unicode.sgml

This GLib version 2.16.1. GLib is the low-level core library that forms the basis for projects such

@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

<!-- ##### FUNCTION g_unichar_get_script ##### -->
<para>

</para>

@ch: 
@Returns: 


<!-- ##### MACRO g_utf8_next_char ##### -->
<para>
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.
</para>

@p: Pointer to the start of a valid UTF-8 character.


<!-- ##### FUNCTION g_utf8_get_char ##### -->
<para>

</para>

@p: 
@Returns: 


<!-- ##### FUNCTION g_utf8_get_char_validated ##### -->
<para>

</para>

@p: 
@max_len: 
@Returns: 


<!-- ##### FUNCTION g_utf8_offset_to_pointer ##### -->
<para>

</para>

@str: 
@offset: 
@Returns: 


<!-- ##### FUNCTION g_utf8_pointer_to_offset ##### -->
<para>

</para>

@str: 
@pos: 
@Returns: 


<!-- ##### FUNCTION g_utf8_prev_char ##### -->
<para>

</para>

@p: 
@Returns: 


<!-- ##### FUNCTION g_utf8_find_next_char ##### -->
<para>

</para>

@p: 
@end: 
@Returns: 


<!-- ##### FUNCTION g_utf8_find_prev_char ##### -->
<para>

</para>

@str: 
@p: 
@Returns: 


<!-- ##### FUNCTION g_utf8_strlen ##### -->
<para>

</para>

@p: 
@max: 
@Returns: 


<!-- ##### FUNCTION g_utf8_strncpy ##### -->
<para>

</para>

@dest: 
@src: 
@n: 
@Returns: 


<!-- ##### FUNCTION g_utf8_strchr ##### -->
<para>

</para>

@p: 
@len: 
@c: 
@Returns: 


<!-- ##### FUNCTION g_utf8_strrchr ##### -->
<para>

</para>

@p: 
@len: 
@c: 
@Returns: 


<!-- ##### FUNCTION g_utf8_strreverse ##### -->
<para>

</para>

@str: 
@len: 
@Returns: 


<!-- ##### FUNCTION g_utf8_validate ##### -->
<para>

</para>

@str: 
@max_len: 
@end: 
@Returns: 


<!-- ##### FUNCTION g_utf8_strup ##### -->
<para>

</para>

@str: 
@len: 
@Returns: 


<!-- ##### FUNCTION g_utf8_strdown ##### -->
<para>

</para>

@str: 
@len: 
@Returns: 


<!-- ##### FUNCTION g_utf8_casefold ##### -->
<para>

</para>

@str: 
@len: 
@Returns: 


<!-- ##### FUNCTION g_utf8_normalize ##### -->
<para>

</para>

@str: 
@len: 
@mode: 
@Returns: 


<!-- ##### ENUM GNormalizeMode ##### -->
<para>
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.
</para>

@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.

<!-- ##### FUNCTION g_utf8_collate ##### -->
<para>

</para>

@str1: 
@str2: 
@Returns: 


<!-- ##### FUNCTION g_utf8_collate_key ##### -->
<para>

</para>

@str: 
@len: 
@Returns: 


<!-- ##### FUNCTION g_utf8_collate_key_for_filename ##### -->
<para>

</para>

@str: 
@len: 
@Returns: 


<!-- ##### FUNCTION g_utf8_to_utf16 ##### -->
<para>

</para>

@str: 
@len: 
@items_read: 
@items_written: 
@error: 
@Returns: 


<!-- ##### FUNCTION g_utf8_to_ucs4 ##### -->
<para>

</para>

@str: 
@len: 
@items_read: 
@items_written: 
@error: 
@Returns: 


<!-- ##### FUNCTION g_utf8_to_ucs4_fast ##### -->
<para>

</para>

@str: 
@len: 
@items_written: 
@Returns: 


<!-- ##### FUNCTION g_utf16_to_ucs4 ##### -->
<para>

</para>

@str: 
@len: 
@items_read: 
@items_written: 
@error: 
@Returns: 


<!-- ##### FUNCTION g_utf16_to_utf8 ##### -->
<para>

</para>

@str: 
@len: 
@items_read: 
@items_written: 
@error: 
@Returns: 


<!-- ##### FUNCTION g_ucs4_to_utf16 ##### -->
<para>

</para>

@str: 
@len: 
@items_read: 
@items_written: 
@error: 
@Returns: 


<!-- ##### FUNCTION g_ucs4_to_utf8 ##### -->
<para>

</para>

@str: 
@len: 
@items_read: 
@items_written: 
@error: 
@Returns: 


<!-- ##### FUNCTION g_unichar_to_utf8 ##### -->
<para>

</para>

@c: 
@outbuf: 
@Returns: