CONTENIDO Forum

Code: Alles auswählen

function is_utf8($input)
{
    // FIXME: Split long strings into smaller chunks otherwhise we could end up in a PCRE
    // stack overflow and a PHP crash, see https://bugs.php.net/bug.php?id=61213
    // TODO: Use mb_detect_encoding if available
    if (strlen($input) > 128) {
        $inputList = explode("\n", chunk_split($input, 128, "\n"));
    } else {
        $inputList = array($input);
    }

    foreach ($inputList as $item) {
        $result = preg_match('%^(?:
                  [\x09\x0A\x0D\x20-\x7E]            # ASCII
                | [\xC2-\xDF][\x80-\xBF]             # non-overlong 2-byte
                |  \xE0[\xA0-\xBF][\x80-\xBF]        # excluding overlongs
                | [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}  # straight 3-byte
                |  \xED[\x80-\x9F][\x80-\xBF]        # excluding surrogates
                |  \xF0[\x90-\xBF][\x80-\xBF]{2}     # planes 1-3
                | [\xF1-\xF3][\x80-\xBF]{3}          # planes 4-15
                |  \xF4[\x80-\x8F][\x80-\xBF]{2}     # plane 16
            )*$%xs', $item);
        
        if ($result) {
            return true;
        }
    }

    return false;
}