diff options
author | Havoc Pennington <hp@redhat.com> | 2000-11-29 23:38:24 +0000 |
---|---|---|
committer | Havoc Pennington <hp@src.gnome.org> | 2000-11-29 23:38:24 +0000 |
commit | 7fce6d3abcca3639e2b3b268ad47557179a8a21f (patch) | |
tree | 883e01df3df5e107da090b86e28987937c9dadbd /gunicode.h | |
parent | 61c2307387173c7af3d827f083aefc42fd747175 (diff) |
s/UNICODE_LAST_CHAR/G_UNICODE_LAST_CHAR/
2000-11-29 Havoc Pennington <hp@redhat.com>
* gunidecomp.c (COMBINING_CLASS): s/UNICODE_LAST_CHAR/G_UNICODE_LAST_CHAR/
* gunichartables.h: Update for data in Unicode 3.0.1,
and include tables for line break properties
* gunidecomp.h: Ditto
* gunicode.h (GUnicodeBreakType): Enum for line break properties
(g_unichar_break_type): Get the break property for a char
* gunibreak.h: Autogenerated line break property tables
* gunibreak.c (g_unichar_break_type): added
* Makefile.am (EXTRA_DIST): dist gen-unicode-tables.pl
* Makefile.am (libglib_1_3_la_SOURCES): Add gunibreak.h, gunibreak.c
* gen-unicode-tables.pl: Include the script to update the unicode
char tables
Diffstat (limited to 'gunicode.h')
-rw-r--r-- | gunicode.h | 45 |
1 files changed, 43 insertions, 2 deletions
diff --git a/gunicode.h b/gunicode.h index 2665894f8..6810a2106 100644 --- a/gunicode.h +++ b/gunicode.h @@ -30,8 +30,11 @@ G_BEGIN_DECLS typedef guint32 gunichar; typedef guint16 gunichar2; -/* These are the possible character classifications. */ -typedef enum { +/* These are the possible character classifications. + * See http://www.unicode.org/Public/UNIDATA/UnicodeData.html + */ +typedef enum +{ G_UNICODE_CONTROL, G_UNICODE_FORMAT, G_UNICODE_UNASSIGNED, @@ -64,6 +67,42 @@ typedef enum { G_UNICODE_SPACE_SEPARATOR } GUnicodeType; +/* These are the possible line break classifications. + * See http://www.unicode.org/unicode/reports/tr14/ + */ +typedef enum +{ + G_UNICODE_BREAK_MANDATORY, + G_UNICODE_BREAK_CARRIAGE_RETURN, + G_UNICODE_BREAK_LINE_FEED, + G_UNICODE_BREAK_COMBINING_MARK, + G_UNICODE_BREAK_SURROGATE, + G_UNICODE_BREAK_ZERO_WIDTH_SPACE, + G_UNICODE_BREAK_INSEPARABLE, + G_UNICODE_BREAK_NON_BREAKING_GLUE, + G_UNICODE_BREAK_CONTINGENT, + G_UNICODE_BREAK_SPACE, + G_UNICODE_BREAK_AFTER, + G_UNICODE_BREAK_BEFORE, + G_UNICODE_BREAK_BEFORE_AND_AFTER, + G_UNICODE_BREAK_HYPHEN, + G_UNICODE_BREAK_NON_STARTER, + G_UNICODE_BREAK_OPEN_PUNCTUATION, + G_UNICODE_BREAK_CLOSE_PUNCTUATION, + G_UNICODE_BREAK_QUOTATION, + G_UNICODE_BREAK_EXCLAMATION, + G_UNICODE_BREAK_IDEOGRAPHIC, + G_UNICODE_BREAK_NUMERIC, + G_UNICODE_BREAK_INFIX_SEPARATOR, + G_UNICODE_BREAK_SYMBOL, + G_UNICODE_BREAK_ALPHABETIC, + G_UNICODE_BREAK_PREFIX, + G_UNICODE_BREAK_POSTFIX, + G_UNICODE_BREAK_COMPLEX_CONTEXT, + G_UNICODE_BREAK_AMBIGUOUS, + G_UNICODE_BREAK_UNKNOWN +} GUnicodeBreakType; + /* Returns TRUE if current locale uses UTF-8 charset. If CHARSET is * not null, sets *CHARSET to the name of the current locale's * charset. This value is statically allocated. @@ -102,6 +141,8 @@ gint g_unichar_xdigit_value (gunichar c) G_GNUC_CONST; /* Return the Unicode character type of a given character. */ GUnicodeType g_unichar_type (gunichar c) G_GNUC_CONST; +/* Return the line break property for a given character */ +GUnicodeBreakType g_unichar_break_type (gunichar c) G_GNUC_CONST; /* Compute canonical ordering of a string in-place. This rearranges |