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#ifndef G_DISABLE_DEPRECATED
158#define G_UNICODE_COMBINING_MARK G_UNICODE_SPACING_MARK
159#endif
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
200 * @G_UNICODE_BREAK_CONDITIONAL_JAPANESE_STARTER: Conditional Japanese Starter (CJ). Since: 2.32
201 * @G_UNICODE_BREAK_HEBREW_LETTER: Hebrew Letter (HL). Since: 2.32
202 * @G_UNICODE_BREAK_REGIONAL_INDICATOR: Regional Indicator (RI). Since: 2.36
203 * @G_UNICODE_BREAK_EMOJI_BASE: Emoji Base (EB). Since: 2.50
204 * @G_UNICODE_BREAK_EMOJI_MODIFIER: Emoji Modifier (EM). Since: 2.50
205 * @G_UNICODE_BREAK_ZERO_WIDTH_JOINER: Zero Width Joiner (ZWJ). Since: 2.50
206 *
207 * These are the possible line break classifications.
208 *
209 * Since new unicode versions may add new types here, applications should be ready
210 * to handle unknown values. They may be regarded as %G_UNICODE_BREAK_UNKNOWN.
211 *
212 * See [Unicode Line Breaking Algorithm](http://www.unicode.org/unicode/reports/tr14/).
213 */
214typedef enum
215{
216 G_UNICODE_BREAK_MANDATORY,
217 G_UNICODE_BREAK_CARRIAGE_RETURN,
218 G_UNICODE_BREAK_LINE_FEED,
219 G_UNICODE_BREAK_COMBINING_MARK,
220 G_UNICODE_BREAK_SURROGATE,
221 G_UNICODE_BREAK_ZERO_WIDTH_SPACE,
222 G_UNICODE_BREAK_INSEPARABLE,
223 G_UNICODE_BREAK_NON_BREAKING_GLUE,
224 G_UNICODE_BREAK_CONTINGENT,
225 G_UNICODE_BREAK_SPACE,
226 G_UNICODE_BREAK_AFTER,
227 G_UNICODE_BREAK_BEFORE,
228 G_UNICODE_BREAK_BEFORE_AND_AFTER,
229 G_UNICODE_BREAK_HYPHEN,
230 G_UNICODE_BREAK_NON_STARTER,
231 G_UNICODE_BREAK_OPEN_PUNCTUATION,
232 G_UNICODE_BREAK_CLOSE_PUNCTUATION,
233 G_UNICODE_BREAK_QUOTATION,
234 G_UNICODE_BREAK_EXCLAMATION,
235 G_UNICODE_BREAK_IDEOGRAPHIC,
236 G_UNICODE_BREAK_NUMERIC,
237 G_UNICODE_BREAK_INFIX_SEPARATOR,
238 G_UNICODE_BREAK_SYMBOL,
239 G_UNICODE_BREAK_ALPHABETIC,
240 G_UNICODE_BREAK_PREFIX,
241 G_UNICODE_BREAK_POSTFIX,
242 G_UNICODE_BREAK_COMPLEX_CONTEXT,
243 G_UNICODE_BREAK_AMBIGUOUS,
244 G_UNICODE_BREAK_UNKNOWN,
245 G_UNICODE_BREAK_NEXT_LINE,
246 G_UNICODE_BREAK_WORD_JOINER,
247 G_UNICODE_BREAK_HANGUL_L_JAMO,
248 G_UNICODE_BREAK_HANGUL_V_JAMO,
249 G_UNICODE_BREAK_HANGUL_T_JAMO,
250 G_UNICODE_BREAK_HANGUL_LV_SYLLABLE,
251 G_UNICODE_BREAK_HANGUL_LVT_SYLLABLE,
252 G_UNICODE_BREAK_CLOSE_PARANTHESIS,
253 G_UNICODE_BREAK_CONDITIONAL_JAPANESE_STARTER,
254 G_UNICODE_BREAK_HEBREW_LETTER,
255 G_UNICODE_BREAK_REGIONAL_INDICATOR,
256 G_UNICODE_BREAK_EMOJI_BASE,
257 G_UNICODE_BREAK_EMOJI_MODIFIER,
258 G_UNICODE_BREAK_ZERO_WIDTH_JOINER
259} GUnicodeBreakType;
260
261/**
262 * GUnicodeScript:
263 * @G_UNICODE_SCRIPT_INVALID_CODE:
264 * a value never returned from g_unichar_get_script()
265 * @G_UNICODE_SCRIPT_COMMON: a character used by multiple different scripts
266 * @G_UNICODE_SCRIPT_INHERITED: a mark glyph that takes its script from the
267 * base glyph to which it is attached
268 * @G_UNICODE_SCRIPT_ARABIC: Arabic
269 * @G_UNICODE_SCRIPT_ARMENIAN: Armenian
270 * @G_UNICODE_SCRIPT_BENGALI: Bengali
271 * @G_UNICODE_SCRIPT_BOPOMOFO: Bopomofo
272 * @G_UNICODE_SCRIPT_CHEROKEE: Cherokee
273 * @G_UNICODE_SCRIPT_COPTIC: Coptic
274 * @G_UNICODE_SCRIPT_CYRILLIC: Cyrillic
275 * @G_UNICODE_SCRIPT_DESERET: Deseret
276 * @G_UNICODE_SCRIPT_DEVANAGARI: Devanagari
277 * @G_UNICODE_SCRIPT_ETHIOPIC: Ethiopic
278 * @G_UNICODE_SCRIPT_GEORGIAN: Georgian
279 * @G_UNICODE_SCRIPT_GOTHIC: Gothic
280 * @G_UNICODE_SCRIPT_GREEK: Greek
281 * @G_UNICODE_SCRIPT_GUJARATI: Gujarati
282 * @G_UNICODE_SCRIPT_GURMUKHI: Gurmukhi
283 * @G_UNICODE_SCRIPT_HAN: Han
284 * @G_UNICODE_SCRIPT_HANGUL: Hangul
