Author: jukka
Date: Sun Dec 13 21:21:58 2009
New Revision: 890122
URL: http://svn.apache.org/viewvc?rev=890122&view=rev
Log:
TIKA-343: some parsers produces glued words
The <address> tag can be semantically useful, pass it as a safe element
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=890122&r1=890121&r2=890122&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
Sun Dec 13 21:21:58 2009
@@ -213,6 +213,8 @@
if ("TH".equals(name)) return "th";
if ("TD".equals(name)) return "td";
+ if ("ADDRESS".equals(name)) return "address";
+
return null;
}