0 +l=J!e@pNjbѿ h"_I|+?/* gunicode.h - Unicode manipulation functions * * Copyright (C) 1999, 2000 Tom Tromey * Copyright 2000, 2005 Red Hat, Inc. * * This library is free software; you can redistribute it and/or * modify it under the terms of the GNU Lesser General Public * License as published by the Free Software Foundation; either * version 2.1 of the License, or (at your option) any later version. * * This library is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * Lesser General Public License for more details. * * You should have received a copy of the GNU Lesser General Public License * along with this library; if not, see . */ #ifndef __G_UNICODE_H__ #define __G_UNICODE_H__ #if !defined (__GLIB_H_INSIDE__) && !defined (GLIB_COMPILATION) #error "Only can be included directly." #endif #include #include 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", &c) * g_print ("Read U+%04"G_GINT32_FORMAT"X", c); * ]| */ typedef guint32 gunichar; /** * gunichar2: * * A type which can hold any UTF-16 code * pointUTF-16 also has so called * surrogate pairs 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.. * * 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; /** * 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_