Reduce Join案例实操

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。

代码实现

（1）创建商品和订单合并后的TableBean类

package com.mischen.mapreduce.wordcount.reduceJoin;

import org.apache.hadoop.io.Writable;

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

/**
 * @ClassName TableBean
 * @Description DOTO
 * @Author mischen
 * @Date 2021/5/22 0022 8:02
 * @Version 1.0
 **/
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 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;
    }
    //空参构造
    public TableBean() {
    }

    //序列化方法
    public void write(DataOutput dataOutput) throws IOException {
         dataOutput.writeUTF(id);
         dataOutput.writeUTF(pid);
         dataOutput.writeInt(amount);
         dataOutput.writeUTF(pname);
         dataOutput.writeUTF(flag);
    }
    //反序列化方法，反序列化方法必须与序列化方法一致
    public void readFields(DataInput dataInput) throws IOException {
        this.id=dataInput.readUTF();
        this.pid = dataInput.readUTF();
        this.amount = dataInput.readInt();
        this.pname = dataInput.readUTF();
        this.flag = dataInput.readUTF();
    }
    //重写tostring方法，只需要输出id pname amount
    @Override
    public String toString() {
        return id + "\t" + pname + "\t" + amount;
    }
}

 

（2）编写TableMapper类

package com.mischen.mapreduce.wordcount.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;

/**
 * @ClassName TableMapper
 * @Description DOTO
 * @Author mischen
 * @Date 2021/5/22 0022 8:26
 * @Version 1.0
 **/
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.mischen.mapreduce.wordcount.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;

/**
 * @ClassName TableReducer
 * @Description DOTO
 * @Author mischen
 * @Date 2021/5/22 0022 9:18
 * @Version 1.0
 **/
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.mischen.mapreduce.wordcount.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;

/**
 * @ClassName TableDriver
 * @Description DOTO
 * @Author mischen
 * @Date 2021/5/22 0022 9:23
 * @Version 1.0
 **/
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("E:\\input\\inputtable"));
        FileOutputFormat.setOutputPath(job, new Path("E:\\input\\output"));
        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0 : 1);
    }
}