luc14n0/glib
1
0
Fork 0
mirror of https://gitlab.gnome.org/GNOME/glib.git synced 2025-03-15 20:25:12 +01:00
Code Issues Packages Projects Releases Wiki Activity

Move Unicode docs inline, ditch template

Browse Source
This commit is contained in:
Matthias Clasen 2011-07-18 23:23:17 -04:00
parent 2358616d6a
commit 09e2d2a61c
4 changed files with 370 additions and 982 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
docs/reference/glib/tmpl/.gitignore vendored
View File

@ -43,4 +43,5 @@ trees-binary.sgml
trees-nary.sgml
timers.sgml
timezone.sgml
unicode.sgml
version.sgml

908
docs/reference/glib/tmpl/unicode.sgml
View File

@ -1,908 +0,0 @@
<!-- ##### SECTION Title ##### -->
Unicode Manipulation
<!-- ##### SECTION Short_Description ##### -->
functions operating on Unicode characters and UTF-8 strings
<!-- ##### SECTION Long_Description ##### -->
<para>
This section describes a number of functions for dealing with
Unicode characters and strings. There are analogues of the
traditional <filename>ctype.h</filename> character classification
and case conversion functions, UTF-8 analogues of some string utility
functions, functions to perform normalization, case conversion and
collation on UTF-8 strings and finally functions to convert between
the UTF-8, UTF-16 and UCS-4 encodings of Unicode.
</para>
<para>
The implementations of the Unicode functions in GLib are based
on the Unicode Character Data tables, which are available from
<ulink url="http://www.unicode.org/">www.unicode.org</ulink>.
GLib 2.8 supports Unicode 4.0, GLib 2.10 supports Unicode 4.1,
GLib 2.12 supports Unicode 5.0, GLib 2.16.3 supports Unicode 5.1.
</para>
<!-- ##### SECTION See_Also ##### -->
<para>
<variablelist>
<varlistentry>
<term>g_locale_to_utf8(), g_locale_from_utf8()</term>
<listitem><para>
Convenience functions for converting between UTF-8 and the locale encoding.
</para></listitem>
</varlistentry>
</variablelist>
</para>
<!-- ##### SECTION Stability_Level ##### -->
<!-- ##### SECTION Image ##### -->
<!-- ##### TYPEDEF gunichar ##### -->
<para>
A type which can hold any UTF-32 or UCS-4 character code, also known
as a Unicode code point.
</para>
<para>
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.
</para>
<para>
To print/scan values of this type as integer, use
%G_GINT32_MODIFIER and/or %G_GUINT32_FORMAT.
</para>
<para>
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".
<informalexample>
<programlisting>
gunichar c;
sscanf ("U+0041", "U+%06"G_GINT32_FORMAT"X", &amp;c)
g_print ("Read U+%04"G_GINT32_FORMAT"X", c);
</programlisting>
</informalexample>
</para>
<!-- ##### TYPEDEF gunichar2 ##### -->
<para>
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>.
</para>
<para>
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().
</para>
<para>
To print/scan values of this type as integer, use
%G_GINT16_MODIFIER and/or %G_GUINT16_FORMAT.
</para>
<!-- ##### FUNCTION g_unichar_validate ##### -->
<para>
</para>
@ch:
@Returns:
<!-- ##### FUNCTION g_unichar_isalnum ##### -->
<para>
</para>
@c:
@Returns:
<!-- ##### FUNCTION g_unichar_isalpha ##### -->
<para>
</para>
@c:
@Returns:
<!-- ##### FUNCTION g_unichar_iscntrl ##### -->
<para>
</para>
@c:
@Returns:
<!-- ##### FUNCTION g_unichar_isdefined ##### -->
<para>
