- Generated by
1.10.0
|
Github User Fetcher 1.0.0
C Application with Server and GUI
|
Go to the source code of this file.
Macros | |
| #define | G_UNICODE_COMBINING_MARK G_UNICODE_SPACING_MARK GLIB_DEPRECATED_MACRO_IN_2_30_FOR(G_UNICODE_SPACING_MARK) |
| #define | G_UNICHAR_MAX_DECOMPOSITION_LENGTH 18 /* codepoints */ |
| #define | g_utf8_next_char(p) ((p) + g_utf8_skip[*(const guchar *)(p)]) |
Typedefs | |
| typedef guint16 | gunichar2 |
Variables | |
| G_BEGIN_DECLS typedef guint32 | gunichar |
| GLIB_VAR const gchar *const | g_utf8_skip |
| #define G_UNICHAR_MAX_DECOMPOSITION_LENGTH 18 /* codepoints */ |
G_UNICHAR_MAX_DECOMPOSITION_LENGTH:
The maximum length (in codepoints) of a compatibility or canonical decomposition of a single Unicode character.
This is as defined by Unicode 6.1.
Since: 2.32
Definition at line 775 of file gunicode.h.
| #define G_UNICODE_COMBINING_MARK G_UNICODE_SPACING_MARK GLIB_DEPRECATED_MACRO_IN_2_30_FOR(G_UNICODE_SPACING_MARK) |
G_UNICODE_COMBINING_MARK:
Older name for G_UNICODE_SPACING_MARK.
Deprecated: 2.30: Use G_UNICODE_SPACING_MARK.
Definition at line 159 of file gunicode.h.
| #define g_utf8_next_char | ( | p | ) | ((p) + g_utf8_skip[*(const guchar *)(p)]) |
g_utf8_next_char: : Pointer to the start of a valid UTF-8 character
Skips to the next character in a UTF-8 string.
The string must be valid; this macro is as fast as possible, and has no error-checking.
You would use this macro to iterate over a string character by character.
The macro returns the start of the next UTF-8 character.
Before using this macro, use g_utf8_validate() to validate strings that may contain invalid UTF-8.
Definition at line 809 of file gunicode.h.
gunichar2:
A type which can hold any UTF-16 code point<footnote id="utf16_surrogate_pairs">UTF-16 also has so called <firstterm>surrogate pairs</firstterm> to encode characters beyond the BMP as pairs of 16bit numbers. Surrogate pairs cannot be stored in a single gunichar2 field, but all GLib functions accepting gunichar2 arrays will correctly interpret surrogate pairs.</footnote>.
To print/scan values of this type to/from text you need to convert to/from UTF-8, using g_utf16_to_utf8()/g_utf8_to_utf16().
To print/scan values of this type as integer, use G_GINT16_MODIFIER and/or G_GUINT16_FORMAT.
Definition at line 79 of file gunicode.h.
| enum GNormalizeMode |
GNormalizeMode: @G_NORMALIZE_DEFAULT: standardize differences that do not affect the text content, such as the above-mentioned accent representation @G_NORMALIZE_NFD: another name for G_NORMALIZE_DEFAULT @G_NORMALIZE_DEFAULT_COMPOSE: like G_NORMALIZE_DEFAULT, but with composed forms rather than a maximally decomposed form @G_NORMALIZE_NFC: another name for G_NORMALIZE_DEFAULT_COMPOSE @G_NORMALIZE_ALL: beyond G_NORMALIZE_DEFAULT also standardize the "compatibility" characters in Unicode, such as SUPERSCRIPT THREE to the standard forms (in this case DIGIT THREE). Formatting information may be lost but for most text operations such characters should be considered the same @G_NORMALIZE_NFKD: another name for G_NORMALIZE_ALL @G_NORMALIZE_ALL_COMPOSE: like G_NORMALIZE_ALL, but with composed forms rather than a maximally decomposed form @G_NORMALIZE_NFKC: another name for G_NORMALIZE_ALL_COMPOSE
Defines how a Unicode string is transformed in a canonical form, standardizing such issues as whether a character with an accent is represented as a base character and combining accent or as a single precomposed character. Unicode strings should generally be normalized before comparing them.
| Enumerator | |
|---|---|
| G_NORMALIZE_DEFAULT | |
| G_NORMALIZE_NFD | |
| G_NORMALIZE_DEFAULT_COMPOSE | |
| G_NORMALIZE_NFC | |
| G_NORMALIZE_ALL | |
| G_NORMALIZE_NFKD | |
| G_NORMALIZE_ALL_COMPOSE | |
| G_NORMALIZE_NFKC | |
Definition at line 952 of file gunicode.h.
