Zend FR

<?php
/**
 * Rewix extension for Zend Framework
 *
 * LICENSE
 *
 * This source file is subject to the new BSD license that is bundled
 * with this package in the file LICENSE.txt.
 * It is also available through the world-wide-web at this URL:
 * http://www.rewix.com/license/new-bsd
 * If you did not receive a copy of the license and are unable to
 * obtain it through the world-wide-web, please send an email
 * to contact@rewix.com so we can send you a copy immediately.
 *
 * @category   Rx
 * @package    Rx
 * @copyright  Copyright (c) 2007 Rewix (http://www.rewix.com)
 * @license    http://www.rewix.com/license/new-bsd     New BSD License
 */

require_once 'Zend/Filter/Interface.php';


class Rx_Filter_Text implements Zend_Filter_Interface {

    /**
     * Is PCRE is compiled with UTF-8 and Unicode support
     *
     * @var mixed
     **/
    protected static $_unicodeEnabled;
    
    /**
     * Special charateres autorised (not really special)
     *
     * @var String
     */
    protected static $_specialChars = '\?\.,;:\/!€£$=\*\+\-\(\)\{\}\[\]&\#~\"\'\|`‘’«»\\\^@°%µø<>';
    
    /**
     * Accentued charateres autorised
     *
     * @var String
     */
    protected static $_accentuedChars = 'ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõöœøùúûýýþÿ';

    /**
     * Sets default option values for this instance
     *
     * @param  boolean $allowWhiteSpace
     * @return void
     */
    public function __construct()
    {
        if (null === self::$_unicodeEnabled) {
            self::$_unicodeEnabled = (@preg_match('/\pL/u', 'a')) ? true : false;
        }
    }

    /**
     * Defined by Zend_Filter_Interface
     *
     * Returns the string $value, removing all but alphabetic and digit characters
     *
     * @param  string $value
     * @return string
     */
    public function filter($value)
    {
        if (!self::$_unicodeEnabled) {
            // POSIX named classes are not supported, use alternative a-zA-Z0-9 match
            $pattern = '/[^a-zA-Z0-9\s' . self::$_accentuedChars . self::$_specialChars . ']/';
        } else if (extension_loaded('mbstring')) {
            // Unicode safe filter for the value with mbstring
            $pattern = '/[^[:alnum:]\s' . self::$_accentuedChars . self::$_specialChars . ']/u';
        } else {
            // Unicode safe filter for the value without mbstring
            $pattern = '/[^\p{L}\p{N}\s' . self::$_accentuedChars . self::$_specialChars . ']/u';
        }

        return preg_replace($pattern, '', (string) $value);
    }
}