~ overflow ~

Problem:

There are many issues when you run across a non utf8 string and even worse a mixed variable, that could or couldn’t be utf8 at same time.

Solution:

Based on my previous postings i’ve improved my utf8 functions taking as referral this great post.

define('_is_utf8_split',5000);

function utf8_encode_array(&$x) {
	if (is_array($x)) {
		foreach ($x as &$v) // loop through arrays and/or items
			$v=utf8_encode_array($v);
		return $x;
	} else // not array
		return !is_utf8($x) ? utf8_encode($x) : $x;
}
function to_utf8($x) { // v1.01
	/*
		This function will convert a string or an array to utf8.
		The input can have mixed encodings.

		-- 100424
	*/
	if (!is_utf8($x)) {
		if (is_array($x)) {
			foreach ($x as &$v) {
				$v=to_utf8($v);
			}
		} else {
			$x=utf8_encode($x);
		}
	}
	return $x;
}
function is_utf8($string) { // v1.03
	if (is_array($string)) {
		foreach ($string as $v) {
			if (is_utf8($string))
				return true;
		}
		return false;
	} elseif (strlen($string) > _is_utf8_split) {
		// Based on: http://mobile-website.mobi/php-utf8-vs-iso-8859-1-59
		for ($s=$i=0,$j=ceil(strlen($string)/_is_utf8_split);$i < $j;$i++,$s+=_is_utf8_split) {
			if (!is_utf8(substr($string,$s,_is_utf8_split)))
				return false;
		}
		return true;
	} else {
		// From http://w3.org/International/questions/qa-forms-utf-8.html
		return preg_match('%^(?:
				[\x09\x0A\x0D\x20-\x7E]            # ASCII
			| [\xC2-\xDF][\x80-\xBF]             # non-overlong 2-byte
			|  \xE0[\xA0-\xBF][\x80-\xBF]        # excluding overlongs
			| [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}  # straight 3-byte
			|  \xED[\x80-\x9F][\x80-\xBF]        # excluding surrogates
			|  \xF0[\x90-\xBF][\x80-\xBF]{2}     # planes 1-3
			| [\xF1-\xF3][\x80-\xBF]{3}          # planes 4-15
			|  \xF4[\x80-\x8F][\x80-\xBF]{2}     # plane 16
		)*$%xs', $string);
	}
}
function _r_json($x) {
	$x=utf8_encode_array($x);
	echo json_encode($x);
}