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 * write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330, 19 * Boston, MA 02111-1307, USA. 20 */ 21 22 #if defined(G_DISABLE_SINGLE_INCLUDES) && !defined (__GLIB_H_INSIDE__) && !defined (GLIB_COMPILATION) 23 #error "Only <glib.h> can be included directly." 24 #endif 25 26 #ifndef __G_UNICODE_H__ 27 #define __G_UNICODE_H__ 28 29 #include <glib/gerror.h> 30 #include <glib/gtypes.h> 31 32 G_BEGIN_DECLS 33 34 /** 35 * gunichar: 36 * 37 * A type which can hold any UTF-32 or UCS-4 character code, 38 * also known as a Unicode code point. 39 * 40 * If you want to produce the UTF-8 representation of a #gunichar, 41 * use g_ucs4_to_utf8(). See also g_utf8_to_ucs4() for the reverse 42 * process. 43 * 44 * To print/scan values of this type as integer, use 45 * %G_GINT32_MODIFIER and/or %G_GUINT32_FORMAT. 46 * 47 * The notation to express a Unicode code point in running text is 48 * as a hexadecimal number with four to six digits and uppercase 49 * letters, prefixed by the string "U+". Leading zeros are omitted, 50 * unless the code point would have fewer than four hexadecimal digits. 51 * For example, "U+0041 LATIN CAPITAL LETTER A". To print a code point 52 * in the U+-notation, use the format string "U+\%04"G_GINT32_FORMAT"X". 53 * To scan, use the format string "U+\%06"G_GINT32_FORMAT"X". 54 * 55 * |[ 56 * gunichar c; 57 * sscanf ("U+0041", "U+%06"G_GINT32_FORMAT"X", &c) 58 * g_print ("Read U+%04"G_GINT32_FORMAT"X", c); 59 * ]| 60 */ 61 typedef guint32 gunichar; 62 63 /** 64 * gunichar2: 65 * 66 * A type which can hold any UTF-16 code 67 * point<footnote id="utf16_surrogate_pairs">UTF-16 also has so called 68 * <firstterm>surrogate pairs</firstterm> to encode characters beyond 69 * the BMP as pairs of 16bit numbers. Surrogate pairs cannot be stored 70 * in a single gunichar2 field, but all GLib functions accepting gunichar2 71 * arrays will correctly interpret surrogate pairs.</footnote>. 72 * 73 * To print/scan values of this type to/from text you need to convert 74 * to/from UTF-8, using g_utf16_to_utf8()/g_utf8_to_utf16(). 75 * 76 * To print/scan values of this type as integer, use 77 * %G_GINT16_MODIFIER and/or %G_GUINT16_FORMAT. 78 */ 79 typedef guint16 gunichar2; 80 81 /** 82 * GUnicodeType: 83 * @G_UNICODE_CONTROL: General category "Other, Control" (Cc) 84 * @G_UNICODE_FORMAT: General category "Other, Format" (Cf) 85 * @G_UNICODE_UNASSIGNED: General category "Other, Not Assigned" (Cn) 86 * @G_UNICODE_PRIVATE_USE: General category "Other, Private Use" (Co) 87 * @G_UNICODE_SURROGATE: General category "Other, Surrogate" (Cs) 88 * @G_UNICODE_LOWERCASE_LETTER: General category "Letter, Lowercase" (Ll) 89 * @G_UNICODE_MODIFIER_LETTER: General category "Letter, Modifier" (Lm) 90 * @G_UNICODE_OTHER_LETTER: General category "Letter, Other" (Lo) 91 * @G_UNICODE_TITLECASE_LETTER: General category "Letter, Titlecase" (Lt) 92 * @G_UNICODE_UPPERCASE_LETTER: General category "Letter, Uppercase" (Lu) 93 * @G_UNICODE_SPACING_MARK: General category "Mark, Spacing" (Mc) 94 * @G_UNICODE_ENCLOSING_MARK: General category "Mark, Enclosing" (Me) 95 * @G_UNICODE_NON_SPACING_MARK: General category "Mark, Nonspacing" (Mn) 96 * @G_UNICODE_DECIMAL_NUMBER: General category "Number, Decimal Digit" (Nd) 97 * @G_UNICODE_LETTER_NUMBER: General category "Number, Letter" (Nl) 98 * @G_UNICODE_OTHER_NUMBER: General category "Number, Other" (No) 99 * @G_UNICODE_CONNECT_PUNCTUATION: General category "Punctuation, Connector" (Pc) 100 * @G_UNICODE_DASH_PUNCTUATION: General category "Punctuation, Dash" (Pd) 101 * @G_UNICODE_CLOSE_PUNCTUATION: General category "Punctuation, Close" (Pe) 102 * @G_UNICODE_FINAL_PUNCTUATION: General category "Punctuation, Final quote" (Pf) 103 * @G_UNICODE_INITIAL_PUNCTUATION: General category "Punctuation, Initial quote" (Pi) 104 * @G_UNICODE_OTHER_PUNCTUATION: General category "Punctuation, Other" (Po) 105 * @G_UNICODE_OPEN_PUNCTUATION: General category "Punctuation, Open" (Ps) 106 * @G_UNICODE_CURRENCY_SYMBOL: General category "Symbol, Currency" (Sc) 107 * @G_UNICODE_MODIFIER_SYMBOL: General category "Symbol, Modifier" (Sk) 108 * @G_UNICODE_MATH_SYMBOL: General category "Symbol, Math" (Sm) 109 * @G_UNICODE_OTHER_SYMBOL: General category "Symbol, Other" (So) 110 * @G_UNICODE_LINE_SEPARATOR: General category "Separator, Line" (Zl) 111 * @G_UNICODE_PARAGRAPH_SEPARATOR: General category "Separator, Paragraph" (Zp) 112 * @G_UNICODE_SPACE_SEPARATOR: General category "Separator, Space" (Zs) 113 * 114 * These are the possible character classifications from the 115 * Unicode specification. 116 * See <ulink url="http://www.unicode.org/Public/UNIDATA/UnicodeData.html">http://www.unicode.org/Public/UNIDATA/UnicodeData.html</ulink>. 117 */ 118 typedef enum 119 { 120 G_UNICODE_CONTROL, 121 G_UNICODE_FORMAT, 122 G_UNICODE_UNASSIGNED, 123 G_UNICODE_PRIVATE_USE, 124 G_UNICODE_SURROGATE, 125 G_UNICODE_LOWERCASE_LETTER, 126 G_UNICODE_MODIFIER_LETTER, 127 G_UNICODE_OTHER_LETTER, 128 G_UNICODE_TITLECASE_LETTER, 129 G_UNICODE_UPPERCASE_LETTER, 130 G_UNICODE_SPACING_MARK, 131 G_UNICODE_ENCLOSING_MARK, 132 G_UNICODE_NON_SPACING_MARK, 133 G_UNICODE_DECIMAL_NUMBER, 134 G_UNICODE_LETTER_NUMBER, 135 G_UNICODE_OTHER_NUMBER, 136 G_UNICODE_CONNECT_PUNCTUATION, 137 G_UNICODE_DASH_PUNCTUATION, 138 G_UNICODE_CLOSE_PUNCTUATION, 139 G_UNICODE_FINAL_PUNCTUATION, 140 G_UNICODE_INITIAL_PUNCTUATION, 141 G_UNICODE_OTHER_PUNCTUATION, 142 G_UNICODE_OPEN_PUNCTUATION, 143 G_UNICODE_CURRENCY_SYMBOL, 144 G_UNICODE_MODIFIER_SYMBOL, 145 G_UNICODE_MATH_SYMBOL, 146 G_UNICODE_OTHER_SYMBOL, 147 G_UNICODE_LINE_SEPARATOR, 148 G_UNICODE_PARAGRAPH_SEPARATOR, 149 G_UNICODE_SPACE_SEPARATOR 150 } GUnicodeType; 151 152 /** 153 * G_UNICODE_COMBINING_MARK: 154 * 155 * Older name for %G_UNICODE_SPACING_MARK. 156 * 157 * Deprecated: 2.30: Use %G_UNICODE_SPACING_MARK. 158 */ 159 #ifndef G_DISABLE_DEPRECATED 160 #define G_UNICODE_COMBINING_MARK G_UNICODE_SPACING_MARK 161 #endif 162 163 /** 164 * GUnicodeBreakType: 165 * @G_UNICODE_BREAK_MANDATORY: Mandatory Break (BK) 166 * @G_UNICODE_BREAK_CARRIAGE_RETURN: Carriage Return (CR) 167 * @G_UNICODE_BREAK_LINE_FEED: Line Feed (LF) 168 * @G_UNICODE_BREAK_COMBINING_MARK: Attached Characters and Combining Marks (CM) 169 * @G_UNICODE_BREAK_SURROGATE: Surrogates (SG) 170 * @G_UNICODE_BREAK_ZERO_WIDTH_SPACE: Zero Width Space (ZW) 171 * @G_UNICODE_BREAK_INSEPARABLE: Inseparable (IN) 172 * @G_UNICODE_BREAK_NON_BREAKING_GLUE: Non-breaking ("Glue") (GL) 173 * @G_UNICODE_BREAK_CONTINGENT: Contingent Break Opportunity (CB) 174 * @G_UNICODE_BREAK_SPACE: Space (SP) 175 * @G_UNICODE_BREAK_AFTER: Break Opportunity After (BA) 176 * @G_UNICODE_BREAK_BEFORE: Break Opportunity Before (BB) 177 * @G_UNICODE_BREAK_BEFORE_AND_AFTER: Break Opportunity Before and After (B2) 178 * @G_UNICODE_BREAK_HYPHEN: Hyphen (HY) 179 * @G_UNICODE_BREAK_NON_STARTER: