简单的数据清洗

创建weblog项目，要保证此电脑的文件里面有vm文件在E盘，以及里面有weblogs文件

package com.example.weblog;
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 {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

        //设置用户名：
        //1.获取job对象
        Configuration conf = new Configuration();
       // conf.set("fs.defaultFS", "hdfs://hadoop100:8020");

        Job job = Job.getInstance(conf);
        //2.关联啊本地Driver类的jar
        job.setJarByClass(WebLogDriver.class);
        //3.关联map和reduce
        job.setMapperClass(WeblogMapper.class);

        //4.设置map的输出kv类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);
        //5.设置map的输出kv类型

        //6.设置输入数据和输出结果的地址
        FileInputFormat.setInputPaths(job, new Path("E:\\vm\\weblogs"));
        FileOutputFormat.setOutputPath(job, new Path("E:\\vm\\weblog_out1112"));

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

    }
}

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 {
            //每一行的文本内容，使用空格做拆分，得到一个列表
            System.out.println(value);


            //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组
            if (words.length == 9) {
               context.write(value, NullWritable.get());
            }

        }
    }

package com.example.weblog;

public class WeblogReducer {
}