libidn/toutf8.c

   1 /* toutf8.c --- Convert strings from system locale into UTF-8.
   2  * Copyright (C) 2002, 2003, 2004, 2005  Simon Josefsson
   3  *
   4  * This file is part of GNU Libidn.
   5  *
   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.
  10  *
  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.
  15  *
  16  * You should have received a copy of the GNU Lesser General Public
  17  * License along with GNU Libidn; if not, see <http://www.gnu.org/licenses/>.
  18  */
  19
  20 #if HAVE_CONFIG_H
  21 # include "config.h"
  22 #endif
  23
  24 /* Get prototypes. */
  25 #include "stringprep.h"
  26
  27 /* Get fprintf. */
  28 #include <stdio.h>
  29
  30 /* Get getenv. */
  31 #include <stdlib.h>
  32
  33 /* Get strlen. */
  34 #include <string.h>
  35
  36 /* Get iconv_string. */
  37 #include "iconvme.h"
  38
  39 #ifdef _LIBC
  40 # define HAVE_ICONV 1
  41 # define LOCALE_WORKS 1
  42 #endif
  43
  44 #if LOCALE_WORKS
  45 # include <langinfo.h>
  46 # include <locale.h>
  47 #endif
  48
  49 #ifdef _LIBC
  50 # define stringprep_locale_charset() nl_langinfo (CODESET)
  51 #else
  52 /**
  53  * stringprep_locale_charset - return charset used in current locale
  54  *
  55  * Find out current locale charset.  The function respect the CHARSET
  56  * environment variable, but typically uses nl_langinfo(CODESET) when
  57  * it is supported.  It fall back on "ASCII" if CHARSET isn't set and
  58  * nl_langinfo isn't supported or return anything.
  59  *
  60  * Note that this function return the application's locale's preferred
  61  * charset (or thread's locale's preffered charset, if your system
  62  * support thread-specific locales).  It does not return what the
  63  * system may be using.  Thus, if you receive data from external
  64  * sources you cannot in general use this function to guess what
  65  * charset it is encoded in.  Use stringprep_convert from the external
  66  * representation into the charset returned by this function, to have
  67  * data in the locale encoding.
  68  *
  69  * Return value: Return the character set used by the current locale.
  70  *   It will never return NULL, but use "ASCII" as a fallback.
  71  **/
  72 const char *
  73 stringprep_locale_charset (void)
  74 {
  75   const char *charset = getenv ("CHARSET");     /* flawfinder: ignore */
  76
  77   if (charset && *charset)
  78     return charset;
  79
  80 # ifdef LOCALE_WORKS
  81   charset = nl_langinfo (CODESET);
  82
  83   if (charset && *charset)
  84     return charset;
  85 # endif
  86
  87   return "ASCII";
  88 }
  89 #endif
  90
  91 /**
  92  * stringprep_convert - encode string using new character set
  93  * @str: input zero-terminated string.
  94  * @to_codeset: name of destination character set.
  95  * @from_codeset: name of origin character set, as used by @str.
  96  *
  97  * Convert the string from one character set to another using the
  98  * system's iconv() function.
  99  *
 100  * Return value: Returns newly allocated zero-terminated string which
 101  *   is @str transcoded into to_codeset.
 102  **/
 103 char *
 104 stringprep_convert (const char *str,
 105                     const char *to_codeset, const char *from_codeset)
 106 {
 107 #if HAVE_ICONV
 108   return iconv_string (str, from_codeset, to_codeset);
 109 #else
 110   char *p;
 111   fprintf (stderr, "libidn: warning: libiconv not installed, cannot "
 112            "convert data to UTF-8\n");
 113   p = malloc (strlen (str) + 1);
 114   if (!p)
 115     return NULL;
 116   return strcpy (p, str);
 117 #endif
 118 }
 119
 120 /**
 121  * stringprep_locale_to_utf8 - convert locale encoded string to UTF-8
 122  * @str: input zero terminated string.
 123  *
 124  * Convert string encoded in the locale's character set into UTF-8 by
 125  * using stringprep_convert().
 126  *
 127  * Return value: Returns newly allocated zero-terminated string which
 128  *   is @str transcoded into UTF-8.
 129  **/
 130 char *
 131 stringprep_locale_to_utf8 (const char *str)
 132 {
 133   return stringprep_convert (str, "UTF-8", stringprep_locale_charset ());
 134 }
 135
 136 /**
 137  * stringprep_utf8_to_locale - encode UTF-8 string to locale encoding
 138  * @str: input zero terminated string.
 139  *
 140  * Convert string encoded in UTF-8 into the locale's character set by
 141  * using stringprep_convert().
 142  *
 143  * Return value: Returns newly allocated zero-terminated string which
 144  *   is @str transcoded into the locale's character set.
 145  **/
 146 char *
 147 stringprep_utf8_to_locale (const char *str)
 148 {
 149   return stringprep_convert (str, stringprep_locale_charset (), "UTF-8");
 150 }