285 * @G_UNICODE_SCRIPT_HEBREW: Hebrew
286 * @G_UNICODE_SCRIPT_HIRAGANA: Hiragana
287 * @G_UNICODE_SCRIPT_KANNADA: Kannada
288 * @G_UNICODE_SCRIPT_KATAKANA: Katakana
289 * @G_UNICODE_SCRIPT_KHMER: Khmer
290 * @G_UNICODE_SCRIPT_LAO: Lao
291 * @G_UNICODE_SCRIPT_LATIN: Latin
292 * @G_UNICODE_SCRIPT_MALAYALAM: Malayalam
293 * @G_UNICODE_SCRIPT_MONGOLIAN: Mongolian
294 * @G_UNICODE_SCRIPT_MYANMAR: Myanmar
295 * @G_UNICODE_SCRIPT_OGHAM: Ogham
296 * @G_UNICODE_SCRIPT_OLD_ITALIC: Old Italic
297 * @G_UNICODE_SCRIPT_ORIYA: Oriya
298 * @G_UNICODE_SCRIPT_RUNIC: Runic
299 * @G_UNICODE_SCRIPT_SINHALA: Sinhala
300 * @G_UNICODE_SCRIPT_SYRIAC: Syriac
301 * @G_UNICODE_SCRIPT_TAMIL: Tamil
302 * @G_UNICODE_SCRIPT_TELUGU: Telugu
303 * @G_UNICODE_SCRIPT_THAANA: Thaana
304 * @G_UNICODE_SCRIPT_THAI: Thai
305 * @G_UNICODE_SCRIPT_TIBETAN: Tibetan
306 * @G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL:
307 * Canadian Aboriginal
308 * @G_UNICODE_SCRIPT_YI: Yi
309 * @G_UNICODE_SCRIPT_TAGALOG: Tagalog
310 * @G_UNICODE_SCRIPT_HANUNOO: Hanunoo
311 * @G_UNICODE_SCRIPT_BUHID: Buhid
312 * @G_UNICODE_SCRIPT_TAGBANWA: Tagbanwa
313 * @G_UNICODE_SCRIPT_BRAILLE: Braille
314 * @G_UNICODE_SCRIPT_CYPRIOT: Cypriot
315 * @G_UNICODE_SCRIPT_LIMBU: Limbu
316 * @G_UNICODE_SCRIPT_OSMANYA: Osmanya
317 * @G_UNICODE_SCRIPT_SHAVIAN: Shavian
318 * @G_UNICODE_SCRIPT_LINEAR_B: Linear B
319 * @G_UNICODE_SCRIPT_TAI_LE: Tai Le
320 * @G_UNICODE_SCRIPT_UGARITIC: Ugaritic
321 * @G_UNICODE_SCRIPT_NEW_TAI_LUE:
322 * New Tai Lue
323 * @G_UNICODE_SCRIPT_BUGINESE: Buginese
324 * @G_UNICODE_SCRIPT_GLAGOLITIC: Glagolitic
325 * @G_UNICODE_SCRIPT_TIFINAGH: Tifinagh
326 * @G_UNICODE_SCRIPT_SYLOTI_NAGRI:
327 * Syloti Nagri
328 * @G_UNICODE_SCRIPT_OLD_PERSIAN:
329 * Old Persian
330 * @G_UNICODE_SCRIPT_KHAROSHTHI: Kharoshthi
331 * @G_UNICODE_SCRIPT_UNKNOWN: an unassigned code point
332 * @G_UNICODE_SCRIPT_BALINESE: Balinese
333 * @G_UNICODE_SCRIPT_CUNEIFORM: Cuneiform
334 * @G_UNICODE_SCRIPT_PHOENICIAN: Phoenician
335 * @G_UNICODE_SCRIPT_PHAGS_PA: Phags-pa
336 * @G_UNICODE_SCRIPT_NKO: N'Ko
337 * @G_UNICODE_SCRIPT_KAYAH_LI: Kayah Li. Since 2.16.3
338 * @G_UNICODE_SCRIPT_LEPCHA: Lepcha. Since 2.16.3
339 * @G_UNICODE_SCRIPT_REJANG: Rejang. Since 2.16.3
340 * @G_UNICODE_SCRIPT_SUNDANESE: Sundanese. Since 2.16.3
341 * @G_UNICODE_SCRIPT_SAURASHTRA: Saurashtra. Since 2.16.3
342 * @G_UNICODE_SCRIPT_CHAM: Cham. Since 2.16.3
343 * @G_UNICODE_SCRIPT_OL_CHIKI: Ol Chiki. Since 2.16.3
344 * @G_UNICODE_SCRIPT_VAI: Vai. Since 2.16.3
345 * @G_UNICODE_SCRIPT_CARIAN: Carian. Since 2.16.3
346 * @G_UNICODE_SCRIPT_LYCIAN: Lycian. Since 2.16.3
347 * @G_UNICODE_SCRIPT_LYDIAN: Lydian. Since 2.16.3
348 * @G_UNICODE_SCRIPT_AVESTAN: Avestan. Since 2.26
349 * @G_UNICODE_SCRIPT_BAMUM: Bamum. Since 2.26
350 * @G_UNICODE_SCRIPT_EGYPTIAN_HIEROGLYPHS:
351 * Egyptian Hieroglpyhs. Since 2.26
352 * @G_UNICODE_SCRIPT_IMPERIAL_ARAMAIC:
353 * Imperial Aramaic. Since 2.26
354 * @G_UNICODE_SCRIPT_INSCRIPTIONAL_PAHLAVI:
355 * Inscriptional Pahlavi. Since 2.26
356 * @G_UNICODE_SCRIPT_INSCRIPTIONAL_PARTHIAN:
357 * Inscriptional Parthian. Since 2.26
358 * @G_UNICODE_SCRIPT_JAVANESE: Javanese. Since 2.26
359 * @G_UNICODE_SCRIPT_KAITHI: Kaithi. Since 2.26
360 * @G_UNICODE_SCRIPT_LISU: Lisu. Since 2.26
361 * @G_UNICODE_SCRIPT_MEETEI_MAYEK:
362 * Meetei Mayek. Since 2.26
363 * @G_UNICODE_SCRIPT_OLD_SOUTH_ARABIAN:
364 * Old South Arabian. Since 2.26
365 * @G_UNICODE_SCRIPT_OLD_TURKIC: Old Turkic. Since 2.28
366 * @G_UNICODE_SCRIPT_SAMARITAN: Samaritan. Since 2.26
367 * @G_UNICODE_SCRIPT_TAI_THAM: Tai Tham. Since 2.26
