1 /* gunicode.h - Unicode manipulation functions
3 * Copyright (C) 1999, 2000 Tom Tromey
4 * Copyright 2000, 2005 Red Hat, Inc.
6 * SPDX-License-Identifier: LGPL-2.1-or-later
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.
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.
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/>.
22 #ifndef __G_UNICODE_H__
23 #define __G_UNICODE_H__
25 #if !defined (__GLIB_H_INSIDE__) && !defined (GLIB_COMPILATION)
26 #error "Only <glib.h> can be included directly."
29 #include <glib/gerror.h>
30 #include <glib/gtypes.h>
37 * A type which can hold any UTF-32 or UCS-4 character code,
38 * also known as a Unicode code point.
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
44 * To print/scan values of this type as integer, use
45 * %G_GINT32_MODIFIER and/or %G_GUINT32_FORMAT.
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".
57 * sscanf ("U+0041", "U+%06"G_GINT32_FORMAT"X", &c)
58 * g_print ("Read U+%04"G_GINT32_FORMAT"X", c);
61 typedef guint32 gunichar;
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>.
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().
76 * To print/scan values of this type as integer, use
77 * %G_GINT16_MODIFIER and/or %G_GUINT16_FORMAT.
79 typedef guint16 gunichar2;
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)
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).
122 G_UNICODE_UNASSIGNED,
123 G_UNICODE_PRIVATE_USE,
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
153 * G_UNICODE_COMBINING_MARK:
155 * Older name for %G_UNICODE_SPACING_MARK.
157 * Deprecated: 2.30: Use %G_UNICODE_SPACING_MARK.
159 #define G_UNICODE_COMBINING_MARK G_UNICODE_SPACING_MARK GLIB_DEPRECATED_MACRO_IN_2_30_FOR(G_UNICODE_SPACING_MARK)
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
208 * These are the possible line break classifications.
210 * Since new unicode versions may add new types here, applications should be ready
211 * to handle unknown values. They may be regarded as %G_UNICODE_BREAK_UNKNOWN.
213 * See [Unicode Line Breaking Algorithm](http://www.unicode.org/unicode/reports/tr14/).
217 G_UNICODE_BREAK_MANDATORY,
218 G_UNICODE_BREAK_CARRIAGE_RETURN,
219 G_UNICODE_BREAK_LINE_FEED,
220 G_UNICODE_BREAK_COMBINING_MARK,
221 G_UNICODE_BREAK_SURROGATE,
222 G_UNICODE_BREAK_ZERO_WIDTH_SPACE,
223 G_UNICODE_BREAK_INSEPARABLE,
224 G_UNICODE_BREAK_NON_BREAKING_GLUE,
225 G_UNICODE_BREAK_CONTINGENT,
226 G_UNICODE_BREAK_SPACE,
227 G_UNICODE_BREAK_AFTER,
228 G_UNICODE_BREAK_BEFORE,
229 G_UNICODE_BREAK_BEFORE_AND_AFTER,
230 G_UNICODE_BREAK_HYPHEN,
231 G_UNICODE_BREAK_NON_STARTER,
232 G_UNICODE_BREAK_OPEN_PUNCTUATION,
233 G_UNICODE_BREAK_CLOSE_PUNCTUATION,
234 G_UNICODE_BREAK_QUOTATION,
235 G_UNICODE_BREAK_EXCLAMATION,
236 G_UNICODE_BREAK_IDEOGRAPHIC,
237 G_UNICODE_BREAK_NUMERIC,
238 G_UNICODE_BREAK_INFIX_SEPARATOR,
239 G_UNICODE_BREAK_SYMBOL,
240 G_UNICODE_BREAK_ALPHABETIC,
241 G_UNICODE_BREAK_PREFIX,
242 G_UNICODE_BREAK_POSTFIX,
243 G_UNICODE_BREAK_COMPLEX_CONTEXT,
244 G_UNICODE_BREAK_AMBIGUOUS,
245 G_UNICODE_BREAK_UNKNOWN,
246 G_UNICODE_BREAK_NEXT_LINE,
247 G_UNICODE_BREAK_WORD_JOINER,
248 G_UNICODE_BREAK_HANGUL_L_JAMO,
249 G_UNICODE_BREAK_HANGUL_V_JAMO,
250 G_UNICODE_BREAK_HANGUL_T_JAMO,
251 G_UNICODE_BREAK_HANGUL_LV_SYLLABLE,
252 G_UNICODE_BREAK_HANGUL_LVT_SYLLABLE,
253 G_UNICODE_BREAK_CLOSE_PARANTHESIS,
254 G_UNICODE_BREAK_CLOSE_PARENTHESIS GLIB_AVAILABLE_ENUMERATOR_IN_2_70 = G_UNICODE_BREAK_CLOSE_PARANTHESIS,
255 G_UNICODE_BREAK_CONDITIONAL_JAPANESE_STARTER,
