import org.apache.hadoop.io.Writable;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
/**
 * 1.实现Writable接口
 * 2.重写序列化接口和反序列化接口
 * 3.重写无参构造
 * 4.重写toString方法
 */
public class FlowBean implements Writable {
    private long upFlow;    //上行流量
    private long downFlow;    //下行流量
    private long sumFlow;    //总流量
    //3.无参构造
    public FlowBean(){
    }
    //2.1序列化方法
    @Override
    public void write(DataOutput dataOutput) throws IOException {
        //序列化顺序无所谓,但是必须和反序列化顺序一致
        dataOutput.writeLong(upFlow);
        dataOutput.writeLong(downFlow);
        dataOutput.writeLong(sumFlow);
    }
    //2.2反序列化方法
    @Override
    public void readFields(DataInput dataInput) throws IOException {
        this.upFlow = dataInput.readLong();
        this.downFlow = dataInput.readLong();
        this.sumFlow = dataInput.readLong();
    }
    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;
    }
    //重载setSumFlow方法
    public void setSumFlow() {
        this.sumFlow = this.upFlow+this.downFlow;
    }
    @Override
    public String toString() {
        return upFlow + "\t" + downFlow + "\t" + sumFlow;
    }
}

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.util.StringUtils;
import java.io.IOException;
public class FlowMapper extends Mapper<LongWritable, Text,Text,FlowBean> {
    //尽可能节省内存,不要每次读取一行就新建对象
    private String phone;   //手机号
    private long upFlow;  //上行流量
    private long downFlow;    //下行流量
    private Text outKey = new Text();
    private FlowBean outValue = new FlowBean();
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //1.获取一行
        //1363157991076  13926435656  20-10-7A-28-CC-0A:CMCC  120.196.100.99    2 4 132 1512  200
        String line = value.toString();
        //2.切割
        String[] words =  StringUtils.split(line,'\t');
        //3.获取想要的数据
        phone = words[1];
        upFlow = Long.parseLong(words[words.length-3]);
        downFlow = Long.parseLong(words[words.length-2]);
        //4.封装
        outKey.set(phone);
        outValue.setUpFlow(upFlow);
        outValue.setDownFlow(downFlow);
        outValue.setSumFlow();
        //5.写出
        context.write(outKey,outValue);
    }
}

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
public class FlowReducer extends Reducer<Text,FlowBean,Text,FlowBean> {
    private FlowBean outValue = new FlowBean();
    //reduce方法每次只计算相同的key,所以totalUp和totalDown必须放在reduce方法内部,否则会把所有key的上行流量和下行流量加在一起
    @Override
    protected void reduce(Text key, Iterable<FlowBean> values, Context context) throws IOException, InterruptedException {
        //1.遍历集合,累加值
        long totalUp = 0;    //上行流量
        long totalDown = 0;    //下行流量
        for (FlowBean value : values) {
            totalUp += value.getUpFlow();
            totalDown += value.getDownFlow();
        }
        //2.封装outKey,outValue
        outValue.setUpFlow(totalUp);
        outValue.setDownFlow(totalDown);
        outValue.setSumFlow();
        //3. 写出
        context.write(key,outValue);
    }
}

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.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
public class FlowRunner extends Configured implements Tool {
    public static void main(String[] args) throws Exception {
        ToolRunner.run(new Configuration(),new FlowRunner(),args);
    }
    @Override
    public int run(String[] args) throws Exception {
        //1.获取job
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "flow compu");
        //2.配置jar包路径
        job.setJarByClass(FlowRunner.class);
        //3.关联mapper和reducer
        job.setMapperClass(FlowMapper.class);
        job.setReducerClass(FlowReducer.class);
        //4.设置map、reduce输出的k、v类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);
        //5.设置数据输入的路径
        FileInputFormat.setInputPaths(job,new Path("D:\\MapReduce_Data_Test\\writable\\input1"));
        //6.设置输出路径-输出目录不可存在
        FileOutputFormat.setOutputPath(job,new Path("D:\\MapReduce_Data_Test\\writable\\output1"));
        //7.提交job
        return job.waitForCompletion(true) ? 0 : 1;//verbose：是否监控并打印job的信息
    }
}