368 * @G_UNICODE_SCRIPT_TAI_VIET: Tai Viet. Since 2.26
369 * @G_UNICODE_SCRIPT_BATAK: Batak. Since 2.28
370 * @G_UNICODE_SCRIPT_BRAHMI: Brahmi. Since 2.28
371 * @G_UNICODE_SCRIPT_MANDAIC: Mandaic. Since 2.28
372 * @G_UNICODE_SCRIPT_CHAKMA: Chakma. Since: 2.32
373 * @G_UNICODE_SCRIPT_MEROITIC_CURSIVE: Meroitic Cursive. Since: 2.32
374 * @G_UNICODE_SCRIPT_MEROITIC_HIEROGLYPHS: Meroitic Hieroglyphs. Since: 2.32
375 * @G_UNICODE_SCRIPT_MIAO: Miao. Since: 2.32
376 * @G_UNICODE_SCRIPT_SHARADA: Sharada. Since: 2.32
377 * @G_UNICODE_SCRIPT_SORA_SOMPENG: Sora Sompeng. Since: 2.32
378 * @G_UNICODE_SCRIPT_TAKRI: Takri. Since: 2.32
379 * @G_UNICODE_SCRIPT_BASSA_VAH: Bassa. Since: 2.42
380 * @G_UNICODE_SCRIPT_CAUCASIAN_ALBANIAN: Caucasian Albanian. Since: 2.42
381 * @G_UNICODE_SCRIPT_DUPLOYAN: Duployan. Since: 2.42
382 * @G_UNICODE_SCRIPT_ELBASAN: Elbasan. Since: 2.42
383 * @G_UNICODE_SCRIPT_GRANTHA: Grantha. Since: 2.42
384 * @G_UNICODE_SCRIPT_KHOJKI: Kjohki. Since: 2.42
385 * @G_UNICODE_SCRIPT_KHUDAWADI: Khudawadi, Sindhi. Since: 2.42
386 * @G_UNICODE_SCRIPT_LINEAR_A: Linear A. Since: 2.42
387 * @G_UNICODE_SCRIPT_MAHAJANI: Mahajani. Since: 2.42
388 * @G_UNICODE_SCRIPT_MANICHAEAN: Manichaean. Since: 2.42
389 * @G_UNICODE_SCRIPT_MENDE_KIKAKUI: Mende Kikakui. Since: 2.42
390 * @G_UNICODE_SCRIPT_MODI: Modi. Since: 2.42
391 * @G_UNICODE_SCRIPT_MRO: Mro. Since: 2.42
392 * @G_UNICODE_SCRIPT_NABATAEAN: Nabataean. Since: 2.42
393 * @G_UNICODE_SCRIPT_OLD_NORTH_ARABIAN: Old North Arabian. Since: 2.42
394 * @G_UNICODE_SCRIPT_OLD_PERMIC: Old Permic. Since: 2.42
395 * @G_UNICODE_SCRIPT_PAHAWH_HMONG: Pahawh Hmong. Since: 2.42
396 * @G_UNICODE_SCRIPT_PALMYRENE: Palmyrene. Since: 2.42
397 * @G_UNICODE_SCRIPT_PAU_CIN_HAU: Pau Cin Hau. Since: 2.42
398 * @G_UNICODE_SCRIPT_PSALTER_PAHLAVI: Psalter Pahlavi. Since: 2.42
399 * @G_UNICODE_SCRIPT_SIDDHAM: Siddham. Since: 2.42
400 * @G_UNICODE_SCRIPT_TIRHUTA: Tirhuta. Since: 2.42
401 * @G_UNICODE_SCRIPT_WARANG_CITI: Warang Citi. Since: 2.42
402 * @G_UNICODE_SCRIPT_AHOM: Ahom. Since: 2.48
403 * @G_UNICODE_SCRIPT_ANATOLIAN_HIEROGLYPHS: Anatolian Hieroglyphs. Since: 2.48
404 * @G_UNICODE_SCRIPT_HATRAN: Hatran. Since: 2.48
405 * @G_UNICODE_SCRIPT_MULTANI: Multani. Since: 2.48
406 * @G_UNICODE_SCRIPT_OLD_HUNGARIAN: Old Hungarian. Since: 2.48
407 * @G_UNICODE_SCRIPT_SIGNWRITING: Signwriting. Since: 2.48
408 * @G_UNICODE_SCRIPT_ADLAM: Adlam. Since: 2.50
409 * @G_UNICODE_SCRIPT_BHAIKSUKI: Bhaiksuki. Since: 2.50
410 * @G_UNICODE_SCRIPT_MARCHEN: Marchen. Since: 2.50
411 * @G_UNICODE_SCRIPT_NEWA: Newa. Since: 2.50
412 * @G_UNICODE_SCRIPT_OSAGE: Osage. Since: 2.50
413 * @G_UNICODE_SCRIPT_TANGUT: Tangut. Since: 2.50
414 * @G_UNICODE_SCRIPT_MASARAM_GONDI: Masaram Gondi. Since: 2.54
415 * @G_UNICODE_SCRIPT_NUSHU: Nushu. Since: 2.54
416 * @G_UNICODE_SCRIPT_SOYOMBO: Soyombo. Since: 2.54
417 * @G_UNICODE_SCRIPT_ZANABAZAR_SQUARE: Zanabazar Square. Since: 2.54
418 * @G_UNICODE_SCRIPT_DOGRA: Dogra. Since: 2.58
419 * @G_UNICODE_SCRIPT_GUNJALA_GONDI: Gunjala Gondi. Since: 2.58
420 * @G_UNICODE_SCRIPT_HANIFI_ROHINGYA: Hanifi Rohingya. Since: 2.58
421 * @G_UNICODE_SCRIPT_MAKASAR: Makasar. Since: 2.58
422 * @G_UNICODE_SCRIPT_MEDEFAIDRIN: Medefaidrin. Since: 2.58
423 * @G_UNICODE_SCRIPT_OLD_SOGDIAN: Old Sogdian. Since: 2.58
424 * @G_UNICODE_SCRIPT_SOGDIAN: Sogdian. Since: 2.58
425 *
426 * The #GUnicodeScript enumeration identifies different writing
427 * systems. The values correspond to the names as defined in the
428 * Unicode standard. The enumeration has been added in GLib 2.14,
429 * and is interchangeable with #PangoScript.
