Intellij idea开发Hadoop MapReduce程序

一、下载一个Hadoop包

http://mirrors.hust.edu.cn/apache/hadoop/common/

二、打开Idea新建一个java项目

三、项目配置 File ---- Project Structure

        1. SDK的配置

        2. 加入Hadoop的jar包依赖

        3.打包配置

        4.开发map-reduce代码

import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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 Dedup {

    //map将输入中的value复制到输出数据的key上，并直接输出
    public static class Map extends Mapper{
        private static Text line=new Text();//每行数据

        //实现map函数
        public void map(Object key,Text value,Context context)
                throws IOException,InterruptedException{

            line=value;
            context.write(line, new Text(""));
        }

    }



    //reduce将输入中的key复制到输出数据的key上，并直接输出
    public static class Reduce extends Reducer{
        
        //实现reduce函数
        public void reduce(Text key,Iterable values,Context context)
                throws IOException,InterruptedException{

            context.write(key, new Text(""));
        }

    }



    public static void main(String[] args) throws Exception{

        Configuration conf = new Configuration();
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

        Job job = new Job(conf, "Data Deduplication");
        job.setJarByClass(Dedup.class);

        //设置Map、Combine和Reduce处理类
        job.setMapperClass(Map.class);
        job.setCombinerClass(Reduce.class);
        job.setReducerClass(Reduce.class);

        //设置输出类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);

        //设置输入和输出目录
        FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }

}

        5.配置编译器

        5.运行结果