1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150
|
/* toutf8.c --- Convert strings from system locale into UTF-8.
* Copyright (C) 2002, 2003, 2004, 2005 Simon Josefsson
*
* This file is part of GNU Libidn.
*
* GNU Libidn is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* GNU Libidn is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with GNU Libidn; if not, see <http://www.gnu.org/licenses/>.
*/
#if HAVE_CONFIG_H
# include "config.h"
#endif
/* Get prototypes. */
#include "stringprep.h"
/* Get fprintf. */
#include <stdio.h>
/* Get getenv. */
#include <stdlib.h>
/* Get strlen. */
#include <string.h>
/* Get iconv_string. */
#include "iconvme.h"
#ifdef _LIBC
# define HAVE_ICONV 1
# define LOCALE_WORKS 1
#endif
#if LOCALE_WORKS
# include <langinfo.h>
# include <locale.h>
#endif
#ifdef _LIBC
# define stringprep_locale_charset() nl_langinfo (CODESET)
#else
/**
* stringprep_locale_charset - return charset used in current locale
*
* Find out current locale charset. The function respect the CHARSET
* environment variable, but typically uses nl_langinfo(CODESET) when
* it is supported. It fall back on "ASCII" if CHARSET isn't set and
* nl_langinfo isn't supported or return anything.
*
* Note that this function return the application's locale's preferred
* charset (or thread's locale's preffered charset, if your system
* support thread-specific locales). It does not return what the
* system may be using. Thus, if you receive data from external
* sources you cannot in general use this function to guess what
* charset it is encoded in. Use stringprep_convert from the external
* representation into the charset returned by this function, to have
* data in the locale encoding.
*
* Return value: Return the character set used by the current locale.
* It will never return NULL, but use "ASCII" as a fallback.
**/
const char *
stringprep_locale_charset (void)
{
const char *charset = getenv ("CHARSET"); /* flawfinder: ignore */
if (charset && *charset)
return charset;
# ifdef LOCALE_WORKS
charset = nl_langinfo (CODESET);
if (charset && *charset)
return charset;
# endif
return "ASCII";
}
#endif
/**
* stringprep_convert - encode string using new character set
* @str: input zero-terminated string.
* @to_codeset: name of destination character set.
* @from_codeset: name of origin character set, as used by @str.
*
* Convert the string from one character set to another using the
* system's iconv() function.
*
* Return value: Returns newly allocated zero-terminated string which
* is @str transcoded into to_codeset.
**/
char *
stringprep_convert (const char *str,
const char *to_codeset, const char *from_codeset)
{
#if HAVE_ICONV
return iconv_string (str, from_codeset, to_codeset);
#else
char *p;
fprintf (stderr, "libidn: warning: libiconv not installed, cannot "
"convert data to UTF-8\n");
p = malloc (strlen (str) + 1);
if (!p)
return NULL;
return strcpy (p, str);
#endif
}
/**
* stringprep_locale_to_utf8 - convert locale encoded string to UTF-8
* @str: input zero terminated string.
*
* Convert string encoded in the locale's character set into UTF-8 by
* using stringprep_convert().
*
* Return value: Returns newly allocated zero-terminated string which
* is @str transcoded into UTF-8.
**/
char *
stringprep_locale_to_utf8 (const char *str)
{
return stringprep_convert (str, "UTF-8", stringprep_locale_charset ());
}
/**
* stringprep_utf8_to_locale - encode UTF-8 string to locale encoding
* @str: input zero terminated string.
*
* Convert string encoded in UTF-8 into the locale's character set by
* using stringprep_convert().
*
* Return value: Returns newly allocated zero-terminated string which
* is @str transcoded into the locale's character set.
**/
char *
stringprep_utf8_to_locale (const char *str)
{
return stringprep_convert (str, stringprep_locale_charset (), "UTF-8");
}
|