| enum GUnicodeBreakType |
GUnicodeBreakType: @G_UNICODE_BREAK_MANDATORY: Mandatory Break (BK) @G_UNICODE_BREAK_CARRIAGE_RETURN: Carriage Return (CR) @G_UNICODE_BREAK_LINE_FEED: Line Feed (LF) @G_UNICODE_BREAK_COMBINING_MARK: Attached Characters and Combining Marks (CM) @G_UNICODE_BREAK_SURROGATE: Surrogates (SG) @G_UNICODE_BREAK_ZERO_WIDTH_SPACE: Zero Width Space (ZW) @G_UNICODE_BREAK_INSEPARABLE: Inseparable (IN) @G_UNICODE_BREAK_NON_BREAKING_GLUE: Non-breaking ("Glue") (GL) @G_UNICODE_BREAK_CONTINGENT: Contingent Break Opportunity (CB) @G_UNICODE_BREAK_SPACE: Space (SP) @G_UNICODE_BREAK_AFTER: Break Opportunity After (BA) @G_UNICODE_BREAK_BEFORE: Break Opportunity Before (BB) @G_UNICODE_BREAK_BEFORE_AND_AFTER: Break Opportunity Before and After (B2) @G_UNICODE_BREAK_HYPHEN: Hyphen (HY) @G_UNICODE_BREAK_NON_STARTER: Nonstarter (NS) @G_UNICODE_BREAK_OPEN_PUNCTUATION: Opening Punctuation (OP) @G_UNICODE_BREAK_CLOSE_PUNCTUATION: Closing Punctuation (CL) @G_UNICODE_BREAK_QUOTATION: Ambiguous Quotation (QU) @G_UNICODE_BREAK_EXCLAMATION: Exclamation/Interrogation (EX) @G_UNICODE_BREAK_IDEOGRAPHIC: Ideographic (ID) @G_UNICODE_BREAK_NUMERIC: Numeric (NU) @G_UNICODE_BREAK_INFIX_SEPARATOR: Infix Separator (Numeric) (IS) @G_UNICODE_BREAK_SYMBOL: Symbols Allowing Break After (SY) @G_UNICODE_BREAK_ALPHABETIC: Ordinary Alphabetic and Symbol Characters (AL) @G_UNICODE_BREAK_PREFIX: Prefix (Numeric) (PR) @G_UNICODE_BREAK_POSTFIX: Postfix (Numeric) (PO) @G_UNICODE_BREAK_COMPLEX_CONTEXT: Complex Content Dependent (South East Asian) (SA) @G_UNICODE_BREAK_AMBIGUOUS: Ambiguous (Alphabetic or Ideographic) (AI) @G_UNICODE_BREAK_UNKNOWN: Unknown (XX) @G_UNICODE_BREAK_NEXT_LINE: Next Line (NL) @G_UNICODE_BREAK_WORD_JOINER: Word Joiner (WJ) @G_UNICODE_BREAK_HANGUL_L_JAMO: Hangul L Jamo (JL) @G_UNICODE_BREAK_HANGUL_V_JAMO: Hangul V Jamo (JV) @G_UNICODE_BREAK_HANGUL_T_JAMO: Hangul T Jamo (JT) @G_UNICODE_BREAK_HANGUL_LV_SYLLABLE: Hangul LV Syllable (H2) @G_UNICODE_BREAK_HANGUL_LVT_SYLLABLE: Hangul LVT Syllable (H3) @G_UNICODE_BREAK_CLOSE_PARANTHESIS: Closing Parenthesis (CP). Since 2.28. Deprecated: 2.70: Use G_UNICODE_BREAK_CLOSE_PARENTHESIS instead. @G_UNICODE_BREAK_CLOSE_PARENTHESIS: Closing Parenthesis (CP). Since 2.70 @G_UNICODE_BREAK_CONDITIONAL_JAPANESE_STARTER: Conditional Japanese Starter (CJ). Since: 2.32 @G_UNICODE_BREAK_HEBREW_LETTER: Hebrew Letter (HL). Since: 2.32 @G_UNICODE_BREAK_REGIONAL_INDICATOR: Regional Indicator (RI). Since: 2.36 @G_UNICODE_BREAK_EMOJI_BASE: Emoji Base (EB). Since: 2.50 @G_UNICODE_BREAK_EMOJI_MODIFIER: Emoji Modifier (EM). Since: 2.50 @G_UNICODE_BREAK_ZERO_WIDTH_JOINER: Zero Width Joiner (ZWJ). Since: 2.50 @G_UNICODE_BREAK_AKSARA: Aksara (AK). Since: 2.80 @G_UNICODE_BREAK_AKSARA_PRE_BASE (AP). Since: 2.80 @G_UNICODE_BREAK_AKSARA_START (AS). Since: 2.80 @G_UNICODE_BREAK_VIRAMA_FINAL (VF). Since: 2.80 @G_UNICODE_BREAK_VIRAMA (VI). Since: 2.80
These are the possible line break classifications.
Since new Unicode versions may add new types here, applications should be ready to handle unknown values. They may be regarded as G_UNICODE_BREAK_UNKNOWN.
See Unicode Line Breaking Algorithm.
