hadoop-18 数据清洗 ETL

ETL：Extract-Transform-Load 用来描述将数据从来源端警告抽取Extract 转换Transform 加载Load至目的端的过程

清理的过程只需要运行Mapper程序，不需要运行Reduce程序

WebLogMapper.java

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 WebLogMapper extends Mapper<LongWritable, Text, Text, NullWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        // 获取一行数据
        String line = value.toString();
        // ETL
        boolean result = parseLog(line);
        if (!result) {
            return;
        }
        // 写出
        context.write(value, NullWritable.get());
    }

    private boolean parseLog(String line) {
        String[] fields = line.split(" ");
        // 判断日志长度是否大于11
        if (fields.length > 11) {
            return true;
        } else {
            return false;
        }
    }
}

WebLogDriver.java

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 WebLogDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        job.setJarByClass(WebLogDriver.class);
        job.setMapperClass(WebLogMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
        job.setNumReduceTasks(0);
        FileInputFormat.setInputPaths(job, new Path("E:\\hadoop\\webloginput"));
        FileOutputFormat.setOutputPath(job, new Path("E:\\hadoop\\weblogoutput"));
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);
    }
}

Blog

hadoop-18 数据清洗 ETL