430 *
431 * Note that new types may be added in the future. Applications
432 * should be ready to handle unknown values.
433 * See [Unicode Standard Annex #24: Script names](http://www.unicode.org/reports/tr24/).
434 */
435typedef enum
436{ /* ISO 15924 code */
437 G_UNICODE_SCRIPT_INVALID_CODE = -1,
438 G_UNICODE_SCRIPT_COMMON = 0, /* Zyyy */
439 G_UNICODE_SCRIPT_INHERITED, /* Zinh (Qaai) */
440 G_UNICODE_SCRIPT_ARABIC, /* Arab */
441 G_UNICODE_SCRIPT_ARMENIAN, /* Armn */
442 G_UNICODE_SCRIPT_BENGALI, /* Beng */
443 G_UNICODE_SCRIPT_BOPOMOFO, /* Bopo */
444 G_UNICODE_SCRIPT_CHEROKEE, /* Cher */
445 G_UNICODE_SCRIPT_COPTIC, /* Copt (Qaac) */
446 G_UNICODE_SCRIPT_CYRILLIC, /* Cyrl (Cyrs) */
447 G_UNICODE_SCRIPT_DESERET, /* Dsrt */
448 G_UNICODE_SCRIPT_DEVANAGARI, /* Deva */
449 G_UNICODE_SCRIPT_ETHIOPIC, /* Ethi */
450 G_UNICODE_SCRIPT_GEORGIAN, /* Geor (Geon, Geoa) */
451 G_UNICODE_SCRIPT_GOTHIC, /* Goth */
452 G_UNICODE_SCRIPT_GREEK, /* Grek */
453 G_UNICODE_SCRIPT_GUJARATI, /* Gujr */
454 G_UNICODE_SCRIPT_GURMUKHI, /* Guru */
455 G_UNICODE_SCRIPT_HAN, /* Hani */
456 G_UNICODE_SCRIPT_HANGUL, /* Hang */
457 G_UNICODE_SCRIPT_HEBREW, /* Hebr */
458 G_UNICODE_SCRIPT_HIRAGANA, /* Hira */
459 G_UNICODE_SCRIPT_KANNADA, /* Knda */
460 G_UNICODE_SCRIPT_KATAKANA, /* Kana */
461 G_UNICODE_SCRIPT_KHMER, /* Khmr */
462 G_UNICODE_SCRIPT_LAO, /* Laoo */
463 G_UNICODE_SCRIPT_LATIN, /* Latn (Latf, Latg) */
464 G_UNICODE_SCRIPT_MALAYALAM, /* Mlym */
465 G_UNICODE_SCRIPT_MONGOLIAN, /* Mong */
466 G_UNICODE_SCRIPT_MYANMAR, /* Mymr */
467 G_UNICODE_SCRIPT_OGHAM, /* Ogam */
468 G_UNICODE_SCRIPT_OLD_ITALIC, /* Ital */
469 G_UNICODE_SCRIPT_ORIYA, /* Orya */
470 G_UNICODE_SCRIPT_RUNIC, /* Runr */
471 G_UNICODE_SCRIPT_SINHALA, /* Sinh */
472 G_UNICODE_SCRIPT_SYRIAC, /* Syrc (Syrj, Syrn, Syre) */
473 G_UNICODE_SCRIPT_TAMIL, /* Taml */
474 G_UNICODE_SCRIPT_TELUGU, /* Telu */
475 G_UNICODE_SCRIPT_THAANA, /* Thaa */
476 G_UNICODE_SCRIPT_THAI, /* Thai */
477 G_UNICODE_SCRIPT_TIBETAN, /* Tibt */
478 G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL, /* Cans */
479 G_UNICODE_SCRIPT_YI, /* Yiii */
480 G_UNICODE_SCRIPT_TAGALOG, /* Tglg */
481 G_UNICODE_SCRIPT_HANUNOO, /* Hano */
482 G_UNICODE_SCRIPT_BUHID, /* Buhd */
483 G_UNICODE_SCRIPT_TAGBANWA, /* Tagb */
484
485 /* Unicode-4.0 additions */
486 G_UNICODE_SCRIPT_BRAILLE, /* Brai */
487 G_UNICODE_SCRIPT_CYPRIOT, /* Cprt */
488 G_UNICODE_SCRIPT_LIMBU, /* Limb */
489 G_UNICODE_SCRIPT_OSMANYA, /* Osma */
490 G_UNICODE_SCRIPT_SHAVIAN, /* Shaw */
491 G_UNICODE_SCRIPT_LINEAR_B, /* Linb */
492 G_UNICODE_SCRIPT_TAI_LE, /* Tale */
493 G_UNICODE_SCRIPT_UGARITIC, /* Ugar */
494
495 /* Unicode-4.1 additions */
496 G_UNICODE_SCRIPT_NEW_TAI_LUE, /* Talu */
497 G_UNICODE_SCRIPT_BUGINESE, /* Bugi */
498 G_UNICODE_SCRIPT_GLAGOLITIC, /* Glag */
499 G_UNICODE_SCRIPT_TIFINAGH, /* Tfng */
500 G_UNICODE_SCRIPT_SYLOTI_NAGRI, /* Sylo */
501 G_UNICODE_SCRIPT_OLD_PERSIAN, /* Xpeo */
502 G_UNICODE_SCRIPT_KHAROSHTHI, /* Khar */
503
504 /* Unicode-5.0 additions */
505 G_UNICODE_SCRIPT_UNKNOWN, /* Zzzz */
506 G_UNICODE_SCRIPT_BALINESE, /* Bali */
507 G_UNICODE_SCRIPT_CUNEIFORM, /* Xsux */
508 G_UNICODE_SCRIPT_PHOENICIAN, /* Phnx */
509 G_UNICODE_SCRIPT_PHAGS_PA, /* Phag */
510 G_UNICODE_SCRIPT_NKO, /* Nkoo */
511
512 /* Unicode-5.1 additions */
513 G_UNICODE_SCRIPT_KAYAH_LI, /* Kali */
514 G_UNICODE_SCRIPT_LEPCHA, /* Lepc */
515 G_UNICODE_SCRIPT_REJANG, /* Rjng */
516 G_UNICODE_SCRIPT_SUNDANESE, /* Sund */
517 G_UNICODE_SCRIPT_SAURASHTRA, /* Saur */
518 G_UNICODE_SCRIPT_CHAM, /* Cham */
519 G_UNICODE_SCRIPT_OL_CHIKI, /* Olck */
520 G_UNICODE_SCRIPT_VAI, /* Vaii */
521 G_UNICODE_SCRIPT_CARIAN, /* Cari */
522 G_UNICODE_SCRIPT_LYCIAN, /* Lyci */
523 G_UNICODE_SCRIPT_LYDIAN, /* Lydi */
524
525 /* Unicode-5.2 additions */
526 G_UNICODE_SCRIPT_AVESTAN, /* Avst */
527 G_UNICODE_SCRIPT_BAMUM, /* Bamu */
528 G_UNICODE_SCRIPT_EGYPTIAN_HIEROGLYPHS, /* Egyp */
529 G_UNICODE_SCRIPT_IMPERIAL_ARAMAIC, /* Armi */
530 G_UNICODE_SCRIPT_INSCRIPTIONAL_PAHLAVI, /* Phli */
531 G_UNICODE_SCRIPT_INSCRIPTIONAL_PARTHIAN, /* Prti */
532 G_UNICODE_SCRIPT_JAVANESE, /* Java */
533 G_UNICODE_SCRIPT_KAITHI, /* Kthi */
534 G_UNICODE_SCRIPT_LISU, /* Lisu */
535 G_UNICODE_SCRIPT_MEETEI_MAYEK, /* Mtei */
536 G_UNICODE_SCRIPT_OLD_SOUTH_ARABIAN, /* Sarb */
537 G_UNICODE_SCRIPT_OLD_TURKIC, /* Orkh */
538 G_UNICODE_SCRIPT_SAMARITAN, /* Samr */
539 G_UNICODE_SCRIPT_TAI_THAM, /* Lana */
540 G_UNICODE_SCRIPT_TAI_VIET, /* Tavt */
541
542 /* Unicode-6.0 additions */
543 G_UNICODE_SCRIPT_BATAK, /* Batk */
544 G_UNICODE_SCRIPT_BRAHMI, /* Brah */
545 G_UNICODE_SCRIPT_MANDAIC, /* Mand */
546
547 /* Unicode-6.1 additions */
548 G_UNICODE_SCRIPT_CHAKMA, /* Cakm */
549 G_UNICODE_SCRIPT_MEROITIC_CURSIVE, /* Merc */
550 G_UNICODE_SCRIPT_MEROITIC_HIEROGLYPHS, /* Mero */
551 G_UNICODE_SCRIPT_MIAO, /* Plrd */
552 G_UNICODE_SCRIPT_SHARADA, /* Shrd */
553 G_UNICODE_SCRIPT_SORA_SOMPENG, /* Sora */
554 G_UNICODE_SCRIPT_TAKRI, /* Takr */
555
556 /* Unicode 7.0 additions */
557 G_UNICODE_SCRIPT_BASSA_VAH, /* Bass */
558 G_UNICODE_SCRIPT_CAUCASIAN_ALBANIAN, /* Aghb */
559 G_UNICODE_SCRIPT_DUPLOYAN, /* Dupl */
560 G_UNICODE_SCRIPT_ELBASAN, /* Elba */
561 G_UNICODE_SCRIPT_GRANTHA, /* Gran */
562 G_UNICODE_SCRIPT_KHOJKI, /* Khoj */
563 G_UNICODE_SCRIPT_KHUDAWADI, /* Sind */
564 G_UNICODE_SCRIPT_LINEAR_A, /* Lina */
565 G_UNICODE_SCRIPT_MAHAJANI, /* Mahj */
566 G_UNICODE_SCRIPT_MANICHAEAN, /* Manu */
567 G_UNICODE_SCRIPT_MENDE_KIKAKUI, /* Mend */
568 G_UNICODE_SCRIPT_MODI, /* Modi */
569 G_UNICODE_SCRIPT_MRO, /* Mroo */
570 G_UNICODE_SCRIPT_NABATAEAN, /* Nbat */
571 G_UNICODE_SCRIPT_OLD_NORTH_ARABIAN, /* Narb */
572 G_UNICODE_SCRIPT_OLD_PERMIC, /* Perm */
573 G_UNICODE_SCRIPT_PAHAWH_HMONG, /* Hmng */
574 G_UNICODE_SCRIPT_PALMYRENE, /* Palm */
575 G_UNICODE_SCRIPT_PAU_CIN_HAU, /* Pauc */
576 G_UNICODE_SCRIPT_PSALTER_PAHLAVI, /* Phlp */
577 G_UNICODE_SCRIPT_SIDDHAM, /* Sidd */
