glib/gunicode.h

   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 (__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", &amp;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  * @G_UNICODE_BREAK_CONDITIONAL_JAPANESE_STARTER: Conditional Japanese Starter (CJ). Since: 2.32
 203  * @G_UNICODE_BREAK_HEBREW_LETTER: Hebrew Letter (HL). Since: 2.32
 204  *
 205  * These are the possible line break classifications.
 206  *
 207  * The five Hangul types were added in Unicode 4.1, so, has been
 208  * introduced in GLib 2.10. Note that new types may be added in the future.
 209  * Applications should be ready to handle unknown values.
 210  * They may be regarded as %G_UNICODE_BREAK_UNKNOWN.
 211  *
 212  * See <ulink url="http://www.unicode.org/unicode/reports/tr14/">http://www.unicode.org/unicode/reports/tr14/</ulink>.
 213  */
 214 typedef enum
 215 {
 216   G_UNICODE_BREAK_MANDATORY,
 217   G_UNICODE_BREAK_CARRIAGE_RETURN,
 218   G_UNICODE_BREAK_LINE_FEED,
 219   G_UNICODE_BREAK_COMBINING_MARK,
 220   G_UNICODE_BREAK_SURROGATE,
 221   G_UNICODE_BREAK_ZERO_WIDTH_SPACE,
 222   G_UNICODE_BREAK_INSEPARABLE,
 223   G_UNICODE_BREAK_NON_BREAKING_GLUE,
 224   G_UNICODE_BREAK_CONTINGENT,
 225   G_UNICODE_BREAK_SPACE,
 226   G_UNICODE_BREAK_AFTER,
 227   G_UNICODE_BREAK_BEFORE,
 228   G_UNICODE_BREAK_BEFORE_AND_AFTER,
 229   G_UNICODE_BREAK_HYPHEN,
 230   G_UNICODE_BREAK_NON_STARTER,
 231   G_UNICODE_BREAK_OPEN_PUNCTUATION,
 232   G_UNICODE_BREAK_CLOSE_PUNCTUATION,
 233   G_UNICODE_BREAK_QUOTATION,
 234   G_UNICODE_BREAK_EXCLAMATION,
 235   G_UNICODE_BREAK_IDEOGRAPHIC,
 236   G_UNICODE_BREAK_NUMERIC,
 237   G_UNICODE_BREAK_INFIX_SEPARATOR,
 238   G_UNICODE_BREAK_SYMBOL,
 239   G_UNICODE_BREAK_ALPHABETIC,
 240   G_UNICODE_BREAK_PREFIX,
 241   G_UNICODE_BREAK_POSTFIX,
 242   G_UNICODE_BREAK_COMPLEX_CONTEXT,
 243   G_UNICODE_BREAK_AMBIGUOUS,
 244   G_UNICODE_BREAK_UNKNOWN,
 245   G_UNICODE_BREAK_NEXT_LINE,
 246   G_UNICODE_BREAK_WORD_JOINER,
 247   G_UNICODE_BREAK_HANGUL_L_JAMO,
 248   G_UNICODE_BREAK_HANGUL_V_JAMO,
 249   G_UNICODE_BREAK_HANGUL_T_JAMO,
 250   G_UNICODE_BREAK_HANGUL_LV_SYLLABLE,
 251   G_UNICODE_BREAK_HANGUL_LVT_SYLLABLE,
 252   G_UNICODE_BREAK_CLOSE_PARANTHESIS,
 253   G_UNICODE_BREAK_CONDITIONAL_JAPANESE_STARTER,
 254   G_UNICODE_BREAK_HEBREW_LETTER
 255 } GUnicodeBreakType;
 256
 257 /**
 258  * GUnicodeScript:
 259  * @G_UNICODE_SCRIPT_INVALID_CODE:
 260  *                               a value never returned from g_unichar_get_script()
 261  * @G_UNICODE_SCRIPT_COMMON:     a character used by multiple different scripts
 262  * @G_UNICODE_SCRIPT_INHERITED:  a mark glyph that takes its script from the
 263  * i                             base glyph to which it is attached
 264  * @G_UNICODE_SCRIPT_ARABIC:     Arabic
 265  * @G_UNICODE_SCRIPT_ARMENIAN:   Armenian
 266  * @G_UNICODE_SCRIPT_BENGALI:    Bengali
 267  * @G_UNICODE_SCRIPT_BOPOMOFO:   Bopomofo
