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 Library 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 * Library General Public License for more details.
16 * You should have received a copy of the GNU Library 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 __GUNICODE_H__
23 #define __GUNICODE_H__
25 #include <stdlib.h> /* For size_t */
32 typedef guint32 gunichar
;
33 typedef guint16 gunichar2
;
35 /* These are the possible character classifications. */
40 G_UNICODE_PRIVATE_USE
,
42 G_UNICODE_LOWERCASE_LETTER
,
43 G_UNICODE_MODIFIER_LETTER
,
44 G_UNICODE_OTHER_LETTER
,
45 G_UNICODE_TITLECASE_LETTER
,
46 G_UNICODE_UPPERCASE_LETTER
,
47 G_UNICODE_COMBINING_MARK
,
48 G_UNICODE_ENCLOSING_MARK
,
49 G_UNICODE_NON_SPACING_MARK
,
50 G_UNICODE_DECIMAL_NUMBER
,
51 G_UNICODE_LETTER_NUMBER
,
52 G_UNICODE_OTHER_NUMBER
,
53 G_UNICODE_CONNECT_PUNCTUATION
,
54 G_UNICODE_DASH_PUNCTUATION
,
55 G_UNICODE_CLOSE_PUNCTUATION
,
56 G_UNICODE_FINAL_PUNCTUATION
,
57 G_UNICODE_INITIAL_PUNCTUATION
,
58 G_UNICODE_OTHER_PUNCTUATION
,
59 G_UNICODE_OPEN_PUNCTUATION
,
60 G_UNICODE_CURRENCY_SYMBOL
,
61 G_UNICODE_MODIFIER_SYMBOL
,
62 G_UNICODE_MATH_SYMBOL
,
63 G_UNICODE_OTHER_SYMBOL
,
64 G_UNICODE_LINE_SEPARATOR
,
65 G_UNICODE_PARAGRAPH_SEPARATOR
,
66 G_UNICODE_SPACE_SEPARATOR
69 /* Returns TRUE if current locale uses UTF-8 charset. If CHARSET is
70 * not null, sets *CHARSET to the name of the current locale's
71 * charset. This value is statically allocated.
73 gboolean
g_get_charset (char **charset
);
75 /* These are all analogs of the <ctype.h> functions.
77 gboolean
g_unichar_isalnum (gunichar c
);
78 gboolean
g_unichar_isalpha (gunichar c
);
79 gboolean
g_unichar_iscntrl (gunichar c
);
80 gboolean
g_unicphar_isdigit (gunichar c
);
81 gboolean
g_unichar_isgraph (gunichar c
);
82 gboolean
g_unichar_islower (gunichar c
);
83 gboolean
g_unichar_isprint (gunichar c
);
84 gboolean
g_unichar_ispunct (gunichar c
);
85 gboolean
g_unichar_isspace (gunichar c
);
86 gboolean
g_unichar_isupper (gunichar c
);
87 gboolean
g_unichar_isxdigit (gunichar c
);
88 gboolean
g_unichar_istitle (gunichar c
);
89 gboolean
g_unichar_isdefined (gunichar c
);
90 gboolean
g_unichar_iswide (gunichar c
);
92 /* More <ctype.h> functions. These convert between the three cases.
93 * See the Unicode book to understand title case. */
94 gunichar
g_unichar_toupper (gunichar c
);
95 gunichar
g_unichar_tolower (gunichar c
);
96 gunichar
g_unichar_totitle (gunichar c
);
98 /* If C is a digit (according to `g_unichar_isdigit'), then return its
99 numeric value. Otherwise return -1. */
100 gint
g_unichar_digit_value (gunichar c
);
102 gint
g_unichar_xdigit_value (gunichar c
);
104 /* Return the Unicode character type of a given character. */
105 GUnicodeType
g_unichar_type (gunichar c
);
109 /* Compute canonical ordering of a string in-place. This rearranges
110 decomposed characters in the string according to their combining
111 classes. See the Unicode manual for more information. */
112 void g_unicode_canonical_ordering (gunichar
*string
,
115 /* Compute canonical decomposition of a character. Returns g_malloc()d
116 string of Unicode characters. RESULT_LEN is set to the resulting
117 length of the string. */
118 gunichar
*g_unicode_canonical_decomposition (gunichar ch
,
121 /* Array of skip-bytes-per-initial character
123 extern char g_utf8_skip
[256];
125 #define g_utf8_next_char(p) (char *)((p) + g_utf8_skip[*(guchar *)(p)])
127 gunichar
g_utf8_get_char (const gchar
*p
);
128 gchar
* g_utf8_offset_to_pointer (const gchar
*str
,
130 gint
g_utf8_pointer_to_offset (const gchar
*str
,
132 gchar
* g_utf8_prev_char (const gchar
*p
);
133 gchar
* g_utf8_find_next_char (const gchar
*p
,
135 gchar
* g_utf8_find_prev_char (const gchar
*str
,
138 gint
g_utf8_strlen (const gchar
*p
,
141 /* Copies n characters from src to dest */
142 gchar
*g_utf8_strncpy (gchar
*dest
,
146 /* Find the UTF-8 character corresponding to ch, in string p. These
147 functions are equivalants to strchr and strrchr */
149 gchar
*g_utf8_strchr (const gchar
*p
,
151 gchar
*g_utf8_strrchr (const gchar
*p
,
154 gunichar2
*g_utf8_to_utf16 (const gchar
*str
,
156 gunichar
* g_utf8_to_ucs4 (const gchar
*str
,
158 gunichar
* g_utf16_to_ucs4 (const gunichar2
*str
,
160 gchar
* g_utf16_to_utf8 (const gunichar2
*str
,
162 gunichar
* g_ucs4_to_utf16 (const gunichar
*str
,
164 gchar
* g_ucs4_to_utf8 (const gunichar
*str
,
167 /* Convert a single character into UTF-8. outbuf must have at
168 * least 6 bytes of space. Returns the number of bytes in the
171 gint
g_unichar_to_utf8 (gunichar c
,
178 #endif /* GUNICODE_H */