578 G_UNICODE_SCRIPT_TIRHUTA, /* Tirh */
579 G_UNICODE_SCRIPT_WARANG_CITI, /* Wara */
580
581 /* Unicode 8.0 additions */
582 G_UNICODE_SCRIPT_AHOM, /* Ahom */
583 G_UNICODE_SCRIPT_ANATOLIAN_HIEROGLYPHS, /* Hluw */
584 G_UNICODE_SCRIPT_HATRAN, /* Hatr */
585 G_UNICODE_SCRIPT_MULTANI, /* Mult */
586 G_UNICODE_SCRIPT_OLD_HUNGARIAN, /* Hung */
587 G_UNICODE_SCRIPT_SIGNWRITING, /* Sgnw */
588
589 /* Unicode 9.0 additions */
590 G_UNICODE_SCRIPT_ADLAM, /* Adlm */
591 G_UNICODE_SCRIPT_BHAIKSUKI, /* Bhks */
592 G_UNICODE_SCRIPT_MARCHEN, /* Marc */
593 G_UNICODE_SCRIPT_NEWA, /* Newa */
594 G_UNICODE_SCRIPT_OSAGE, /* Osge */
595 G_UNICODE_SCRIPT_TANGUT, /* Tang */
596
597 /* Unicode 10.0 additions */
598 G_UNICODE_SCRIPT_MASARAM_GONDI, /* Gonm */
599 G_UNICODE_SCRIPT_NUSHU, /* Nshu */
600 G_UNICODE_SCRIPT_SOYOMBO, /* Soyo */
601 G_UNICODE_SCRIPT_ZANABAZAR_SQUARE, /* Zanb */
602
603 /* Unicode 11.0 additions */
604 G_UNICODE_SCRIPT_DOGRA, /* Dogr */
605 G_UNICODE_SCRIPT_GUNJALA_GONDI, /* Gong */
606 G_UNICODE_SCRIPT_HANIFI_ROHINGYA, /* Rohg */
607 G_UNICODE_SCRIPT_MAKASAR, /* Maka */
608 G_UNICODE_SCRIPT_MEDEFAIDRIN, /* Medf */
609 G_UNICODE_SCRIPT_OLD_SOGDIAN, /* Sogo */
610 G_UNICODE_SCRIPT_SOGDIAN /* Sogd */
611} GUnicodeScript;
612
613GLIB_AVAILABLE_IN_ALL
614guint32 g_unicode_script_to_iso15924 (GUnicodeScript script);
615GLIB_AVAILABLE_IN_ALL
616GUnicodeScript g_unicode_script_from_iso15924 (guint32 iso15924);
617
618/* These are all analogs of the <ctype.h> functions.
619 */
620GLIB_AVAILABLE_IN_ALL
621gboolean g_unichar_isalnum (gunichar c) G_GNUC_CONST;
622GLIB_AVAILABLE_IN_ALL
623gboolean g_unichar_isalpha (gunichar c) G_GNUC_CONST;
624GLIB_AVAILABLE_IN_ALL
625gboolean g_unichar_iscntrl (gunichar c) G_GNUC_CONST;
626GLIB_AVAILABLE_IN_ALL
627gboolean g_unichar_isdigit (gunichar c) G_GNUC_CONST;
628GLIB_AVAILABLE_IN_ALL
629gboolean g_unichar_isgraph (gunichar c) G_GNUC_CONST;
630GLIB_AVAILABLE_IN_ALL
631gboolean g_unichar_islower (gunichar c) G_GNUC_CONST;
632GLIB_AVAILABLE_IN_ALL
633gboolean g_unichar_isprint (gunichar c) G_GNUC_CONST;
634GLIB_AVAILABLE_IN_ALL
635gboolean g_unichar_ispunct (gunichar c) G_GNUC_CONST;
636GLIB_AVAILABLE_IN_ALL
637gboolean g_unichar_isspace (gunichar c) G_GNUC_CONST;
638GLIB_AVAILABLE_IN_ALL
639gboolean g_unichar_isupper (gunichar c) G_GNUC_CONST;
640GLIB_AVAILABLE_IN_ALL
641gboolean g_unichar_isxdigit (gunichar c) G_GNUC_CONST;
642GLIB_AVAILABLE_IN_ALL
643gboolean g_unichar_istitle (gunichar c) G_GNUC_CONST;
644GLIB_AVAILABLE_IN_ALL
645gboolean g_unichar_isdefined (gunichar c) G_GNUC_CONST;
646GLIB_AVAILABLE_IN_ALL
647gboolean g_unichar_iswide (gunichar c) G_GNUC_CONST;
648GLIB_AVAILABLE_IN_ALL
649gboolean g_unichar_iswide_cjk(gunichar c) G_GNUC_CONST;
650GLIB_AVAILABLE_IN_ALL
651gboolean g_unichar_iszerowidth(gunichar c) G_GNUC_CONST;
652GLIB_AVAILABLE_IN_ALL
653gboolean g_unichar_ismark (gunichar c) G_GNUC_CONST;
654
655/* More <ctype.h> functions. These convert between the three cases.
