SafeUtf8Filter.class.php

Go to the documentation of this file.
00001 <?php
00002 /***************************************************************************
00003  *   Copyright (C) 2007 by Ivan Y. Khvostishkov                            *
00004  *                                                                         *
00005  *   This program is free software; you can redistribute it and/or modify  *
00006  *   it under the terms of the GNU Lesser General Public License as        *
00007  *   published by the Free Software Foundation; either version 3 of the    *
00008  *   License, or (at your option) any later version.                       *
00009  *                                                                         *
00010  ***************************************************************************/
00011 /* $Id: SafeUtf8Filter.class.php 4687 2007-12-09 18:57:18Z voxus $ */
00012 
00016     final class SafeUtf8Filter extends BaseFilter
00017     {
00021         public static function me()
00022         {
00023             return Singleton::getInstance(__CLASS__);
00024         }
00025 
00026         public function apply($value)
00027         {
00028             $matches = null;
00029             
00030             // voodoo magic from w3 validator
00031             preg_match_all(
00032                 '/[\x00-\x7F]                         ' # ASCII
00033                 .'| [\xC2-\xDF]        [\x80-\xBF]    ' # non-overlong 2-byte sequences
00034                 .'|  \xE0[\xA0-\xBF]   [\x80-\xBF]    ' # excluding overlongs
00035                 .'| [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2} ' # straight 3-byte sequences
00036                 .'|  \xED[\x80-\x9F]   [\x80-\xBF]    ' # excluding surrogates
00037                 .'|  \xF0[\x90-\xBF]   [\x80-\xBF]{2} ' # planes 1-3
00038                 .'| [\xF1-\xF3]        [\x80-\xBF]{3} ' # planes 4-15
00039                 .'|  \xF4[\x80-\x8F][\x80-\xBF]{2}    ' # plane 16
00040                 .'/x',
00041                 $value,
00042                 $matches
00043             );
00044 
00045             if (!isset($matches[0]))
00046                 return null;
00047             else
00048                 return implode(null, $matches[0]);
00049         }
00050     }
00051 ?>

Generated on Sun Dec 9 21:56:23 2007 for onPHP by  doxygen 1.5.4