From 1499b9aa3c98718be6428a95582b84ad4f62b26e Mon Sep 17 00:00:00 2001
From: OfficialCRUGG <ich@crugg.de>
Date: Fri, 2 Feb 2024 15:08:26 +0100
Subject: [PATCH] feat: remove style tags

---
 includes/SimpleDescriptionProvider.php | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/includes/SimpleDescriptionProvider.php b/includes/SimpleDescriptionProvider.php
index ea3f904..fbbc3a4 100644
--- a/includes/SimpleDescriptionProvider.php
+++ b/includes/SimpleDescriptionProvider.php
@@ -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 <table> and <style> 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.
@@ -17,7 +17,7 @@ class SimpleDescriptionProvider implements DescriptionProvider {
 	 * @return string
 	 */
 	public function derive( string $text ): ?string {
-		$pattern = '%<table\b[^>]*+>(?:(?R)|[^<]*+(?:(?!</?table\b)<[^<]*+)*+)*+</table>%i';
+		$pattern = '%<(table|style)\b[^>]*+>(?:(?R)|[^<]*+(?:(?!</?(table|style)\b)<[^<]*+)*+)*+</(table|style)>%i';
 		$myText = preg_replace( $pattern, '', $text );
 
 		$paragraphs = [];