You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@nutch.apache.org by pk...@apache.org on 2005/09/23 18:14:30 UTC
svn commit: r291157 -
/lucene/nutch/branches/Release-0.7/src/plugin/parse-rss/src/java/org/apache/nutch/parse/rss/RSSParser.java
Author: pkosiorowski
Date: Fri Sep 23 09:14:23 2005
New Revision: 291157
URL: http://svn.apache.org/viewcvs?rev=291157&view=rev
Log:
NUTCH-89 parse-rss null pointer exception. Sumbitted by Michael Nebel.
Modified:
lucene/nutch/branches/Release-0.7/src/plugin/parse-rss/src/java/org/apache/nutch/parse/rss/RSSParser.java
Modified: lucene/nutch/branches/Release-0.7/src/plugin/parse-rss/src/java/org/apache/nutch/parse/rss/RSSParser.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/Release-0.7/src/plugin/parse-rss/src/java/org/apache/nutch/parse/rss/RSSParser.java?rev=291157&r1=291156&r2=291157&view=diff
==============================================================================
--- lucene/nutch/branches/Release-0.7/src/plugin/parse-rss/src/java/org/apache/nutch/parse/rss/RSSParser.java (original)
+++ lucene/nutch/branches/Release-0.7/src/plugin/parse-rss/src/java/org/apache/nutch/parse/rss/RSSParser.java Fri Sep 23 09:14:23 2005
@@ -157,11 +157,13 @@
if (r.getLink() != null) {
try {
// get the outlink
- theOutlinks.add(new Outlink(r.getLink(), r
- .getDescription()));
+ if (r.getDescription()!= null ) {
+ theOutlinks.add(new Outlink(r.getLink(), r.getDescription()));
+ } else {
+ theOutlinks.add(new Outlink(r.getLink(), ""));
+ }
} catch (MalformedURLException e) {
- LOG
- .info("nutch:parse-rss:RSSParser Exception: MalformedURL: "
+ LOG.info("nutch:parse-rss:RSSParser Exception: MalformedURL: "
+ r.getLink()
+ ": Attempting to continue processing outlinks");
e.printStackTrace();
@@ -185,12 +187,13 @@
if (whichLink != null) {
try {
- theOutlinks.add(new Outlink(whichLink, theRSSItem
- .getDescription()));
-
+ if (theRSSItem.getDescription()!=null) {
+ theOutlinks.add(new Outlink(whichLink, theRSSItem.getDescription()));
+ } else {
+ theOutlinks.add(new Outlink(whichLink, ""));
+ }
} catch (MalformedURLException e) {
- LOG
- .info("nutch:parse-rss:RSSParser Exception: MalformedURL: "
+ LOG.info("nutch:parse-rss:RSSParser Exception: MalformedURL: "
+ whichLink
+ ": Attempting to continue processing outlinks");
e.printStackTrace();
@@ -206,23 +209,18 @@
LOG.fine("nutch:parse-rss:getParse:contentTitle=" + contentTitle);
} else {
- LOG
- .fine("nutch:parse-rss:Error:getParse: No RSS Channels recorded!");
+ LOG.fine("nutch:parse-rss:Error:getParse: No RSS Channels recorded!");
}
// format the outlinks
+ Outlink[] outlinks = (Outlink[]) theOutlinks.toArray(new Outlink[theOutlinks.size()]);
- Outlink[] outlinks = (Outlink[]) theOutlinks
- .toArray(new Outlink[theOutlinks.size()]);
-
- LOG.fine("nutch:parse-rss:getParse:found " + outlinks.length
- + " outlinks");
+ LOG.fine("nutch:parse-rss:getParse:found " + outlinks.length + " outlinks");
// LOG.info("Outlinks: "+outlinks);
ParseData parseData = new ParseData(ParseStatus.STATUS_SUCCESS,
contentTitle.toString(), outlinks, content.getMetadata());
return new ParseImpl(indexText.toString(), parseData);
-
}
}