| 1 | <?php |
| 2 | /** |
| 3 | * decode/cp10029.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 cp10029 (MacLatin2) decoding function that |
| 10 | * is needed to read cp10029 encoded mails in non-cp10029 locale. |
| 11 | * |
| 12 | * Original data taken from: |
| 13 | * ftp://ftp.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/LATIN2.TXT |
| 14 | * |
| 15 | * Name: cp10029_MacLatin2 to Unicode table |
| 16 | * Unicode version: 2.0 |
| 17 | * Table version: 2.00 |
| 18 | * Table format: Format A |
| 19 | * Date: 04/24/96 |
| 20 | * Authors: Lori Brownell <loribr@microsoft.com> |
| 21 | * K.D. Chang <a-kchang@microsoft.com> |
| 22 | * @package squirrelmail |
| 23 | * @subpackage decode |
| 24 | */ |
| 25 | |
| 26 | /** |
| 27 | * Decode cp10029 (MacLatin2) string |
| 28 | * @param string $string Encoded string |
| 29 | * @return string $string Decoded string |
| 30 | */ |
| 31 | function charset_decode_cp10029 ($string) { |
| 32 | global $default_charset; |
| 33 | |
| 34 | if (strtolower($default_charset) == 'x-mac-centraleurroman') |
| 35 | return $string; |
| 36 | |
| 37 | /* Only do the slow convert if there are 8-bit characters */ |
| 38 | /* avoid using 0xA0 (\240) in ereg ranges. RH73 does not like that */ |
| 39 | if (! ereg("[\200-\237]", $string) and ! ereg("[\241-\377]", $string) ) |
| 40 | return $string; |
| 41 | |
| 42 | $cp10029 = array( |
| 43 | "\0x80" => 'Ä', |
| 44 | "\0x81" => 'Ā', |
| 45 | "\0x82" => 'ā', |
| 46 | "\0x83" => 'É', |
| 47 | "\0x84" => 'Ą', |
| 48 | "\0x85" => 'Ö', |
| 49 | "\0x86" => 'Ü', |
| 50 | "\0x87" => 'á', |
| 51 | "\0x88" => 'ą', |
| 52 | "\0x89" => 'Č', |
| 53 | "\0x8A" => 'ä', |
| 54 | "\0x8B" => 'č', |
| 55 | "\0x8C" => 'Ć', |
| 56 | "\0x8D" => 'ć', |
| 57 | "\0x8E" => 'é', |
| 58 | "\0x8F" => 'Ź', |
| 59 | "\0x90" => 'ź', |
| 60 | "\0x91" => 'Ď', |
| 61 | "\0x92" => 'í', |
| 62 | "\0x93" => 'ď', |
| 63 | "\0x94" => 'Ē', |
| 64 | "\0x95" => 'ē', |
| 65 | "\0x96" => 'Ė', |
| 66 | "\0x97" => 'ó', |
| 67 | "\0x98" => 'ė', |
| 68 | "\0x99" => 'ô', |
| 69 | "\0x9A" => 'ö', |
| 70 | "\0x9B" => 'õ', |
| 71 | "\0x9C" => 'ú', |
| 72 | "\0x9D" => 'Ě', |
| 73 | "\0x9E" => 'ě', |
| 74 | "\0x9F" => 'ü', |
| 75 | "\0xA0" => '†', |
| 76 | "\0xA1" => '°', |
| 77 | "\0xA2" => 'Ę', |
| 78 | "\0xA3" => '£', |
| 79 | "\0xA4" => '§', |
| 80 | "\0xA5" => '•', |
| 81 | "\0xA6" => '¶', |
| 82 | "\0xA7" => 'ß', |
| 83 | "\0xA8" => '®', |
