1 /* toutf8.c Convert strings from system locale into UTF-8.
2 * Copyright (C) 2002, 2003 Simon Josefsson
4 * This file is part of GNU Libidn.
6 * GNU Libidn is free software; you can redistribute it and/or
7 * modify it under the terms of the GNU Lesser General Public
8 * License as published by the Free Software Foundation; either
9 * version 2.1 of the License, or (at your option) any later version.
11 * GNU Libidn 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 GNU Libidn; if not, write to the Free Software
18 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
34 stringprep_locale_charset_slow (void)
36 const char *charset
= getenv ("CHARSET"); /* flawfinder: ignore */
38 if (charset
&& *charset
)
45 p
= setlocale (LC_CTYPE
, NULL
);
46 setlocale (LC_CTYPE
, "");
48 charset
= nl_langinfo (CODESET
);
50 setlocale (LC_CTYPE
, p
);
52 if (charset
&& *charset
)
60 static const char *stringprep_locale_charset_cache
= NULL
;
63 * stringprep_locale_charset:
65 * Find out system locale charset.
67 * Note that this function return what it believe the SYSTEM is using
68 * as a locale, not what locale the program is currently in (modified,
69 * e.g., by a setlocale(LC_CTYPE, "ISO-8859-1")). The reason is that
70 * data read from argv[], stdin etc comes from the system, and is more
71 * likely to be encoded using the system locale than the program
74 * You can set the environment variable CHARSET to override the value
75 * returned. Note that this function caches the result, so you will
76 * have to modify CHARSET before calling (even indirectly) any
77 * stringprep functions, e.g., by setting it when invoking the
80 * Return value: Return the character set used by the system locale.
81 * It will never return NULL, but use "ASCII" as a fallback.
84 stringprep_locale_charset (void)
86 if (!stringprep_locale_charset_cache
)
87 stringprep_locale_charset_cache
= stringprep_locale_charset_slow ();
89 return stringprep_locale_charset_cache
;
94 * @str: input zero-terminated string.
95 * @to_codeset: name of destination character set.
96 * @from_codeset: name of origin character set, as used by @str.
98 * Convert the string from one character set to another using the
99 * system's iconv() function.
101 * Return value: Returns newly allocated zero-terminated string which
102 * is @str transcoded into to_codeset.
105 stringprep_convert (const char *str
,
106 const char *to_codeset
, const char *from_codeset
)
112 size_t inbytes_remaining
;
113 size_t outbytes_remaining
;
119 if (strcmp (to_codeset
, from_codeset
) == 0)
122 p
= malloc (strlen (str
) + 1);
129 cd
= iconv_open (to_codeset
, from_codeset
);
131 if (cd
== (iconv_t
) - 1)
134 p
= (char *) malloc (strlen (str
) + 1);
140 inbytes_remaining
= len
;
141 outbuf_size
= len
+ 1; /* + 1 for nul in case len == 1 */
143 outbytes_remaining
= outbuf_size
- 1; /* -1 for nul */
144 outp
= dest
= malloc (outbuf_size
);
148 err
= iconv (cd
, (ICONV_CONST
char **) &p
, &inbytes_remaining
,
149 &outp
, &outbytes_remaining
);
151 if (err
== (size_t) - 1)
156 /* Incomplete text, do not report an error */
161 size_t used
= outp
- dest
;
164 dest
= realloc (dest
, outbuf_size
);
167 outbytes_remaining
= outbuf_size
- used
- 1; /* -1 for nul */
185 if ((p
- startp
) != len
)
205 stringprep_locale_charset ()
211 stringprep_convert (const char *str
,
212 const char *to_codeset
, const char *from_codeset
)
215 fprintf (stderr
, "libidn: warning: libiconv not installed, cannot "
216 "convert data to UTF-8\n");
217 p
= malloc (strlen (str
) + 1);
227 * stringprep_locale_to_utf8:
228 * @str: input zero terminated string.
230 * Convert string encoded in the locale's character set into UTF-8 by
231 * using stringprep_convert().
233 * Return value: Returns newly allocated zero-terminated string which
234 * is @str transcoded into UTF-8.
237 stringprep_locale_to_utf8 (const char *str
)
239 return stringprep_convert (str
, "UTF-8", stringprep_locale_charset ());
243 * stringprep_utf8_to_locale:
244 * @str: input zero terminated string.
246 * Convert string encoded in UTF-8 into the locale's character set by
247 * using stringprep_convert().
249 * Return value: Returns newly allocated zero-terminated string which
250 * is @str transcoded into the locale's character set.
253 stringprep_utf8_to_locale (const char *str
)
255 return stringprep_convert (str
, stringprep_locale_charset (), "UTF-8");