hadoop-mapreduce-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From tomwh...@apache.org
Subject svn commit: r1209281 [2/2] - in /hadoop/common/trunk/hadoop-mapreduce-project: ./ hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/conf/ hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/or...
Date Thu, 01 Dec 2011 22:29:46 GMT
Added: hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapred/WordCount.java
URL: http://svn.apache.org/viewvc/hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapred/WordCount.java?rev=1209281&view=auto
==============================================================================
--- hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapred/WordCount.java
(added)
+++ hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapred/WordCount.java
Thu Dec  1 22:29:42 2011
@@ -0,0 +1,159 @@
+/**
+ * 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;
+
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.Iterator;
+import java.util.List;
+import java.util.StringTokenizer;
+
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.conf.Configured;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.io.IntWritable;
+import org.apache.hadoop.io.LongWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapred.FileInputFormat;
+import org.apache.hadoop.mapred.FileOutputFormat;
+import org.apache.hadoop.mapred.JobClient;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.mapred.MapReduceBase;
+import org.apache.hadoop.mapred.Mapper;
+import org.apache.hadoop.mapred.OutputCollector;
+import org.apache.hadoop.mapred.Reducer;
+import org.apache.hadoop.mapred.Reporter;
+import org.apache.hadoop.util.Tool;
+import org.apache.hadoop.util.ToolRunner;
+
+/**
+ * This is an example Hadoop Map/Reduce application.
+ * It reads the text input files, breaks each line into words
+ * and counts them. The output is a locally sorted list of words and the 
+ * count of how often they occurred.
+ *
+ * To run: bin/hadoop jar build/hadoop-examples.jar wordcount
+ *            [-m <i>maps</i>] [-r <i>reduces</i>] <i>in-dir</i>
<i>out-dir</i> 
+ */
+public class WordCount extends Configured implements Tool {
+  
+  /**
+   * Counts the words in each line.
+   * For each line of input, break the line into words and emit them as
+   * (<b>word</b>, <b>1</b>).
+   */
+  public static class MapClass extends MapReduceBase
+    implements Mapper<LongWritable, Text, Text, IntWritable> {
+    
+    private final static IntWritable one = new IntWritable(1);
+    private Text word = new Text();
+    
+    public void map(LongWritable key, Text value, 
+                    OutputCollector<Text, IntWritable> output, 
+                    Reporter reporter) throws IOException {
+      String line = value.toString();
+      StringTokenizer itr = new StringTokenizer(line);
+      while (itr.hasMoreTokens()) {
+        word.set(itr.nextToken());
+        output.collect(word, one);
+      }
+    }
+  }
+  
+  /**
+   * A reducer class that just emits the sum of the input values.
+   */
+  public static class Reduce extends MapReduceBase
+    implements Reducer<Text, IntWritable, Text, IntWritable> {
+    
+    public void reduce(Text key, Iterator<IntWritable> values,
+                       OutputCollector<Text, IntWritable> output, 
+                       Reporter reporter) throws IOException {
+      int sum = 0;
+      while (values.hasNext()) {
+        sum += values.next().get();
+      }
+      output.collect(key, new IntWritable(sum));
+    }
+  }
+  
+  static int printUsage() {
+    System.out.println("wordcount [-m <maps>] [-r <reduces>] <input> <output>");
+    ToolRunner.printGenericCommandUsage(System.out);
+    return -1;
+  }
+  
+  /**
+   * The main driver for word count map/reduce program.
+   * Invoke this method to submit the map/reduce job.
+   * @throws IOException When there is communication problems with the 
+   *                     job tracker.
+   */
+  public int run(String[] args) throws Exception {
+    JobConf conf = new JobConf(getConf(), WordCount.class);
+    conf.setJobName("wordcount");
+ 
+    // the keys are words (strings)
+    conf.setOutputKeyClass(Text.class);
+    // the values are counts (ints)
+    conf.setOutputValueClass(IntWritable.class);
+    
+    conf.setMapperClass(MapClass.class);        
+    conf.setCombinerClass(Reduce.class);
+    conf.setReducerClass(Reduce.class);
+    
+    List<String> other_args = new ArrayList<String>();
+    for(int i=0; i < args.length; ++i) {
+      try {
+        if ("-m".equals(args[i])) {
+          conf.setNumMapTasks(Integer.parseInt(args[++i]));
+        } else if ("-r".equals(args[i])) {
+          conf.setNumReduceTasks(Integer.parseInt(args[++i]));
+        } else {
+          other_args.add(args[i]);
+        }
+      } catch (NumberFormatException except) {
+        System.out.println("ERROR: Integer expected instead of " + args[i]);
+        return printUsage();
+      } catch (ArrayIndexOutOfBoundsException except) {
+        System.out.println("ERROR: Required parameter missing from " +
+                           args[i-1]);
+        return printUsage();
+      }
+    }
+    // Make sure there are exactly 2 parameters left.
+    if (other_args.size() != 2) {
+      System.out.println("ERROR: Wrong number of parameters: " +
+                         other_args.size() + " instead of 2.");
+      return printUsage();
+    }
+    FileInputFormat.setInputPaths(conf, other_args.get(0));
+    FileOutputFormat.setOutputPath(conf, new Path(other_args.get(1)));
+        
+    JobClient.runJob(conf);
+    return 0;
+  }
+  
+  
+  public static void main(String[] args) throws Exception {
+    int res = ToolRunner.run(new Configuration(), new WordCount(), args);
+    System.exit(res);
+  }
+
+}