</para>
@c:
@Returns:
<!-- ##### FUNCTION g_unichar_isdigit ##### -->
<para>
</para>
@c:
@Returns:
<!-- ##### FUNCTION g_unichar_isgraph ##### -->
<para>
</para>
@c:
@Returns:
<!-- ##### FUNCTION g_unichar_islower ##### -->
<para>
</para>
@c:
@Returns:
<!-- ##### FUNCTION g_unichar_ismark ##### -->
<para>
</para>
@c:
@Returns:
<!-- ##### FUNCTION g_unichar_isprint ##### -->
<para>
</para>
@c:
@Returns:
<!-- ##### FUNCTION g_unichar_ispunct ##### -->
<para>
</para>
@c:
@Returns:
<!-- ##### FUNCTION g_unichar_isspace ##### -->
<para>
</para>
@c:
@Returns:
<!-- ##### FUNCTION g_unichar_istitle ##### -->
<para>
</para>
@c:
@Returns:
<!-- ##### FUNCTION g_unichar_isupper ##### -->
<para>
</para>
@c:
@Returns:
<!-- ##### FUNCTION g_unichar_isxdigit ##### -->
<para>
</para>
@c:
@Returns:
<!-- ##### FUNCTION g_unichar_iswide ##### -->
<para>
</para>
@c:
@Returns:
<!-- ##### FUNCTION g_unichar_iswide_cjk ##### -->
<para>
</para>
@c:
@Returns:
<!-- ##### FUNCTION g_unichar_iszerowidth ##### -->
<para>
</para>
@c:
@Returns:
<!-- ##### FUNCTION g_unichar_toupper ##### -->
<para>
</para>
@c:
@Returns:
<!-- ##### FUNCTION g_unichar_tolower ##### -->
<para>
</para>
@c:
@Returns:
<!-- ##### FUNCTION g_unichar_totitle ##### -->
<para>
</para>
@c:
@Returns:
<!-- ##### FUNCTION g_unichar_digit_value ##### -->
<para>
</para>
@c:
@Returns:
<!-- ##### FUNCTION g_unichar_xdigit_value ##### -->
<para>
</para>
@c:
@Returns:
<!-- ##### ENUM GUnicodeType ##### -->
<para>
These are the possible character classifications from the
Unicode specification.
See <ulink url="http://www.unicode.org/Public/UNIDATA/UnicodeData.html"
>http://www.unicode.org/Public/UNIDATA/UnicodeData.html</ulink>.
</para>
@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_COMBINING_MARK: General category "Mark, Spacing Combining" (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)
<!-- ##### FUNCTION g_unichar_type ##### -->
<para>
</para>
@c:
@Returns:
<!-- ##### ENUM GUnicodeBreakType ##### -->
<para>
These are the possible line break classifications.
The five Hangul types were added in Unicode 4.1, so, has been
introduced in GLib 2.10. Note that new types may be added in the future.
Applications should be ready to handle unknown values.
They may be regarded as %G_UNICODE_BREAK_UNKNOWN.
See <ulink url="http://www.unicode.org/unicode/reports/tr14/"
>http://www.unicode.org/unicode/reports/tr14/</ulink>.
</para>
@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
<!-- ##### FUNCTION g_unichar_break_type ##### -->
<para>
</para>
@c:
@Returns:
<!-- ##### FUNCTION g_unichar_combining_class ##### -->
<para>
</para>
@uc:
@Returns:
<!-- ##### FUNCTION g_unicode_canonical_ordering ##### -->
<para>
</para>
@string:
@len:
<!-- ##### FUNCTION g_unicode_canonical_decomposition ##### -->
<para>
</para>
@ch:
@result_len:
@Returns:
<!-- ##### FUNCTION g_unichar_get_mirror_char ##### -->
<para>
</para>
@ch:
@mirrored_ch:
@Returns:
<!-- ##### ENUM GUnicodeScript ##### -->
<para>
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 <ulink
url="http://www.unicode.org/reports/tr24/">Unicode Standard Annex
#24: Script names</ulink>.
</para>
@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
<!-- ##### 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:

