1/* gunicode.h - Unicode manipulation functions
2 *
3 * Copyright (C) 1999, 2000 Tom Tromey
4 * Copyright 2000, 2005 Red Hat, Inc.
5 *
6 * The Gnome Library is free software; you can redistribute it and/or
7 * modify it under the terms of the GNU Lesser General Public License as
8 * published by the Free Software Foundation; either version 2 of the
9 * License, or (at your option) any later version.
10 *
11 * The Gnome Library is distributed in the hope that it will be useful,
12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
14 * Lesser General Public License for more details.
15 *
16 * You should have received a copy of the GNU Lesser General Public
17 * License along with the Gnome Library; see the file COPYING.LIB. If not,
18 * see <http://www.gnu.org/licenses/>.
19 */
20
21#ifndef __G_UNICODE_H__
22#define __G_UNICODE_H__
23
24#if !defined (__GLIB_H_INSIDE__) && !defined (GLIB_COMPILATION)
25#error "Only <glib.h> can be included directly."
26#endif
27
28#include <glib/gerror.h>
29#include <glib/gtypes.h>
30
31G_BEGIN_DECLS
32
33/**
34 * gunichar:
35 *
36 * A type which can hold any UTF-32 or UCS-4 character code,
37 * also known as a Unicode code point.
38 *
39 * If you want to produce the UTF-8 representation of a #gunichar,
40 * use g_ucs4_to_utf8(). See also g_utf8_to_ucs4() for the reverse
41 * process.
42 *
43 * To print/scan values of this type as integer, use
44 * %G_GINT32_MODIFIER and/or %G_GUINT32_FORMAT.
45 *
46 * The notation to express a Unicode code point in running text is
47 * as a hexadecimal number with four to six digits and uppercase
48 * letters, prefixed by the string "U+". Leading zeros are omitted,
49 * unless the code point would have fewer than four hexadecimal digits.
50 * For example, "U+0041 LATIN CAPITAL LETTER A". To print a code point
51 * in the U+-notation, use the format string "U+\%04"G_GINT32_FORMAT"X".
52 * To scan, use the format string "U+\%06"G_GINT32_FORMAT"X".
53 *
54 * |[
55 * gunichar c;
56 * sscanf ("U+0041", "U+%06"G_GINT32_FORMAT"X", &amp;c)
57 * g_print ("Read U+%04"G_GINT32_FORMAT"X", c);
58 * ]|
59 */
60typedef guint32 gunichar;
61
62/**
63 * gunichar2:
64 *
65 * A type which can hold any UTF-16 code
66 * point<footnote id="utf16_surrogate_pairs">UTF-16 also has so called
67 * <firstterm>surrogate pairs</firstterm> to encode characters beyond
68 * the BMP as pairs of 16bit numbers. Surrogate pairs cannot be stored
69 * in a single gunichar2 field, but all GLib functions accepting gunichar2
70 * arrays will correctly interpret surrogate pairs.</footnote>.
71 *
72 * To print/scan values of this type to/from text you need to convert
73 * to/from UTF-8, using g_utf16_to_utf8()/g_utf8_to_utf16().
74 *
75 * To print/scan values of this type as integer, use
76 * %G_GINT16_MODIFIER and/or %G_GUINT16_FORMAT.
77 */
78typedef guint16 gunichar2;
79
80/**
81 * GUnicodeType:
82 * @G_UNICODE_CONTROL: General category "Other, Control" (Cc)
83 * @G_UNICODE_FORMAT: General category "Other, Format" (Cf)
84 * @G_UNICODE_UNASSIGNED: General category "Other, Not Assigned" (Cn)
85 * @G_UNICODE_PRIVATE_USE: General category "Other, Private Use" (Co)
86 * @G_UNICODE_SURROGATE: General category "Other, Surrogate" (Cs)
87 * @G_UNICODE_LOWERCASE_LETTER: General category "Letter, Lowercase" (Ll)
88 * @G_UNICODE_MODIFIER_LETTER: General category "Letter, Modifier" (Lm)
89 * @G_UNICODE_OTHER_LETTER: General category "Letter, Other" (Lo)
90 * @G_UNICODE_TITLECASE_LETTER: General category "Letter, Titlecase" (Lt)
91 * @G_UNICODE_UPPERCASE_LETTER: General category "Letter, Uppercase" (Lu)
92 * @G_UNICODE_SPACING_MARK: General category "Mark, Spacing" (Mc)
93 * @G_UNICODE_ENCLOSING_MARK: General category "Mark, Enclosing" (Me)
94 * @G_UNICODE_NON_SPACING_MARK: General category "Mark, Nonspacing" (Mn)
95 * @G_UNICODE_DECIMAL_NUMBER: General category "Number, Decimal Digit" (Nd)
96 * @G_UNICODE_LETTER_NUMBER: General category "Number, Letter" (Nl)
97 * @G_UNICODE_OTHER_NUMBER: General category "Number, Other" (No)
98 * @G_UNICODE_CONNECT_PUNCTUATION: General category "Punctuation, Connector" (Pc)
99 * @G_UNICODE_DASH_PUNCTUATION: General category "Punctuation, Dash" (Pd)
100 * @G_UNICODE_CLOSE_PUNCTUATION: General category "Punctuation, Close" (Pe)
101 * @G_UNICODE_FINAL_PUNCTUATION: General category "Punctuation, Final quote" (Pf)
102 * @G_UNICODE_INITIAL_PUNCTUATION: General category "Punctuation, Initial quote" (Pi)
103 * @G_UNICODE_OTHER_PUNCTUATION: General category "Punctuation, Other" (Po)
104 * @G_UNICODE_OPEN_PUNCTUATION: General category "Punctuation, Open" (Ps)
105 * @G_UNICODE_CURRENCY_SYMBOL: General category "Symbol, Currency" (Sc)
106 * @G_UNICODE_MODIFIER_SYMBOL: General category "Symbol, Modifier" (Sk)
107 * @G_UNICODE_MATH_SYMBOL: General category "Symbol, Math" (Sm)
108 * @G_UNICODE_OTHER_SYMBOL: General category "Symbol, Other" (So)
109 * @G_UNICODE_LINE_SEPARATOR: General category "Separator, Line" (Zl)
110 * @G_UNICODE_PARAGRAPH_SEPARATOR: General category "Separator, Paragraph" (Zp)
111 * @G_UNICODE_SPACE_SEPARATOR: General category "Separator, Space" (Zs)
112 *
113 * These are the possible character classifications from the
114 * Unicode specification.
