在reduce中进行join

package 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 orderId;
    private String pId;
    private int amount;
    private String pname;
    private String flag;

    public TableBean() {
        super();
    }

    public TableBean(String orderId, String pId, int amount, String pname, String flag) {
        super();
        this.orderId = orderId;
        this.pId = pId;
        this.amount = amount;
        this.pname = pname;
        this.flag = 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
    public void write(DataOutput out) throws IOException {
        out.writeUTF(orderId);
        out.writeUTF(pId);
        out.writeInt(amount);
        out.writeUTF(pname);
        out.writeUTF(flag);
    }

    @Override
    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 pId + "\t" + pname + "\t" + amount;
    }
}

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;

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

    String name;

    TableBean tableBean = new TableBean();
    Text k = new Text();

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

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
//        id   pid amount
//        1001 01   1
        if (name.startsWith("order")) {
            //代表产品订单
            String[] fields = value.toString().split("\t");
            tableBean.setOrderId(fields[0]);
            tableBean.setpId(fields[1]);
            tableBean.setAmount(Integer.parseInt(fields[2]));
            tableBean.setPname("");
            tableBean.setFlag("order");

            k.set(fields[1]);

            //        pid pname
            //        01 小米
        }else {
            String[] fields = value.toString().split("\t");

            tableBean.setOrderId("");
            tableBean.setpId(fields[0]);
            tableBean.setAmount(0);
            tableBean.setPname(fields[1]);
            tableBean.setFlag("product");

            k.set(fields[0]);
        }

        context.write(k, tableBean);


    }
}

package reducejoin;

import javafx.scene.control.Tab;
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 {
        ArrayList<TableBean> tableBeans = new ArrayList<>();
        TableBean productBean = new TableBean();

        for (TableBean tableBean : values) {

            if ("order".equals(tableBean.getFlag())){
                //此时 bean中全是订单,但只是包含的引用信息,需要将其copy
                TableBean tmpBean = new TableBean();

                try {
                    BeanUtils.copyProperties(tmpBean, tableBean);
                    tableBeans.add(tmpBean);
                } catch (IllegalAccessException e) {
                    e.printStackTrace();
                } catch (InvocationTargetException e) {
                    e.printStackTrace();
                }
            }else {
                try {
                    BeanUtils.copyProperties(productBean, tableBean);
                } catch (IllegalAccessException e) {
                    e.printStackTrace();
                } catch (InvocationTargetException e) {
                    e.printStackTrace();
                }
            }
        }

        for (TableBean orderBean :tableBeans) {
            orderBean.setPname(productBean.getPname());
            context.write(orderBean, NullWritable.get());
        }
    }
}

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[]{"/home/torrent/input", "/home/torrent/output"};

        // 1 获取配置信息，或者job对象实例
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);

        // 2 指定本程序的jar包所在的本地路径
        job.setJarByClass(TableDriver.class);

        // 3 指定本业务job要使用的Mapper/Reducer业务类
        job.setMapperClass(TableMapper.class);
        job.setReducerClass(TableReducer.class);

        // 4 指定Mapper输出数据的kv类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(TableBean.class);

        // 5 指定最终输出的数据的kv类型
        job.setOutputKeyClass(TableBean.class);
        job.setOutputValueClass(NullWritable.class);

        // 6 指定job的输入原始文件所在目录
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        // 7 将job中配置的相关参数，以及job所用的java类所在的jar包， 提交给yarn去运行
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);
    }
}

转载于:https://www.jianshu.com/p/2b713fe0c942