diff options
| author | Aleksander Machniak <alec@alec.pl> | 2012-11-15 13:55:42 +0100 |
|---|---|---|
| committer | Aleksander Machniak <alec@alec.pl> | 2012-11-15 13:55:42 +0100 |
| commit | 0679b22150dfded4383d0729940a888fcc7a1b99 (patch) | |
| tree | 384e59910b6eb4b6430e9dfb5e233273f3562efb /program/include/rcube_charset.php | |
| parent | 3c047d0e87339e2eeb2d8784def2b270201f88ac (diff) | |
Improved rcube_charset::detect() with BOM checks from rcube_vcard::detect_encoding() - removed code duplication
Diffstat (limited to 'program/include/rcube_charset.php')
| -rw-r--r-- | program/include/rcube_charset.php | 57 |
1 files changed, 42 insertions, 15 deletions
diff --git a/program/include/rcube_charset.php b/program/include/rcube_charset.php index ff4c2bbce..e6da882ac 100644 --- a/program/include/rcube_charset.php +++ b/program/include/rcube_charset.php @@ -655,22 +655,49 @@ class rcube_charset */ public static function detect($string, $failover='') { - if (!function_exists('mb_detect_encoding')) { - return $failover; - } - - // FIXME: the order is important, because sometimes - // iso string is detected as euc-jp and etc. - $enc = array( - 'UTF-8', 'SJIS', 'BIG5', 'GB2312', - 'ISO-8859-1', 'ISO-8859-2', 'ISO-8859-3', 'ISO-8859-4', - 'ISO-8859-5', 'ISO-8859-6', 'ISO-8859-7', 'ISO-8859-8', 'ISO-8859-9', - 'ISO-8859-10', 'ISO-8859-13', 'ISO-8859-14', 'ISO-8859-15', 'ISO-8859-16', - 'WINDOWS-1252', 'WINDOWS-1251', 'EUC-JP', 'EUC-TW', 'KOI8-R', - 'ISO-2022-KR', 'ISO-2022-JP' - ); + if (substr($string, 0, 4) == "\0\0\xFE\xFF") return 'UTF-32BE'; // Big Endian + if (substr($string, 0, 4) == "\xFF\xFE\0\0") return 'UTF-32LE'; // Little Endian + if (substr($string, 0, 2) == "\xFE\xFF") return 'UTF-16BE'; // Big Endian + if (substr($string, 0, 2) == "\xFF\xFE") return 'UTF-16LE'; // Little Endian + if (substr($string, 0, 3) == "\xEF\xBB\xBF") return 'UTF-8'; + + // heuristics + if ($string[0] == "\0" && $string[1] == "\0" && $string[2] == "\0" && $string[3] != "\0") return 'UTF-32BE'; + if ($string[0] != "\0" && $string[1] == "\0" && $string[2] == "\0" && $string[3] == "\0") return 'UTF-32LE'; + if ($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', 'BIG5', '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', + 'ISO-2022-KR', 'ISO-2022-JP' + ); - $result = mb_detect_encoding($string, join(',', $enc)); + $result = mb_detect_encoding($string, join(',', $enc)); + } + else { + // No match, check for UTF-8 + // from http://w3.org/International/questions/qa-forms-utf-8.html + if (preg_match('/\A( + [\x09\x0A\x0D\x20-\x7E] + | [\xC2-\xDF][\x80-\xBF] + | \xE0[\xA0-\xBF][\x80-\xBF] + | [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2} + | \xED[\x80-\x9F][\x80-\xBF] + | \xF0[\x90-\xBF][\x80-\xBF]{2} + | [\xF1-\xF3][\x80-\xBF]{3} + | \xF4[\x80-\x8F][\x80-\xBF]{2} + )*\z/xs', substr($string, 0, 2048)) + ) { + return 'UTF-8'; + } + } return $result ? $result : $failover; } |