115 * See <ulink url="http://www.unicode.org/Public/UNIDATA/UnicodeData.html">http://www.unicode.org/Public/UNIDATA/UnicodeData.html</ulink>.
116 */
117typedef enum
118{
119 G_UNICODE_CONTROL,
120 G_UNICODE_FORMAT,
121 G_UNICODE_UNASSIGNED,
122 G_UNICODE_PRIVATE_USE,
123 G_UNICODE_SURROGATE,
124 G_UNICODE_LOWERCASE_LETTER,
125 G_UNICODE_MODIFIER_LETTER,
126 G_UNICODE_OTHER_LETTER,
127 G_UNICODE_TITLECASE_LETTER,
128 G_UNICODE_UPPERCASE_LETTER,
129 G_UNICODE_SPACING_MARK,
130 G_UNICODE_ENCLOSING_MARK,
131 G_UNICODE_NON_SPACING_MARK,
132 G_UNICODE_DECIMAL_NUMBER,
133 G_UNICODE_LETTER_NUMBER,
134 G_UNICODE_OTHER_NUMBER,
135 G_UNICODE_CONNECT_PUNCTUATION,
136 G_UNICODE_DASH_PUNCTUATION,
137 G_UNICODE_CLOSE_PUNCTUATION,
138 G_UNICODE_FINAL_PUNCTUATION,
139 G_UNICODE_INITIAL_PUNCTUATION,
140 G_UNICODE_OTHER_PUNCTUATION,
141 G_UNICODE_OPEN_PUNCTUATION,
142 G_UNICODE_CURRENCY_SYMBOL,
143 G_UNICODE_MODIFIER_SYMBOL,
144 G_UNICODE_MATH_SYMBOL,
145 G_UNICODE_OTHER_SYMBOL,
146 G_UNICODE_LINE_SEPARATOR,
147 G_UNICODE_PARAGRAPH_SEPARATOR,
148 G_UNICODE_SPACE_SEPARATOR
149} GUnicodeType;
150
151/**
152 * G_UNICODE_COMBINING_MARK:
153 *
154 * Older name for %G_UNICODE_SPACING_MARK.
155 *
156 * Deprecated: 2.30: Use %G_UNICODE_SPACING_MARK.
157 */
158#ifndef G_DISABLE_DEPRECATED
159#define G_UNICODE_COMBINING_MARK G_UNICODE_SPACING_MARK
160#endif
161
162/**
163 * GUnicodeBreakType:
164 * @G_UNICODE_BREAK_MANDATORY: Mandatory Break (BK)
165 * @G_UNICODE_BREAK_CARRIAGE_RETURN: Carriage Return (CR)
166 * @G_UNICODE_BREAK_LINE_FEED: Line Feed (LF)
167 * @G_UNICODE_BREAK_COMBINING_MARK: Attached Characters and Combining Marks (CM)
168 * @G_UNICODE_BREAK_SURROGATE: Surrogates (SG)
169 * @G_UNICODE_BREAK_ZERO_WIDTH_SPACE: Zero Width Space (ZW)
170 * @G_UNICODE_BREAK_INSEPARABLE: Inseparable (IN)
171 * @G_UNICODE_BREAK_NON_BREAKING_GLUE: Non-breaking ("Glue") (GL)
172 * @G_UNICODE_BREAK_CONTINGENT: Contingent Break Opportunity (CB)
173 * @G_UNICODE_BREAK_SPACE: Space (SP)
174 * @G_UNICODE_BREAK_AFTER: Break Opportunity After (BA)
175 * @G_UNICODE_BREAK_BEFORE: Break Opportunity Before (BB)
176 * @G_UNICODE_BREAK_BEFORE_AND_AFTER: Break Opportunity Before and After (B2)
177 * @G_UNICODE_BREAK_HYPHEN: Hyphen (HY)
178 * @G_UNICODE_BREAK_NON_STARTER: Nonstarter (NS)
179 * @G_UNICODE_BREAK_OPEN_PUNCTUATION: Opening Punctuation (OP)
180 * @G_UNICODE_BREAK_CLOSE_PUNCTUATION: Closing Punctuation (CL)
181 * @G_UNICODE_BREAK_QUOTATION: Ambiguous Quotation (QU)
182 * @G_UNICODE_BREAK_EXCLAMATION: Exclamation/Interrogation (EX)
183 * @G_UNICODE_BREAK_IDEOGRAPHIC: Ideographic (ID)
184 * @G_UNICODE_BREAK_NUMERIC: Numeric (NU)
185 * @G_UNICODE_BREAK_INFIX_SEPARATOR: Infix Separator (Numeric) (IS)
186 * @G_UNICODE_BREAK_SYMBOL: Symbols Allowing Break After (SY)
187 * @G_UNICODE_BREAK_ALPHABETIC: Ordinary Alphabetic and Symbol Characters (AL)
188 * @G_UNICODE_BREAK_PREFIX: Prefix (Numeric) (PR)
189 * @G_UNICODE_BREAK_POSTFIX: Postfix (Numeric) (PO)
190 * @G_UNICODE_BREAK_COMPLEX_CONTEXT: Complex Content Dependent (South East Asian) (SA)
191 * @G_UNICODE_BREAK_AMBIGUOUS: Ambiguous (Alphabetic or Ideographic) (AI)
192 * @G_UNICODE_BREAK_UNKNOWN: Unknown (XX)
193 * @G_UNICODE_BREAK_NEXT_LINE: Next Line (NL)
194 * @G_UNICODE_BREAK_WORD_JOINER: Word Joiner (WJ)
195 * @G_UNICODE_BREAK_HANGUL_L_JAMO: Hangul L Jamo (JL)
196 * @G_UNICODE_BREAK_HANGUL_V_JAMO: Hangul V Jamo (JV)
197 * @G_UNICODE_BREAK_HANGUL_T_JAMO: Hangul T Jamo (JT)
198 * @G_UNICODE_BREAK_HANGUL_LV_SYLLABLE: Hangul LV Syllable (H2)
199 * @G_UNICODE_BREAK_HANGUL_LVT_SYLLABLE: Hangul LVT Syllable (H3)
200 * @G_UNICODE_BREAK_CLOSE_PARANTHESIS: Closing Parenthesis (CP). Since 2.28
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 *
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 <ulink url="http://www.unicode.org/unicode/reports/tr14/">http://www.unicode.org/unicode/reports/tr14/</ulink>.
