functions/decode/utf_8.php

   1 <?php
   2 /**
   3  * decode/utf-8.php
   4  * $Id$
   5  *
   6  * Copyright (c) 2003 The SquirrelMail Project Team
   7  * Licensed under the GNU GPL. For full terms see the file COPYING.
   8  *
   9  * This file contains utf-8 decoding function that is needed to read
  10  * utf-8 encoded mails in non-utf-8 locale.
  11  *
  12  * Every decoded character consists of n bytes. First byte is octal
  13  * 300-375, other bytes - always octals 200-277.
  14  *
  15  * \a\b characters are decoded to html code octdec(a-300)*64 + octdec(b-200)
  16  * \a\b\c characters are decoded to html code octdec(a-340)*64*64 + octdec(b-200)*64 + octdec(c-200)
  17  *
  18  * decoding cycle is unfinished. please test and report problems to tokul@users.sourceforge.net
  19  *
  20  * @package squirrelmail
  21  * @subpackage decode
  22  */
  23
  24 /**
  25  * Decode utf-8 strings
  26  * @param string $string Encoded string
  27  * @return string Decoded string
  28  */
  29 function charset_decode_utf_8 ($string) {
  30   global $default_charset,$squirrelmail_language;
  31
  32     if ($squirrelmail_language == 'ja_JP')
  33         return $string;
  34
  35     /* Only do the slow convert if there are 8-bit characters */
  36     /* avoid using 0xA0 (\240) in ereg ranges. RH73 does not like that */
  37     if (! ereg("[\200-\237]", $string) and ! ereg("[\241-\377]", $string))
  38         return $string;
  39
  40     // decode three byte unicode characters
  41     $string = preg_replace("/([\340-\357])([\200-\277])([\200-\277])/e",
  42     "'&#'.((ord('\\1')-224)*4096+(ord('\\2')-128)*64+(ord('\\3')-128)).';'",
  43     $string);
  44
  45     // decode two byte unicode characters
  46     $string = preg_replace("/([\300-\337])([\200-\277])/e",
  47     "'&#'.((ord('\\1')-192)*64+(ord('\\2')-128)).';'",
  48     $string);
  49
  50     return $string;
  51 }
  52
  53 ?>