256 G_UNICODE_BREAK_HEBREW_LETTER,
257 G_UNICODE_BREAK_REGIONAL_INDICATOR,
258 G_UNICODE_BREAK_EMOJI_BASE,
259 G_UNICODE_BREAK_EMOJI_MODIFIER,
260 G_UNICODE_BREAK_ZERO_WIDTH_JOINER
265 * @G_UNICODE_SCRIPT_INVALID_CODE:
266 * a value never returned from g_unichar_get_script()
267 * @G_UNICODE_SCRIPT_COMMON: a character used by multiple different scripts
268 * @G_UNICODE_SCRIPT_INHERITED: a mark glyph that takes its script from the
269 * base glyph to which it is attached
270 * @G_UNICODE_SCRIPT_ARABIC: Arabic
271 * @G_UNICODE_SCRIPT_ARMENIAN: Armenian
272 * @G_UNICODE_SCRIPT_BENGALI: Bengali
273 * @G_UNICODE_SCRIPT_BOPOMOFO: Bopomofo
274 * @G_UNICODE_SCRIPT_CHEROKEE: Cherokee
275 * @G_UNICODE_SCRIPT_COPTIC: Coptic
276 * @G_UNICODE_SCRIPT_CYRILLIC: Cyrillic
277 * @G_UNICODE_SCRIPT_DESERET: Deseret
278 * @G_UNICODE_SCRIPT_DEVANAGARI: Devanagari
279 * @G_UNICODE_SCRIPT_ETHIOPIC: Ethiopic
280 * @G_UNICODE_SCRIPT_GEORGIAN: Georgian
281 * @G_UNICODE_SCRIPT_GOTHIC: Gothic
282 * @G_UNICODE_SCRIPT_GREEK: Greek
283 * @G_UNICODE_SCRIPT_GUJARATI: Gujarati
284 * @G_UNICODE_SCRIPT_GURMUKHI: Gurmukhi
285 * @G_UNICODE_SCRIPT_HAN: Han
286 * @G_UNICODE_SCRIPT_HANGUL: Hangul
287 * @G_UNICODE_SCRIPT_HEBREW: Hebrew
288 * @G_UNICODE_SCRIPT_HIRAGANA: Hiragana
289 * @G_UNICODE_SCRIPT_KANNADA: Kannada
290 * @G_UNICODE_SCRIPT_KATAKANA: Katakana
291 * @G_UNICODE_SCRIPT_KHMER: Khmer
292 * @G_UNICODE_SCRIPT_LAO: Lao
293 * @G_UNICODE_SCRIPT_LATIN: Latin
294 * @G_UNICODE_SCRIPT_MALAYALAM: Malayalam
295 * @G_UNICODE_SCRIPT_MONGOLIAN: Mongolian
296 * @G_UNICODE_SCRIPT_MYANMAR: Myanmar
297 * @G_UNICODE_SCRIPT_OGHAM: Ogham
298 * @G_UNICODE_SCRIPT_OLD_ITALIC: Old Italic
299 * @G_UNICODE_SCRIPT_ORIYA: Oriya
300 * @G_UNICODE_SCRIPT_RUNIC: Runic
301 * @G_UNICODE_SCRIPT_SINHALA: Sinhala
302 * @G_UNICODE_SCRIPT_SYRIAC: Syriac
303 * @G_UNICODE_SCRIPT_TAMIL: Tamil
304 * @G_UNICODE_SCRIPT_TELUGU: Telugu
305 * @G_UNICODE_SCRIPT_THAANA: Thaana
306 * @G_UNICODE_SCRIPT_THAI: Thai
307 * @G_UNICODE_SCRIPT_TIBETAN: Tibetan
308 * @G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL:
309 * Canadian Aboriginal
310 * @G_UNICODE_SCRIPT_YI: Yi
311 * @G_UNICODE_SCRIPT_TAGALOG: Tagalog
312 * @G_UNICODE_SCRIPT_HANUNOO: Hanunoo
313 * @G_UNICODE_SCRIPT_BUHID: Buhid
314 * @G_UNICODE_SCRIPT_TAGBANWA: Tagbanwa
315 * @G_UNICODE_SCRIPT_BRAILLE: Braille
316 * @G_UNICODE_SCRIPT_CYPRIOT: Cypriot
317 * @G_UNICODE_SCRIPT_LIMBU: Limbu
318 * @G_UNICODE_SCRIPT_OSMANYA: Osmanya
319 * @G_UNICODE_SCRIPT_SHAVIAN: Shavian
320 * @G_UNICODE_SCRIPT_LINEAR_B: Linear B
321 * @G_UNICODE_SCRIPT_TAI_LE: Tai Le
322 * @G_UNICODE_SCRIPT_UGARITIC: Ugaritic
323 * @G_UNICODE_SCRIPT_NEW_TAI_LUE:
325 * @G_UNICODE_SCRIPT_BUGINESE: Buginese
326 * @G_UNICODE_SCRIPT_GLAGOLITIC: Glagolitic
327 * @G_UNICODE_SCRIPT_TIFINAGH: Tifinagh
328 * @G_UNICODE_SCRIPT_SYLOTI_NAGRI:
330 * @G_UNICODE_SCRIPT_OLD_PERSIAN:
332 * @G_UNICODE_SCRIPT_KHAROSHTHI: Kharoshthi
333 * @G_UNICODE_SCRIPT_UNKNOWN: an unassigned code point
334 * @G_UNICODE_SCRIPT_BALINESE: Balinese
335 * @G_UNICODE_SCRIPT_CUNEIFORM: Cuneiform
336 * @G_UNICODE_SCRIPT_PHOENICIAN: Phoenician
337 * @G_UNICODE_SCRIPT_PHAGS_PA: Phags-pa
338 * @G_UNICODE_SCRIPT_NKO: N'Ko
339 * @G_UNICODE_SCRIPT_KAYAH_LI: Kayah Li. Since 2.16.3
340 * @G_UNICODE_SCRIPT_LEPCHA: Lepcha. Since 2.16.3
341 * @G_UNICODE_SCRIPT_REJANG: Rejang. Since 2.16.3
342 * @G_UNICODE_SCRIPT_SUNDANESE: Sundanese. Since 2.16.3
343 * @G_UNICODE_SCRIPT_SAURASHTRA: Saurashtra. Since 2.16.3
344 * @G_UNICODE_SCRIPT_CHAM: Cham. Since 2.16.3
