流量统计之自定义Mapper类（第二步）

1、access.log

（1）在com.imooc.bigdata(hadoop-train-v2)下新建directory：access

（2）在access下新建directory：input

（3）在input下新建file：access.log

001    13161021751    192.168.126.100    200    5    10
002    13161021751    192.168.126.100    200    5    10
003    13161021751    192.168.126.100    200    5    10
004    13161021751    192.168.126.100    200    5    10
005    13161021751    192.168.126.100    200    5    10
006    13161021752    192.168.126.101    200    15    20
007    13161021752    192.168.126.101    200    15    20
008    13161021752    192.168.126.101    200    15    20
009    13161021752    192.168.126.101    200    15    20
010    13161021752    192.168.126.101    200    15    20
011    13161021753    192.168.126.102    200    25    30
012    13161021753    192.168.126.102    200    25    30
013    13161021753    192.168.126.102    200    25    30
014    13161021753    192.168.126.102    200    25    30
015    13161021753    192.168.126.102    200    25    30
016    13161021754    192.168.126.103    200    35    40
017    13161021754    192.168.126.103    200    35    40
018    13161021754    192.168.126.103    200    35    40
019    13161021754    192.168.126.103    200    35    40
020    13161021754    192.168.126.103    200    35    40
021    13161021755    192.168.126.104    200    45    50
022    13161021755    192.168.126.104    200    45    50
023    13161021755    192.168.126.104    200    45    50
024    13161021755    192.168.126.104    200    45    50
025    13161021755    192.168.126.104    200    45    50
026    13161021755    192.168.126.104    200    45    50
027    13161021755    192.168.126.104    200    45    50
028    13161021755    192.168.126.104    200    45    50
029    13161021755    192.168.126.104    200    45    50
030    13161021755    192.168.126.104    200    45    50

2、AccessMapper.java

package com.imooc.bigdata.hadoop.mr.access;


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

import java.io.IOException;

/*
 * 自定义Mapper处理类
 *
 * Mapper就是把所需要的东西提取出来，做一些适当的转换
 */

//按照实现，要先继承Mapper
/*
 * LongWritable输入的偏移量
 * Text输入的每行文本
 * Text输出的电话号码作为key
 * Access输出的Access.java中的复杂数据类型
 */

public class AccessMapper extends Mapper<LongWritable, Text, Text, Access> {

    // 实现一个map方法
    // 具体操作：输入map，选择protected...
    // 任务：把读进来的日志access.log，按照tab键进行分割，取出3个字段
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

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

        String phone = lines[1];                            //取出手机号
        long up = Long.parseLong(lines[lines.length-2]);    //取出上行流量
        long down = Long.parseLong(lines[lines.length-1]);  //取出下行流量
        //通过上下文write出来sum
        context.write(new Text(phone), new Access(phone, up, down));
    }
}

3、Access.java

（1）除了默认的构造方法外，还需添加以下代码，为AccessMapper.java方便使用

    //为了AccessMapper.java使用方便
    public Access(String phone, long up, long down){
        this.phone = phone;
        this.up = up;
        this.down = down;
        this.sum = up + down;
    }