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} GUnicodeBreakType;
255
256/**
257 * GUnicodeScript:
258 * @G_UNICODE_SCRIPT_INVALID_CODE:
259 * a value never returned from g_unichar_get_script()
260 * @G_UNICODE_SCRIPT_COMMON: a character used by multiple different scripts
261 * @G_UNICODE_SCRIPT_INHERITED: a mark glyph that takes its script from the
262 * base glyph to which it is attached
263 * @G_UNICODE_SCRIPT_ARABIC: Arabic
264 * @G_UNICODE_SCRIPT_ARMENIAN: Armenian
265 * @G_UNICODE_SCRIPT_BENGALI: Bengali
266 * @G_UNICODE_SCRIPT_BOPOMOFO: Bopomofo
267 * @G_UNICODE_SCRIPT_CHEROKEE: Cherokee
268 * @G_UNICODE_SCRIPT_COPTIC: Coptic
269 * @G_UNICODE_SCRIPT_CYRILLIC: Cyrillic
270 * @G_UNICODE_SCRIPT_DESERET: Deseret
271 * @G_UNICODE_SCRIPT_DEVANAGARI: Devanagari
272 * @G_UNICODE_SCRIPT_ETHIOPIC: Ethiopic
273 * @G_UNICODE_SCRIPT_GEORGIAN: Georgian
274 * @G_UNICODE_SCRIPT_GOTHIC: Gothic
275 * @G_UNICODE_SCRIPT_GREEK: Greek
276 * @G_UNICODE_SCRIPT_GUJARATI: Gujarati
277 * @G_UNICODE_SCRIPT_GURMUKHI: Gurmukhi
278 * @G_UNICODE_SCRIPT_HAN: Han
279 * @G_UNICODE_SCRIPT_HANGUL: Hangul
280 * @G_UNICODE_SCRIPT_HEBREW: Hebrew
281 * @G_UNICODE_SCRIPT_HIRAGANA: Hiragana
282 * @G_UNICODE_SCRIPT_KANNADA: Kannada
283 * @G_UNICODE_SCRIPT_KATAKANA: Katakana
284 * @G_UNICODE_SCRIPT_KHMER: Khmer
285 * @G_UNICODE_SCRIPT_LAO: Lao
286 * @G_UNICODE_SCRIPT_LATIN: Latin
287 * @G_UNICODE_SCRIPT_MALAYALAM: Malayalam
288 * @G_UNICODE_SCRIPT_MONGOLIAN: Mongolian
289 * @G_UNICODE_SCRIPT_MYANMAR: Myanmar
290 * @G_UNICODE_SCRIPT_OGHAM: Ogham
291 * @G_UNICODE_SCRIPT_OLD_ITALIC: Old Italic
292 * @G_UNICODE_SCRIPT_ORIYA: Oriya
293 * @G_UNICODE_SCRIPT_RUNIC: Runic
294 * @G_UNICODE_SCRIPT_SINHALA: Sinhala
295 * @G_UNICODE_SCRIPT_SYRIAC: Syriac
296 * @G_UNICODE_SCRIPT_TAMIL: Tamil
297 * @G_UNICODE_SCRIPT_TELUGU: Telugu
298 * @G_UNICODE_SCRIPT_THAANA: Thaana
299 * @G_UNICODE_SCRIPT_THAI: Thai
300 * @G_UNICODE_SCRIPT_TIBETAN: Tibetan
301 * @G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL:
302 * Canadian Aboriginal
303 * @G_UNICODE_SCRIPT_YI: Yi
304 * @G_UNICODE_SCRIPT_TAGALOG: Tagalog
305 * @G_UNICODE_SCRIPT_HANUNOO: Hanunoo
306 * @G_UNICODE_SCRIPT_BUHID: Buhid
307 * @G_UNICODE_SCRIPT_TAGBANWA: Tagbanwa
308 * @G_UNICODE_SCRIPT_BRAILLE: Braille
309 * @G_UNICODE_SCRIPT_CYPRIOT: Cypriot
310 * @G_UNICODE_SCRIPT_LIMBU: Limbu
311 * @G_UNICODE_SCRIPT_OSMANYA: Osmanya
312 * @G_UNICODE_SCRIPT_SHAVIAN: Shavian
313 * @G_UNICODE_SCRIPT_LINEAR_B: Linear B
314 * @G_UNICODE_SCRIPT_TAI_LE: Tai Le
315 * @G_UNICODE_SCRIPT_UGARITIC: Ugaritic
316 * @G_UNICODE_SCRIPT_NEW_TAI_LUE:
317 * New Tai Lue
318 * @G_UNICODE_SCRIPT_BUGINESE: Buginese
319 * @G_UNICODE_SCRIPT_GLAGOLITIC: Glagolitic
320 * @G_UNICODE_SCRIPT_TIFINAGH: Tifinagh
321 * @G_UNICODE_SCRIPT_SYLOTI_NAGRI:
322 * Syloti Nagri
323 * @G_UNICODE_SCRIPT_OLD_PERSIAN:
324 * Old Persian
325 * @G_UNICODE_SCRIPT_KHAROSHTHI: Kharoshthi
326 * @G_UNICODE_SCRIPT_UNKNOWN: an unassigned code point
327 * @G_UNICODE_SCRIPT_BALINESE: Balinese
328 * @G_UNICODE_SCRIPT_CUNEIFORM: Cuneiform
329 * @G_UNICODE_SCRIPT_PHOENICIAN: Phoenician
330 * @G_UNICODE_SCRIPT_PHAGS_PA: Phags-pa
331 * @G_UNICODE_SCRIPT_NKO: N'Ko
332 * @G_UNICODE_SCRIPT_KAYAH_LI: Kayah Li. Since 2.16.3
333 * @G_UNICODE_SCRIPT_LEPCHA: Lepcha. Since 2.16.3
334 * @G_UNICODE_SCRIPT_REJANG: Rejang. Since 2.16.3
335 * @G_UNICODE_SCRIPT_SUNDANESE: Sundanese. Since 2.16.3
336 * @G_UNICODE_SCRIPT_SAURASHTRA: Saurashtra. Since 2.16.3
337 * @G_UNICODE_SCRIPT_CHAM: Cham. Since 2.16.3
338 * @G_UNICODE_SCRIPT_OL_CHIKI: Ol Chiki. Since 2.16.3
339 * @G_UNICODE_SCRIPT_VAI: Vai. Since 2.16.3
340 * @G_UNICODE_SCRIPT_CARIAN: Carian. Since 2.16.3
341 * @G_UNICODE_SCRIPT_LYCIAN: Lycian. Since 2.16.3
342 * @G_UNICODE_SCRIPT_LYDIAN: Lydian. Since 2.16.3