345 * @G_UNICODE_SCRIPT_OL_CHIKI: Ol Chiki. Since 2.16.3
346 * @G_UNICODE_SCRIPT_VAI: Vai. Since 2.16.3
347 * @G_UNICODE_SCRIPT_CARIAN: Carian. Since 2.16.3
348 * @G_UNICODE_SCRIPT_LYCIAN: Lycian. Since 2.16.3
349 * @G_UNICODE_SCRIPT_LYDIAN: Lydian. Since 2.16.3
350 * @G_UNICODE_SCRIPT_AVESTAN: Avestan. Since 2.26
351 * @G_UNICODE_SCRIPT_BAMUM: Bamum. Since 2.26
352 * @G_UNICODE_SCRIPT_EGYPTIAN_HIEROGLYPHS:
353 * Egyptian Hieroglpyhs. Since 2.26
354 * @G_UNICODE_SCRIPT_IMPERIAL_ARAMAIC:
355 * Imperial Aramaic. Since 2.26
356 * @G_UNICODE_SCRIPT_INSCRIPTIONAL_PAHLAVI:
357 * Inscriptional Pahlavi. Since 2.26
358 * @G_UNICODE_SCRIPT_INSCRIPTIONAL_PARTHIAN:
359 * Inscriptional Parthian. Since 2.26
360 * @G_UNICODE_SCRIPT_JAVANESE: Javanese. Since 2.26
361 * @G_UNICODE_SCRIPT_KAITHI: Kaithi. Since 2.26
362 * @G_UNICODE_SCRIPT_LISU: Lisu. Since 2.26
363 * @G_UNICODE_SCRIPT_MEETEI_MAYEK:
364 * Meetei Mayek. Since 2.26
365 * @G_UNICODE_SCRIPT_OLD_SOUTH_ARABIAN:
366 * Old South Arabian. Since 2.26
367 * @G_UNICODE_SCRIPT_OLD_TURKIC: Old Turkic. Since 2.28
368 * @G_UNICODE_SCRIPT_SAMARITAN: Samaritan. Since 2.26
369 * @G_UNICODE_SCRIPT_TAI_THAM: Tai Tham. Since 2.26
370 * @G_UNICODE_SCRIPT_TAI_VIET: Tai Viet. Since 2.26
371 * @G_UNICODE_SCRIPT_BATAK: Batak. Since 2.28
372 * @G_UNICODE_SCRIPT_BRAHMI: Brahmi. Since 2.28
373 * @G_UNICODE_SCRIPT_MANDAIC: Mandaic. Since 2.28
374 * @G_UNICODE_SCRIPT_CHAKMA: Chakma. Since: 2.32
375 * @G_UNICODE_SCRIPT_MEROITIC_CURSIVE: Meroitic Cursive. Since: 2.32
376 * @G_UNICODE_SCRIPT_MEROITIC_HIEROGLYPHS: Meroitic Hieroglyphs. Since: 2.32
377 * @G_UNICODE_SCRIPT_MIAO: Miao. Since: 2.32
378 * @G_UNICODE_SCRIPT_SHARADA: Sharada. Since: 2.32
379 * @G_UNICODE_SCRIPT_SORA_SOMPENG: Sora Sompeng. Since: 2.32
380 * @G_UNICODE_SCRIPT_TAKRI: Takri. Since: 2.32
381 * @G_UNICODE_SCRIPT_BASSA_VAH: Bassa. Since: 2.42
382 * @G_UNICODE_SCRIPT_CAUCASIAN_ALBANIAN: Caucasian Albanian. Since: 2.42
383 * @G_UNICODE_SCRIPT_DUPLOYAN: Duployan. Since: 2.42
384 * @G_UNICODE_SCRIPT_ELBASAN: Elbasan. Since: 2.42
385 * @G_UNICODE_SCRIPT_GRANTHA: Grantha. Since: 2.42
386 * @G_UNICODE_SCRIPT_KHOJKI: Kjohki. Since: 2.42
387 * @G_UNICODE_SCRIPT_KHUDAWADI: Khudawadi, Sindhi. Since: 2.42
388 * @G_UNICODE_SCRIPT_LINEAR_A: Linear A. Since: 2.42
389 * @G_UNICODE_SCRIPT_MAHAJANI: Mahajani. Since: 2.42
390 * @G_UNICODE_SCRIPT_MANICHAEAN: Manichaean. Since: 2.42
391 * @G_UNICODE_SCRIPT_MENDE_KIKAKUI: Mende Kikakui. Since: 2.42
392 * @G_UNICODE_SCRIPT_MODI: Modi. Since: 2.42
393 * @G_UNICODE_SCRIPT_MRO: Mro. Since: 2.42
394 * @G_UNICODE_SCRIPT_NABATAEAN: Nabataean. Since: 2.42
395 * @G_UNICODE_SCRIPT_OLD_NORTH_ARABIAN: Old North Arabian. Since: 2.42
396 * @G_UNICODE_SCRIPT_OLD_PERMIC: Old Permic. Since: 2.42
397 * @G_UNICODE_SCRIPT_PAHAWH_HMONG: Pahawh Hmong. Since: 2.42
398 * @G_UNICODE_SCRIPT_PALMYRENE: Palmyrene. Since: 2.42
399 * @G_UNICODE_SCRIPT_PAU_CIN_HAU: Pau Cin Hau. Since: 2.42
400 * @G_UNICODE_SCRIPT_PSALTER_PAHLAVI: Psalter Pahlavi. Since: 2.42
401 * @G_UNICODE_SCRIPT_SIDDHAM: Siddham. Since: 2.42
402 * @G_UNICODE_SCRIPT_TIRHUTA: Tirhuta. Since: 2.42
403 * @G_UNICODE_SCRIPT_WARANG_CITI: Warang Citi. Since: 2.42
404 * @G_UNICODE_SCRIPT_AHOM: Ahom. Since: 2.48
405 * @G_UNICODE_SCRIPT_ANATOLIAN_HIEROGLYPHS: Anatolian Hieroglyphs. Since: 2.48
406 * @G_UNICODE_SCRIPT_HATRAN: Hatran. Since: 2.48
407 * @G_UNICODE_SCRIPT_MULTANI: Multani. Since: 2.48
408 * @G_UNICODE_SCRIPT_OLD_HUNGARIAN: Old Hungarian. Since: 2.48
