X-Git-Url: https://vcs.fsf.org/?p=squirrelmail.git;a=blobdiff_plain;f=functions%2Fi18n.php;h=061ad1ef9890b55f1337862e68cbbd1421c7dd2e;hp=f7ad4658d76398f62a3e47766275cefbc4c8baec;hb=c48a8ca7d6f39d2a109da30fa6ea861dffdb1023;hpb=3714db455146001df65467fe7694f17963bee117 diff --git a/functions/i18n.php b/functions/i18n.php index f7ad4658..061ad1ef 100644 --- a/functions/i18n.php +++ b/functions/i18n.php @@ -3,7 +3,7 @@ /** * i18n.php * - * Copyright (c) 1999-2002 The SquirrelMail Project Team + * Copyright (c) 1999-2003 The SquirrelMail Project Team * Licensed under the GNU GPL. For full terms see the file COPYING. * * This file contains variuos functions that are needed to do @@ -15,6 +15,8 @@ * $Id$ */ +require_once(SM_PATH . 'functions/global.php'); + /* Decodes a string to the internal encoding from the given charset */ function charset_decode ($charset, $string) { global $languages, $squirrelmail_language; @@ -25,17 +27,28 @@ function charset_decode ($charset, $string) { } /* All HTML special characters are 7 bit and can be replaced first */ + $string = htmlspecialchars ($string); $charset = strtolower($charset); + set_my_charset() ; + if (ereg('iso-8859-([[:digit:]]+)', $charset, $res)) { if ($res[1] == '1') { $ret = charset_decode_iso_8859_1 ($string); } else if ($res[1] == '2') { $ret = charset_decode_iso_8859_2 ($string); + } else if ($res[1] == '4') { + $ret = charset_decode_iso_8859_4 ($string); + } else if ($res[1] == '5') { + $ret = charset_decode_iso_8859_5 ($string); } else if ($res[1] == '7') { $ret = charset_decode_iso_8859_7 ($string); + } else if ($res[1] == '9') { + $ret = charset_decode_iso_8859_9 ($string); + } else if ($res[1] == '13') { + $ret = charset_decode_iso_8859_13 ($string); } else if ($res[1] == '15') { $ret = charset_decode_iso_8859_15 ($string); } else { @@ -45,8 +58,22 @@ function charset_decode ($charset, $string) { $ret = charset_decode_ns_4551_1 ($string); } else if ($charset == 'koi8-r') { $ret = charset_decode_koi8r ($string); + } else if ($charset == 'koi8-u') { + $ret = charset_decode_koi8u ($string); } else if ($charset == 'windows-1251') { - $ret = charset_decode_koi8r ($string); + $ret = charset_decode_windows_1251 ($string); + } else if ($charset == 'windows-1253') { + $ret = charset_decode_windows_1253 ($string); + } else if ($charset == 'windows-1254') { + $ret = charset_decode_windows_1254 ($string); + } else if ($charset == 'windows-1255') { + $ret = charset_decode_windows_1255 ($string); + } else if ($charset == 'windows-1256') { + $ret = charset_decode_windows_1256 ($string); + } else if ($charset == 'windows-1257') { + $ret = charset_decode_windows_1257 ($string); + } else if ($charset == 'utf-8') { + $ret = charset_decode_utf8 ($string); } else { $ret = $string; } @@ -403,6 +430,109 @@ function charset_decode_iso_8859_2 ($string) { return $string; } +/* + ISO/IEC 8859-4:1998 Latin Alphabet No. 4 +*/ + +function charset_decode_iso_8859_4 ($string) { + global $default_charset; + + if (strtolower($default_charset) == 'iso-8859-4') + return $string; + + /* Only do the slow convert if there are 8-bit characters */ + if (! ereg("[\200-\377]", $string)) + return $string; + + $string = str_replace ("\241", 'Ą', $string); + $string = str_replace ("\242", 'ĸ', $string); + $string = str_replace ("\243", 'Ŗ', $string); + $string = str_replace ("\245", 'Ĩ', $string); + $string = str_replace ("\246", 'Ļ', $string); + $string = str_replace ("\251", 'Š', $string); + $string = str_replace ("\252", 'Ē', $string); + $string = str_replace ("\253", 'Ģ', $string); + $string = str_replace ("\254", 'Ŧ', $string); + $string = str_replace ("\256", 'Ž', $string); + $string = str_replace ("\261", 'ą', $string); + $string = str_replace ("\262", '˛', $string); + $string = str_replace ("\263", 'ŗ', $string); + $string = str_replace ("\265", 'ĩ', $string); + $string = str_replace ("\266", 'ļ', $string); + $string = str_replace ("\267", 'ˇ', $string); + $string = str_replace ("\271", 'š', $string); + $string = str_replace ("\272", 'ē', $string); + $string = str_replace ("\273", 'ģ', $string); + $string = str_replace ("\274", 'ŧ', $string); + $string = str_replace ("\275", 'Ŋ', $string); + $string = str_replace ("\276", 'ž', $string); + $string = str_replace ("\277", 'ŋ', $string); + $string = str_replace ("\300", 'Ā', $string); + $string = str_replace ("\307", 'Į', $string); + $string = str_replace ("\310", 'Č', $string); + $string = str_replace ("\312", 'Ę', $string); + $string = str_replace ("\314", 'Ė', $string); + $string = str_replace ("\317", 'Ī', $string); + $string = str_replace ("\320", 'Đ', $string); + $string = str_replace ("\321", 'Ņ', $string); + $string = str_replace ("\322", 'Ō', $string); + $string = str_replace ("\323", 'Ķ', $string); + $string = str_replace ("\331", 'Ų', $string); + $string = str_replace ("\335", 'Ũ', $string); + $string = str_replace ("\336", 'Ū', $string); + $string = str_replace ("\340", 'ā', $string); + $string = str_replace ("\347", 'į', $string); + $string = str_replace ("\350", 'č', $string); + $string = str_replace ("\352", 'ę', $string); + $string = str_replace ("\354", 'ė', $string); + $string = str_replace ("\357", 'ī', $string); + $string = str_replace ("\360", 'đ', $string); + $string = str_replace ("\361", 'ņ', $string); + $string = str_replace ("\362", 'ō', $string); + $string = str_replace ("\363", 'ķ', $string); + $string = str_replace ("\371", 'ų', $string); + $string = str_replace ("\375", 'ũ', $string); + $string = str_replace ("\376", 'ū', $string); + $string = str_replace ("\377", '˙', $string); + + // rest of charset is the same as ISO-8859-1 + return (charset_decode_iso_8859_1($string)); +} + +/* ISO-8859-5 is Cyrillic */ +function charset_decode_iso_8859_5 ($string) { + global $default_charset; + + if (strtolower($default_charset) == 'iso-8859-5') { + return $string; + } + + /* Only do the slow convert if there are 8-bit characters */ + if (! ereg("[\200-\377]", $string)) + return $string; + + // NO-BREAK SPACE + $string = str_replace("\240", ' ', $string); + // 161-172 -> 1025-1036 (+864) + $string = preg_replace("/([\241-\254])/e","'&#' . (ord('\\1')+864) . ';'",$string); + // SOFT HYPHEN + $string = str_replace("\255", '­', $string); + // 174-239 -> 1038-1103 (+864) + $string = preg_replace("/([\256-\357])/e","'&#' . (ord('\\1')+864) . ';'",$string); + // NUMERO SIGN + $string = str_replace("\360", '№', $string); + // 241-252 -> 1105-1116 (+864) + $string = preg_replace("/([\361-\374])/e","'&#' . (ord('\\1')+864) . ';'",$string); + // SECTION SIGN + $string = str_replace("\375", '§', $string); + // CYRILLIC SMALL LETTER SHORT U (Byelorussian) + $string = str_replace("\376", 'ў', $string); + // CYRILLIC SMALL LETTER DZHE + $string = str_replace("\377", 'џ', $string); + + return $string; +} + /* iso-8859-7 is Greek. */ function charset_decode_iso_8859_7 ($string) { global $default_charset; @@ -441,7 +571,7 @@ function charset_decode_iso_8859_7 ($string) { * ISO-8859-7 characters from 11/04 (0xB4) to 11/06 (0xB6) * These are Unicode 900-902 */ - $string = preg_replace("/([\264-\266])/","'&#' . (ord(\\1)+720)",$string); + $string = preg_replace("/([\264-\266])/e","'&#' . (ord('\\1')+720);",$string); /* 11/07 (0xB7) Middle dot is the same in iso-8859-1 */ $string = str_replace("\267", '·', $string); @@ -450,7 +580,7 @@ function charset_decode_iso_8859_7 ($string) { * ISO-8859-7 characters from 11/08 (0xB8) to 11/10 (0xBA) * These are Unicode 900-902 */ - $string = preg_replace("/([\270-\272])/","'&#' . (ord(\\1)+720)",$string); + $string = preg_replace("/([\270-\272])/e","'&#' . (ord('\\1')+720);",$string); /* * 11/11 (0xBB) Right angle quotation mark is the same as in @@ -459,11 +589,117 @@ function charset_decode_iso_8859_7 ($string) { $string = str_replace("\273", '»', $string); /* And now the rest of the charset */ - $string = preg_replace("/([\274-\376])/","'&#' . (ord(\\1)+720)",$string); + $string = preg_replace("/([\274-\376])/e","'&#'.