Author: markus
Date: Wed Aug 10 12:26:49 2011
New Revision: 1156132
URL: http://svn.apache.org/viewvc?rev=1156132&view=rev
Log:
NUTCH-1028 Log urls when parsing
Modified:
nutch/branches/branch-1.4/CHANGES.txt
nutch/branches/branch-1.4/src/java/org/apache/nutch/parse/ParseSegment.java
Modified: nutch/branches/branch-1.4/CHANGES.txt
URL:
http://svn.apache.org/viewvc/nutch/branches/branch-1.4/CHANGES.txt?rev=1156132&r1=1156131&r2=1156132&view=diff
==============================================================================
--- nutch/branches/branch-1.4/CHANGES.txt (original)
+++ nutch/branches/branch-1.4/CHANGES.txt Wed Aug 10 12:26:49 2011
@@ -2,6 +2,8 @@ Nutch Change Log
Release 1.4 - Current development
+* NUTCH-1028 Log urls when parsing (markus)
+
* NUTCH-1065 New mvn.template (lewismc)
* NUTCH-1072 Display number and size of queues in Fetcher status (jnioche)
Modified:
nutch/branches/branch-1.4/src/java/org/apache/nutch/parse/ParseSegment.java
URL:
http://svn.apache.org/viewvc/nutch/branches/branch-1.4/src/java/org/apache/nutch/parse/ParseSegment.java?rev=1156132&r1=1156131&r2=1156132&view=diff
==============================================================================
--- nutch/branches/branch-1.4/src/java/org/apache/nutch/parse/ParseSegment.java
(original)
+++ nutch/branches/branch-1.4/src/java/org/apache/nutch/parse/ParseSegment.java
Wed Aug 10 12:26:49 2011
@@ -93,9 +93,10 @@ public class ParseSegment extends Config
Text url = entry.getKey();
Parse parse = entry.getValue();
ParseStatus parseStatus = parse.getData().getStatus();
-
+
+ LOG.info("Parsing: " + url);
reporter.incrCounter("ParserStatus",
ParseStatus.majorCodes[parseStatus.getMajorCode()], 1);
-
+
if (!parseStatus.isSuccess()) {
LOG.warn("Error parsing: " + key + ": " + parseStatus);
parse = parseStatus.getEmptyParse(getConf());