Author: jukka
Date: Wed Sep 30 14:22:43 2009
New Revision: 820278
URL: http://svn.apache.org/viewvc?rev=820278&view=rev
Log:
TIKA-297: The HtmlParser ignores <menu> tags, resulting in invalid XHTML
Fixed as suggested by Ken Krugler.
Modified:
lucene/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/html/HtmlParser.java
Modified:
lucene/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/html/HtmlParser.java
URL:
http://svn.apache.org/viewvc/lucene/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/html/HtmlParser.java?rev=820278&r1=820277&r2=820278&view=diff
==============================================================================
---
lucene/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/html/HtmlParser.java
(original)
+++
lucene/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/html/HtmlParser.java
Wed Sep 30 14:22:43 2009
@@ -72,6 +72,7 @@
SAFE_ELEMENTS.put("UL", "ul");
SAFE_ELEMENTS.put("OL", "ol");
SAFE_ELEMENTS.put("LI", "li");
+ SAFE_ELEMENTS.put("MENU", "li");
SAFE_ELEMENTS.put("DL", "dl");
SAFE_ELEMENTS.put("DT", "dt");
SAFE_ELEMENTS.put("DD", "dd");