1 /* gunicode.h - Unicode manipulation functions
3 * Copyright (C) 1999, 2000 Tom Tromey
4 * Copyright 2000 Red Hat, Inc.
6 * The Gnome Library is free software; you can redistribute it and/or
7 * modify it under the terms of the GNU Lesser General Public License as
8 * published by the Free Software Foundation; either version 2 of the
9 * License, or (at your option) any later version.
11 * The Gnome Library is distributed in the hope that it will be useful,
12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
14 * Lesser General Public License for more details.
16 * You should have received a copy of the GNU Lesser General Public
17 * License along with the Gnome Library; see the file COPYING.LIB. If not,
18 * write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
19 * Boston, MA 02111-1307, USA.
22 #ifndef __G_UNICODE_H__
23 #define __G_UNICODE_H__
25 #include <stddef.h> /* For size_t */
30 typedef guint32 gunichar;
31 typedef guint16 gunichar2;
33 /* These are the possible character classifications. */
38 G_UNICODE_PRIVATE_USE,
40 G_UNICODE_LOWERCASE_LETTER,
41 G_UNICODE_MODIFIER_LETTER,
42 G_UNICODE_OTHER_LETTER,
43 G_UNICODE_TITLECASE_LETTER,
44 G_UNICODE_UPPERCASE_LETTER,
45 G_UNICODE_COMBINING_MARK,
46 G_UNICODE_ENCLOSING_MARK,
47 G_UNICODE_NON_SPACING_MARK,
48 G_UNICODE_DECIMAL_NUMBER,
49 G_UNICODE_LETTER_NUMBER,
50 G_UNICODE_OTHER_NUMBER,
51 G_UNICODE_CONNECT_PUNCTUATION,
52 G_UNICODE_DASH_PUNCTUATION,
53 G_UNICODE_CLOSE_PUNCTUATION,
54 G_UNICODE_FINAL_PUNCTUATION,
55 G_UNICODE_INITIAL_PUNCTUATION,
56 G_UNICODE_OTHER_PUNCTUATION,
57 G_UNICODE_OPEN_PUNCTUATION,
58 G_UNICODE_CURRENCY_SYMBOL,
59 G_UNICODE_MODIFIER_SYMBOL,
60 G_UNICODE_MATH_SYMBOL,
61 G_UNICODE_OTHER_SYMBOL,
62 G_UNICODE_LINE_SEPARATOR,
63 G_UNICODE_PARAGRAPH_SEPARATOR,
64 G_UNICODE_SPACE_SEPARATOR
67 /* Returns TRUE if current locale uses UTF-8 charset. If CHARSET is
68 * not null, sets *CHARSET to the name of the current locale's
69 * charset. This value is statically allocated.
71 gboolean g_get_charset (char **charset);
73 /* These are all analogs of the <ctype.h> functions.
75 gboolean g_unichar_isalnum (gunichar c) G_GNUC_CONST;
76 gboolean g_unichar_isalpha (gunichar c) G_GNUC_CONST;
77 gboolean g_unichar_iscntrl (gunichar c) G_GNUC_CONST;
78 gboolean g_unichar_isdigit (gunichar c) G_GNUC_CONST;
79 gboolean g_unichar_isgraph (gunichar c) G_GNUC_CONST;
80 gboolean g_unichar_islower (gunichar c) G_GNUC_CONST;
81 gboolean g_unichar_isprint (gunichar c) G_GNUC_CONST;
82 gboolean g_unichar_ispunct (gunichar c) G_GNUC_CONST;
83 gboolean g_unichar_isspace (gunichar c) G_GNUC_CONST;
84 gboolean g_unichar_isupper (gunichar c) G_GNUC_CONST;
85 gboolean g_unichar_isxdigit (gunichar c) G_GNUC_CONST;
86 gboolean g_unichar_istitle (gunichar c) G_GNUC_CONST;
87 gboolean g_unichar_isdefined (gunichar c) G_GNUC_CONST;
88 gboolean g_unichar_iswide (gunichar c) G_GNUC_CONST;
90 /* More <ctype.h> functions. These convert between the three cases.
91 * See the Unicode book to understand title case. */
92 gunichar g_unichar_toupper (gunichar c) G_GNUC_CONST;
93 gunichar g_unichar_tolower (gunichar c) G_GNUC_CONST;
94 gunichar g_unichar_totitle (gunichar c) G_GNUC_CONST;
96 /* If C is a digit (according to `g_unichar_isdigit'), then return its
97 numeric value. Otherwise return -1. */
98 gint g_unichar_digit_value (gunichar c) G_GNUC_CONST;
100 gint g_unichar_xdigit_value (gunichar c) G_GNUC_CONST;
102 /* Return the Unicode character type of a given character. */
103 GUnicodeType g_unichar_type (gunichar c) G_GNUC_CONST;
107 /* Compute canonical ordering of a string in-place. This rearranges
108 decomposed characters in the string according to their combining
109 classes. See the Unicode manual for more information. */
110 void g_unicode_canonical_ordering (gunichar *string,
113 /* Compute canonical decomposition of a character. Returns g_malloc()d
114 string of Unicode characters. RESULT_LEN is set to the resulting
115 length of the string. */
116 gunichar *g_unicode_canonical_decomposition (gunichar ch,
119 /* Array of skip-bytes-per-initial character.
120 * We prefix variable declarations so they can
121 * properly get exported in windows dlls.
125 # ifdef GLIB_COMPILATION
126 # define GLIB_VAR __declspec(dllexport)
127 # else /* !GLIB_COMPILATION */
128 # define GLIB_VAR extern __declspec(dllimport)
129 # endif /* !GLIB_COMPILATION */
130 # else /* !G_OS_WIN32 */
131 # define GLIB_VAR extern
132 # endif /* !G_OS_WIN32 */
133 #endif /* !GLIB_VAR */
135 GLIB_VAR char g_utf8_skip[256];
137 #define g_utf8_next_char(p) (char *)((p) + g_utf8_skip[*(guchar *)(p)])
139 gunichar g_utf8_get_char (const gchar *p);
140 gchar * g_utf8_offset_to_pointer (const gchar *str,
142 gint g_utf8_pointer_to_offset (const gchar *str,
144 gchar * g_utf8_prev_char (const gchar *p);
145 gchar * g_utf8_find_next_char (const gchar *p,
147 gchar * g_utf8_find_prev_char (const gchar *str,
150 gint g_utf8_strlen (const gchar *p,
153 /* Copies n characters from src to dest */
154 gchar *g_utf8_strncpy (gchar *dest,
158 /* Find the UTF-8 character corresponding to ch, in string p. These
159 functions are equivalants to strchr and strrchr */
161 gchar *g_utf8_strchr (const gchar *p,
163 gchar *g_utf8_strrchr (const gchar *p,
166 gunichar2 *g_utf8_to_utf16 (const gchar *str,
168 gunichar * g_utf8_to_ucs4 (const gchar *str,
170 gunichar * g_utf16_to_ucs4 (const gunichar2 *str,
172 gchar * g_utf16_to_utf8 (const gunichar2 *str,
174 gunichar * g_ucs4_to_utf16 (const gunichar *str,
176 gchar * g_ucs4_to_utf8 (const gunichar *str,
179 /* Convert a single character into UTF-8. outbuf must have at
180 * least 6 bytes of space. Returns the number of bytes in the
183 gint g_unichar_to_utf8 (gunichar c,
186 /* Validate a UTF8 string, return TRUE if valid, put pointer to
187 * first invalid char in **end
190 gboolean g_utf8_validate (const gchar *str,
196 #endif /* __G_UNICODE_H__ */