EIC code displayed by LXR |
|
|
|
|||
File indexing completed on 2025-12-22 10:14:08
0001 /* gunicode.h - Unicode manipulation functions 0002 * 0003 * Copyright (C) 1999, 2000 Tom Tromey 0004 * Copyright 2000, 2005 Red Hat, Inc. 0005 * 0006 * SPDX-License-Identifier: LGPL-2.1-or-later 0007 * 0008 * This library is free software; you can redistribute it and/or 0009 * modify it under the terms of the GNU Lesser General Public 0010 * License as published by the Free Software Foundation; either 0011 * version 2.1 of the License, or (at your option) any later version. 0012 * 0013 * This library is distributed in the hope that it will be useful, 0014 * but WITHOUT ANY WARRANTY; without even the implied warranty of 0015 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 0016 * Lesser General Public License for more details. 0017 * 0018 * You should have received a copy of the GNU Lesser General Public License 0019 * along with this library; if not, see <http://www.gnu.org/licenses/>. 0020 */ 0021 0022 #ifndef __G_UNICODE_H__ 0023 #define __G_UNICODE_H__ 0024 0025 #if !defined (__GLIB_H_INSIDE__) && !defined (GLIB_COMPILATION) 0026 #error "Only <glib.h> can be included directly." 0027 #endif 0028 0029 #include <glib/gerror.h> 0030 #include <glib/gtypes.h> 0031 0032 G_BEGIN_DECLS 0033 0034 /** 0035 * gunichar: 0036 * 0037 * A type which can hold any UTF-32 or UCS-4 character code, 0038 * also known as a Unicode code point. 0039 * 0040 * If you want to produce the UTF-8 representation of a #gunichar, 0041 * use g_ucs4_to_utf8(). See also g_utf8_to_ucs4() for the reverse 0042 * process. 0043 * 0044 * To print/scan values of this type as integer, use 0045 * %G_GINT32_MODIFIER and/or %G_GUINT32_FORMAT. 0046 * 0047 * The notation to express a Unicode code point in running text is 0048 * as a hexadecimal number with four to six digits and uppercase 0049 * letters, prefixed by the string "U+". Leading zeros are omitted, 0050 * unless the code point would have fewer than four hexadecimal digits. 0051 * For example, "U+0041 LATIN CAPITAL LETTER A". To print a code point 0052 * in the U+-notation, use the format string "U+\%04"G_GINT32_FORMAT"X". 0053 * To scan, use the format string "U+\%06"G_GINT32_FORMAT"X". 0054 * 0055 * |[ 0056 * gunichar c; 0057 * sscanf ("U+0041", "U+%06"G_GINT32_FORMAT"X", &c) 0058 * g_print ("Read U+%04"G_GINT32_FORMAT"X", c); 0059 * ]| 0060 */ 0061 typedef guint32 gunichar; 0062 0063 /** 0064 * gunichar2: 0065 * 0066 * A type which can hold any UTF-16 code 0067 * point<footnote id="utf16_surrogate_pairs">UTF-16 also has so called 0068 * <firstterm>surrogate pairs</firstterm> to encode characters beyond 0069 * the BMP as pairs of 16bit numbers. Surrogate pairs cannot be stored 0070 * in a single gunichar2 field, but all GLib functions accepting gunichar2 0071 * arrays will correctly interpret surrogate pairs.</footnote>. 0072 * 0073 * To print/scan values of this type to/from text you need to convert 0074 * to/from UTF-8, using g_utf16_to_utf8()/g_utf8_to_utf16(). 0075 * 0076 * To print/scan values of this type as integer, use 0077 * %G_GINT16_MODIFIER and/or %G_GUINT16_FORMAT. 0078 */ 0079 typedef guint16 gunichar2; 0080 0081 /** 0082 * GUnicodeType: 0083 * @G_UNICODE_CONTROL: General category "Other, Control" (Cc) 0084 * @G_UNICODE_FORMAT: General category "Other, Format" (Cf) 0085 * @G_UNICODE_UNASSIGNED: General category "Other, Not Assigned" (Cn) 0086 * @G_UNICODE_PRIVATE_USE: General category "Other, Private Use" (Co) 0087 * @G_UNICODE_SURROGATE: General category "Other, Surrogate" (Cs) 0088 * @G_UNICODE_LOWERCASE_LETTER: General category "Letter, Lowercase" (Ll) 0089 * @G_UNICODE_MODIFIER_LETTER: General category "Letter, Modifier" (Lm) 0090 * @G_UNICODE_OTHER_LETTER: General category "Letter, Other" (Lo) 0091 * @G_UNICODE_TITLECASE_LETTER: General category "Letter, Titlecase" (Lt) 0092 * @G_UNICODE_UPPERCASE_LETTER: General category "Letter, Uppercase" (Lu) 0093 * @G_UNICODE_SPACING_MARK: General category "Mark, Spacing" (Mc) 0094 * @G_UNICODE_ENCLOSING_MARK: General category "Mark, Enclosing" (Me) 0095 * @G_UNICODE_NON_SPACING_MARK: General category "Mark, Nonspacing" (Mn) 0096 * @G_UNICODE_DECIMAL_NUMBER: General category "Number, Decimal Digit" (Nd) 0097 * @G_UNICODE_LETTER_NUMBER: General category "Number, Letter" (Nl) 0098 * @G_UNICODE_OTHER_NUMBER: General category "Number, Other" (No) 0099 * @G_UNICODE_CONNECT_PUNCTUATION: General category "Punctuation, Connector" (Pc) 0100 * @G_UNICODE_DASH_PUNCTUATION: General category "Punctuation, Dash" (Pd) 0101 * @G_UNICODE_CLOSE_PUNCTUATION: General category "Punctuation, Close" (Pe) 0102 * @G_UNICODE_FINAL_PUNCTUATION: General category "Punctuation, Final quote" (Pf) 0103 * @G_UNICODE_INITIAL_PUNCTUATION: General category "Punctuation, Initial quote" (Pi) 0104 * @G_UNICODE_OTHER_PUNCTUATION: General category "Punctuation, Other" (Po) 0105 * @G_UNICODE_OPEN_PUNCTUATION: General category "Punctuation, Open" (Ps) 0106 * @G_UNICODE_CURRENCY_SYMBOL: General category "Symbol, Currency" (Sc) 0107 * @G_UNICODE_MODIFIER_SYMBOL: General category "Symbol, Modifier" (Sk) 0108 * @G_UNICODE_MATH_SYMBOL: General category "Symbol, Math" (Sm) 0109 * @G_UNICODE_OTHER_SYMBOL: General category "Symbol, Other" (So) 0110 * @G_UNICODE_LINE_SEPARATOR: General category "Separator, Line" (Zl) 0111 * @G_UNICODE_PARAGRAPH_SEPARATOR: General category "Separator, Paragraph" (Zp) 0112 * @G_UNICODE_SPACE_SEPARATOR: General category "Separator, Space" (Zs) 0113 * 0114 * These are the possible character classifications from the 0115 * Unicode specification. 