MRUnit Example

WordCountをMRUnitでユニットテストを行うサンプル

依存ライブラリ

MRUnitはclassifierにhadoop1 or hadoop2を指定する必要があります

pom.xml

<dependencies>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-core</artifactId>
        <version>1.0.3</version>
    </dependency>
    <dependency>
        <groupId>org.apache.mrunit</groupId>
        <artifactId>mrunit</artifactId>
        <version>1.1.0</version>
        <classifier>hadoop1</classifier>
        <scope>test</scope>
    </dependency>
</dependencies>

プロダクトコード

WordCount.java

package examples.mrunit;

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

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;

public class WordCount {

    public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable>{
        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        @Override
        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            StringTokenizer itr = new StringTokenizer(value.toString());
            while (itr.hasMoreTokens()) {
                word.set(itr.nextToken());
                context.write(word, one);
            }
        }
    }

    public static class IntSumReducer extends Reducer<Text,IntWritable,Text,IntWritable> {
        private IntWritable result = new IntWritable();

        @Override
        public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            result.set(sum);
            context.write(key, result);
            }
        }

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = new Job(conf, "word count");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

テストコード

WordCountTest.java

package examples.mrunit;

import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mrunit.mapreduce.MapDriver;
import org.apache.hadoop.mrunit.mapreduce.MapReduceDriver;
import org.apache.hadoop.mrunit.mapreduce.ReduceDriver;
import org.junit.Before;
import org.junit.Test;

import examples.mrunit.WordCount.*;

public class WordCountTest {

    private Mapper<Object, Text, Text, IntWritable> mapper;
    private Reducer<Text, IntWritable, Text, IntWritable> reducer;

    private MapDriver<Object, Text, Text, IntWritable> mapDriver;
    private ReduceDriver<Text, IntWritable, Text, IntWritable> reduceDriver;
    private MapReduceDriver<Object, Text, Text, IntWritable, Text, IntWritable> mapReduceDriver;

    @Before
    public void setUp(){
        mapper = new TokenizerMapper();
        reducer = new IntSumReducer();

        mapDriver = new MapDriver<Object, Text, Text, IntWritable>(mapper);
        reduceDriver = new ReduceDriver<Text, IntWritable, Text, IntWritable>(reducer);
        mapReduceDriver = new MapReduceDriver<Object, Text, Text, IntWritable, Text, IntWritable>(mapper, reducer);
    }

    @Test
    public void testMapper() throws IOException{
        mapDriver.withInput(new LongWritable(1), new Text("cat cat dog"));
        mapDriver.withOutput(new Text("cat"), new IntWritable(1));
        mapDriver.withOutput(new Text("cat"), new IntWritable(1));
        mapDriver.withOutput(new Text("dog"), new IntWritable(1));
        mapDriver.runTest();
    }

    @Test
    public void testReducer() throws IOException{
        List<IntWritable> values = new ArrayList<IntWritable>();
        values.add(new IntWritable(1));
        values.add(new IntWritable(1));
        reduceDriver.withInput(new Text("cat"), values);
        reduceDriver.withOutput(new Text("cat"), new IntWritable(2));
        reduceDriver.runTest();
    }

    @Test
    public void testMapReduce() throws IOException{
        mapReduceDriver.withInput(new LongWritable(1), new Text("cat cat dog"));
        mapReduceDriver.addOutput(new Text("cat"), new IntWritable(2));
        mapReduceDriver.addOutput(new Text("dog"), new IntWritable(1));
        mapReduceDriver.runTest();
    }
}

pom.xmlとソースコードはgithub上にも置いてあります
https://github.com/ishihamat/MRUnitExample