| | |
| | | static $iconv_options = null; |
| | | static $mbstring_list = null; |
| | | static $mbstring_sch = null; |
| | | static $conv = null; |
| | | |
| | | $to = empty($to) ? RCUBE_CHARSET : $to; |
| | | $from = self::parse_charset($from); |
| | |
| | | $iconv_options = ''; |
| | | } |
| | | } |
| | | else { |
| | | $iconv_options = false; |
| | | } |
| | | } |
| | | |
| | | // convert charset using iconv module |
| | | if ($iconv_options !== null && $from != 'UTF7-IMAP' && $to != 'UTF7-IMAP') { |
| | | if ($iconv_options !== false && $from != 'UTF7-IMAP' && $to != 'UTF7-IMAP') { |
| | | // throw an exception if iconv reports an illegal character in input |
| | | // it means that input string has been truncated |
| | | set_error_handler(array('rcube_charset', 'error_handler'), E_NOTICE); |
| | |
| | | $mbstring_list = mb_list_encodings(); |
| | | $mbstring_list = array_map('strtoupper', $mbstring_list); |
| | | } |
| | | else { |
| | | $mbstring_list = false; |
| | | } |
| | | } |
| | | |
| | | // convert charset using mbstring module |
| | | if ($mbstring_list !== null) { |
| | | if ($mbstring_list !== false) { |
| | | $aliases['WINDOWS-1257'] = 'ISO-8859-13'; |
| | | // it happens that mbstring supports ASCII but not US-ASCII |
| | | if (($from == 'US-ASCII' || $to == 'US-ASCII') && !in_array('US-ASCII', $mbstring_list)) { |
| | |
| | | else if ($from == 'ISO-8859-1' && function_exists('utf8_encode')) { |
| | | return utf8_encode($str); |
| | | } |
| | | else if (class_exists('utf8')) { |
| | | if (!$conv) { |
| | | $conv = new utf8($from); |
| | | } |
| | | else { |
| | | $conv->loadCharset($from); |
| | | } |
| | | |
| | | if ($_str = $conv->strToUtf8($str)) { |
| | | return $_str; |
| | | } |
| | | else { |
| | | trigger_error("No suitable function found for UTF-8 encoding"); |
| | | } |
| | | } |
| | | |
| | |
| | | else if ($to == 'ISO-8859-1' && function_exists('utf8_decode')) { |
| | | return utf8_decode($str); |
| | | } |
| | | else if (class_exists('utf8')) { |
| | | if (!$conv) { |
| | | $conv = new utf8($to); |
| | | } |
| | | else { |
| | | $conv->loadCharset($from); |
| | | } |
| | | |
| | | if ($_str = $conv->strToUtf8($str)) { |
| | | return $_str; |
| | | } |
| | | else { |
| | | trigger_error("No suitable function found for UTF-8 decoding"); |
| | | } |
| | | } |
| | | |
| | |
| | | /** |
| | | * A method to guess character set of a string. |
| | | * |
| | | * @param string $string String. |
| | | * @param string $failover Default result for failover. |
| | | * @param string $string String |
| | | * @param string $failover Default result for failover |
| | | * @param string $language User language |
| | | * |
| | | * @return string Charset name |
| | | */ |
| | | public static function detect($string, $failover='') |
| | | public static function detect($string, $failover = null, $language = null) |
| | | { |
| | | if (substr($string, 0, 4) == "\0\0\xFE\xFF") return 'UTF-32BE'; // Big Endian |
| | | if (substr($string, 0, 4) == "\xFF\xFE\0\0") return 'UTF-32LE'; // Little Endian |
| | |
| | | if ($string[0] == "\0" && $string[1] != "\0" && $string[2] == "\0" && $string[3] != "\0") return 'UTF-16BE'; |
| | | if ($string[0] != "\0" && $string[1] == "\0" && $string[2] != "\0" && $string[3] == "\0") return 'UTF-16LE'; |
| | | |
| | | if (function_exists('mb_detect_encoding')) { |
| | | // FIXME: the order is important, because sometimes |
| | | // iso string is detected as euc-jp and etc. |
| | | $enc = array( |
| | | 'UTF-8', 'SJIS', 'GB2312', |
| | | 'ISO-8859-1', 'ISO-8859-2', 'ISO-8859-3', 'ISO-8859-4', |
| | | 'ISO-8859-5', 'ISO-8859-6', 'ISO-8859-7', 'ISO-8859-8', 'ISO-8859-9', |
| | | 'ISO-8859-10', 'ISO-8859-13', 'ISO-8859-14', 'ISO-8859-15', 'ISO-8859-16', |
| | | 'WINDOWS-1252', 'WINDOWS-1251', 'EUC-JP', 'EUC-TW', 'KOI8-R', 'BIG5', |
| | | 'ISO-2022-KR', 'ISO-2022-JP', |
| | | ); |
| | | |
| | | $result = mb_detect_encoding($string, join(',', $enc)); |
| | | if (empty($language)) { |
| | | $rcube = rcube::get_instance(); |
