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