAMATION,
241 G_UNICODE_BREAK_IDEOGRAPHIC,
242 G_UNICODE_BREAK_NUMERIC,
243 G_UNICODE_BREAK_INFIX_SEPARATOR,
244 G_UNICODE_BREAK_SYMBOL,
245 G_UNICODE_BREAK_ALPHABETIC,
246 G_UNICODE_BREAK_PREFIX,
247 G_UNICODE_BREAK_POSTFIX,
248 G_UNICODE_BREAK_COMPLEX_CONTEXT,
249 G_UNICODE_BREAK_AMBIGUOUS,
250 G_UNICODE_BREAK_UNKNOWN,
251 G_UNICODE_BREAK_NEXT_LINE,
252 G_UNICODE_BREAK_WORD_JOINER,
253 G_UNICODE_BREAK_HANGUL_L_JAMO,
254 G_UNICODE_BREAK_HANGUL_V_JAMO,
255 G_UNICODE_BREAK_HANGUL_T_JAMO,
256 G_UNICODE_BREAK_HANGUL_LV_SYLLABLE,
257 G_UNICODE_BREAK_HANGUL_LVT_SYLLABLE,
258 G_UNICODE_BREAK_CLOSE_PARANTHESIS,
259 G_UNICODE_BREAK_CLOSE_PARENTHESIS GLIB_AVAILABLE_ENUMERATOR_IN_2_70 = G_UNICODE_BREAK_CLOSE_PARANTHESIS,
260 G_UNICODE_BREAK_CONDITIONAL_JAPANESE_STARTER,
261 G_UNICODE_BREAK_HEBREW_LETTER,
262 G_UNICODE_BREAK_REGIONAL_INDICATOR,
263 G_UNICODE_BREAK_EMOJI_BASE,
264 G_UNICODE_BREAK_EMOJI_MODIFIER,
265 G_UNICODE_BREAK_ZERO_WIDTH_JOINER,
266 G_UNICODE_BREAK_AKSARA,
267 G_UNICODE_BREAK_AKSARA_PRE_BASE,
268 G_UNICODE_BREAK_AKSARA_START,
269 G_UNICODE_BREAK_VIRAMA_FINAL,
270 G_UNICODE_BREAK_VIRAMA
271} GUnicodeBreakType;
272
273/**
274 * GUnicodeScript:
275 * @G_UNICODE_SCRIPT_INVALID_CODE:
276 * a value never returned from g_unichar_get_script()
277 * @G_UNICODE_SCRIPT_COMMON: a character used by multiple different scripts
278 * @G_UNICODE_SCRIPT_INHERITED: a mark glyph that takes its script from the
279 * base glyph to which it is attached
280 * @G_UNICODE_SCRIPT_ARABIC: Arabic
281 * @G_UNICODE_SCRIPT_ARMENIAN: Armenian
282 * @G_UNICODE_SCRIPT_BENGALI: Bengali
283 * @G_UNICODE_SCRIPT_BOPOMOFO: Bopomofo
284 * @G_UNICODE_SCRIPT_CHEROKEE: Cherokee
285 * @G_UNICODE_SCRIPT_COPTIC: Coptic
286 * @G_UNICODE_SCRIPT_CYRILLIC: Cyrillic
287 * @G_UNICODE_SCRIPT_DESERET: Deseret
288 * @G_UNICODE_SCRIPT_DEVANAGARI: Devanagari
289 * @G_UNICODE_SCRIPT_ETHIOPIC: Ethiopic
290 * @G_UNICODE_SCRIPT_GEORGIAN: Georgian
291 * @G_UNICODE_SCRIPT_GOTHIC: Gothic
292 * @G_UNICODE_SCRIPT_GREEK: Greek
293 * @G_UNICODE_SCRIPT_GUJARATI: Gujarati
294 * @G_UNICODE_SCRIPT_GURMUKHI: Gurmukhi
295 * @G_UNICODE_SCRIPT_HAN: Han
296 * @G_UNICODE_SCRIPT_HANGUL: Hangul
297 * @G_UNICODE_SCRIPT_HEBREW: Hebrew
298 * @G_UNICODE_SCRIPT_HIRAGANA: Hiragana
299 * @G_UNICODE_SCRIPT_KANNADA: Kannada
300 * @G_UNICODE_SCRIPT_KATAKANA: Katakana
301 * @G_UNICODE_SCRIPT_KHMER: Khmer
302 * @G_UNICODE_SCRIPT_LAO: Lao
303 * @G_UNICODE_SCRIPT_LATIN: Latin
304 * @G_UNICODE_SCRIPT_MALAYALAM: Malayalam
305 * @G_UNICODE_SCRIPT_MONGOLIAN: Mongolian
306 * @G_UNICODE_SCRIPT_MYANMAR: Myanmar
307 * @G_UNICODE_SCRIPT_OGHAM: Ogham
308 * @G_UNICODE_SCRIPT_OLD_ITALIC: Old Italic
309 * @G_UNICODE_SCRIPT_ORIYA: Oriya
310 * @G_UNICODE_SCRIPT_RUNIC: Runic
311 * @G_UNICODE_SCRIPT_SINHALA: Sinhala
312 * @G_UNICODE_SCRIPT_SYRIAC: Syriac
313 * @G_UNICODE_SCRIPT_TAMIL: Tamil
314 * @G_UNICODE_SCRIPT_TELUGU: Telugu
315 * @G_UNICODE_SCRIPT_THAANA: Thaana
316 * @G_UNICODE_SCRIPT_THAI: Thai
317 * @G_UNICODE_SCRIPT_TIBETAN: Tibetan
318 * @G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL:
319 * Canadian Aboriginal
320 * @G_UNICODE_SCRIPT_YI: Yi
321 * @G_UNICODE_SCRIPT_TAGALOG: Tagalog
322 * @G_UNICODE_SCRIPT_HANUNOO: Hanunoo
323 * @G_UNICODE_SCRIPT_BUHID: Buhid
324 * @G_UNICODE_SCRIPT_TAGBANWA: Tagbanwa
325 * @G_UNICODE_SCRIPT_BRAILLE: Braille
326 * @G_UNICODE_SCRIPT_CYPRIOT: Cypriot
327 * @G_UNICODE_SCRIPT_LIMBU: Limbu
