[置顶] Hadoop2.2.0源码分析（一）——Eclipse运行WordCount.java

    学习一门技术，并不仅仅要会用，还要知道它的原理，这里简单分析一下Hadoop样例程序源码，便于后边的学习（分析的不到位，还望各位指教）。

    在hadoop-2.2.0.tar.gz文件下没有找到源码（新版本不但没有Eclipse插件，也没有源码，只有.class字节码文件），可以下载hadoop-2.2.0-src.tar.gz，解压，然后在hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples目录下获取源码。

/**
 * 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.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<Object, Text, Text, IntWritable>{
    
    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();
    // value已经是文件内容的一行
    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();

    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();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length != 2) {
      System.err.println("Usage: wordcount <in> <out>");
      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);
  }
}

    在Eclipse中创建一个MapReduce Project，然后新建Java类，例如创建一个MyWordCount 类，然后将WordCount.java程序代码拷贝到MyWordCount.java文件中。然后点击Run-->Run Configurations…，在弹出的对话框中左边栏选择Java Application，选中MyWordCount，在右边栏中对Arguments进行配置。

在Program arguments中配置输入输出目录参数

/home/jack/Desktop/in /home/jack/Desktop/out

在VM arguments中配置VM arguments的参数

-Xms512m -Xmx1024m -XX:MaxPermSize=256m

注：

1. in文件夹是需要在程序运行前创建的，并且要放入需要统计词频的文件，out文件夹是不能提前创建的，要由系统自动生成，否则运行时会出现Output directory file:/home/jack/Desktop/out already exists错误。
2. 文件输入和输出目录为本地文件系统中的文件。
3. 程序运行需要点击菜单栏上的Run。

    程序运行结束后，可以在/home/jack/Desktop/out目录下的part-r-00000文件查看到词频统计的结果。