Nonstarter (NS) 180 * @G_UNICODE_BREAK_OPEN_PUNCTUATION: Opening Punctuation (OP) 181 * @G_UNICODE_BREAK_CLOSE_PUNCTUATION: Closing Punctuation (CL) 182 * @G_UNICODE_BREAK_QUOTATION: Ambiguous Quotation (QU) 183 * @G_UNICODE_BREAK_EXCLAMATION: Exclamation/Interrogation (EX) 184 * @G_UNICODE_BREAK_IDEOGRAPHIC: Ideographic (ID) 185 * @G_UNICODE_BREAK_NUMERIC: Numeric (NU) 186 * @G_UNICODE_BREAK_INFIX_SEPARATOR: Infix Separator (Numeric) (IS) 187 * @G_UNICODE_BREAK_SYMBOL: Symbols Allowing Break After (SY) 188 * @G_UNICODE_BREAK_ALPHABETIC: Ordinary Alphabetic and Symbol Characters (AL) 189 * @G_UNICODE_BREAK_PREFIX: Prefix (Numeric) (PR) 190 * @G_UNICODE_BREAK_POSTFIX: Postfix (Numeric) (PO) 191 * @G_UNICODE_BREAK_COMPLEX_CONTEXT: Complex Content Dependent (South East Asian) (SA) 192 * @G_UNICODE_BREAK_AMBIGUOUS: Ambiguous (Alphabetic or Ideographic) (AI) 193 * @G_UNICODE_BREAK_UNKNOWN: Unknown (XX) 194 * @G_UNICODE_BREAK_NEXT_LINE: Next Line (NL) 195 * @G_UNICODE_BREAK_WORD_JOINER: Word Joiner (WJ) 196 * @G_UNICODE_BREAK_HANGUL_L_JAMO: Hangul L Jamo (JL) 197 * @G_UNICODE_BREAK_HANGUL_V_JAMO: Hangul V Jamo (JV) 198 * @G_UNICODE_BREAK_HANGUL_T_JAMO: Hangul T Jamo (JT) 199 * @G_UNICODE_BREAK_HANGUL_LV_SYLLABLE: Hangul LV Syllable (H2) 200 * @G_UNICODE_BREAK_HANGUL_LVT_SYLLABLE: Hangul LVT Syllable (H3) 201 * @G_UNICODE_BREAK_CLOSE_PARANTHESIS: Closing Parenthesis (CP). Since 2.28 202 * 203 * These are the possible line break classifications. 204 * 205 * The five Hangul types were added in Unicode 4.1, so, has been 206 * introduced in GLib 2.10. Note that new types may be added in the future. 207 * Applications should be ready to handle unknown values. 208 * 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 */ 212 typedef 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 } GUnicodeBreakType; 252 253 /** 254 * GUnicodeScript: 255 * @G_UNICODE_SCRIPT_INVALID_CODE: 256 * a value never returned from g_unichar_get_script() 257 * @G_UNICODE_SCRIPT_COMMON: a character used by multiple different scripts 258 * @G_UNICODE_SCRIPT_INHERITED: a mark glyph that takes its script from the 259 * i base glyph to which it is attached 260 * @G_UNICODE_SCRIPT_ARABIC: Arabic 261 * @G_UNICODE_SCRIPT_ARMENIAN: Armenian 262 * @G_UNICODE_SCRIPT_BENGALI: Bengali 263 * @G_UNICODE_SCRIPT_BOPOMOFO: Bopomofo 264 * @G_UNICODE_SCRIPT_CHEROKEE: Cherokee 265 * @G_UNICODE_SCRIPT_COPTIC: Coptic 266 * @G_UNICODE_SCRIPT_CYRILLIC: Cyrillic 267 * @G_UNICODE_SCRIPT_DESERET: Deseret 268 * @G_UNICODE_SCRIPT_DEVANAGARI: Devanagari 269 * @G_UNICODE_SCRIPT_ETHIOPIC: Ethiopic 270 * @G_UNICODE_SCRIPT_GEORGIAN: Georgian 271 * @G_UNICODE_SCRIPT_GOTHIC: Gothic 272 * @G_UNICODE_SCRIPT_GREEK: Greek 273 * @G_UNICODE_SCRIPT_GUJARATI: Gujarati 274 * @G_UNICODE_SCRIPT_GURMUKHI: Gurmukhi 275 * @G_UNICODE_SCRIPT_HAN: Han 276 * @G_UNICODE_SCRIPT_HANGUL: Hangul 277 * @G_UNICODE_SCRIPT_HEBREW: Hebrew 278 * @G_UNICODE_SCRIPT_HIRAGANA: Hiragana 279 * @G_UNICODE_SCRIPT_KANNADA: Kannada 280 * @G_UNICODE_SCRIPT_KATAKANA: Katakana 281 * @G_UNICODE_SCRIPT_KHMER: Khmer 282 * @G_UNICODE_SCRIPT_LAO: Lao 283 * @G_UNICODE_SCRIPT_LATIN: Latin 284 * @G_UNICODE_SCRIPT_MALAYALAM: Malayalam 285 * @G_UNICODE_SCRIPT_MONGOLIAN: Mongolian 286 * @G_UNICODE_SCRIPT_MYANMAR: Myanmar 287 * @G_UNICODE_SCRIPT_OGHAM: Ogham 288 * @G_UNICODE_SCRIPT_OLD_ITALIC: Old Italic 289 * @G_UNICODE_SCRIPT_ORIYA: Oriya 290 * @G_UNICODE_SCRIPT_RUNIC: Runic 291 * @G_UNICODE_SCRIPT_SINHALA: Sinhala 292 * @G_UNICODE_SCRIPT_SYRIAC: Syriac 293 * @G_UNICODE_SCRIPT_TAMIL: Tamil 294 * @G_UNICODE_SCRIPT_TELUGU: Telugu 295 * @G_UNICODE_SCRIPT_THAANA: Thaana 296 * @G_UNICODE_SCRIPT_THAI: Thai 297 * @G_UNICODE_SCRIPT_TIBETAN: Tibetan 298 * @G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL: 299 * Canadian Aboriginal 300 * @G_UNICODE_SCRIPT_YI: Yi 301 * @G_UNICODE_SCRIPT_TAGALOG: Tagalog 302 * @G_UNICODE_SCRIPT_HANUNOO: Hanunoo 303 * @G_UNICODE_SCRIPT_BUHID: Buhid 304 * @G_UNICODE_SCRIPT_TAGBANWA: Tagbanwa 305 * @G_UNICODE_SCRIPT_BRAILLE: Braille 306 * @G_UNICODE_SCRIPT_CYPRIOT: Cypriot 307 * @G_UNICODE_SCRIPT_LIMBU: Limbu 308 * @G_UNICODE_SCRIPT_OSMANYA: Osmanya 309 * @G_UNICODE_SCRIPT_SHAVIAN: Shavian 310 * @G_UNICODE_SCRIPT_LINEAR_B: Linear B 311 * @G_UNICODE_SCRIPT_TAI_LE: Tai Le 312 * @G_UNICODE_SCRIPT_UGARITIC: Ugaritic 313 * @G_UNICODE_SCRIPT_NEW_TAI_LUE: 314 * New Tai Lue 315 * @G_UNICODE_SCRIPT_BUGINESE: Buginese 316 * @G_UNICODE_SCRIPT_GLAGOLITIC: Glagolitic 317 * @G_UNICODE_SCRIPT_TIFINAGH: Tifinagh 318 * @G_UNICODE_SCRIPT_SYLOTI_NAGRI: 319 * Syloti Nagri 320 * @G_UNICODE_SCRIPT_OLD_PERSIAN: 321 * Old Persian 322 * @G_UNICODE_SCRIPT_KHAROSHTHI: Kharoshthi 323 * @G_UNICODE_SCRIPT_UNKNOWN: an unassigned code point 324 * @G_UNICODE_SCRIPT_BALINESE: Balinese 325 * @G_UNICODE_SCRIPT_CUNEIFORM: Cuneiform 326 * @G_UNICODE_SCRIPT_PHOENICIAN: Phoenician 327 * @G_UNICODE_SCRIPT_PHAGS_PA: Phags-pa 328 * @G_UNICODE_SCRIPT_NKO: N'Ko 329 * @G_UNICODE_SCRIPT_KAYAH_LI: Kayah Li. Since 2.16.3 330 * @G_UNICODE_SCRIPT_LEPCHA: Lepcha. Since 2.16.3 331 * @G_UNICODE_SCRIPT_REJANG: Rejang. Since 2.16.3 332 * @G_UNICODE_SCRIPT_SUNDANESE: Sundanese. Since 2.16.3 333 * @G_UNICODE_SCRIPT_SAURASHTRA: Saurashtra. Since 2.16.3 334 * @G_UNICODE_SCRIPT_CHAM: Cham. Since 2.16.3 335 * @G_UNICODE_SCRIPT_OL_CHIKI: Ol Chiki. Since 2.16.3 336 * @G_UNICODE_SCRIPT_VAI: Vai. Since 2.16.3 337 * @G_UNICODE_SCRIPT_CARIAN: Carian. Since 2.16.3 338 * @G_UNICODE_SCRIPT_LYCIAN: Lycian. Since 2.16.3 339 * @G_UNICODE_SCRIPT_LYDIAN: Lydian. Since 2.16.3 340 * @G_UNICODE_SCRIPT_AVESTAN: Avestan. Since 2.26 341 * @G_UNICODE_SCRIPT_BAMUM: Bamum. Since 2.26 342 * @G_UNICODE_SCRIPT_EGYPTIAN_HIEROGLYPHS: 343 * Egyptian Hieroglpyhs. Since 2.26 344 * @G_UNICODE_SCRIPT_IMPERIAL_ARAMAIC: 345 * Imperial Aramaic. Since 2.26 346 * @G_UNICODE_SCRIPT_INSCRIPTIONAL_PAHLAVI: 347 * Inscriptional Pahlavi. Since 2.26 348 * @G_UNICODE_SCRIPT_INSCRIPTIONAL_PARTHIAN: 349 * Inscriptional Parthian. Since 2.26 350 * @G_UNICODE_SCRIPT_JAVANESE: Javanese. Since 2.26 351 * @G_UNICODE_SCRIPT_KAITHI: Kaithi. Since 2.26 352 * @G_UNICODE_SCRIPT_LISU: Lisu. Since 2.26 353 * @G_UNICODE_SCRIPT_MEETEI_MAYEK: 354 * Meetei Mayek. Since 2.26 355 * @G_UNICODE_SCRIPT_OLD_SOUTH_ARABIAN: 356 * Old South Arabian. Since 2.26 357 * @G_UNICODE_SCRIPT_OLD_TURKIC: Old Turkic. Since 2.28 358 * @G_UNICODE_SCRIPT_SAMARITAN: Samaritan. Since 2.26 359 * @G_UNICODE_SCRIPT_TAI_THAM: Tai Tham. Since 2.26 360 * @G_UNICODE_SCRIPT_TAI_VIET: Tai Viet. Since 2.26 361 * @G_UNICODE_SCRIPT_BATAK: Batak. Since 2.28 362 * @G_UNICODE_SCRIPT_BRAHMI: Brahmi. Since 2.28 363 * @G_UNICODE_SCRIPT_MANDAIC: Mandaic. Since 2.28 364 * 365 * The #GUnicodeScript enumeration identifies different writing 366 * systems. The values correspond to the names as defined in the 367 * Unicode standard. The enumeration has been added in GLib 2.14, 368 * and is interchangeable with #PangoScript. 