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 * Return value: Return the character set used by the system locale.
66 * It will never return NULL, but use "ASCII" as a fallback.
69 stringprep_locale_charset (void)
71 if (!stringprep_locale_charset_cache
)
72 stringprep_locale_charset_cache
= stringprep_locale_charset_slow ();
74 return stringprep_locale_charset_cache
;
79 * @str: input zero-terminated string.
80 * @to_codeset: name of destination character set.
81 * @from_codeset: name of origin character set, as used by @str.
83 * Convert the string from one character set to another using the
84 * system's iconv() function.
86 * Return value: Returns newly allocated zero-terminated string which
87 * is @str transcoded into to_codeset.
90 stringprep_convert (const char *str
,
91 const char *to_codeset
, const char *from_codeset
)
97 size_t inbytes_remaining
;
98 size_t outbytes_remaining
;
104 if (strcmp (to_codeset
, from_codeset
) == 0)
105 return (char *) strdup (str
);
107 cd
= iconv_open (to_codeset
, from_codeset
);
109 if (cd
== (iconv_t
) - 1)
112 p
= (char *) strdup (str
);
117 inbytes_remaining
= len
;
118 outbuf_size
= len
+ 1; /* + 1 for nul in case len == 1 */
120 outbytes_remaining
= outbuf_size
- 1; /* -1 for nul */
121 outp
= dest
= malloc (outbuf_size
);
125 err
= iconv (cd
, &p
, &inbytes_remaining
, &outp
, &outbytes_remaining
);
127 if (err
== (size_t) - 1)
132 /* Incomplete text, do not report an error */
137 size_t used
= outp
- dest
;
140 dest
= realloc (dest
, outbuf_size
);
143 outbytes_remaining
= outbuf_size
- used
- 1; /* -1 for nul */
161 if ((p
- startp
) != len
)
181 stringprep_locale_charset ()
187 stringprep_convert (const char *str
,
188 const char *to_codeset
, const char *from_codeset
)
191 "warning: cannot convert data to UTF-8, returning source\n");
192 fprintf (stderr
, "warning: this indicate a badly installed GNU Libidn\n");
199 * stringprep_locale_to_utf8:
200 * @str: input zero terminated string.
202 * Convert string encoded in the locale's character set into UTF-8 by
203 * using stringprep_convert().
205 * Return value: Returns newly allocated zero-terminated string which
206 * is @str transcoded into UTF-8.
209 stringprep_locale_to_utf8 (const char *str
)
211 return stringprep_convert (str
, "UTF-8", stringprep_locale_charset ());
215 * stringprep_utf8_to_locale:
216 * @str: input zero terminated string.
218 * Convert string encoded in UTF-8 into the locale's character set by
219 * using stringprep_convert().
221 * Return value: Returns newly allocated zero-terminated string which
222 * is @str transcoded into the locale's character set.
225 stringprep_utf8_to_locale (const char *str
)
227 return stringprep_convert (str
, stringprep_locale_charset (), "UTF-8");