Definition at line 220 of file gunicode.h.
| enum GUnicodeScript |
GUnicodeScript: @G_UNICODE_SCRIPT_INVALID_CODE: a value never returned from g_unichar_get_script() @G_UNICODE_SCRIPT_COMMON: a character used by multiple different scripts @G_UNICODE_SCRIPT_INHERITED: a mark glyph that takes its script from the base glyph to which it is attached @G_UNICODE_SCRIPT_ARABIC: Arabic @G_UNICODE_SCRIPT_ARMENIAN: Armenian @G_UNICODE_SCRIPT_BENGALI: Bengali @G_UNICODE_SCRIPT_BOPOMOFO: Bopomofo @G_UNICODE_SCRIPT_CHEROKEE: Cherokee @G_UNICODE_SCRIPT_COPTIC: Coptic @G_UNICODE_SCRIPT_CYRILLIC: Cyrillic @G_UNICODE_SCRIPT_DESERET: Deseret @G_UNICODE_SCRIPT_DEVANAGARI: Devanagari @G_UNICODE_SCRIPT_ETHIOPIC: Ethiopic @G_UNICODE_SCRIPT_GEORGIAN: Georgian @G_UNICODE_SCRIPT_GOTHIC: Gothic @G_UNICODE_SCRIPT_GREEK: Greek @G_UNICODE_SCRIPT_GUJARATI: Gujarati @G_UNICODE_SCRIPT_GURMUKHI: Gurmukhi @G_UNICODE_SCRIPT_HAN: Han @G_UNICODE_SCRIPT_HANGUL: Hangul @G_UNICODE_SCRIPT_HEBREW: Hebrew @G_UNICODE_SCRIPT_HIRAGANA: Hiragana @G_UNICODE_SCRIPT_KANNADA: Kannada @G_UNICODE_SCRIPT_KATAKANA: Katakana @G_UNICODE_SCRIPT_KHMER: Khmer @G_UNICODE_SCRIPT_LAO: Lao @G_UNICODE_SCRIPT_LATIN: Latin @G_UNICODE_SCRIPT_MALAYALAM: Malayalam @G_UNICODE_SCRIPT_MONGOLIAN: Mongolian @G_UNICODE_SCRIPT_MYANMAR: Myanmar @G_UNICODE_SCRIPT_OGHAM: Ogham @G_UNICODE_SCRIPT_OLD_ITALIC: Old Italic @G_UNICODE_SCRIPT_ORIYA: Oriya @G_UNICODE_SCRIPT_RUNIC: Runic @G_UNICODE_SCRIPT_SINHALA: Sinhala @G_UNICODE_SCRIPT_SYRIAC: Syriac @G_UNICODE_SCRIPT_TAMIL: Tamil @G_UNICODE_SCRIPT_TELUGU: Telugu @G_UNICODE_SCRIPT_THAANA: Thaana @G_UNICODE_SCRIPT_THAI: Thai @G_UNICODE_SCRIPT_TIBETAN: Tibetan @G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL: Canadian Aboriginal @G_UNICODE_SCRIPT_YI: Yi @G_UNICODE_SCRIPT_TAGALOG: Tagalog @G_UNICODE_SCRIPT_HANUNOO: Hanunoo @G_UNICODE_SCRIPT_BUHID: Buhid @G_UNICODE_SCRIPT_TAGBANWA: Tagbanwa @G_UNICODE_SCRIPT_BRAILLE: Braille @G_UNICODE_SCRIPT_CYPRIOT: Cypriot @G_UNICODE_SCRIPT_LIMBU: Limbu @G_UNICODE_SCRIPT_OSMANYA: Osmanya @G_UNICODE_SCRIPT_SHAVIAN: Shavian @G_UNICODE_SCRIPT_LINEAR_B: Linear B @G_UNICODE_SCRIPT_TAI_LE: Tai Le @G_UNICODE_SCRIPT_UGARITIC: Ugaritic @G_UNICODE_SCRIPT_NEW_TAI_LUE: New Tai Lue @G_UNICODE_SCRIPT_BUGINESE: Buginese @G_UNICODE_SCRIPT_GLAGOLITIC: Glagolitic @G_UNICODE_SCRIPT_TIFINAGH: Tifinagh @G_UNICODE_SCRIPT_SYLOTI_NAGRI: Syloti Nagri @G_UNICODE_SCRIPT_OLD_PERSIAN: Old Persian @G_UNICODE_SCRIPT_KHAROSHTHI: Kharoshthi @G_UNICODE_SCRIPT_UNKNOWN: an unassigned code point @G_UNICODE_SCRIPT_BALINESE: Balinese @G_UNICODE_SCRIPT_CUNEIFORM: Cuneiform @G_UNICODE_SCRIPT_PHOENICIAN: Phoenician @G_UNICODE_SCRIPT_PHAGS_PA: Phags-pa @G_UNICODE_SCRIPT_NKO: N'Ko @G_UNICODE_SCRIPT_KAYAH_LI: Kayah Li. Since 2.16.3 @G_UNICODE_SCRIPT_LEPCHA: Lepcha. Since 2.16.3 @G_UNICODE_SCRIPT_REJANG: Rejang. Since 2.16.3 @G_UNICODE_SCRIPT_SUNDANESE: Sundanese. Since 2.16.3 @G_UNICODE_SCRIPT_SAURASHTRA: Saurashtra. Since 2.16.3 @G_UNICODE_SCRIPT_CHAM: Cham. Since 2.16.3 @G_UNICODE_SCRIPT_OL_CHIKI: Ol Chiki. Since 2.16.3 @G_UNICODE_SCRIPT_VAI: Vai. Since 2.16.3 @G_UNICODE_SCRIPT_CARIAN: Carian. Since 2.16.3 @G_UNICODE_SCRIPT_LYCIAN: Lycian. Since 2.16.3 @G_UNICODE_SCRIPT_LYDIAN: Lydian. Since 2.16.3 @G_UNICODE_SCRIPT_AVESTAN: Avestan. Since 2.26 @G_UNICODE_SCRIPT_BAMUM: Bamum. Since 2.26 @G_UNICODE_SCRIPT_EGYPTIAN_HIEROGLYPHS: Egyptian Hieroglpyhs. Since 2.26 @G_UNICODE_SCRIPT_IMPERIAL_ARAMAIC: Imperial Aramaic. Since 2.26 @G_UNICODE_SCRIPT_INSCRIPTIONAL_PAHLAVI: Inscriptional Pahlavi. Since 2.26 @G_UNICODE_SCRIPT_INSCRIPTIONAL_PARTHIAN: Inscriptional Parthian. Since 2.26 @G_UNICODE_SCRIPT_JAVANESE: Javanese. Since 2.26 @G_UNICODE_SCRIPT_KAITHI: Kaithi. Since 2.26 @G_UNICODE_SCRIPT_LISU: Lisu. Since 2.26 @G_UNICODE_SCRIPT_MEETEI_MAYEK: Meetei Mayek. Since 2.26 @G_UNICODE_SCRIPT_OLD_SOUTH_ARABIAN: Old South Arabian. Since 2.26 @G_UNICODE_SCRIPT_OLD_TURKIC: Old Turkic. Since 2.28 @G_UNICODE_SCRIPT_SAMARITAN: Samaritan. Since 2.26 @G_UNICODE_SCRIPT_TAI_THAM: Tai Tham. Since 2.26 @G_UNICODE_SCRIPT_TAI_VIET: Tai Viet. Since 2.26 @G_UNICODE_SCRIPT_BATAK: Batak. Since 2.28 @G_UNICODE_SCRIPT_BRAHMI: Brahmi. Since 2.28 @G_UNICODE_SCRIPT_MANDAIC: Mandaic. Since 2.28 @G_UNICODE_SCRIPT_CHAKMA: Chakma. Since: 2.32 @G_UNICODE_SCRIPT_MEROITIC_CURSIVE: Meroitic Cursive. Since: 2.32 @G_UNICODE_SCRIPT_MEROITIC_HIEROGLYPHS: Meroitic Hieroglyphs. Since: 2.32 @G_UNICODE_SCRIPT_MIAO: Miao. Since: 2.32 @G_UNICODE_SCRIPT_SHARADA: Sharada. Since: 2.32 @G_UNICODE_SCRIPT_SORA_SOMPENG: Sora Sompeng. Since: 2.32 @G_UNICODE_SCRIPT_TAKRI: Takri. Since: 2.32 @G_UNICODE_SCRIPT_BASSA_VAH: Bassa. Since: 2.42 @G_UNICODE_SCRIPT_CAUCASIAN_ALBANIAN: Caucasian Albanian. Since: 2.42 @G_UNICODE_SCRIPT_DUPLOYAN: Duployan. Since: 2.42 @G_UNICODE_SCRIPT_ELBASAN: Elbasan. Since: 2.42 @G_UNICODE_SCRIPT_GRANTHA: Grantha. Since: 2.42 @G_UNICODE_SCRIPT_KHOJKI: Kjohki. Since: 2.42 @G_UNICODE_SCRIPT_KHUDAWADI: Khudawadi, Sindhi. Since: 2.42 @G_UNICODE_SCRIPT_LINEAR_A: Linear A. Since: 2.42 @G_UNICODE_SCRIPT_MAHAJANI: Mahajani. Since: 2.42 @G_UNICODE_SCRIPT_MANICHAEAN: Manichaean. Since: 2.42 @G_UNICODE_SCRIPT_MENDE_KIKAKUI: Mende Kikakui. Since: 2.42 @G_UNICODE_SCRIPT_MODI: Modi. Since: 2.42 @G_UNICODE_SCRIPT_MRO: Mro. Since: 2.42 @G_UNICODE_SCRIPT_NABATAEAN: Nabataean. Since: 2.42 @G_UNICODE_SCRIPT_OLD_NORTH_ARABIAN: Old North Arabian. Since: 2.42 @G_UNICODE_SCRIPT_OLD_PERMIC: Old Permic. Since: 2.42 @G_UNICODE_SCRIPT_PAHAWH_HMONG: Pahawh Hmong. Since: 2.42 @G_UNICODE_SCRIPT_PALMYRENE: Palmyrene. Since: 2.42 @G_UNICODE_SCRIPT_PAU_CIN_HAU: Pau Cin Hau. Since: 2.42 @G_UNICODE_SCRIPT_PSALTER_PAHLAVI: Psalter Pahlavi. Since: 2.42 @G_UNICODE_SCRIPT_SIDDHAM: Siddham. Since: 2.42 @G_UNICODE_SCRIPT_TIRHUTA: Tirhuta. Since: 2.42 @G_UNICODE_SCRIPT_WARANG_CITI: Warang Citi. Since: 2.42 @G_UNICODE_SCRIPT_AHOM: Ahom. Since: 2.48 @G_UNICODE_SCRIPT_ANATOLIAN_HIEROGLYPHS: Anatolian Hieroglyphs. Since: 2.48 @G_UNICODE_SCRIPT_HATRAN: Hatran. Since: 2.48 @G_UNICODE_SCRIPT_MULTANI: Multani. Since: 2.48 @G_UNICODE_SCRIPT_OLD_HUNGARIAN: Old Hungarian. Since: 2.48 @G_UNICODE_SCRIPT_SIGNWRITING: Signwriting. Since: 2.48 @G_UNICODE_SCRIPT_ADLAM: Adlam. Since: 2.50 @G_UNICODE_SCRIPT_BHAIKSUKI: Bhaiksuki. Since: 2.50 @G_UNICODE_SCRIPT_MARCHEN: Marchen. Since: 2.50 @G_UNICODE_SCRIPT_NEWA: Newa. Since: 2.50 @G_UNICODE_SCRIPT_OSAGE: Osage. Since: 2.50 @G_UNICODE_SCRIPT_TANGUT: Tangut. Since: 2.50 @G_UNICODE_SCRIPT_MASARAM_GONDI: Masaram Gondi. Since: 2.54 @G_UNICODE_SCRIPT_NUSHU: Nushu. Since: 2.54 @G_UNICODE_SCRIPT_SOYOMBO: Soyombo. Since: 2.54 @G_UNICODE_SCRIPT_ZANABAZAR_SQUARE: Zanabazar Square. Since: 2.54 @G_UNICODE_SCRIPT_DOGRA: Dogra. Since: 2.58 @G_UNICODE_SCRIPT_GUNJALA_GONDI: Gunjala Gondi. Since: 2.58 @G_UNICODE_SCRIPT_HANIFI_ROHINGYA: Hanifi Rohingya. Since: 2.58 @G_UNICODE_SCRIPT_MAKASAR: Makasar. Since: 2.58 @G_UNICODE_SCRIPT_MEDEFAIDRIN: Medefaidrin. Since: 2.58 @G_UNICODE_SCRIPT_OLD_SOGDIAN: Old Sogdian. Since: 2.58 @G_UNICODE_SCRIPT_SOGDIAN: Sogdian. Since: 2.58 @G_UNICODE_SCRIPT_ELYMAIC: Elym. Since: 2.62 @G_UNICODE_SCRIPT_NANDINAGARI: Nand. Since: 2.62 @G_UNICODE_SCRIPT_NYIAKENG_PUACHUE_HMONG: Rohg. Since: 2.62 @G_UNICODE_SCRIPT_WANCHO: Wcho. Since: 2.62 @G_UNICODE_SCRIPT_CHORASMIAN: Chorasmian. Since: 2.66 @G_UNICODE_SCRIPT_DIVES_AKURU: Dives Akuru. Since: 2.66 @G_UNICODE_SCRIPT_KHITAN_SMALL_SCRIPT: Khitan small script. Since: 2.66 @G_UNICODE_SCRIPT_YEZIDI: Yezidi. Since: 2.66 @G_UNICODE_SCRIPT_CYPRO_MINOAN: Cypro-Minoan. Since: 2.72 @G_UNICODE_SCRIPT_OLD_UYGHUR: Old Uyghur. Since: 2.72 @G_UNICODE_SCRIPT_TANGSA: Tangsa. Since: 2.72 @G_UNICODE_SCRIPT_TOTO: Toto. Since: 2.72 @G_UNICODE_SCRIPT_VITHKUQI: Vithkuqi. Since: 2.72 @G_UNICODE_SCRIPT_MATH: Mathematical notation. Since: 2.72 @G_UNICODE_SCRIPT_KAWI: Kawi. Since 2.74 @G_UNICODE_SCRIPT_NAG_MUNDARI: Nag Mundari. Since 2.74
The GUnicodeScript enumeration identifies different writing systems. The values correspond to the names as defined in the Unicode standard. The enumeration has been added in GLib 2.14, and is interchangeable with PangoScript.
