MapReduce的Join应用

 先写一个实体类

package com.kgc.myhdfs001.join;

import org.apache.hadoop.io.Writable;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

/*
两张表custmoers表和orders表
customers表里面有userid、username、age
orders表里面有orderid、userid、goodid、buynum
 */
public class CustomOrder implements Writable {
    private String userid="";
    private String username="";
    private String age="";
    private String orderid="";
    private String goodid="";
    private String buynum="";
    private String flag="";//标志属性 区分你写入的表是customers还是orders 1：orders 0：customers

    @Override
    //重写序列化方法
    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeUTF(userid);
        dataOutput.writeUTF(username);
        dataOutput.writeUTF(age);
        dataOutput.writeUTF(orderid);
        dataOutput.writeUTF(goodid);
        dataOutput.writeUTF(buynum);
        dataOutput.writeUTF(flag);

    }

    @Override
    //重写反序列化方法
    //注意反序列化的顺序和序列化的顺序完全一致
    public void readFields(DataInput dataInput) throws IOException {
        userid=dataInput.readUTF();
        username=dataInput.readUTF();
        age=dataInput.readUTF();
        orderid=dataInput.readUTF();
        goodid=dataInput.readUTF();
        buynum=dataInput.readUTF();
        flag=dataInput.readUTF();
    }

    public CustomOrder() {
    }

    public CustomOrder(String userid, String username, String age, String orderid, String goodid, String buynum, String flag) {
        this.userid = userid;
        this.username = username;
        this.age = age;
        this.orderid = orderid;
        this.goodid = goodid;
        this.buynum = buynum;
        this.flag = flag;
    }

    @Override
    public String toString() {
        return "CustomOrder{" +
                "userid='" + userid + '\'' +
                ", username='" + username + '\'' +
                ", age='" + age + '\'' +
                ", orderid='" + orderid + '\'' +
                ", goodid='" + goodid + '\'' +
                ", buynum='" + buynum + '\'' +
                ", flag='" + flag + '\'' +
                '}';
    }

    public String getUserid() {
        return userid;
    }

    public void setUserid(String userid) {
        this.userid = userid;
    }

    public String getUsername() {
        return username;
    }

    public void setUsername(String username) {
        this.username = username;
    }

    public String getAge() {
        return age;
    }

    public void setAge(String age) {
        this.age = age;
    }

    public String getOrderid() {
        return orderid;
    }

    public void setOrderid(String orderid) {
        this.orderid = orderid;
    }

    public String getGoodid() {
        return goodid;
    }

    public void setGoodid(String goodid) {
        this.goodid = goodid;
    }

    public String getBuynum() {
        return buynum;
    }

    public void setBuynum(String buynum) {
        this.buynum = buynum;
    }

    public String getFlag() {
        return flag;
    }

    public void setFlag(String flag) {
        this.flag = flag;
    }
}

然后写JoinedMapper

package com.kgc.myhdfs001.join;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;

import java.io.IOException;

public class JoinedMapper extends Mapper {
    String fileName;
    @Override
    //初始化方法
    protected void setup(Context context) throws IOException, InterruptedException {
       //获得用户读入的文件信息
       FileSplit fs= (FileSplit)context.getInputSplit();
       //将文件名存放到全局变量
        fileName=fs.getPath().getName();
    }

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
       //准备一个CustomOrder对象根据不同的文件名填充不同的属性
        CustomOrder co=new CustomOrder();
        //分割字符串
        String[] infos = value.toString().split(",");
        if(fileName.startsWith("order")){
            co.setOrderid(infos[0]);
            co.setUserid(infos[1]);
            co.setGoodid(infos[2]);
            co.setBuynum(infos[3]);

            co.setFlag("1");
        }else {
            co.setUserid(infos[0]);
            co.setUsername(infos[1]);
            co.setAge(infos[2]);

            co.setFlag("0");
        }

        //设置mapper输出的key是用户userid
        context.write(new Text(co.getUserid()),co);
    }
}

然后写JoinedReducer

package com.kgc.myhdfs001.join;

import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

public class JoinedReducer extends Reducer {
    @Override
    protected void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException {
        CustomOrder fillCs=new CustomOrder();
        for(CustomOrder co:values){
            if(co.getFlag().equals("0")){
                fillCs.setUserid(co.getUserid());
                fillCs.setUsername(co.getUsername());
                fillCs.setAge(co.getAge());
            }else {
                fillCs.setOrderid(co.getOrderid());
                fillCs.setGoodid(co.getGoodid());
                fillCs.setBuynum(co.getBuynum());
            }
        }
        context.write(fillCs,NullWritable.get());
    }
}

最后写主Job类 

package com.kgc.myhdfs001.join;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class JoinedJob {
    public static void main(String[] args) throws Exception{
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        job.setJarByClass(JoinedJob.class);

        Path path=new Path("file:///d:/temp02/write/");
        if(path.getFileSystem(conf).exists(path)){
            path.getFileSystem(conf).delete(path,true);
        }

        FileInputFormat.setInputPaths(job,new Path("file:///d:/temp02/read/"));
        FileOutputFormat.setOutputPath(job,new Path("file:///d:/temp02/write/"));

        job.setMapperClass(JoinedMapper.class);
        //指定本次mr程序map阶段的输出类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(CustomOrder.class);

        //指定本次mr程序的reducer
        job.setReducerClass(JoinedReducer.class);
        //指定本次mr程序reduce阶段的输出类型
        job.setOutputKeyClass(CustomOrder.class);
        job.setOutputValueClass(NullWritable.class);

        job.waitForCompletion(true);
    }
}