WordPress 技巧：去除非法字符

function wpjam_strip_invalid_text($str){
	$regex = '/
	(
		(?: [\x00-\x7F]                  # single-byte sequences   0xxxxxxx
		|   [\xC2-\xDF][\x80-\xBF]       # double-byte sequences   110xxxxx 10xxxxxx
		|   \xE0[\xA0-\xBF][\x80-\xBF]   # triple-byte sequences   1110xxxx 10xxxxxx * 2
		|   [\xE1-\xEC][\x80-\xBF]{2}
		|   \xED[\x80-\x9F][\x80-\xBF]
		|   [\xEE-\xEF][\x80-\xBF]{2}
		|    \xF0[\x90-\xBF][\x80-\xBF]{2} # four-byte sequences   11110xxx 10xxxxxx * 3
		|    [\xF1-\xF3][\x80-\xBF]{3}
		|    \xF4[\x80-\x8F][\x80-\xBF]{2}
		){1,50}                          # ...one or more times
	)
	| .                                  # anything else
	/x';

	return preg_replace($regex, '$1', $str);
}