hadoop-MapReduce框架之Join多种应用

1.Reduce Join

　　1.1 工作原理

　　　　map端的主要工作：为来自不同表或文件的key/value对，打标签以区别不同的来源记录；然后用连接字段作为key，其余部分和新加的标志作为是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，我们只主要在每一个分组当中将那些来源于不用文件的记录（在map阶段已经打标签）分开，最后进行合并就OK了；

　　1.2 需求

　　　　订单表数据

　　　　　　

　　　　表商品信息

　　　　　　

 

　　　　将最终数据形成

 

 　　　　　　

2.Reduce Join 案例实操

　　2.1 OrderBean编写

package com.wn.bean;

import org.apache.hadoop.io.WritableComparable;

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

public class OrderBean implements WritableComparable<OrderBean> {

    private String id;
    private String pid;
    private int amount;
    private String pname;

    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;
    }

    @Override
    public String toString() {
        return "OrderBean{" +
                "id='" + id + '\'' +
                ", pid='" + pid + '\'' +
                ", amount=" + amount +
                ", pname='" + pname + '\'' +
                '}';
    }

    @Override
    public int compareTo(OrderBean o) {
        int compare = this.pid.compareTo(o.pid);
        if (compare==0){
            return o.pname.compareTo(this.pname);
        }else{
            return compare;
        }
    }

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

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

　　2.2 RJMapper编写　　

package com.wn.reducejoin;

import com.wn.bean.OrderBean;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
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 RJMapper extends Mapper<LongWritable, Text, OrderBean, NullWritable> {

    private OrderBean orderBean=new OrderBean();

    private String filename;

    @Override
    protected void setup(Context context) throws IOException, InterruptedException {
        FileSplit fs = (FileSplit) context.getInputSplit();
        filename = fs.getPath().getName();
    }

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String[] fields = value.toString().split("\t");
        if (filename.equals("order.txt")){
            orderBean.setId(fields[0]);
            orderBean.setPid(fields[1]);
            orderBean.setAmount(Integer.parseInt(fields[2]));
            orderBean.setPname("");
        }else{
            orderBean.setPid(fields[0]);
            orderBean.setPname(fields[1]);
            orderBean.setId("");
            orderBean.setAmount(0);
        }
        context.write(orderBean,NullWritable.get());
    }
}

　　2.3 RJComparator编写

package com.wn.reducejoin;

import com.wn.bean.OrderBean;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;

public class RJComparator extends WritableComparator {
    protected RJComparator(){
        super(OrderBean.class,true);
    }

    @Override
    public int compare(WritableComparable a, WritableComparable b) {
        OrderBean oa=(OrderBean) a;
        OrderBean ob=(OrderBean) b;
        return oa.getPid().compareTo(ob.getPid());
    }
}

　　2.4 RJReducer编写　　

package com.wn.reducejoin;

import com.wn.bean.OrderBean;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;
import java.util.Iterator;

public class RJReducer extends Reducer<OrderBean, NullWritable,OrderBean,NullWritable> {

    private OrderBean orderBean=new OrderBean();

    @Override
    protected void reduce(OrderBean key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
        Iterator<NullWritable> iterator = values.iterator();
        iterator.next();
        String pname = key.getPname();
        while(iterator.hasNext()){
            iterator.next();
            key.setPname(pname);
            context.write(key,NullWritable.get());
        }
    }
}

　　2.5 RJDriver编写

package com.wn.reducejoin;

import com.wn.bean.OrderBean;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

public class RJDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Job job = Job.getInstance(new Configuration());
        job.setJarByClass(RJDriver.class);
        job.setMapperClass(RJMapper.class);
        job.setReducerClass(RJReducer.class);

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

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

        job.setGroupingComparatorClass(RJComparator.class);
        FileInputFormat.setInputPaths(job,new Path("E:\\北大青鸟\\大数据04\\hadoop\\Join\\Reduce"));
        FileOutputFormat.setOutputPath(job,new Path("E:\\北大青鸟\\大数据04\\hadoop\\Join\\OutReduce"));

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

3.Map Join

　　3.1 使用场景　

　　　　Map Join适用于一张表十分小，一张表很大的场景；

　　3.2 优点

　　　　在map端缓存多张表，提前处理业务逻辑，这样增加map端业务，减少reduce端数据的压力，尽可能的减少数据倾斜；

　　3.3 具体方法

　　　　3.3.1 在mapper的setup阶段，将文件读取到缓存集合中；

　　　　3.3.2 在驱动函数中加载缓存；

　　　　　　//缓存普通文件到Task运行节点；

　　　　　　job.addCacheFile(new URI("file://e:/cache/pd.txt"));

4.Map Join案例实操

　　4.1 Driver编写

package com.wn.mapjoin;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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;
import java.net.URI;

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

        job.setJarByClass(MJDriver.class);
        job.setMapperClass(MJMapper.class);
        job.setNumReduceTasks(0);

        job.addCacheFile(URI.create("file:///E:/北大青鸟/大数据04/hadoop/Join/Reduce/pd.txt"));
        FileInputFormat.setInputPaths(job,new Path("E:\\北大青鸟\\大数据04\\hadoop\\Join\\Reduce\\order.txt"));
        FileOutputFormat.setOutputPath(job,new Path("E:\\北大青鸟\\大数据04\\hadoop\\Join\\OutReduce"));

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

　　4.2 mapper编写

package com.wn.mapjoin;

import org.apache.commons.lang.StringUtils;
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.Mapper;

import java.io.*;
import java.net.URI;
import java.util.HashMap;
import java.util.Map;

public class MJMapper extends Mapper<LongWritable, Text,Text, NullWritable> {

    private Map<String,String> pMap=new HashMap<>();

    private Text k=new Text();

    @Override
    protected void setup(Context context) throws IOException, InterruptedException {
        URI[] cacheFiles = context.getCacheFiles();
        String path = cacheFiles[0].getPath().toString();
        BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(new FileInputStream(path)));
        String line;
        while (StringUtils.isNotEmpty(line=bufferedReader.readLine())){
            String[] split = line.split("\t");
            pMap.put(split[0],split[1]);
        }
        IOUtils.closeStream(bufferedReader);
    }

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String[] fieIds = value.toString().split("\t");
        String pname = pMap.get(fieIds[1]);
        k.set(fieIds[0]+"\t"+pname+"\t"+fieIds[2]);
        context.write(k,NullWritable.get());
    }
}