* Boston, MA 02111-1307, USA.
*/
+#if defined(G_DISABLE_SINGLE_INCLUDES) && !defined (__G_LIB_H__) && !defined (GLIB_COMPILATION)
+#error "Only <glib.h> can be included directly."
+#endif
+
#ifndef __G_UNICODE_H__
#define __G_UNICODE_H__
G_UNICODE_BREAK_HANGUL_LVT_SYLLABLE
} GUnicodeBreakType;
+typedef enum
+{ /* ISO 15924 code */
+ G_UNICODE_SCRIPT_INVALID_CODE = -1,
+ G_UNICODE_SCRIPT_COMMON = 0, /* Zyyy */
+ G_UNICODE_SCRIPT_INHERITED, /* Qaai */
+ G_UNICODE_SCRIPT_ARABIC, /* Arab */
+ G_UNICODE_SCRIPT_ARMENIAN, /* Armn */
+ G_UNICODE_SCRIPT_BENGALI, /* Beng */
+ G_UNICODE_SCRIPT_BOPOMOFO, /* Bopo */
+ G_UNICODE_SCRIPT_CHEROKEE, /* Cher */
+ G_UNICODE_SCRIPT_COPTIC, /* Qaac */
+ G_UNICODE_SCRIPT_CYRILLIC, /* Cyrl (Cyrs) */
+ G_UNICODE_SCRIPT_DESERET, /* Dsrt */
+ G_UNICODE_SCRIPT_DEVANAGARI, /* Deva */
+ G_UNICODE_SCRIPT_ETHIOPIC, /* Ethi */
+ G_UNICODE_SCRIPT_GEORGIAN, /* Geor (Geon, Geoa) */
+ G_UNICODE_SCRIPT_GOTHIC, /* Goth */
+ G_UNICODE_SCRIPT_GREEK, /* Grek */
+ G_UNICODE_SCRIPT_GUJARATI, /* Gujr */
+ G_UNICODE_SCRIPT_GURMUKHI, /* Guru */
+ G_UNICODE_SCRIPT_HAN, /* Hani */
+ G_UNICODE_SCRIPT_HANGUL, /* Hang */
+ G_UNICODE_SCRIPT_HEBREW, /* Hebr */
+ G_UNICODE_SCRIPT_HIRAGANA, /* Hira */
+ G_UNICODE_SCRIPT_KANNADA, /* Knda */
+ G_UNICODE_SCRIPT_KATAKANA, /* Kana */
+ G_UNICODE_SCRIPT_KHMER, /* Khmr */
+ G_UNICODE_SCRIPT_LAO, /* Laoo */
+ G_UNICODE_SCRIPT_LATIN, /* Latn (Latf, Latg) */
+ G_UNICODE_SCRIPT_MALAYALAM, /* Mlym */
+ G_UNICODE_SCRIPT_MONGOLIAN, /* Mong */
+ G_UNICODE_SCRIPT_MYANMAR, /* Mymr */
+ G_UNICODE_SCRIPT_OGHAM, /* Ogam */
+ G_UNICODE_SCRIPT_OLD_ITALIC, /* Ital */
+ G_UNICODE_SCRIPT_ORIYA, /* Orya */
+ G_UNICODE_SCRIPT_RUNIC, /* Runr */
+ G_UNICODE_SCRIPT_SINHALA, /* Sinh */
+ G_UNICODE_SCRIPT_SYRIAC, /* Syrc (Syrj, Syrn, Syre) */
+ G_UNICODE_SCRIPT_TAMIL, /* Taml */
+ G_UNICODE_SCRIPT_TELUGU, /* Telu */
+ G_UNICODE_SCRIPT_THAANA, /* Thaa */
+ G_UNICODE_SCRIPT_THAI, /* Thai */
+ G_UNICODE_SCRIPT_TIBETAN, /* Tibt */
+ G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL, /* Cans */
+ G_UNICODE_SCRIPT_YI, /* Yiii */
+ G_UNICODE_SCRIPT_TAGALOG, /* Tglg */
+ G_UNICODE_SCRIPT_HANUNOO, /* Hano */
+ G_UNICODE_SCRIPT_BUHID, /* Buhd */
+ G_UNICODE_SCRIPT_TAGBANWA, /* Tagb */
+
+ /* Unicode-4.0 additions */
+ G_UNICODE_SCRIPT_BRAILLE, /* Brai */
+ G_UNICODE_SCRIPT_CYPRIOT, /* Cprt */
+ G_UNICODE_SCRIPT_LIMBU, /* Limb */
+ G_UNICODE_SCRIPT_OSMANYA, /* Osma */
+ G_UNICODE_SCRIPT_SHAVIAN, /* Shaw */
+ G_UNICODE_SCRIPT_LINEAR_B, /* Linb */
+ G_UNICODE_SCRIPT_TAI_LE, /* Tale */
+ G_UNICODE_SCRIPT_UGARITIC, /* Ugar */
+
+ /* Unicode-4.1 additions */
+ G_UNICODE_SCRIPT_NEW_TAI_LUE, /* Talu */
+ G_UNICODE_SCRIPT_BUGINESE, /* Bugi */
+ G_UNICODE_SCRIPT_GLAGOLITIC, /* Glag */
+ G_UNICODE_SCRIPT_TIFINAGH, /* Tfng */
+ G_UNICODE_SCRIPT_SYLOTI_NAGRI, /* Sylo */
+ G_UNICODE_SCRIPT_OLD_PERSIAN, /* Xpeo */
+ G_UNICODE_SCRIPT_KHAROSHTHI, /* Khar */
+
+ /* Unicode-5.0 additions */