0116 * See [Unicode Character Database](http://www.unicode.org/reports/tr44/#General_Category_Values). 0117 */ 0118 typedef enum 0119 { 0120 G_UNICODE_CONTROL, 0121 G_UNICODE_FORMAT, 0122 G_UNICODE_UNASSIGNED, 0123 G_UNICODE_PRIVATE_USE, 0124 G_UNICODE_SURROGATE, 0125 G_UNICODE_LOWERCASE_LETTER, 0126 G_UNICODE_MODIFIER_LETTER, 0127 G_UNICODE_OTHER_LETTER, 0128 G_UNICODE_TITLECASE_LETTER, 0129 G_UNICODE_UPPERCASE_LETTER, 0130 G_UNICODE_SPACING_MARK, 0131 G_UNICODE_ENCLOSING_MARK, 0132 G_UNICODE_NON_SPACING_MARK, 0133 G_UNICODE_DECIMAL_NUMBER, 0134 G_UNICODE_LETTER_NUMBER, 0135 G_UNICODE_OTHER_NUMBER, 0136 G_UNICODE_CONNECT_PUNCTUATION, 0137 G_UNICODE_DASH_PUNCTUATION, 0138 G_UNICODE_CLOSE_PUNCTUATION, 0139 G_UNICODE_FINAL_PUNCTUATION, 0140 G_UNICODE_INITIAL_PUNCTUATION, 0141 G_UNICODE_OTHER_PUNCTUATION, 0142 G_UNICODE_OPEN_PUNCTUATION, 0143 G_UNICODE_CURRENCY_SYMBOL, 0144 G_UNICODE_MODIFIER_SYMBOL, 0145 G_UNICODE_MATH_SYMBOL, 0146 G_UNICODE_OTHER_SYMBOL, 0147 G_UNICODE_LINE_SEPARATOR, 0148 G_UNICODE_PARAGRAPH_SEPARATOR, 0149 G_UNICODE_SPACE_SEPARATOR 0150 } GUnicodeType; 0151 0152 /** 0153 * G_UNICODE_COMBINING_MARK: 0154 * 0155 * Older name for %G_UNICODE_SPACING_MARK. 0156 * 0157 * Deprecated: 2.30: Use %G_UNICODE_SPACING_MARK. 0158 */ 0159 #define G_UNICODE_COMBINING_MARK G_UNICODE_SPACING_MARK GLIB_DEPRECATED_MACRO_IN_2_30_FOR(G_UNICODE_SPACING_MARK) 0160 0161 /** 0162 * GUnicodeBreakType: 0163 * @G_UNICODE_BREAK_MANDATORY: Mandatory Break (BK) 0164 * @G_UNICODE_BREAK_CARRIAGE_RETURN: Carriage Return (CR) 0165 * @G_UNICODE_BREAK_LINE_FEED: Line Feed (LF) 0166 * @G_UNICODE_BREAK_COMBINING_MARK: Attached Characters and Combining Marks (CM) 0167 * @G_UNICODE_BREAK_SURROGATE: Surrogates (SG) 0168 * @G_UNICODE_BREAK_ZERO_WIDTH_SPACE: Zero Width Space (ZW) 0169 * @G_UNICODE_BREAK_INSEPARABLE: Inseparable (IN) 0170 * @G_UNICODE_BREAK_NON_BREAKING_GLUE: Non-breaking ("Glue") (GL) 0171 * @G_UNICODE_BREAK_CONTINGENT: Contingent Break Opportunity (CB) 0172 * @G_UNICODE_BREAK_SPACE: Space (SP) 0173 * @G_UNICODE_BREAK_AFTER: Break Opportunity After (BA) 0174 * @G_UNICODE_BREAK_BEFORE: Break Opportunity Before (BB) 0175 * @G_UNICODE_BREAK_BEFORE_AND_AFTER: Break Opportunity Before and After (B2) 0176 * @G_UNICODE_BREAK_HYPHEN: Hyphen (HY) 0177 * @G_UNICODE_BREAK_NON_STARTER: Nonstarter (NS) 0178 * @G_UNICODE_BREAK_OPEN_PUNCTUATION: Opening Punctuation (OP) 0179 * @G_UNICODE_BREAK_CLOSE_PUNCTUATION: Closing Punctuation (CL) 0180 * @G_UNICODE_BREAK_QUOTATION: Ambiguous Quotation (QU) 0181 * @G_UNICODE_BREAK_EXCLAMATION: Exclamation/Interrogation (EX) 0182 * @G_UNICODE_BREAK_IDEOGRAPHIC: Ideographic (ID) 0183 * @G_UNICODE_BREAK_NUMERIC: Numeric (NU) 0184 * @G_UNICODE_BREAK_INFIX_SEPARATOR: Infix Separator (Numeric) (IS) 0185 * @G_UNICODE_BREAK_SYMBOL: Symbols Allowing Break After (SY) 0186 * @G_UNICODE_BREAK_ALPHABETIC: Ordinary Alphabetic and Symbol Characters (AL) 0187 * @G_UNICODE_BREAK_PREFIX: Prefix (Numeric) (PR) 0188 * @G_UNICODE_BREAK_POSTFIX: Postfix (Numeric) (PO) 0189 * @G_UNICODE_BREAK_COMPLEX_CONTEXT: Complex Content Dependent (South East Asian) (SA) 0190 * @G_UNICODE_BREAK_AMBIGUOUS: Ambiguous (Alphabetic or Ideographic) (AI) 0191 * @G_UNICODE_BREAK_UNKNOWN: Unknown (XX) 0192 * @G_UNICODE_BREAK_NEXT_LINE: Next Line (NL) 0193 * @G_UNICODE_BREAK_WORD_JOINER: Word Joiner (WJ) 0194 * @G_UNICODE_BREAK_HANGUL_L_JAMO: Hangul L Jamo (JL) 0195 * @G_UNICODE_BREAK_HANGUL_V_JAMO: Hangul V Jamo (JV) 0196 * @G_UNICODE_BREAK_HANGUL_T_JAMO: Hangul T Jamo (JT) 0197 * @G_UNICODE_BREAK_HANGUL_LV_SYLLABLE: Hangul LV Syllable (H2) 0198 * @G_UNICODE_BREAK_HANGUL_LVT_SYLLABLE: Hangul LVT Syllable (H3) 0199 * @G_UNICODE_BREAK_CLOSE_PARANTHESIS: Closing Parenthesis (CP). Since 2.28. Deprecated: 2.70: Use %G_UNICODE_BREAK_CLOSE_PARENTHESIS instead. 0200 * @G_UNICODE_BREAK_CLOSE_PARENTHESIS: Closing Parenthesis (CP). Since 2.70 0201 * @G_UNICODE_BREAK_CONDITIONAL_JAPANESE_STARTER: Conditional Japanese Starter (CJ). Since: 2.32 0202 * @G_UNICODE_BREAK_HEBREW_LETTER: Hebrew Letter (HL). Since: 2.32 0203 * @G_UNICODE_BREAK_REGIONAL_INDICATOR: Regional Indicator (RI). Since: 2.36 0204 * @G_UNICODE_BREAK_EMOJI_BASE: Emoji Base (EB). Since: 2.50 0205 * @G_UNICODE_BREAK_EMOJI_MODIFIER: Emoji Modifier (EM). Since: 2.50 0206 * @G_UNICODE_BREAK_ZERO_WIDTH_JOINER: Zero Width Joiner (ZWJ). Since: 2.50 0207 * @G_UNICODE_BREAK_AKSARA: Aksara (AK). Since: 2.80 0208 * @G_UNICODE_BREAK_AKSARA_PRE_BASE (AP). Since: 2.80 0209 * @G_UNICODE_BREAK_AKSARA_START (AS). Since: 2.80 0210 * @G_UNICODE_BREAK_VIRAMA_FINAL (VF). Since: 2.80 0211 * @G_UNICODE_BREAK_VIRAMA (VI). Since: 2.80 0212 * 0213 * These are the possible line break classifications. 