328 * @G_UNICODE_SCRIPT_OSMANYA: Osmanya
329 * @G_UNICODE_SCRIPT_SHAVIAN: Shavian
330 * @G_UNICODE_SCRIPT_LINEAR_B: Linear B
331 * @G_UNICODE_SCRIPT_TAI_LE: Tai Le
332 * @G_UNICODE_SCRIPT_UGARITIC: Ugaritic
333 * @G_UNICODE_SCRIPT_NEW_TAI_LUE:
334 * New Tai Lue
335 * @G_UNICODE_SCRIPT_BUGINESE: Buginese
336 * @G_UNICODE_SCRIPT_GLAGOLITIC: Glagolitic
337 * @G_UNICODE_SCRIPT_TIFINAGH: Tifinagh
338 * @G_UNICODE_SCRIPT_SYLOTI_NAGRI:
339 * Syloti Nagri
340 * @G_UNICODE_SCRIPT_OLD_PERSIAN:
341 * Old Persian
342 * @G_UNICODE_SCRIPT_KHAROSHTHI: Kharoshthi
343 * @G_UNICODE_SCRIPT_UNKNOWN: an unassigned code point
344 * @G_UNICODE_SCRIPT_BALINESE: Balinese
345 * @G_UNICODE_SCRIPT_CUNEIFORM: Cuneiform
346 * @G_UNICODE_SCRIPT_PHOENICIAN: Phoenician
347 * @G_UNICODE_SCRIPT_PHAGS_PA: Phags-pa
348 * @G_UNICODE_SCRIPT_NKO: N'Ko
349 * @G_UNICODE_SCRIPT_KAYAH_LI: Kayah Li. Since 2.16.3
350 * @G_UNICODE_SCRIPT_LEPCHA: Lepcha. Since 2.16.3
351 * @G_UNICODE_SCRIPT_REJANG: Rejang. Since 2.16.3
352 * @G_UNICODE_SCRIPT_SUNDANESE: Sundanese. Since 2.16.3
353 * @G_UNICODE_SCRIPT_SAURASHTRA: Saurashtra. Since 2.16.3
354 * @G_UNICODE_SCRIPT_CHAM: Cham. Since 2.16.3
355 * @G_UNICODE_SCRIPT_OL_CHIKI: Ol Chiki. Since 2.16.3
356 * @G_UNICODE_SCRIPT_VAI: Vai. Since 2.16.3
357 * @G_UNICODE_SCRIPT_CARIAN: Carian. Since 2.16.3
358 * @G_UNICODE_SCRIPT_LYCIAN: Lycian. Since 2.16.3
359 * @G_UNICODE_SCRIPT_LYDIAN: Lydian. Since 2.16.3
360 * @G_UNICODE_SCRIPT_AVESTAN: Avestan. Since 2.26
361 * @G_UNICODE_SCRIPT_BAMUM: Bamum. Since 2.26
362 * @G_UNICODE_SCRIPT_EGYPTIAN_HIEROGLYPHS:
363 * Egyptian Hieroglpyhs. Since 2.26
364 * @G_UNICODE_SCRIPT_IMPERIAL_ARAMAIC:
365 * Imperial Aramaic. Since 2.26
366 * @G_UNICODE_SCRIPT_INSCRIPTIONAL_PAHLAVI:
367 * Inscriptional Pahlavi. Since 2.26
368 * @G_UNICODE_SCRIPT_INSCRIPTIONAL_PARTHIAN:
369 * Inscriptional Parthian. Since 2.26
370 * @G_UNICODE_SCRIPT_JAVANESE: Javanese. Since 2.26
371 * @G_UNICODE_SCRIPT_KAITHI: Kaithi. Since 2.26
372 * @G_UNICODE_SCRIPT_LISU: Lisu. Since 2.26
373 * @G_UNICODE_SCRIPT_MEETEI_MAYEK:
374 * Meetei Mayek. Since 2.26
375 * @G_UNICODE_SCRIPT_OLD_SOUTH_ARABIAN:
376 * Old South Arabian. Since 2.26
377 * @G_UNICODE_SCRIPT_OLD_TURKIC: Old Turkic. Since 2.28
378 * @G_UNICODE_SCRIPT_SAMARITAN: Samaritan. Since 2.26
379 * @G_UNICODE_SCRIPT_TAI_THAM: Tai Tham. Since 2.26
380 * @G_UNICODE_SCRIPT_TAI_VIET: Tai Viet. Since 2.26
381 * @G_UNICODE_SCRIPT_BATAK: Batak. Since 2.28
382 * @G_UNICODE_SCRIPT_BRAHMI: Brahmi. Since 2.28
383 * @G_UNICODE_SCRIPT_MANDAIC: Mandaic. Since 2.28
384 * @G_UNICODE_SCRIPT_CHAKMA: Chakma. Since: 2.32
385 * @G_UNICODE_SCRIPT_MEROITIC_CURSIVE: Meroitic Cursive. Since: 2.32
386 * @G_UNICODE_SCRIPT_MEROITIC_HIEROGLYPHS: Meroitic Hieroglyphs. Since: 2.32
387 * @G_UNICODE_SCRIPT_MIAO: Miao. Since: 2.32
388 * @G_UNICODE_SCRIPT_SHARADA: Sharada. Since: 2.32
389 * @G_UNICODE_SCRIPT_SORA_SOMPENG: Sora Sompeng. Since: 2.32
390 * @G_UNICODE_SCRIPT_TAKRI: Takri. Since: 2.32
391 * @G_UNICODE_SCRIPT_BASSA_VAH: Bassa. Since: 2.42
392 * @G_UNICODE_SCRIPT_CAUCASIAN_ALBANIAN: Caucasian Albanian. Since: 2.42
393 * @G_UNICODE_SCRIPT_DUPLOYAN: Duployan. Since: 2.42
394 * @G_UNICODE_SCRIPT_ELBASAN: Elbasan. Since: 2.42
395 * @G_UNICODE_SCRIPT_GRANTHA: Grantha. Since: 2.42
396 * @G_UNICODE_SCRIPT_KHOJKI: Kjohki. Since: 2.42
397 * @G_UNICODE_SCRIPT_KHUDAWADI: Khudawadi, Sindhi. Since: 2.42
398 * @G_UNICODE_SCRIPT_LINEAR_A: Linear A. Since: 2.42
399 * @G_UNICODE_SCRIPT_MAHAJANI: Mahajani. Since: 2.42
400 * @G_UNICODE_SCRIPT_MANICHAEAN: Manichaean. Since: 2.42
401 * @G_UNICODE_SCRIPT_MENDE_KIKAKUI: Mende Kikakui. Since: 2.42
402 * @G_UNICODE_SCRIPT_MODI: Modi. Since: 2.42
403 * @G_UNICODE_SCRIPT_MRO: Mro. Since: 2.42
404 * @G_UNICODE_SCRIPT_NABATAEAN: Nabataean. Since: 2.42
405 * @G_UNICODE_SCRIPT_OLD_NORTH_ARABIAN: Old North Arabian. Since: 2.42
406 * @G_UNICODE_SCRIPT_OLD_PERMIC: Old Permic. Since: 2.42
407 * @G_UNICODE_SCRIPT_PAHAWH_HMONG: Pahawh Hmong. Since: 2.42
408 * @G_UNICODE_SCRIPT_PALMYRENE: Palmyrene. Since: 2.42
409 * @G_UNICODE_SCRIPT_PAU_CIN_HAU: Pau Cin Hau. Since: 2.42
410 * @G_UNICODE_SCRIPT_PSALTER_PAHLAVI: Psalter Pahlavi. Since: 2.42
411 * @G_UNICODE_SCRIPT_SIDDHAM: Siddham. Since: 2.42
412 * @G_UNICODE_SCRIPT_TIRHUTA: Tirhuta. Since: 2.42
413 * @G_UNICODE_SCRIPT_WARANG_CITI: Warang Citi. Since: 2.42
414 * @G_UNICODE_SCRIPT_AHOM: Ahom. Since: 2.48
415 * @G_UNICODE_SCRIPT_ANATOLIAN_HIEROGLYPHS: Anatolian Hieroglyphs. Since: 2.48
416 * @G_UNICODE_SCRIPT_HATRAN: Hatran. Since: 2.48
417 * @G_UNICODE_SCRIPT_MULTANI: Multani. Since: 2.48
418 * @G_UNICODE_SCRIPT_OLD_HUNGARIAN: Old Hungarian. Since: 2.48
419 * @G_UNICODE_SCRIPT_SIGNWRITING: Signwriting. Since: 2.48
420 * @G_UNICODE_SCRIPT_ADLAM: Adlam. Since: 2.50
421 * @G_UNICODE_SCRIPT_BHAIKSUKI: Bhaiksuki. Since: 2.50
422 * @G_UNICODE_SCRIPT_MARCHEN: Marchen. Since: 2.50
423 * @G_UNICODE_SCRIPT_NEWA: Newa. Since: 2.50
424 * @G_UNICODE_SCRIPT_OSAGE: Osage. Since: 2.50
425 * @G_UNICODE_SCRIPT_TANGUT: Tangut. Since: 2.50
426 * @G_UNICODE_SCRIPT_MASARAM_GONDI: Masaram Gondi. Since: 2.54
427 * @G_UNICODE_SCRIPT_NUSHU: Nushu. Since: 2.54
428 * @G_UNICODE_SCRIPT_SOYOMBO: Soyombo. Since: 2.54
429 * @G_UNICODE_SCRIPT_ZANABAZAR_SQUARE: Zanabazar Square. Since: 2.54
430 * @G_UNICODE_SCRIPT_DOGRA: Dogra. Since: 2.58
431 * @G_UNICODE_SCRIPT_GUNJALA_GONDI: Gunjala Gondi. Since: 2.58
432 * @G_UNICODE_SCRIPT_HANIFI_ROHINGYA: Hanifi Rohingya. Since: 2.58
433 * @G_UNICODE_SCRIPT_MAKASAR: Makasar. Since: 2.58
434 * @G_UNICODE_SCRIPT_MEDEFAIDRIN: Medefaidrin. Since: 2.58
435 * @G_UNICODE_SCRIPT_OLD_SOGDIAN: Old Sogdian. Since: 2.58
436 * @G_UNICODE_SCRIPT_SOGDIAN: Sogdian. Since: 2.58
437 * @G_UNICODE_SCRIPT_ELYMAIC: Elym. Since: 2.62
438 * @G_UNICODE_SCRIPT_NANDINAGARI: Nand. Since: 2.62
439 * @G_UNICODE_SCRIPT_NYIAKENG_PUACHUE_HMONG: Rohg. Since: 2.62
440 * @G_UNICODE_SCRIPT_WANCHO: Wcho. Since: 2.62
441 * @G_UNICODE_SCRIPT_CHORASMIAN: Chorasmian. Since: 2.66
442 * @G_UNICODE_SCRIPT_DIVES_AKURU: Dives Akuru. Since: 2.66
443 * @G_UNICODE_SCRIPT_KHITAN_SMALL_SCRIPT: Khitan small script. Since: 2.66
444 * @G_UNICODE_SCRIPT_YEZIDI: Yezidi. Since: 2.66
445 * @G_UNICODE_SCRIPT_CYPRO_MINOAN: Cypro-Minoan. Since: 2.72
446 * @G_UNICODE_SCRIPT_OLD_UYGHUR: Old Uyghur. Since: 2.72
447 * @G_UNICODE_SCRIPT_TANGSA: Tangsa. Since: 2.72
448 * @G_UNICODE_SCRIPT_TOTO: Toto. Since: 2.72
449 * @G_UNICODE_SCRIPT_VITHKUQI: Vithkuqi. Since: 2.72
450 * @G_UNICODE_SCRIPT_MATH: Mathematical notation. Since: 2.72
451 * @G_UNICODE_SCRIPT_KAWI: Kawi. Since 2.74
452 * @G_UNICODE_SCRIPT_NAG_MUNDARI: Nag Mundari. Since 2.74
453 *
454 * The #GUnicodeScript enumeration identifies different writing
455 * systems. The values correspond to the names as defined in the
456 * Unicode standard. The enumeration has been added in GLib 2.14,
457 * and is interchangeable with #PangoScript.
