2 * This file is part of DisOrder.
3 * Copyright (C) 2004, 2005 Richard Kettlewell
5 * This program is free software; you can redistribute it and/or modify
6 * it under the terms of the GNU General Public License as published by
7 * the Free Software Foundation; either version 2 of the License, or
8 * (at your option) any later version.
10 * This program is distributed in the hope that it will be useful, but
11 * WITHOUT ANY WARRANTY; without even the implied warranty of
12 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
13 * General Public License for more details.
15 * You should have received a copy of the GNU General Public License
16 * along with this program; if not, write to the Free Software
17 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
20 /** @file lib/charset.c @brief Character set conversion */
33 #include "configuration.h"
37 /** @brief Low-level converstion routine
38 * @param from Source encoding
39 * @param to Destination encoding
40 * @param ptr First byte to convert
41 * @param n Number of bytes to convert
42 * @return Converted text, 0-terminated; or NULL on error.
44 static void *convert(const char *from
, const char *to
,
45 const void *ptr
, size_t n
) {
48 char *buf
= 0, *s
, *d
;
49 size_t bufsize
= 0, sl
, dl
;
51 if((i
= iconv_open(to
, from
)) == (iconv_t
)-1)
52 fatal(errno
, "error calling iconv_open");
54 bufsize
= bufsize ?
2 * bufsize
: 32;
55 buf
= xrealloc_noptr(buf
, bufsize
);
61 /* (void *) to work around FreeBSD's nonstandard iconv prototype */
62 len
= iconv(i
, (void *)&s
, &sl
, &d
, &dl
);
63 } while(len
== (size_t)-1 && errno
== E2BIG
);
65 if(len
== (size_t)-1) {
66 error(errno
, "error converting from %s to %s", from
, to
);
72 /** @brief Convert from the local multibyte encoding to UTF-8 */
73 char *mb2utf8(const char *mb
) {
74 return convert(nl_langinfo(CODESET
), "UTF-8", mb
, strlen(mb
) + 1);
77 /** @brief Convert from UTF-8 to the local multibyte encoding */
78 char *utf82mb(const char *utf8
) {
79 return convert("UTF-8", nl_langinfo(CODESET
), utf8
, strlen(utf8
) + 1);
82 /** @brief Convert from encoding @p from to UTF-8 */
83 char *any2utf8(const char *from
, const char *any
) {
84 return convert(from
, "UTF-8", any
, strlen(any
) + 1);
87 /** @brief Convert from encoding @p from to the local multibyte encoding */
88 char *any2mb(const char *from
, const char *any
) {
89 if(from
) return convert(from
, nl_langinfo(CODESET
), any
, strlen(any
) + 1);
90 else return xstrdup(any
);
93 /** @brief Convert from encoding @p from to encoding @p to */
94 char *any2any(const char *from
,
97 if(from
|| to
) return convert(from
, to
, any
, strlen(any
) + 1);
98 else return xstrdup(any
);
101 /** @brief Truncate a string for display purposes
102 * @param s Pointer to UTF-8 string
103 * @param max Maximum number of columns
104 * @return @p or truncated string (never NULL)
106 * Returns a string that is no longer than @p max graphemes long and is either
107 * (canonically) equal to @p s or is a truncated form of it with an ellipsis
110 * We don't take display width into account (tricky for HTML!) and we don't
111 * attempt to implement the Bidi algorithm. If you have track names for which
112 * either of these matter in practice then get in touch.
114 const char *truncate_for_display(const char *s
, long max
) {
119 /* Convert to UTF-32 for processing */
120 if(!(s32
= utf8_to_utf32(s
, strlen(s
), &l32
)))
122 it
= utf32_iterator_new(s32
, l32
);
124 while(max
&& utf32_iterator_where(it
) < l32
) {
125 utf32_iterator_advance(it
, 1);
126 if(utf32_iterator_grapheme_boundary(it
))
129 cut
= utf32_iterator_where(it
);
131 if(max
== 0) { /* we need to cut */
132 s32
[cut
] = 0x2026; /* HORIZONTAL ELLIPSIS */
134 s
= utf32_to_utf8(s32
, l32
, 0);