414
glib/gunicode.h
View File

@ -31,11 +31,89 @@
G_BEGIN_DECLS
/**
* 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", &amp;c)
* g_print ("Read U+%04"G_GINT32_FORMAT"X", c);
* ]|
*/
typedef guint32 gunichar;
/**
* 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.
*/
typedef guint16 gunichar2;
/* These are the possible character classifications.
* See http://www.unicode.org/Public/UNIDATA/UCD.html#General_Category_Values
/**
* 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_COMBINING_MARK: General category "Mark, Spacing Combining" (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 <ulink url="http://www.unicode.org/Public/UNIDATA/UnicodeData.html"
* >http://www.unicode.org/Public/UNIDATA/UnicodeData.html</ulink>.
*/
typedef enum
{
@ -71,10 +149,55 @@ typedef enum
G_UNICODE_SPACE_SEPARATOR
} GUnicodeType;
/* These are the possible line break classifications.
* Note that new types may be added in the future.
* Implementations may regard unknown values like G_UNICODE_BREAK_UNKNOWN
* See http://www.unicode.org/unicode/reports/tr14/
/**
* 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
*
* These are the possible line break classifications.
*
* The five Hangul types were added in Unicode 4.1, so, has been
* introduced in GLib 2.10. Note that new types may be added in the future.
* Applications should be ready to handle unknown values.
* They may be regarded as %G_UNICODE_BREAK_UNKNOWN.
*
* See <ulink url="http://www.unicode.org/unicode/reports/tr14/"
* >http://www.unicode.org/unicode/reports/tr14/</ulink>.
*/
typedef enum
{
@ -117,6 +240,129 @@ typedef enum
G_UNICODE_BREAK_CLOSE_PARANTHESIS
} GUnicodeBreakType;
/**
* 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
* i 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
*
* 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 <ulink
* url="http://www.unicode.org/reports/tr24/">Unicode Standard Annex
* #24: Script names</ulink>.
*/
typedef enum
{ /* ISO 15924 code */
G_UNICODE_SCRIPT_INVALID_CODE = -1,
@ -289,48 +535,59 @@ gboolean g_unichar_validate (gunichar ch) G_GNUC_CONST;
/* Pairwise canonical compose/decompose */
gboolean g_unichar_compose (gunichar a,
gunichar b,
gunichar *ch);
gunichar b,
gunichar *ch);
gboolean g_unichar_decompose (gunichar ch,
gunichar *a,
gunichar *b);
gunichar *a,
gunichar *b);
gsize g_unichar_fully_decompose (gunichar ch,
gboolean compat,
gunichar *result,
gsize result_len);
gboolean compat,
gunichar *result,
gsize result_len);
/* Compute canonical ordering of a string in-place. This rearranges
decomposed characters in the string according to their combining
classes. See the Unicode manual for more information. */
void g_unicode_canonical_ordering (gunichar *string,
gsize len);
gsize len);
/* Deprecated. Use g_unichar_fully_decompose() */
gunichar *g_unicode_canonical_decomposition (gunichar ch,
gsize *result_len) G_GNUC_MALLOC;
gsize *result_len) G_GNUC_MALLOC;
/* Array of skip-bytes-per-initial character.
*/
GLIB_VAR const gchar * const g_utf8_skip;
/**
* g_utf8_next_char:
* @p: 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.
*/
#define g_utf8_next_char(p) (char *)((p) + g_utf8_skip[*(const guchar *)(p)])
gunichar g_utf8_get_char (const gchar *p) G_GNUC_PURE;
gunichar g_utf8_get_char_validated (const gchar *p,
gssize max_len) G_GNUC_PURE;
gssize max_len) G_GNUC_PURE;
gchar* g_utf8_offset_to_pointer (const gchar *str,
glong offset) G_GNUC_PURE;
glong g_utf8_pointer_to_offset (const gchar *str,
const gchar *pos) G_GNUC_PURE;
const gchar *pos) G_GNUC_PURE;
gchar* g_utf8_prev_char (const gchar *p) G_GNUC_PURE;
gchar* g_utf8_find_next_char (const gchar *p,
const gchar *end) G_GNUC_PURE;
const gchar *end) G_GNUC_PURE;
gchar* g_utf8_find_prev_char (const gchar *str,
const gchar *p) G_GNUC_PURE;
const gchar *p) G_GNUC_PURE;
glong g_utf8_strlen (const gchar *p,
gssize max) G_GNUC_PURE;
@ -339,78 +596,93 @@ gchar *g_utf8_substring (const gchar *p,
glong start_pos,
glong end_pos) G_GNUC_MALLOC;
/* Copies n characters from src to dest */
gchar* g_utf8_strncpy (gchar *dest,
const gchar *src,
gsize n);
gchar *g_utf8_strncpy (gchar *dest,
const gchar *src,
gsize n);
/* Find the UTF-8 character corresponding to ch, in string p. These