458 *
459 * Note that new types may be added in the future. Applications
460 * should be ready to handle unknown values.
461 * See [Unicode Standard Annex #24: Script names](http://www.unicode.org/reports/tr24/).
462 */
463typedef enum
464{ /* ISO 15924 code */
465 G_UNICODE_SCRIPT_INVALID_CODE = -1,
466 G_UNICODE_SCRIPT_COMMON = 0, /* Zyyy */
467 G_UNICODE_SCRIPT_INHERITED, /* Zinh (Qaai) */
468 G_UNICODE_SCRIPT_ARABIC, /* Arab */
469 G_UNICODE_SCRIPT_ARMENIAN, /* Armn */
470 G_UNICODE_SCRIPT_BENGALI, /* Beng */
471 G_UNICODE_SCRIPT_BOPOMOFO, /* Bopo */
472 G_UNICODE_SCRIPT_CHEROKEE, /* Cher */
473 G_UNICODE_SCRIPT_COPTIC, /* Copt (Qaac) */
474 G_UNICODE_SCRIPT_CYRILLIC, /* Cyrl (Cyrs) */
475 G_UNICODE_SCRIPT_DESERET, /* Dsrt */
476 G_UNICODE_SCRIPT_DEVANAGARI, /* Deva */
477 G_UNICODE_SCRIPT_ETHIOPIC, /* Ethi */
478 G_UNICODE_SCRIPT_GEORGIAN, /* Geor (Geon, Geoa) */
479 G_UNICODE_SCRIPT_GOTHIC, /* Goth */
480 G_UNICODE_SCRIPT_GREEK, /* Grek */
481 G_UNICODE_SCRIPT_GUJARATI, /* Gujr */
482 G_UNICODE_SCRIPT_GURMUKHI, /* Guru */
483 G_UNICODE_SCRIPT_HAN, /* Hani */
484 G_UNICODE_SCRIPT_HANGUL, /* Hang */
485 G_UNICODE_SCRIPT_HEBREW, /* Hebr */
486 G_UNICODE_SCRIPT_HIRAGANA, /* Hira */
487 G_UNICODE_SCRIPT_KANNADA, /* Knda */
488 G_UNICODE_SCRIPT_KATAKANA, /* Kana */
489 G_UNICODE_SCRIPT_KHMER, /* Khmr */
490 G_UNICODE_SCRIPT_LAO, /* Laoo */
491 G_UNICODE_SCRIPT_LATIN, /* Latn (Latf, Latg) */
492 G_UNICODE_SCRIPT_MALAYALAM, /* Mlym */
493 G_UNICODE_SCRIPT_MONGOLIAN, /* Mong */
494 G_UNICODE_SCRIPT_MYANMAR, /* Mymr */
495 G_UNICODE_SCRIPT_OGHAM, /* Ogam */
496 G_UNICODE_SCRIPT_OLD_ITALIC, /* Ital */
497 G_UNICODE_SCRIPT_ORIYA, /* Orya */
498 G_UNICODE_SCRIPT_RUNIC, /* Runr */
499 G_UNICODE_SCRIPT_SINHALA, /* Sinh */
500 G_UNICODE_SCRIPT_SYRIAC, /* Syrc (Syrj, Syrn, Syre) */
501 G_UNICODE_SCRIPT_TAMIL, /* Taml */
502 G_UNICODE_SCRIPT_TELUGU, /* Telu */
503 G_UNICODE_SCRIPT_THAANA, /* Thaa */
504 G_UNICODE_SCRIPT_THAI, /* Thai */
505 G_UNICODE_SCRIPT_TIBETAN, /* Tibt */
506 G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL, /* Cans */
507 G_UNICODE_SCRIPT_YI, /* Yiii */
508 G_UNICODE_SCRIPT_TAGALOG, /* Tglg */
509 G_UNICODE_SCRIPT_HANUNOO, /* Hano */
510 G_UNICODE_SCRIPT_BUHID, /* Buhd */
511 G_UNICODE_SCRIPT_TAGBANWA, /* Tagb */
512
513 /* Unicode-4.0 additions */
514 G_UNICODE_SCRIPT_BRAILLE, /* Brai */
515 G_UNICODE_SCRIPT_CYPRIOT, /* Cprt */
516 G_UNICODE_SCRIPT_LIMBU, /* Limb */
517 G_UNICODE_SCRIPT_OSMANYA, /* Osma */
518 G_UNICODE_SCRIPT_SHAVIAN, /* Shaw */
519 G_UNICODE_SCRIPT_LINEAR_B, /* Linb */
520 G_UNICODE_SCRIPT_TAI_LE, /* Tale */
521 G_UNICODE_SCRIPT_UGARITIC, /* Ugar */
522
523 /* Unicode-4.1 additions */
524 G_UNICODE_SCRIPT_NEW_TAI_LUE, /* Talu */
525 G_UNICODE_SCRIPT_BUGINESE, /* Bugi */
526 G_UNICODE_SCRIPT_GLAGOLITIC, /* Glag */
527 G_UNICODE_SCRIPT_TIFINAGH, /* Tfng */
528 G_UNICODE_SCRIPT_SYLOTI_NAGRI, /* Sylo */
529 G_UNICODE_SCRIPT_OLD_PERSIAN, /* Xpeo */
530 G_UNICODE_SCRIPT_KHAROSHTHI, /* Khar */
531
532 /* Unicode-5.0 additions */
533 G_UNICODE_SCRIPT_UNKNOWN, /* Zzzz */
534 G_UNICODE_SCRIPT_BALINESE, /* Bali */
535 G_UNICODE_SCRIPT_CUNEIFORM, /* Xsux */
536 G_UNICODE_SCRIPT_PHOENICIAN, /* Phnx */
537 G_UNICODE_SCRIPT_PHAGS_PA, /* Phag */
538 G_UNICODE_SCRIPT_NKO, /* Nkoo */
539
540 /* Unicode-5.1 additions */
