1.需求:数据来源各种各样,大量的数据中难免会有脏数据,我们需要将脏数据清洗掉,提高数据的准确度。
本次要将字段缺失的数据过滤掉,只留下保存度完整的数据。
2.项目开发:
(1)清洗数据类:
package com.xnmzdx.mapreduce.etl;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class LogMapper extends Mapper<LongWritable, Text, Text, NullWritable> {
@Override
protected void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
//1 获取一行数据
String line = value.toString();
//2 解析日志
boolean result = parseLog(line,context);
//3 判断日志符合不符合要求
if(!result){
return;
}
//4 写出数据
context.write(value, NullWritable.get());
}
private boolean parseLog(String line, Context context) {
//1 截取数据
String[] split = line.split(" ");
//2 日志长度大于11为符合要求
if(split.length > 11){
//计算器
context.getCounter("LogMapper", "parseLog true").increment(1);
return true;
}else{
//计算器
context.getCounter("LogMapper", "parseLog false").increment(1);
return false;
}
}
}
(2)驱动类:
package com.xnmzdx.mapreduce.etl;
import java.io.IOException;
import java.net.URI;
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;
public class LogDrive {
static{ //static代码块说明:windows中hadoop的问题,无法找到dll文件,所以提前加载一下,hadoop正常的,代码块删除即可
System.load("E:\\tools\\hadoop2.7.2_win10\\bin\\hadoop.dll");
}
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
args = new String[]{"D:/DSJ_ceshi/web.log","D:/DSJ_ceshi/inputlogout2"};
// 1 获取配置信息,创建job
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
// 2 指定本地程序jar包所在的路径
job.setJarByClass(LogDrive.class);
// 3 关联map业务类
job.setMapperClass(LogMapper.class);
// 5 指定最终输出的K,V类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(NullWritable.class);
// 设置reduce个数为0,就没有reduce阶段了
job.setNumReduceTasks(0);
// 6 指定job的输入和输出目录
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
// 7 提交job
// job.submit();
// 等待job完成
job.waitForCompletion(true);
}
}