 268  * @G_UNICODE_SCRIPT_CHEROKEE:   Cherokee
 269  * @G_UNICODE_SCRIPT_COPTIC:     Coptic
 270  * @G_UNICODE_SCRIPT_CYRILLIC:   Cyrillic
 271  * @G_UNICODE_SCRIPT_DESERET:    Deseret
 272  * @G_UNICODE_SCRIPT_DEVANAGARI: Devanagari
 273  * @G_UNICODE_SCRIPT_ETHIOPIC:   Ethiopic
 274  * @G_UNICODE_SCRIPT_GEORGIAN:   Georgian
 275  * @G_UNICODE_SCRIPT_GOTHIC:     Gothic
 276  * @G_UNICODE_SCRIPT_GREEK:      Greek
 277  * @G_UNICODE_SCRIPT_GUJARATI:   Gujarati
 278  * @G_UNICODE_SCRIPT_GURMUKHI:   Gurmukhi
 279  * @G_UNICODE_SCRIPT_HAN:        Han
 280  * @G_UNICODE_SCRIPT_HANGUL:     Hangul
 281  * @G_UNICODE_SCRIPT_HEBREW:     Hebrew
 282  * @G_UNICODE_SCRIPT_HIRAGANA:   Hiragana
 283  * @G_UNICODE_SCRIPT_KANNADA:    Kannada
 284  * @G_UNICODE_SCRIPT_KATAKANA:   Katakana
 285  * @G_UNICODE_SCRIPT_KHMER:      Khmer
 286  * @G_UNICODE_SCRIPT_LAO:        Lao
 287  * @G_UNICODE_SCRIPT_LATIN:      Latin
 288  * @G_UNICODE_SCRIPT_MALAYALAM:  Malayalam
 289  * @G_UNICODE_SCRIPT_MONGOLIAN:  Mongolian
 290  * @G_UNICODE_SCRIPT_MYANMAR:    Myanmar
 291  * @G_UNICODE_SCRIPT_OGHAM:      Ogham
 292  * @G_UNICODE_SCRIPT_OLD_ITALIC: Old Italic
 293  * @G_UNICODE_SCRIPT_ORIYA:      Oriya
 294  * @G_UNICODE_SCRIPT_RUNIC:      Runic
 295  * @G_UNICODE_SCRIPT_SINHALA:    Sinhala
 296  * @G_UNICODE_SCRIPT_SYRIAC:     Syriac
 297  * @G_UNICODE_SCRIPT_TAMIL:      Tamil
 298  * @G_UNICODE_SCRIPT_TELUGU:     Telugu
 299  * @G_UNICODE_SCRIPT_THAANA:     Thaana
 300  * @G_UNICODE_SCRIPT_THAI:       Thai
 301  * @G_UNICODE_SCRIPT_TIBETAN:    Tibetan
 302  * @G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL:
 303  *                               Canadian Aboriginal
 304  * @G_UNICODE_SCRIPT_YI:         Yi
 305  * @G_UNICODE_SCRIPT_TAGALOG:    Tagalog
 306  * @G_UNICODE_SCRIPT_HANUNOO:    Hanunoo
 307  * @G_UNICODE_SCRIPT_BUHID:      Buhid
 308  * @G_UNICODE_SCRIPT_TAGBANWA:   Tagbanwa
 309  * @G_UNICODE_SCRIPT_BRAILLE:    Braille
 310  * @G_UNICODE_SCRIPT_CYPRIOT:    Cypriot
 311  * @G_UNICODE_SCRIPT_LIMBU:      Limbu
 312  * @G_UNICODE_SCRIPT_OSMANYA:    Osmanya
 313  * @G_UNICODE_SCRIPT_SHAVIAN:    Shavian
 314  * @G_UNICODE_SCRIPT_LINEAR_B:   Linear B
 315  * @G_UNICODE_SCRIPT_TAI_LE:     Tai Le
 316  * @G_UNICODE_SCRIPT_UGARITIC:   Ugaritic
 317  * @G_UNICODE_SCRIPT_NEW_TAI_LUE:
 318  *                               New Tai Lue
 319  * @G_UNICODE_SCRIPT_BUGINESE:   Buginese
 320  * @G_UNICODE_SCRIPT_GLAGOLITIC: Glagolitic
 321  * @G_UNICODE_SCRIPT_TIFINAGH:   Tifinagh
 322  * @G_UNICODE_SCRIPT_SYLOTI_NAGRI:
 323  *                               Syloti Nagri
 324  * @G_UNICODE_SCRIPT_OLD_PERSIAN:
 325  *                               Old Persian
 326  * @G_UNICODE_SCRIPT_KHAROSHTHI: Kharoshthi
 327  * @G_UNICODE_SCRIPT_UNKNOWN:    an unassigned code point
 328  * @G_UNICODE_SCRIPT_BALINESE:   Balinese
 329  * @G_UNICODE_SCRIPT_CUNEIFORM:  Cuneiform
 330  * @G_UNICODE_SCRIPT_PHOENICIAN: Phoenician
