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 UTF-8 to UCS-4
73 * @param mb Pointer to 0-terminated UTF-8 string
74 * @return Pointer to 0-terminated UCS-4 string
76 * Not everybody's iconv supports UCS-4, and it's inconvenient to have to know
77 * our endianness, and it's easy to convert it ourselves, so we do. See also
80 uint32_t *utf82ucs4(const char *mb) {
87 error(0, "invalid UTF-8 sequence"); return 0;);
88 dynstr_ucs4_append(&d, c);
90 dynstr_ucs4_terminate(&d);
94 /** @brief Convert one UCS-4 character to UTF-8
95 * @param c Character to convert
96 * @param d Dynamic string to append UTF-8 sequence to
97 * @return 0 on success, -1 on error
99 int one_ucs42utf8(uint32_t c, struct dynstr *d) {
103 dynstr_append(d, 0xC0 | (c >> 6));
104 dynstr_append(d, 0x80 | (c & 0x3F));
105 } else if(c < 0x10000) {
106 dynstr_append(d, 0xE0 | (c >> 12));
107 dynstr_append(d, 0x80 | ((c >> 6) & 0x3F));
108 dynstr_append(d, 0x80 | (c & 0x3F));
109 } else if(c < 0x110000) {
110 dynstr_append(d, 0xF0 | (c >> 18));
111 dynstr_append(d, 0x80 | ((c >> 12) & 0x3F));
112 dynstr_append(d, 0x80 | ((c >> 6) & 0x3F));
113 dynstr_append(d, 0x80 | (c & 0x3F));
115 error(0, "invalid UCS-4 character %#"PRIx32, c);
121 /** @brief Convert UCS-4 to UTF-8
122 * @param u Pointer to 0-terminated UCS-4 string
123 * @return Pointer to 0-terminated UTF-8 string
125 * See @ref utf82ucs4().
127 char *ucs42utf8(const uint32_t *u) {
133 if(one_ucs42utf8(c, &d))
136 dynstr_terminate(&d);
140 /** @brief Convert from the local multibyte encoding to UTF-8 */
141 char *mb2utf8(const char *mb) {
142 return convert(nl_langinfo(CODESET), "UTF-8", mb, strlen(mb) + 1);
145 /** @brief Convert from UTF-8 to the local multibyte encoding */
146 char *utf82mb(const char *utf8) {
147 return convert("UTF-8", nl_langinfo(CODESET), utf8, strlen(utf8) + 1);
150 /** @brief Convert from encoding @p from to UTF-8 */
151 char *any2utf8(const char *from, const char *any) {
152 return convert(from, "UTF-8", any, strlen(any) + 1);
155 /** @brief Convert from encoding @p from to the local multibyte encoding */
156 char *any2mb(const char *from, const char *any) {
157 if(from) return convert(from, nl_langinfo(CODESET), any, strlen(any) + 1);
158 else return xstrdup(any);
161 /** @brief Convert from encoding @p from to encoding @p to */
162 char *any2any(const char *from,
165 if(from || to) return convert(from, to, any, strlen(any) + 1);
166 else return xstrdup(any);
169 /** @brief strlen workalike for UCS-4 strings
171 * We don't rely on the local @c wchar_t being UCS-4.
173 int ucs4cmp(const uint32_t *a, const uint32_t *b) {
174 while(*a && *b && *a == *b) ++a, ++b;
175 if(*a > *b) return 1;
176 else if(*a < *b) return -1;