Note that new types may be added in the future. Applications should be ready to handle unknown values. See Unicode Standard Annex #24: Script names.
Definition at line 463 of file gunicode.h.
| enum GUnicodeType |
GUnicodeType: @G_UNICODE_CONTROL: General category "Other, Control" (Cc) @G_UNICODE_FORMAT: General category "Other, Format" (Cf) @G_UNICODE_UNASSIGNED: General category "Other, Not Assigned" (Cn) @G_UNICODE_PRIVATE_USE: General category "Other, Private Use" (Co) @G_UNICODE_SURROGATE: General category "Other, Surrogate" (Cs) @G_UNICODE_LOWERCASE_LETTER: General category "Letter, Lowercase" (Ll) @G_UNICODE_MODIFIER_LETTER: General category "Letter, Modifier" (Lm) @G_UNICODE_OTHER_LETTER: General category "Letter, Other" (Lo) @G_UNICODE_TITLECASE_LETTER: General category "Letter, Titlecase" (Lt) @G_UNICODE_UPPERCASE_LETTER: General category "Letter, Uppercase" (Lu) @G_UNICODE_SPACING_MARK: General category "Mark, Spacing" (Mc) @G_UNICODE_ENCLOSING_MARK: General category "Mark, Enclosing" (Me) @G_UNICODE_NON_SPACING_MARK: General category "Mark, Nonspacing" (Mn) @G_UNICODE_DECIMAL_NUMBER: General category "Number, Decimal Digit" (Nd) @G_UNICODE_LETTER_NUMBER: General category "Number, Letter" (Nl) @G_UNICODE_OTHER_NUMBER: General category "Number, Other" (No) @G_UNICODE_CONNECT_PUNCTUATION: General category "Punctuation, Connector" (Pc) @G_UNICODE_DASH_PUNCTUATION: General category "Punctuation, Dash" (Pd) @G_UNICODE_CLOSE_PUNCTUATION: General category "Punctuation, Close" (Pe) @G_UNICODE_FINAL_PUNCTUATION: General category "Punctuation, Final quote" (Pf) @G_UNICODE_INITIAL_PUNCTUATION: General category "Punctuation, Initial quote" (Pi) @G_UNICODE_OTHER_PUNCTUATION: General category "Punctuation, Other" (Po) @G_UNICODE_OPEN_PUNCTUATION: General category "Punctuation, Open" (Ps) @G_UNICODE_CURRENCY_SYMBOL: General category "Symbol, Currency" (Sc) @G_UNICODE_MODIFIER_SYMBOL: General category "Symbol, Modifier" (Sk) @G_UNICODE_MATH_SYMBOL: General category "Symbol, Math" (Sm) @G_UNICODE_OTHER_SYMBOL: General category "Symbol, Other" (So) @G_UNICODE_LINE_SEPARATOR: General category "Separator, Line" (Zl) @G_UNICODE_PARAGRAPH_SEPARATOR: General category "Separator, Paragraph" (Zp) @G_UNICODE_SPACE_SEPARATOR: General category "Separator, Space" (Zs)
These are the possible character classifications from the Unicode specification. See Unicode Character Database.
Definition at line 118 of file gunicode.h.
| GLIB_AVAILABLE_IN_ALL gunichar2 * g_ucs4_to_utf16 | ( | const gunichar * | str, |
| glong | len, | ||
| glong * | items_read, | ||
| glong * | items_written, | ||
| GError ** | error ) |
| GLIB_AVAILABLE_IN_ALL gchar * g_ucs4_to_utf8 | ( | const gunichar * | str, |
| glong | len, | ||
| glong * | items_read, | ||
| glong * | items_written, | ||
| GError ** | error ) |
| GLIB_AVAILABLE_IN_ALL GUnicodeBreakType g_unichar_break_type | ( | gunichar | c | ) |
| GLIB_AVAILABLE_IN_ALL gint g_unichar_combining_class | ( | gunichar | uc | ) |
| GLIB_AVAILABLE_IN_ALL gboolean g_unichar_compose | ( | gunichar | a, |
| gunichar | b, | ||
| gunichar * | ch ) |
| GLIB_AVAILABLE_IN_ALL gboolean g_unichar_decompose | ( | gunichar | ch, |
| gunichar * | a, | ||
| gunichar * | b ) |
| GLIB_AVAILABLE_IN_ALL gint g_unichar_digit_value | ( | gunichar | c | ) |
| GLIB_AVAILABLE_IN_ALL gsize g_unichar_fully_decompose | ( | gunichar | ch, |
| gboolean | compat, | ||
| gunichar * | result, | ||
| gsize | result_len ) |