541 G_UNICODE_SCRIPT_KAYAH_LI, /* Kali */
542 G_UNICODE_SCRIPT_LEPCHA, /* Lepc */
543 G_UNICODE_SCRIPT_REJANG, /* Rjng */
544 G_UNICODE_SCRIPT_SUNDANESE, /* Sund */
545 G_UNICODE_SCRIPT_SAURASHTRA, /* Saur */
546 G_UNICODE_SCRIPT_CHAM, /* Cham */
547 G_UNICODE_SCRIPT_OL_CHIKI, /* Olck */
548 G_UNICODE_SCRIPT_VAI, /* Vaii */
549 G_UNICODE_SCRIPT_CARIAN, /* Cari */
550 G_UNICODE_SCRIPT_LYCIAN, /* Lyci */
551 G_UNICODE_SCRIPT_LYDIAN, /* Lydi */
552
553 /* Unicode-5.2 additions */
554 G_UNICODE_SCRIPT_AVESTAN, /* Avst */
555 G_UNICODE_SCRIPT_BAMUM, /* Bamu */
556 G_UNICODE_SCRIPT_EGYPTIAN_HIEROGLYPHS, /* Egyp */
557 G_UNICODE_SCRIPT_IMPERIAL_ARAMAIC, /* Armi */
558 G_UNICODE_SCRIPT_INSCRIPTIONAL_PAHLAVI, /* Phli */
559 G_UNICODE_SCRIPT_INSCRIPTIONAL_PARTHIAN, /* Prti */
560 G_UNICODE_SCRIPT_JAVANESE, /* Java */
561 G_UNICODE_SCRIPT_KAITHI, /* Kthi */
562 G_UNICODE_SCRIPT_LISU, /* Lisu */
563 G_UNICODE_SCRIPT_MEETEI_MAYEK, /* Mtei */
564 G_UNICODE_SCRIPT_OLD_SOUTH_ARABIAN, /* Sarb */
565 G_UNICODE_SCRIPT_OLD_TURKIC, /* Orkh */
566 G_UNICODE_SCRIPT_SAMARITAN, /* Samr */
567 G_UNICODE_SCRIPT_TAI_THAM, /* Lana */
568 G_UNICODE_SCRIPT_TAI_VIET, /* Tavt */
569
570 /* Unicode-6.0 additions */
571 G_UNICODE_SCRIPT_BATAK, /* Batk */
572 G_UNICODE_SCRIPT_BRAHMI, /* Brah */
573 G_UNICODE_SCRIPT_MANDAIC, /* Mand */
574
575 /* Unicode-6.1 additions */
576 G_UNICODE_SCRIPT_CHAKMA, /* Cakm */
577 G_UNICODE_SCRIPT_MEROITIC_CURSIVE, /* Merc */
578 G_UNICODE_SCRIPT_MEROITIC_HIEROGLYPHS, /* Mero */
579 G_UNICODE_SCRIPT_MIAO, /* Plrd */
580 G_UNICODE_SCRIPT_SHARADA, /* Shrd */
581 G_UNICODE_SCRIPT_SORA_SOMPENG, /* Sora */
582 G_UNICODE_SCRIPT_TAKRI, /* Takr */
583
584 /* Unicode 7.0 additions */
585 G_UNICODE_SCRIPT_BASSA_VAH, /* Bass */
586 G_UNICODE_SCRIPT_CAUCASIAN_ALBANIAN, /* Aghb */
587 G_UNICODE_SCRIPT_DUPLOYAN, /* Dupl */
588 G_UNICODE_SCRIPT_ELBASAN, /* Elba */
589 G_UNICODE_SCRIPT_GRANTHA, /* Gran */
590 G_UNICODE_SCRIPT_KHOJKI, /* Khoj */
591 G_UNICODE_SCRIPT_KHUDAWADI, /* Sind */
592 G_UNICODE_SCRIPT_LINEAR_A, /* Lina */
593 G_UNICODE_SCRIPT_MAHAJANI, /* Mahj */
594 G_UNICODE_SCRIPT_MANICHAEAN, /* Mani */
595 G_UNICODE_SCRIPT_MENDE_KIKAKUI, /* Mend */
596 G_UNICODE_SCRIPT_MODI, /* Modi */
597 G_UNICODE_SCRIPT_MRO, /* Mroo */
598 G_UNICODE_SCRIPT_NABATAEAN, /* Nbat */
599 G_UNICODE_SCRIPT_OLD_NORTH_ARABIAN, /* Narb */
600 G_UNICODE_SCRIPT_OLD_PERMIC, /* Perm */
601 G_UNICODE_SCRIPT_PAHAWH_HMONG, /* Hmng */
602 G_UNICODE_SCRIPT_PALMYRENE, /* Palm */
603 G_UNICODE_SCRIPT_PAU_CIN_HAU, /* Pauc */
604 G_UNICODE_SCRIPT_PSALTER_PAHLAVI, /* Phlp */
605 G_UNICODE_SCRIPT_SIDDHAM, /* Sidd */
606 G_UNICODE_SCRIPT_TIRHUTA, /* Tirh */
607 G_UNICODE_SCRIPT_WARANG_CITI, /* Wara */
608
609 /* Unicode 8.0 additions */
610 G_UNICODE_SCRIPT_AHOM, /* Ahom */
611 G_UNICODE_SCRIPT_ANATOLIAN_HIEROGLYPHS, /* Hluw */
612 G_UNICODE_SCRIPT_HATRAN, /* Hatr */
613 G_UNICODE_SCRIPT_MULTANI, /* Mult */
614 G_UNICODE_SCRIPT_OLD_HUNGARIAN, /* Hung */
615 G_UNICODE_SCRIPT_SIGNWRITING, /* Sgnw */
616
617 /* Unicode 9.0 additions */
618 G_UNICODE_SCRIPT_ADLAM, /* Adlm */
619 G_UNICODE_SCRIPT_BHAIKSUKI, /* Bhks */
620 G_UNICODE_SCRIPT_MARCHEN, /* Marc */
621 G_UNICODE_SCRIPT_NEWA, /* Newa */
622 G_UNICODE_SCRIPT_OSAGE, /* Osge */
623 G_UNICODE_SCRIPT_TANGUT, /* Tang */