409 * @G_UNICODE_SCRIPT_SIGNWRITING: Signwriting. Since: 2.48
410 * @G_UNICODE_SCRIPT_ADLAM: Adlam. Since: 2.50
411 * @G_UNICODE_SCRIPT_BHAIKSUKI: Bhaiksuki. Since: 2.50
412 * @G_UNICODE_SCRIPT_MARCHEN: Marchen. Since: 2.50
413 * @G_UNICODE_SCRIPT_NEWA: Newa. Since: 2.50
414 * @G_UNICODE_SCRIPT_OSAGE: Osage. Since: 2.50
415 * @G_UNICODE_SCRIPT_TANGUT: Tangut. Since: 2.50
416 * @G_UNICODE_SCRIPT_MASARAM_GONDI: Masaram Gondi. Since: 2.54
417 * @G_UNICODE_SCRIPT_NUSHU: Nushu. Since: 2.54
418 * @G_UNICODE_SCRIPT_SOYOMBO: Soyombo. Since: 2.54
419 * @G_UNICODE_SCRIPT_ZANABAZAR_SQUARE: Zanabazar Square. Since: 2.54
420 * @G_UNICODE_SCRIPT_DOGRA: Dogra. Since: 2.58
421 * @G_UNICODE_SCRIPT_GUNJALA_GONDI: Gunjala Gondi. Since: 2.58
422 * @G_UNICODE_SCRIPT_HANIFI_ROHINGYA: Hanifi Rohingya. Since: 2.58
423 * @G_UNICODE_SCRIPT_MAKASAR: Makasar. Since: 2.58
424 * @G_UNICODE_SCRIPT_MEDEFAIDRIN: Medefaidrin. Since: 2.58
425 * @G_UNICODE_SCRIPT_OLD_SOGDIAN: Old Sogdian. Since: 2.58
426 * @G_UNICODE_SCRIPT_SOGDIAN: Sogdian. Since: 2.58
427 * @G_UNICODE_SCRIPT_ELYMAIC: Elym. Since: 2.62
428 * @G_UNICODE_SCRIPT_NANDINAGARI: Nand. Since: 2.62
429 * @G_UNICODE_SCRIPT_NYIAKENG_PUACHUE_HMONG: Rohg. Since: 2.62
430 * @G_UNICODE_SCRIPT_WANCHO: Wcho. Since: 2.62
431 * @G_UNICODE_SCRIPT_CHORASMIAN: Chorasmian. Since: 2.66
432 * @G_UNICODE_SCRIPT_DIVES_AKURU: Dives Akuru. Since: 2.66
433 * @G_UNICODE_SCRIPT_KHITAN_SMALL_SCRIPT: Khitan small script. Since: 2.66
434 * @G_UNICODE_SCRIPT_YEZIDI: Yezidi. Since: 2.66
435 * @G_UNICODE_SCRIPT_CYPRO_MINOAN: Cypro-Minoan. Since: 2.72
436 * @G_UNICODE_SCRIPT_OLD_UYGHUR: Old Uyghur. Since: 2.72
437 * @G_UNICODE_SCRIPT_TANGSA: Tangsa. Since: 2.72
438 * @G_UNICODE_SCRIPT_TOTO: Toto. Since: 2.72
439 * @G_UNICODE_SCRIPT_VITHKUQI: Vithkuqi. Since: 2.72
440 * @G_UNICODE_SCRIPT_MATH: Mathematical notation. Since: 2.72
441 * @G_UNICODE_SCRIPT_KAWI: Kawi. Since 2.74
442 * @G_UNICODE_SCRIPT_NAG_MUNDARI: Nag Mundari. Since 2.74
444 * The #GUnicodeScript enumeration identifies different writing
445 * systems. The values correspond to the names as defined in the
446 * Unicode standard. The enumeration has been added in GLib 2.14,
447 * and is interchangeable with #PangoScript.
449 * Note that new types may be added in the future. Applications
450 * should be ready to handle unknown values.
451 * See [Unicode Standard Annex #24: Script names](http://www.unicode.org/reports/tr24/).
454 { /* ISO 15924 code */
455 G_UNICODE_SCRIPT_INVALID_CODE = -1,
456 G_UNICODE_SCRIPT_COMMON = 0, /* Zyyy */
457 G_UNICODE_SCRIPT_INHERITED, /* Zinh (Qaai) */
458 G_UNICODE_SCRIPT_ARABIC, /* Arab */
459 G_UNICODE_SCRIPT_ARMENIAN, /* Armn */
460 G_UNICODE_SCRIPT_BENGALI, /* Beng */
461 G_UNICODE_SCRIPT_BOPOMOFO, /* Bopo */
462 G_UNICODE_SCRIPT_CHEROKEE, /* Cher */
463 G_UNICODE_SCRIPT_COPTIC, /* Copt (Qaac) */
464 G_UNICODE_SCRIPT_CYRILLIC, /* Cyrl (Cyrs) */
465 G_UNICODE_SCRIPT_DESERET, /* Dsrt */
466 G_UNICODE_SCRIPT_DEVANAGARI, /* Deva */
467 G_UNICODE_SCRIPT_ETHIOPIC, /* Ethi */
468 G_UNICODE_SCRIPT_GEORGIAN, /* Geor (Geon, Geoa) */
469 G_UNICODE_SCRIPT_GOTHIC, /* Goth */
470 G_UNICODE_SCRIPT_GREEK, /* Grek */
471 G_UNICODE_SCRIPT_GUJARATI, /* Gujr */
472 G_UNICODE_SCRIPT_GURMUKHI, /* Guru */
473 G_UNICODE_SCRIPT_HAN, /* Hani */
474 G_UNICODE_SCRIPT_HANGUL, /* Hang */
475 G_UNICODE_SCRIPT_HEBREW, /* Hebr */
476 G_UNICODE_SCRIPT_HIRAGANA, /* Hira */
477 G_UNICODE_SCRIPT_KANNADA, /* Knda */
478 G_UNICODE_SCRIPT_KATAKANA, /* Kana */
479 G_UNICODE_SCRIPT_KHMER, /* Khmr */
