File oops_lib/Xmf/Utilities.php

  1: <?php
  2: /*
  3:  You may not change or alter any portion of this comment or credits
  4:  of supporting developers from this source code or any supporting source code
  5:  which is considered copyrighted (c) material of the original comment or credit authors.
  6: 
  7:  This program is distributed in the hope that it will be useful,
  8:  but WITHOUT ANY WARRANTY; without even the implied warranty of
  9:  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
 10:  */
 11: 
 12: namespace Xmf;
 13: 
 14: /**
 15:  * Utilities
 16:  *
 17:  * @category  Xmf\Module\Utilities
 18:  * @package   Xmf
 19:  * @author    trabis <lusopoemas@gmail.com>
 20:  * @copyright 2011-2013 XOOPS Project (http://xoops.org)
 21:  * @license   GNU GPL 2 or later (http://www.gnu.org/licenses/gpl-2.0.html)
 22:  * @version   Release: 1.0
 23:  * @link      http://xoops.org
 24:  * @since     1.0
 25:  */
 26: class Utilities
 27: {
 28: 
 29:     /**
 30:      * purifyText
 31:      *
 32:      * @param string  $text    text to clean
 33:      * @param boolean $keyword replace some punctuation with white space
 34:      *
 35:      * @return string cleaned text
 36:      */
 37:     public static function purifyText($text, $keyword = false)
 38:     {
 39:         $myts = \Xoops\Core\Text\Sanitizer::getInstance();
 40:         $text = str_replace('&nbsp;', ' ', $text);
 41:         $text = str_replace('<br />', ' ', $text);
 42:         $text = str_replace('<br/>', ' ', $text);
 43:         $text = str_replace('<br', ' ', $text);
 44:         $text = strip_tags($text);
 45:         $text = html_entity_decode($text);
 46:         $text = $myts->undoHtmlSpecialChars($text);
 47:         $text = str_replace(')', ' ', $text);
 48:         $text = str_replace('(', ' ', $text);
 49:         $text = str_replace(':', ' ', $text);
 50:         $text = str_replace('&euro', ' euro ', $text);
 51:         $text = str_replace('&hellip', '...', $text);
 52:         $text = str_replace('&rsquo', ' ', $text);
 53:         $text = str_replace('!', ' ', $text);
 54:         $text = str_replace('?', ' ', $text);
 55:         $text = str_replace('"', ' ', $text);
 56:         $text = str_replace('-', ' ', $text);
 57:         $text = str_replace('\n', ' ', $text);
 58:         $text = str_replace('&#8213;', ' ', $text);
 59: 
 60:         if ($keyword) {
 61:             $text = str_replace('.', ' ', $text);
 62:             $text = str_replace(',', ' ', $text);
 63:             $text = str_replace('\'', ' ', $text);
 64:         }
 65:         $text = str_replace(';', ' ', $text);
 66: 
 67:         return $text;
 68:     }
 69: 
 70:     /**
 71:      * html2text
 72:      * This will remove HTML tags, javascript sections and white space. It will also
 73:      * convert some common HTML entities to their text equivalent. Credits to newbb2
 74:      *
 75:      * @param string $document HTML to be converted
 76:      *
 77:      * @return string Text version of $documnent parameter
 78:      */
 79:     public static function html2text($document)
 80:     {
 81:         $search = array ("'<script[^>]*?>.*?</script>'si",  // Strip out javascript
 82:         "'<img.*?/>'si",       // Strip out img tags
 83:         "'<[\/\!]*?[^<>]*?>'si",          // Strip out HTML tags
 84:         "'([\r\n])[\s]+'",                // Strip out white space
 85:         "'&(quot|#34);'i",                // Replace HTML entities
 86:         "'&(amp|#38);'i",
 87:         "'&(lt|#60);'i",
 88:         "'&(gt|#62);'i",
 89:         "'&(nbsp|#160);'i",
 90:         "'&(iexcl|#161);'i",
 91:         "'&(cent|#162);'i",
 92:         "'&(pound|#163);'i",
 93:         "'&(copy|#169);'i");
 94: 
 95:         $replace = array ("",
 96:         "",
 97:         "",
 98:         "\\1",
 99:         "\"",
100:         "&",
101:         "<",
102:         ">",
103:         " ",
104:         chr(161),
105:         chr(162),
106:         chr(163),
107:         chr(169));
108: 
109:         $text = preg_replace($search, $replace, $document);
110: 
111:         preg_replace_callback(
112:             '/&#(\d+);/',
113:             function ($matches) {
114:                 return chr($matches[1]);
115:             },
116:             $document
117:         );
118: 
119:         return $text;
120:     }
121: }
122:
Namespaces

Classes

Interfaces

Exceptions

Functions