624
625 /* Unicode 10.0 additions */
626 G_UNICODE_SCRIPT_MASARAM_GONDI, /* Gonm */
627 G_UNICODE_SCRIPT_NUSHU, /* Nshu */
628 G_UNICODE_SCRIPT_SOYOMBO, /* Soyo */
629 G_UNICODE_SCRIPT_ZANABAZAR_SQUARE, /* Zanb */
630
631 /* Unicode 11.0 additions */
632 G_UNICODE_SCRIPT_DOGRA, /* Dogr */
633 G_UNICODE_SCRIPT_GUNJALA_GONDI, /* Gong */
634 G_UNICODE_SCRIPT_HANIFI_ROHINGYA, /* Rohg */
635 G_UNICODE_SCRIPT_MAKASAR, /* Maka */
636 G_UNICODE_SCRIPT_MEDEFAIDRIN, /* Medf */
637 G_UNICODE_SCRIPT_OLD_SOGDIAN, /* Sogo */
638 G_UNICODE_SCRIPT_SOGDIAN, /* Sogd */
639
640 /* Unicode 12.0 additions */
641 G_UNICODE_SCRIPT_ELYMAIC, /* Elym */
642 G_UNICODE_SCRIPT_NANDINAGARI, /* Nand */
643 G_UNICODE_SCRIPT_NYIAKENG_PUACHUE_HMONG, /* Rohg */
644 G_UNICODE_SCRIPT_WANCHO, /* Wcho */
645
646 /* Unicode 13.0 additions */
647 G_UNICODE_SCRIPT_CHORASMIAN, /* Chrs */
648 G_UNICODE_SCRIPT_DIVES_AKURU, /* Diak */
649 G_UNICODE_SCRIPT_KHITAN_SMALL_SCRIPT, /* Kits */
650 G_UNICODE_SCRIPT_YEZIDI, /* Yezi */
651
652 /* Unicode 14.0 additions */
653 G_UNICODE_SCRIPT_CYPRO_MINOAN, /* Cpmn */
654 G_UNICODE_SCRIPT_OLD_UYGHUR, /* Ougr */
655 G_UNICODE_SCRIPT_TANGSA, /* Tnsa */
656 G_UNICODE_SCRIPT_TOTO, /* Toto */
657 G_UNICODE_SCRIPT_VITHKUQI, /* Vith */
658
659 /* not really a Unicode script, but part of ISO 15924 */
660 G_UNICODE_SCRIPT_MATH, /* Zmth */
661
662 /* Unicode 15.0 additions */
663 G_UNICODE_SCRIPT_KAWI GLIB_AVAILABLE_ENUMERATOR_IN_2_74, /* Kawi */
664 G_UNICODE_SCRIPT_NAG_MUNDARI GLIB_AVAILABLE_ENUMERATOR_IN_2_74, /* Nag Mundari */
665} GUnicodeScript;
666
667GLIB_AVAILABLE_IN_ALL
668guint32 g_unicode_script_to_iso15924 (GUnicodeScript script);
669GLIB_AVAILABLE_IN_ALL
670GUnicodeScript g_unicode_script_from_iso15924 (guint32 iso15924);
671
672/* These are all analogs of the <ctype.h> functions.
673 */
674GLIB_AVAILABLE_IN_ALL
675gboolean g_unichar_isalnum (gunichar c) G_GNUC_CONST;
676GLIB_AVAILABLE_IN_ALL
677gboolean g_unichar_isalpha (gunichar c) G_GNUC_CONST;
678GLIB_AVAILABLE_IN_ALL
679gboolean g_unichar_iscntrl (gunichar c) G_GNUC_CONST;
680GLIB_AVAILABLE_IN_ALL
681gboolean g_unichar_isdigit (gunichar c) G_GNUC_CONST;
682GLIB_AVAILABLE_IN_ALL
683gboolean g_unichar_isgraph (gunichar c) G_GNUC_CONST;
684GLIB_AVAILABLE_IN_ALL
685gboolean g_unichar_islower (gunichar c) G_GNUC_CONST;
686GLIB_AVAILABLE_IN_ALL
687gboolean g_unichar_isprint (gunichar c) G_GNUC_CONST;
688GLIB_AVAILABLE_IN_ALL
689gboolean g_unichar_ispunct (gunichar c) G_GNUC_CONST;
690GLIB_AVAILABLE_IN_ALL
691gboolean g_unichar_isspace (gunichar c) G_GNUC_CONST;
692GLIB_AVAILABLE_IN_ALL
693gboolean g_unichar_isupper (gunichar c) G_GNUC_CONST;
694GLIB_AVAILABLE_IN_ALL
695gboolean g_unichar_isxdigit (gunichar c) G_GNUC_CONST;
696GLIB_AVAILABLE_IN_ALL
697gboolean g_unichar_istitle (gunichar c) G_GNUC_CONST;
698GLIB_AVAILABLE_IN_ALL
699gboolean g_unichar_isdefined (gunichar c) G_GNUC_CONST;
700GLIB_AVAILABLE_IN_ALL
701gboolean g_unichar_iswide (gunichar c) G_GNUC_CONST;
702GLIB_AVAILABLE_IN_ALL
703gboolean g_unichar_iswide_cjk(gunichar c) G_GNUC_CONST;
704GLIB_AVAILABLE_IN_ALL
705gboolean g_unichar_iszerowidth(gunichar c) G_GNUC_CONST;
706GLIB_AVAILABLE_IN_ALL
707gboolean g_unichar_ismark (gunichar c) G_GNUC_CONST;
708
709/* More <ctype.h> functions. These convert between the three cases.