0214 * 0215 * Since new Unicode versions may add new types here, applications should be ready 0216 * to handle unknown values. They may be regarded as %G_UNICODE_BREAK_UNKNOWN. 0217 * 0218 * See [Unicode Line Breaking Algorithm](https://www.unicode.org/reports/tr14/). 0219 */ 0220 typedef enum 0221 { 0222 G_UNICODE_BREAK_MANDATORY, 0223 G_UNICODE_BREAK_CARRIAGE_RETURN, 0224 G_UNICODE_BREAK_LINE_FEED, 0225 G_UNICODE_BREAK_COMBINING_MARK, 0226 G_UNICODE_BREAK_SURROGATE, 0227 G_UNICODE_BREAK_ZERO_WIDTH_SPACE, 0228 G_UNICODE_BREAK_INSEPARABLE, 0229 G_UNICODE_BREAK_NON_BREAKING_GLUE, 0230 G_UNICODE_BREAK_CONTINGENT, 0231 G_UNICODE_BREAK_SPACE, 0232 G_UNICODE_BREAK_AFTER, 0233 G_UNICODE_BREAK_BEFORE, 0234 G_UNICODE_BREAK_BEFORE_AND_AFTER, 0235 G_UNICODE_BREAK_HYPHEN, 0236 G_UNICODE_BREAK_NON_STARTER, 0237 G_UNICODE_BREAK_OPEN_PUNCTUATION, 0238 G_UNICODE_BREAK_CLOSE_PUNCTUATION, 0239 G_UNICODE_BREAK_QUOTATION, 0240 G_UNICODE_BREAK_EXCLAMATION, 0241 G_UNICODE_BREAK_IDEOGRAPHIC, 0242 G_UNICODE_BREAK_NUMERIC, 0243 G_UNICODE_BREAK_INFIX_SEPARATOR, 0244 G_UNICODE_BREAK_SYMBOL, 0245 G_UNICODE_BREAK_ALPHABETIC, 0246 G_UNICODE_BREAK_PREFIX, 0247 G_UNICODE_BREAK_POSTFIX, 0248 G_UNICODE_BREAK_COMPLEX_CONTEXT, 0249 G_UNICODE_BREAK_AMBIGUOUS, 0250 G_UNICODE_BREAK_UNKNOWN, 0251 G_UNICODE_BREAK_NEXT_LINE, 0252 G_UNICODE_BREAK_WORD_JOINER, 0253 G_UNICODE_BREAK_HANGUL_L_JAMO, 0254 G_UNICODE_BREAK_HANGUL_V_JAMO, 0255 G_UNICODE_BREAK_HANGUL_T_JAMO, 0256 G_UNICODE_BREAK_HANGUL_LV_SYLLABLE, 0257 G_UNICODE_BREAK_HANGUL_LVT_SYLLABLE, 0258 G_UNICODE_BREAK_CLOSE_PARANTHESIS, 0259 G_UNICODE_BREAK_CLOSE_PARENTHESIS GLIB_AVAILABLE_ENUMERATOR_IN_2_70 = G_UNICODE_BREAK_CLOSE_PARANTHESIS, 0260 G_UNICODE_BREAK_CONDITIONAL_JAPANESE_STARTER, 0261 G_UNICODE_BREAK_HEBREW_LETTER, 0262 G_UNICODE_BREAK_REGIONAL_INDICATOR, 0263 G_UNICODE_BREAK_EMOJI_BASE, 0264 G_UNICODE_BREAK_EMOJI_MODIFIER, 0265 G_UNICODE_BREAK_ZERO_WIDTH_JOINER, 0266 G_UNICODE_BREAK_AKSARA, 0267 G_UNICODE_BREAK_AKSARA_PRE_BASE, 0268 G_UNICODE_BREAK_AKSARA_START, 0269 G_UNICODE_BREAK_VIRAMA_FINAL, 0270 G_UNICODE_BREAK_VIRAMA 0271 } GUnicodeBreakType; 0272 0273 /** 0274 * GUnicodeScript: 0275 * @G_UNICODE_SCRIPT_INVALID_CODE: 0276 * a value never returned from g_unichar_get_script() 0277 * @G_UNICODE_SCRIPT_COMMON: a character used by multiple different scripts 0278 * @G_UNICODE_SCRIPT_INHERITED: a mark glyph that takes its script from the 0279 * base glyph to which it is attached 0280 * @G_UNICODE_SCRIPT_ARABIC: Arabic 0281 * @G_UNICODE_SCRIPT_ARMENIAN: Armenian 0282 * @G_UNICODE_SCRIPT_BENGALI: Bengali 0283 * @G_UNICODE_SCRIPT_BOPOMOFO: Bopomofo 0284 * @G_UNICODE_SCRIPT_CHEROKEE: Cherokee 0285 * @G_UNICODE_SCRIPT_COPTIC: Coptic 0286 * @G_UNICODE_SCRIPT_CYRILLIC: Cyrillic 0287 * @G_UNICODE_SCRIPT_DESERET: Deseret 0288 * @G_UNICODE_SCRIPT_DEVANAGARI: Devanagari 0289 * @G_UNICODE_SCRIPT_ETHIOPIC: Ethiopic 0290 * @G_UNICODE_SCRIPT_GEORGIAN: Georgian 0291 * @G_UNICODE_SCRIPT_GOTHIC: Gothic 0292 * @G_UNICODE_SCRIPT_GREEK: Greek 0293 * @G_UNICODE_SCRIPT_GUJARATI: Gujarati 0294 * @G_UNICODE_SCRIPT_GURMUKHI: Gurmukhi 0295 * @G_UNICODE_SCRIPT_HAN: Han 0296 * @G_UNICODE_SCRIPT_HANGUL: Hangul 0297 * @G_UNICODE_SCRIPT_HEBREW: Hebrew 0298 * @G_UNICODE_SCRIPT_HIRAGANA: Hiragana 0299 * @G_UNICODE_SCRIPT_KANNADA: Kannada 0300 * @G_UNICODE_SCRIPT_KATAKANA: Katakana 0301 * @G_UNICODE_SCRIPT_KHMER: Khmer 0302 * @G_UNICODE_SCRIPT_LAO: Lao 0303 * @G_UNICODE_SCRIPT_LATIN: Latin 0304 * @G_UNICODE_SCRIPT_MALAYALAM: Malayalam 0305 * @G_UNICODE_SCRIPT_MONGOLIAN: Mongolian 0306 * @G_UNICODE_SCRIPT_MYANMAR: Myanmar 0307 * @G_UNICODE_SCRIPT_OGHAM: Ogham 0308 * @G_UNICODE_SCRIPT_OLD_ITALIC: Old Italic 0309 * @G_UNICODE_SCRIPT_ORIYA: Oriya 0310 * @G_UNICODE_SCRIPT_RUNIC: Runic 0311 * @G_UNICODE_SCRIPT_SINHALA: Sinhala 0312 * @G_UNICODE_SCRIPT_SYRIAC: Syriac 0313 * @G_UNICODE_SCRIPT_TAMIL: Tamil 0314 * @G_UNICODE_SCRIPT_TELUGU: Telugu 0315 * @G_UNICODE_SCRIPT_THAANA: Thaana 0316 * @G_UNICODE_SCRIPT_THAI: Thai 0317 * @G_UNICODE_SCRIPT_TIBETAN: Tibetan 0318 * @G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL: 0319 * Canadian Aboriginal 0320 * @G_UNICODE_SCRIPT_YI: Yi 0321 * @G_UNICODE_SCRIPT_TAGALOG: Tagalog 0322 * @G_UNICODE_SCRIPT_HANUNOO: Hanunoo 0323 * @G_UNICODE_SCRIPT_BUHID: Buhid 0324 * @G_UNICODE_SCRIPT_TAGBANWA: Tagbanwa 0325 * @G_UNICODE_SCRIPT_BRAILLE: Braille 0326 * @G_UNICODE_SCRIPT_CYPRIOT: Cypriot 0327 * @G_UNICODE_SCRIPT_LIMBU: Limbu 0328 * @G_UNICODE_SCRIPT_OSMANYA: Osmanya 0329 * @G_UNICODE_SCRIPT_SHAVIAN: Shavian 0330 * @G_UNICODE_SCRIPT_LINEAR_B: Linear B 0331 * @G_UNICODE_SCRIPT_TAI_LE: Tai Le 0332 * @G_UNICODE_SCRIPT_UGARITIC: Ugaritic 0333 * @G_UNICODE_SCRIPT_NEW_TAI_LUE: 0334 * New Tai Lue 0335 * @G_UNICODE_SCRIPT_BUGINESE: Buginese 0336 * @G_UNICODE_SCRIPT_GLAGOLITIC: Glagolitic 0337 * @G_UNICODE_SCRIPT_TIFINAGH: Tifinagh 0338 * @G_UNICODE_SCRIPT_SYLOTI_NAGRI: 0339 * Syloti Nagri 0340 * @G_UNICODE_SCRIPT_OLD_PERSIAN: 0341 * Old Persian 0342 * @G_UNICODE_SCRIPT_KHAROSHTHI: Kharoshthi 0343 * @G_UNICODE_SCRIPT_UNKNOWN: an unassigned code point 0344 * @G_UNICODE_SCRIPT_BALINESE: Balinese 0345 * @G_UNICODE_SCRIPT_CUNEIFORM: Cuneiform 0346 * @G_UNICODE_SCRIPT_PHOENICIAN: Phoenician 0347 * @G_UNICODE_SCRIPT_PHAGS_PA: Phags-pa 