 331  * @G_UNICODE_SCRIPT_PHAGS_PA:   Phags-pa
 332  * @G_UNICODE_SCRIPT_NKO:        N'Ko
 333  * @G_UNICODE_SCRIPT_KAYAH_LI:   Kayah Li. Since 2.16.3
 334  * @G_UNICODE_SCRIPT_LEPCHA:     Lepcha. Since 2.16.3
 335  * @G_UNICODE_SCRIPT_REJANG:     Rejang. Since 2.16.3
 336  * @G_UNICODE_SCRIPT_SUNDANESE:  Sundanese. Since 2.16.3
 337  * @G_UNICODE_SCRIPT_SAURASHTRA: Saurashtra. Since 2.16.3
 338  * @G_UNICODE_SCRIPT_CHAM:       Cham. Since 2.16.3
 339  * @G_UNICODE_SCRIPT_OL_CHIKI:   Ol Chiki. Since 2.16.3
 340  * @G_UNICODE_SCRIPT_VAI:        Vai. Since 2.16.3
 341  * @G_UNICODE_SCRIPT_CARIAN:     Carian. Since 2.16.3
 342  * @G_UNICODE_SCRIPT_LYCIAN:     Lycian. Since 2.16.3
 343  * @G_UNICODE_SCRIPT_LYDIAN:     Lydian. Since 2.16.3
 344  * @G_UNICODE_SCRIPT_AVESTAN:    Avestan. Since 2.26
 345  * @G_UNICODE_SCRIPT_BAMUM:      Bamum. Since 2.26
 346  * @G_UNICODE_SCRIPT_EGYPTIAN_HIEROGLYPHS:
 347  *                               Egyptian Hieroglpyhs. Since 2.26
 348  * @G_UNICODE_SCRIPT_IMPERIAL_ARAMAIC:
 349  *                               Imperial Aramaic. Since 2.26
 350  * @G_UNICODE_SCRIPT_INSCRIPTIONAL_PAHLAVI:
 351  *                               Inscriptional Pahlavi. Since 2.26
 352  * @G_UNICODE_SCRIPT_INSCRIPTIONAL_PARTHIAN:
 353  *                               Inscriptional Parthian. Since 2.26
 354  * @G_UNICODE_SCRIPT_JAVANESE:   Javanese. Since 2.26
 355  * @G_UNICODE_SCRIPT_KAITHI:     Kaithi. Since 2.26
 356  * @G_UNICODE_SCRIPT_LISU:       Lisu. Since 2.26
 357  * @G_UNICODE_SCRIPT_MEETEI_MAYEK:
 358  *                               Meetei Mayek. Since 2.26
 359  * @G_UNICODE_SCRIPT_OLD_SOUTH_ARABIAN:
 360  *                               Old South Arabian. Since 2.26
 361  * @G_UNICODE_SCRIPT_OLD_TURKIC: Old Turkic. Since 2.28
 362  * @G_UNICODE_SCRIPT_SAMARITAN:  Samaritan. Since 2.26
 363  * @G_UNICODE_SCRIPT_TAI_THAM:   Tai Tham. Since 2.26
 364  * @G_UNICODE_SCRIPT_TAI_VIET:   Tai Viet. Since 2.26
 365  * @G_UNICODE_SCRIPT_BATAK:      Batak. Since 2.28
 366  * @G_UNICODE_SCRIPT_BRAHMI:     Brahmi. Since 2.28
 367  * @G_UNICODE_SCRIPT_MANDAIC:    Mandaic. Since 2.28
 368  * @G_UNICODE_SCRIPT_CHAKMA:               Chakma. Since: 2.32
 369  * @G_UNICODE_SCRIPT_MEROITIC_CURSIVE:     Meroitic Cursive. Since: 2.32
 370  * @G_UNICODE_SCRIPT_MEROITIC_HIEROGLYPHS: Meroitic Hieroglyphs. Since: 2.32
 371  * @G_UNICODE_SCRIPT_MIAO:                 Miao. Since: 2.32
 372  * @G_UNICODE_SCRIPT_SHARADA:              Sharada. Since: 2.32
 373  * @G_UNICODE_SCRIPT_SORA_SOMPENG:         Sora Sompeng. Since: 2.32
 374  * @G_UNICODE_SCRIPT_TAKRI:                Takri. Since: 2.32
 375  *
 376  * The #GUnicodeScript enumeration identifies different writing
 377  * systems. The values correspond to the names as defined in the
 378  * Unicode standard. The enumeration has been added in GLib 2.14,
 379  * and is interchangeable with #PangoScript.