Propchange: hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapred/WordCount.java
------------------------------------------------------------------------------
    svn:eol-style = native

Added: hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapred/jobcontrol/JobControlTestUtils.java
URL: http://svn.apache.org/viewvc/hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapred/jobcontrol/JobControlTestUtils.java?rev=1209281&view=auto
==============================================================================
--- hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapred/jobcontrol/JobControlTestUtils.java
(added)
+++ hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapred/jobcontrol/JobControlTestUtils.java
Thu Dec  1 22:29:42 2011
@@ -0,0 +1,154 @@
+/**
+ * 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.jobcontrol;
+
+import java.io.IOException;
+import java.text.NumberFormat;
+import java.util.Iterator;
+import java.util.List;
+import java.util.Random;
+
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FSDataOutputStream;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.io.LongWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapred.FileInputFormat;
+import org.apache.hadoop.mapred.FileOutputFormat;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.mapred.MapReduceBase;
+import org.apache.hadoop.mapred.Mapper;
+import org.apache.hadoop.mapred.OutputCollector;
+import org.apache.hadoop.mapred.Reducer;
+import org.apache.hadoop.mapred.Reporter;
+
+/**
+ * Utility methods used in various Job Control unit tests.
+ */
+public class JobControlTestUtils {
+
+  static private Random rand = new Random();
+
+  private static NumberFormat idFormat = NumberFormat.getInstance();
+
+  static {
+    idFormat.setMinimumIntegerDigits(4);
+    idFormat.setGroupingUsed(false);
+  }
+
+  /**
+   * Cleans the data from the passed Path in the passed FileSystem.
+   * 
+   * @param fs FileSystem to delete data from.
+   * @param dirPath Path to be deleted.
+   * @throws IOException If an error occurs cleaning the data.
+   */
+  static void cleanData(FileSystem fs, Path dirPath) throws IOException {
+    fs.delete(dirPath, true);
+  }
+
+  /**
+   * Generates a string of random digits.
+   * 
+   * @return A random string.
+   */
+  private static String generateRandomWord() {
+    return idFormat.format(rand.nextLong());
+  }
+
+  /**
+   * Generates a line of random text.
+   * 
+   * @return A line of random text.
+   */
+  private static String generateRandomLine() {
+    long r = rand.nextLong() % 7;
+    long n = r + 20;
+    StringBuffer sb = new StringBuffer();
+    for (int i = 0; i < n; i++) {
+      sb.append(generateRandomWord()).append(" ");
+    }
+    sb.append("\n");
+    return sb.toString();
+  }
+
+  /**
+   * Generates data that can be used for Job Control tests.
+   * 
+   * @param fs FileSystem to create data in.
+   * @param dirPath Path to create the data in.
+   * @throws IOException If an error occurs creating the data.
+   */
+  static void generateData(FileSystem fs, Path dirPath) throws IOException {
+    FSDataOutputStream out = fs.create(new Path(dirPath, "data.txt"));
+    for (int i = 0; i < 10000; i++) {
+      String line = generateRandomLine();
+      out.write(line.getBytes("UTF-8"));
+    }
+    out.close();
+  }
+
+  /**
+   * Creates a simple copy job.
+   * 
+   * @param indirs List of input directories.
+   * @param outdir Output directory.
+   * @return JobConf initialised for a simple copy job.
+   * @throws Exception If an error occurs creating job configuration.
+   */
+  static JobConf createCopyJob(List<Path> indirs, Path outdir) throws Exception {
+
+    Configuration defaults = new Configuration();
+    JobConf theJob = new JobConf(defaults, TestJobControl.class);
+    theJob.setJobName("DataMoveJob");
+
+    FileInputFormat.setInputPaths(theJob, indirs.toArray(new Path[0]));
+    theJob.setMapperClass(DataCopy.class);
+    FileOutputFormat.setOutputPath(theJob, outdir);
+    theJob.setOutputKeyClass(Text.class);
+    theJob.setOutputValueClass(Text.class);
+    theJob.setReducerClass(DataCopy.class);
+    theJob.setNumMapTasks(12);
+    theJob.setNumReduceTasks(4);
+    return theJob;
+  }
+
+  /**
+   * Simple Mapper and Reducer implementation which copies data it reads in.
+   */
+  public static class DataCopy extends MapReduceBase implements
+      Mapper<LongWritable, Text, Text, Text>, Reducer<Text, Text, Text, Text>
{
+    public void map(LongWritable key, Text value, OutputCollector<Text, Text> output,
+        Reporter reporter) throws IOException {
+      output.collect(new Text(key.toString()), value);
+    }
+
+    public void reduce(Text key, Iterator<Text> values,
+        OutputCollector<Text, Text> output, Reporter reporter)
+        throws IOException {
+      Text dumbKey = new Text("");
+      while (values.hasNext()) {
+        Text data = values.next();
+        output.collect(dumbKey, data);
+      }
+    }
+  }
+
+}

Propchange: hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapred/jobcontrol/JobControlTestUtils.java
------------------------------------------------------------------------------
    svn:eol-style = native



Mime
View raw message