hadoop MapReducer的join操作 类似数据库的join操作

需求如下

---

相关文件资源见：相关文件和完整源码

---

java代码如下：

1、TableBean类

package com.lqs.mapreduce.reducejoin;

import org.apache.hadoop.io.Writable;

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

/**
 * @author qingSong liu
 * @version 1.0
 * @time 2021/12/14 15:18
 */

public class TableBean implements Writable {

    /**
     * 订单id
     */
    private String id;
    /**
     * 产品id
     */
    private String pid;
    /**
     * 产品数量
     */
    private int amount;
    /**
     * 产品名称
     */
    private String pname;

    /**
     * 判断是order表还是pd表的标志
     */
    private String flag;

    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 dataOutput) throws IOException {
        dataOutput.writeUTF(id);
        dataOutput.writeUTF(pid);
        dataOutput.writeInt(amount);
        dataOutput.writeUTF(pname);
        dataOutput.writeUTF(flag);
    }

    @Override
    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();
    }
}

2、TableMapper类

package com.lqs.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;

/**
 * @author qingSong liu
 * @version 1.0
 * @time 2021/12/14 16:53
 */

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

    private String filename;
    private Text outK;
    private TableBean outV;

    @Override
    protected void setup(Mapper<LongWritable, Text, Text, TableBean>.Context context) throws IOException, InterruptedException {
        outK = new Text();
        outV = new TableBean();

        //获取对应文件名称
        InputSplit inputSplit = context.getInputSplit();
        FileSplit fileSplit = (FileSplit) inputSplit;
        filename = fileSplit.getPath().getName();
    }

    /**
     * pd
     * pid  pname
     * 01	小米
     *
     * order
     * id   pid amount
     * 1001	01	1
     *
     * 最终样子
     * id pname amount
     * 1001 小米 1
     */
    @Override
    protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, TableBean>.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
        //订单表的处理
        if (filename.contains("order")){
            String[] split = line.split("\t");
            //封装outK
            //pid
            outK.set(split[1]);
            //封装outV
            outV.setId(split[0]);
            outV.setPid(split[1]);
            outV.setAmount(Integer.parseInt(split[2]));
            //因为order表没有pname
            outV.setPname("");
            outV.setFlag("order");
        }else {
            //商品列表处理
            String[] split = line.split("\t");
            //封装outK
            //pid
            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、TableReducer类

package com.lqs.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;

/**
 * @author qingSong liu
 * @version 1.0
 * @time 2021/12/14 16:54
 */

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

    @Override
    protected void reduce(Text key, Iterable<TableBean> values, Reducer<Text, TableBean, TableBean, NullWritable>.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
            //本判断是判断其是否为订单表
            if ("order".equals(value.getFlag())){

                //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 {
                //处理商品表
                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、TableDriver类如下：

package com.lqs.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 org.apache.log4j.BasicConfigurator;

import java.io.IOException;

/**
 * @author qingSong liu
 * @version 1.0
 * @time 2021/12/14 16:54
 */

public class TableDriver {

    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {

        BasicConfigurator.configure();

        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        job.setJarByClass(TableDriver.class);

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

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

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

        FileInputFormat.setInputPaths(job, new Path("F:\\hdpData\\Input\\inputtable"));
        FileOutputFormat.setOutputPath(job, new Path("F:\\hdpData\\Output\\outputTable3"));

        boolean b = job.waitForCompletion(true);

        System.exit(b ? 0 : 1);

    }

}

配置文件pom.xml如下：

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>org.example</groupId>
    <artifactId>MapReduceDemo</artifactId>
    <version>1.0-SNAPSHOT</version>
    
    <properties>
        <maven.compiler.source>8</maven.compiler.source>
        <maven.compiler.target>8</maven.compiler.target>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>3.1.3</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>1.7.30</version>
        </dependency>
    </dependencies>

    <build>
        <plugins>
            <plugin>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.6.1</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>

            <plugin>
                <artifactId>maven-assembly-plugin</artifactId>
                <configuration>
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                </configuration>
                <executions>
                    <execution>
                        <id>make-assembly</id>
                        <phase>package</phase>
                        <goals>
                            <goal>single</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>
</project>