(ord('\\1')+720);",$string); return $string; } +/* + ISOIEC 8859-9:1999 Latin Alphabet No. 5 + +*/ +function charset_decode_iso_8859_9 ($string) { + global $default_charset; + + if (strtolower($default_charset) == 'iso-8859-9') + return $string; + + /* Only do the slow convert if there are 8-bit characters */ + if (! ereg("[\200-\377]", $string)) + return $string; + + // latin capital letter g with breve 208->286 + $string = str_replace("\320", 'Ğ', $string); + // latin capital letter i with dot above 221->304 + $string = str_replace("\335", 'İ', $string); + // latin capital letter s with cedilla 222->350 + $string = str_replace("\336", 'Ş', $string); + // latin small letter g with breve 240->287 + $string = str_replace("\360", 'ğ', $string); + // latin small letter dotless i 253->305 + $string = str_replace("\375", 'ı', $string); + // latin small letter s with cedilla 254->351 + $string = str_replace("\376", 'ş', $string); + + // rest of charset is the same as ISO-8859-1 + return (charset_decode_iso_8859_1($string)); +} + + +/* + ISO/IEC 8859-13:1998 Latin Alphabet No. 7 (Baltic Rim) +*/ +function charset_decode_iso_8859_13 ($string) { + global $default_charset; + + if (strtolower($default_charset) == 'iso-8859-13') + return $string; + + /* Only do the slow convert if there are 8-bit characters */ + if (! ereg("[\200-\377]", $string)) + return $string; + + $string = str_replace ("\241", '”', $string); + $string = str_replace ("\245", '„', $string); + $string = str_replace ("\250", 'Ø', $string); + $string = str_replace ("\252", 'Ŗ', $string); + $string = str_replace ("\257", 'Æ', $string); + $string = str_replace ("\264", '“', $string); + $string = str_replace ("\270", 'ø', $string); + $string = str_replace ("\272", 'ŗ', $string); + $string = str_replace ("\277", 'æ', $string); + $string = str_replace ("\300", 'Ą', $string); + $string = str_replace ("\301", 'Į', $string); + $string = str_replace ("\302", 'Ā', $string); + $string = str_replace ("\303", 'Ć', $string); + $string = str_replace ("\306", 'Ę', $string); + $string = str_replace ("\307", 'Ē', $string); + $string = str_replace ("\310", 'Č', $string); + $string = str_replace ("\312", 'Ź', $string); + $string = str_replace ("\313", 'Ė', $string); + $string = str_replace ("\314", 'Ģ', $string); + $string = str_replace ("\315", 'Ķ', $string); + $string = str_replace ("\316", 'Ī', $string); + $string = str_replace ("\317", 'Ļ', $string); + $string = str_replace ("\320", 'Š', $string); + $string = str_replace ("\321", 'Ń', $string); + $string = str_replace ("\322", 'Ņ', $string); + $string = str_replace ("\324", 'Ō', $string); + $string = str_replace ("\330", 'Ų', $string); + $string = str_replace ("\331", 'Ł', $string); + $string = str_replace ("\332", 'Ś', $string); + $string = str_replace ("\333", 'Ū', $string); + $string = str_replace ("\335", 'Ż', $string); + $string = str_replace ("\336", 'Ž', $string); + $string = str_replace ("\340", 'ą', $string); + $string = str_replace ("\341", 'į', $string); + $string = str_replace ("\342", 'ā', $string); + $string = str_replace ("\343", 'ć', $string); + $string = str_replace ("\346", 'ę', $string); + $string = str_replace ("\347", 'ē', $string); + $string = str_replace ("\350", 'č', $string); + $string = str_replace ("\352", 'ź', $string); + $string = str_replace ("\353", 'ė', $string); + $string = str_replace ("\354", 'ģ', $string); + $string = str_replace ("\355", 'ķ', $string); + $string = str_replace ("\356", 'ī', $string); + $string = str_replace ("\357", 'ļ', $string); + $string = str_replace ("\360", 'š', $string); + $string = str_replace ("\361", 'ń', $string); + $string = str_replace ("\362", 'ņ', $string); + $string = str_replace ("\364", 'ō', $string); + $string = str_replace ("\370", 'ų', $string); + $string = str_replace ("\371", 'ł', $string); + $string = str_replace ("\372", 'ś', $string); + $string = str_replace ("\373", 'ū', $string); + $string = str_replace ("\375", 'ż', $string); + $string = str_replace ("\376", 'ž', $string); + $string = str_replace ("\377", '’', $string); + + // rest of charset is the same as ISO-8859-1 + return (charset_decode_iso_8859_1($string)); +} + /* * iso-8859-15 is Latin 9 and has very much the same use as Latin 1 * but has the Euro symbol and some characters needed for French. @@ -489,12 +725,6 @@ function charset_decode_iso_8859_15 ($string) { return (charset_decode_iso_8859_1($string)); } -/* ISO-8859-5 is Cyrillic */ -function charset_decode_iso_8859_5 ($string) { - // Convert to KOI8-R, then return this decoded. - $string = convert_cyr_string($string, 'i', 'k'); - return charset_decode_koi8r($string); -} /* Remove all 8 bit characters from all other ISO-8859 character sets */ function charset_decode_iso_8859_default ($string) { @@ -679,60 +909,779 @@ function charset_decode_koi8r ($string) { return $string; } - /* - * Japanese charset extra function - * + * KOI8-U is used to encode Ukrainian mail (Cyrrilic). Defined in RFC + * 2319. */ -function japanese_charset_xtra() { - $ret = func_get_arg(1); /* default return value */ - if (function_exists('mb_detect_encoding')) { - switch (func_get_arg(0)) { /* action */ - case 'decode': - $detect_encoding = mb_detect_encoding($ret); - if ($detect_encoding == 'JIS' || - $detect_encoding == 'EUC-JP' || - $detect_encoding == 'SJIS') { - - $ret = mb_convert_encoding($ret, 'EUC-JP', 'AUTO'); - } - break; - case 'encode': - $detect_encoding = mb_detect_encoding($ret); - if ($detect_encoding == 'JIS' || - $detect_encoding == 'EUC-JP' || - $detect_encoding == 'SJIS') { - - $ret = mb_convert_encoding($ret, 'JIS', 'AUTO'); - } - break; - case 'strimwidth': - $width = func_get_arg(2); - $ret = mb_strimwidth($ret, 0, $width, '...'); - break; - case 'encodeheader': - $ret = mb_encode_mimeheader($ret); - break; - case 'decodeheader': - $ret = str_replace("\t", "", $ret); - if (eregi('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=', $ret)) - $ret = mb_decode_mimeheader($ret); - $ret = mb_convert_encoding($ret, 'EUC-JP', 'AUTO'); - break; - case 'downloadfilename': - $useragent = func_get_arg(2); - if (strstr($useragent, 'Windows') !== false || - strstr($useragent, 'Mac_') !