From 6689f199562836142fa4c3e82b1885ff56255ccb Mon Sep 17 00:00:00 2001
From: Kevin Decherf <kevin@kdecherf.com>
Date: Sat, 11 Jun 2022 00:11:36 +0200
Subject: [PATCH] Strip script and style tags through ::clean() method instead
 of preg_replace

Huge tags can lead to a failure of preg_replace, thus erasing the whole
fetched content.

Fixes https://github.com/wallabag/wallabag/issues/5847

Signed-off-by: Kevin Decherf <kevin@kdecherf.com>
---
 src/Readability.php | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/src/Readability.php b/src/Readability.php
index 306fcf4..4336bca 100644
--- a/src/Readability.php
+++ b/src/Readability.php
@@ -108,10 +108,6 @@ class Readability implements LoggerAwareInterface
     protected $useTidy;
     // raw HTML filters
     protected $pre_filters = [
-        // remove obvious scripts
-        '!<script[^>]*>(.*?)</script>!is' => '',
-        // remove obvious styles
-        '!<style[^>]*>(.*?)</style>!is' => '',
         // remove spans as we redefine styles and they're probably special-styled
         '!</?span[^>]*>!is' => '',
         // HACK: firewall-filtered content
@@ -366,6 +362,9 @@ class Readability implements LoggerAwareInterface
 
         $this->logger->debug($this->lightClean ? 'Light clean enabled.' : 'Standard clean enabled.');
 
+        $this->clean($articleContent, 'style');
+        $this->clean($articleContent, 'script');
+
         $this->cleanStyles($articleContent);
         $this->killBreaks($articleContent);