480 G_UNICODE_SCRIPT_LAO, /* Laoo */
481 G_UNICODE_SCRIPT_LATIN, /* Latn (Latf, Latg) */
482 G_UNICODE_SCRIPT_MALAYALAM, /* Mlym */
483 G_UNICODE_SCRIPT_MONGOLIAN, /* Mong */
484 G_UNICODE_SCRIPT_MYANMAR, /* Mymr */
485 G_UNICODE_SCRIPT_OGHAM, /* Ogam */
486 G_UNICODE_SCRIPT_OLD_ITALIC, /* Ital */
487 G_UNICODE_SCRIPT_ORIYA, /* Orya */
488 G_UNICODE_SCRIPT_RUNIC, /* Runr */
489 G_UNICODE_SCRIPT_SINHALA, /* Sinh */
490 G_UNICODE_SCRIPT_SYRIAC, /* Syrc (Syrj, Syrn, Syre) */
491 G_UNICODE_SCRIPT_TAMIL, /* Taml */
492 G_UNICODE_SCRIPT_TELUGU, /* Telu */
493 G_UNICODE_SCRIPT_THAANA, /* Thaa */
494 G_UNICODE_SCRIPT_THAI, /* Thai */
495 G_UNICODE_SCRIPT_TIBETAN, /* Tibt */
496 G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL, /* Cans */
497 G_UNICODE_SCRIPT_YI, /* Yiii */
498 G_UNICODE_SCRIPT_TAGALOG, /* Tglg */
499 G_UNICODE_SCRIPT_HANUNOO, /* Hano */
500 G_UNICODE_SCRIPT_BUHID, /* Buhd */
501 G_UNICODE_SCRIPT_TAGBANWA, /* Tagb */
503 /* Unicode-4.0 additions */
504 G_UNICODE_SCRIPT_BRAILLE, /* Brai */
505 G_UNICODE_SCRIPT_CYPRIOT, /* Cprt */
506 G_UNICODE_SCRIPT_LIMBU, /* Limb */
507 G_UNICODE_SCRIPT_OSMANYA, /* Osma */
508 G_UNICODE_SCRIPT_SHAVIAN, /* Shaw */
509 G_UNICODE_SCRIPT_LINEAR_B, /* Linb */
510 G_UNICODE_SCRIPT_TAI_LE, /* Tale */
511 G_UNICODE_SCRIPT_UGARITIC, /* Ugar */
513 /* Unicode-4.1 additions */
514 G_UNICODE_SCRIPT_NEW_TAI_LUE, /* Talu */
515 G_UNICODE_SCRIPT_BUGINESE, /* Bugi */
516 G_UNICODE_SCRIPT_GLAGOLITIC, /* Glag */
517 G_UNICODE_SCRIPT_TIFINAGH, /* Tfng */
518 G_UNICODE_SCRIPT_SYLOTI_NAGRI, /* Sylo */
519 G_UNICODE_SCRIPT_OLD_PERSIAN, /* Xpeo */
520 G_UNICODE_SCRIPT_KHAROSHTHI, /* Khar */
522 /* Unicode-5.0 additions */
523 G_UNICODE_SCRIPT_UNKNOWN, /* Zzzz */
524 G_UNICODE_SCRIPT_BALINESE, /* Bali */
525 G_UNICODE_SCRIPT_CUNEIFORM, /* Xsux */
526 G_UNICODE_SCRIPT_PHOENICIAN, /* Phnx */
527 G_UNICODE_SCRIPT_PHAGS_PA, /* Phag */
528 G_UNICODE_SCRIPT_NKO, /* Nkoo */
530 /* Unicode-5.1 additions */
531 G_UNICODE_SCRIPT_KAYAH_LI, /* Kali */
532 G_UNICODE_SCRIPT_LEPCHA, /* Lepc */
533 G_UNICODE_SCRIPT_REJANG, /* Rjng */
534 G_UNICODE_SCRIPT_SUNDANESE, /* Sund */
535 G_UNICODE_SCRIPT_SAURASHTRA, /* Saur */
536 G_UNICODE_SCRIPT_CHAM, /* Cham */
537 G_UNICODE_SCRIPT_OL_CHIKI, /* Olck */
538 G_UNICODE_SCRIPT_VAI, /* Vaii */
539 G_UNICODE_SCRIPT_CARIAN, /* Cari */
540 G_UNICODE_SCRIPT_LYCIAN, /* Lyci */
541 G_UNICODE_SCRIPT_LYDIAN, /* Lydi */
543 /* Unicode-5.2 additions */
544 G_UNICODE_SCRIPT_AVESTAN, /* Avst */
545 G_UNICODE_SCRIPT_BAMUM, /* Bamu */
546 G_UNICODE_SCRIPT_EGYPTIAN_HIEROGLYPHS, /* Egyp */
547 G_UNICODE_SCRIPT_IMPERIAL_ARAMAIC, /* Armi */
548 G_UNICODE_SCRIPT_INSCRIPTIONAL_PAHLAVI, /* Phli */
549 G_UNICODE_SCRIPT_INSCRIPTIONAL_PARTHIAN, /* Prti */
550 G_UNICODE_SCRIPT_JAVANESE, /* Java */
551 G_UNICODE_SCRIPT_KAITHI, /* Kthi */
552 G_UNICODE_SCRIPT_LISU, /* Lisu */
553 G_UNICODE_SCRIPT_MEETEI_MAYEK, /* Mtei */
554 G_UNICODE_SCRIPT_OLD_SOUTH_ARABIAN, /* Sarb */
555 G_UNICODE_SCRIPT_OLD_TURKIC, /* Orkh */
556 G_UNICODE_SCRIPT_SAMARITAN, /* Samr */
557 G_UNICODE_SCRIPT_TAI_THAM, /* Lana */
558 G_UNICODE_SCRIPT_TAI_VIET, /* Tavt */
560 /* Unicode-6.0 additions */
561 G_UNICODE_SCRIPT_BATAK, /* Batk */
562 G_UNICODE_SCRIPT_BRAHMI, /* Brah */
563 G_UNICODE_SCRIPT_MANDAIC, /* Mand */
565 /* Unicode-6.1 additions */
566 G_UNICODE_SCRIPT_CHAKMA, /* Cakm */
567 G_UNICODE_SCRIPT_MEROITIC_CURSIVE, /* Merc */
568 G_UNICODE_SCRIPT_MEROITIC_HIEROGLYPHS, /* Mero */
569 G_UNICODE_SCRIPT_MIAO, /* Plrd */
