note 99640 added to function.strip-tags

With most web based user input or more than a line of text, it seems I get 90% 'paste from Word'. I've developed this fn over time to try to strip all of this cruft out. A few things I do here are application specific, but if it helps you - great, if you can improve on it or have a better way - please - post it... function strip_word_html($text, $allowed_tags = '<b><i><sup><sub><em><strong><u><br>') { mb_regex_encoding('UTF-8'); //replace MS special characters first $search = array('/&lsquo;/u', '/&rsquo;/u', '/&ldquo;/u', '/&rdquo;/u', '/&mdash;/u'); $replace = array('\'', '\'', '"', '"', '-'); $text = preg_replace($search, $replace, $text); //make sure _all_ html entities are converted to the plain ascii equivalents - it appears //in some MS headers, some html entities are encoded and some aren't $text = html_entity_decode($text, ENT_QUOTES, 'UTF-8'); //try to strip out any C style comments first, since these, embedded in html comments, seem to //prevent strip_tags from removing html comments (MS Word introduced combination) if(mb_stripos($text, '/*') !== FALSE){ $text = mb_eregi_replace('/\*(.)*\*', '', $text, 'm'); } //introduce a space into any arithmetic expressions that could be caught by strip_tags so that they won't be //'<1' becomes '< 1'(note: somewhat application specific) $text = preg_replace(array('/<([0-9]+)/'), array('< $1'), $text); $text = strip_tags($text, $allowed_tags); //eliminate extraneous whitespace from start and end of line, or anywhere there are two or more spaces, convert it to one $text = preg_replace(array('/^\s\s+/', '/\s\s+$/', '/\s\s+/u'), array('', '', ' '), $text); //strip out inline css and simplify style tags $search = array('#<(strong|b)[^>]*>(.*?)</(strong|b)>#isu', '#<(em|i)[^>]*>(.*?)</(em|i)>#isu', '#<u[^>]*>(.*?)</u>#isu', '#<br\s{0,1}/{0,1}>#'); $replace = array('<b>$2</b>', '<i>$2</i>', '<u>$1</u>', '\n'); $text = preg_replace($search, $replace, $text); //on some of the ?newer MS Word exports, where you get conditionals of the form 'if gte mso 9', etc., it appears //that whatever is in one of the html comments prevents strip_tags from eradicating the html comment that contains //some MS Style Definitions - this last bit gets rid of any leftover comments $num_matches = preg_match_all("/\<!--/u", $text, $matches); if($num_matches){ $text = preg_replace('/\<!--(.)*--\>/isu', '', $text); } return $text; } ---- Server IP: 69.147.83.197 Probable Submitter: 71.164.23.176 ---- Manual Page -- http://www.php.net/manual/en/function.strip-tags.php Edit -- https://master.php.net/note/edit/99640 Del: integrated -- https://master.php.net/note/delete/99640/integrated Del: useless -- https://master.php.net/note/delete/99640/useless Del: bad code -- https://master.php.net/note/delete/99640/bad+code Del: spam -- https://master.php.net/note/delete/99640/spam Del: non-english -- https://master.php.net/note/delete/99640/non-english Del: in docs -- https://master.php.net/note/delete/99640/in+docs Del: other reasons-- https://master.php.net/note/delete/99640 Reject -- https://master.php.net/note/reject/99640 Search -- https://master.php.net/manage/user-notes.php