0348 * @G_UNICODE_SCRIPT_NKO: N'Ko 0349 * @G_UNICODE_SCRIPT_KAYAH_LI: Kayah Li. Since 2.16.3 0350 * @G_UNICODE_SCRIPT_LEPCHA: Lepcha. Since 2.16.3 0351 * @G_UNICODE_SCRIPT_REJANG: Rejang. Since 2.16.3 0352 * @G_UNICODE_SCRIPT_SUNDANESE: Sundanese. Since 2.16.3 0353 * @G_UNICODE_SCRIPT_SAURASHTRA: Saurashtra. Since 2.16.3 0354 * @G_UNICODE_SCRIPT_CHAM: Cham. Since 2.16.3 0355 * @G_UNICODE_SCRIPT_OL_CHIKI: Ol Chiki. Since 2.16.3 0356 * @G_UNICODE_SCRIPT_VAI: Vai. Since 2.16.3 0357 * @G_UNICODE_SCRIPT_CARIAN: Carian. Since 2.16.3 0358 * @G_UNICODE_SCRIPT_LYCIAN: Lycian. Since 2.16.3 0359 * @G_UNICODE_SCRIPT_LYDIAN: Lydian. Since 2.16.3 0360 * @G_UNICODE_SCRIPT_AVESTAN: Avestan. Since 2.26 0361 * @G_UNICODE_SCRIPT_BAMUM: Bamum. Since 2.26 0362 * @G_UNICODE_SCRIPT_EGYPTIAN_HIEROGLYPHS: 0363 * Egyptian Hieroglpyhs. Since 2.26 0364 * @G_UNICODE_SCRIPT_IMPERIAL_ARAMAIC: 0365 * Imperial Aramaic. Since 2.26 0366 * @G_UNICODE_SCRIPT_INSCRIPTIONAL_PAHLAVI: 0367 * Inscriptional Pahlavi. Since 2.26 0368 * @G_UNICODE_SCRIPT_INSCRIPTIONAL_PARTHIAN: 0369 * Inscriptional Parthian. Since 2.26 0370 * @G_UNICODE_SCRIPT_JAVANESE: Javanese. Since 2.26 0371 * @G_UNICODE_SCRIPT_KAITHI: Kaithi. Since 2.26 0372 * @G_UNICODE_SCRIPT_LISU: Lisu. Since 2.26 0373 * @G_UNICODE_SCRIPT_MEETEI_MAYEK: 0374 * Meetei Mayek. Since 2.26 0375 * @G_UNICODE_SCRIPT_OLD_SOUTH_ARABIAN: 0376 * Old South Arabian. Since 2.26 0377 * @G_UNICODE_SCRIPT_OLD_TURKIC: Old Turkic. Since 2.28 0378 * @G_UNICODE_SCRIPT_SAMARITAN: Samaritan. Since 2.26 0379 * @G_UNICODE_SCRIPT_TAI_THAM: Tai Tham. Since 2.26 0380 * @G_UNICODE_SCRIPT_TAI_VIET: Tai Viet. Since 2.26 0381 * @G_UNICODE_SCRIPT_BATAK: Batak. Since 2.28 0382 * @G_UNICODE_SCRIPT_BRAHMI: Brahmi. Since 2.28 0383 * @G_UNICODE_SCRIPT_MANDAIC: Mandaic. Since 2.28 0384 * @G_UNICODE_SCRIPT_CHAKMA: Chakma. Since: 2.32 0385 * @G_UNICODE_SCRIPT_MEROITIC_CURSIVE: Meroitic Cursive. Since: 2.32 0386 * @G_UNICODE_SCRIPT_MEROITIC_HIEROGLYPHS: Meroitic Hieroglyphs. Since: 2.32 0387 * @G_UNICODE_SCRIPT_MIAO: Miao. Since: 2.32 0388 * @G_UNICODE_SCRIPT_SHARADA: Sharada. Since: 2.32 0389 * @G_UNICODE_SCRIPT_SORA_SOMPENG: Sora Sompeng. Since: 2.32 0390 * @G_UNICODE_SCRIPT_TAKRI: Takri. Since: 2.32 0391 * @G_UNICODE_SCRIPT_BASSA_VAH: Bassa. Since: 2.42 0392 * @G_UNICODE_SCRIPT_CAUCASIAN_ALBANIAN: Caucasian Albanian. Since: 2.42 0393 * @G_UNICODE_SCRIPT_DUPLOYAN: Duployan. Since: 2.42 0394 * @G_UNICODE_SCRIPT_ELBASAN: Elbasan. Since: 2.42 0395 * @G_UNICODE_SCRIPT_GRANTHA: Grantha. Since: 2.42 0396 * @G_UNICODE_SCRIPT_KHOJKI: Kjohki. Since: 2.42 0397 * @G_UNICODE_SCRIPT_KHUDAWADI: Khudawadi, Sindhi. Since: 2.42 0398 * @G_UNICODE_SCRIPT_LINEAR_A: Linear A. Since: 2.42 0399 * @G_UNICODE_SCRIPT_MAHAJANI: Mahajani. Since: 2.42 0400 * @G_UNICODE_SCRIPT_MANICHAEAN: Manichaean. Since: 2.42 0401 * @G_UNICODE_SCRIPT_MENDE_KIKAKUI: Mende Kikakui. Since: 2.42 0402 * @G_UNICODE_SCRIPT_MODI: Modi. Since: 2.42 0403 * @G_UNICODE_SCRIPT_MRO: Mro. Since: 2.42 0404 * @G_UNICODE_SCRIPT_NABATAEAN: Nabataean. Since: 2.42 0405 * @G_UNICODE_SCRIPT_OLD_NORTH_ARABIAN: Old North Arabian. Since: 2.42 0406 * @G_UNICODE_SCRIPT_OLD_PERMIC: Old Permic. Since: 2.42 0407 * @G_UNICODE_SCRIPT_PAHAWH_HMONG: Pahawh Hmong. Since: 2.42 0408 * @G_UNICODE_SCRIPT_PALMYRENE: Palmyrene. Since: 2.42 0409 * @G_UNICODE_SCRIPT_PAU_CIN_HAU: Pau Cin Hau. Since: 2.42 0410 * @G_UNICODE_SCRIPT_PSALTER_PAHLAVI: Psalter Pahlavi. Since: 2.42 0411 * @G_UNICODE_SCRIPT_SIDDHAM: Siddham. Since: 2.42 0412 * @G_UNICODE_SCRIPT_TIRHUTA: Tirhuta. Since: 2.42 0413 * @G_UNICODE_SCRIPT_WARANG_CITI: Warang Citi. Since: 2.42 0414 * @G_UNICODE_SCRIPT_AHOM: Ahom. Since: 2.48 0415 * @G_UNICODE_SCRIPT_ANATOLIAN_HIEROGLYPHS: Anatolian Hieroglyphs. Since: 2.48 0416 * @G_UNICODE_SCRIPT_HATRAN: Hatran. Since: 2.48 0417 * @G_UNICODE_SCRIPT_MULTANI: Multani. Since: 2.48 0418 * @G_UNICODE_SCRIPT_OLD_HUNGARIAN: Old Hungarian. Since: 2.48 0419 * @G_UNICODE_SCRIPT_SIGNWRITING: Signwriting. Since: 2.48 0420 * @G_UNICODE_SCRIPT_ADLAM: Adlam. Since: 2.50 0421 * @G_UNICODE_SCRIPT_BHAIKSUKI: Bhaiksuki. Since: 2.50 0422 * @G_UNICODE_SCRIPT_MARCHEN: Marchen. Since: 2.50 0423 * @G_UNICODE_SCRIPT_NEWA: Newa. Since: 2.50 0424 * @G_UNICODE_SCRIPT_OSAGE: Osage. Since: 2.50 0425 * @G_UNICODE_SCRIPT_TANGUT: Tangut. Since: 2.50 0426 * @G_UNICODE_SCRIPT_MASARAM_GONDI: Masaram Gondi. Since: 2.54 0427 * @G_UNICODE_SCRIPT_NUSHU: Nushu. Since: 2.54 0428 * @G_UNICODE_SCRIPT_SOYOMBO: Soyombo. Since: 2.54 0429 * @G_UNICODE_SCRIPT_ZANABAZAR_SQUARE: Zanabazar Square. Since: 2.54 0430 * @G_UNICODE_SCRIPT_DOGRA: Dogra. Since: 2.58 0431 * @G_UNICODE_SCRIPT_GUNJALA_GONDI: Gunjala Gondi. Since: 2.58 0432 * @G_UNICODE_SCRIPT_HANIFI_ROHINGYA: Hanifi Rohingya. Since: 2.58 0433 * @G_UNICODE_SCRIPT_MAKASAR: Makasar. Since: 2.58 0434 * @G_UNICODE_SCRIPT_MEDEFAIDRIN: Medefaidrin. Since: 2.58 0435 * @G_UNICODE_SCRIPT_OLD_SOGDIAN: Old Sogdian. Since: 2.58 0436 * @G_UNICODE_SCRIPT_SOGDIAN: Sogdian. Since: 2.58 0437 * @G_UNICODE_SCRIPT_ELYMAIC: Elym. Since: 2.62 0438 * @G_UNICODE_SCRIPT_NANDINAGARI: Nand. Since: 2.62 0439 * @G_UNICODE_SCRIPT_NYIAKENG_PUACHUE_HMONG: Rohg. Since: 2.62 0440 * @G_UNICODE_SCRIPT_WANCHO: Wcho. Since: 