简单的数据清洗

//1
package com.example.weblog;

import com.example.mapreduce.WordCountReducer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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;

import java.io.IOException;
public class WebLogDriver {

    // mapreduce的Driver
    // 提交job
    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
        //设置操作集群时的用户名为root
        System.setProperty("HADOOP_USER_NAME", "root");
        // 1. 获取配置信息以及获取job对象
        Configuration conf = new Configuration();


        Job job = Job.getInstance(conf);
        // 2. 关联本地的jar
        job.setJarByClass(WebLogDriver.class);

        // 3. 关联Mapper和Reducer
        job.setMapperClass(WebLogMapper.class);

        // 4. 设置Mapper输出的KV类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);

        // 5. 设置最终输出KV类型


//        // 6. 设置输入和输出路径。请确保wcinput是存在的,并且下面有待统计词频的单词文件。
//        //                         output1会自动被创建，如果它已经存在，程序会报错!
//        FileInputFormat.setInputPaths(job, new Path("E://vm//wordcount"));
//        FileOutputFormat.setOutputPath(job, new Path("E://vm//wordcount1"));

        //改成集群的地址
        FileInputFormat.setInputPaths(job, new Path("D:\\vm\\weblogs"));
        FileOutputFormat.setOutputPath(job, new Path("D:\\vm\\weblog_us12"));

        // 7. 提交job
        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0 : 1);
    }
}

//2

package com.example.weblog;

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

import java.io.IOException;

//1.继承Mapper类
//2.重写map方法
public class WebLogMapper extends Mapper<LongWritable, Text, Text, NullWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        System.out.println(value);
        System.out.println("=========================================");
        //1.获取一行数据，使用空格拆分，得到字段数组
        String[] words = value.toString().split("\\s+");
        System.out.println(words.length);
        System.out.println("=========================================");
        //2.如果有6个字段，我们就保留这条数据
        if (words.length == 8) {
            context.write(value, NullWritable.get());
        }

    }
}