pvmapper

package com.qingjiao.traning.mr.weblog.pv;

 

import com.qingjiao.traning.mr.weblog.UserUtils;

import com.qingjiao.traning.mr.weblog.WebLog;

import org.apache.hadoop.io.IntWritable;

import org.apache.hadoop.io.LongWritable;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Mapper;

 

import java.io.IOException;

 

/*

input: key=> 行偏移量 value=> 一行日志

output: <url,1>

 */

public class PVMapper extends Mapper<LongWritable, Text,Text, IntWritable> {

    // 初始化key和value

    Text k =new Text();

    IntWritable v=new IntWritable(1);

 

    @Override

    protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.Context context) throws IOException, InterruptedException {

        // 读取一行数据，调用对应的方法实现对日志的过滤和清洗

        WebLog webLog = UserUtils.filterByPVs(value.toString());

 

        // 判断日志是否合法，合法参与数据统计

        if (webLog.isFlag()) {

            // 将用户请求的url封装为key

            k.set(webLog.getRequestURL());

            context.write(k,v);

        }

    }

}