简单的日志清洗

最新推荐文章于 2024-07-01 00:28:57 发布

青城雪

最新推荐文章于 2024-07-01 00:28:57 发布

阅读量594

点赞数

分类专栏：程序人生文章标签：文件清洗 hadoop

本文链接：https://blog.csdn.net/jimi0614/article/details/100026312

版权

程序人生专栏收录该内容

17 篇文章 0 订阅

订阅专栏

原文件 web.txt

在这里插入图片描述

Map类

java
package telephone;

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;
public class LogCleanMapper extends Mapper<LongWritable, Text,Text, NullWritable> {

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //1.读取一行数据
        String line = value.toString();
        parseLog(line,context);

        boolean b =parseLog(line,context);
        if (!b){
            return;
        }
        context.write(value,NullWritable.get());
}
    //判断数据是否符合
    public  boolean parseLog(String line,Context context){
        //获取数据
        String[]words=line.split(" ");
        //判断计数器
        if (words.length>11){
            context.getCounter("map","正常数据").increment(1);
            return  true;
        }else{
            context.getCounter("map","非正常数据").increment(1);
            return  false;
        }
    }

}

Reduce

java
package telephone;

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;

import java.io.IOException;

public class LogCleanDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        args=new String[]{"G:\\a\\web.txt","G:\\a\\OutWeb1.txt"};

        Job job = Job.getInstance(new Configuration());
        job.setJarByClass(LogCleanDriver.class);

        //配置mapper类及输出数据类型
        job.setMapperClass(LogCleanMapper.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);

        //设置reduce的个数，默认是1
        job.setNumReduceTasks(0);

        //输入数据路径
        FileInputFormat.setInputPaths(job,new Path(args[0]));
        //输出数据路径
        FileOutputFormat.setOutputPath(job,new Path(args[1]));
        //提交 任务
        job.waitForCompletion(true);

    }
}