MapReduce Join应用 Reduce Join

一、Reduce Join

Map端的主要工作：为来自不同表或文件的key/value对，打标签以区别不同来源的记录。然后用连接字段作为key，其余部分和新加的标志作为value，最后进行输出。

Reduce端的主要工作：在Reduce端以连接字段作为key的分组已经完成，我们只需要在每一个分组当中将那些来源于不同文件的记录（在Map阶段已经打标志）分开，最后进行合并就ok了。

二、Reduce Join案例实操

1. 需求

有两个文件

order.txt

1001	01	1
1002	02	2
1003	03	3
1004	01	4
1005	02	5
1006	03	6

pd.txt

01	小米
02	华为
03	格力

相当于以下两个表

id	pid	amount
1001	01	1
1002	02	2
1003	03	3
1004	01	4
1005	02	5
1006	03	6

pid	pname
01	小米
02	华为
03	格力

需要将商品信息表中数据根据商品pid合并到订单数据表中，最终效果为:

id	pname	amount
1001	小米	1
1004	小米	4
1002	华为	2
1005	华为	5
1003	格力	3
1006	格力	6

2. 需求分析

通过将关联条件作为Map输出的key，将两表满足Join条件的数据并携带数据所来源的文件信息，发往同一个ReduceTask，在Reduce中进行数据的串联。

3. 代码实现

（1）创建商品和订单合并后的TableBean类

package com.atguigu.mapreduce.reducejoin;

import org.apache.hadoop.io.Writable;

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

public class TableBean implements Writable {

    private String id; //订单id
    private String pid; //产品id
    private int amount; //产品数量
    private String pname; //产品名称
    private String flag; //判断是order表还是pd表的标志字段

    public TableBean() {
    }

    public String getId() {
        return id;
    }

    public void setId(String id) {
        this.id = id;
    }

    public String getPid() {
        return pid;
    }

    public void setPid(String pid) {
        this.pid = pid;
    }

    public int getAmount() {
        return amount;
    }

    public void setAmount(int amount) {
        this.amount = amount;
    }

    public String getPname() {
        return pname;
    }

    public void setPname(String pname) {
        this.pname = pname;
    }

    public String getFlag() {
        return flag;
    }

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

    @Override
    public String toString() {
        return id + "\t" + pname + "\t" + amount;
    }

    @Override
    public void write(DataOutput out) throws IOException {
        out.writeUTF(id);
        out.writeUTF(pid);
        out.writeInt(amount);
        out.writeUTF(pname);
        out.writeUTF(flag);
    }

    @Override
    public void readFields(DataInput in) throws IOException {
        this.id = in.readUTF();
        this.pid = in.readUTF();
        this.amount = in.readInt();
        this.pname = in.readUTF();
        this.flag = in.readUTF();
    }
}

（2）编写TableMapper类

package com.atguigu.mapreduce.reducejoin;

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

import java.io.IOException;

public class TableMapper extends Mapper<LongWritable,Text,Text,TableBean> {

    private String filename;
    private Text outK = new Text();
    private TableBean outV = new TableBean();

    @Override
    protected void setup(Context context) throws IOException, InterruptedException {
        //获取对应文件名称
        InputSplit split = context.getInputSplit();
        FileSplit fileSplit = (FileSplit) split;
        filename = fileSplit.getPath().getName();
    }

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

        //获取一行
        String line = value.toString();

        //判断是哪个文件,然后针对文件进行不同的操作
        if(filename.contains("order")){  //订单表的处理
            String[] split = line.split("\t");
            //封装outK
            outK.set(split[1]);
            //封装outV
            outV.setId(split[0]);
            outV.setPid(split[1]);
            outV.setAmount(Integer.parseInt(split[2]));
            outV.setPname("");
            outV.setFlag("order");
        }else {                             //商品表的处理
            String[] split = line.split("\t");
            //封装outK
            outK.set(split[0]);
            //封装outV
            outV.setId("");
            outV.setPid(split[0]);
            outV.setAmount(0);
            outV.setPname(split[1]);
            outV.setFlag("pd");
        }

        //写出KV
        context.write(outK,outV);
    }
}

（3）编写TableReducer类

package com.atguigu.mapreduce.reducejoin;

import org.apache.commons.beanutils.BeanUtils;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;
import java.lang.reflect.InvocationTargetException;
import java.util.ArrayList;

public class TableReducer extends Reducer<Text,TableBean,TableBean, NullWritable> {

    @Override
    protected void reduce(Text key, Iterable<TableBean> values, Context context) throws IOException, InterruptedException {

        ArrayList<TableBean> orderBeans = new ArrayList<>();
        TableBean pdBean = new TableBean();

        for (TableBean value : values) {

            //判断数据来自哪个表
            if("order".equals(value.getFlag())){   //订单表

			  //创建一个临时TableBean对象接收value
                TableBean tmpOrderBean = new TableBean();

                try {
                    BeanUtils.copyProperties(tmpOrderBean,value);
                } catch (IllegalAccessException e) {
                    e.printStackTrace();
                } catch (InvocationTargetException e) {
                    e.printStackTrace();
                }

			  //将临时TableBean对象添加到集合orderBeans
                orderBeans.add(tmpOrderBean);
            }else {                                    //商品表
                try {
                    BeanUtils.copyProperties(pdBean,value);
                } catch (IllegalAccessException e) {
                    e.printStackTrace();
                } catch (InvocationTargetException e) {
                    e.printStackTrace();
                }
            }
        }

        //遍历集合orderBeans,替换掉每个orderBean的pid为pname,然后写出
        for (TableBean orderBean : orderBeans) {

            orderBean.setPname(pdBean.getPname());

		   //写出修改后的orderBean对象
            context.write(orderBean,NullWritable.get());
        }
    }
}

（4）编写TableDriver类

package com.atguigu.mapreduce.reducejoin;

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;

import java.io.IOException;

public class TableDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Job job = Job.getInstance(new Configuration());

        job.setJarByClass(TableDriver.class);
        job.setMapperClass(TableMapper.class);
        job.setReducerClass(TableReducer.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(TableBean.class);

        job.setOutputKeyClass(TableBean.class);
        job.setOutputValueClass(NullWritable.class);

        FileInputFormat.setInputPaths(job, new Path("D:\\input"));
        FileOutputFormat.setOutputPath(job, new Path("D:\\output"));

        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0 : 1);
    }
}

总结

缺点：这种方式中，合并的操作是在Reduce阶段完成，Reduce端的处理压力太大，Map节点的运算负载则很低，资源利用率不高，且在Reduce阶段极易产生数据倾斜。

解决方案：Map端实现数据合并。