710 * See the Unicode book to understand title case. */
711GLIB_AVAILABLE_IN_ALL
712gunichar g_unichar_toupper (gunichar c) G_GNUC_CONST;
713GLIB_AVAILABLE_IN_ALL
714gunichar g_unichar_tolower (gunichar c) G_GNUC_CONST;
715GLIB_AVAILABLE_IN_ALL
716gunichar g_unichar_totitle (gunichar c) G_GNUC_CONST;
717
718/* If C is a digit (according to 'g_unichar_isdigit'), then return its
719 numeric value. Otherwise return -1. */
720GLIB_AVAILABLE_IN_ALL
721gint g_unichar_digit_value (gunichar c) G_GNUC_CONST;
722
723GLIB_AVAILABLE_IN_ALL
724gint g_unichar_xdigit_value (gunichar c) G_GNUC_CONST;
725
726/* Return the Unicode character type of a given character. */
727GLIB_AVAILABLE_IN_ALL
728GUnicodeType g_unichar_type (gunichar c) G_GNUC_CONST;
729
730/* Return the line break property for a given character */
731GLIB_AVAILABLE_IN_ALL
732GUnicodeBreakType g_unichar_break_type (gunichar c) G_GNUC_CONST;
733
734/* Returns the combining class for a given character */
735GLIB_AVAILABLE_IN_ALL
736gint g_unichar_combining_class (gunichar uc) G_GNUC_CONST;
737
738GLIB_AVAILABLE_IN_ALL
739gboolean g_unichar_get_mirror_char (gunichar ch,
740 gunichar *mirrored_ch);
741
742GLIB_AVAILABLE_IN_ALL
743GUnicodeScript g_unichar_get_script (gunichar ch) G_GNUC_CONST;
744
745/* Validate a Unicode character */
746GLIB_AVAILABLE_IN_ALL
747gboolean g_unichar_validate (gunichar ch) G_GNUC_CONST;
748
749/* Pairwise canonical compose/decompose */
750GLIB_AVAILABLE_IN_ALL
751gboolean g_unichar_compose (gunichar a,
752 gunichar b,
753 gunichar *ch);
754GLIB_AVAILABLE_IN_ALL
755gboolean g_unichar_decompose (gunichar ch,
756 gunichar *a,
757 gunichar *b);
758
759GLIB_AVAILABLE_IN_ALL
760gsize g_unichar_fully_decompose (gunichar ch,
761 gboolean compat,
762 gunichar *result,
763 gsize result_len);
764
765/**
766 * G_UNICHAR_MAX_DECOMPOSITION_LENGTH:
767 *
768 * The maximum length (in codepoints) of a compatibility or canonical
769 * decomposition of a single Unicode character.
770 *
771 * This is as defined by Unicode 6.1.
772 *
773 * Since: 2.32
774 */
775#define G_UNICHAR_MAX_DECOMPOSITION_LENGTH 18 /* codepoints */
776
777/* Compute canonical ordering of a string in-place. This rearranges
778 decomposed characters in the string according to their combining
779 classes. See the Unicode manual for more information. */
780GLIB_AVAILABLE_IN_ALL
781void g_unicode_canonical_ordering (gunichar *string,
782 gsize len);
783
784
785GLIB_DEPRECATED_IN_2_30
786gunichar *g_unicode_canonical_decomposition (gunichar ch,
787 gsize *result_len) G_GNUC_MALLOC;
788
789/* Array of skip-bytes-per-initial character.
790 */
791GLIB_VAR const gchar * const g_utf8_skip;
792
793/**
794 * g_utf8_next_char:
795 * @p: Pointer to the start of a valid UTF-8 character
796 *
797 * Skips to the next character in a UTF-8 string.
798 *
799 * The string must be valid; this macro is as fast as possible, and has
800 * no error-checking.
801 *
802 * You would use this macro to iterate over a string character by character.
803 *
804 * The macro returns the start of the next UTF-8 character.
805 *
806 * Before using this macro, use g_utf8_validate() to validate strings
807 * that may contain invalid UTF-8.
808 */
809#define g_utf8_next_char(p) (char *)((p) + g_utf8_skip[*(const guchar *)(p)])
810
811GLIB_AVAILABLE_IN_ALL
812gunichar g_utf8_get_char (const gchar *p) G_GNUC_PURE;
813GLIB_AVAILABLE_IN_ALL
814gunichar g_utf8_get_char_validated (const gchar *p,
815 gssize max_len) G_GNUC_PURE;
816
817GLIB_AVAILABLE_IN_ALL
818gchar* g_utf8_offset_to_pointer (const gchar *str,
819 glong offset) G_GNUC_PURE;
820GLIB_AVAILABLE_IN_ALL
821glong g_utf8_pointer_to_offset (const gchar *str,
822 const gchar *pos) G_GNUC_PURE;
823GLIB_AVAILABLE_IN_ALL
824gchar* g_utf8_prev_char (const gchar *p) G_GNUC_PURE;
825GLIB_AVAILABLE_IN_ALL
826gchar* g_utf8_find_next_char (const gchar *p,
827 const gchar *end) G_GNUC_PURE;
828GLIB_AVAILABLE_IN_ALL
829gchar* g_utf8_find_prev_char (const gchar *str,
830 const gchar *p) G_GNUC_PURE;
831
832GLIB_AVAILABLE_IN_ALL
833glong g_utf8_strlen (const gchar *p,
834 gssize max) G_GNUC_PURE;
835
836GLIB_AVAILABLE_IN_2_30
837gchar *g_utf8_substring (const gchar *str,
838 glong start_pos,
839 glong end_pos) G_GNUC_MALLOC;
840
841GLIB_AVAILABLE_IN_ALL
842gchar *g_utf8_strncpy (gchar *dest,
843 const gchar *src,
844 gsize n);
845
846GLIB_AVAILABLE_IN_2_78
847gchar *g_utf8_truncate_middle (const gchar *string,
848 gsize truncate_length);
849
850/* Find the UTF-8 character corresponding to ch, in string p. These
