基于MapReduce实现手机流量统计 - DAY2

（2）使用java编写MapReduce程序

定义一个Drive.java类

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;


public class Driver {

    public static void main(String[] args) throws Exception {

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

        job.setJarByClass(Driver.class);

        job.setMapperClass(Mapper.class);
        job.setReducerClass(Reducer.class);

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

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

        job.setPartitionerClass(Partitioner.class);
        job.setNumReduceTasks(3);

        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

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

 定义一个phoneBean.java

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import org.apache.hadoop.io.Writable;

public class phoneBean implements Writable {

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

    public phoneBean() {
        super();
    }

    public phoneBean(long upFlow, long downFlow) {
        super();
        this.upFlow = upFlow;
        this.downFlow = downFlow;
        this.sumFlow = upFlow + downFlow;
    }

    public long getSumFlow() {
        return sumFlow;
    }

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

    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;
    }

    @Override
    public void write(DataOutput out) throws IOException {
        out.writeLong(upFlow);
        out.writeLong(downFlow);
        out.writeLong(sumFlow);
    }

    @Override
    public void readFields(DataInput in) throws IOException {
        upFlow = in.readLong();
        downFlow = in.readLong();
        sumFlow = in.readLong();
    }

    @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;
    }
}

定义Mapper和Reduce方法

mapper

import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
public class Mapper extends org.apache.hadoop.mapreduce.Mapper<LongWritable, Text, Text, phoneBean> {

    //不能在map方法中new对象，map方法执行频率高，内存消耗大。这也就是需要在bean对象中要有一个空构造方法的原因
    phoneBean bean = new phoneBean();
    Text k = new Text();

    @Override
    protected void map(LongWritable key, Text value, Context context)
            throws IOException, InterruptedException {

        //1.获取一行数据（）
        String line = value.toString();

        //2.截取字段（）
        String[] fields = line.split("\t");

        //3.封装bean对象，获取电话号码（）
        String phoneNum = fields[1];
        long upFlow = Long.parseLong(fields[fields.length - 3]);
        long downFlow = Long.parseLong(fields[fields.length - 2]);
        bean.set(upFlow, downFlow);
        k.set(phoneNum);

        //4.写出去（将数据输出出去，key和value分别是什么，规定清楚）
        context.write(k, bean);
    }
}

 reducer

import java.io.IOException;
import org.apache.hadoop.io.Text;

public class Reducer extends org.apache.hadoop.mapreduce.Reducer<Text, phoneBean, Text, phoneBean> {

    @Override
    protected void reduce(Text key, Iterable<phoneBean> values, Context context)
            throws IOException, InterruptedException {
        //计算总流量
        long sum_upFlow = 0;
        long sum_downFlow = 0;
        for(phoneBean bean : values){
            sum_upFlow += bean.getUpFlow();
            sum_downFlow += bean.getDownFlow();
        }

        context.write(key, new phoneBean(sum_upFlow,sum_downFlow));
    }
}