MapReduce的单元测试框架MRUnit

最近在写MapReduce程序，写完后再放到hadoop集群上跑，发现不是很方便。然后在window环境上装了eclipse直接写程序远程提交job到hadoop集群上，大大提高了效率。但是mapreduce的单元测试工具还是得要的，有利于程序的调试。

Apache官方提供了MRUnit框架用来专门测试MapReduce程序，它是基于Junit框架的。链接如下：

http://mrunit.apache.org/general/downloads.html

下载最新的apache-mrunit-1.0.0-hadoop1-bin.tar.gz，解压将其jar包放在Project的BuildPath下面。

以求气象温度的mapreduce代码为例子写单元测试

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

import org.apache.hadoop.io.*;
import org.apache.hadoop.mrunit.mapreduce.MapDriver;
import org.apache.hadoop.mrunit.mapreduce.MapReduceDriver;
import org.apache.hadoop.mrunit.mapreduce.ReduceDriver;
import org.junit.*;

public class AvgTemperatureTest {
	MapDriver<LongWritable, Text, Text, IntWritable> mapDriver;
	ReduceDriver<Text, IntWritable, Text, IntWritable> reduceDriver;
	MapReduceDriver<LongWritable, Text, Text, IntWritable, Text, IntWritable> mapReduceDriver;
	
	
	 @Before
	  public void setUp() {
		AvgTemperatureMapper mapper = new AvgTemperatureMapper();
		AvgTemperatureReducer reducer = new AvgTemperatureReducer();
	    mapDriver = MapDriver.newMapDriver(mapper);;
	    reduceDriver = ReduceDriver.newReduceDriver(reducer);
	    mapReduceDriver = MapReduceDriver.newMapReduceDriver(mapper, reducer);
	  }
	 
	 @Test
	  public void testMapper() throws IOException{
	  // Temperature
	  Text value = new Text("0043011990999991950051518004+68750+023550FM-12+0382" + "99999V0203201N00261220001CN9999999N9-00111+99999999999");
	  
	  mapDriver.withInput(new LongWritable(), value);
	  mapDriver.withOutput(new Text("1950"), new IntWritable(-11));
	  mapDriver.runTest();
	 }
	 
	 @Test
	  public void testReducer() throws IOException {
	    List<IntWritable> values = new ArrayList<IntWritable>();
	    values.add(new IntWritable(40));
	    values.add(new IntWritable(42));
	    reduceDriver.withInput(new Text("1950"), values);
	    reduceDriver.withOutput(new Text("1950"), new IntWritable(41));
	    reduceDriver.runTest();
	  }

}