Author: ab
Date: Thu Mar 30 15:07:48 2006
New Revision: 390275
URL: http://svn.apache.org/viewcvs?rev=390275&view=rev
Log:
Fix a bug where TagSoup would sometimes submit invalid index values.
Modified:
lucene/nutch/trunk/src/plugin/parse-html/src/java/org/apache/nutch/parse/html/DOMBuilder.java
Modified:
lucene/nutch/trunk/src/plugin/parse-html/src/java/org/apache/nutch/parse/html/DOMBuilder.java
URL:
http://svn.apache.org/viewcvs/lucene/nutch/trunk/src/plugin/parse-html/src/java/org/apache/nutch/parse/html/DOMBuilder.java?rev=390275&r1=390274&r2=390275&view=diff
==============================================================================
---
lucene/nutch/trunk/src/plugin/parse-html/src/java/org/apache/nutch/parse/html/DOMBuilder.java
(original)
+++
lucene/nutch/trunk/src/plugin/parse-html/src/java/org/apache/nutch/parse/html/DOMBuilder.java
Thu Mar 30 15:07:48 2006
@@ -550,6 +550,8 @@
*/
public void comment(char ch[], int start, int length) throws
org.xml.sax.SAXException
{
+ // tagsoup sometimes submits invalid values here
+ if (ch == null || start < 0 || length >= ch.length) return;
append(m_doc.createComment(new String(ch, start, length)));
}