ETL

数据从来源端经过抽取（Extract）、转换（Transform）、加载（Load）至目的端的过程
清理的过程往往只需要运行 Mapper 程序，不需要运行 Reduce 程序。

案例

将含有空字段的行清洗
在这里插入图片描述

编写ETLMapper类

package ETL;

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;

/**
 * @author 公羽
 * date: 2021/8/22
 * desc:
 */
public class ETLMapper extends Mapper<LongWritable, Text, Text , NullWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
//        获取每行数据
        String line = value.toString();
//        ETL清洗
        boolean result = parselog(line, context);
        if (!result){
            return;
        }
        context.write(value,NullWritable.get());

    }

    private boolean parselog(String line, Context context) {
//        将每个字段进行切分
        String[] split = line.split("\t");
        //        判断字段数量
        if (split.length > 5){
            return true;
        }else {
            return false;
        }
    }
}

编写ETLDriver类

package ETL;

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;


/**
 * @author 公羽
 * date: 2021/8/22
 * desc:
 */
public class ETLDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
//        TODO 1.获取配置信息以及封装任务
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);
//        TODO 2.设置jar加载路径
        job.setJarByClass(ETLDriver.class);
//        TODO 3.设置map和reduce类
        job.setMapperClass(ETLMapper.class);
//        TODO 4.设置map输出路径
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);
//         TODO 5.设置最终输出kv类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);
//         TODO 6.设置reduce
        job.setNumReduceTasks(0);
//         TODO 7.设置输出和输入路径
        FileInputFormat.setInputPaths(job, new Path("E:\\data.log"));
        FileOutputFormat.setOutputPath(job, new Path("E:\\outdata_log"));
//         TODO 8.提交
        boolean b = job.waitForCompletion(true);
        System.exit(b? 0:1);
    }
}