343 * @G_UNICODE_SCRIPT_AVESTAN: Avestan. Since 2.26
344 * @G_UNICODE_SCRIPT_BAMUM: Bamum. Since 2.26
345 * @G_UNICODE_SCRIPT_EGYPTIAN_HIEROGLYPHS:
346 * Egyptian Hieroglpyhs. Since 2.26
347 * @G_UNICODE_SCRIPT_IMPERIAL_ARAMAIC:
348 * Imperial Aramaic. Since 2.26
349 * @G_UNICODE_SCRIPT_INSCRIPTIONAL_PAHLAVI:
350 * Inscriptional Pahlavi. Since 2.26
351 * @G_UNICODE_SCRIPT_INSCRIPTIONAL_PARTHIAN:
352 * Inscriptional Parthian. Since 2.26
353 * @G_UNICODE_SCRIPT_JAVANESE: Javanese. Since 2.26
354 * @G_UNICODE_SCRIPT_KAITHI: Kaithi. Since 2.26
355 * @G_UNICODE_SCRIPT_LISU: Lisu. Since 2.26
356 * @G_UNICODE_SCRIPT_MEETEI_MAYEK:
357 * Meetei Mayek. Since 2.26
358 * @G_UNICODE_SCRIPT_OLD_SOUTH_ARABIAN:
359 * Old South Arabian. Since 2.26
360 * @G_UNICODE_SCRIPT_OLD_TURKIC: Old Turkic. Since 2.28
361 * @G_UNICODE_SCRIPT_SAMARITAN: Samaritan. Since 2.26
362 * @G_UNICODE_SCRIPT_TAI_THAM: Tai Tham. Since 2.26
363 * @G_UNICODE_SCRIPT_TAI_VIET: Tai Viet. Since 2.26
364 * @G_UNICODE_SCRIPT_BATAK: Batak. Since 2.28
365 * @G_UNICODE_SCRIPT_BRAHMI: Brahmi. Since 2.28
366 * @G_UNICODE_SCRIPT_MANDAIC: Mandaic. Since 2.28
367 * @G_UNICODE_SCRIPT_CHAKMA: Chakma. Since: 2.32
368 * @G_UNICODE_SCRIPT_MEROITIC_CURSIVE: Meroitic Cursive. Since: 2.32
369 * @G_UNICODE_SCRIPT_MEROITIC_HIEROGLYPHS: Meroitic Hieroglyphs. Since: 2.32
370 * @G_UNICODE_SCRIPT_MIAO: Miao. Since: 2.32
371 * @G_UNICODE_SCRIPT_SHARADA: Sharada. Since: 2.32
372 * @G_UNICODE_SCRIPT_SORA_SOMPENG: Sora Sompeng. Since: 2.32
373 * @G_UNICODE_SCRIPT_TAKRI: Takri. Since: 2.32
374 * @G_UNICODE_SCRIPT_BASSA_VAH: Bassa. Since: 2.42
375 * @G_UNICODE_SCRIPT_CAUCASIAN_ALBANIAN: Caucasian Albanian. Since: 2.42
376 * @G_UNICODE_SCRIPT_DUPLOYAN: Duployan. Since: 2.42
377 * @G_UNICODE_SCRIPT_ELBASAN: Elbasan. Since: 2.42
378 * @G_UNICODE_SCRIPT_GRANTHA: Grantha. Since: 2.42
379 * @G_UNICODE_SCRIPT_KHOJKI: Kjohki. Since: 2.42
380 * @G_UNICODE_SCRIPT_KHUDAWADI: Khudawadi, Sindhi. Since: 2.42
381 * @G_UNICODE_SCRIPT_LINEAR_A: Linear A. Since: 2.42
382 * @G_UNICODE_SCRIPT_MAHAJANI: Mahajani. Since: 2.42
383 * @G_UNICODE_SCRIPT_MANICHAEAN: Manichaean. Since: 2.42
384 * @G_UNICODE_SCRIPT_MENDE_KIKAKUI: Mende Kikakui. Since: 2.42
385 * @G_UNICODE_SCRIPT_MODI: Modi. Since: 2.42
386 * @G_UNICODE_SCRIPT_MRO: Mro. Since: 2.42
387 * @G_UNICODE_SCRIPT_NABATAEAN: Nabataean. Since: 2.42
388 * @G_UNICODE_SCRIPT_OLD_NORTH_ARABIAN: Old North Arabian. Since: 2.42
389 * @G_UNICODE_SCRIPT_OLD_PERMIC: Old Permic. Since: 2.42
390 * @G_UNICODE_SCRIPT_PAHAWH_HMONG: Pahawh Hmong. Since: 2.42
391 * @G_UNICODE_SCRIPT_PALMYRENE: Palmyrene. Since: 2.42
392 * @G_UNICODE_SCRIPT_PAU_CIN_HAU: Pau Cin Hau. Since: 2.42
393 * @G_UNICODE_SCRIPT_PSALTER_PAHLAVI: Psalter Pahlavi. Since: 2.42
394 * @G_UNICODE_SCRIPT_SIDDHAM: Siddham. Since: 2.42
395 * @G_UNICODE_SCRIPT_TIRHUTA: Tirhuta. Since: 2.42
396 * @G_UNICODE_SCRIPT_WARANG_CITI: Warang Citi. Since: 2.42
397 * @G_UNICODE_SCRIPT_AHOM: Ahom. Since: 2.48
398 * @G_UNICODE_SCRIPT_ANATOLIAN_HIEROGLYPHS: Anatolian Hieroglyphs. Since: 2.48
399 * @G_UNICODE_SCRIPT_HATRAN: Hatran. Since: 2.48
400 * @G_UNICODE_SCRIPT_MULTANI: Multani. Since: 2.48
401 * @G_UNICODE_SCRIPT_OLD_HUNGARIAN: Old Hungarian. Since: 2.48
402 * @G_UNICODE_SCRIPT_SIGNWRITING: Signwriting. Since: 2.48
403 *
404 * The #GUnicodeScript enumeration identifies different writing
405 * systems. The values correspond to the names as defined in the
406 * Unicode standard. The enumeration has been added in GLib 2.14,
407 * and is interchangeable with #PangoScript.
408 *
409 * Note that new types may be added in the future. Applications
410 * should be ready to handle unknown values.
411 * See <ulink
412 * url="http://www.unicode.org/reports/tr24/">Unicode Standard Annex
413 * #24: Script names</ulink>.
