MapReduce（四）

需求分析：

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-aPRi5msX-1638758714162)(F:大数据图片13.png)]

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 {

    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 {

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

        ArrayList 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);
    }
}

运行程序查看结果

1004 小米 4

1001 小米 1

1005 华为 5

1002 华为 2

1006 格力 6

1003 格力 3

**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。

package com.zch.exercise.day1130.MapJoin;

import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
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 java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.URI;
import java.util.HashMap;


public class MapJoinDriver {

    public static class MapJoinMapper
            extends Mapper {
        // 保存         pid      pname
        private HashMap map = new HashMap();
        private Text k = new Text();

        @Override
        protected void setup(Context context) throws IOException, InterruptedException {
            // 获取缓存的文件，并把文件内容封装到集合
            URI[] cacheFiles = context.getCacheFiles();

            FileSystem fs = FileSystem.get(new Configuration());
            FSDataInputStream inputStream = fs.open(new Path(cacheFiles[0]));

            // 从输入流中获取数据
            BufferedReader reader = new BufferedReader(new InputStreamReader(inputStream, "UTF-8"));

            String line;
            while (!StringUtils.isEmpty(line = reader.readLine())) {
                // 切割
                String[] split = line.split("t");
                //赋值
                map.put(split[0], split[1]);
            }
            // 关流
            IOUtils.closeStream(reader);
        }

        @Override
        protected void map(LongWritable key, Text value, Context context)
                throws IOException, InterruptedException {
            //处理 order.txt
            String[] split = value.toString().split("t");
            // 获取pid
            String pid = split[1];
            //获取pname
            String pname = map.get(pid);
            // 获取订单ip 订单shuliang
            String id = split[0];
            String num = split[2];
            k.set(id + "t" + num);

            context.write(k, NullWritable.get());
        }
    }

    public static class MapJoinReducer extends
            Reducer{
        @Override
        protected void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException {
            context.write(key,NullWritable.get());
        }
    }

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

        job.setMapperClass(MapJoinMapper.class);
        job.setJarByClass(MapJoinDriver.class);
        job.setReducerClass(MapJoinReducer.class);

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

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


        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));

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

}