Author: kubes
Date: Mon Apr 2 14:40:10 2007
New Revision: 524932
URL: http://svn.apache.org/viewvc?view=rev&rev=524932
Log:
NUTCH-333 - SegmentMerger and SegmentReader should use NutchJob. Patch
supplied originally by Michael Stack and updated by Doğacan Güney.
Modified:
lucene/nutch/trunk/src/java/org/apache/nutch/segment/SegmentMerger.java
lucene/nutch/trunk/src/java/org/apache/nutch/segment/SegmentReader.java
Modified:
lucene/nutch/trunk/src/java/org/apache/nutch/segment/SegmentMerger.java
URL:
http://svn.apache.org/viewvc/lucene/nutch/trunk/src/java/org/apache/nutch/segment/SegmentMerger.java?view=diff&rev=524932&r1=524931&r2=524932
==============================================================================
--- lucene/nutch/trunk/src/java/org/apache/nutch/segment/SegmentMerger.java
(original)
+++ lucene/nutch/trunk/src/java/org/apache/nutch/segment/SegmentMerger.java Mon
Apr 2 14:40:10 2007
@@ -18,17 +18,37 @@
package org.apache.nutch.segment;
import java.io.IOException;
-import java.util.*;
+import java.util.ArrayList;
+import java.util.HashMap;
+import java.util.Iterator;
+import java.util.TreeMap;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
-
-import org.apache.hadoop.conf.*;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.fs.PathFilter;
-import org.apache.hadoop.io.*;
-import org.apache.hadoop.mapred.*;
+import org.apache.hadoop.io.MapFile;
+import org.apache.hadoop.io.SequenceFile;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.io.UTF8;
+import org.apache.hadoop.io.Writable;
+import org.apache.hadoop.io.WritableComparable;
+import org.apache.hadoop.mapred.FileSplit;
+import org.apache.hadoop.mapred.InputSplit;
+import org.apache.hadoop.mapred.JobClient;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.mapred.Mapper;
+import org.apache.hadoop.mapred.OutputCollector;
+import org.apache.hadoop.mapred.OutputFormatBase;
+import org.apache.hadoop.mapred.RecordReader;
+import org.apache.hadoop.mapred.RecordWriter;
+import org.apache.hadoop.mapred.Reducer;
+import org.apache.hadoop.mapred.Reporter;
+import org.apache.hadoop.mapred.SequenceFileInputFormat;
+import org.apache.hadoop.mapred.SequenceFileRecordReader;
import org.apache.hadoop.util.Progressable;
import org.apache.nutch.crawl.CrawlDatum;
import org.apache.nutch.crawl.Generator;
@@ -39,6 +59,7 @@
import org.apache.nutch.parse.ParseText;
import org.apache.nutch.protocol.Content;
import org.apache.nutch.util.NutchConfiguration;
+import org.apache.nutch.util.NutchJob;
/**
* This tool takes several segments and merges their data together. Only the
@@ -482,7 +503,7 @@
if (LOG.isInfoEnabled()) {
LOG.info("Merging " + segs.length + " segments to " + out + "/" +
segmentName);
}
- JobConf job = new JobConf(getConf());
+ JobConf job = new NutchJob(getConf());
job.setJobName("mergesegs " + out + "/" + segmentName);
job.setBoolean("segment.merger.filter", filter);
job.setLong("segment.merger.slice", slice);
Modified:
lucene/nutch/trunk/src/java/org/apache/nutch/segment/SegmentReader.java
URL:
http://svn.apache.org/viewvc/lucene/nutch/trunk/src/java/org/apache/nutch/segment/SegmentReader.java?view=diff&rev=524932&r1=524931&r2=524932
==============================================================================
--- lucene/nutch/trunk/src/java/org/apache/nutch/segment/SegmentReader.java
(original)
+++ lucene/nutch/trunk/src/java/org/apache/nutch/segment/SegmentReader.java Mon
Apr 2 14:40:10 2007
@@ -17,18 +17,48 @@
package org.apache.nutch.segment;
-import java.io.*;
+import java.io.BufferedReader;
+import java.io.BufferedWriter;
+import java.io.IOException;
+import java.io.InputStreamReader;
+import java.io.OutputStreamWriter;
+import java.io.PrintStream;
+import java.io.PrintWriter;
+import java.io.Writer;
import java.text.SimpleDateFormat;
-import java.util.*;
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.Date;
+import java.util.HashMap;
+import java.util.Iterator;
+import java.util.List;
+import java.util.Map;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
-
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
-import org.apache.hadoop.fs.*;
-import org.apache.hadoop.io.*;
-import org.apache.hadoop.mapred.*;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.fs.PathFilter;
+import org.apache.hadoop.io.MapFile;
+import org.apache.hadoop.io.ObjectWritable;
+import org.apache.hadoop.io.SequenceFile;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.io.UTF8;
+import org.apache.hadoop.io.Writable;
+import org.apache.hadoop.io.WritableComparable;
+import org.apache.hadoop.mapred.JobClient;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.mapred.MapFileOutputFormat;
+import org.apache.hadoop.mapred.MapReduceBase;
+import org.apache.hadoop.mapred.Mapper;
+import org.apache.hadoop.mapred.OutputCollector;
+import org.apache.hadoop.mapred.RecordWriter;
+import org.apache.hadoop.mapred.Reducer;
+import org.apache.hadoop.mapred.Reporter;
+import org.apache.hadoop.mapred.SequenceFileInputFormat;
+import org.apache.hadoop.mapred.SequenceFileOutputFormat;
import org.apache.hadoop.util.Progressable;
import org.apache.nutch.crawl.CrawlDatum;
import org.apache.nutch.parse.ParseData;
@@ -36,6 +66,7 @@
import org.apache.nutch.protocol.Content;
import org.apache.nutch.util.LogUtil;
import org.apache.nutch.util.NutchConfiguration;
+import org.apache.nutch.util.NutchJob;
/** Dump the content of a segment. */
public class SegmentReader extends Configured implements Reducer {
@@ -120,7 +151,7 @@
}
private JobConf createJobConf() {
- JobConf job = new JobConf(getConf());
+ JobConf job = new NutchJob(getConf());
job.setBoolean("segment.reader.co", this.co);
job.setBoolean("segment.reader.fe", this.fe);
job.setBoolean("segment.reader.ge", this.ge);
-------------------------------------------------------------------------
Take Surveys. Earn Cash. Influence the Future of IT
Join SourceForge.net's Techsay panel and you'll get the chance to share your
opinions on IT & business topics through brief surveys-and earn cash
http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV
_______________________________________________
Nutch-cvs mailing list
Nutch-cvs@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/nutch-cvs
