http://abloz.com

hadoop自帶一個wordcount的示例程式碼，用於計算單詞個數。我將其單獨移出來，測試成功。原始碼如下：

package org.apache.hadoop.examples;

import java.io.IOException;
import java.util.StringTokenizer;

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.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop
 
.util.GenericOptionsParser;

public class WordCount {

  public static class TokenizerMapper
       extends Mapper{

    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();

    public void map(Object key, Text value, Context context
                    ) throws
 
 IOException, InterruptedException {
      StringTokenizer itr = new StringTokenizer(value.toString());
      while (itr.hasMoreTokens()) {
        word  = new Text(itr.nextToken()); //to unitest,should be new Text word.set(itr.nextToken())
        context.write(word, new IntWritable(1));
      }
    }
  }

  public static class IntSumReducer
       extends Reducer {
    private IntWritable result = new IntWritable();

    public void reduce(Text key, Iterable 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();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length != 2) {
      System.err.println("Usage: wordcount  ");
      System.exit(2);
    }
    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.addInputPath(job, new Path(otherArgs[0]));
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

現在我想對其進行單元測試。一種方式，是job執行完了後，讀取輸出目錄中的檔案，確認計數是否正確。但這樣的情況如果失敗，也不知道是哪裡失敗。我們需要對map和reduce單獨進行測試。 tomwhite的書《hadoop權威指南》有提到如何用Mockito進行單元測試，我們依照原書對溫度的單元測試來對wordcount進行單元測試。(原書第二版的示例已經過時，可以參考英文版第三版或我的程式)。

package org.apache.hadoop.examples;
/* author zhouhh
 * date:2012.8.7
 */
import static org.mockito.Mockito.*;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

import org.apache.hadoop.io.*;
import org.junit.*;

public class WordCountTest {

	@Test
	public  void testWordCountMap() throws IOException, InterruptedException
	{
		WordCount w = new WordCount();
		WordCount.TokenizerMapper mapper = new WordCount.TokenizerMapper();
		Text value = new Text("a b c b a a");
		@SuppressWarnings("unchecked")
		WordCount.TokenizerMapper.Context context = mock(WordCount.TokenizerMapper.Context.class);
		mapper.map(null, value, context);
		verify(context,times(3)).write(new Text("a"), new IntWritable(1));
		verify(context).write(new Text("c"), new IntWritable(1));
		//verify(context).write(new Text("cc"), new IntWritable(1));

	}

	@Test
	public void testWordCountReduce() throws IOException, InterruptedException
	{
		WordCount.IntSumReducer reducer = new WordCount.IntSumReducer();
		WordCount.IntSumReducer.Context context = mock(WordCount.IntSumReducer.Context.class);
		Text key = new Text("a");
		List values = new ArrayList();
		values.add(new IntWritable(1));
		values.add(new IntWritable(1));
		reducer.reduce(key, values, context);

		verify(context).write(new Text("a"), new IntWritable(2));

	}

	public static void main(String[] args) {
//		try {
//			WordCountTest t = new WordCountTest();
//
//			//t.testWordCountMap();
//			t.testWordCountReduce();
//		} catch (IOException e) {
//			// TODO Auto-generated catch block
//			e.printStackTrace();
//		} catch (InterruptedException e) {
//			// TODO Auto-generated catch block
//			e.printStackTrace();
//		}

	}

}

verify(context)只檢查一次的寫，如果多次寫，需用verify(contex,times(n))檢查,否則會失敗。

執行時在測試檔案上點run as JUnit Test，會得到測試結果是否通過。 本示例程式在hadoop1.0.3環境中測試通過。Mockito也在hadoop的lib中自帶，打包在mockito-all-1.8.5.jar

參考： http://bobflagg.com/blog/unit-testing-wordcount-mapreduce-example/ http://blog.pfa-labs.com/2010/01/unit-testing-hadoop-wordcount-example.html

如非註明轉載, 均為原創. 本站遵循知識共享CC協議,轉載請註明來源