| GLIB_AVAILABLE_IN_ALL gboolean g_unichar_get_mirror_char | ( | gunichar | ch, |
| gunichar * | mirrored_ch ) |
| GLIB_AVAILABLE_IN_ALL GUnicodeScript g_unichar_get_script | ( | gunichar | ch | ) |
| GLIB_AVAILABLE_IN_ALL gboolean g_unichar_isalnum | ( | gunichar | c | ) |
| GLIB_AVAILABLE_IN_ALL gboolean g_unichar_isalpha | ( | gunichar | c | ) |
| GLIB_AVAILABLE_IN_ALL gboolean g_unichar_iscntrl | ( | gunichar | c | ) |
| GLIB_AVAILABLE_IN_ALL gboolean g_unichar_isdefined | ( | gunichar | c | ) |
| GLIB_AVAILABLE_IN_ALL gboolean g_unichar_isdigit | ( | gunichar | c | ) |
| GLIB_AVAILABLE_IN_ALL gboolean g_unichar_isgraph | ( | gunichar | c | ) |
| GLIB_AVAILABLE_IN_ALL gboolean g_unichar_islower | ( | gunichar | c | ) |
| GLIB_AVAILABLE_IN_ALL gboolean g_unichar_ismark | ( | gunichar | c | ) |
| GLIB_AVAILABLE_IN_ALL gboolean g_unichar_isprint | ( | gunichar | c | ) |
| GLIB_AVAILABLE_IN_ALL gboolean g_unichar_ispunct | ( | gunichar | c | ) |
| GLIB_AVAILABLE_IN_ALL gboolean g_unichar_isspace | ( | gunichar | c | ) |
| GLIB_AVAILABLE_IN_ALL gboolean g_unichar_istitle | ( | gunichar | c | ) |
| GLIB_AVAILABLE_IN_ALL gboolean g_unichar_isupper | ( | gunichar | c | ) |
| GLIB_AVAILABLE_IN_ALL gboolean g_unichar_iswide | ( | gunichar | c | ) |
| GLIB_AVAILABLE_IN_ALL gboolean g_unichar_iswide_cjk | ( | gunichar | c | ) |
| GLIB_AVAILABLE_IN_ALL gboolean g_unichar_isxdigit | ( | gunichar | c | ) |
| GLIB_AVAILABLE_IN_ALL gboolean g_unichar_iszerowidth | ( | gunichar | c | ) |
| GLIB_AVAILABLE_IN_ALL gint g_unichar_to_utf8 | ( | gunichar | c, |
| gchar * | outbuf ) |
| GLIB_AVAILABLE_IN_ALL gunichar g_unichar_tolower | ( | gunichar | c | ) |
| GLIB_AVAILABLE_IN_ALL gunichar g_unichar_totitle | ( | gunichar | c | ) |
| GLIB_AVAILABLE_IN_ALL gunichar g_unichar_toupper | ( | gunichar | c | ) |
| GLIB_AVAILABLE_IN_ALL GUnicodeType g_unichar_type | ( | gunichar | c | ) |
| GLIB_AVAILABLE_IN_ALL gboolean g_unichar_validate | ( | gunichar | ch | ) |
| GLIB_AVAILABLE_IN_ALL gint g_unichar_xdigit_value | ( | gunichar | c | ) |
| GLIB_DEPRECATED_IN_2_30 gunichar * g_unicode_canonical_decomposition | ( | gunichar | ch, |
| gsize * | result_len ) |
| GLIB_AVAILABLE_IN_ALL void g_unicode_canonical_ordering | ( | gunichar * | string, |
| gsize | len ) |
| GLIB_AVAILABLE_IN_ALL GUnicodeScript g_unicode_script_from_iso15924 | ( | guint32 | iso15924 | ) |
| GLIB_AVAILABLE_IN_ALL guint32 g_unicode_script_to_iso15924 | ( | GUnicodeScript | script | ) |
| GLIB_AVAILABLE_IN_ALL gunichar * g_utf16_to_ucs4 | ( | const gunichar2 * | str, |
| glong | len, | ||
| glong * | items_read, | ||
| glong * | items_written, | ||
| GError ** | error ) |
| GLIB_AVAILABLE_IN_ALL gchar * g_utf16_to_utf8 | ( | const gunichar2 * | str, |
| glong | len, | ||
| glong * | items_read, | ||
| glong * | items_written, | ||
| GError ** | error ) |
| GLIB_AVAILABLE_IN_ALL gchar * g_utf8_casefold | ( | const gchar * | str, |
| gssize | len ) |
| GLIB_AVAILABLE_IN_ALL gint g_utf8_collate | ( | const gchar * | str1, |
| const gchar * | str2 ) |
| GLIB_AVAILABLE_IN_ALL gchar * g_utf8_collate_key | ( | const gchar * | str, |
| gssize | len ) |
| GLIB_AVAILABLE_IN_ALL gchar * g_utf8_collate_key_for_filename | ( | const gchar * | str, |
| gssize | len ) |
| GLIB_AVAILABLE_IN_ALL gchar * g_utf8_find_next_char | ( | const gchar * | p, |
| const gchar * | end ) |
| GLIB_AVAILABLE_IN_ALL gchar * g_utf8_find_prev_char | ( | const gchar * | str, |
| const gchar * | p ) |