 380  *
 381  * Note that new types may be added in the future. Applications
 382  * should be ready to handle unknown values.
 383  * See <ulink
 384  * url="http://www.unicode.org/reports/tr24/">Unicode Standard Annex
 385  * #24: Script names</ulink>.
 386  */
 387 typedef enum
 388 {                         /* ISO 15924 code */
 389   G_UNICODE_SCRIPT_INVALID_CODE = -1,
 390   G_UNICODE_SCRIPT_COMMON       = 0,   /* Zyyy */
 391   G_UNICODE_SCRIPT_INHERITED,          /* Zinh (Qaai) */
 392   G_UNICODE_SCRIPT_ARABIC,             /* Arab */
 393   G_UNICODE_SCRIPT_ARMENIAN,           /* Armn */
 394   G_UNICODE_SCRIPT_BENGALI,            /* Beng */
 395   G_UNICODE_SCRIPT_BOPOMOFO,           /* Bopo */
 396   G_UNICODE_SCRIPT_CHEROKEE,           /* Cher */
 397   G_UNICODE_SCRIPT_COPTIC,             /* Copt (Qaac) */
 398   G_UNICODE_SCRIPT_CYRILLIC,           /* Cyrl (Cyrs) */
 399   G_UNICODE_SCRIPT_DESERET,            /* Dsrt */
 400   G_UNICODE_SCRIPT_DEVANAGARI,         /* Deva */
 401   G_UNICODE_SCRIPT_ETHIOPIC,           /* Ethi */
 402   G_UNICODE_SCRIPT_GEORGIAN,           /* Geor (Geon, Geoa) */
 403   G_UNICODE_SCRIPT_GOTHIC,             /* Goth */
 404   G_UNICODE_SCRIPT_GREEK,              /* Grek */
 405   G_UNICODE_SCRIPT_GUJARATI,           /* Gujr */
 406   G_UNICODE_SCRIPT_GURMUKHI,           /* Guru */
 407   G_UNICODE_SCRIPT_HAN,                /* Hani */
 408   G_UNICODE_SCRIPT_HANGUL,             /* Hang */
 409   G_UNICODE_SCRIPT_HEBREW,             /* Hebr */
 410   G_UNICODE_SCRIPT_HIRAGANA,           /* Hira */
 411   G_UNICODE_SCRIPT_KANNADA,            /* Knda */
 412   G_UNICODE_SCRIPT_KATAKANA,           /* Kana */
 413   G_UNICODE_SCRIPT_KHMER,              /* Khmr */
 414   G_UNICODE_SCRIPT_LAO,                /* Laoo */
 415   G_UNICODE_SCRIPT_LATIN,              /* Latn (Latf, Latg) */
 416   G_UNICODE_SCRIPT_MALAYALAM,          /* Mlym */
 417   G_UNICODE_SCRIPT_MONGOLIAN,          /* Mong */
 418   G_UNICODE_SCRIPT_MYANMAR,            /* Mymr */
 419   G_UNICODE_SCRIPT_OGHAM,              /* Ogam */
 420   G_UNICODE_SCRIPT_OLD_ITALIC,         /* Ital */
 421   G_UNICODE_SCRIPT_ORIYA,              /* Orya */
 422   G_UNICODE_SCRIPT_RUNIC,              /* Runr */
 423   G_UNICODE_SCRIPT_SINHALA,            /* Sinh */
 424   G_UNICODE_SCRIPT_SYRIAC,             /* Syrc (Syrj, Syrn, Syre) */
 425   G_UNICODE_SCRIPT_TAMIL,              /* Taml */
 426   G_UNICODE_SCRIPT_TELUGU,             /* Telu */
 427   G_UNICODE_SCRIPT_THAANA,             /* Thaa */
 428   G_UNICODE_SCRIPT_THAI,               /* Thai */
 429   G_UNICODE_SCRIPT_TIBETAN,            /* Tibt */
 430   G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL, /* Cans */
 431   G_UNICODE_SCRIPT_YI,                 /* Yiii */
 432   G_UNICODE_SCRIPT_TAGALOG,            /* Tglg */
 433   G_UNICODE_SCRIPT_HANUNOO,            /* Hano */
 434   G_UNICODE_SCRIPT_BUHID,              /* Buhd */
 435   G_UNICODE_SCRIPT_TAGBANWA,           /* Tagb */
 436
 437   /* Unicode-4.0 additions */
 438   G_UNICODE_SCRIPT_BRAILLE,            /* Brai */
 439   G_UNICODE_SCRIPT_CYPRIOT,            /* Cprt */
 440   G_UNICODE_SCRIPT_LIMBU,              /* Limb */
 441   G_UNICODE_SCRIPT_OSMANYA,            /* Osma */
 442   G_UNICODE_SCRIPT_SHAVIAN,            /* Shaw */
 443   G_UNICODE_SCRIPT_LINEAR_B,           /* Linb */
 444   G_UNICODE_SCRIPT_TAI_LE,             /* Tale */
 445   G_UNICODE_SCRIPT_UGARITIC,           /* Ugar */
 446
 447   /* Unicode-4.1 additions */
 448   G_UNICODE_SCRIPT_NEW_TAI_LUE,        /* Talu */
 449   G_UNICODE_SCRIPT_BUGINESE,           /* Bugi */
 450   G_UNICODE_SCRIPT_GLAGOLITIC,         /* Glag */
 451   G_UNICODE_SCRIPT_TIFINAGH,           /* Tfng */
 452   G_UNICODE_SCRIPT_SYLOTI_NAGRI,       /* Sylo */
 453   G_UNICODE_SCRIPT_OLD_PERSIAN,        /* Xpeo */
 454   G_UNICODE_SCRIPT_KHAROSHTHI,         /* Khar */
 455
 456   /* Unicode-5.0 additions */
 457   G_UNICODE_SCRIPT_UNKNOWN,            /* Zzzz */
 458   G_UNICODE_SCRIPT_BALINESE,           /* Bali */
 459   G_UNICODE_SCRIPT_CUNEIFORM,          /* Xsux */
 460   G_UNICODE_SCRIPT_PHOENICIAN,         /* Phnx */
 461   G_UNICODE_SCRIPT_PHAGS_PA,           /* Phag */
 462   G_UNICODE_SCRIPT_NKO,                /* Nkoo */
 463
 464   /* Unicode-5.1 additions */
 465   G_UNICODE_SCRIPT_KAYAH_LI,           /* Kali */
 466   G_UNICODE_SCRIPT_LEPCHA,             /* Lepc */
 467   G_UNICODE_SCRIPT_REJANG,             /* Rjng */
 468   G_UNICODE_SCRIPT_SUNDANESE,          /* Sund */
 469   G_UNICODE_SCRIPT_SAURASHTRA,         /* Saur */
 470   G_UNICODE_SCRIPT_CHAM,               /* Cham */
 471   G_UNICODE_SCRIPT_OL_CHIKI,           /* Olck */
 472   G_UNICODE_SCRIPT_VAI,                /* Vaii */
 473   G_UNICODE_SCRIPT_CARIAN,             /* Cari */
 474   G_UNICODE_SCRIPT_LYCIAN,             /* Lyci */
 475   G_UNICODE_SCRIPT_LYDIAN,             /* Lydi */
 476
 477   /* Unicode-5.2 additions */
 478   G_UNICODE_SCRIPT_AVESTAN,                /* Avst */
 479   G_UNICODE_SCRIPT_BAMUM,                  /* Bamu */
 480   G_UNICODE_SCRIPT_EGYPTIAN_HIEROGLYPHS,   /* Egyp */
 481   G_UNICODE_SCRIPT_IMPERIAL_ARAMAIC,       /* Armi */
 482   G_UNICODE_SCRIPT_INSCRIPTIONAL_PAHLAVI,  /* Phli */
 483   G_UNICODE_SCRIPT_INSCRIPTIONAL_PARTHIAN, /* Prti */
 484   G_UNICODE_SCRIPT_JAVANESE,               /* Java */
 485   G_UNICODE_SCRIPT_KAITHI,                 /* Kthi */
 486   G_UNICODE_SCRIPT_LISU,                   /* Lisu */
 487   G_UNICODE_SCRIPT_MEETEI_MAYEK,           /* Mtei */
 488   G_UNICODE_SCRIPT_OLD_SOUTH_ARABIAN,      /* Sarb */
 489   G_UNICODE_SCRIPT_OLD_TURKIC,             /* Orkh */
 490   G_UNICODE_SCRIPT_SAMARITAN,              /* Samr */
 491   G_UNICODE_SCRIPT_TAI_THAM,               /* Lana */
 492   G_UNICODE_SCRIPT_TAI_VIET,               /* Tavt */
 493
 494   /* Unicode-6.0 additions */
 495   G_UNICODE_SCRIPT_BATAK,                  /* Batk */
 496   G_UNICODE_SCRIPT_BRAHMI,                 /* Brah */
 497   G_UNICODE_SCRIPT_MANDAIC,                /* Mand */
 498
 499   /* Unicode-6.1 additions */
 500   G_UNICODE_SCRIPT_CHAKMA,                 /* Cakm */
 501   G_UNICODE_SCRIPT_MEROITIC_CURSIVE,       /* Merc */
 502   G_UNICODE_SCRIPT_MEROITIC_HIEROGLYPHS,   /* Mero */
 503   G_UNICODE_SCRIPT_MIAO,                   /* Plrd */
 504   G_UNICODE_SCRIPT_SHARADA,                /* Shrd */
 505   G_UNICODE_SCRIPT_SORA_SOMPENG,           /* Sora */
 506   G_UNICODE_SCRIPT_TAKRI                   /* Takr */
 507 } GUnicodeScript;
 508
 509 guint32        g_unicode_script_to_iso15924   (GUnicodeScript script);
 510 GUnicodeScript g_unicode_script_from_iso15924 (guint32        iso15924);
 511
 512 /* These are all analogs of the <ctype.h> functions.