570 G_UNICODE_SCRIPT_SHARADA, /* Shrd */
571 G_UNICODE_SCRIPT_SORA_SOMPENG, /* Sora */
572 G_UNICODE_SCRIPT_TAKRI, /* Takr */
574 /* Unicode 7.0 additions */
575 G_UNICODE_SCRIPT_BASSA_VAH, /* Bass */
576 G_UNICODE_SCRIPT_CAUCASIAN_ALBANIAN, /* Aghb */
577 G_UNICODE_SCRIPT_DUPLOYAN, /* Dupl */
578 G_UNICODE_SCRIPT_ELBASAN, /* Elba */
579 G_UNICODE_SCRIPT_GRANTHA, /* Gran */
580 G_UNICODE_SCRIPT_KHOJKI, /* Khoj */
581 G_UNICODE_SCRIPT_KHUDAWADI, /* Sind */
582 G_UNICODE_SCRIPT_LINEAR_A, /* Lina */
583 G_UNICODE_SCRIPT_MAHAJANI, /* Mahj */
584 G_UNICODE_SCRIPT_MANICHAEAN, /* Mani */
585 G_UNICODE_SCRIPT_MENDE_KIKAKUI, /* Mend */
586 G_UNICODE_SCRIPT_MODI, /* Modi */
587 G_UNICODE_SCRIPT_MRO, /* Mroo */
588 G_UNICODE_SCRIPT_NABATAEAN, /* Nbat */
589 G_UNICODE_SCRIPT_OLD_NORTH_ARABIAN, /* Narb */
590 G_UNICODE_SCRIPT_OLD_PERMIC, /* Perm */
591 G_UNICODE_SCRIPT_PAHAWH_HMONG, /* Hmng */
592 G_UNICODE_SCRIPT_PALMYRENE, /* Palm */
593 G_UNICODE_SCRIPT_PAU_CIN_HAU, /* Pauc */
594 G_UNICODE_SCRIPT_PSALTER_PAHLAVI, /* Phlp */
595 G_UNICODE_SCRIPT_SIDDHAM, /* Sidd */
596 G_UNICODE_SCRIPT_TIRHUTA, /* Tirh */
597 G_UNICODE_SCRIPT_WARANG_CITI, /* Wara */
599 /* Unicode 8.0 additions */
600 G_UNICODE_SCRIPT_AHOM, /* Ahom */
601 G_UNICODE_SCRIPT_ANATOLIAN_HIEROGLYPHS, /* Hluw */
602 G_UNICODE_SCRIPT_HATRAN, /* Hatr */
603 G_UNICODE_SCRIPT_MULTANI, /* Mult */
604 G_UNICODE_SCRIPT_OLD_HUNGARIAN, /* Hung */
605 G_UNICODE_SCRIPT_SIGNWRITING, /* Sgnw */
607 /* Unicode 9.0 additions */
608 G_UNICODE_SCRIPT_ADLAM, /* Adlm */
609 G_UNICODE_SCRIPT_BHAIKSUKI, /* Bhks */
610 G_UNICODE_SCRIPT_MARCHEN, /* Marc */
611 G_UNICODE_SCRIPT_NEWA, /* Newa */
612 G_UNICODE_SCRIPT_OSAGE, /* Osge */
613 G_UNICODE_SCRIPT_TANGUT, /* Tang */
615 /* Unicode 10.0 additions */
616 G_UNICODE_SCRIPT_MASARAM_GONDI, /* Gonm */
617 G_UNICODE_SCRIPT_NUSHU, /* Nshu */
618 G_UNICODE_SCRIPT_SOYOMBO, /* Soyo */
619 G_UNICODE_SCRIPT_ZANABAZAR_SQUARE, /* Zanb */
621 /* Unicode 11.0 additions */
622 G_UNICODE_SCRIPT_DOGRA, /* Dogr */
623 G_UNICODE_SCRIPT_GUNJALA_GONDI, /* Gong */
624 G_UNICODE_SCRIPT_HANIFI_ROHINGYA, /* Rohg */
625 G_UNICODE_SCRIPT_MAKASAR, /* Maka */
626 G_UNICODE_SCRIPT_MEDEFAIDRIN, /* Medf */
627 G_UNICODE_SCRIPT_OLD_SOGDIAN, /* Sogo */
628 G_UNICODE_SCRIPT_SOGDIAN, /* Sogd */
630 /* Unicode 12.0 additions */
631 G_UNICODE_SCRIPT_ELYMAIC, /* Elym */
632 G_UNICODE_SCRIPT_NANDINAGARI, /* Nand */
633 G_UNICODE_SCRIPT_NYIAKENG_PUACHUE_HMONG, /* Rohg */
634 G_UNICODE_SCRIPT_WANCHO, /* Wcho */
636 /* Unicode 13.0 additions */
637 G_UNICODE_SCRIPT_CHORASMIAN, /* Chrs */
638 G_UNICODE_SCRIPT_DIVES_AKURU, /* Diak */
639 G_UNICODE_SCRIPT_KHITAN_SMALL_SCRIPT, /* Kits */
640 G_UNICODE_SCRIPT_YEZIDI, /* Yezi */
642 /* Unicode 14.0 additions */
643 G_UNICODE_SCRIPT_CYPRO_MINOAN, /* Cpmn */
644 G_UNICODE_SCRIPT_OLD_UYGHUR, /* Ougr */
645 G_UNICODE_SCRIPT_TANGSA, /* Tnsa */
646 G_UNICODE_SCRIPT_TOTO, /* Toto */
647 G_UNICODE_SCRIPT_VITHKUQI, /* Vith */
649 /* not really a Unicode script, but part of ISO 15924 */
650 G_UNICODE_SCRIPT_MATH, /* Zmth */
652 /* Unicode 15.0 additions */
653 G_UNICODE_SCRIPT_KAWI GLIB_AVAILABLE_ENUMERATOR_IN_2_74, /* Kawi */
654 G_UNICODE_SCRIPT_NAG_MUNDARI GLIB_AVAILABLE_ENUMERATOR_IN_2_74, /* Nag Mundari */
657 GLIB_AVAILABLE_IN_ALL
658 guint32 g_unicode_script_to_iso15924 (GUnicodeScript script);
659 GLIB_AVAILABLE_IN_ALL
660 GUnicodeScript g_unicode_script_from_iso15924 (guint32 iso15924);
662 /* These are all analogs of the <ctype.h> functions.
