Hadoop编程学习1--WordCount

package org.apache.hadoop.examples;

import java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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;

public class MyWordCount 
{
     //main方法
     public static void main(String[] args) throws Exception 
     {
        //初始化Conf 连接到HDFS 
        Configuration conf = new Configuration();
        conf.set("fs.defaultFS", "hdfs://localhost:9000/user/root");

        //指定输入输出目录
        String[] otherArgs = new String[]{"/user/root/input","/user/root/output"};

        Path path = new Path(otherArgs[1]); 

        //如果输出路径已存在则删除
        FileSystem fileSystem = path.getFileSystem(conf);       
        if (fileSystem.exists(new Path(otherArgs[1]))) 
        {  
           fileSystem.delete(new Path(otherArgs[1]),true);  
        }  

        //如果不是一个输入一个输出路径,则报错
        if(otherArgs.length < 2) 
        {
            System.err.println("Usage: wordcount <in> [<in>...] <out>");
            System.exit(2);
        }

        Job job = Job.getInstance(conf, "word count");  //Job(Configuration conf, String jobName) 设置job名称
        job.setJarByClass(MyWordCount.class);
        job.setMapperClass(MyWordCount.TokenizerMapper.class);  //为job设置Mapper类 
        job.setCombinerClass(MyWordCount.IntSumReducer.class);  //为job设置Combiner类 
        job.setReducerClass(MyWordCount.IntSumReducer.class);  //为job设置Reduce类 

        job.setOutputKeyClass(Text.class);  //设置输出key的类型
        job.setOutputValueClass(IntWritable.class); //设置输出value的类型

        FileInputFormat.addInputPath(job, new Path(otherArgs[0]));  //为map-reduce任务设置InputFormat实现类   设置输入路径
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));  //为map-reduce任务设置OutputFormat实现类  设置输出路径
        System.exit(job.waitForCompletion(true)?0:1);
    }

    //Map类，继承自Mapper类--一个抽象类
    public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> 
    {
        //每个单词都在Context中写入1（频次）
        private static final IntWritable one = new IntWritable(1);

        //Text 实现了BinaryComparable类可以作为key值
        private Text word = new Text();   

        public void map(Object key, Text value, Mapper<Object, Text, Text, IntWritable>.Context context) throws IOException, InterruptedException 
        {
            StringTokenizer itr = new StringTokenizer(value.toString()); //得到什么值   StringTokenizer是分割String串的方法

            //如果itr还有下一个分割的值
            while(itr.hasMoreTokens()) 
            {
                //word为Text类型，要用set方法定义值
                this.word.set(itr.nextToken());

                //写入context（上下文，传给Reduce节点）
                context.write(this.word, one);
            }
        }
    }

  //Reduce类，继承自Reducer类--一个抽象类
public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> 
{
        private IntWritable result = new IntWritable();
        public void reduce(Text key, Iterable<IntWritable> values, Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException 
        {
            int sum = 0;

            IntWritable val;

            //对于每一个相同的key值即word，计算所有节点传入的频次和
            for(Iterator i = values.iterator(); i.hasNext(); sum += val.get()) 
            {
                val = (IntWritable)i.next();
            }

            this.result.set(sum);

            //key为word，result为频次
            context.write(key, this.result);
        } 
    }
}

代码有很清晰的注释，看不懂的话可以评论给我，input目录文件及运行结果output目录如下：

DFS文件目录：

/input/a.txt

/input/aa.txt

/output/part-r-00000