You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@nutch.apache.org by ma...@apache.org on 2011/11/11 16:16:50 UTC

svn commit: r1200915 - in /nutch/trunk: CHANGES.txt src/java/org/apache/nutch/parse/ParseSegment.java

Author: markus
Date: Fri Nov 11 15:16:49 2011
New Revision: 1200915

URL: http://svn.apache.org/viewvc?rev=1200915&view=rev
Log:
NUTCH-1203 ParseSegment to show number of milliseconds per parse

Modified:
    nutch/trunk/CHANGES.txt
    nutch/trunk/src/java/org/apache/nutch/parse/ParseSegment.java

Modified: nutch/trunk/CHANGES.txt
URL: http://svn.apache.org/viewvc/nutch/trunk/CHANGES.txt?rev=1200915&r1=1200914&r2=1200915&view=diff
==============================================================================
--- nutch/trunk/CHANGES.txt (original)
+++ nutch/trunk/CHANGES.txt Fri Nov 11 15:16:49 2011
@@ -1,5 +1,9 @@
 Nutch Change Log
 
+* NUTCH-1203 ParseSegment to show number of milliseconds per parse (markus)
+
+* NUTCH-1174 Outlinks are not properly normalized (markus)
+
 * NUTCH-1185 Decrease solr.commit.size to 250 (markus)
 
 * NUTCH-1180 UpdateDB to backup previous CrawlDB (markus)

Modified: nutch/trunk/src/java/org/apache/nutch/parse/ParseSegment.java
URL: http://svn.apache.org/viewvc/nutch/trunk/src/java/org/apache/nutch/parse/ParseSegment.java?rev=1200915&r1=1200914&r2=1200915&view=diff
==============================================================================
--- nutch/trunk/src/java/org/apache/nutch/parse/ParseSegment.java (original)
+++ nutch/trunk/src/java/org/apache/nutch/parse/ParseSegment.java Fri Nov 11 15:16:49 2011
@@ -94,7 +94,8 @@ public class ParseSegment extends Config
       Parse parse = entry.getValue();
       ParseStatus parseStatus = parse.getData().getStatus();
 
-      LOG.info("Parsing: " + url);
+      long start = System.currentTimeMillis();
+
       reporter.incrCounter("ParserStatus", ParseStatus.majorCodes[parseStatus.getMajorCode()], 1);
 
       if (!parseStatus.isSuccess()) {
@@ -120,6 +121,10 @@ public class ParseSegment extends Config
           LOG.warn("Error passing score: "+ url +": "+e.getMessage());
         }
       }
+
+      long end = System.currentTimeMillis();
+      LOG.info("Parsed (" + Long.toString(end - start) + "ms):" + url);
+
       output.collect(url, new ParseImpl(new ParseText(parse.getText()), 
                                         parse.getData(), parse.isCanonical()));
     }