369 * 370 * Note that new types may be added in the future. Applications 371 * should be ready to handle unknown values. 372 * See <ulink 373 * url="http://www.unicode.org/reports/tr24/">Unicode Standard Annex 374 * #24: Script names</ulink>. 375 */ 376 typedef enum 377 { /* ISO 15924 code */ 378 G_UNICODE_SCRIPT_INVALID_CODE = -1, 379 G_UNICODE_SCRIPT_COMMON = 0, /* Zyyy */ 380 G_UNICODE_SCRIPT_INHERITED, /* Qaai */ 381 G_UNICODE_SCRIPT_ARABIC, /* Arab */ 382 G_UNICODE_SCRIPT_ARMENIAN, /* Armn */ 383 G_UNICODE_SCRIPT_BENGALI, /* Beng */ 384 G_UNICODE_SCRIPT_BOPOMOFO, /* Bopo */ 385 G_UNICODE_SCRIPT_CHEROKEE, /* Cher */ 386 G_UNICODE_SCRIPT_COPTIC, /* Qaac */ 387 G_UNICODE_SCRIPT_CYRILLIC, /* Cyrl (Cyrs) */ 388 G_UNICODE_SCRIPT_DESERET, /* Dsrt */ 389 G_UNICODE_SCRIPT_DEVANAGARI, /* Deva */ 390 G_UNICODE_SCRIPT_ETHIOPIC, /* Ethi */ 391 G_UNICODE_SCRIPT_GEORGIAN, /* Geor (Geon, Geoa) */ 392 G_UNICODE_SCRIPT_GOTHIC, /* Goth */ 393 G_UNICODE_SCRIPT_GREEK, /* Grek */ 394 G_UNICODE_SCRIPT_GUJARATI, /* Gujr */ 395 G_UNICODE_SCRIPT_GURMUKHI, /* Guru */ 396 G_UNICODE_SCRIPT_HAN, /* Hani */ 397 G_UNICODE_SCRIPT_HANGUL, /* Hang */ 398 G_UNICODE_SCRIPT_HEBREW, /* Hebr */ 399 G_UNICODE_SCRIPT_HIRAGANA, /* Hira */ 400 G_UNICODE_SCRIPT_KANNADA, /* Knda */ 401 G_UNICODE_SCRIPT_KATAKANA, /* Kana */ 402 G_UNICODE_SCRIPT_KHMER, /* Khmr */ 403 G_UNICODE_SCRIPT_LAO, /* Laoo */ 404 G_UNICODE_SCRIPT_LATIN, /* Latn (Latf, Latg) */ 405 G_UNICODE_SCRIPT_MALAYALAM, /* Mlym */ 406 G_UNICODE_SCRIPT_MONGOLIAN, /* Mong */ 407 G_UNICODE_SCRIPT_MYANMAR, /* Mymr */ 408 G_UNICODE_SCRIPT_OGHAM, /* Ogam */ 409 G_UNICODE_SCRIPT_OLD_ITALIC, /* Ital */ 410 G_UNICODE_SCRIPT_ORIYA, /* Orya */ 411 G_UNICODE_SCRIPT_RUNIC, /* Runr */ 412 G_UNICODE_SCRIPT_SINHALA, /* Sinh */ 413 G_UNICODE_SCRIPT_SYRIAC, /* Syrc (Syrj, Syrn, Syre) */ 414 G_UNICODE_SCRIPT_TAMIL, /* Taml */ 415 G_UNICODE_SCRIPT_TELUGU, /* Telu */ 416 G_UNICODE_SCRIPT_THAANA, /* Thaa */ 417 G_UNICODE_SCRIPT_THAI, /* Thai */ 418 G_UNICODE_SCRIPT_TIBETAN, /* Tibt */ 419 G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL, /* Cans */ 420 G_UNICODE_SCRIPT_YI, /* Yiii */ 421 G_UNICODE_SCRIPT_TAGALOG, /* Tglg */ 422 G_UNICODE_SCRIPT_HANUNOO, /* Hano */ 423 G_UNICODE_SCRIPT_BUHID, /* Buhd */ 424 G_UNICODE_SCRIPT_TAGBANWA, /* Tagb */ 425 426 /* Unicode-4.0 additions */ 427 G_UNICODE_SCRIPT_BRAILLE, /* Brai */ 428 G_UNICODE_SCRIPT_CYPRIOT, /* Cprt */ 429 G_UNICODE_SCRIPT_LIMBU, /* Limb */ 430 G_UNICODE_SCRIPT_OSMANYA, /* Osma */ 431 G_UNICODE_SCRIPT_SHAVIAN, /* Shaw */ 432 G_UNICODE_SCRIPT_LINEAR_B, /* Linb */ 433 G_UNICODE_SCRIPT_TAI_LE, /* Tale */ 434 G_UNICODE_SCRIPT_UGARITIC, /* Ugar */ 435 436 /* Unicode-4.1 additions */ 437 G_UNICODE_SCRIPT_NEW_TAI_LUE, /* Talu */ 438 G_UNICODE_SCRIPT_BUGINESE, /* Bugi */ 439 G_UNICODE_SCRIPT_GLAGOLITIC, /* Glag */ 440 G_UNICODE_SCRIPT_TIFINAGH, /* Tfng */ 441 G_UNICODE_SCRIPT_SYLOTI_NAGRI, /* Sylo */ 442 G_UNICODE_SCRIPT_OLD_PERSIAN, /* Xpeo */ 443 G_UNICODE_SCRIPT_KHAROSHTHI, /* Khar */ 444 445 /* Unicode-5.0 additions */ 446 G_UNICODE_SCRIPT_UNKNOWN, /* Zzzz */ 447 G_UNICODE_SCRIPT_BALINESE, /* Bali */ 448 G_UNICODE_SCRIPT_CUNEIFORM, /* Xsux */ 449 G_UNICODE_SCRIPT_PHOENICIAN, /* Phnx */ 450 G_UNICODE_SCRIPT_PHAGS_PA, /* Phag */ 451 G_UNICODE_SCRIPT_NKO, /* Nkoo */ 452 453 /* Unicode-5.1 additions */ 454 G_UNICODE_SCRIPT_KAYAH_LI, /* Kali */ 455 G_UNICODE_SCRIPT_LEPCHA, /* Lepc */ 456 