| | | $language = $rcube->get_user_language(); |
| | | } |
| | | else { |
| | | // No match, check for UTF-8 |
| | | // from http://w3.org/International/questions/qa-forms-utf-8.html |
| | | if (preg_match('/\A( |
| | | [\x09\x0A\x0D\x20-\x7E] |
| | | | [\xC2-\xDF][\x80-\xBF] |
| | | | \xE0[\xA0-\xBF][\x80-\xBF] |
| | | | [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2} |
| | | | \xED[\x80-\x9F][\x80-\xBF] |
| | | | \xF0[\x90-\xBF][\x80-\xBF]{2} |
| | | | [\xF1-\xF3][\x80-\xBF]{3} |
| | | | \xF4[\x80-\x8F][\x80-\xBF]{2} |
| | | )*\z/xs', substr($string, 0, 2048)) |
| | | ) { |
| | | return 'UTF-8'; |
| | | |
| | | // Prioritize charsets according to current language (#1485669) |
| | | switch ($language) { |
| | | case 'ja_JP': |
| | | $prio = array('ISO-2022-JP', 'JIS', 'UTF-8', 'EUC-JP', 'eucJP-win', 'SJIS', 'SJIS-win'); |
| | | break; |
| | | |
| | | case 'zh_CN': |
| | | case 'zh_TW': |
| | | $prio = array('UTF-8', 'BIG-5', 'GB2312', 'EUC-TW'); |
| | | break; |
| | | |
| | | case 'ko_KR': |
| | | $prio = array('UTF-8', 'EUC-KR', 'ISO-2022-KR'); |
| | | break; |
| | | |
| | | case 'ru_RU': |
| | | $prio = array('UTF-8', 'WINDOWS-1251', 'KOI8-R'); |
| | | break; |
| | | |
| | | case 'tr_TR': |
| | | $prio = array('UTF-8', 'ISO-8859-9', 'WINDOWS-1254'); |
| | | break; |
| | | } |
| | | |
| | | // mb_detect_encoding() is not reliable for some charsets (#1490135) |
| | | // use mb_check_encoding() to make charset priority lists really working |
| | | if ($prio && function_exists('mb_check_encoding')) { |
| | | foreach ($prio as $encoding) { |
| | | if (mb_check_encoding($string, $encoding)) { |
| | | return $encoding; |
| | | } |
| | | } |
| | | } |
| | | |
| | | return $result ? $result : $failover; |
| | | if (function_exists('mb_detect_encoding')) { |
| | | if (!$prio) { |
| | | $prio = array('UTF-8', 'SJIS', 'GB2312', |
| | | 'ISO-8859-1', 'ISO-8859-2', 'ISO-8859-3', 'ISO-8859-4', |
| | | 'ISO-8859-5', 'ISO-8859-6', 'ISO-8859-7', 'ISO-8859-8', 'ISO-8859-9', |
| | | 'ISO-8859-10', 'ISO-8859-13', 'ISO-8859-14', 'ISO-8859-15', 'ISO-8859-16', |
| | | 'WINDOWS-1252', 'WINDOWS-1251', 'EUC-JP', 'EUC-TW', 'KOI8-R', 'BIG-5', |
| | | 'ISO-2022-KR', 'ISO-2022-JP', |
| | | ); |
| | | } |
| | | |
| | | $encodings = array_unique(array_merge($prio, mb_list_encodings())); |
| | | |
| | | if ($encoding = mb_detect_encoding($string, $encodings)) { |
| | | return $encoding; |
| | | } |
| | | } |
| | | |
| | | // No match, check for UTF-8 |
| | | // from http://w3.org/International/questions/qa-forms-utf-8.html |
| | | if (preg_match('/\A( |
| | | [\x09\x0A\x0D\x20-\x7E] |
| | | | [\xC2-\xDF][\x80-\xBF] |
| | | | \xE0[\xA0-\xBF][\x80-\xBF] |
| | | | [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2} |
| | | | \xED[\x80-\x9F][\x80-\xBF] |
| | | | \xF0[\x90-\xBF][\x80-\xBF]{2} |
| | | | [\xF1-\xF3][\x80-\xBF]{3} |
| | | | \xF4[\x80-\x8F][\x80-\xBF]{2} |
| | | )*\z/xs', substr($string, 0, 2048)) |
| | | ) { |
| | | return 'UTF-8'; |
| | | } |
| | | |
| | | return $failover; |
| | | } |
| | | |
| | | |
| | |
| | | |
| | | // iconv/mbstring are much faster (especially with long strings) |
| | | if (function_exists('mb_convert_encoding')) { |
| | | if (($res = mb_convert_encoding($input, 'UTF-8', 'UTF-8')) !== false) { |
| | | $msch = mb_substitute_character('none'); |
| | | mb_substitute_character('none'); |
| | | $res = mb_convert_encoding($input, 'UTF-8', 'UTF-8'); |
| | | mb_substitute_character($msch); |
| | | |
| | | if ($res !== false) { |
| | | return $res; |
| | | } |
| | | } |
| | |
| | | } |
| | | $seq = ''; |
| | | $out .= $chr; |
| | | // first (or second) byte of multibyte sequence |
| | | } |
| | | // first (or second) byte of multibyte sequence |
| | | else if ($ord >= 0xC0) { |
| | | if (strlen($seq) > 1) { |
| | | $out .= preg_match($regexp, $seq) ? $seq : ''; |
| | |
| | | $seq = ''; |
| | | } |
| | | $seq .= $chr; |
| | | // next byte of multibyte sequence |
| | | } |
| | | // next byte of multibyte sequence |
| | | else if ($seq) { |
| | | $seq .= $chr; |
| | | } |