2.62 0441 * @G_UNICODE_SCRIPT_CHORASMIAN: Chorasmian. Since: 2.66 0442 * @G_UNICODE_SCRIPT_DIVES_AKURU: Dives Akuru. Since: 2.66 0443 * @G_UNICODE_SCRIPT_KHITAN_SMALL_SCRIPT: Khitan small script. Since: 2.66 0444 * @G_UNICODE_SCRIPT_YEZIDI: Yezidi. Since: 2.66 0445 * @G_UNICODE_SCRIPT_CYPRO_MINOAN: Cypro-Minoan. Since: 2.72 0446 * @G_UNICODE_SCRIPT_OLD_UYGHUR: Old Uyghur. Since: 2.72 0447 * @G_UNICODE_SCRIPT_TANGSA: Tangsa. Since: 2.72 0448 * @G_UNICODE_SCRIPT_TOTO: Toto. Since: 2.72 0449 * @G_UNICODE_SCRIPT_VITHKUQI: Vithkuqi. Since: 2.72 0450 * @G_UNICODE_SCRIPT_MATH: Mathematical notation. Since: 2.72 0451 * @G_UNICODE_SCRIPT_KAWI: Kawi. Since 2.74 0452 * @G_UNICODE_SCRIPT_NAG_MUNDARI: Nag Mundari. Since 2.74 0453 * 0454 * The #GUnicodeScript enumeration identifies different writing 0455 * systems. The values correspond to the names as defined in the 0456 * Unicode standard. The enumeration has been added in GLib 2.14, 0457 * and is interchangeable with #PangoScript. 0458 * 0459 * Note that new types may be added in the future. Applications 0460 * should be ready to handle unknown values. 0461 * See [Unicode Standard Annex #24: Script names](http://www.unicode.org/reports/tr24/). 0462 */ 0463 typedef enum 0464 { /* ISO 15924 code */ 0465 G_UNICODE_SCRIPT_INVALID_CODE = -1, 0466 G_UNICODE_SCRIPT_COMMON = 0, /* Zyyy */ 0467 G_UNICODE_SCRIPT_INHERITED, /* Zinh (Qaai) */ 0468 G_UNICODE_SCRIPT_ARABIC, /* Arab */ 0469 G_UNICODE_SCRIPT_ARMENIAN, /* Armn */ 0470 G_UNICODE_SCRIPT_BENGALI, /* Beng */ 0471 G_UNICODE_SCRIPT_BOPOMOFO, /* Bopo */ 0472 G_UNICODE_SCRIPT_CHEROKEE, /* Cher */ 0473 G_UNICODE_SCRIPT_COPTIC, /* Copt (Qaac) */ 0474 G_UNICODE_SCRIPT_CYRILLIC, /* Cyrl (Cyrs) */ 0475 G_UNICODE_SCRIPT_DESERET, /* Dsrt */ 0476 G_UNICODE_SCRIPT_DEVANAGARI, /* Deva */ 0477 G_UNICODE_SCRIPT_ETHIOPIC, /* Ethi */ 0478 G_UNICODE_SCRIPT_GEORGIAN, /* Geor (Geon, Geoa) */ 0479 G_UNICODE_SCRIPT_GOTHIC, /* Goth */ 0480 G_UNICODE_SCRIPT_GREEK, /* Grek */ 0481 G_UNICODE_SCRIPT_GUJARATI, /* Gujr */ 0482 G_UNICODE_SCRIPT_GURMUKHI, /* Guru */ 0483 G_UNICODE_SCRIPT_HAN, /* Hani */ 0484 G_UNICODE_SCRIPT_HANGUL, /* Hang */ 0485 G_UNICODE_SCRIPT_HEBREW, /* Hebr */ 0486 G_UNICODE_SCRIPT_HIRAGANA, /* Hira */ 0487 G_UNICODE_SCRIPT_KANNADA, /* Knda */ 0488 G_UNICODE_SCRIPT_KATAKANA, /* Kana */ 0489 G_UNICODE_SCRIPT_KHMER, /* Khmr */ 0490 G_UNICODE_SCRIPT_LAO, /* Laoo */ 0491 G_UNICODE_SCRIPT_LATIN, /* Latn (Latf, Latg) */ 0492 G_UNICODE_SCRIPT_MALAYALAM, /* Mlym */ 0493 G_UNICODE_SCRIPT_MONGOLIAN, /* Mong */ 0494 G_UNICODE_SCRIPT_MYANMAR, /* Mymr */ 0495 G_UNICODE_SCRIPT_OGHAM, /* Ogam */ 0496 G_UNICODE_SCRIPT_OLD_ITALIC, /* Ital */ 0497 G_UNICODE_SCRIPT_ORIYA, /* Orya */ 0498 G_UNICODE_SCRIPT_RUNIC, /* Runr */ 0499 G_UNICODE_SCRIPT_SINHALA, /* Sinh */ 0500 G_UNICODE_SCRIPT_SYRIAC, /* Syrc (Syrj, Syrn, Syre) */ 0501 G_UNICODE_SCRIPT_TAMIL, /* Taml */ 0502 G_UNICODE_SCRIPT_TELUGU, /* Telu */ 0503 G_UNICODE_SCRIPT_THAANA, /* Thaa */ 0504 G_UNICODE_SCRIPT_THAI, /* Thai */ 0505 G_UNICODE_SCRIPT_TIBETAN, /* Tibt */ 0506 G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL, /* Cans */ 0507 G_UNICODE_SCRIPT_YI, /* Yiii */ 0508 G_UNICODE_SCRIPT_TAGALOG, /* Tglg */ 0509 G_UNICODE_SCRIPT_HANUNOO, /* Hano */ 0510 G_UNICODE_SCRIPT_BUHID, /* Buhd */ 0511 G_UNICODE_SCRIPT_TAGBANWA, /* Tagb */ 0512 0513 /* Unicode-4.0 additions */ 0514 G_UNICODE_SCRIPT_BRAILLE, /* Brai */ 0515 G_UNICODE_SCRIPT_CYPRIOT, /* Cprt */ 0516 G_UNICODE_SCRIPT_LIMBU, /* Limb */ 0517 G_UNICODE_SCRIPT_OSMANYA, /* Osma */ 0518 G_UNICODE_SCRIPT_SHAVIAN, /* Shaw */ 0519 G_UNICODE_SCRIPT_LINEAR_B, /* Linb */ 0520 G_UNICODE_SCRIPT_TAI_LE, /* Tale */ 0521 G_UNICODE_SCRIPT_UGARITIC, /* Ugar */ 0522 0523 /* Unicode-4.1 additions */ 0524 G_UNICODE_SCRIPT_NEW_TAI_LUE, /* Talu */ 0525 G_UNICODE_SCRIPT_BUGINESE, /* Bugi */ 0526 G_UNICODE_SCRIPT_GLAGOLITIC, /* Glag */ 0527 G_UNICODE_SCRIPT_TIFINAGH, /* Tfng */ 0528 G_UNICODE_SCRIPT_SYLOTI_NAGRI, /* Sylo */ 0529 G_UNICODE_SCRIPT_OLD_PERSIAN, /* Xpeo */ 0530 G_UNICODE_SCRIPT_KHAROSHTHI, /* Khar */ 0531 0532 /* Unicode-5.0 additions */ 0533 G_UNICODE_SCRIPT_UNKNOWN, /* Zzzz */ 0534 G_UNICODE_SCRIPT_BALINESE, /* Bali */ 0535 G_UNICODE_SCRIPT_CUNEIFORM, /* Xsux */ 0536 G_UNICODE_SCRIPT_PHOENICIAN, /* Phnx */ 0537 G_UNICODE_SCRIPT_PHAGS_PA, /* Phag */ 0538 G_UNICODE_SCRIPT_NKO, /* Nkoo */ 0539 0540 /* Unicode-5.1 additions */ 0541 G_UNICODE_SCRIPT_KAYAH_LI, /* Kali */ 0542 G_UNICODE_SCRIPT_LEPCHA, /* Lepc */ 0543 G_UNICODE_SCRIPT_REJANG, /* Rjng */ 0544 G_UNICODE_SCRIPT_SUNDANESE, /* Sund */ 0545 G_UNICODE_SCRIPT_SAURASHTRA, /* Saur */ 0546 G_UNICODE_SCRIPT_CHAM, /* Cham */ 0547 G_UNICODE_SCRIPT_OL_CHIKI, /* Olck */ 0548 G_UNICODE_SCRIPT_VAI, /* Vaii */ 0549 G_UNICODE_SCRIPT_CARIAN, /* Cari */ 0550 G_UNICODE_SCRIPT_LYCIAN, /* Lyci */ 0551 G_UNICODE_SCRIPT_LYDIAN, /* Lydi */ 0552 0553 /* Unicode-5.2 additions */ 0554 G_UNICODE_SCRIPT_AVESTAN, /* Avst */ 0555 G_UNICODE_SCRIPT_BAMUM, /* Bamu */ 0556 G_UNICODE_SCRIPT_EGYPTIAN_HIEROGLYPHS, /* Egyp */ 0557 G_UNICODE_SCRIPT_IMPERIAL_ARAMAIC, /* Armi */ 0558 G_UNICODE_SCRIPT_INSCRIPTIONAL_PAHLAVI, /* Phli */ 0559 G_UNICODE_SCRIPT_INSCRIPTIONAL_PARTHIAN, /* Prti */ 