SimplePie: decode special chars for MAYBE_HTML

https://github.com/FreshRSS/FreshRSS/issues/754
Needs to check with many feeds to see if this does not introduce
incompatibilities with some valid feeds.

1 files changed, 5 insertions, 0 deletions

diff --git a/lib/SimplePie/SimplePie/Sanitize.php b/lib/SimplePie/SimplePie/Sanitize.php
index 168a5e2e8..3da7239be 100644
--- a/lib/SimplePie/SimplePie/Sanitize.php
+++ b/lib/SimplePie/SimplePie/Sanitize.php
@@ -249,6 +249,11 @@ class SimplePie_Sanitize
 		{
 			if ($type & SIMPLEPIE_CONSTRUCT_MAYBE_HTML)
 			{
+				if (preg_match('/&#(x[0-9a-fA-F]+|[0-9]+);/', $data))	//FreshRSS
+				{
+					$data = htmlspecialchars_decode($data, ENT_QUOTES);	//FreshRSS
+					//syslog(LOG_DEBUG, 'SimplePie sanitize MAYBE_HTML htmlspecialchars_decode: ' . $data);	//FreshRSS
+				}
 				if (preg_match('/(&(#(x[0-9a-fA-F]+|[0-9]+)|[a-zA-Z0-9]+)|<\/[A-Za-z][^\x09\x0A\x0B\x0C\x0D\x20\x2F\x3E]*' . SIMPLEPIE_PCRE_HTML_ATTRIBUTE . '>)/', $data))
 				{
 					$type |= SIMPLEPIE_CONSTRUCT_HTML;