414 */
415typedef enum
416{ /* ISO 15924 code */
417 G_UNICODE_SCRIPT_INVALID_CODE = -1,
418 G_UNICODE_SCRIPT_COMMON = 0, /* Zyyy */
419 G_UNICODE_SCRIPT_INHERITED, /* Zinh (Qaai) */
420 G_UNICODE_SCRIPT_ARABIC, /* Arab */
421 G_UNICODE_SCRIPT_ARMENIAN, /* Armn */
422 G_UNICODE_SCRIPT_BENGALI, /* Beng */
423 G_UNICODE_SCRIPT_BOPOMOFO, /* Bopo */
424 G_UNICODE_SCRIPT_CHEROKEE, /* Cher */
425 G_UNICODE_SCRIPT_COPTIC, /* Copt (Qaac) */
426 G_UNICODE_SCRIPT_CYRILLIC, /* Cyrl (Cyrs) */
427 G_UNICODE_SCRIPT_DESERET, /* Dsrt */
428 G_UNICODE_SCRIPT_DEVANAGARI, /* Deva */
429 G_UNICODE_SCRIPT_ETHIOPIC, /* Ethi */
430 G_UNICODE_SCRIPT_GEORGIAN, /* Geor (Geon, Geoa) */
431 G_UNICODE_SCRIPT_GOTHIC, /* Goth */
432 G_UNICODE_SCRIPT_GREEK, /* Grek */
433 G_UNICODE_SCRIPT_GUJARATI, /* Gujr */
434 G_UNICODE_SCRIPT_GURMUKHI, /* Guru */
435 G_UNICODE_SCRIPT_HAN, /* Hani */
436 G_UNICODE_SCRIPT_HANGUL, /* Hang */
437 G_UNICODE_SCRIPT_HEBREW, /* Hebr */
438 G_UNICODE_SCRIPT_HIRAGANA, /* Hira */
439 G_UNICODE_SCRIPT_KANNADA, /* Knda */
440 G_UNICODE_SCRIPT_KATAKANA, /* Kana */
441 G_UNICODE_SCRIPT_KHMER, /* Khmr */
442 G_UNICODE_SCRIPT_LAO, /* Laoo */
443 G_UNICODE_SCRIPT_LATIN, /* Latn (Latf, Latg) */
444 G_UNICODE_SCRIPT_MALAYALAM, /* Mlym */
445 G_UNICODE_SCRIPT_MONGOLIAN, /* Mong */
446 G_UNICODE_SCRIPT_MYANMAR, /* Mymr */
447 G_UNICODE_SCRIPT_OGHAM, /* Ogam */
448 G_UNICODE_SCRIPT_OLD_ITALIC, /* Ital */
449 G_UNICODE_SCRIPT_ORIYA, /* Orya */
450 G_UNICODE_SCRIPT_RUNIC, /* Runr */
451 G_UNICODE_SCRIPT_SINHALA, /* Sinh */
452 G_UNICODE_SCRIPT_SYRIAC, /* Syrc (Syrj, Syrn, Syre) */
453 G_UNICODE_SCRIPT_TAMIL, /* Taml */
454 G_UNICODE_SCRIPT_TELUGU, /* Telu */
455 G_UNICODE_SCRIPT_THAANA, /* Thaa */
456 G_UNICODE_SCRIPT_THAI, /* Thai */
457 G_UNICODE_SCRIPT_TIBETAN, /* Tibt */
458 G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL, /* Cans */
459 G_UNICODE_SCRIPT_YI, /* Yiii */
460 G_UNICODE_SCRIPT_TAGALOG, /* Tglg */
461 G_UNICODE_SCRIPT_HANUNOO, /* Hano */
462 G_UNICODE_SCRIPT_BUHID, /* Buhd */
463 G_UNICODE_SCRIPT_TAGBANWA, /* Tagb */
464
465 /* Unicode-4.0 additions */
466 G_UNICODE_SCRIPT_BRAILLE, /* Brai */
467 G_UNICODE_SCRIPT_CYPRIOT, /* Cprt */
468 G_UNICODE_SCRIPT_LIMBU, /* Limb */
469 G_UNICODE_SCRIPT_OSMANYA, /* Osma */
470 G_UNICODE_SCRIPT_SHAVIAN, /* Shaw */
471 G_UNICODE_SCRIPT_LINEAR_B, /* Linb */
472 G_UNICODE_SCRIPT_TAI_LE, /* Tale */
473 G_UNICODE_SCRIPT_UGARITIC, /* Ugar */
474
475 /* Unicode-4.1 additions */
476 G_UNICODE_SCRIPT_NEW_TAI_LUE, /* Talu */
477 G_UNICODE_SCRIPT_BUGINESE, /* Bugi */
478 G_UNICODE_SCRIPT_GLAGOLITIC, /* Glag */
479 G_UNICODE_SCRIPT_TIFINAGH, /* Tfng */
480 G_UNICODE_SCRIPT_SYLOTI_NAGRI, /* Sylo */
481 G_UNICODE_SCRIPT_OLD_PERSIAN, /* Xpeo */
482 G_UNICODE_SCRIPT_KHAROSHTHI, /* Khar */
483
484 /* Unicode-5.0 additions */
485 G_UNICODE_SCRIPT_UNKNOWN, /* Zzzz */
486 G_UNICODE_SCRIPT_BALINESE, /* Bali */
487 G_UNICODE_SCRIPT_CUNEIFORM, /* Xsux */
488 G_UNICODE_SCRIPT_PHOENICIAN, /* Phnx */
489 G_UNICODE_SCRIPT_PHAGS_PA, /* Phag */
490 G_UNICODE_SCRIPT_NKO, /* Nkoo */
491
492 /* Unicode-5.1 additions */
493 G_UNICODE_SCRIPT_KAYAH_LI, /* Kali */
494 G_UNICODE_SCRIPT_LEPCHA, /* Lepc */
