第2节 mapreduce深入学习：9、手机上行流量排序

还是上次那个例子，需求二：上行流量倒序排序（递减排序）

分析，以需求一的输出数据作为排序的输入数据，自定义FlowBean,以FlowBean为map输出的key，以手机号作为Map输出的value，因为MapReduce程序会对Map阶段输出的key进行排序。

代码：

FlowMain：

package cn.itcast.demo3.flowSort;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
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.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class FlowMain extends Configured implements Tool {
    @Override
    public int run(String[] args) throws Exception {

        Job job = Job.getInstance(this.getConf(), FlowMain.class.getSimpleName());
//        job.setJarByClass(FlowMain.class);

        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job,new Path("file:///D:\\Study\\BigData\\heima\\stage2\\4、大数据离线第四天\\流量统计\\1sum\\part-r-00000"));

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

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

        job.setOutputFormatClass(TextOutputFormat.class);
        TextOutputFormat.setOutputPath(job,new Path("file:///D:\\Study\\BigData\\heima\\stage2\\4、大数据离线第四天\\流量统计\\2sort"));


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

    public static void main(String[] args) throws Exception {
        int run = ToolRunner.run(new Configuration(), new FlowMain(), args);
        System.exit(run);
    }
}

FlowMapper：

package cn.itcast.demo3.flowSort;

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

import java.io.IOException;

public class FlowMapper extends Mapper<LongWritable,Text,FlowBean,Text> {
    //13726230503  24 27 2481   24681
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        FlowBean flowBean = new FlowBean();

        String[] split = value.toString().split("\t");

        flowBean.setUpFlow(Integer.parseInt(split[1]));//上行流量
        flowBean.setDownFlow(Integer.parseInt(split[2]));//下行流量
        flowBean.setUpCountFlow(Integer.parseInt(split[3]));//上行总流量
        flowBean.setDownCountFlow(Integer.parseInt(split[4]));//下行总流量
        //split[0]) 手机号
        context.write(flowBean,new Text(split[0]));
    }
}

FlowReducer：

package cn.itcast.demo3.flowSort;

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

import java.io.IOException;

public class FlowReducer extends Reducer<FlowBean,Text,Text,FlowBean> {

    @Override
    protected void reduce(FlowBean key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
        for(Text text:values)
            context.write(text,key);
    }
}

FlowBean：

package cn.itcast.demo3.flowSort;

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> {
    //上行流量
    private Integer  upFlow;
    //下行流量
    private Integer  downFlow;
    //上行总流量
    private Integer  upCountFlow;
    //下行总流量
    private Integer  downCountFlow;

    /**
     * 序列化方法
     * @param out
     * @throws IOException
     */
    @Override
    public void write(DataOutput out) throws IOException {
        out.writeInt(this.upFlow);
        out.writeInt(this.downFlow);
        out.writeInt(this.upCountFlow);
        out.writeInt(this.downCountFlow);
    }

    /**
     * 反序列化的方法
     * @param in
     * @throws IOException
     */
    @Override
    public void readFields(DataInput in) throws IOException {
        this.upFlow = in.readInt();
        this.downFlow = in.readInt();
        this.upCountFlow = in.readInt();
        this.downCountFlow = in.readInt();
    }

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

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

    public void setUpCountFlow(Integer upCountFlow) {
        this.upCountFlow = upCountFlow;
    }

    public void setDownCountFlow(Integer downCountFlow) {
        this.downCountFlow = downCountFlow;
    }

    public Integer getUpFlow() {
        return upFlow;
    }

    public Integer getDownFlow() {
        return downFlow;
    }

    public Integer getUpCountFlow() {
        return upCountFlow;
    }

    public Integer getDownCountFlow() {
        return downCountFlow;
    }

    @Override
    public String toString() {
        /*return "上行流量=" + upFlow +
                ", 下行流量=" + downFlow +
                ", 上行总流量=" + upCountFlow +
                ", 下行总流量=" + downCountFlow;*/
        return upFlow+"\t"+downFlow+"\t"+upCountFlow+"\t"+downCountFlow;
    }

    /**
     * 实现比较器
     * @param o
     * @return
     */
    @Override
    public int compareTo(FlowBean o) {
        int i = this.upFlow.compareTo(o.upFlow);
        return -i;
    }
}

注意：如果使用FlowBean作为Map阶段输出的key，则必须实现WritableComparable接口，否则报错:

java.lang.Exception: java.lang.ClassCastException: class cn.itcast.demo3.flowSort.FlowBean
at org.apache.hadoop.mapred.LocalJobRunner$Job.run(LocalJobRunner.java:406)
Caused by: java.lang.ClassCastException: class cn.itcast.demo3.flowSort.FlowBean
at java.lang.Class.asSubclass(Class.java:3404)