851 functions are equivalants to strchr and strrchr */
852GLIB_AVAILABLE_IN_ALL
853gchar* g_utf8_strchr (const gchar *p,
854 gssize len,
855 gunichar c);
856GLIB_AVAILABLE_IN_ALL
857gchar* g_utf8_strrchr (const gchar *p,
858 gssize len,
859 gunichar c);
860GLIB_AVAILABLE_IN_ALL
861gchar* g_utf8_strreverse (const gchar *str,
862 gssize len);
863
864GLIB_AVAILABLE_IN_ALL
865gunichar2 *g_utf8_to_utf16 (const gchar *str,
866 glong len,
867 glong *items_read,
868 glong *items_written,
869 GError **error) G_GNUC_MALLOC;
870GLIB_AVAILABLE_IN_ALL
871gunichar * g_utf8_to_ucs4 (const gchar *str,
872 glong len,
873 glong *items_read,
874 glong *items_written,
875 GError **error) G_GNUC_MALLOC;
876GLIB_AVAILABLE_IN_ALL
877gunichar * g_utf8_to_ucs4_fast (const gchar *str,
878 glong len,
879 glong *items_written) G_GNUC_MALLOC;
880GLIB_AVAILABLE_IN_ALL
881gunichar * g_utf16_to_ucs4 (const gunichar2 *str,
882 glong len,
883 glong *items_read,
884 glong *items_written,
885 GError **error) G_GNUC_MALLOC;
886GLIB_AVAILABLE_IN_ALL
887gchar* g_utf16_to_utf8 (const gunichar2 *str,
888 glong len,
889 glong *items_read,
890 glong *items_written,
891 GError **error) G_GNUC_MALLOC;
892GLIB_AVAILABLE_IN_ALL
893gunichar2 *g_ucs4_to_utf16 (const gunichar *str,
894 glong len,
895 glong *items_read,
896 glong *items_written,
897 GError **error) G_GNUC_MALLOC;
898GLIB_AVAILABLE_IN_ALL
899gchar* g_ucs4_to_utf8 (const gunichar *str,
900 glong len,
901 glong *items_read,
902 glong *items_written,
903 GError **error) G_GNUC_MALLOC;
904
905GLIB_AVAILABLE_IN_ALL
906gint g_unichar_to_utf8 (gunichar c,
907 gchar *outbuf);
908
909GLIB_AVAILABLE_IN_ALL
910gboolean g_utf8_validate (const gchar *str,
911 gssize max_len,
912 const gchar **end);
913GLIB_AVAILABLE_IN_2_60
914gboolean g_utf8_validate_len (const gchar *str,
915 gsize max_len,
916 const gchar **end);
917
918GLIB_AVAILABLE_IN_ALL
919gchar *g_utf8_strup (const gchar *str,
920 gssize len) G_GNUC_MALLOC;
921GLIB_AVAILABLE_IN_ALL
922gchar *g_utf8_strdown (const gchar *str,
923 gssize len) G_GNUC_MALLOC;
924GLIB_AVAILABLE_IN_ALL
925gchar *g_utf8_casefold (const gchar *str,
926 gssize len) G_GNUC_MALLOC;
927
928/**
929 * GNormalizeMode:
930 * @G_NORMALIZE_DEFAULT: standardize differences that do not affect the
931 * text content, such as the above-mentioned accent representation
932 * @G_NORMALIZE_NFD: another name for %G_NORMALIZE_DEFAULT
933 * @G_NORMALIZE_DEFAULT_COMPOSE: like %G_NORMALIZE_DEFAULT, but with
934 * composed forms rather than a maximally decomposed form
935 * @G_NORMALIZE_NFC: another name for %G_NORMALIZE_DEFAULT_COMPOSE
936 * @G_NORMALIZE_ALL: beyond %G_NORMALIZE_DEFAULT also standardize the
937 * "compatibility" characters in Unicode, such as SUPERSCRIPT THREE
938 * to the standard forms (in this case DIGIT THREE). Formatting
939 * information may be lost but for most text operations such
940 * characters should be considered the same
941 * @G_NORMALIZE_NFKD: another name for %G_NORMALIZE_ALL
942 * @G_NORMALIZE_ALL_COMPOSE: like %G_NORMALIZE_ALL, but with composed
943 * forms rather than a maximally decomposed form
944 * @G_NORMALIZE_NFKC: another name for %G_NORMALIZE_ALL_COMPOSE
945 *
946 * Defines how a Unicode string is transformed in a canonical
947 * form, standardizing such issues as whether a character with
948 * an accent is represented as a base character and combining
949 * accent or as a single precomposed character. Unicode strings
950 * should generally be normalized before comparing them.
951 */
952typedef enum {
953 G_NORMALIZE_DEFAULT,
954 G_NORMALIZE_NFD = G_NORMALIZE_DEFAULT,
955 G_NORMALIZE_DEFAULT_COMPOSE,
956 G_NORMALIZE_NFC = G_NORMALIZE_DEFAULT_COMPOSE,
957 G_NORMALIZE_ALL,
958 G_NORMALIZE_NFKD = G_NORMALIZE_ALL,
959 G_NORMALIZE_ALL_COMPOSE,
960 G_NORMALIZE_NFKC = G_NORMALIZE_ALL_COMPOSE
961} GNormalizeMode;
962
963GLIB_AVAILABLE_IN_ALL
964gchar *g_utf8_normalize (const gchar *str,
965 gssize len,
966 GNormalizeMode mode) G_GNUC_MALLOC;
967
968GLIB_AVAILABLE_IN_ALL
969gint g_utf8_collate (const gchar *str1,
970 const gchar *str2) G_GNUC_PURE;
971GLIB_AVAILABLE_IN_ALL
972gchar *g_utf8_collate_key (const gchar *str,
973 gssize len) G_GNUC_MALLOC;
974GLIB_AVAILABLE_IN_ALL
975gchar *g_utf8_collate_key_for_filename (const gchar *str,
976 gssize len) G_GNUC_MALLOC;
977
978GLIB_AVAILABLE_IN_2_52
979gchar *g_utf8_make_valid (const gchar *str,
980 gssize len) G_GNUC_MALLOC;
981
982G_END_DECLS
983
984#endif /* __G_UNICODE_H__ */
985