664 GLIB_AVAILABLE_IN_ALL
665 gboolean g_unichar_isalnum (gunichar c) G_GNUC_CONST;
666 GLIB_AVAILABLE_IN_ALL
667 gboolean g_unichar_isalpha (gunichar c) G_GNUC_CONST;
668 GLIB_AVAILABLE_IN_ALL
669 gboolean g_unichar_iscntrl (gunichar c) G_GNUC_CONST;
670 GLIB_AVAILABLE_IN_ALL
671 gboolean g_unichar_isdigit (gunichar c) G_GNUC_CONST;
672 GLIB_AVAILABLE_IN_ALL
673 gboolean g_unichar_isgraph (gunichar c) G_GNUC_CONST;
674 GLIB_AVAILABLE_IN_ALL
675 gboolean g_unichar_islower (gunichar c) G_GNUC_CONST;
676 GLIB_AVAILABLE_IN_ALL
677 gboolean g_unichar_isprint (gunichar c) G_GNUC_CONST;
678 GLIB_AVAILABLE_IN_ALL
679 gboolean g_unichar_ispunct (gunichar c) G_GNUC_CONST;
680 GLIB_AVAILABLE_IN_ALL
681 gboolean g_unichar_isspace (gunichar c) G_GNUC_CONST;
682 GLIB_AVAILABLE_IN_ALL
683 gboolean g_unichar_isupper (gunichar c) G_GNUC_CONST;
684 GLIB_AVAILABLE_IN_ALL
685 gboolean g_unichar_isxdigit (gunichar c) G_GNUC_CONST;
686 GLIB_AVAILABLE_IN_ALL
687 gboolean g_unichar_istitle (gunichar c) G_GNUC_CONST;
688 GLIB_AVAILABLE_IN_ALL
689 gboolean g_unichar_isdefined (gunichar c) G_GNUC_CONST;
690 GLIB_AVAILABLE_IN_ALL
691 gboolean g_unichar_iswide (gunichar c) G_GNUC_CONST;
692 GLIB_AVAILABLE_IN_ALL
693 gboolean g_unichar_iswide_cjk(gunichar c) G_GNUC_CONST;
694 GLIB_AVAILABLE_IN_ALL
695 gboolean g_unichar_iszerowidth(gunichar c) G_GNUC_CONST;
696 GLIB_AVAILABLE_IN_ALL
697 gboolean g_unichar_ismark (gunichar c) G_GNUC_CONST;
699 /* More <ctype.h> functions. These convert between the three cases.
700 * See the Unicode book to understand title case. */
701 GLIB_AVAILABLE_IN_ALL
702 gunichar g_unichar_toupper (gunichar c) G_GNUC_CONST;
703 GLIB_AVAILABLE_IN_ALL
704 gunichar g_unichar_tolower (gunichar c) G_GNUC_CONST;
705 GLIB_AVAILABLE_IN_ALL
706 gunichar g_unichar_totitle (gunichar c) G_GNUC_CONST;
708 /* If C is a digit (according to 'g_unichar_isdigit'), then return its
709 numeric value. Otherwise return -1. */
710 GLIB_AVAILABLE_IN_ALL
711 gint g_unichar_digit_value (gunichar c) G_GNUC_CONST;
713 GLIB_AVAILABLE_IN_ALL
714 gint g_unichar_xdigit_value (gunichar c) G_GNUC_CONST;
716 /* Return the Unicode character type of a given character. */
717 GLIB_AVAILABLE_IN_ALL
718 GUnicodeType g_unichar_type (gunichar c) G_GNUC_CONST;
720 /* Return the line break property for a given character */
721 GLIB_AVAILABLE_IN_ALL
722 GUnicodeBreakType g_unichar_break_type (gunichar c) G_GNUC_CONST;
724 /* Returns the combining class for a given character */
725 GLIB_AVAILABLE_IN_ALL
726 gint g_unichar_combining_class (gunichar uc) G_GNUC_CONST;
728 GLIB_AVAILABLE_IN_ALL
729 gboolean g_unichar_get_mirror_char (gunichar ch,
730 gunichar *mirrored_ch);
732 GLIB_AVAILABLE_IN_ALL
733 GUnicodeScript g_unichar_get_script (gunichar ch) G_GNUC_CONST;
735 /* Validate a Unicode character */
736 GLIB_AVAILABLE_IN_ALL
737 gboolean g_unichar_validate (gunichar ch) G_GNUC_CONST;
739 /* Pairwise canonical compose/decompose */
740 GLIB_AVAILABLE_IN_ALL
741 gboolean g_unichar_compose (gunichar a,
744 GLIB_AVAILABLE_IN_ALL
745 gboolean g_unichar_decompose (gunichar ch,
749 GLIB_AVAILABLE_IN_ALL
750 gsize g_unichar_fully_decompose (gunichar ch,
756 * G_UNICHAR_MAX_DECOMPOSITION_LENGTH:
758 * The maximum length (in codepoints) of a compatibility or canonical
759 * decomposition of a single Unicode character.
761 * This is as defined by Unicode 6.1.
765 #define G_UNICHAR_MAX_DECOMPOSITION_LENGTH 18 /* codepoints */
767 /* Compute canonical ordering of a string in-place. This rearranges
768 decomposed characters in the string according to their combining
769 classes. See the Unicode manual for more information. */
770 GLIB_AVAILABLE_IN_ALL
771 void g_unicode_canonical_ordering (gunichar *string,
775 GLIB_DEPRECATED_IN_2_30
776 gunichar *g_unicode_canonical_decomposition (gunichar ch,
777 gsize *result_len) G_GNUC_MALLOC;
779 /* Array of skip-bytes-per-initial character.
781 GLIB_VAR const gchar * const g_utf8_skip;
785 * @p: Pointer to the start of a valid UTF-8 character
787 * Skips to the next character in a UTF-8 string.
789 * The string must be valid; this macro is as fast as possible, and has
792 * You would use this macro to iterate over a string character by character.
794 * The macro returns the start of the next UTF-8 character.
796 * Before using this macro, use g_utf8_validate() to validate strings
797 * that may contain invalid UTF-8.