G_UNICODE_SCRIPT_REJANG, /* Rjng */ 457 G_UNICODE_SCRIPT_SUNDANESE, /* Sund */ 458 G_UNICODE_SCRIPT_SAURASHTRA, /* Saur */ 459 G_UNICODE_SCRIPT_CHAM, /* Cham */ 460 G_UNICODE_SCRIPT_OL_CHIKI, /* Olck */ 461 G_UNICODE_SCRIPT_VAI, /* Vaii */ 462 G_UNICODE_SCRIPT_CARIAN, /* Cari */ 463 G_UNICODE_SCRIPT_LYCIAN, /* Lyci */ 464 G_UNICODE_SCRIPT_LYDIAN, /* Lydi */ 465 466 /* Unicode-5.2 additions */ 467 G_UNICODE_SCRIPT_AVESTAN, /* Avst */ 468 G_UNICODE_SCRIPT_BAMUM, /* Bamu */ 469 G_UNICODE_SCRIPT_EGYPTIAN_HIEROGLYPHS, /* Egyp */ 470 G_UNICODE_SCRIPT_IMPERIAL_ARAMAIC, /* Armi */ 471 G_UNICODE_SCRIPT_INSCRIPTIONAL_PAHLAVI, /* Phli */ 472 G_UNICODE_SCRIPT_INSCRIPTIONAL_PARTHIAN, /* Prti */ 473 G_UNICODE_SCRIPT_JAVANESE, /* Java */ 474 G_UNICODE_SCRIPT_KAITHI, /* Kthi */ 475 G_UNICODE_SCRIPT_LISU, /* Lisu */ 476 G_UNICODE_SCRIPT_MEETEI_MAYEK, /* Mtei */ 477 G_UNICODE_SCRIPT_OLD_SOUTH_ARABIAN, /* Sarb */ 478 G_UNICODE_SCRIPT_OLD_TURKIC, /* Orkh */ 479 G_UNICODE_SCRIPT_SAMARITAN, /* Samr */ 480 G_UNICODE_SCRIPT_TAI_THAM, /* Lana */ 481 G_UNICODE_SCRIPT_TAI_VIET, /* Tavt */ 482 483 /* Unicode-6.0 additions */ 484 G_UNICODE_SCRIPT_BATAK, /* Batk */ 485 G_UNICODE_SCRIPT_BRAHMI, /* Brah */ 486 G_UNICODE_SCRIPT_MANDAIC /* Mand */ 487 } GUnicodeScript; 488 489 guint32 g_unicode_script_to_iso15924 (GUnicodeScript script); 490 GUnicodeScript g_unicode_script_from_iso15924 (guint32 iso15924); 491 492 /* Returns TRUE if current locale uses UTF-8 charset. If CHARSET is 493 * not null, sets *CHARSET to the name of the current locale's 494 * charset. This value is statically allocated, and should be copied 495 * in case the locale's charset will be changed later using setlocale() 496 * or in some other way. 497 */ 498 gboolean g_get_charset (const char **charset); 499 500 /* These are all analogs of the <ctype.h> functions. 501 */ 502 gboolean g_unichar_isalnum (gunichar c) G_GNUC_CONST; 503 gboolean g_unichar_isalpha (gunichar c) G_GNUC_CONST; 504 gboolean g_unichar_iscntrl (gunichar c) G_GNUC_CONST; 505 gboolean g_unichar_isdigit (gunichar c) G_GNUC_CONST; 506 gboolean g_unichar_isgraph (gunichar c) G_GNUC_CONST; 507 gboolean g_unichar_islower (gunichar c) G_GNUC_CONST; 508 gboolean g_unichar_isprint (gunichar c) G_GNUC_CONST; 509 gboolean g_unichar_ispunct (gunichar c) G_GNUC_CONST; 510 gboolean g_unichar_isspace (gunichar c) G_GNUC_CONST; 511 gboolean g_unichar_isupper (gunichar c) G_GNUC_CONST; 512 gboolean g_unichar_isxdigit (gunichar c) G_GNUC_CONST; 513 gboolean g_unichar_istitle (gunichar c) G_GNUC_CONST; 514 gboolean g_unichar_isdefined (gunichar c) G_GNUC_CONST; 515 gboolean g_unichar_iswide (gunichar c) G_GNUC_CONST; 516 gboolean g_unichar_iswide_cjk(gunichar c) G_GNUC_CONST; 517 gboolean g_unichar_iszerowidth(gunichar c) G_GNUC_CONST; 518 gboolean g_unichar_ismark (gunichar c) G_GNUC_CONST; 519 520 /* More <ctype.h> functions. These convert between the three cases. 521 * See the Unicode book to understand title case. */ 522 gunichar g_unichar_toupper (gunichar c) G_GNUC_CONST; 523 gunichar g_unichar_tolower (gunichar c) G_GNUC_CONST; 524 gunichar g_unichar_totitle (gunichar c) G_GNUC_CONST; 525 526 /* If C is a digit (according to `g_unichar_isdigit'), then return its 527 numeric value. Otherwise return -1. */ 528 gint g_unichar_digit_value (gunichar c) G_GNUC_CONST; 529 530 gint g_unichar_xdigit_value (gunichar c) G_GNUC_CONST; 531 532 /* Return the Unicode character type of a given