0560 G_UNICODE_SCRIPT_JAVANESE, /* Java */ 0561 G_UNICODE_SCRIPT_KAITHI, /* Kthi */ 0562 G_UNICODE_SCRIPT_LISU, /* Lisu */ 0563 G_UNICODE_SCRIPT_MEETEI_MAYEK, /* Mtei */ 0564 G_UNICODE_SCRIPT_OLD_SOUTH_ARABIAN, /* Sarb */ 0565 G_UNICODE_SCRIPT_OLD_TURKIC, /* Orkh */ 0566 G_UNICODE_SCRIPT_SAMARITAN, /* Samr */ 0567 G_UNICODE_SCRIPT_TAI_THAM, /* Lana */ 0568 G_UNICODE_SCRIPT_TAI_VIET, /* Tavt */ 0569 0570 /* Unicode-6.0 additions */ 0571 G_UNICODE_SCRIPT_BATAK, /* Batk */ 0572 G_UNICODE_SCRIPT_BRAHMI, /* Brah */ 0573 G_UNICODE_SCRIPT_MANDAIC, /* Mand */ 0574 0575 /* Unicode-6.1 additions */ 0576 G_UNICODE_SCRIPT_CHAKMA, /* Cakm */ 0577 G_UNICODE_SCRIPT_MEROITIC_CURSIVE, /* Merc */ 0578 G_UNICODE_SCRIPT_MEROITIC_HIEROGLYPHS, /* Mero */ 0579 G_UNICODE_SCRIPT_MIAO, /* Plrd */ 0580 G_UNICODE_SCRIPT_SHARADA, /* Shrd */ 0581 G_UNICODE_SCRIPT_SORA_SOMPENG, /* Sora */ 0582 G_UNICODE_SCRIPT_TAKRI, /* Takr */ 0583 0584 /* Unicode 7.0 additions */ 0585 G_UNICODE_SCRIPT_BASSA_VAH, /* Bass */ 0586 G_UNICODE_SCRIPT_CAUCASIAN_ALBANIAN, /* Aghb */ 0587 G_UNICODE_SCRIPT_DUPLOYAN, /* Dupl */ 0588 G_UNICODE_SCRIPT_ELBASAN, /* Elba */ 0589 G_UNICODE_SCRIPT_GRANTHA, /* Gran */ 0590 G_UNICODE_SCRIPT_KHOJKI, /* Khoj */ 0591 G_UNICODE_SCRIPT_KHUDAWADI, /* Sind */ 0592 G_UNICODE_SCRIPT_LINEAR_A, /* Lina */ 0593 G_UNICODE_SCRIPT_MAHAJANI, /* Mahj */ 0594 G_UNICODE_SCRIPT_MANICHAEAN, /* Mani */ 0595 G_UNICODE_SCRIPT_MENDE_KIKAKUI, /* Mend */ 0596 G_UNICODE_SCRIPT_MODI, /* Modi */ 0597 G_UNICODE_SCRIPT_MRO, /* Mroo */ 0598 G_UNICODE_SCRIPT_NABATAEAN, /* Nbat */ 0599 G_UNICODE_SCRIPT_OLD_NORTH_ARABIAN, /* Narb */ 0600 G_UNICODE_SCRIPT_OLD_PERMIC, /* Perm */ 0601 G_UNICODE_SCRIPT_PAHAWH_HMONG, /* Hmng */ 0602 G_UNICODE_SCRIPT_PALMYRENE, /* Palm */ 0603 G_UNICODE_SCRIPT_PAU_CIN_HAU, /* Pauc */ 0604 G_UNICODE_SCRIPT_PSALTER_PAHLAVI, /* Phlp */ 0605 G_UNICODE_SCRIPT_SIDDHAM, /* Sidd */ 0606 G_UNICODE_SCRIPT_TIRHUTA, /* Tirh */ 0607 G_UNICODE_SCRIPT_WARANG_CITI, /* Wara */ 0608 0609 /* Unicode 8.0 additions */ 0610 G_UNICODE_SCRIPT_AHOM, /* Ahom */ 0611 G_UNICODE_SCRIPT_ANATOLIAN_HIEROGLYPHS, /* Hluw */ 0612 G_UNICODE_SCRIPT_HATRAN, /* Hatr */ 0613 G_UNICODE_SCRIPT_MULTANI, /* Mult */ 0614 G_UNICODE_SCRIPT_OLD_HUNGARIAN, /* Hung */ 0615 G_UNICODE_SCRIPT_SIGNWRITING, /* Sgnw */ 0616 0617 /* Unicode 9.0 additions */ 0618 G_UNICODE_SCRIPT_ADLAM, /* Adlm */ 0619 G_UNICODE_SCRIPT_BHAIKSUKI, /* Bhks */ 0620 G_UNICODE_SCRIPT_MARCHEN, /* Marc */ 0621 G_UNICODE_SCRIPT_NEWA, /* Newa */ 0622 G_UNICODE_SCRIPT_OSAGE, /* Osge */ 0623 G_UNICODE_SCRIPT_TANGUT, /* Tang */ 0624 0625 /* Unicode 10.0 additions */ 0626 G_UNICODE_SCRIPT_MASARAM_GONDI, /* Gonm */ 0627 G_UNICODE_SCRIPT_NUSHU, /* Nshu */ 0628 G_UNICODE_SCRIPT_SOYOMBO, /* Soyo */ 0629 G_UNICODE_SCRIPT_ZANABAZAR_SQUARE, /* Zanb */ 0630 0631 /* Unicode 11.0 additions */ 0632 G_UNICODE_SCRIPT_DOGRA, /* Dogr */ 0633 G_UNICODE_SCRIPT_GUNJALA_GONDI, /* Gong */ 0634 G_UNICODE_SCRIPT_HANIFI_ROHINGYA, /* Rohg */ 0635 G_UNICODE_SCRIPT_MAKASAR, /* Maka */ 0636 G_UNICODE_SCRIPT_MEDEFAIDRIN, /* Medf */ 0637 G_UNICODE_SCRIPT_OLD_SOGDIAN, /* Sogo */ 0638 G_UNICODE_SCRIPT_SOGDIAN, /* Sogd */ 0639 0640 /* Unicode 12.0 additions */ 0641 G_UNICODE_SCRIPT_ELYMAIC, /* Elym */ 0642 G_UNICODE_SCRIPT_NANDINAGARI, /* Nand */ 0643 G_UNICODE_SCRIPT_NYIAKENG_PUACHUE_HMONG, /* Rohg */ 0644 G_UNICODE_SCRIPT_WANCHO, /* Wcho */ 0645 0646 /* Unicode 13.0 additions */ 0647 G_UNICODE_SCRIPT_CHORASMIAN, /* Chrs */ 0648 G_UNICODE_SCRIPT_DIVES_AKURU, /* Diak */ 0649 G_UNICODE_SCRIPT_KHITAN_SMALL_SCRIPT, /* Kits */ 0650 G_UNICODE_SCRIPT_YEZIDI, /* Yezi */ 0651 0652 /* Unicode 14.0 additions */ 0653 G_UNICODE_SCRIPT_CYPRO_MINOAN, /* Cpmn */ 0654 G_UNICODE_SCRIPT_OLD_UYGHUR, /* Ougr */ 0655 G_UNICODE_SCRIPT_TANGSA, /* Tnsa */ 0656 G_UNICODE_SCRIPT_TOTO, /* Toto */ 0657 G_UNICODE_SCRIPT_VITHKUQI, /* Vith */ 0658 0659 /* not really a Unicode script, but part of ISO 15924 */ 0660 G_UNICODE_SCRIPT_MATH, /* Zmth */ 0661 0662 /* Unicode 15.0 additions */ 0663 G_UNICODE_SCRIPT_KAWI GLIB_AVAILABLE_ENUMERATOR_IN_2_74, /* Kawi */ 0664 G_UNICODE_SCRIPT_NAG_MUNDARI GLIB_AVAILABLE_ENUMERATOR_IN_2_74, /* Nag Mundari */ 0665 } GUnicodeScript; 0666 0667 GLIB_AVAILABLE_IN_ALL 0668 guint32 g_unicode_script_to_iso15924 (GUnicodeScript script); 0669 GLIB_AVAILABLE_IN_ALL 0670 GUnicodeScript g_unicode_script_from_iso15924 (guint32 iso15924); 0671 0672 /* These are all analogs of the <ctype.h> functions. 