+ G_UNICODE_SCRIPT_UNKNOWN, /* Zzzz */
+ G_UNICODE_SCRIPT_BALINESE, /* Bali */
+ G_UNICODE_SCRIPT_CUNEIFORM, /* Xsux */
+ G_UNICODE_SCRIPT_PHOENICIAN, /* Phnx */
+ G_UNICODE_SCRIPT_PHAGS_PA, /* Phag */
+ G_UNICODE_SCRIPT_NKO /* Nkoo */
+} GUnicodeScript;
+
/* 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, and should be copied
gboolean g_unichar_istitle (gunichar c) G_GNUC_CONST;
gboolean g_unichar_isdefined (gunichar c) G_GNUC_CONST;
gboolean g_unichar_iswide (gunichar c) G_GNUC_CONST;
+gboolean g_unichar_iswide_cjk(gunichar c) G_GNUC_CONST;
+gboolean g_unichar_iszerowidth(gunichar c) G_GNUC_CONST;
+gboolean g_unichar_ismark (gunichar c) G_GNUC_CONST;
/* More <ctype.h> functions. These convert between the three cases.
* See the Unicode book to understand title case. */
/* Return the line break property for a given character */
GUnicodeBreakType g_unichar_break_type (gunichar c) G_GNUC_CONST;
+/* Returns the combining class for a given character */
+gint g_unichar_combining_class (gunichar uc) G_GNUC_CONST;
+
/* Compute canonical ordering of a string in-place. This rearranges
decomposed characters in the string according to their combining
*/
GLIB_VAR const gchar * const g_utf8_skip;
-#define g_utf8_next_char(p) (char *)((p) + g_utf8_skip[*(guchar *)(p)])
+#define g_utf8_next_char(p) (char *)((p) + g_utf8_skip[*(const guchar *)(p)])
-gunichar g_utf8_get_char (const gchar *p);
+gunichar g_utf8_get_char (const gchar *p) G_GNUC_PURE;
gunichar g_utf8_get_char_validated (const gchar *p,
- gssize max_len);
+ gssize max_len) G_GNUC_PURE;
gchar* g_utf8_offset_to_pointer (const gchar *str,
- glong offset);
+ glong offset) G_GNUC_PURE;
glong g_utf8_pointer_to_offset (const gchar *str,
- const gchar *pos);
-gchar* g_utf8_prev_char (const gchar *p);
+ 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);
+ const gchar *end) G_GNUC_PURE;
gchar* g_utf8_find_prev_char (const gchar *str,
- const gchar *p);
+ const gchar *p) G_GNUC_PURE;
glong g_utf8_strlen (const gchar *p,
- gssize max);
+ gssize max) G_GNUC_PURE;
/* Copies n characters from src to dest */
gchar* g_utf8_strncpy (gchar *dest,
const gchar **end);
/* Validate a Unicode character */
-gboolean g_unichar_validate (gunichar ch);
+gboolean g_unichar_validate (gunichar ch) G_GNUC_CONST;
gchar *g_utf8_strup (const gchar *str,
gssize len) G_GNUC_MALLOC;
GNormalizeMode mode) G_GNUC_MALLOC;
gint g_utf8_collate (const gchar *str1,
- const gchar *str2);
+ const gchar *str2) G_GNUC_PURE;
gchar *g_utf8_collate_key (const gchar *str,
gssize len) G_GNUC_MALLOC;
gchar *g_utf8_collate_key_for_filename (const gchar *str,
gboolean g_unichar_get_mirror_char (gunichar ch,
gunichar *mirrored_ch);
+GUnicodeScript g_unichar_get_script (gunichar ch) G_GNUC_CONST;
+
+
+/* private */
+
+gchar *_g_utf8_make_valid (const gchar *name);
+
G_END_DECLS
#endif /* __G_UNICODE_H__ */
projects / platform / upstream / glib.git / blobdiff