character. */ 533 GUnicodeType g_unichar_type (gunichar c) G_GNUC_CONST; 534 535 /* Return the line break property for a given character */ 536 GUnicodeBreakType g_unichar_break_type (gunichar c) G_GNUC_CONST; 537 538 /* Returns the combining class for a given character */ 539 gint g_unichar_combining_class (gunichar uc) G_GNUC_CONST; 540 541 gboolean g_unichar_get_mirror_char (gunichar ch, 542 gunichar *mirrored_ch); 543 544 GUnicodeScript g_unichar_get_script (gunichar ch) G_GNUC_CONST; 545 546 /* Validate a Unicode character */ 547 gboolean g_unichar_validate (gunichar ch) G_GNUC_CONST; 548 549 /* Pairwise canonical compose/decompose */ 550 gboolean g_unichar_compose (gunichar a, 551 gunichar b, 552 gunichar *ch); 553 gboolean g_unichar_decompose (gunichar ch, 554 gunichar *a, 555 gunichar *b); 556 557 gsize g_unichar_fully_decompose (gunichar ch, 558 gboolean compat, 559 gunichar *result, 560 gsize result_len); 561 562 /* Compute canonical ordering of a string in-place. This rearranges 563 decomposed characters in the string according to their combining 564 classes. See the Unicode manual for more information. */ 565 void g_unicode_canonical_ordering (gunichar *string, 566 gsize len); 567 568 569 #ifndef G_DISABLE_DEPRECATED 570 /* Deprecated. Use g_unichar_fully_decompose() */ 571 gunichar *g_unicode_canonical_decomposition (gunichar ch, 572 gsize *result_len) G_GNUC_MALLOC; 573 #endif 574 575 /* Array of skip-bytes-per-initial character. 576 */ 577 GLIB_VAR const gchar * const g_utf8_skip; 578 579 /** 580 * g_utf8_next_char: 581 * @p: Pointer to the start of a valid UTF-8 character 582 * 583 * Skips to the next character in a UTF-8 string. The string must be 584 * valid; this macro is as fast as possible, and has no error-checking. 585 * You would use this macro to iterate over a string character by 586 * character. The macro returns the start of the next UTF-8 character. 587 * Before using this macro, use g_utf8_validate() to validate strings 588 * that may contain invalid UTF-8. 589 */ 590 #define g_utf8_next_char(p) (char *)((p) + g_utf8_skip[*(const guchar *)(p)]) 591 592 gunichar g_utf8_get_char (const gchar *p) G_GNUC_PURE; 593 gunichar g_utf8_get_char_validated (const gchar *p, 594 gssize max_len) G_GNUC_PURE; 595 596 gchar* g_utf8_offset_to_pointer (const gchar *str, 597 glong offset) G_GNUC_PURE; 598 glong g_utf8_pointer_to_offset (const gchar *str, 599 const gchar *pos) G_GNUC_PURE; 600 gchar* g_utf8_prev_char (const gchar *p) G_GNUC_PURE; 601 gchar* g_utf8_find_next_char (const gchar *p, 602 const gchar *end) G_GNUC_PURE; 603 gchar* g_utf8_find_prev_char (const gchar *str, 604 const gchar *p) G_GNUC_PURE; 605 606 glong g_utf8_strlen (const gchar *p, 607 gssize max) G_GNUC_PURE; 608 609 gchar *g_utf8_substring (const gchar *str, 610 glong start_pos, 611 glong end_pos) G_GNUC_MALLOC; 612 613 gchar *g_utf8_strncpy (gchar *dest, 614 const gchar *src, 615 gsize n); 616 617 /* Find the UTF-8 character corresponding to ch, in string p. These 618 functions are equivalants to strchr and strrchr */ 619 gchar* g_utf8_strchr (const gchar *p, 620 gssize len, 621 gunichar c); 622 gchar* g_utf8_strrchr (const gchar *p, 623 gssize len, 624 gunichar c); 625 gchar* g_utf8_strreverse (const gchar *str, 626 gssize len); 627 628 gunichar2 *g_utf8_to_utf16 (const gchar *str, 629 glong len, 630 glong *items_read, 631 glong *items_written, 632 GError **error) G_GNUC_MALLOC; 633 