I’ve never worked with special characters such as Korean, Arabic or any of the non-english characters, but I’ve been using this and it’s been saving me several headaches. If you guys are willing, feel free to add to it (especially the dw_replaceChars
function below!).
// Santize file uploads
function dw_safeFileUploads( $file ) {
$file['name'] = dw_url( $file['name'] );
return $file;
}
add_action('wp_handle_upload_prefilter', 'dw_safeFileUploads');
// Sanitize permalinks
function dw_cleanPermalink($url){
$url = dw_url( $url );
return $url;
}
add_filter('the_permalink', 'dw_cleanPermalink');
// The grunt work
function dw_url( $str = '' ) {
$str = dw_replaceChars( $str );
$str = strtolower($str);
$str = trim($str);
$str = preg_replace("/[\s-]+/", "-", $str);
$str = str_replace("_", "-",$str);
$str = preg_replace("/[^a-z0-9.-]/", "", $str);
$str = str_replace("-.", ".",$str);
return $str;
}
// Keep the replacement apart just to look cleaner
function dw_replaceChars($str) {
$unwanted_array = array(
' '=>'-', '?'=>'S', '?'=>'s', 'D'=>'Dj', '?'=>'Z', '?'=>'z', 'C'=>'C', 'c'=>'c', 'C'=>'C', 'c'=>'c',
'à'=>'A', 'á'=>'A', '?'=>'A', '?'=>'A', '?'=>'A', '?'=>'A', '?'=>'A', '?'=>'C', 'è'=>'E', 'é'=>'E',
'ê'=>'E', '?'=>'E', 'ì'=>'I', 'í'=>'I', '?'=>'I', '?'=>'I', '?'=>'N', 'ò'=>'O', 'ó'=>'O', '?'=>'O',
'?'=>'O', '?'=>'O', '?'=>'O', 'ù'=>'U', 'ú'=>'U', '?'=>'U', 'ü'=>'U', 'Y'=>'Y', 'T'=>'B', '?'=>'Ss',
'à'=>'a', 'á'=>'a', 'a'=>'a', '?'=>'a', '?'=>'a', '?'=>'a', '?'=>'a', '?'=>'c', 'è'=>'e', 'é'=>'e',
'ê'=>'e', '?'=>'e', 'ì'=>'i', 'í'=>'i', '?'=>'i', '?'=>'i', 'e'=>'o', '?'=>'n', 'ò'=>'o', 'ó'=>'o',
'?'=>'o', '?'=>'o', '?'=>'o', '?'=>'o', 'ù'=>'u', 'ú'=>'u', '?'=>'u', 'y'=>'y', 'y'=>'y', 't'=>'b',
'?'=>'y', 'R'=>'R', 'r'=>'r', "'"=>'-', '"'=>'-', '’'=>'-' );
$str = strtr( $str, $unwanted_array );
return $str;
}