clean-slugs.php

<?php
/*
Plugin Name: Clean Slugs
Description: Disallows foreign and encoded characters in post slugs
Version: 0.1
Author: Mark Jaquith
Author URI: http://coveredwebservices.com/
*/

class CWS_Clean_Post_Slugs {
	static $instance;
	function __construct() {
		self::$instance =& $this;
		add_filter( 'wp_insert_post_data', array( $this, 'update_slug' ) );
	}

	function update_slug( $data ) {
		$data['post_name'] = $this->sanitize( $data['post_name'] );
		return $data;
	}

	// Mostly copied from WordPress' sanitize_title_with_dashes()
	function sanitize( $title ) {
		$title = strip_tags($title);
		// Preserve escaped octets.
		$title = preg_replace('|%([a-fA-F0-9][a-fA-F0-9])|', '---$1---', $title);
		// Remove percent signs that are not part of an octet.
		$title = str_replace('%', '', $title);
		// Remove octets.
		$title = preg_replace('|---([a-fA-F0-9][a-fA-F0-9])---|', '', $title);

		$title = remove_accents($title);
		if (seems_utf8($title)) {
			if (function_exists('mb_strtolower')) {
				$title = mb_strtolower($title, 'UTF-8');
			}
			// $title = utf8_uri_encode($title, 200);
		}

		$title = strtolower($title);
		$title = preg_replace('/&.+?;/', '', $title); // kill entities
		$title = str_replace('.', '-', $title);
		$title = preg_replace('/[^%a-z0-9 _-]/', '', $title);
		$title = preg_replace('/\s+/', '-', $title);
		$title = preg_replace('|-+|', '-', $title);
		$title = trim($title, '-');

		return $title;
	}
}

new CWS_Clean_Post_Slugs;