656 * See the Unicode book to understand title case. */
657GLIB_AVAILABLE_IN_ALL
658gunichar g_unichar_toupper (gunichar c) G_GNUC_CONST;
659GLIB_AVAILABLE_IN_ALL
660gunichar g_unichar_tolower (gunichar c) G_GNUC_CONST;
661GLIB_AVAILABLE_IN_ALL
662gunichar g_unichar_totitle (gunichar c) G_GNUC_CONST;
663
664/* If C is a digit (according to 'g_unichar_isdigit'), then return its
665 numeric value. Otherwise return -1. */
666GLIB_AVAILABLE_IN_ALL
667gint g_unichar_digit_value (gunichar c) G_GNUC_CONST;
668
669GLIB_AVAILABLE_IN_ALL
670gint g_unichar_xdigit_value (gunichar c) G_GNUC_CONST;
671
672/* Return the Unicode character type of a given character. */
673GLIB_AVAILABLE_IN_ALL
674GUnicodeType g_unichar_type (gunichar c) G_GNUC_CONST;
675
676/* Return the line break property for a given character */
677GLIB_AVAILABLE_IN_ALL
678GUnicodeBreakType g_unichar_break_type (gunichar c) G_GNUC_CONST;
679
680/* Returns the combining class for a given character */
681GLIB_AVAILABLE_IN_ALL
682gint g_unichar_combining_class (gunichar uc) G_GNUC_CONST;
683
684GLIB_AVAILABLE_IN_ALL
685gboolean g_unichar_get_mirror_char (gunichar ch,
686 gunichar *mirrored_ch);
687
688GLIB_AVAILABLE_IN_ALL
689GUnicodeScript g_unichar_get_script (gunichar ch) G_GNUC_CONST;
690
691/* Validate a Unicode character */
692GLIB_AVAILABLE_IN_ALL
693gboolean g_unichar_validate (gunichar ch) G_GNUC_CONST;
694
695/* Pairwise canonical compose/decompose */
696GLIB_AVAILABLE_IN_ALL
697gboolean g_unichar_compose (gunichar a,
698 gunichar b,
699 gunichar *ch);
700GLIB_AVAILABLE_IN_ALL
701gboolean g_unichar_decompose (gunichar ch,
702 gunichar *a,
703 gunichar *b);
704
705GLIB_AVAILABLE_IN_ALL
706gsize g_unichar_fully_decompose (gunichar ch,
707 gboolean compat,
708 gunichar *result,
709 gsize result_len);
710
711/**
712 * G_UNICHAR_MAX_DECOMPOSITION_LENGTH:
713 *
714 * The maximum length (in codepoints) of a compatibility or canonical
715 * decomposition of a single Unicode character.
716 *
717 * This is as defined by Unicode 6.1.
718 *
719 * Since: 2.32
720 */
721#define G_UNICHAR_MAX_DECOMPOSITION_LENGTH 18 /* codepoints */
722
723/* Compute canonical ordering of a string in-place. This rearranges
724 decomposed characters in the string according to their combining
725 classes. See the Unicode manual for more information. */
726GLIB_AVAILABLE_IN_ALL
727void g_unicode_canonical_ordering (gunichar *string,
728 gsize len);
729
730
731GLIB_DEPRECATED_IN_2_30
732gunichar *g_unicode_canonical_decomposition (gunichar ch,
733 gsize *result_len) G_GNUC_MALLOC;
734
735/* Array of skip-bytes-per-initial character.
736 */
737GLIB_VAR const gchar * const g_utf8_skip;
738
739/**
740 * g_utf8_next_char:
741 * @p: Pointer to the start of a valid UTF-8 character
742 *
743 * Skips to the next character in a UTF-8 string. The string must be
744 * valid; this macro is as fast as possible, and has no error-checking.
745 * You would use this macro to iterate over a string character by
746 * character. The macro returns the start of the next UTF-8 character.
747 * Before using this macro, use g_utf8_validate() to validate strings
748 * that may contain invalid UTF-8.
749 */
750#define g_utf8_next_char(p) (char *)((p) + g_utf8_skip[*(const guchar *)(p)])
751
752GLIB_AVAILABLE_IN_ALL
753gunichar g_utf8_get_char (const gchar *p) G_GNUC_PURE;
754GLIB_AVAILABLE_IN_ALL
755gunichar g_utf8_get_char_validated (const gchar *p,
756 gssize max_len) G_GNUC_PURE;
757
758GLIB_AVAILABLE_IN_ALL
759gchar* g_utf8_offset_to_pointer (const gchar *str,
760 glong offset) G_GNUC_PURE;
761GLIB_AVAILABLE_IN_ALL
762glong g_utf8_pointer_to_offset (const gchar *str,
763 const gchar *pos) G_GNUC_PURE;
764GLIB_AVAILABLE_IN_ALL
765gchar* g_utf8_prev_char (const gchar *p) G_GNUC_PURE;
766GLIB_AVAILABLE_IN_ALL
767gchar* g_utf8_find_next_char (const gchar *p,
768 const gchar *end) G_GNUC_PURE;
769GLIB_AVAILABLE_IN_ALL
770gchar* g_utf8_find_prev_char (const gchar *str,
771 const gchar *p) G_GNUC_PURE;
772
773GLIB_AVAILABLE_IN_ALL
774glong g_utf8_strlen (const gchar *p,
775 gssize max) G_GNUC_PURE;
776
777GLIB_AVAILABLE_IN_2_30
778gchar *g_utf8_substring (const gchar *str,
779 glong start_pos,
780 glong end_pos) G_GNUC_MALLOC;
781
782GLIB_AVAILABLE_IN_ALL
783gchar *g_utf8_strncpy (gchar *dest,
784 const gchar *src,
785 gsize n);
786
787/* Find the UTF-8 character corresponding to ch, in string p. These