== false) { - $ret = mb_convert_encoding($ret, 'SJIS', 'AUTO'); - } else { - $ret = mb_convert_encoding($ret, 'EUC-JP', 'AUTO'); +function charset_decode_koi8u ($string) { + global $default_charset; + + if (strtolower($default_charset) == 'koi8-u') { + return $string; + } + + /* Only do the slow convert if there are 8-bit characters */ + if (! ereg("[\200-\377]", $string)) + return $string; + + // BOX DRAWINGS LIGHT HORIZONTAL + $string = str_replace("\200", '─', $string); + // BOX DRAWINGS LIGHT VERTICAL + $string = str_replace("\201", '│', $string); + // BOX DRAWINGS LIGHT DOWN AND RIGHT + $string = str_replace("\202", '┌', $string); + // BOX DRAWINGS LIGHT DOWN AND LEFT + $string = str_replace("\203", '┐', $string); + // BOX DRAWINGS LIGHT UP AND RIGHT + $string = str_replace("\204", '└', $string); + // BOX DRAWINGS LIGHT UP AND LEFT + $string = str_replace("\205", '┘', $string); + // BOX DRAWINGS LIGHT VERTICAL AND RIGHT + $string = str_replace("\206", '├', $string); + // BOX DRAWINGS LIGHT VERTICAL AND LEFT + $string = str_replace("\207", '┤', $string); + // BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + $string = str_replace("\210", '┬', $string); + // BOX DRAWINGS LIGHT UP AND HORIZONTAL + $string = str_replace("\211", '┴', $string); + // BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + $string = str_replace("\212", '┼', $string); + // UPPER HALF BLOCK + $string = str_replace("\213", '▀', $string); + // LOWER HALF BLOCK + $string = str_replace("\214", '▄', $string); + // FULL BLOCK + $string = str_replace("\215", '█', $string); + // LEFT HALF BLOCK + $string = str_replace("\216", '▌', $string); + // RIGHT HALF BLOCK + $string = str_replace("\217", '▐', $string); + // LIGHT SHADE + $string = str_replace("\220", '░', $string); + // MEDIUM SHADE + $string = str_replace("\221", '▒', $string); + // DARK SHADE + $string = str_replace("\222", '▓', $string); + // TOP HALF INTEGRAL + $string = str_replace("\223", '⌠', $string); + // BLACK SQUARE + $string = str_replace("\224", '■', $string); + // BULLET OPERATOR + $string = str_replace("\225", '∙', $string); + // SQUARE ROOT + $string = str_replace("\226", '√', $string); + // ALMOST EQUAL TO + $string = str_replace("\227", '≈', $string); + // LESS THAN OR EQUAL TO + $string = str_replace("\230", '≤', $string); + // GREATER THAN OR EQUAL TO + $string = str_replace("\231", '≥', $string); + // NO-BREAK SPACE + $string = str_replace("\232", ' ', $string); + // BOTTOM HALF INTEGRAL + $string = str_replace("\233", '⌡', $string); + // DEGREE SIGN + $string = str_replace("\234", '°', $string); + // SUPERSCRIPT DIGIT TWO + $string = str_replace("\235", '²', $string); + // MIDDLE DOT + $string = str_replace("\236", '·', $string); + // DIVISION SIGN + $string = str_replace("\237", '÷', $string); + // BOX DRAWINGS DOUBLE HORIZONTAL + $string = str_replace("\240", '═', $string); + // BOX DRAWINGS DOUBLE VERTICAL + $string = str_replace("\241", '║', $string); + // BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + $string = str_replace("\242", '╒', $string); + // CYRILLIC SMALL LETTER IO + $string = str_replace("\243", 'ё', $string); + // CYRILLIC SMALL LETTER UKRAINIAN IE + $string = str_replace("\244", 'є', $string); + // BOX DRAWINGS DOUBLE DOWN AND RIGHT + $string = str_replace("\245", '╔', $string); + // CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I + $string = str_replace("\246", 'і', $string); + // CYRILLIC SMALL LETTER YI (Ukrainian) + $string = str_replace("\247", 'ї', $string); + // BOX DRAWINGS DOUBLE DOWN AND LEFT + $string = str_replace("\250", '╗', $string); + // BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + $string = str_replace("\251", '╘', $string); + // BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + $string = str_replace("\252", '╙', $string); + // BOX DRAWINGS DOUBLE UP AND RIGHT + $string = str_replace("\253", '╚', $string); + // BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + $string = str_replace("\254", '╛', $string); + // CYRILLIC SMALL LETTER GHE WITH UPTURN + $string = str_replace("\255", 'ґ', $string); + // BOX DRAWINGS DOUBLE UP AND LEFT + $string = str_replace("\256", '╝', $string); + // BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + $string = str_replace("\257", '╞', $string); + // BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + $string = str_replace("\260", '╟', $string); + // BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + $string = str_replace("\261", '╠', $string); + // BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + $string = str_replace("\262", '╡', $string); + // CYRILLIC CAPITAL LETTER IO + $string = str_replace("\263", 'Ё', $string); + // CYRILLIC CAPITAL LETTER UKRAINIAN IE + $string = str_replace("\264", 'Є', $string); + // DOUBLE VERTICAL AND LEFT + $string = str_replace("\265", '╣', $string); + // CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I + $string = str_replace("\266", 'І', $string); + // CYRILLIC CAPITAL LETTER YI (Ukrainian) + $string = str_replace("\267", 'Ї', $string); + // BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + $string = str_replace("\270", '╦', $string); + // BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + $string = str_replace("\271", '╧', $string); + // BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + $string = str_replace("\272", '╨', $string); + // BOX DRAWINGS DOUBLE UP AND HORIZONTAL + $string = str_replace("\273", '╩', $string); + // BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + $string = str_replace("\274", '╪', $string); + // CYRILLIC CAPITAL LETTER GHE WITH UPTURN + $string = str_replace("\275", 'Ґ', $string); + // BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + $string = str_replace("\276", '╬', $string); + // COPYRIGHT SIGN + $string = str_replace("\277", '©', $string); + // CYRILLIC SMALL LETTER YU + $string = str_replace("\300", 'ю', $string); + // CYRILLIC SMALL LETTER A + $string = str_replace("\301", 'а', $string); + // CYRILLIC SMALL LETTER BE + $string = str_replace("\302", 'б', $string); + // CYRILLIC SMALL LETTER TSE + $string = str_replace("\303", 'ц', $string); + // CYRILLIC SMALL LETTER DE + $string = str_replace("\304", 'д', $string); + // CYRILLIC SMALL LETTER IE + $string = str_replace("\305", 'е', $string); + // CYRILLIC SMALL LETTER EF + $string = str_replace("\306", 'ф', $string); + // CYRILLIC SMALL LETTER GHE + $string = str_replace("\307", 'г', $string); + // CYRILLIC SMALL LETTER HA + $string = str_replace("\310", 'х', $string); + // CYRILLIC SMALL LETTER I + $string = str_replace("\311", 'и', $string); + // CYRILLIC SMALL LETTER SHORT I + $string = str_replace("\312", 'й', $string); + // CYRILLIC SMALL LETTER KA + $string = str_replace("\313", 'к', $string); + // CYRILLIC SMALL LETTER EL + $string = str_replace("\314", 'л', $string); + // CYRILLIC SMALL LETTER EM + $string = str_replace("\315", 'м', $string); + // CYRILLIC SMALL LETTER EN + $string = str_replace("\316", 'н', $string); + // CYRILLIC SMALL LETTER O + $string = str_replace("\317", 'о', $string); + // CYRILLIC SMALL LETTER PE + $string = str_replace("\320", 'п', $string); + // CYRILLIC SMALL LETTER YA + $string = str_replace("\321", 'я', $string); + // CYRILLIC SMALL LETTER ER + $string = str_replace("\322", 'р', $string); + // CYRILLIC SMALL LETTER ES + $string = str_replace("\323", 'с', $string); + // CYRILLIC SMALL LETTER TE + $string = str_replace("\324", 'т', $string); + // CYRILLIC SMALL LETTER U + $string = str_replace("\325", 'у', $string); + // CYRILLIC SMALL LETTER ZHE + $string = str_replace("\326", 'ж', $string); + // CYRILLIC SMALL LETTER VE + $string = str_replace("\327", 'в', $string); + // CYRILLIC SMALL LETTER SOFT SIGN + $string = str_replace("\330", 'ь', $string); + // CYRILLIC SMALL LETTER YERU + $string = str_replace("\331", 'ы', $string); + // CYRILLIC SMALL LETTER ZE + $string = str_replace("\332", 'з', $string); + // CYRILLIC SMALL LETTER SHA + $string = str_replace("\333", 'ш', $string); + // CYRILLIC SMALL LETTER E + $string = str_replace("\334", 'э', $string); + // CYRILLIC SMALL LETTER SHCHA + $string = str_replace("\335", 'щ', $string); + // CYRILLIC SMALL LETTER CHE + $string = str_replace("\336", 'ч', $string); + // CYRILLIC SMALL LETTER HARD SIGN + $string = str_replace("\337", 'ъ', $string); + // CYRILLIC CAPITAL LETTER YU + $string = str_replace("\340", 'Ю', $string); + // CYRILLIC CAPITAL LETTER A + $string = str_replace("\341", 'А', $string); + // CYRILLIC CAPITAL LETTER BE + $string = str_replace("\342", 'Б', $string); + // CYRILLIC CAPITAL LETTER TSE + $string = str_replace("\343", 'Ц', $string); + // CYRILLIC CAPITAL LETTER DE + $string = str_replace("\344", 'Д', $string); + // CYRILLIC CAPITAL LETTER IE + $string = str_replace("\345", 'Е', $string); + // CYRILLIC CAPITAL LETTER EF + $string = str_replace("\346", 'Ф', $string); + // CYRILLIC CAPITAL LETTER GHE + $string = str_replace("\347", 'Г', $string); + // CYRILLIC CAPITAL LETTER HA + $string = str_replace("\350", 'Х', $string); + // CYRILLIC CAPITAL LETTER I + $string = str_replace("\351", 'И', $string); + // CYRILLIC CAPITAL LETTER SHORT I + $string = str_replace("\352", 'Й', $string); + // CYRILLIC CAPITAL LETTER KA + $string = str_replace("\353", 'К', $string); + // CYRILLIC CAPITAL LETTER EL + $string = str_replace("\354", 'Л', $string); + // CYRILLIC CAPITAL LETTER EM + $string = str_replace("\355", 'М', $string); + // CYRILLIC CAPITAL LETTER EN + $string = str_replace("\356", 'Н', $string); + // CYRILLIC CAPITAL LETTER O + $string = str_replace("\357", 'О', $string); + // CYRILLIC CAPITAL LETTER PE + $string = str_replace("\360", 'П', $string); + // CYRILLIC CAPITAL LETTER YA + $string = str_replace("\361", 'Я', $string); + // CYRILLIC CAPITAL LETTER ER + $string = str_replace("\362", 'Р', $string); + // CYRILLIC CAPITAL LETTER ES + $string = str_replace("\363", 'С', $string); + // CYRILLIC CAPITAL LETTER TE + $string = str_replace("\364", 'Т', $string); + // CYRILLIC CAPITAL LETTER U + $string = str_replace("\365", 'У', $string); + // CYRILLIC CAPITAL LETTER ZHE + $string = str_replace("\366", 'Ж', $string); + // CYRILLIC CAPITAL LETTER VE + $string = str_replace("\367", 'В', $string); + // CYRILLIC CAPITAL LETTER SOFT SIGN + $string = str_replace("\370", 'Ь', $string); + // CYRILLIC CAPITAL LETTER YERU + $string = str_replace("\371", 'Ы', $string); + // CYRILLIC CAPITAL LETTER ZE + $string = str_replace("\372", 'З', $string); + // CYRILLIC CAPITAL LETTER SHA + $string = str_replace("\373", 'Ш', $string); + // CYRILLIC CAPITAL LETTER E + $string = str_replace("\374", 'Э', $string); + // CYRILLIC CAPITAL LETTER SHCHA + $string = str_replace("\375", 'Щ', $string); + // CYRILLIC CAPITAL LETTER CHE + $string = str_replace("\376", 'Ч', $string); + // CYRILLIC CAPITAL LETTER HARD SIGN + $string = str_replace("\377", 'Ъ', $string); + + return $string; } - break; - default: - break; - } + +/* + * windows-1251 is used to encode Bulgarian mail (Cyrrilic). + */ +function charset_decode_windows_1251 ($string) { + global $default_charset; + + if (strtolower($default_charset) == 'windows-1251') { + return $string; } - return $ret; + + /* Only do the slow convert if there are 8-bit characters */ + if (! ereg("[\200-\377]", $string)) + return $string; + + // CYRILLIC CAPITAL LETTER DJE (Serbocroatian) + $string = str_replace("\200", 'Ђ', $string); + // CYRILLIC CAPITAL LETTER GJE + $string = str_replace("\201", 'Ѓ', $string); + // SINGLE LOW-9 QUOTATION MARK + $string = str_replace("\202", '‚', $string); + // CYRILLIC SMALL LETTER GJE + $string = str_replace("\203", 'ѓ', $string); + // DOUBLE LOW-9 QUOTATION MARK + $string = str_replace("\204", '„', $string); + // HORIZONTAL ELLIPSIS + $string = str_replace("\205", '…', $string); + // DAGGER + $string = str_replace("\206", '†', $string); + // DOUBLE DAGGER + $string = str_replace("\207", '‡', $string); + // EURO SIGN + $string = str_replace("\210", '€', $string); + // PER MILLE SIGN + $string = str_replace("\211", '‰', $string); + // CYRILLIC CAPITAL LETTER LJE + $string = str_replace("\212", 'Љ', $string); + // SINGLE LEFT-POINTING ANGLE QUOTATION MARK + $string = str_replace("\213", '‹', $string); + // CYRILLIC CAPITAL LETTER NJE + $string = str_replace("\214", 'Њ', $string); + // CYRILLIC CAPITAL LETTER KJE + $string = str_replace("\215", 'Ќ', $string); + // CYRILLIC CAPITAL LETTER TSHE (Serbocroatian) + $string = str_replace("\216", 'Ћ', $string); + // CYRILLIC CAPITAL LETTER DZHE + $string = str_replace("\217", 'Џ', $string); + // CYRILLIC SMALL LETTER DJE (Serbocroatian) + $string = str_replace("\220", 'ђ', $string); + // LEFT SINGLE QUOTATION MARK + $string = str_replace("\221", '‘', $string); + // RIGHT SINGLE QUOTATION MARK + $string = str_replace("\222", '’', $string); + // LEFT DOUBLE QUOTATION MARK + $string = str_replace("\223", '“', $string); + // RIGHT DOUBLE QUOTATION MARK + $string = str_replace("\224", '”', $string); + // BULLET + $string = str_replace("\225", '•', $string); + // EN DASH + $string = str_replace("\226", '–', $string); + // EM DASH + $string = str_replace("\227", '—', $string); + // TRADE MARK SIGN + $string = str_replace("\231", '™', $string); + // CYRILLIC SMALL LETTER LJE + $string = str_replace("\232", 'љ', $string); + // SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + $string = str_replace("\233", '›', $string); + // CYRILLIC SMALL LETTER NJE + $string = str_replace("\234", 'њ', $string); + // CYRILLIC SMALL LETTER KJE + $string = str_replace("\235", 'ќ', $string); + // CYRILLIC SMALL LETTER TSHE (Serbocroatian) + $string = str_replace("\236", 'ћ', $string); + // CYRILLIC SMALL LETTER DZHE + $string = str_replace("\237", 'џ', $string); + // NO-BREAK SPACE + $string = str_replace("\240", ' ', $string); + // CYRILLIC CAPITAL LETTER SHORT U (Byelorussian) + $string = str_replace("\241", 'Ў', $string); + // CYRILLIC SMALL LETTER SHORT U (Byelorussian) + $string = str_replace("\242", 'ў', $string); + // CYRILLIC CAPITAL LETTER JE + $string = str_replace("\243", 'Ј', $string); + // CURRENCY SIGN + $string = str_replace("\244", '¤', $string); + // CYRILLIC CAPITAL LETTER GHE WITH UPTURN + $string = str_replace("\245", 'Ґ', $string); + // BROKEN BAR + $string = str_replace("\246", '¦', $string); + // SECTION