You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@wookie.apache.org by sc...@apache.org on 2012/10/07 13:56:42 UTC
svn commit: r1395279 -
/incubator/wookie/trunk/src/org/apache/wookie/util/html/HtmlCleaner.java
Author: scottbw
Date: Sun Oct 7 11:56:41 2012
New Revision: 1395279
URL: http://svn.apache.org/viewvc?rev=1395279&view=rev
Log:
Altered HtmlCleaner config to recognise unicode decimal numeric characters. This *almost* fixes WOOKIE-380 however hex unicode characters still don't work properly.
Modified:
incubator/wookie/trunk/src/org/apache/wookie/util/html/HtmlCleaner.java
Modified: incubator/wookie/trunk/src/org/apache/wookie/util/html/HtmlCleaner.java
URL: http://svn.apache.org/viewvc/incubator/wookie/trunk/src/org/apache/wookie/util/html/HtmlCleaner.java?rev=1395279&r1=1395278&r2=1395279&view=diff
==============================================================================
--- incubator/wookie/trunk/src/org/apache/wookie/util/html/HtmlCleaner.java (original)
+++ incubator/wookie/trunk/src/org/apache/wookie/util/html/HtmlCleaner.java Sun Oct 7 11:56:41 2012
@@ -63,6 +63,8 @@ public class HtmlCleaner implements IHtm
//
properties.setTranslateSpecialEntities(true);
properties.setTransSpecialEntitiesToNCR(true);
+ properties.setAdvancedXmlEscape(true);
+ properties.setRecognizeUnicodeChars(false);
}