ReduceJoin多表连接

需求：将商品表与订单表关联

order.txt

201801    01    1
201802    02    2
201803    03    3
201804    01    4
201805    02    5
201806    03    6

......

pd.txt

01    小米
02    华为
03    格力

......

当数据量比较小的时候，可以使用MapJoin，数据量较大是，使用ReduceJoin

1：定义TableBean类

package ReduceJoin;
import lombok.AllArgsConstructor;
import lombok.NoArgsConstructor;
import org.apache.hadoop.io.Writable;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

@AllArgsConstructor
@NoArgsConstructor
public class TableBean implements Writable {
    //订单id、产品id、产品数量、产品名、表标记
    private String orderId;
    private String pId;
    private int amount;
    private String pName;
    private String flag;

    public String getOrderId() {
        return orderId;
    }
    public void setOrderId(String orderId) {
        this.orderId = orderId;
    }
    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  //序列化
    public void write(DataOutput out) throws IOException {
        out.writeUTF(orderId);
        out.writeUTF(pId);
        out.writeInt(amount);
        out.writeUTF(pName);
        out.writeUTF(flag);
    }
    @Override  //反序列化
    public void readFields(DataInput in) throws IOException {
        this.orderId = in.readUTF();
        this.pId = in.readUTF();
        this.amount = in.readInt();
        this.pName = in.readUTF();
        this.flag = in.readUTF();
    }
    @Override
    public String toString() {
        return orderId + "\t" + pName + "\t" + amount;
    }
}

2：定义TableMapper类

package 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;

/**
 * LongWritable,Text   偏移量，数据文本
 * Text,Bean           pid，Bean
 */
public class TableMapper extends Mapper<LongWritable, Text, Text, TableBean> {
    Text k = new Text();
    TableBean bean = new TableBean();
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //通过context找到InputSplit的子类FileSplit 注：转类型
        FileSplit split =  (FileSplit) context.getInputSplit();
        //找到文件名，用于判断两个文件
        String name = split.getPath().getName();

        String line = value.toString();
        // 0 按订单表处理 orderid、pid、amount
        if (name.startsWith("order")) {
            String[] fields = line.split("\t");
            bean.setOrderId(fields[0]);
            bean.setPid(fields[1]);
            bean.setAmount(Integer.parseInt(fields[2]));
            bean.setPname("");
            bean.setFlag("0");

            k.set(fields[1]);
        }else {
            // 1 按产品表处理
            String[] fields = line.split("\t");
            bean.setPid(fields[0]);
            bean.setPname(fields[1]);
            bean.setAmount(0);
            bean.setOrderId("");
            bean.setFlag("1");

            k.set(fields[0]);
        }
        context.write(k,bean);
    }
}

3：定义TableReducer类

package 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.util.ArrayList;
import java.util.List;

public class TableReducer extends Reducer<Text, TableBean,TableBean, NullWritable> {
    @Override
    protected void reduce(Text key, Iterable<TableBean> values, Context context) throws IOException, InterruptedException {
        List<TableBean> orderBeans = new ArrayList<>();
        TableBean pdBean = new TableBean();

        for(TableBean bean : values){
            // 0 是订单表
            if("0".equals(bean.getFlag())){
                TableBean orderBean = new TableBean();
                try {
                    //bean copy to orderBean
                    BeanUtils.copyProperties(orderBean,bean);
                } catch (Exception e) {
                    e.printStackTrace();
                }
                orderBeans.add(orderBean);
            }else {
                // 1 是产品表
                try {
                    BeanUtils.copyProperties(pdBean,bean);
                } catch (Exception e) {
                    e.printStackTrace();
                }
            }
        }
        for(TableBean bean : orderBeans) {
            bean.setPname(pdBean.getPname());
            context.write(bean,NullWritable.get().get());
        }
    }
}

4：定义TableDriver类

package 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 {
        args = new String[]{"E:\\bigdata_code\\reducejoin","E:\\bigdata_code\\reducejoin\\out"};

        //获取配置信息，job对象实例
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        //指定Jar包所在的路径
        job.setJarByClass(TableDriver.class);

        //指定Map类和Map输出数据的KV类型
        job.setMapperClass(TableMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(TableBean.class);

        //指定reduce类和reduce输出数据类型
        job.setReducerClass(TableReducer.class);
        job.setOutputKeyClass(TableBean.class);
        job.setOutputValueClass(NullWritable.class);

        //指定输入输出类型
        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));

        //提交
        job.waitForCompletion(true);
    }
}

输出结果：

201804    小米    4
201801    小米    1
201805    华为    5
201802    华为    2
201806    格力    6
201803    格力    3
......