MapReduceWordCount.md

How to run a simple MapReduce job in the DOPA-VM?

In complete analogy to http://www.cloudera.com/content/cloudera-content/cloudera-docs/HadoopTutorial/CDH4/Hadoop-Tutorial.html the following steps can be performed to test a simple word count job.

sudo su hdfs
hadoop fs -mkdir /user/vagrant 
hadoop fs -chown vagrant /user/vagrant
exit
hadoop fs -mkdir /user/vagrant/wordcount /user/vagrant/wordcount/input
echo "Hello World Bye World" > file0
echo "Hello Hadoop Goodbye Hadoop" > file1
hadoop fs -put file* /user/vagrant/wordcount/input
mkdir wordcount_classes
cd wordcount_classes
vi WordCount.java

Copy the following source

package org.myorg;

import java.io.IOException;
import java.util.*;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapred.*;
import org.apache.hadoop.util.*;

public class WordCount {

  public static class Map 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 tokenizer = new StringTokenizer(line);
      while (tokenizer.hasMoreTokens()) {
        word.set(tokenizer.nextToken());
        output.collect(word, one);
      }
    }
  }

  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));
    }
  }

  public static void main(String[] args) throws Exception {
    JobConf conf = new JobConf(WordCount.class);
    conf.setJobName("wordcount");

    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(IntWritable.class);

    conf.setMapperClass(Map.class);
    conf.setCombinerClass(Reduce.class);
    conf.setReducerClass(Reduce.class);

    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);

    FileInputFormat.setInputPaths(conf, new Path(args[0]));
    FileOutputFormat.setOutputPath(conf, new Path(args[1]));

    JobClient.runJob(conf);
  }
}

in the console press i paste press (ESC):wq

javac -cp /usr/lib/hadoop/*:/usr/lib/hadoop/client-0.20/* -d wordcount_classes WordCount.java
cd ..
javac -cp /usr/lib/hadoop/*:/usr/lib/hadoop/client-0.20/* -d wordcount_classes wordcount_classes/WordCount.java
jar -cvf wordcount.jar -C wordcount_classes/ . 
hadoop jar wordcount.jar org.myorg.WordCount /user/vagrant/wordcount/input /user/vagrant/wordcount/output