799 #define g_utf8_next_char(p) (char *)((p) + g_utf8_skip[*(const guchar *)(p)])
801 GLIB_AVAILABLE_IN_ALL
802 gunichar g_utf8_get_char (const gchar *p) G_GNUC_PURE;
803 GLIB_AVAILABLE_IN_ALL
804 gunichar g_utf8_get_char_validated (const gchar *p,
805 gssize max_len) G_GNUC_PURE;
807 GLIB_AVAILABLE_IN_ALL
808 gchar* g_utf8_offset_to_pointer (const gchar *str,
809 glong offset) G_GNUC_PURE;
810 GLIB_AVAILABLE_IN_ALL
811 glong g_utf8_pointer_to_offset (const gchar *str,
812 const gchar *pos) G_GNUC_PURE;
813 GLIB_AVAILABLE_IN_ALL
814 gchar* g_utf8_prev_char (const gchar *p) G_GNUC_PURE;
815 GLIB_AVAILABLE_IN_ALL
816 gchar* g_utf8_find_next_char (const gchar *p,
817 const gchar *end) G_GNUC_PURE;
818 GLIB_AVAILABLE_IN_ALL
819 gchar* g_utf8_find_prev_char (const gchar *str,
820 const gchar *p) G_GNUC_PURE;
822 GLIB_AVAILABLE_IN_ALL
823 glong g_utf8_strlen (const gchar *p,
824 gssize max) G_GNUC_PURE;
826 GLIB_AVAILABLE_IN_2_30
827 gchar *g_utf8_substring (const gchar *str,
829 glong end_pos) G_GNUC_MALLOC;
831 GLIB_AVAILABLE_IN_ALL
832 gchar *g_utf8_strncpy (gchar *dest,
836 /* Find the UTF-8 character corresponding to ch, in string p. These
837 functions are equivalants to strchr and strrchr */
838 GLIB_AVAILABLE_IN_ALL
839 gchar* g_utf8_strchr (const gchar *p,
842 GLIB_AVAILABLE_IN_ALL
843 gchar* g_utf8_strrchr (const gchar *p,
846 GLIB_AVAILABLE_IN_ALL
847 gchar* g_utf8_strreverse (const gchar *str,
850 GLIB_AVAILABLE_IN_ALL
851 gunichar2 *g_utf8_to_utf16 (const gchar *str,
854 glong *items_written,
855 GError **error) G_GNUC_MALLOC;
856 GLIB_AVAILABLE_IN_ALL
857 gunichar * g_utf8_to_ucs4 (const gchar *str,
860 glong *items_written,
861 GError **error) G_GNUC_MALLOC;
862 GLIB_AVAILABLE_IN_ALL
863 gunichar * g_utf8_to_ucs4_fast (const gchar *str,
865 glong *items_written) G_GNUC_MALLOC;
866 GLIB_AVAILABLE_IN_ALL
867 gunichar * g_utf16_to_ucs4 (const gunichar2 *str,
870 glong *items_written,
871 GError **error) G_GNUC_MALLOC;
872 GLIB_AVAILABLE_IN_ALL
873 gchar* g_utf16_to_utf8 (const gunichar2 *str,
876 glong *items_written,
877 GError **error) G_GNUC_MALLOC;
878 GLIB_AVAILABLE_IN_ALL
879 gunichar2 *g_ucs4_to_utf16 (const gunichar *str,
882 glong *items_written,
883 GError **error) G_GNUC_MALLOC;
884 GLIB_AVAILABLE_IN_ALL
885 gchar* g_ucs4_to_utf8 (const gunichar *str,
888 glong *items_written,
889 GError **error) G_GNUC_MALLOC;
891 GLIB_AVAILABLE_IN_ALL
892 gint g_unichar_to_utf8 (gunichar c,
895 GLIB_AVAILABLE_IN_ALL
896 gboolean g_utf8_validate (const gchar *str,
899 GLIB_AVAILABLE_IN_2_60
900 gboolean g_utf8_validate_len (const gchar *str,
904 GLIB_AVAILABLE_IN_ALL
905 gchar *g_utf8_strup (const gchar *str,
906 gssize len) G_GNUC_MALLOC;
907 GLIB_AVAILABLE_IN_ALL
908 gchar *g_utf8_strdown (const gchar *str,
909 gssize len) G_GNUC_MALLOC;
910 GLIB_AVAILABLE_IN_ALL
911 gchar *g_utf8_casefold (const gchar *str,
912 gssize len) G_GNUC_MALLOC;
916 * @G_NORMALIZE_DEFAULT: standardize differences that do not affect the
917 * text content, such as the above-mentioned accent representation
918 * @G_NORMALIZE_NFD: another name for %G_NORMALIZE_DEFAULT
919 * @G_NORMALIZE_DEFAULT_COMPOSE: like %G_NORMALIZE_DEFAULT, but with
920 * composed forms rather than a maximally decomposed form
921 * @G_NORMALIZE_NFC: another name for %G_NORMALIZE_DEFAULT_COMPOSE
922 * @G_NORMALIZE_ALL: beyond %G_NORMALIZE_DEFAULT also standardize the
923 * "compatibility" characters in Unicode, such as SUPERSCRIPT THREE
924 * to the standard forms (in this case DIGIT THREE). Formatting
925 * information may be lost but for most text operations such
926 * characters should be considered the same
927 * @G_NORMALIZE_NFKD: another name for %G_NORMALIZE_ALL
928 * @G_NORMALIZE_ALL_COMPOSE: like %G_NORMALIZE_ALL, but with composed
929 * forms rather than a maximally decomposed form
930 * @G_NORMALIZE_NFKC: another name for %G_NORMALIZE_ALL_COMPOSE
932 * Defines how a Unicode string is transformed in a canonical
933 * form, standardizing such issues as whether a character with
934 * an accent is represented as a base character and combining
935 * accent or as a single precomposed character. Unicode strings
936 * should generally be normalized before comparing them.
940 G_NORMALIZE_NFD = G_NORMALIZE_DEFAULT,
941 G_NORMALIZE_DEFAULT_COMPOSE,
942 G_NORMALIZE_NFC = G_NORMALIZE_DEFAULT_COMPOSE,
944 G_NORMALIZE_NFKD = G_NORMALIZE_ALL,
945 G_NORMALIZE_ALL_COMPOSE,
946 G_NORMALIZE_NFKC = G_NORMALIZE_ALL_COMPOSE
949 GLIB_AVAILABLE_IN_ALL
950 gchar *g_utf8_normalize (const gchar *str,
952 GNormalizeMode mode) G_GNUC_MALLOC;
954 GLIB_AVAILABLE_IN_ALL
955 gint g_utf8_collate (const gchar *str1,
956 const gchar *str2) G_GNUC_PURE;
957 GLIB_AVAILABLE_IN_ALL
958 gchar *g_utf8_collate_key (const gchar *str,
959 gssize len) G_GNUC_MALLOC;
960 GLIB_AVAILABLE_IN_ALL
961 gchar *g_utf8_collate_key_for_filename (const gchar *str,
962 gssize len) G_GNUC_MALLOC;
964 GLIB_AVAILABLE_IN_2_52
965 gchar *g_utf8_make_valid (const gchar *str,
966 gssize len) G_GNUC_MALLOC;
970 #endif /* __G_UNICODE_H__ */