Strip head first because of possible nested tags

joomla · Oct 13, 2016 · 85e572c · 85e572c
1 parent 42f4171
commit 85e572c
Showing 1 changed file with 5 additions and 3 deletions.
diff --git a/administrator/components/com_finder/helpers/indexer/parser/html.php b/administrator/components/com_finder/helpers/indexer/parser/html.php
@@ -35,17 +35,19 @@ public function parse($input)
 		// Strip invalid UTF-8 characters.
 		$input = iconv("utf-8", "utf-8//IGNORE", $input);
 
-		// Convert <style>, <noscript> and <head> tags to <script> tags
+		// Remove anything between <head> and </head> tags.  Do this first
+		// because there might be <script> or <style> tags nested inside.
+		$input = $this->removeBlocks($input, '<head>', '</head>');
+
+		// Convert <style> and <noscript> tags to <script> tags
 		// so we can remove them efficiently.
 		$search = array(
 			'<style', '</style',
 			'<noscript', '</noscript',
-			'<head', '</head',
 		);
 		$replace = array(
 			'<script', '</script',
 			'<script', '</script',
-			'<script', '</script',
 		);
 		$input = str_replace($search, $replace, $input);