functions are equivalants to strchr and strrchr */
gchar* g_utf8_strchr (const gchar *p,
gssize len,
gunichar c);
gssize len,
gunichar c);
gchar* g_utf8_strrchr (const gchar *p,
gssize len,
gunichar c);
gssize len,
gunichar c);
gchar* g_utf8_strreverse (const gchar *str,
gssize len);
gssize len);
gunichar2 *g_utf8_to_utf16 (const gchar *str,
glong len,
glong *items_read,
glong *items_written,
GError **error) G_GNUC_MALLOC;
glong len,
glong *items_read,
glong *items_written,
GError **error) G_GNUC_MALLOC;
gunichar * g_utf8_to_ucs4 (const gchar *str,
glong len,
glong *items_read,
glong *items_written,
GError **error) G_GNUC_MALLOC;
glong len,
glong *items_read,
glong *items_written,
GError **error) G_GNUC_MALLOC;
gunichar * g_utf8_to_ucs4_fast (const gchar *str,
glong len,
glong *items_written) G_GNUC_MALLOC;
glong len,
glong *items_written) G_GNUC_MALLOC;
gunichar * g_utf16_to_ucs4 (const gunichar2 *str,
glong len,
glong *items_read,
glong *items_written,
GError **error) G_GNUC_MALLOC;
glong len,
glong *items_read,
glong *items_written,
GError **error) G_GNUC_MALLOC;
gchar* g_utf16_to_utf8 (const gunichar2 *str,
glong len,
glong *items_read,
glong *items_written,
GError **error) G_GNUC_MALLOC;
glong len,
glong *items_read,
glong *items_written,
GError **error) G_GNUC_MALLOC;
gunichar2 *g_ucs4_to_utf16 (const gunichar *str,
glong len,
glong *items_read,
glong *items_written,
GError **error) G_GNUC_MALLOC;
glong len,
glong *items_read,
glong *items_written,
GError **error) G_GNUC_MALLOC;
gchar* g_ucs4_to_utf8 (const gunichar *str,
glong len,
glong *items_read,
glong *items_written,
GError **error) G_GNUC_MALLOC;
glong len,
glong *items_read,
glong *items_written,
GError **error) G_GNUC_MALLOC;
/* Convert a single character into UTF-8. outbuf must have at
* least 6 bytes of space. Returns the number of bytes in the
* result.
*/
gint g_unichar_to_utf8 (gunichar c,
gchar *outbuf);
/* Validate a UTF8 string, return TRUE if valid, put pointer to
* first invalid char in **end
*/
gchar *outbuf);
gboolean g_utf8_validate (const gchar *str,
gssize max_len,
const gchar **end);
gchar *g_utf8_strup (const gchar *str,
gssize len) G_GNUC_MALLOC;
gssize len) G_GNUC_MALLOC;
gchar *g_utf8_strdown (const gchar *str,
gssize len) G_GNUC_MALLOC;
gssize len) G_GNUC_MALLOC;
gchar *g_utf8_casefold (const gchar *str,
gssize len) G_GNUC_MALLOC;
gssize len) G_GNUC_MALLOC;
/**
* 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.
*/
typedef enum {
G_NORMALIZE_DEFAULT,
G_NORMALIZE_NFD = G_NORMALIZE_DEFAULT,
@ -423,15 +695,15 @@ typedef enum {
} GNormalizeMode;
gchar *g_utf8_normalize (const gchar *str,
gssize len,
GNormalizeMode mode) G_GNUC_MALLOC;
gssize len,
GNormalizeMode mode) G_GNUC_MALLOC;
gint g_utf8_collate (const gchar *str1,
const gchar *str2) G_GNUC_PURE;
const gchar *str2) G_GNUC_PURE;
gchar *g_utf8_collate_key (const gchar *str,
gssize len) G_GNUC_MALLOC;
gssize len) G_GNUC_MALLOC;
gchar *g_utf8_collate_key_for_filename (const gchar *str,
gssize len) G_GNUC_MALLOC;
gssize len) G_GNUC_MALLOC;
/* private */

23
glib/gunidecomp.c
View File

@ -19,6 +19,29 @@
* Boston, MA 02111-1307, USA.
*/
/**
* SECTION:unicode
* @Title: Unicode Manipulation
* @Short_description: functions operating on Unicode characters and
* UTF-8 strings
* @See_also: g_locale_to_utf8(), g_locale_from_utf8()
*
* This section describes a number of functions for dealing with
* Unicode characters and strings. There are analogues of the
* traditional <filename>ctype.h</filename> character classification
* and case conversion functions, UTF-8 analogues of some string utility
* functions, functions to perform normalization, case conversion and
* collation on UTF-8 strings and finally functions to convert between
* the UTF-8, UTF-16 and UCS-4 encodings of Unicode.
*
* The implementations of the Unicode functions in GLib are based
* on the Unicode Character Data tables, which are available from
* <ulink url="http://www.unicode.org/">www.unicode.org</ulink>.
* GLib 2.8 supports Unicode 4.0, GLib 2.10 supports Unicode 4.1,
* GLib 2.12 supports Unicode 5.0, GLib 2.16.3 supports Unicode 5.1,
* GLib 2.30 supports Unicode 6.0.
*/
#include "config.h"
#include <stdlib.h>