| GLIB_AVAILABLE_IN_ALL gunichar g_utf8_get_char | ( | const gchar * | p | ) |
| GLIB_AVAILABLE_IN_ALL gunichar g_utf8_get_char_validated | ( | const gchar * | p, |
| gssize | max_len ) |
| GLIB_AVAILABLE_IN_2_52 gchar * g_utf8_make_valid | ( | const gchar * | str, |
| gssize | len ) |
| GLIB_AVAILABLE_IN_ALL gchar * g_utf8_normalize | ( | const gchar * | str, |
| gssize | len, | ||
| GNormalizeMode | mode ) |
| GLIB_AVAILABLE_IN_ALL gchar * g_utf8_offset_to_pointer | ( | const gchar * | str, |
| glong | offset ) |
| GLIB_AVAILABLE_IN_ALL glong g_utf8_pointer_to_offset | ( | const gchar * | str, |
| const gchar * | pos ) |
| GLIB_AVAILABLE_IN_ALL gchar * g_utf8_prev_char | ( | const gchar * | p | ) |
| GLIB_AVAILABLE_IN_ALL gchar * g_utf8_strchr | ( | const gchar * | p, |
| gssize | len, | ||
| gunichar | c ) |
| GLIB_AVAILABLE_IN_ALL gchar * g_utf8_strdown | ( | const gchar * | str, |
| gssize | len ) |
| GLIB_AVAILABLE_IN_ALL glong g_utf8_strlen | ( | const gchar * | p, |
| gssize | max ) |
| GLIB_AVAILABLE_IN_ALL gchar * g_utf8_strncpy | ( | gchar * | dest, |
| const gchar * | src, | ||
| gsize | n ) |
| GLIB_AVAILABLE_IN_ALL gchar * g_utf8_strrchr | ( | const gchar * | p, |
| gssize | len, | ||
| gunichar | c ) |
| GLIB_AVAILABLE_IN_ALL gchar * g_utf8_strreverse | ( | const gchar * | str, |
| gssize | len ) |
| GLIB_AVAILABLE_IN_ALL gchar * g_utf8_strup | ( | const gchar * | str, |
| gssize | len ) |
| GLIB_AVAILABLE_IN_2_30 gchar * g_utf8_substring | ( | const gchar * | str, |
| glong | start_pos, | ||
| glong | end_pos ) |
| GLIB_AVAILABLE_IN_ALL gunichar * g_utf8_to_ucs4 | ( | const gchar * | str, |
| glong | len, | ||
| glong * | items_read, | ||
| glong * | items_written, | ||
| GError ** | error ) |
| GLIB_AVAILABLE_IN_ALL gunichar * g_utf8_to_ucs4_fast | ( | const gchar * | str, |
| glong | len, | ||
| glong * | items_written ) |
| GLIB_AVAILABLE_IN_ALL gunichar2 * g_utf8_to_utf16 | ( | const gchar * | str, |
| glong | len, | ||
| glong * | items_read, | ||
| glong * | items_written, | ||
| GError ** | error ) |
| GLIB_AVAILABLE_IN_2_78 gchar * g_utf8_truncate_middle | ( | const gchar * | string, |
| gsize | truncate_length ) |
| GLIB_AVAILABLE_IN_ALL gboolean g_utf8_validate | ( | const gchar * | str, |
| gssize | max_len, | ||
| const gchar ** | end ) |
| GLIB_AVAILABLE_IN_2_60 gboolean g_utf8_validate_len | ( | const gchar * | str, |
| gsize | max_len, | ||
| const gchar ** | end ) |
Definition at line 791 of file gunicode.h.
| G_BEGIN_DECLS typedef guint32 gunichar |
gunichar:
A type which can hold any UTF-32 or UCS-4 character code, also known as a Unicode code point.
If you want to produce the UTF-8 representation of a gunichar, use g_ucs4_to_utf8(). See also g_utf8_to_ucs4() for the reverse process.
To print/scan values of this type as integer, use G_GINT32_MODIFIER and/or G_GUINT32_FORMAT.
The notation to express a Unicode code point in running text is as a hexadecimal number with four to six digits and uppercase letters, prefixed by the string "U+". Leading zeros are omitted, unless the code point would have fewer than four hexadecimal digits. For example, "U+0041 LATIN CAPITAL LETTER A". To print a code point in the U+-notation, use the format string "U+\%04"G_GINT32_FORMAT"X". To scan, use the format string "U+\%06"G_GINT32_FORMAT"X".
|[ gunichar c; sscanf ("U+0041", "U+%06"G_GINT32_FORMAT"X", &c) g_print ("Read U+%04"G_GINT32_FORMAT"X", c); ]|
Definition at line 61 of file gunicode.h.
1.10.0