数据清洗-日志

（1）编写WebLogMapper类

package com.root.mapreduce.weblog;

import java.io.IOException;

import org.apache.hadoop.io.LongWritable;

import org.apache.hadoop.io.NullWritable;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Mapper;

public class WebLogMapper extends Mapper<LongWritable, Text, Text, NullWritable>{

@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
    // 1. 获取一行数据,使用空格进行拆分，判断是否有8个字段
    String[] fields = value.toString().split(" ");
    if (fields.length > 7) {
        // 这条数据是有意义的,保留
        System.out.println(fields[0]);
        context.write(value, NullWritable.get());
    }
   }

}

（2）编写WebLogDriver类

package com.root.mapreduce.weblog;

import org.apache.hadoop.conf.Configuration;

import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.NullWritable;

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 WebLogDriver {

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

// 1 获取job信息

Configuration conf = new Configuration();

Job job = Job.getInstance(conf);

// 2 加载jar包

job.setJarByClass(LogDriver.class);

// 3 关联map

job.setMapperClass(WebLogMapper.class);

// 4 设置最终输出类型

job.setOutputKeyClass(Text.class);

job.setOutputValueClass(NullWritable.class);

// 设置reducetask个数为0

job.setNumReduceTasks(0);

// 5 设置输入和输出路径
         FileInputFormat.setInputPaths(job, new Path("E:\\vm\\web.log"));
         FileOutputFormat.setOutputPath(job, new Path("E:\\vm\\ouput2"));

// 6 提交

         boolean b = job.waitForCompletion(true);

         System.exit(b ? 0 : 1);

}

}