 513  */
 514 gboolean g_unichar_isalnum   (gunichar c) G_GNUC_CONST;
 515 gboolean g_unichar_isalpha   (gunichar c) G_GNUC_CONST;
 516 gboolean g_unichar_iscntrl   (gunichar c) G_GNUC_CONST;
 517 gboolean g_unichar_isdigit   (gunichar c) G_GNUC_CONST;
 518 gboolean g_unichar_isgraph   (gunichar c) G_GNUC_CONST;
 519 gboolean g_unichar_islower   (gunichar c) G_GNUC_CONST;
 520 gboolean g_unichar_isprint   (gunichar c) G_GNUC_CONST;
 521 gboolean g_unichar_ispunct   (gunichar c) G_GNUC_CONST;
 522 gboolean g_unichar_isspace   (gunichar c) G_GNUC_CONST;
 523 gboolean g_unichar_isupper   (gunichar c) G_GNUC_CONST;
 524 gboolean g_unichar_isxdigit  (gunichar c) G_GNUC_CONST;
 525 gboolean g_unichar_istitle   (gunichar c) G_GNUC_CONST;
 526 gboolean g_unichar_isdefined (gunichar c) G_GNUC_CONST;
 527 gboolean g_unichar_iswide    (gunichar c) G_GNUC_CONST;
 528 gboolean g_unichar_iswide_cjk(gunichar c) G_GNUC_CONST;
 529 gboolean g_unichar_iszerowidth(gunichar c) G_GNUC_CONST;
 530 gboolean g_unichar_ismark    (gunichar c) G_GNUC_CONST;
 531
 532 /* More <ctype.h> functions.  These convert between the three cases.
 533  * See the Unicode book to understand title case.  */
 534 gunichar g_unichar_toupper (gunichar c) G_GNUC_CONST;
 535 gunichar g_unichar_tolower (gunichar c) G_GNUC_CONST;
 536 gunichar g_unichar_totitle (gunichar c) G_GNUC_CONST;
 537
 538 /* If C is a digit (according to `g_unichar_isdigit'), then return its
 539    numeric value.  Otherwise return -1.  */
 540 gint g_unichar_digit_value (gunichar c) G_GNUC_CONST;
 541
 542 gint g_unichar_xdigit_value (gunichar c) G_GNUC_CONST;
 543
 544 /* Return the Unicode character type of a given character.  */
 545 GUnicodeType g_unichar_type (gunichar c) G_GNUC_CONST;
 546
 547 /* Return the line break property for a given character */
 548 GUnicodeBreakType g_unichar_break_type (gunichar c) G_GNUC_CONST;
 549
 550 /* Returns the combining class for a given character */
 551 gint g_unichar_combining_class (gunichar uc) G_GNUC_CONST;
 552
 553 gboolean g_unichar_get_mirror_char (gunichar ch,
 554                                     gunichar *mirrored_ch);
 555
 556 GUnicodeScript g_unichar_get_script (gunichar ch) G_GNUC_CONST;
 557
 558 /* Validate a Unicode character */
 559 gboolean g_unichar_validate (gunichar ch) G_GNUC_CONST;
 560
 561 /* Pairwise canonical compose/decompose */
 562 gboolean g_unichar_compose (gunichar  a,
 563                             gunichar  b,
 564                             gunichar *ch);
 565 gboolean g_unichar_decompose (gunichar  ch,
 566                               gunichar *a,
 567                               gunichar *b);
 568
 569 gsize g_unichar_fully_decompose (gunichar  ch,
 570                                  gboolean  compat,
 571                                  gunichar *result,
 572                                  gsize     result_len);
 573
 574 /**
 575  * G_UNICHAR_MAX_DECOMPOSITION_LENGTH:
 576  *
 577  * The maximum length (in codepoints) of a compatibility or canonical
 578  * decomposition of a single Unicode character.
 579  *
 580  * This is as defined by Unicode 6.1.
 581  *
 582  * Since: 2.32
 583  */
 584 #define G_UNICHAR_MAX_DECOMPOSITION_LENGTH 18 /* codepoints */
 585
 586 /* Compute canonical ordering of a string in-place.  This rearranges
 587    decomposed characters in the string according to their combining
 588    classes.  See the Unicode manual for more information.  */
 589 void g_unicode_canonical_ordering (gunichar *string,
 590                                    gsize     len);
 591
 592
 593 GLIB_DEPRECATED_IN_2_30
 594 gunichar *g_unicode_canonical_decomposition (gunichar  ch,
 595                                              gsize    *result_len) G_GNUC_MALLOC;
 596
 597 /* Array of skip-bytes-per-initial character.
 598  */
 599 GLIB_VAR const gchar * const g_utf8_skip;
 600
 601 /**
 602  * g_utf8_next_char:
 603  * @p: Pointer to the start of a valid UTF-8 character
 604  *
 605  * Skips to the next character in a UTF-8 string. The string must be
 606  * valid; this macro is as fast as possible, and has no error-checking.
 607  * You would use this macro to iterate over a string character by
 608  * character. The macro returns the start of the next UTF-8 character.
 609  * Before using this macro, use g_utf8_validate() to validate strings
 610  * that may contain invalid UTF-8.
 611  */
 612 #define g_utf8_next_char(p) (char *)((p) + g_utf8_skip[*(const guchar *)(p)])
 613
 614 gunichar g_utf8_get_char           (const gchar  *p) G_GNUC_PURE;
 615 gunichar g_utf8_get_char_validated (const  gchar *p,
 616                                     gssize        max_len) G_GNUC_PURE;
 617
 618 gchar*   g_utf8_offset_to_pointer (const gchar *str,
 619                                    glong        offset) G_GNUC_PURE;
 620 glong    g_utf8_pointer_to_offset (const gchar *str,
 621                                    const gchar *pos) G_GNUC_PURE;
 622 gchar*   g_utf8_prev_char         (const gchar *p) G_GNUC_PURE;
 623 gchar*   g_utf8_find_next_char    (const gchar *p,
 624                                    const gchar *end) G_GNUC_PURE;
 625 gchar*   g_utf8_find_prev_char    (const gchar *str,
 626                                    const gchar *p) G_GNUC_PURE;
 627
 628 glong    g_utf8_strlen            (const gchar *p,
 629                                    gssize       max) G_GNUC_PURE;
 630
 631 GLIB_AVAILABLE_IN_2_30
 632 gchar   *g_utf8_substring         (const gchar *str,
 633                                    glong        start_pos,
 634                                    glong        end_pos) G_GNUC_MALLOC;
 635
 636 gchar   *g_utf8_strncpy           (gchar       *dest,
 637                                    const gchar *src,
 638                                    gsize        n);
 639
 640 /* Find the UTF-8 character corresponding to ch, in string p. These
 641    functions are equivalants to strchr and strrchr */
 642 gchar* g_utf8_strchr  (const gchar *p,
 643                        gssize       len,
 644                        gunichar     c);
 645 gchar* g_utf8_strrchr (const gchar *p,
 646                        gssize       len,
 647                        gunichar     c);
 648 gchar* g_utf8_strreverse (const gchar *str,
 649                           gssize len);
 650
 651 gunichar2 *g_utf8_to_utf16     (const gchar      *str,
 652                                 glong             len,
 653                                 glong            *items_read,
 654                                 glong            *items_written,
 655                                 GError          **error) G_GNUC_MALLOC;
 656 gunichar * g_utf8_to_ucs4      (const gchar      *str,
 657                                 glong             len,
 658                                 glong            *items_read,
 659                                 glong            *items_written,
 660                                 GError          **error) G_GNUC_MALLOC;
 661 gunichar * g_utf8_to_ucs4_fast (const gchar      *str,
 662                                 glong             len,
 663                                 glong            *items_written) G_GNUC_MALLOC;
 664 gunichar * g_utf16_to_ucs4     (const gunichar2  *str,
 665                                 glong             len,
