MapReduce数据清洗

一、 简单解析版

1.需求

去除日志中字段长度小于等于11的日志。

2.输入数据

3.实现代码

（1）编写LogMapper

package com.bigdata.mapreduce.weblog;
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>{	
	Text k = new Text();
	
	@Override
	protected void map(LongWritable key, Text value, Context context)
			throws IOException, InterruptedException {
		
		// 1 获取1行数据
		String line = value.toString();
		
		// 2 解析日志
		boolean result = parseLog(line,context);
		
		// 3 日志不合法退出
		if (!result) {
			return;
		}
		
		// 4 设置key
		k.set(line);
		
		// 5 写出数据
		context.write(k, NullWritable.get());
   	}

	// 2 解析日志
	private boolean parseLog(String line, Context context) {
		// 1 截取
		String[] fields = line.split(" ");
		
		// 2 日志长度大于11的为合法
		if (fields.length > 11) {
			// 系统计数器
			context.getCounter("map", "true").increment(1);
			return true;
		}else {
			context.getCounter("map", "false").increment(1);
			return false;
		}
	}
}

（2）编写LogDriver

package com.bigdata.mapreduce.weblog;
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 LogDriver {

	public static void main(String[] args) throws Exception {

      		args = new String[] { "e:/input/inputlog", "e:/output1" };

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

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

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

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

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

		// 5 设置输入和输出路径
		FileInputFormat.setInputPaths(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));

		// 6 提交
		job.waitForCompletion(true);
	}
}

二、复杂解析版

1．需求

对web访问日志中的各字段识别切分
去除日志中不合法的记录
根据统计需求，生成各类访问请求过滤数据

2．输入数据

3．实现代码

（1）定义一个bean，用来记录日志数据中的各数据字段

package com.bigdata.mapreduce.log;

@Data
public class LogBean {
	private String remote_addr;// 记录客户端的ip地址
	private String remote_user;// 记录客户端用户名称,忽略属性"-"
	private String time_local;// 记录访问时间与时区
	private String request;// 记录请求的url与http协议
	private String status;// 记录请求状态；成功是200
	private String body_bytes_sent;// 记录发送给客户端文件主体内容大小
	private String http_referer;// 用来记录从那个页面链接访问过来的
	private String http_user_agent;// 记录客户浏览器的相关信息
	private boolean valid = true;// 判断数据是否合法

	@Override
	public String toString() {
		StringBuilder sb = new StringBuilder();
		sb.append(this.valid);
		sb.append("\001").append(this.remote_addr);
		sb.append("\001").append(this.remote_user);
		sb.append("\001").append(this.time_local);
		sb.append("\001").append(this.request);
		sb.append("\001").append(this.status);
		sb.append("\001").append(this.body_bytes_sent);
		sb.append("\001").append(this.http_referer);
		sb.append("\001").append(this.http_user_agent);
		
		return sb.toString();
	}
}

（2）编写LogMapper程序

package com.bigdata.mapreduce.log;
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>{
	Text k = new Text();

@Override
protected void map(LongWritable key, Text value, Context context)
		throws IOException, InterruptedException {
	// 1 获取1行
	String line = value.toString();
	
	// 2 解析日志是否合法
	LogBean bean = pressLog(line);
	
	if (!bean.isValid()) {
		return;
	}
	
	k.set(bean.toString());
	
	// 3 输出
	context.write(k, NullWritable.get());
}

// 解析日志
private LogBean pressLog(String line) {
	LogBean logBean = new LogBean();
	
	// 1 截取
	String[] fields = line.split(" ");
	
	if (fields.length > 11) {
		// 2封装数据
		logBean.setRemote_addr(fields[0]);
		logBean.setRemote_user(fields[1]);
		logBean.setTime_local(fields[3].substring(1));
		logBean.setRequest(fields[6]);
		logBean.setStatus(fields[8]);
		logBean.setBody_bytes_sent(fields[9]);
		logBean.setHttp_referer(fields[10]);
		
		if (fields.length > 12) {
			logBean.setHttp_user_agent(fields[11] + " "+ fields[12]);
		}else {
			logBean.setHttp_user_agent(fields[11]);
		}
		
		// 大于400，HTTP错误
		if (Integer.parseInt(logBean.getStatus()) >= 400) {
			logBean.setValid(false);
		}
	}else {
		logBean.setValid(false);
	}
	
	return logBean;
}
}

（3）编写LogDriver程序

package com.bigdata.mapreduce.log;
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 LogDriver {
	public static void main(String[] args) throws Exception {
		// 1 获取job信息
		Configuration conf = new Configuration();
		Job job = Job.getInstance(conf);

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

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

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

	// 5 设置输入和输出路径
	FileInputFormat.setInputPaths(job, new Path(args[0]));
	FileOutputFormat.setOutputPath(job, new Path(args[1]));

	// 6 提交
	job.waitForCompletion(true);
}
}