SIGN + $string = str_replace("\247", '§', $string); + // CYRILLIC CAPITAL LETTER IO + $string = str_replace("\250", 'Ё', $string); + // COPYRIGHT SIGN + $string = str_replace("\251", '©', $string); + // CYRILLIC CAPITAL LETTER UKRAINIAN IE + $string = str_replace("\252", 'Є', $string); + // LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + $string = str_replace("\253", '«', $string); + // NOT SIGN + $string = str_replace("\254", '¬', $string); + // SOFT HYPHEN + $string = str_replace("\255", '­', $string); + // REGISTERED SIGN + $string = str_replace("\256", '®', $string); + // CYRILLIC CAPITAL LETTER YI (Ukrainian) + $string = str_replace("\257", 'Ї', $string); + // DEGREE SIGN + $string = str_replace("\260", '°', $string); + // PLUS-MINUS SIGN + $string = str_replace("\261", '±', $string); + // CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I + $string = str_replace("\262", 'І', $string); + // CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I + $string = str_replace("\263", 'і', $string); + // CYRILLIC SMALL LETTER GHE WITH UPTURN + $string = str_replace("\264", 'ґ', $string); + // MICRO SIGN + $string = str_replace("\265", 'µ', $string); + // PILCROW SIGN + $string = str_replace("\266", '¶', $string); + // MIDDLE DOT + $string = str_replace("\267", '·', $string); + // CYRILLIC SMALL LETTER IO + $string = str_replace("\270", 'ё', $string); + // NUMERO SIGN + $string = str_replace("\271", '№', $string); + // CYRILLIC SMALL LETTER UKRAINIAN IE + $string = str_replace("\272", 'є', $string); + // RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + $string = str_replace("\273", '»', $string); + // CYRILLIC SMALL LETTER JE + $string = str_replace("\274", 'ј', $string); + // CYRILLIC CAPITAL LETTER DZE + $string = str_replace("\275", 'Ѕ', $string); + // CYRILLIC SMALL LETTER DZE + $string = str_replace("\276", 'ѕ', $string); + // CYRILLIC SMALL LETTER YI (Ukrainian) + $string = str_replace("\277", 'ї', $string); + + // 192-255 > 1040-1103 (+848) + $string = preg_replace("/([\300-\377])/e","'&#' . (ord('\\1')+848) . ';'",$string); + + return $string; +} + +/* + windows-1253 (Greek) + */ +function charset_decode_windows_1253 ($string) { + global $default_charset; + + if (strtolower($default_charset) == 'windows-1253') + return $string; + + /* Only do the slow convert if there are 8-bit characters */ + if (! ereg("[\200-\377]", $string)) + return $string; + + $string = str_replace("\200", '€', $string); + $string = str_replace("\202", '‚', $string); + $string = str_replace("\203", 'ƒ', $string); + $string = str_replace("\204", '„', $string); + $string = str_replace("\205", '…', $string); + $string = str_replace("\206", '†', $string); + $string = str_replace("\207", '‡', $string); + $string = str_replace("\211", '‰', $string); + $string = str_replace("\213", '‹', $string); + $string = str_replace("\221", '‘', $string); + $string = str_replace("\222", '’', $string); + $string = str_replace("\223", '“', $string); + $string = str_replace("\224", '”', $string); + $string = str_replace("\225", '•', $string); + $string = str_replace("\226", '–', $string); + $string = str_replace("\227", '—', $string); + $string = str_replace("\231", '™', $string); + $string = str_replace("\233", '›', $string); + $string = str_replace("\241", '΅', $string); + $string = str_replace("\242", 'Ά', $string); + $string = str_replace ("\257", '―', $string); + $string = str_replace("\264", '΄', $string); + $string = str_replace("\270", 'Έ', $string); + $string = str_replace ("\271", 'Ή', $string); + $string = str_replace ("\272", 'Ί', $string); + $string = str_replace ("\274", 'Ό', $string); + // cycle for 190-254 symbols + $string = preg_replace("/([\274-\376])/e","'&#' . (ord('\\1')+720);",$string); + + // Rest of charset is like iso-8859-1 + return (charset_decode_iso_8859_1($string)); +} + +/* + windows-1254 (Turks) + */ +function charset_decode_windows_1254 ($string) { + global $default_charset; + + if (strtolower($default_charset) == 'windows-1254') + return $string; + + /* Only do the slow convert if there are 8-bit characters */ + if (! ereg("[\200-\377]", $string)) + return $string; + + // Euro sign 128 -> 8364 + $string = str_replace("\200", '€', $string); + // Single low-9 quotation mark 130 -> 8218 + $string = str_replace("\202", '‚', $string); + // latin small letter f with hook 131 -> 402 + $string = str_replace("\203", 'ƒ', $string); + // Double low-9 quotation mark 132 -> 8222 + $string = str_replace("\204", '„', $string); + // horizontal ellipsis 133 -> 8230 + $string = str_replace("\205", '…', $string); + // dagger 134 -> 8224 + $string = str_replace("\206", '†', $string); + // double dagger 135 -> 8225 + $string = str_replace("\207", '‡', $string); + // modifier letter circumflex accent 136->710 + $string = str_replace("\210", 'ˆ', $string); + // per mille sign 137 -> 8240 + $string = str_replace("\211", '‰', $string); + // latin capital letter s with caron 138 -> 352 + $string = str_replace("\212", 'Š', $string); + // single left-pointing angle quotation mark 139 -> 8249 + $string = str_replace("\213", '‹', $string); + // latin capital ligature oe 140 -> 338 + $string = str_replace("\214", 'Œ', $string); + // left single quotation mark 145 -> 8216 + $string = str_replace("\221", '‘', $string); + // right single quotation mark 146 -> 8217 + $string = str_replace("\222", '’', $string); + // left double quotation mark 147 -> 8220 + $string = str_replace("\223", '“', $string); + // right double quotation mark 148 -> 8221 + $string = str_replace("\224", '”', $string); + // bullet 149 -> 8226 + $string = str_replace("\225", '•', $string); + // en dash 150 -> 8211 + $string = str_replace("\226", '–', $string); + // em dash 151 -> 8212 + $string = str_replace("\227", '—', $string); + // small tilde 152 -> 732 + $string = str_replace("\230", '˜', $string); + // trade mark sign 153 -> 8482 + $string = str_replace("\231", '™', $string); + // latin small letter s with caron 154 -> 353 + $string = str_replace("\232", 'š', $string); + // single right-pointing angle quotation mark 155 -> 8250 + $string = str_replace("\233", '›', $string); + // latin small ligature oe 156 -> 339 + $string = str_replace("\234", 'œ', $string); + // latin capital letter y with diaresis 159->376 + $string = str_replace("\237", 'Ÿ', $string); + // latin capital letter g with breve 208->286 + $string = str_replace("\320", 'Ğ', $string); + // latin capital letter i with dot above 221->304 + $string = str_replace("\335", 'İ', $string); + // latin capital letter s with cedilla 222->350 + $string = str_replace("\336", 'Ş', $string); + // latin small letter g with breve 240->287 + $string = str_replace("\360", 'ğ', $string); + // latin small letter dotless i 253->305 + $string = str_replace("\375", 'ı', $string); + // latin small letter s with cedilla 254->351 + $string = str_replace("\376", 'ş', $string); + + // Rest of charset is like iso-8859-1 + return (charset_decode_iso_8859_1($string)); +} + +/* + windows-1255 (Hebr) + */ +function charset_decode_windows_1255 ($string) { + global $default_charset; + + if (strtolower($default_charset) == 'windows-1255') + return $string; + + /* Only do the slow convert if there are 8-bit characters */ + if (! ereg("[\200-\377]", $string)) + return $string; + + $string = str_replace("\200", '€', $string); + $string = str_replace("\202", '‚', $string); + $string = str_replace("\203", 'ƒ', $string); + $string = str_replace("\204", '„', $string); + $string = str_replace("\205", '…', $string); + $string = str_replace("\206", '†', $string); + $string = str_replace("\207", '‡', $string); + $string = str_replace("\211", '‰', $string); + $string = str_replace("\213", '‹', $string); + $string = str_replace("\221", '‘', $string); + $string = str_replace("\222", '’', $string); + $string = str_replace("\223", '“', $string); + $string = str_replace("\224", '”', $string); + $string = str_replace("\225", '•', $string); + $string = str_replace("\226", '–', $string); + $string = str_replace("\227", '—', $string); + $string = str_replace("\231", '™', $string); + $string = str_replace("\233", '›', $string); + $string = str_replace("\240", ' ', $string); + // 162-169 + $string = preg_replace("/([\242-\251])/e","'&#' . ord('\\1') . ';'",$string); + $string = str_replace("\252", '×', $string); + // 171-174 + $string = preg_replace("/([\253-\256])/e","'&#' . ord('\\1') . ';'",$string); + $string = str_replace ("\257", '̍', $string); + // 176-185 + $string = preg_replace("/([\260-\271])/e","'&#' . ord('\\1') . ';'",$string); + $string = str_replace ("\272", '÷', $string); + // 187-190 + $string = preg_replace("/([\273-\276])/e","'&#' . ord('\\1') . ';'",$string); + $string = str_replace ("\337", '‗', $string); + // 224-250 1488-1514 (+1264) + $string = preg_replace("/([\340-\372])/e","'&#' . (ord('\\1')+1264) . ';'",$string); + + return ($string); +} + +/* + windows-1256 (Arab) + */ +function charset_decode_windows_1256 ($string) { + global $default_charset; + + if (strtolower($default_charset) == 'windows-1256') + return $string; + + /* Only do the slow convert if there are 8-bit characters */ + if (! ereg("[\200-\377]", $string)) + return $string; + + $string = str_replace("\200", '،', $string); + $string = str_replace("\202", '‚', $string); + $string = str_replace("\204", '„', $string); + $string = str_replace("\205", '…', $string); + $string = str_replace("\206", '†', $string); + $string = str_replace("\207", '‡', $string); + $string = str_replace("\211", '‰', $string); + $string = str_replace("\213", '‹', $string); + $string = str_replace("\221", '‘', $string); + $string = str_replace("\222", '’', $string); + $string = str_replace("\223", '“', $string); + $string = str_replace("\224", '”', $string); + $string = str_replace("\225", '•', $string); + $string = str_replace("\226", '–', $string); + $string = str_replace("\227", '—', $string); + $string = str_replace("\230", '؜', $string); + $string = str_replace("\231", '™', $string); + $string = str_replace("\232", '؟', $string); + $string = str_replace("\233", '›', $string); + $string = str_replace("\234", 'ء', $string); + $string = str_replace("\235", 'آ', $string); + $string = str_replace("\236", 'أ', $string); + $string = str_replace("\237", 'Ÿ', $string); + $string = str_replace("\241", 'ؤ', $string); + $string = str_replace("\242", 'إ', $string); + $string = str_replace("\245", 'ئ', $string); + $string = str_replace ("\250", 'ا', $string); + $string = str_replace ("\252", 'ب', $string); + $string = str_replace ("\262", 'ة', $string); + $string = str_replace ("\263", 'ت', $string); + $string = str_replace ("\264", 'ث', $string); + $string = str_replace ("\270", 'ج', $string); + $string = str_replace ("\272", 'ح', $string); + $string = str_replace ("\274", 'خ', $string); + $string = str_replace ("\275", 'د', $string); + $string = str_replace ("\276", 'ذ', $string); + $string = str_replace ("\277", 'ر', $string); + $string = str_replace ("\301", 'ز', $string); + $string = str_replace ("\304", 'س', $string); + $string = str_replace ("\305", 'ش', $string); + $string = str_replace ("\306", 'ص', $string); + $string = str_replace ("\314", 'ض', $string); + $string = str_replace ("\315", 'ط', $string); + $string = str_replace ("\320", 'ظ', $string); + $string = str_replace ("\321", 'ع', $string); + $string = str_replace ("\322", 'غ', $string); + $string = str_replace ("\323", 'ـ', $string); + $string = str_replace ("\325", 'ف', $string); + $string = str_replace ("\326", 'ق', $string); + $string = str_replace ("\330", 'ك', $string); + $string = str_replace ("\332", 'گ', $string); + $string = str_replace ("\335", 'ل', $string); + $string = str_replace ("\336", 'م', $string); + $string = str_replace ("\337", 'ن', $string); + $string = str_replace ("\341", 'ه', $string); + $string = str_replace ("\344", 'و', $string); + $string = str_replace ("\345", 'ى', $string); + $string = str_replace ("\346", 'ي', $string); + $string = str_replace ("\354", 'ً', $string); + $string = str_replace ("\355", 'ٌ', $string); + $string = str_replace ("\360", 'ٍ', $string); + $string = str_replace ("\361", 'َ', $string); + $string = str_replace ("\362", 'ُ', $string); + $string = str_replace ("\363", 'ِ', $string); + $string = str_replace ("\365", 'ّ', $string); + $string = str_replace ("\366", 'ْ', $string); + + // Rest of charset is like iso-8859-1 + return (charset_decode_iso_8859_1($string)); +} + +/* + windows-1257 (BaltRim) + */ +function charset_decode_windows_1257 ($string) { + global $default_charset; + + if (strtolower($default_charset) == 'windows-1257') + return $string; + + /* Only do the slow convert if there are 8-bit characters */ + if (! ereg("[\200-\377]", $string)) + return $string; + + $string = str_replace("\200", '€', $string); + $string = str_replace("\202", '‚', $string); + $string = str_replace("\204", '„', $string); + $string = str_replace("\205", '…', $string); + $string = str_replace("\206", '†', $string); + $string = str_replace("\207", '‡', $string); + $string = str_replace("\211", '‰', $string); + $string = str_replace("\213", '‹', $string); + $string = str_replace("\215", '¨', $string); + $string = str_replace("\216", 'ˇ', $string); + $string = str_replace("\217", '¸', $string); + $string = str_replace("\221", '‘', $string); + $string = str_replace("\222", '’', $string); + $string = str_replace("\223", '“', $string); + $string = str_replace("\224", '”', $string); + $string = str_replace("\225", '•', $string); + $string = str_replace("\226", '–', $string); + $string = str_replace("\227", '—', $string); + $string = str_replace("\231", '™', $string); + $string = str_replace("\233", '›', $string); + $string = str_replace("\235", '¯', $string); + $string = str_replace("\236", '˛', $string); + $string = str_replace ("\250", 'Ø', $string); + $string = str_replace ("\252", 'Ŗ', $string); + $string = str_replace ("\257", 'Æ', $string); + $string = str_replace ("\270", 'ø', $string); + $string = str_replace ("\272", 'ŗ', $string); + $string = str_replace ("\277", 'æ', $string); + $string = str_replace ("\300", 'Ą', $string); + $string = str_replace ("\301", 'Į', $string); + $string = str_replace ("\302", 'Ā', $string); + $string = str_replace ("\303", 'Ć', $string); + $string = str_replace ("\306", 'Ę', $string); + $string = str_replace ("\307", 'Ē', $string); + $string = str_replace ("\310", 'Č', $string); + $string = str_replace ("\312", 'Ź', $string); + $string = str_replace ("\313", 'Ė', $string); + $string = str_replace ("\314", 'Ģ', $string); + $string = str_replace ("\315", 'Ķ', $string); + $string = str_replace ("\316", 'Ī', $string); + $string = str_replace ("\317", 'Ļ', $string); + $string = str_replace ("\320", 'Š', $string); + $string = str_replace ("\321", 'Ń', $string); + $string = str_replace ("\322", 'Ņ', $string); + $string = str_replace ("\324", 'Ō', $string); + $string = str_replace ("\330", 'Ų', $string); + $string = str_replace ("\331", 'Ł', $string); + $string = str_replace ("\332", 'Ŕ', $string); + $string = str_replace ("\333", 'Ū', $string); + $string = str_replace ("\335", 'Ż', $string); + $string = str_replace ("\336", 'Ž', $string); + $string = str_replace ("\340", 'ą', $string); + $string = str_replace ("\341", 'į', $string); + $string = str_replace ("\342", 'ā', $string); + $string = str_replace ("\343", 'ć', $string); + $string = str_replace ("\346", 'ę', $string); + $string = str_replace ("\347", 'ē', $string); + $string = str_replace ("\350", 'č', $string); + $string = str_replace ("\352", 'ź', $string); + $string = str_replace ("\353", 'ė', $string); + $string = str_replace ("\354", 'ģ', $string); + $string = str_replace ("\355", 'ķ', $string); + $string = str_replace ("\356", 'ī', $string); + $string = str_replace ("\357", 'ļ', $string); + $string = str_replace ("\360", 'š', $string); + $string = str_replace ("\361", 'ń', $string); + $string = str_replace ("\362", 'ņ', $string); + $string = str_replace ("\364", 'ō', $string); + $string = str_replace ("\370", 'ų', $string); + $string = str_replace ("\371", 'ł', $string); + $string = str_replace ("\372", 'ś', $string); + $string = str_replace ("\373", 'ū', $string); + $string = str_replace ("\375", 'ż', $string); + $string = str_replace ("\376", 'ž', $string); + $string = str_replace ("\377", '˙', $string); + + // Rest of charset is like iso-8859-1 + return (charset_decode_iso_8859_1($string)); } @@ -744,17 +1693,19 @@ function japanese_charset_xtra() { function set_up_language($sm_language, $do_search = false) { static $SetupAlready = 0; - global $HTTP_ACCEPT_LANGUAGE, $use_gettext, $languages, + global $use_gettext, $languages, $squirrelmail_language, $squirrelmail_default_language, $sm_notAlias; if ($SetupAlready) { return; } + $SetupAlready = TRUE; + sqgetGlobalVar('HTTP_ACCEPT_LANGUAGE', $accept_lang, SQ_SERVER); - if ($do_search && ! $sm_language && isset($HTTP_ACCEPT_LANGUAGE)) { - $sm_language = substr($HTTP_ACCEPT_LANGUAGE, 0, 2); + if ($do_search && ! $sm_language && isset($accept_lang)) { + $sm_language = substr($accept_lang, 0, 2); } if (!$sm_language && isset($squirrelmail_default_language)) { @@ -770,8 +1721,11 @@ function set_up_language($sm_language, $do_search = false) { $use_gettext && $sm_language != '' && isset($languages[$sm_notAlias]['CHARSET']) ) { - bindtextdomain( 'squirrelmail', '../locale/' ); + bindtextdomain( 'squirrelmail', SM_PATH . 'locale/' ); textdomain( 'squirrelmail' ); + if (function_exists('bind_textdomain_codeset')) { + bind_textdomain_codeset ("squirrelmail", $languages[$sm_notAlias]['CHARSET'] ); + } if ( !ini_get('safe_mode') && getenv( 'LC_ALL' ) != $sm_notAlias ) { putenv( "LC_ALL=$sm_notAlias" ); @@ -783,7 +1737,10 @@ function set_up_language($sm_language, $do_search = false) { if ($squirrelmail_language == 'ja_JP' && function_exists('mb_detect_encoding') ) { header ('Content-Type: text/html; charset=EUC-JP'); if (!function_exists('mb_internal_encoding')) { - echo _("You need to have php4 installed with the multibyte string function enabled (using configure option --with-mbstring)."); + echo _("You need to have php4 installed with the multibyte string function enabled (using configure option --enable-mbstring)."); + } + if (function_exists('mb_language')) { + mb_language('Japanese'); } mb_internal_encoding('EUC-JP'); mb_http_output('pass'); @@ -804,11 +1761,11 @@ function set_my_charset(){ * selection. This is "more right" (tm), than just stamping the * message blindly with the system-wide $default_charset. */ - global $data_dir, $username, $default_charset, $languages; + global $data_dir, $username, $default_charset, $languages, $squirrelmail_default_language; $my_language = getPref($data_dir, $username, 'language'); if (!$my_language) { - return; + $my_language = $squirrelmail_default_language ; } while (isset($languages[$my_language]['ALIAS'])) { $my_language = $languages[$my_language]['ALIAS']; @@ -852,6 +1809,10 @@ $languages['de']['ALIAS'] = 'de_DE'; // There is no en_EN! There is en_US, en_BR, en_AU, and so forth, // but who cares about !US, right? Right? :) +$languages['el_GR']['NAME'] = 'Greek'; +$languages['el_GR']['CHARSET'] = 'iso-8859-7'; +$languages['el']['ALIAS'] = 'el_GR'; + $languages['en_US']['NAME'] = 'English'; $languages['en_US']['CHARSET'] = 'iso-8859-1'; $languages['en']['ALIAS'] = 'en_US'; @@ -864,6 +1825,10 @@ $languages['et_EE']['NAME'] = 'Estonian'; $languages['et_EE']['CHARSET'] = 'iso-8859-15'; $languages['et']['ALIAS'] = 'et_EE'; +$languages['fo_FO']['NAME'] = 'Faroese'; +$languages['fo_FO']['CHARSET'] = 'iso-8859-1'; +$languages['fo']['ALIAS'] = 'fo_FO'; + $languages['fi_FI']['NAME'] = 'Finnish'; $languages['fi_FI']['CHARSET'] = 'iso-8859-1'; $languages['fi']['ALIAS'] = 'fi_FI'; @@ -880,7 +1845,7 @@ $languages['hu_HU']['NAME'] = 'Hungarian'; $languages['hu_HU']['CHARSET'] = 'iso-8859-2'; $languages['hu']['ALIAS'] = 'hu_HU'; -$languages['id_ID']['NAME'] = 'Indonesian'; +$languages['id_ID']['NAME'] = 'Bahasa Indonesia'; $languages['id_ID']['CHARSET'] = 'iso-8859-1'; $languages['id']['ALIAS'] = 'id_ID'; @@ -899,6 +1864,7 @@ $languages['ja']['ALIAS'] = 'ja_JP'; $languages['ko_KR']['NAME'] = 'Korean'; $languages['ko_KR']['CHARSET'] = 'euc-KR'; +$languages['ko_KR']['XTRA_CODE'] = 'korean_charset_xtra'; $languages['ko']['ALIAS'] = 'ko_KR'; $languages['nl_NL']['NAME'] = 'Dutch'; @@ -937,13 +1903,13 @@ $languages['tr_TR']['NAME'] = 'Turkish'; $languages['tr_TR']['CHARSET'] = 'iso-8859-9'; $languages['tr']['ALIAS'] = 'tr_TR'; -$languages['zh_TW']['NAME'] = 'Taiwan'; +$languages['zh_TW']['NAME'] = 'Chinese Trad'; $languages['zh_TW']['CHARSET'] = 'big5'; $languages['tw']['ALIAS'] = 'zh_TW'; -$languages['zh_TW']['NAME'] = 'Chinese'; -$languages['zh_TW']['CHARSET'] = 'gb2312'; -$languages['tw']['ALIAS'] = 'zh_CN'; +$languages['zh_CN']['NAME'] = 'Chinese Simp'; +$languages['zh_CN']['CHARSET'] = 'gb2312'; +$languages['cn']['ALIAS'] = 'zh_CN'; $languages['sk_SK']['NAME'] = 'Slovak'; $languages['sk_SK']['CHARSET'] = 'iso-8859-2'; @@ -958,7 +1924,7 @@ $languages['th_TH']['CHARSET'] = 'tis-620'; $languages['th']['ALIAS'] = 'th_TH'; $languages['lt_LT']['NAME'] = 'Lithuanian'; -$languages['lt_LT']['CHARSET'] = 'iso-8859-13'; +$languages['lt_LT']['CHARSET'] = 'windows-1257'; $languages['lt']['ALIAS'] = 'lt_LT'; $languages['sl_SI']['NAME'] = 