495 G_UNICODE_SCRIPT_REJANG, /* Rjng */
496 G_UNICODE_SCRIPT_SUNDANESE, /* Sund */
497 G_UNICODE_SCRIPT_SAURASHTRA, /* Saur */
498 G_UNICODE_SCRIPT_CHAM, /* Cham */
499 G_UNICODE_SCRIPT_OL_CHIKI, /* Olck */
500 G_UNICODE_SCRIPT_VAI, /* Vaii */
501 G_UNICODE_SCRIPT_CARIAN, /* Cari */
502 G_UNICODE_SCRIPT_LYCIAN, /* Lyci */
503 G_UNICODE_SCRIPT_LYDIAN, /* Lydi */
504
505 /* Unicode-5.2 additions */
506 G_UNICODE_SCRIPT_AVESTAN, /* Avst */
507 G_UNICODE_SCRIPT_BAMUM, /* Bamu */
508 G_UNICODE_SCRIPT_EGYPTIAN_HIEROGLYPHS, /* Egyp */
509 G_UNICODE_SCRIPT_IMPERIAL_ARAMAIC, /* Armi */
510 G_UNICODE_SCRIPT_INSCRIPTIONAL_PAHLAVI, /* Phli */
511 G_UNICODE_SCRIPT_INSCRIPTIONAL_PARTHIAN, /* Prti */
512 G_UNICODE_SCRIPT_JAVANESE, /* Java */
513 G_UNICODE_SCRIPT_KAITHI, /* Kthi */
514 G_UNICODE_SCRIPT_LISU, /* Lisu */
515 G_UNICODE_SCRIPT_MEETEI_MAYEK, /* Mtei */
516 G_UNICODE_SCRIPT_OLD_SOUTH_ARABIAN, /* Sarb */
517 G_UNICODE_SCRIPT_OLD_TURKIC, /* Orkh */
518 G_UNICODE_SCRIPT_SAMARITAN, /* Samr */
519 G_UNICODE_SCRIPT_TAI_THAM, /* Lana */
520 G_UNICODE_SCRIPT_TAI_VIET, /* Tavt */
521
522 /* Unicode-6.0 additions */
523 G_UNICODE_SCRIPT_BATAK, /* Batk */
524 G_UNICODE_SCRIPT_BRAHMI, /* Brah */
525 G_UNICODE_SCRIPT_MANDAIC, /* Mand */
526
527 /* Unicode-6.1 additions */
528 G_UNICODE_SCRIPT_CHAKMA, /* Cakm */
529 G_UNICODE_SCRIPT_MEROITIC_CURSIVE, /* Merc */
530 G_UNICODE_SCRIPT_MEROITIC_HIEROGLYPHS, /* Mero */
531 G_UNICODE_SCRIPT_MIAO, /* Plrd */
532 G_UNICODE_SCRIPT_SHARADA, /* Shrd */
533 G_UNICODE_SCRIPT_SORA_SOMPENG, /* Sora */
534 G_UNICODE_SCRIPT_TAKRI, /* Takr */
535
536 /* Unicode 7.0 additions */
537 G_UNICODE_SCRIPT_BASSA_VAH, /* Bass */
538 G_UNICODE_SCRIPT_CAUCASIAN_ALBANIAN, /* Aghb */
539 G_UNICODE_SCRIPT_DUPLOYAN, /* Dupl */
540 G_UNICODE_SCRIPT_ELBASAN, /* Elba */
541 G_UNICODE_SCRIPT_GRANTHA, /* Gran */
542 G_UNICODE_SCRIPT_KHOJKI, /* Khoj */
543 G_UNICODE_SCRIPT_KHUDAWADI, /* Sind */
544 G_UNICODE_SCRIPT_LINEAR_A, /* Lina */
545 G_UNICODE_SCRIPT_MAHAJANI, /* Mahj */
546 G_UNICODE_SCRIPT_MANICHAEAN, /* Manu */
547 G_UNICODE_SCRIPT_MENDE_KIKAKUI, /* Mend */
548 G_UNICODE_SCRIPT_MODI, /* Modi */
549 G_UNICODE_SCRIPT_MRO, /* Mroo */
550 G_UNICODE_SCRIPT_NABATAEAN, /* Nbat */
551 G_UNICODE_SCRIPT_OLD_NORTH_ARABIAN, /* Narb */
552 G_UNICODE_SCRIPT_OLD_PERMIC, /* Perm */
553 G_UNICODE_SCRIPT_PAHAWH_HMONG, /* Hmng */
554 G_UNICODE_SCRIPT_PALMYRENE, /* Palm */
555 G_UNICODE_SCRIPT_PAU_CIN_HAU, /* Pauc */
556 G_UNICODE_SCRIPT_PSALTER_PAHLAVI, /* Phlp */
557 G_UNICODE_SCRIPT_SIDDHAM, /* Sidd */
558 G_UNICODE_SCRIPT_TIRHUTA, /* Tirh */
559 G_UNICODE_SCRIPT_WARANG_CITI, /* Wara */
560
561 /* Unicode 8.0 additions */
562 G_UNICODE_SCRIPT_AHOM, /* Ahom */
563 G_UNICODE_SCRIPT_ANATOLIAN_HIEROGLYPHS, /* Hluw */
564 G_UNICODE_SCRIPT_HATRAN, /* Hatr */
565 G_UNICODE_SCRIPT_MULTANI, /* Mult */
566 G_UNICODE_SCRIPT_OLD_HUNGARIAN, /* Hung */
567 G_UNICODE_SCRIPT_SIGNWRITING /* Sgnw */
568} GUnicodeScript;
569
570GLIB_AVAILABLE_IN_ALL
571guint32 g_unicode_script_to_iso15924 (GUnicodeScript script);
572GLIB_AVAILABLE_IN_ALL
573GUnicodeScript g_unicode_script_from_iso15924 (guint32 iso15924);
574
575/* These are all analogs of the <ctype.h> functions.
