note 118485 added to function.strip-tags

Features: * allowable tags (as in strip_tags), * optional stripping attributes of the allowable tags, * optional comment preserving, * deleting broken and unclosed tags and comments, * optional callback function call for every piece processed allowing for flexible replacements. <?php function better_strip_tags( $str, $allowable_tags = '', $strip_attrs = false, $preserve_comments = false, callable $callback = null ) { $allowable_tags = array_map( 'strtolower', array_filter( // lowercase preg_split( '/(?:>|^)\\s*(?:<|$)/', $allowable_tags, -1, PREG_SPLIT_NO_EMPTY ), // get tag names function( $tag ) { return preg_match( '/^[a-z][a-z0-9_]*$/i', $tag ); } // filter broken ) ); $comments_and_stuff = preg_split( '/(<!--.*?(?:-->|$))/', $str, -1, PREG_SPLIT_DELIM_CAPTURE ); foreach ( $comments_and_stuff as $i => $comment_or_stuff ) { if ( $i % 2 ) { // html comment if ( !( $preserve_comments && preg_match( '/<!--.*?-->/', $comment_or_stuff ) ) ) { $comments_and_stuff[$i] = ''; } } else { // stuff between comments $tags_and_text = preg_split( "/(<(?:[^>\"']++|\"[^\"]*+(?:\"|$)|'[^']*+(?:'|$))*(?:>|$))/", $comment_or_stuff, -1, PREG_SPLIT_DELIM_CAPTURE ); foreach ( $tags_and_text as $j => $tag_or_text ) { $is_broken = false; $is_allowable = true; $result = $tag_or_text; if ( $j % 2 ) { // tag if ( preg_match( "%^(</?)([a-z][a-z0-9_]*)\\b(?:[^>\"'/]++|/+?|\"[^\"]*\"|'[^']*')*?(/?>)%i", $tag_or_text, $matches ) ) { $tag = strtolower( $matches[2] ); if ( in_array( $tag, $allowable_tags ) ) { if ( $strip_attrs ) { $opening = $matches[1]; $closing = ( $opening === '</' ) ? '>' : $closing; $result = $opening . $tag . $closing; } } else { $is_allowable = false; $result = ''; } } else { $is_broken = true; $result = ''; } } else { // text $tag = false; } if ( !$is_broken && isset( $callback ) ) { // allow result modification call_user_func_array( $callback, array( &$result, $tag_or_text, $tag, $is_allowable ) ); } $tags_and_text[$j] = $result; } $comments_and_stuff[$i] = implode( '', $tags_and_text ); } } $str = implode( '', $comments_and_stuff ); return $str; } ?> Callback arguments: * &$result: contains text to be placed insted of original piece (e.g. empty string for forbidden tags), it can be changed; * $tag_or_text: original piece of text or a tag (see below); * $tag: false for text between tags, lowercase tag name for tags; * $is_allowable: boolean telling if a tag isn't allowed (to avoid double checking), always true for text between tags Callback function isn't called for comments and broken tags. Caution: the function doesn't fully validate tags (the more so HTML itself), it just force strips those obviously broken (in addition to stripping forbidden tags). If you want to get valid tags then use strip_attrs option, though it doesn't guarantee tags are balanced or used in the appropriate context. For complex logic consider using DOM parser. ---- Server IP: 72.52.91.14 Probable Submitter: 217.74.47.6 ---- Manual Page -- http://php.net/manual/en/function.strip-tags.php Edit -- https://master.php.net/note/edit/118485 Del: integrated -- https://master.php.net/note/delete/118485/integrated Del: useless -- https://master.php.net/note/delete/118485/useless Del: bad code -- https://master.php.net/note/delete/118485/bad+code Del: spam -- https://master.php.net/note/delete/118485/spam Del: non-english -- https://master.php.net/note/delete/118485/non-english Del: in docs -- https://master.php.net/note/delete/118485/in+docs Del: other reasons-- https://master.php.net/note/delete/118485 Reject -- https://master.php.net/note/reject/118485 Search -- https://master.php.net/manage/user-notes.php