 666                                 glong            *items_read,
 667                                 glong            *items_written,
 668                                 GError          **error) G_GNUC_MALLOC;
 669 gchar*     g_utf16_to_utf8     (const gunichar2  *str,
 670                                 glong             len,
 671                                 glong            *items_read,
 672                                 glong            *items_written,
 673                                 GError          **error) G_GNUC_MALLOC;
 674 gunichar2 *g_ucs4_to_utf16     (const gunichar   *str,
 675                                 glong             len,
 676                                 glong            *items_read,
 677                                 glong            *items_written,
 678                                 GError          **error) G_GNUC_MALLOC;
 679 gchar*     g_ucs4_to_utf8      (const gunichar   *str,
 680                                 glong             len,
 681                                 glong            *items_read,
 682                                 glong            *items_written,
 683                                 GError          **error) G_GNUC_MALLOC;
 684
 685 gint      g_unichar_to_utf8 (gunichar    c,
 686                              gchar      *outbuf);
 687
 688 gboolean g_utf8_validate (const gchar  *str,
 689                           gssize        max_len,
 690                           const gchar **end);
 691
 692 gchar *g_utf8_strup   (const gchar *str,
 693                        gssize       len) G_GNUC_MALLOC;
 694 gchar *g_utf8_strdown (const gchar *str,
 695                        gssize       len) G_GNUC_MALLOC;
 696 gchar *g_utf8_casefold (const gchar *str,
 697                         gssize       len) G_GNUC_MALLOC;
 698
 699 /**
 700  * GNormalizeMode:
 701  * @G_NORMALIZE_DEFAULT: standardize differences that do not affect the
 702  *     text content, such as the above-mentioned accent representation
 703  * @G_NORMALIZE_NFD: another name for %G_NORMALIZE_DEFAULT
 704  * @G_NORMALIZE_DEFAULT_COMPOSE: like %G_NORMALIZE_DEFAULT, but with
 705  *     composed forms rather than a maximally decomposed form
 706  * @G_NORMALIZE_NFC: another name for %G_NORMALIZE_DEFAULT_COMPOSE
 707  * @G_NORMALIZE_ALL: beyond %G_NORMALIZE_DEFAULT also standardize the
 708  *     "compatibility" characters in Unicode, such as SUPERSCRIPT THREE
 709  *     to the standard forms (in this case DIGIT THREE). Formatting
 710  *     information may be lost but for most text operations such
 711  *     characters should be considered the same
 712  * @G_NORMALIZE_NFKD: another name for %G_NORMALIZE_ALL
 713  * @G_NORMALIZE_ALL_COMPOSE: like %G_NORMALIZE_ALL, but with composed
 714  *     forms rather than a maximally decomposed form
 715  * @G_NORMALIZE_NFKC: another name for %G_NORMALIZE_ALL_COMPOSE
 716  *
 717  * Defines how a Unicode string is transformed in a canonical
 718  * form, standardizing such issues as whether a character with
 719  * an accent is represented as a base character and combining
 720  * accent or as a single precomposed character. Unicode strings
 721  * should generally be normalized before comparing them.
 722  */
 723 typedef enum {
 724   G_NORMALIZE_DEFAULT,
 725   G_NORMALIZE_NFD = G_NORMALIZE_DEFAULT,
 726   G_NORMALIZE_DEFAULT_COMPOSE,
 727   G_NORMALIZE_NFC = G_NORMALIZE_DEFAULT_COMPOSE,
 728   G_NORMALIZE_ALL,
 729   G_NORMALIZE_NFKD = G_NORMALIZE_ALL,
 730   G_NORMALIZE_ALL_COMPOSE,
 731   G_NORMALIZE_NFKC = G_NORMALIZE_ALL_COMPOSE
 732 } GNormalizeMode;
 733
 734 gchar *g_utf8_normalize (const gchar   *str,
 735                          gssize         len,
 736                          GNormalizeMode mode) G_GNUC_MALLOC;
 737
 738 gint   g_utf8_collate     (const gchar *str1,
 739                            const gchar *str2) G_GNUC_PURE;
 740 gchar *g_utf8_collate_key (const gchar *str,
 741                            gssize       len) G_GNUC_MALLOC;
 742 gchar *g_utf8_collate_key_for_filename (const gchar *str,
 743                                         gssize       len) G_GNUC_MALLOC;
 744
 745
 746 /* private */
 747
 748 gchar *_g_utf8_make_valid (const gchar *name);
 749
 750 G_END_DECLS
 751
 752 #endif /* __G_UNICODE_H__ */