HADOOP-1166. Add a NullOutputFormat and use it in the RandomWriter example. Contributed by Owen.

git-svn-id: https://svn.apache.org/repos/asf/lucene/hadoop/trunk@524181 13f79535-47bb-0310-9956-ffa450edef68

CHANGES.txt

@@ -58,6 +58,9 @@ Trunk (unreleased changes)
 17. HADOOP-1164.  Fix TestReplicationPolicy to specify port zero, so
     that a free port is automatically selected.  (omalley via cutting)
 
+18. HADOOP-1166.  Add a NullOutputFormat and use it in the
+    RandomWriter example.  (omalley via cutting)
+
 
 Release 0.12.3 (not yet released)
 

src/examples/org/apache/hadoop/examples/RandomWriter.java

@@ -28,7 +28,7 @@ import org.apache.hadoop.io.*;
 import org.apache.hadoop.io.SequenceFile.CompressionType;
 import org.apache.hadoop.mapred.*;
 import org.apache.hadoop.mapred.lib.IdentityReducer;
-import org.apache.hadoop.util.Progressable;
+import org.apache.hadoop.mapred.lib.NullOutputFormat;
 
 /**
  * This program uses map/reduce to just run a distributed job where there is
@@ -107,20 +107,6 @@ public class RandomWriter {
     }
   }
 
-  /**
-   * Consume all outputs and put them in /dev/null. 
-   */
-  static class DataSink implements OutputFormat {
-    public RecordWriter getRecordWriter(FileSystem ignored, JobConf job, 
-                                        String name, Progressable progress) {
-      return new RecordWriter(){
-        public void write(WritableComparable key, Writable value) { }
-        public void close(Reporter reporter) { }
-      };
-    }
-    public void checkOutputSpecs(FileSystem ignored, JobConf job) { }
-  }
-
   static class Map extends MapReduceBase implements Mapper {
     private FileSystem fileSys = null;
     private JobConf jobConf = null;
@@ -202,14 +188,6 @@ public class RandomWriter {
    * It runs 10 maps/node and each node writes 1 gig of data to a DFS file.
    * The reduce doesn't do anything.
    * 
-   * This program uses a useful pattern for dealing with Hadoop's constraints
-   * on InputSplits. Since each input split can only consist of a file and 
-   * byte range and we want to control how many maps there are (and we don't 
-   * really have any inputs), we create a directory with a set of artificial
-   * files that each contain the filename that we want a given map to write 
-   * to. Then, using the text line reader and this "fake" input directory, we
-   * generate exactly the right number of maps. Each map gets a single record
-   * that is the filename it is supposed to write its output to. 
    * @throws IOException 
    */
   public static void main(String[] args) throws IOException {
@@ -237,7 +215,7 @@ public class RandomWriter {
     job.setInputFormat(RandomInputFormat.class);
     job.setMapperClass(Map.class);        
     job.setReducerClass(IdentityReducer.class);
-    job.setOutputFormat(DataSink.class);
+    job.setOutputFormat(NullOutputFormat.class);
     
     JobClient client = new JobClient(job);
     ClusterStatus cluster = client.getClusterStatus();

src/java/org/apache/hadoop/mapred/lib/NullOutputFormat.java

@@ -0,0 +1,43 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.hadoop.mapred.lib;
+
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.io.Writable;
+import org.apache.hadoop.io.WritableComparable;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.mapred.OutputFormat;
+import org.apache.hadoop.mapred.RecordWriter;
+import org.apache.hadoop.mapred.Reporter;
+import org.apache.hadoop.util.Progressable;
+
+/**
+ * Consume all outputs and put them in /dev/null. 
+ */
+public class NullOutputFormat implements OutputFormat {
+  public RecordWriter getRecordWriter(FileSystem ignored, JobConf job, 
+                                      String name, Progressable progress) {
+    return new RecordWriter(){
+      public void write(WritableComparable key, Writable value) { }
+      public void close(Reporter reporter) { }
+    };
+  }
+  
+  public void checkOutputSpecs(FileSystem ignored, JobConf job) { }
+}