576 */
577GLIB_AVAILABLE_IN_ALL
578gboolean g_unichar_isalnum (gunichar c) G_GNUC_CONST;
579GLIB_AVAILABLE_IN_ALL
580gboolean g_unichar_isalpha (gunichar c) G_GNUC_CONST;
581GLIB_AVAILABLE_IN_ALL
582gboolean g_unichar_iscntrl (gunichar c) G_GNUC_CONST;
583GLIB_AVAILABLE_IN_ALL
584gboolean g_unichar_isdigit (gunichar c) G_GNUC_CONST;
585GLIB_AVAILABLE_IN_ALL
586gboolean g_unichar_isgraph (gunichar c) G_GNUC_CONST;
587GLIB_AVAILABLE_IN_ALL
588gboolean g_unichar_islower (gunichar c) G_GNUC_CONST;
589GLIB_AVAILABLE_IN_ALL
590gboolean g_unichar_isprint (gunichar c) G_GNUC_CONST;
591GLIB_AVAILABLE_IN_ALL
592gboolean g_unichar_ispunct (gunichar c) G_GNUC_CONST;
593GLIB_AVAILABLE_IN_ALL
594gboolean g_unichar_isspace (gunichar c) G_GNUC_CONST;
595GLIB_AVAILABLE_IN_ALL
596gboolean g_unichar_isupper (gunichar c) G_GNUC_CONST;
597GLIB_AVAILABLE_IN_ALL
598gboolean g_unichar_isxdigit (gunichar c) G_GNUC_CONST;
599GLIB_AVAILABLE_IN_ALL
600gboolean g_unichar_istitle (gunichar c) G_GNUC_CONST;
601GLIB_AVAILABLE_IN_ALL
602gboolean g_unichar_isdefined (gunichar c) G_GNUC_CONST;
603GLIB_AVAILABLE_IN_ALL
604gboolean g_unichar_iswide (gunichar c) G_GNUC_CONST;
605GLIB_AVAILABLE_IN_ALL
606gboolean g_unichar_iswide_cjk(gunichar c) G_GNUC_CONST;
607GLIB_AVAILABLE_IN_ALL
608gboolean g_unichar_iszerowidth(gunichar c) G_GNUC_CONST;
609GLIB_AVAILABLE_IN_ALL
610gboolean g_unichar_ismark (gunichar c) G_GNUC_CONST;
611
612/* More <ctype.h> functions. These convert between the three cases.
613 * See the Unicode book to understand title case. */
614GLIB_AVAILABLE_IN_ALL
615gunichar g_unichar_toupper (gunichar c) G_GNUC_CONST;
616GLIB_AVAILABLE_IN_ALL
617gunichar g_unichar_tolower (gunichar c) G_GNUC_CONST;
618GLIB_AVAILABLE_IN_ALL
619gunichar g_unichar_totitle (gunichar c) G_GNUC_CONST;
620
621/* If C is a digit (according to 'g_unichar_isdigit'), then return its
622 numeric value. Otherwise return -1. */
623GLIB_AVAILABLE_IN_ALL
624gint g_unichar_digit_value (gunichar c) G_GNUC_CONST;
625
626GLIB_AVAILABLE_IN_ALL
627gint g_unichar_xdigit_value (gunichar c) G_GNUC_CONST;
628
629/* Return the Unicode character type of a given character. */
630GLIB_AVAILABLE_IN_ALL
631GUnicodeType g_unichar_type (gunichar c) G_GNUC_CONST;
632
633/* Return the line break property for a given character */
634GLIB_AVAILABLE_IN_ALL
635GUnicodeBreakType g_unichar_break_type (gunichar c) G_GNUC_CONST;
636
637/* Returns the combining class for a given character */
638GLIB_AVAILABLE_IN_ALL
639gint g_unichar_combining_class (gunichar uc) G_GNUC_CONST;
640
641GLIB_AVAILABLE_IN_ALL
642gboolean g_unichar_get_mirror_char (gunichar ch,
643 gunichar *mirrored_ch);
644
645GLIB_AVAILABLE_IN_ALL
646GUnicodeScript g_unichar_get_script (gunichar ch) G_GNUC_CONST;
647
648/* Validate a Unicode character */
649GLIB_AVAILABLE_IN_ALL
650gboolean g_unichar_validate (gunichar ch) G_GNUC_CONST;
651
652/* Pairwise canonical compose/decompose */
653GLIB_AVAILABLE_IN_ALL
654gboolean g_unichar_compose (gunichar a,
655 gunichar b,
656 gunichar *ch);
657GLIB_AVAILABLE_IN_ALL
658gboolean g_unichar_decompose (gunichar ch,
659 gunichar *a,
660 gunichar *b);
661
662GLIB_AVAILABLE_IN_ALL
663gsize g_unichar_fully_decompose (gunichar ch,
664 gboolean compat,
665 gunichar *result,
666 gsize result_len);
667
668/**
669 * G_UNICHAR_MAX_DECOMPOSITION_LENGTH:
670 *
671 * The maximum length (in codepoints) of a compatibility or canonical
672 * decomposition of a single Unicode character.
673 *
674 * This is as defined by Unicode 6.1.
675 *
676 * Since: 2.32
677 */
678#define G_UNICHAR_MAX_DECOMPOSITION_LENGTH 18 /* codepoints */
679
680/* Compute canonical ordering of a string in-place. This rearranges
681 decomposed characters in the string according to their combining
682 classes. See the Unicode manual for more information. */
683GLIB_AVAILABLE_IN_ALL
684void g_unicode_canonical_ordering (gunichar *string,
685 gsize len);
686
687
688GLIB_DEPRECATED_IN_2_30
689gunichar *g_unicode_canonical_decomposition (gunichar ch,
690 gsize *result_len) G_GNUC_MALLOC;
691
692/* Array of skip-bytes-per-initial character.
693 */
694GLIB_VAR const gchar * const g_utf8_skip;
695
696/**
697 * g_utf8_next_char:
698 * @p: Pointer to the start of a valid UTF-8 character
699 *
700 * Skips to the next character in a UTF-8 string. The string must be
701 * valid; this macro is as fast as possible, and has no error-checking.
702 * You would use this macro to iterate over a string character by
703 * character. The macro returns the start of the next UTF-8 character.
704 * Before using this macro, use g_utf8_validate() to validate strings
705 * that may contain invalid UTF-8.
