第一个Hadoop程序WordCount

首先说一下在eclipse下搭建Hadoop开发环境

1. 准备工具：eclipse ，hadoop插件，注意版本要一致
   eclipse可以去官网下载
   插件我上传了一个，hadoop-eclipse-plugin-2.7.2.jar

2. 将插件cp到eclipse/plugins下面

3. Window -> Open Perspective -> Other 选择Map/Reduce

4. 在eclipse下端，控制台旁边会多一个Tab，叫“Map/Reduce Locations”，在下面空白的地方点右键，选择“New Hadoop location…”在弹出的对话框中填写如下内容：

   Location name（取个名字）
   Map/Reduce Master（Job Tracker的IP和端口，根据mapred-site.xml中配置的mapred.job.tracker来填写）
   DFS Master（Name Node的IP和端口，根据core-site.xml中配置的fs.default.name来填写）

5. 创建MapReduce工程

   5.1配置Hadoop路径

   Window -> Preferences 选择 “Hadoop Map/Reduce”，点击“Browse…”选择Hadoop文件夹的路径。
   这个步骤与运行环境无关，只是在新建工程的时候能将hadoop根目录和lib目录下的所有jar包自动导入。
   5.2创建工程

   File -> New -> Project 选择“Map/Reduce Project”，然后输入项目名称，创建项目。插件会自动把hadoop根目录和lib目录下的所有jar包导入。
   5.3创建Mapper或者Reducer

   File -> New -> Mapper 创建Mapper，自动继承mapred包里面的MapReduceBase并实现Mapper接口。
   注意：这个插件自动继承的是mapred包里旧版的类和接口，新版的Mapper得自己写。

   Reducer同理。
   下面是wordcount源码：

import java.io.IOException;
import java.util.Iterator;
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.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.TextInputFormat;
import org.apache.hadoop.mapred.TextOutputFormat;
import org.apache.hadoop.mapreduce.Job;

import sun.util.locale.StringTokenIterator;


public class WordCount {

    public static class MapClass extends MapReduceBase implements Mapper<LongWritable, Text, Text, IntWritable>{
        private final static IntWritable one=new IntWritable(1);
        private Text word=new Text();
        public void map(LongWritable key,Text value,OutputCollector<Text, IntWritable> output,Reporter reporter)throws IOException{
            String line=value.toString();
            StringTokenizer stringTokenizer=new StringTokenizer(line);
            while(stringTokenizer.hasMoreTokens()){
                word.set(stringTokenizer.nextToken());
                output.collect(word, one);
            }
        }

    }
    public static class Reduce extends MapReduceBase implements Reducer<Text, IntWritable, Text, IntWritable>{
        public void reduce(Text key,Iterator<IntWritable> value,OutputCollector<Text, IntWritable> output,Reporter reporter)throws IOException{
            int sum=0;
            while(value.hasNext()){
                sum+=value.next().get();
            }
            output.collect(key, new IntWritable(sum));
        }
    }

    public static void main(String[] args) throws Exception{
        // TODO Auto-generated method stub
        Configuration conf=new Configuration();
        JobConf job=new JobConf(conf,WordCount.class);
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        job.setJobName("wordcount");
        job.setMapperClass(MapClass.class);
        job.setReducerClass(Reduce.class);
        job.setInputFormat(TextInputFormat.class);
        job.setOutputFormat(TextOutputFormat.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        JobClient.runJob(job);
    }

}