788 functions are equivalants to strchr and strrchr */
789GLIB_AVAILABLE_IN_ALL
790gchar* g_utf8_strchr (const gchar *p,
791 gssize len,
792 gunichar c);
793GLIB_AVAILABLE_IN_ALL
794gchar* g_utf8_strrchr (const gchar *p,
795 gssize len,
796 gunichar c);
797GLIB_AVAILABLE_IN_ALL
798gchar* g_utf8_strreverse (const gchar *str,
799 gssize len);
800
801GLIB_AVAILABLE_IN_ALL
802gunichar2 *g_utf8_to_utf16 (const gchar *str,
803 glong len,
804 glong *items_read,
805 glong *items_written,
806 GError **error) G_GNUC_MALLOC;
807GLIB_AVAILABLE_IN_ALL
808gunichar * g_utf8_to_ucs4 (const gchar *str,
809 glong len,
810 glong *items_read,
811 glong *items_written,
812 GError **error) G_GNUC_MALLOC;
813GLIB_AVAILABLE_IN_ALL
814gunichar * g_utf8_to_ucs4_fast (const gchar *str,
815 glong len,
816 glong *items_written) G_GNUC_MALLOC;
817GLIB_AVAILABLE_IN_ALL
818gunichar * g_utf16_to_ucs4 (const gunichar2 *str,
819 glong len,
820 glong *items_read,
821 glong *items_written,
822 GError **error) G_GNUC_MALLOC;
823GLIB_AVAILABLE_IN_ALL
824gchar* g_utf16_to_utf8 (const gunichar2 *str,
825 glong len,
826 glong *items_read,
827 glong *items_written,
828 GError **error) G_GNUC_MALLOC;
829GLIB_AVAILABLE_IN_ALL
830gunichar2 *g_ucs4_to_utf16 (const gunichar *str,
831 glong len,
832 glong *items_read,
833 glong *items_written,
834 GError **error) G_GNUC_MALLOC;
835GLIB_AVAILABLE_IN_ALL
836gchar* g_ucs4_to_utf8 (const gunichar *str,
837 glong len,
838 glong *items_read,
839 glong *items_written,
840 GError **error) G_GNUC_MALLOC;
841
842GLIB_AVAILABLE_IN_ALL
843gint g_unichar_to_utf8 (gunichar c,
844 gchar *outbuf);
845
846GLIB_AVAILABLE_IN_ALL
847gboolean g_utf8_validate (const gchar *str,
848 gssize max_len,
849 const gchar **end);
850
851GLIB_AVAILABLE_IN_ALL
852gchar *g_utf8_strup (const gchar *str,
853 gssize len) G_GNUC_MALLOC;
854GLIB_AVAILABLE_IN_ALL
855gchar *g_utf8_strdown (const gchar *str,
856 gssize len) G_GNUC_MALLOC;
857GLIB_AVAILABLE_IN_ALL
858gchar *g_utf8_casefold (const gchar *str,
859 gssize len) G_GNUC_MALLOC;
860
861/**
862 * GNormalizeMode:
863 * @G_NORMALIZE_DEFAULT: standardize differences that do not affect the
864 * text content, such as the above-mentioned accent representation
865 * @G_NORMALIZE_NFD: another name for %G_NORMALIZE_DEFAULT
866 * @G_NORMALIZE_DEFAULT_COMPOSE: like %G_NORMALIZE_DEFAULT, but with
867 * composed forms rather than a maximally decomposed form
868 * @G_NORMALIZE_NFC: another name for %G_NORMALIZE_DEFAULT_COMPOSE
869 * @G_NORMALIZE_ALL: beyond %G_NORMALIZE_DEFAULT also standardize the
870 * "compatibility" characters in Unicode, such as SUPERSCRIPT THREE
871 * to the standard forms (in this case DIGIT THREE). Formatting
872 * information may be lost but for most text operations such
873 * characters should be considered the same
874 * @G_NORMALIZE_NFKD: another name for %G_NORMALIZE_ALL
875 * @G_NORMALIZE_ALL_COMPOSE: like %G_NORMALIZE_ALL, but with composed
876 * forms rather than a maximally decomposed form
877 * @G_NORMALIZE_NFKC: another name for %G_NORMALIZE_ALL_COMPOSE
878 *
879 * Defines how a Unicode string is transformed in a canonical
880 * form, standardizing such issues as whether a character with
881 * an accent is represented as a base character and combining
882 * accent or as a single precomposed character. Unicode strings
883 * should generally be normalized before comparing them.
884 */
885typedef enum {
886 G_NORMALIZE_DEFAULT,
887 G_NORMALIZE_NFD = G_NORMALIZE_DEFAULT,
888 G_NORMALIZE_DEFAULT_COMPOSE,
889 G_NORMALIZE_NFC = G_NORMALIZE_DEFAULT_COMPOSE,
890 G_NORMALIZE_ALL,
891 G_NORMALIZE_NFKD = G_NORMALIZE_ALL,
892 G_NORMALIZE_ALL_COMPOSE,
893 G_NORMALIZE_NFKC = G_NORMALIZE_ALL_COMPOSE
894} GNormalizeMode;
895
896GLIB_AVAILABLE_IN_ALL
897gchar *g_utf8_normalize (const gchar *str,
898 gssize len,
899 GNormalizeMode mode) G_GNUC_MALLOC;
900
901GLIB_AVAILABLE_IN_ALL
902gint g_utf8_collate (const gchar *str1,
903 const gchar *str2) G_GNUC_PURE;
904GLIB_AVAILABLE_IN_ALL
905gchar *g_utf8_collate_key (const gchar *str,
906 gssize len) G_GNUC_MALLOC;
907GLIB_AVAILABLE_IN_ALL
908gchar *g_utf8_collate_key_for_filename (const gchar *str,
909 gssize len) G_GNUC_MALLOC;
910
911GLIB_AVAILABLE_IN_2_52
912gchar *g_utf8_make_valid (const gchar *str,
913 gssize len) G_GNUC_MALLOC;
914
915G_END_DECLS
916
917#endif /* __G_UNICODE_H__ */
918