gunichar * g_utf8_to_ucs4 (const gchar *str, 634 glong len, 635 glong *items_read, 636 glong *items_written, 637 GError **error) G_GNUC_MALLOC; 638 gunichar * g_utf8_to_ucs4_fast (const gchar *str, 639 glong len, 640 glong *items_written) G_GNUC_MALLOC; 641 gunichar * g_utf16_to_ucs4 (const gunichar2 *str, 642 glong len, 643 glong *items_read, 644 glong *items_written, 645 GError **error) G_GNUC_MALLOC; 646 gchar* g_utf16_to_utf8 (const gunichar2 *str, 647 glong len, 648 glong *items_read, 649 glong *items_written, 650 GError **error) G_GNUC_MALLOC; 651 gunichar2 *g_ucs4_to_utf16 (const gunichar *str, 652 glong len, 653 glong *items_read, 654 glong *items_written, 655 GError **error) G_GNUC_MALLOC; 656 gchar* g_ucs4_to_utf8 (const gunichar *str, 657 glong len, 658 glong *items_read, 659 glong *items_written, 660 GError **error) G_GNUC_MALLOC; 661 662 gint g_unichar_to_utf8 (gunichar c, 663 gchar *outbuf); 664 665 gboolean g_utf8_validate (const gchar *str, 666 gssize max_len, 667 const gchar **end); 668 669 gchar *g_utf8_strup (const gchar *str, 670 gssize len) G_GNUC_MALLOC; 671 gchar *g_utf8_strdown (const gchar *str, 672 gssize len) G_GNUC_MALLOC; 673 gchar *g_utf8_casefold (const gchar *str, 674 gssize len) G_GNUC_MALLOC; 675 676 /** 677 * GNormalizeMode: 678 * @G_NORMALIZE_DEFAULT: standardize differences that do not affect the 679 * text content, such as the above-mentioned accent representation 680 * @G_NORMALIZE_NFD: another name for %G_NORMALIZE_DEFAULT 681 * @G_NORMALIZE_DEFAULT_COMPOSE: like %G_NORMALIZE_DEFAULT, but with 682 * composed forms rather than a maximally decomposed form 683 * @G_NORMALIZE_NFC: another name for %G_NORMALIZE_DEFAULT_COMPOSE 684 * @G_NORMALIZE_ALL: beyond %G_NORMALIZE_DEFAULT also standardize the 685 * "compatibility" characters in Unicode, such as SUPERSCRIPT THREE 686 * to the standard forms (in this case DIGIT THREE). Formatting 687 * information may be lost but for most text operations such 688 * characters should be considered the same 689 * @G_NORMALIZE_NFKD: another name for %G_NORMALIZE_ALL 690 * @G_NORMALIZE_ALL_COMPOSE: like %G_NORMALIZE_ALL, but with composed 691 * forms rather than a maximally decomposed form 692 * @G_NORMALIZE_NFKC: another name for %G_NORMALIZE_ALL_COMPOSE 693 * 694 * Defines how a Unicode string is transformed in a canonical 695 * form, standardizing such issues as whether a character with 696 * an accent is represented as a base character and combining 697 * accent or as a single precomposed character. Unicode strings 698 * should generally be normalized before comparing them. 699 */ 700 typedef enum { 701 G_NORMALIZE_DEFAULT, 702 G_NORMALIZE_NFD = G_NORMALIZE_DEFAULT, 703 G_NORMALIZE_DEFAULT_COMPOSE, 704 G_NORMALIZE_NFC = G_NORMALIZE_DEFAULT_COMPOSE, 705 G_NORMALIZE_ALL, 706 G_NORMALIZE_NFKD = G_NORMALIZE_ALL, 707 G_NORMALIZE_ALL_COMPOSE, 708 G_NORMALIZE_NFKC = G_NORMALIZE_ALL_COMPOSE 709 } GNormalizeMode; 710 711 gchar *g_utf8_normalize (const gchar *str, 712 gssize len, 713 GNormalizeMode mode) G_GNUC_MALLOC; 714 715 gint g_utf8_collate (const gchar *str1, 716 const gchar *str2) G_GNUC_PURE; 717 gchar *g_utf8_collate_key (const gchar *str, 718 gssize len) G_GNUC_MALLOC; 719 gchar *g_utf8_collate_key_for_filename (const gchar *str, 720 gssize len) G_GNUC_MALLOC; 721 722 723 /* private */ 724 725 gchar *_g_utf8_make_valid (const gchar *name); 726 727 G_END_DECLS 728 729 #endif /* __G_UNICODE_H__ */ 730