0673 */ 0674 GLIB_AVAILABLE_IN_ALL 0675 gboolean g_unichar_isalnum (gunichar c) G_GNUC_CONST; 0676 GLIB_AVAILABLE_IN_ALL 0677 gboolean g_unichar_isalpha (gunichar c) G_GNUC_CONST; 0678 GLIB_AVAILABLE_IN_ALL 0679 gboolean g_unichar_iscntrl (gunichar c) G_GNUC_CONST; 0680 GLIB_AVAILABLE_IN_ALL 0681 gboolean g_unichar_isdigit (gunichar c) G_GNUC_CONST; 0682 GLIB_AVAILABLE_IN_ALL 0683 gboolean g_unichar_isgraph (gunichar c) G_GNUC_CONST; 0684 GLIB_AVAILABLE_IN_ALL 0685 gboolean g_unichar_islower (gunichar c) G_GNUC_CONST; 0686 GLIB_AVAILABLE_IN_ALL 0687 gboolean g_unichar_isprint (gunichar c) G_GNUC_CONST; 0688 GLIB_AVAILABLE_IN_ALL 0689 gboolean g_unichar_ispunct (gunichar c) G_GNUC_CONST; 0690 GLIB_AVAILABLE_IN_ALL 0691 gboolean g_unichar_isspace (gunichar c) G_GNUC_CONST; 0692 GLIB_AVAILABLE_IN_ALL 0693 gboolean g_unichar_isupper (gunichar c) G_GNUC_CONST; 0694 GLIB_AVAILABLE_IN_ALL 0695 gboolean g_unichar_isxdigit (gunichar c) G_GNUC_CONST; 0696 GLIB_AVAILABLE_IN_ALL 0697 gboolean g_unichar_istitle (gunichar c) G_GNUC_CONST; 0698 GLIB_AVAILABLE_IN_ALL 0699 gboolean g_unichar_isdefined (gunichar c) G_GNUC_CONST; 0700 GLIB_AVAILABLE_IN_ALL 0701 gboolean g_unichar_iswide (gunichar c) G_GNUC_CONST; 0702 GLIB_AVAILABLE_IN_ALL 0703 gboolean g_unichar_iswide_cjk(gunichar c) G_GNUC_CONST; 0704 GLIB_AVAILABLE_IN_ALL 0705 gboolean g_unichar_iszerowidth(gunichar c) G_GNUC_CONST; 0706 GLIB_AVAILABLE_IN_ALL 0707 gboolean g_unichar_ismark (gunichar c) G_GNUC_CONST; 0708 0709 /* More <ctype.h> functions. These convert between the three cases. 0710 * See the Unicode book to understand title case. */ 0711 GLIB_AVAILABLE_IN_ALL 0712 gunichar g_unichar_toupper (gunichar c) G_GNUC_CONST; 0713 GLIB_AVAILABLE_IN_ALL 0714 gunichar g_unichar_tolower (gunichar c) G_GNUC_CONST; 0715 GLIB_AVAILABLE_IN_ALL 0716 gunichar g_unichar_totitle (gunichar c) G_GNUC_CONST; 0717 0718 /* If C is a digit (according to 'g_unichar_isdigit'), then return its 0719 numeric value. Otherwise return -1. */ 0720 GLIB_AVAILABLE_IN_ALL 0721 gint g_unichar_digit_value (gunichar c) G_GNUC_CONST; 0722 0723 GLIB_AVAILABLE_IN_ALL 0724 gint g_unichar_xdigit_value (gunichar c) G_GNUC_CONST; 0725 0726 /* Return the Unicode character type of a given character. */ 0727 GLIB_AVAILABLE_IN_ALL 0728 GUnicodeType g_unichar_type (gunichar c) G_GNUC_CONST; 0729 0730 /* Return the line break property for a given character */ 0731 GLIB_AVAILABLE_IN_ALL 0732 GUnicodeBreakType g_unichar_break_type (gunichar c) G_GNUC_CONST; 0733 0734 /* Returns the combining class for a given character */ 0735 GLIB_AVAILABLE_IN_ALL 0736 gint g_unichar_combining_class (gunichar uc) G_GNUC_CONST; 0737 0738 GLIB_AVAILABLE_IN_ALL 0739 gboolean g_unichar_get_mirror_char (gunichar ch, 0740 gunichar *mirrored_ch); 0741 0742 GLIB_AVAILABLE_IN_ALL 0743 GUnicodeScript g_unichar_get_script (gunichar ch) G_GNUC_CONST; 0744 0745 /* Validate a Unicode character */ 0746 GLIB_AVAILABLE_IN_ALL 0747 gboolean g_unichar_validate (gunichar ch) G_GNUC_CONST; 0748 0749 /* Pairwise canonical compose/decompose */ 0750 GLIB_AVAILABLE_IN_ALL 0751 gboolean g_unichar_compose (gunichar a, 0752 gunichar b, 0753 gunichar *ch); 0754 GLIB_AVAILABLE_IN_ALL 0755 gboolean g_unichar_decompose (gunichar ch, 0756 gunichar *a, 0757 gunichar *b); 0758 0759 GLIB_AVAILABLE_IN_ALL 0760 gsize g_unichar_fully_decompose (gunichar ch, 0761 gboolean compat, 0762 gunichar *result, 0763 gsize result_len); 0764 0765 /** 0766 * G_UNICHAR_MAX_DECOMPOSITION_LENGTH: 0767 * 0768 * The maximum length (in codepoints) of a compatibility or canonical 0769 * decomposition of a single Unicode character. 0770 * 0771 * This is as defined by Unicode 6.1. 0772 * 0773 * Since: 2.32 0774 */ 0775 #define G_UNICHAR_MAX_DECOMPOSITION_LENGTH 18 /* codepoints */ 0776 0777 /* Compute canonical ordering of a string in-place. This rearranges 0778 decomposed characters in the string according to their combining 0779 classes. See the Unicode manual for more information. */ 0780 GLIB_AVAILABLE_IN_ALL 0781 void g_unicode_canonical_ordering (gunichar *string, 0782 gsize len); 0783 0784 0785 GLIB_DEPRECATED_IN_2_30 0786 gunichar *g_unicode_canonical_decomposition (gunichar ch, 0787 gsize *result_len) G_GNUC_MALLOC; 0788 0789 /* Array of skip-bytes-per-initial character. 0790 */ 0791 GLIB_VAR const gchar * const g_utf8_skip; 0792 0793 /** 0794 * g_utf8_next_char: 0795 * @p: Pointer to the start of a valid UTF-8 character 0796 * 0797 * Skips to the next character in a UTF-8 string. 0798 * 0799 * The string must be valid; this macro is as fast as possible, and has 0800 * no error-checking. 0801 * 0802 * You would use this macro to iterate over a string character by character. 0803 * 0804 * The macro returns the start of the next UTF-8 character. 0805 * 0806 * Before using this macro, use g_utf8_validate() to validate strings 0807 * that may contain invalid UTF-8. 0808 */ 0809 #define g_utf8_next_char(p) ((p) + g_utf8_skip[*(const guchar *)(p)]) 0810 0811 GLIB_AVAILABLE_IN_ALL 0812 gunichar g_utf8_get_char (const gchar *p) G_GNUC_PURE; 0813 GLIB_AVAILABLE_IN_ALL 0814 gunichar g_utf8_get_char_validated (const gchar *p, 0815 gssize max_len) G_GNUC_PURE; 0816 0817 GLIB_AVAILABLE_IN_ALL 0818 gchar* g_utf8_offset_to_pointer (const gchar *str, 0819 glong offset) G_GNUC_PURE; 0820 GLIB_AVAILABLE_IN_ALL 0821 glong g_utf8_pointer_to_offset (const gchar *str, 0822 const gchar *pos) G_GNUC_PURE; 0823 GLIB_AVAILABLE_IN_ALL 0824 gchar* g_utf8_prev_char (const gchar *p) G_GNUC_PURE; 0825 GLIB_AVAILABLE_IN_ALL 0826 gchar* g_utf8_find_next_char (const gchar *p, 0827 const gchar *end) G_GNUC_PURE; 0828 GLIB_AVAILABLE_IN_ALL 0829 gchar* g_utf8_find_prev_char (const gchar *str, 0830 const gchar *p) G_GNUC_PURE; 0831 0832 GLIB_AVAILABLE_IN_ALL 0833 glong g_utf8_strlen (const gchar *p, 0834 gssize max) G_GNUC_PURE; 0835 0836 GLIB_AVAILABLE_IN_2_30 0837 gchar *g_utf8_substring (const gchar *str, 