Hadoop-HelloWorld（WordCount）

<span style="font-family: Arial, Helvetica, sans-serif;">package org.apache.hadoop.examples;</span>

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 //继承Mapper类型，重写map方法
       extends Mapper<Object, Text, Text, IntWritable>{
    
    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()) {//把每行拆分成一个个单词
        word.set(itr.nextToken());
        context.write(word, one);//key为该行首字母相对于文本文件首地址的偏移量
      }
    }
  }
  
  public static class IntSumReducer //继承Reducer类，重写reduce方法
       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) {//values为对应单词的计数列表
        sum += val.get();//统计
      }
      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对象负责管理和运行一个计算任务
    job.setJarByClass(WordCount.class);
    job.setMapperClass(TokenizerMapper.class);//TokenizerMapper完成Map过程的处理和使用
    job.setCombinerClass(IntSumReducer.class);//Combine过程
    job.setReducerClass(IntSumReducer.class);//IntSumReducer完成Reduce过程的处理和使用
    job.setOutputKeyClass(Text.class);//设置输出的key类型，相当于java的string类型
    job.setOutputValueClass(IntWritable.class);//value类型为IntWritable，相当于int
    FileInputFormat.addInputPath(job, new Path(otherArgs[0]));//任务的输入路径
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));//任务输出路径
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

以上原码所在位置：

图解具体过程：（图片来自http://www.cnblogs.com/xia520pi/archive/2012/05/16/2504205.html）

①由MapReduce完成拆分

key为偏移量（Linux和Windows有区别）。

②用户定义map方法的执行过程

输入：上面过程得到的<key,value>

输出：新的<key,value>

<span style="font-size:14px;">while (itr.hasMoreTokens()) //把每行拆分成一个个单词
word.set(itr.nextToken());
context.write(word, one);//key为该行首字母相对于文本文件首地址的偏移量</span>

③Mapper将刚才得到的<key,value>，按key进行排序并将相同的key进行combine操作

④用户定义reduce方法的执行过程

int sum = 0;
for (IntWritable val : values) {//values为对应单词的计数列表list
sum += val.get();//统计