wikimedia/mediawiki-extensions-Description2
1
0
Fork 1
mirror of https://gerrit.wikimedia.org/r/mediawiki/extensions/Description2 synced 2024-11-27 16:10:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

Remove style tags in description

Browse source 
Some pages' description may include CSS code rendered by [[Extension:TemplateStyles]].

Change-Id: I352ac2338eb5977305308546523ec6c55f7cb599
This commit is contained in:
xtex 2024-01-31 16:13:34 +08:00 committed by Winston Sung
parent bc54a5a120
commit 055927a901
1 changed files with 7 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
includes/SimpleDescriptionProvider.php
View file

@ -8,7 +8,7 @@ class SimpleDescriptionProvider implements DescriptionProvider {
* Extracts description from the HTML representation of a page.
*
* The algorithm:
* 1. Removes all <table> elements and their contents.
* 1. Removes all <style> and <table> elements and their contents.
* 2. Selects all <p> elements.
* 3. Iterates over those paragraphs, strips out all HTML tags and trims white-space around.
* 4. Then the first non-empty paragraph is picked as the result.
@ -17,8 +17,12 @@ class SimpleDescriptionProvider implements DescriptionProvider {
* @return string
*/
public function derive( string $text ): ?string {
$pattern = '%<table\b[^>]*+>(?:(?R)|[^<]*+(?:(?!</?table\b)<[^<]*+)*+)*+</table>%i';
$myText = preg_replace( $pattern, '', $text );
$myText = $text;
$stripTags = [ 'style', 'table' ];
foreach ( $stripTags as $tag ) {
$pattern = "%<$tag\b[^>]*+>(?:(?R)|[^<]*+(?:(?!</?$tag\b)<[^<]*+)*+)*+</$tag>%i";
$myText = preg_replace( $pattern, '', $myText );
}
$paragraphs = [];
if ( preg_match_all( '#<p>.*?</p>#is', $myText, $paragraphs ) ) {