0838 glong start_pos, 0839 glong end_pos) G_GNUC_MALLOC; 0840 0841 GLIB_AVAILABLE_IN_ALL 0842 gchar *g_utf8_strncpy (gchar *dest, 0843 const gchar *src, 0844 gsize n); 0845 0846 GLIB_AVAILABLE_IN_2_78 0847 gchar *g_utf8_truncate_middle (const gchar *string, 0848 gsize truncate_length); 0849 0850 /* Find the UTF-8 character corresponding to ch, in string p. These 0851 functions are equivalants to strchr and strrchr */ 0852 GLIB_AVAILABLE_IN_ALL 0853 gchar* g_utf8_strchr (const gchar *p, 0854 gssize len, 0855 gunichar c); 0856 GLIB_AVAILABLE_IN_ALL 0857 gchar* g_utf8_strrchr (const gchar *p, 0858 gssize len, 0859 gunichar c); 0860 GLIB_AVAILABLE_IN_ALL 0861 gchar* g_utf8_strreverse (const gchar *str, 0862 gssize len); 0863 0864 GLIB_AVAILABLE_IN_ALL 0865 gunichar2 *g_utf8_to_utf16 (const gchar *str, 0866 glong len, 0867 glong *items_read, 0868 glong *items_written, 0869 GError **error) G_GNUC_MALLOC; 0870 GLIB_AVAILABLE_IN_ALL 0871 gunichar * g_utf8_to_ucs4 (const gchar *str, 0872 glong len, 0873 glong *items_read, 0874 glong *items_written, 0875 GError **error) G_GNUC_MALLOC; 0876 GLIB_AVAILABLE_IN_ALL 0877 gunichar * g_utf8_to_ucs4_fast (const gchar *str, 0878 glong len, 0879 glong *items_written) G_GNUC_MALLOC; 0880 GLIB_AVAILABLE_IN_ALL 0881 gunichar * g_utf16_to_ucs4 (const gunichar2 *str, 0882 glong len, 0883 glong *items_read, 0884 glong *items_written, 0885 GError **error) G_GNUC_MALLOC; 0886 GLIB_AVAILABLE_IN_ALL 0887 gchar* g_utf16_to_utf8 (const gunichar2 *str, 0888 glong len, 0889 glong *items_read, 0890 glong *items_written, 0891 GError **error) G_GNUC_MALLOC; 0892 GLIB_AVAILABLE_IN_ALL 0893 gunichar2 *g_ucs4_to_utf16 (const gunichar *str, 0894 glong len, 0895 glong *items_read, 0896 glong *items_written, 0897 GError **error) G_GNUC_MALLOC; 0898 GLIB_AVAILABLE_IN_ALL 0899 gchar* g_ucs4_to_utf8 (const gunichar *str, 0900 glong len, 0901 glong *items_read, 0902 glong *items_written, 0903 GError **error) G_GNUC_MALLOC; 0904 0905 GLIB_AVAILABLE_IN_ALL 0906 gint g_unichar_to_utf8 (gunichar c, 0907 gchar *outbuf); 0908 0909 GLIB_AVAILABLE_IN_ALL 0910 gboolean g_utf8_validate (const gchar *str, 0911 gssize max_len, 0912 const gchar **end); 0913 GLIB_AVAILABLE_IN_2_60 0914 gboolean g_utf8_validate_len (const gchar *str, 0915 gsize max_len, 0916 const gchar **end); 0917 0918 GLIB_AVAILABLE_IN_ALL 0919 gchar *g_utf8_strup (const gchar *str, 0920 gssize len) G_GNUC_MALLOC; 0921 GLIB_AVAILABLE_IN_ALL 0922 gchar *g_utf8_strdown (const gchar *str, 0923 gssize len) G_GNUC_MALLOC; 0924 GLIB_AVAILABLE_IN_ALL 0925 gchar *g_utf8_casefold (const gchar *str, 0926 gssize len) G_GNUC_MALLOC; 0927 0928 /** 0929 * GNormalizeMode: 0930 * @G_NORMALIZE_DEFAULT: standardize differences that do not affect the 0931 * text content, such as the above-mentioned accent representation 0932 * @G_NORMALIZE_NFD: another name for %G_NORMALIZE_DEFAULT 0933 * @G_NORMALIZE_DEFAULT_COMPOSE: like %G_NORMALIZE_DEFAULT, but with 0934 * composed forms rather than a maximally decomposed form 0935 * @G_NORMALIZE_NFC: another name for %G_NORMALIZE_DEFAULT_COMPOSE 0936 * @G_NORMALIZE_ALL: beyond %G_NORMALIZE_DEFAULT also standardize the 0937 * "compatibility" characters in Unicode, such as SUPERSCRIPT THREE 0938 * to the standard forms (in this case DIGIT THREE). Formatting 0939 * information may be lost but for most text operations such 0940 * characters should be considered the same 0941 * @G_NORMALIZE_NFKD: another name for %G_NORMALIZE_ALL 0942 * @G_NORMALIZE_ALL_COMPOSE: like %G_NORMALIZE_ALL, but with composed 0943 * forms rather than a maximally decomposed form 0944 * @G_NORMALIZE_NFKC: another name for %G_NORMALIZE_ALL_COMPOSE 0945 * 0946 * Defines how a Unicode string is transformed in a canonical 0947 * form, standardizing such issues as whether a character with 0948 * an accent is represented as a base character and combining 0949 * accent or as a single precomposed character. Unicode strings 0950 * should generally be normalized before comparing them. 0951 */ 0952 typedef enum { 0953 G_NORMALIZE_DEFAULT, 0954 G_NORMALIZE_NFD = G_NORMALIZE_DEFAULT, 0955 G_NORMALIZE_DEFAULT_COMPOSE, 0956 G_NORMALIZE_NFC = G_NORMALIZE_DEFAULT_COMPOSE, 0957 G_NORMALIZE_ALL, 0958 G_NORMALIZE_NFKD = G_NORMALIZE_ALL, 0959 G_NORMALIZE_ALL_COMPOSE, 0960 G_NORMALIZE_NFKC = G_NORMALIZE_ALL_COMPOSE 0961 } GNormalizeMode; 0962 0963 GLIB_AVAILABLE_IN_ALL 0964 gchar *g_utf8_normalize (const gchar *str, 0965 gssize len, 0966 GNormalizeMode mode) G_GNUC_MALLOC; 0967 0968 GLIB_AVAILABLE_IN_ALL 0969 gint g_utf8_collate (const gchar *str1, 0970 const gchar *str2) G_GNUC_PURE; 0971 GLIB_AVAILABLE_IN_ALL 0972 gchar *g_utf8_collate_key (const gchar *str, 0973 gssize len) G_GNUC_MALLOC; 0974 GLIB_AVAILABLE_IN_ALL 0975 gchar *g_utf8_collate_key_for_filename (const gchar *str, 0976 gssize len) G_GNUC_MALLOC; 0977 0978 GLIB_AVAILABLE_IN_2_52 0979 gchar *g_utf8_make_valid (const gchar *str, 0980 gssize len) G_GNUC_MALLOC; 0981 0982 G_END_DECLS 0983 0984 #endif /* __G_UNICODE_H__ */
| [ Source navigation ] | [ Diff markup ] | [ Identifier search ] | [ general search ] |
|
This page was automatically generated by the 2.3.7 LXR engine. The LXR team |
|