706 */
707#define g_utf8_next_char(p) (char *)((p) + g_utf8_skip[*(const guchar *)(p)])
708
709GLIB_AVAILABLE_IN_ALL
710gunichar g_utf8_get_char (const gchar *p) G_GNUC_PURE;
711GLIB_AVAILABLE_IN_ALL
712gunichar g_utf8_get_char_validated (const gchar *p,
713 gssize max_len) G_GNUC_PURE;
714
715GLIB_AVAILABLE_IN_ALL
716gchar* g_utf8_offset_to_pointer (const gchar *str,
717 glong offset) G_GNUC_PURE;
718GLIB_AVAILABLE_IN_ALL
719glong g_utf8_pointer_to_offset (const gchar *str,
720 const gchar *pos) G_GNUC_PURE;
721GLIB_AVAILABLE_IN_ALL
722gchar* g_utf8_prev_char (const gchar *p) G_GNUC_PURE;
723GLIB_AVAILABLE_IN_ALL
724gchar* g_utf8_find_next_char (const gchar *p,
725 const gchar *end) G_GNUC_PURE;
726GLIB_AVAILABLE_IN_ALL
727gchar* g_utf8_find_prev_char (const gchar *str,
728 const gchar *p) G_GNUC_PURE;
729
730GLIB_AVAILABLE_IN_ALL
731glong g_utf8_strlen (const gchar *p,
732 gssize max) G_GNUC_PURE;
733
734GLIB_AVAILABLE_IN_2_30
735gchar *g_utf8_substring (const gchar *str,
736 glong start_pos,
737 glong end_pos) G_GNUC_MALLOC;
738
739GLIB_AVAILABLE_IN_ALL
740gchar *g_utf8_strncpy (gchar *dest,
741 const gchar *src,
742 gsize n);
743
744/* Find the UTF-8 character corresponding to ch, in string p. These
745 functions are equivalants to strchr and strrchr */
746GLIB_AVAILABLE_IN_ALL
747gchar* g_utf8_strchr (const gchar *p,
748 gssize len,
749 gunichar c);
750GLIB_AVAILABLE_IN_ALL
751gchar* g_utf8_strrchr (const gchar *p,
752 gssize len,
753 gunichar c);
754GLIB_AVAILABLE_IN_ALL
755gchar* g_utf8_strreverse (const gchar *str,
756 gssize len);
757
758GLIB_AVAILABLE_IN_ALL
759gunichar2 *g_utf8_to_utf16 (const gchar *str,
760 glong len,
761 glong *items_read,
762 glong *items_written,
763 GError **error) G_GNUC_MALLOC;
764GLIB_AVAILABLE_IN_ALL
765gunichar * g_utf8_to_ucs4 (const gchar *str,
766 glong len,
767 glong *items_read,
768 glong *items_written,
769 GError **error) G_GNUC_MALLOC;
770GLIB_AVAILABLE_IN_ALL
771gunichar * g_utf8_to_ucs4_fast (const gchar *str,
772 glong len,
773 glong *items_written) G_GNUC_MALLOC;
774GLIB_AVAILABLE_IN_ALL
775gunichar * g_utf16_to_ucs4 (const gunichar2 *str,
776 glong len,
777 glong *items_read,
778 glong *items_written,
779 GError **error) G_GNUC_MALLOC;
780GLIB_AVAILABLE_IN_ALL
781gchar* g_utf16_to_utf8 (const gunichar2 *str,
782 glong len,
783 glong *items_read,
784 glong *items_written,
785 GError **error) G_GNUC_MALLOC;
786GLIB_AVAILABLE_IN_ALL
787gunichar2 *g_ucs4_to_utf16 (const gunichar *str,
788 glong len,
789 glong *items_read,
790 glong *items_written,
791 GError **error) G_GNUC_MALLOC;
792GLIB_AVAILABLE_IN_ALL
793gchar* g_ucs4_to_utf8 (const gunichar *str,
794 glong len,
795 glong *items_read,
796 glong *items_written,
797 GError **error) G_GNUC_MALLOC;
798
799GLIB_AVAILABLE_IN_ALL
800gint g_unichar_to_utf8 (gunichar c,
801 gchar *outbuf);
802
803GLIB_AVAILABLE_IN_ALL
804gboolean g_utf8_validate (const gchar *str,
805 gssize max_len,
806 const gchar **end);
807
808GLIB_AVAILABLE_IN_ALL
809gchar *g_utf8_strup (const gchar *str,
810 gssize len) G_GNUC_MALLOC;
811GLIB_AVAILABLE_IN_ALL
812gchar *g_utf8_strdown (const gchar *str,
813 gssize len) G_GNUC_MALLOC;
814GLIB_AVAILABLE_IN_ALL
815gchar *g_utf8_casefold (const gchar *str,
816 gssize len) G_GNUC_MALLOC;
817
818/**
819 * GNormalizeMode:
820 * @G_NORMALIZE_DEFAULT: standardize differences that do not affect the
821 * text content, such as the above-mentioned accent representation
822 * @G_NORMALIZE_NFD: another name for %G_NORMALIZE_DEFAULT
823 * @G_NORMALIZE_DEFAULT_COMPOSE: like %G_NORMALIZE_DEFAULT, but with
824 * composed forms rather than a maximally decomposed form
825 * @G_NORMALIZE_NFC: another name for %G_NORMALIZE_DEFAULT_COMPOSE
826 * @G_NORMALIZE_ALL: beyond %G_NORMALIZE_DEFAULT also standardize the
827 * "compatibility" characters in Unicode, such as SUPERSCRIPT THREE
828 * to the standard forms (in this case DIGIT THREE). Formatting
829 * information may be lost but for most text operations such
830 * characters should be considered the same
831 * @G_NORMALIZE_NFKD: another name for %G_NORMALIZE_ALL
832 * @G_NORMALIZE_ALL_COMPOSE: like %G_NORMALIZE_ALL, but with composed
833 * forms rather than a maximally decomposed form
834 * @G_NORMALIZE_NFKC: another name for %G_NORMALIZE_ALL_COMPOSE
835 *
836 * Defines how a Unicode string is transformed in a canonical
837 * form, standardizing such issues as whether a character with
838 * an accent is represented as a base character and combining
839 * accent or as a single precomposed character. Unicode strings
840 * should generally be normalized before comparing them.
841 */
842typedef enum {
843 G_NORMALIZE_DEFAULT,
844 G_NORMALIZE_NFD = G_NORMALIZE_DEFAULT,
845 G_NORMALIZE_DEFAULT_COMPOSE,
846 G_NORMALIZE_NFC = G_NORMALIZE_DEFAULT_COMPOSE,
847 G_NORMALIZE_ALL,
848 G_NORMALIZE_NFKD = G_NORMALIZE_ALL,
849 G_NORMALIZE_ALL_COMPOSE,
850 G_NORMALIZE_NFKC = G_NORMALIZE_ALL_COMPOSE
851} GNormalizeMode;
852
853GLIB_AVAILABLE_IN_ALL
854gchar *g_utf8_normalize (const gchar *str,
855 gssize len,
856 GNormalizeMode mode) G_GNUC_MALLOC;
857
858GLIB_AVAILABLE_IN_ALL
859gint g_utf8_collate (const gchar *str1,
860 const gchar *str2) G_GNUC_PURE;
861GLIB_AVAILABLE_IN_ALL
862gchar *g_utf8_collate_key (const gchar *str,
863 gssize len) G_GNUC_MALLOC;
864GLIB_AVAILABLE_IN_ALL
865gchar *g_utf8_collate_key_for_filename (const gchar *str,
866 gssize len) G_GNUC_MALLOC;
867
868
869/* private */
870gchar *_g_utf8_make_valid (const gchar *name);
871
872G_END_DECLS
873
874#endif /* __G_UNICODE_H__ */
875