MapReduce-day05-第三章框架原理-3.6ReduceJoin机制

本文链接：https://blog.csdn.net/AlphaG/article/details/120856051

该博客介绍了一个使用Java实现的MapReduce程序，用于处理订单和产品数据的连接。`TableBean`类用于存储订单ID、产品ID、数量和名称等信息。`TableMapper`类根据输入文件区分订单和产品数据，`TableReducer`类则将订单数据与产品数据进行连接，填充产品名称。整个流程展示了如何在Hadoop环境中进行数据处理。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

1：案例

2：代码

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还是pd表


    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();
    }
}


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")) {
            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 {
            String[] split = line.split(" t");

            outK.set(split[0]);

            outV.setId("");
            outV.setPid(split[0]);
            outV.setAmount(0);
            outV.setPname(split[1]);
            outV.setFlag("pd");
        }

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


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 {

        //准备两个集合
        ArrayList<TableBean> orderBeans = new ArrayList<>();
        TableBean pdBean = new TableBean();

        //循环遍历
        for (TableBean value : values) {

            if ("order".equals(value.getFlag())){//订单表

                TableBean tmptableBean = new TableBean();

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

                orderBeans.add(tmptableBean);
            }else {//商品表
                try {
                    BeanUtils.copyProperties(pdBean,value);
                } catch (IllegalAccessException e) {
                    e.printStackTrace();
                } catch (InvocationTargetException e) {
                    e.printStackTrace();
                }
            }

        }


        //循环遍历orderBeans，赋值pdname
        for (TableBean orderBean : orderBeans) {

            orderBean.setPname(pdBean.getPname());
            context.write(orderBean,NullWritable.get());

        }

    }
}


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("F:\\input\\inputtable"));
        FileOutputFormat.setOutputPath(job, new Path("F:\\output15"));
        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0 : 1);
    }
}