'Slovenian'; @@ -969,13 +1935,28 @@ $languages['bg_BG']['NAME'] = 'Bulgarian'; $languages['bg_BG']['CHARSET'] = 'windows-1251'; $languages['bg']['ALIAS'] = 'bg_BG'; +$languages['uk_UA']['NAME'] = 'Ukrainian'; +$languages['uk_UA']['CHARSET'] = 'koi8-u'; +$languages['uk']['ALIAS'] = 'uk_UA'; + +$languages['cy_GB']['NAME'] = 'Welsh'; +$languages['cy_GB']['CHARSET'] = 'iso-8859-1'; +$languages['cy']['ALIAS'] = 'cy_GB'; + +$languages['vi_VN']['NAME'] = 'Vietnamese'; +$languages['vi_VN']['CHARSET'] = 'utf-8'; +$languages['vi']['ALIAS'] = 'vi_VN'; + // Right to left languages -$languages['he_HE']['NAME'] = 'Hebrew'; -$languages['he_HE']['CHARSET'] = 'windows-1255'; -$languages['he_HE']['DIR'] = 'rtl'; -$languages['he']['ALIAS'] = 'he_HE'; +$languages['ar']['NAME'] = 'Arabic'; +$languages['ar']['CHARSET'] = 'windows-1256'; +$languages['ar']['DIR'] = 'rtl'; +$languages['he_IL']['NAME'] = 'Hebrew'; +$languages['he_IL']['CHARSET'] = 'windows-1255'; +$languages['he_IL']['DIR'] = 'rtl'; +$languages['he']['ALIAS'] = 'he_IL'; /* Detect whether gettext is installed. */ $gettext_flags = 0; @@ -996,7 +1977,7 @@ if ($gettext_flags == 7) { /* If we can fake gettext, try that */ elseif ($gettext_flags == 0) { $use_gettext = true; - include_once('../functions/gettext.php'); + include_once(SM_PATH . 'functions/gettext.php'); } else { /* Uh-ho. A weird install */ if (! $gettext_flags & 1) { @@ -1016,4 +1997,196 @@ elseif ($gettext_flags == 0) { } } -?> +function charset_decode_utf8 ($string) { +/* + Every decoded character consists of n bytes. First byte is octal + 300-375, other bytes - always octals 200-277. + + \a\b characters are decoded to html code octdec(a-300)*64 + octdec(b-200) + \a\b\c characters are decoded to html code octdec(a-340)*64*64 + octdec(b-200)*64 + octdec(c-200) + + decoding cycle is unfinished. please test and report problems to tokul@users.sourceforge.net +*/ + global $default_charset, $languages, $sm_notAlias; + + if (strtolower($default_charset) == 'utf-8') + return $string; + if (strtolower($languages[$sm_notAlias]['CHARSET']) == 'utf-8') + return $string; + + /* Only do the slow convert if there are 8-bit characters */ + if (! ereg("[\200-\377]", $string)) + return $string; + + // decode three byte unicode characters + $string = preg_replace("/([\340-\357])([\200-\277])([\200-\277])/e", + "'&#'.((ord('\\1')-224)*4096+(ord('\\2')-128)*64+(ord('\\3')-128)).';'", + $string); + + // decode two byte unicode characters + $string = preg_replace("/([\300-\337])([\200-\277])/e", + "'&#'.((ord('\\1')-192)*64+(ord('\\2')-128)).';'", + $string); + + return $string; +} + +/* + * Japanese charset extra function + * + */ +function japanese_charset_xtra() { + $ret = func_get_arg(1); /* default return value */ + if (function_exists('mb_detect_encoding')) { + switch (func_get_arg(0)) { /* action */ + case 'decode': + $detect_encoding = @mb_detect_encoding($ret); + if ($detect_encoding == 'JIS' || + $detect_encoding == 'EUC-JP' || + $detect_encoding == 'SJIS' || + $detect_encoding == 'UTF-8') { + + $ret = mb_convert_kana(mb_convert_encoding($ret, 'EUC-JP', 'AUTO'), "KV"); + } + break; + case 'encode': + $detect_encoding = @mb_detect_encoding($ret); + if ($detect_encoding == 'JIS' || + $detect_encoding == 'EUC-JP' || + $detect_encoding == 'SJIS' || + $detect_encoding == 'UTF-8') { + + $ret = mb_convert_encoding(mb_convert_kana($ret, "KV"), 'JIS', 'AUTO'); + } + break; + case 'strimwidth': + $width = func_get_arg(2); + $ret = mb_strimwidth($ret, 0, $width, '...'); + break; + case 'encodeheader': + $result = ''; + if (strlen($ret) > 0) { + $tmpstr = mb_substr($ret, 0, 1); + $prevcsize = strlen($tmpstr); + for ($i = 1; $i < mb_strlen($ret); $i++) { + $tmp = mb_substr($ret, $i, 1); + if (strlen($tmp) == $prevcsize) { + $tmpstr .= $tmp; + } else { + if ($prevcsize == 1) { + $result .= $tmpstr; + } else { + $result .= str_replace(' ', '', + mb_encode_mimeheader($tmpstr,'iso-2022-jp','B','')); + } + $tmpstr = $tmp; + $prevcsize = strlen($tmp); + } + } + if (strlen($tmpstr)) { + if (strlen(mb_substr($tmpstr, 0, 1)) == 1) + $result .= $tmpstr; + else + $result .= str_replace(' ', '', + mb_encode_mimeheader($tmpstr,'iso-2022-jp','B','')); + } + } + $ret = $result; + break; + case 'decodeheader': + $ret = str_replace("\t", "", $ret); + if (eregi('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=', $ret)) + $ret = @mb_decode_mimeheader($ret); + $ret = @mb_convert_encoding($ret, 'EUC-JP', 'AUTO'); + break; + case 'downloadfilename': + $useragent = func_get_arg(2); + if (strstr($useragent, 'Windows') !== false || + strstr($useragent, 'Mac_') !== false) { + $ret = mb_convert_encoding($ret, 'SJIS', 'AUTO'); + } else { + $ret = mb_convert_encoding($ret, 'EUC-JP', 'AUTO'); +} + break; + case 'wordwrap': + $no_begin = "\x21\x25\x29\x2c\x2e\x3a\x3b\x3f\x5d\x7d\xa1\xf1\xa1\xeb\xa1" . + "\xc7\xa1\xc9\xa2\xf3\xa1\xec\xa1\xed\xa1\xee\xa1\xa2\xa1\xa3\xa1\xb9" . + "\xa1\xd3\xa1\xd5\xa1\xd7\xa1\xd9\xa1\xdb\xa1\xcd\xa4\xa1\xa4\xa3\xa4" . + "\xa5\xa4\xa7\xa4\xa9\xa4\xc3\xa4\xe3\xa4\xe5\xa4\xe7\xa4\xee\xa1\xab" . + "\xa1\xac\xa1\xb5\xa1\xb6\xa5\xa1\xa5\xa3\xa5\xa5\xa5\xa7\xa5\xa9\xa5" . + "\xc3\xa5\xe3\xa5\xe5\xa5\xe7\xa5\xee\xa5\xf5\xa5\xf6\xa1\xa6\xa1\xbc" . + "\xa1\xb3\xa1\xb4\xa1\xaa\xa1\xf3\xa1\xcb\xa1\xa4\xa1\xa5\xa1\xa7\xa1" . + "\xa8\xa1\xa9\xa1\xcf\xa1\xd1"; + $no_end = "\x5c\x24\x28\x5b\x7b\xa1\xf2\x5c\xa1\xc6\xa1\xc8\xa1\xd2\xa1" . + "\xd4\xa1\xd6\xa1\xd8\xa1\xda\xa1\xcc\xa1\xf0\xa1\xca\xa1\xce\xa1\xd0\xa1\xef"; + $wrap = func_get_arg(2); + + if (strlen($ret) >= $wrap && + substr($ret, 0, 1) != '>' && + strpos($ret, 'http://') === FALSE && + strpos($ret, 'https://') === FALSE && + strpos($ret, 'ftp://') === FALSE) { + + $ret = mb_convert_kana($ret, "KV"); + + $line_new = ''; + $ptr = 0; + + while ($ptr < strlen($ret) - 1) { + $l = mb_strcut($ret, $ptr, $wrap); + $ptr += strlen($l); + $tmp = $l; + + $l = mb_strcut($ret, $ptr, 2); + while (strlen($l) != 0 && mb_strpos($no_begin, $l) !== FALSE ) { + $tmp .= $l; + $ptr += strlen($l); + $l = mb_strcut($ret, $ptr, 1); + } + $line_new .= $tmp; + if ($ptr < strlen($ret) - 1) + $line_new .= "\n"; + } + $ret = $line_new; + } + break; + case 'utf7-imap_encode': + $ret = mb_convert_encoding($ret, 'UTF7-IMAP', 'EUC-JP'); + break; + case 'utf7-imap_decode': + $ret = mb_convert_encoding($ret, 'EUC-JP', 'UTF7-IMAP'); + break; + } + } + return $ret; +} + + +/* + * Korean charset extra function + * Hangul(Korean Character) Attached File Name Fix. + */ +function korean_charset_xtra() { + + $ret = func_get_arg(1); /* default return value */ + if (func_get_arg(0) == 'downloadfilename') { /* action */ + $ret = str_replace("\x0D\x0A", '', $ret); /* Hanmail's CR/LF Clear */ + for ($i=0;$i= "\xA1" && $ret[$i] <= "\xFE") { /* 0xA1 - 0XFE are Valid */ + $i++; + continue; + } else if (($ret[$i] >= 'a' && $ret[$i] <= 'z') || /* From Original ereg_replace in download.php */ + ($ret[$i] >= 'A' && $ret[$i] <= 'Z') || + ($ret[$i] == '.') || ($ret[$i] == '-')) { + continue; + } else { + $ret[$i] = '_'; + } + } + + } + + return $ret; +} + +?> \ No newline at end of file