MapReduce快速入门系列(14) | MapReduce之计数器应用及简单的数据清洗(ETL)

eunm MyCounter{MALFORORMED,NORMAL}
//对枚举定义的自定义计数器加1
context.getCounter(MyCounter.MALFORORMED).increment(1);

context.getCounter("counterGroup","counter").increment(1);
// 组名和计数器名称随便起，但最好有意义。

需要在Map阶段对输入的数据根据规则进行过滤清洗。

package com.buwenbuhuo.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 卜温不火
 * @create 2020-04-25 20:08
 * com.buwenbuhuo.ETL - the name of the target package where the new class or interface will be created.
 * mapreduce0422 - the name of the current project.
 */
public class ETLMapper extends Mapper<LongWritable, Text, Text, NullWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

        // 截取
        String[] fields = value.toString().split(" ");

        // 2 日志长度大于11的为合法
        if (fields.length > 11) {

            // 3 写出数据
            context.write(value, NullWritable.get());

            // 4 系统计数器
            context.getCounter("ETL", "True").increment(1);
        } else {
            context.getCounter("ETL", "False").increment(1);
        }

    }
}

package com.buwenbuhuo.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 卜温不火
 * @create 2020-04-25 20:08
 * com.buwenbuhuo.ETL - the name of the target package where the new class or interface will be created.
 * mapreduce0422 - the name of the current project.
 */
public class ETLDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

        //  1 获取job信息
        Job job = Job.getInstance(new Configuration());

        // 2 加载jar包
        job.setJarByClass(ETLDriver.class);

        // 3 关联map
        job.setMapperClass(ETLMapper.class);

        // 设置reducetask个数为0
        job.setNumReduceTasks(0);

        // 4 设置最终输出类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);

        // 5 设置输入和输出路径
        FileInputFormat.setInputPaths(job, new Path("d:\\input"));
        FileOutputFormat.setOutputPath(job, new Path("d:\\output"));

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