Hadoop-27、排序

創建以下目錄

FlowBean.class

package com.atguigu.writablecomparable;

import org.apache.hadoop.io.Writable;
import org.apache.hadoop.io.WritableComparable;

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

public class FlowBean implements WritableComparable<FlowBean> {

    private long upFlow;
    private long downFlow;
    private long sumFlow;

    public FlowBean() {

    }

    @Override
    public String toString(){
        return upFlow + "\t" + downFlow + "\t" + sumFlow;
    }

    public void set(long upFlow, long downFlow){
        this.upFlow = upFlow;
        this.downFlow = downFlow;
        this.sumFlow = upFlow + downFlow;
    }


    public long getUpFlow() {
        return upFlow;
    }

    public void setUpFlow(long upFlow) {
        this.upFlow = upFlow;
    }

    public long getDownFlow() {
        return downFlow;
    }

    public void setDownFlow(long downFlow) {
        this.downFlow = downFlow;
    }

    public long getSumFlow() {
        return sumFlow;
    }

    public void setSumFlow(long sumFlow) {
        this.sumFlow = sumFlow;
    }


    /**
     * 序列方法 Out 框架給我們提供的數據出口
     * @param out
     * @throws IOException
     */
    @Override
    public void write(DataOutput out) throws IOException {
        out.writeLong(upFlow);
        out.writeLong(downFlow);
        out.writeLong(sumFlow);
    }

    /**
     *
     * @param in 框架提供的數據來源
     * @throws IOException
     */
    @Override
    public void readFields(DataInput in) throws IOException {
        upFlow = in.readLong();
        downFlow = in.readLong();
        sumFlow = in.readLong();
    }

    @Override
    public int compareTo(FlowBean o) {
        return Long.compare(o.sumFlow,this.sumFlow);
    }
}

FlowDriver.class

package com.atguigu.writablecomparable;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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 SortDriver {

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

        job.setJarByClass(SortDriver.class);
        job.setMapperClass(SortMapper.class);
        job.setReducerClass(SortReducer.class);

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

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

        FileInputFormat.setInputPaths(job,new Path("d:\\output"));
        FileOutputFormat.setOutputPath(job,new Path("d:\\output2"));

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

    }
}

FlowMapper.class

package com.atguigu.writablecomparable;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

public class SortMapper extends Mapper<LongWritable, Text, FlowBean, Text> {

    private FlowBean flow = new FlowBean();
    private Text phone = new Text();
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String[] fields = value.toString().split("\t");
        phone.set(fields[0]);
        flow.setUpFlow(Long.parseLong(fields[1]));
        flow.setDownFlow(Long.parseLong(fields[2]));
        flow.setSumFlow(Long.parseLong(fields[3]));

        context.write(flow, phone);
    }
}

FlowReducer.class

package com.atguigu.writablecomparable;

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

public class SortReducer extends Reducer<FlowBean, Text, Text, FlowBean> {
    @Override
    protected void reduce(FlowBean key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
        for (Text value : values){
            context.write(value,key);
        }
    }
}

現在進行分類排序

MyPartitioner2.class

package com.atguigu.writablecomparable2;

import com.atguigu.writablecomparable.FlowBean;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Partitioner;

public class MyPartitioner2 extends Partitioner<FlowBean, Text> {
    @Override
    public int getPartition(FlowBean flowBean, Text text, int numPartitions) {
        switch (text.toString().substring(0,3)){
            case "136":
                return 0;
            case "137":
                return 1;
            case "138":
                return 2;
            case "139":
                return 3;
            default:
                return 4;
        }
    }
}

SortDriver.class

package com.atguigu.writablecomparable2;

import com.atguigu.partition.MyPartitioner;
import com.atguigu.writablecomparable.FlowBean;
import com.atguigu.writablecomparable.SortMapper;
import com.atguigu.writablecomparable.SortReducer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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 SortDriver {

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

        job.setJarByClass(SortDriver.class);
        job.setMapperClass(SortMapper.class);
        job.setReducerClass(SortReducer.class);

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

        job.setPartitionerClass(MyPartitioner2.class);
        job.setNumReduceTasks(5);

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

        FileInputFormat.setInputPaths(job,new Path("d:\\output"));
        FileOutputFormat.setOutputPath(job,new Path("d:\\output3"));

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

    }
}