| 84 | "\0xA9" => '©', |
| 85 | "\0xAA" => '™', |
| 86 | "\0xAB" => 'ę', |
| 87 | "\0xAC" => '¨', |
| 88 | "\0xAD" => '≠', |
| 89 | "\0xAE" => 'ģ', |
| 90 | "\0xAF" => 'Į', |
| 91 | "\0xB0" => 'į', |
| 92 | "\0xB1" => 'Ī', |
| 93 | "\0xB2" => '≤', |
| 94 | "\0xB3" => '≥', |
| 95 | "\0xB4" => 'ī', |
| 96 | "\0xB5" => 'Ķ', |
| 97 | "\0xB6" => '∂', |
| 98 | "\0xB7" => '∑', |
| 99 | "\0xB8" => 'ł', |
| 100 | "\0xB9" => 'Ļ', |
| 101 | "\0xBA" => 'ļ', |
| 102 | "\0xBB" => 'Ľ', |
| 103 | "\0xBC" => 'ľ', |
| 104 | "\0xBD" => 'Ĺ', |
| 105 | "\0xBE" => 'ĺ', |
| 106 | "\0xBF" => 'Ņ', |
| 107 | "\0xC0" => 'ņ', |
| 108 | "\0xC1" => 'Ń', |
| 109 | "\0xC2" => '¬', |
| 110 | "\0xC3" => '√', |
| 111 | "\0xC4" => 'ń', |
| 112 | "\0xC5" => 'Ň', |
| 113 | "\0xC6" => '∆', |
| 114 | "\0xC7" => '«', |
| 115 | "\0xC8" => '»', |
| 116 | "\0xC9" => '…', |
| 117 | "\0xCA" => ' ', |
| 118 | "\0xCB" => 'ň', |
| 119 | "\0xCC" => 'Ő', |
| 120 | "\0xCD" => 'Õ', |
| 121 | "\0xCE" => 'ő', |
| 122 | "\0xCF" => 'Ō', |
| 123 | "\0xD0" => '–', |
| 124 | "\0xD1" => '—', |
| 125 | "\0xD2" => '“', |
| 126 | "\0xD3" => '”', |
| 127 | "\0xD4" => '‘', |
| 128 | "\0xD5" => '’', |
| 129 | "\0xD6" => '÷', |
| 130 | "\0xD7" => '◊', |
| 131 | "\0xD8" => 'ō', |
| 132 | "\0xD9" => 'Ŕ', |
| 133 | "\0xDA" => 'ŕ', |
| 134 | "\0xDB" => 'Ř', |
| 135 | "\0xDC" => '‹', |
| 136 | "\0xDD" => '›', |
| 137 | "\0xDE" => 'ř', |
| 138 | "\0xDF" => 'Ŗ', |
| 139 | "\0xE0" => 'ŗ', |
| 140 | "\0xE1" => 'Š', |
| 141 | "\0xE2" => '‚', |
| 142 | "\0xE3" => '„', |
| 143 | "\0xE4" => 'š', |
| 144 | "\0xE5" => 'Ś', |
| 145 | "\0xE6" => 'ś', |
| 146 | "\0xE7" => 'Á', |
| 147 | "\0xE8" => 'Ť', |
| 148 | "\0xE9" => 'ť', |
| 149 | "\0xEA" => 'Í', |
| 150 | "\0xEB" => 'Ž', |
| 151 | "\0xEC" => 'ž', |
| 152 | "\0xED" => 'Ū', |
| 153 | "\0xEE" => 'Ó', |
| 154 | "\0xEF" => 'Ô', |
| 155 | "\0xF0" => 'ū', |
| 156 | "\0xF1" => 'Ů', |
| 157 | "\0xF2" => 'Ú', |
| 158 | "\0xF3" => 'ů', |
| 159 | "\0xF4" => 'Ű', |
| 160 | "\0xF5" => 'ű', |
| 161 | "\0xF6" => 'Ų', |
| 162 | "\0xF7" => 'ų', |
| 163 | "\0xF8" => 'Ý', |
| 164 | "\0xF9" => 'ý', |
| 165 | "\0xFA" => 'ķ', |
| 166 | "\0xFB" => 'Ż', |
| 167 | "\0xFC" => 'Ł', |
| 168 | "\0xFD" => 'ż', |
| 169 | "\0xFE" => 'Ģ', |
| 170 | "\0xFF" => 'ˇ' |
| 171 | ); |
| 172 | |
| 173 | $string = str_replace(array_keys($cp10029), array_values($cp10029), $string); |
| 174 | |
| 175 | return $string; |
| 176 | } |
| 177 | ?> |