MR案例之日志清洗

简单版

在运行核心业务Mapreduce程序之前，往往要先对数据进行清洗，清理掉不符合用户要求的数据。清理的过程往往只需要运行mapper程序，不需要运行reduce程序。

需求分析

对于输入的数据文件，需要去除日志中按照空格切分，字段数小于等于11的日志。

输入数据

数据格式如下：

编写代码

CleanMapper编写

简单版本的清洗任务在map中就可以完成，所以不需要编写reduce。

package LogClean;

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;

/***
 * 通过map来进行数据清洗
 */
public class CleanMapper extends Mapper<LongWritable,Text, Text, NullWritable> {

    //快捷键alt+insert实现父类
    //ctrl+alt+o去掉无用的包

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //首先读一行数据
        String logs=value.toString();
        //按照空格切分数据
        String[] log = logs.split(" ");
        //统计一行数据的字段长，去除小于11的字段
        if(log.length>=11) context.write(value,NullWritable.get());
    }
}

CleanDriver编写

package LogClean;

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;

/***
 * 主类，进行对job的封装
 */
public class CleanDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

        //配置job
        Job job = Job.getInstance(new Configuration());
        job.setJarByClass(CleanDriver.class);

        //配置map的类以及输出数据类型
        job.setMapperClass(CleanMapper.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);

        //配置reduce的个数，默认是1
        //但是简单版本不需要reduce，清洗工作在map中已经完成
        job.setNumReduceTasks(0);

        //输入数据路径
        FileInputFormat.setInputPaths(job,new Path("D:\\BigdataTest\\LogCleaning\\web.txt"));
        //输出数据路径
        FileOutputFormat.setOutputPath(job,new Path("D:\\BigdataTest\\LogCleaning\\result"));
        //提交任务
        job.waitForCompletion(true);

    }
}

输出结果

清洗之前：大小2970kb


清洗之后：2901kb


去除掉了字段小于11的数据。

复杂版

需求分析

• 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（1.字段小于等于11不合法 2.状态码大于等于400）
• 根据统计需求，生成各类访问请求过滤数据

输入数据

输入数据同简单版本的输入数据

编写代码

定义Bean

定义一个bean，用来记录日志数据中的各数据字段。

package LogClean;

/***
 * 编写一个Bean用来记录日志数据中心各个数据字段
 */
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

    public String getRemote_addr() {
        return remote_addr;
    }

    public void setRemote_addr(String remote_addr) {
        this.remote_addr = remote_addr;
    }

    public String getRemote_user() {
        return remote_user;
    }

    public void setRemote_user(String remote_user) {
        this.remote_user = remote_user;
    }

    public String getTime_local() {
        return time_local;
    }

    public void setTime_local(String time_local) {
        this.time_local = time_local;
    }

    public String getRequest() {
        return request;
    }

    public void setRequest(String request) {
        this.request = request;
    }

    public String getStatus() {
        return status;
    }

    public void setStatus(String status) {
        this.status = status;
    }

    public String getBody_bytes_sent() {
        return body_bytes_sent;
    }

    public void setBody_bytes_sent(String body_bytes_sent) {
        this.body_bytes_sent = body_bytes_sent;
    }

    public String getHttp_referer() {
        return http_referer;
    }

    public void setHttp_referer(String http_referer) {
        this.http_referer = http_referer;
    }

    public String getHttp_user_agent() {
        return http_user_agent;
    }

    public void setHttp_user_agent(String http_user_agent) {
        this.http_user_agent = http_user_agent;
    }

    public boolean isValid(){
        return valid;
    }
    public void setValid(boolean valid){
        this.valid=valid;
    }

    //重写toString方法用来拼接数据

    @Override
    public String toString(){
        
        StringBuilder sb = new StringBuilder();
        sb.append(this.valid);
        //"\001"是一个特殊符号
        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();

    }

}

编写CleanMapper2

package LogClean;

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 CleanMapper2 extends Mapper<LongWritable, Text,Text, NullWritable> {

    //自动补全的快捷键 ctrl+alt+空格
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //获取数据
        String logs = value.toString();
        //判断日志是否合法
        LogBean logBean = pressLog(logs);
        
        if(!logBean.isValid()) return;
        
        context.write(new Text(logBean.toString()),NullWritable.get());

    }
    public LogBean pressLog(String logs){

        LogBean logBean = new LogBean();
        //切分数据
        String[] fields = logs.split(" ");

        //长度判定
        if(fields.length>11){
            //封装数据到LogBean
            logBean.setRemote_addr(fields[0]);
            logBean.setRemote_user(fields[1]);
            logBean.setTime_local(fields[3]+fields[4]);
            logBean.setRequest(fields[7]);
            logBean.setStatus(fields[8]);
            logBean.setBody_bytes_sent(fields[9]);
            logBean.setHttp_referer(fields[10]);
            //用户信息
            if(fields.length>12){
                logBean.setHttp_user_agent(fields[11]+" "+fields[12]);
            }else logBean.setHttp_user_agent(fields[11]);
            
            //判断状态码 去除状态码大于等于400的
            if(Integer.parseInt(logBean.getStatus())>=400) logBean.setValid(false);
            
            
        }else logBean.setValid(false);
        
        return logBean;
    }

}

编写CleanDriver2

package LogClean;

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 CleanDriver2 {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

        //配置job
        Job job = Job.getInstance(new Configuration());
        job.setJarByClass(CleanDriver2.class);

        //配置map的类以及输出数据类型
        job.setMapperClass(CleanMapper2.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);

        //配置reduce的个数，默认是1
        //但是简单版本不需要reduce，清洗工作在map中已经完成
        job.setNumReduceTasks(0);

        //输入数据路径
        FileInputFormat.setInputPaths(job,new Path("D:\\BigdataTest\\LogCleaning\\web.txt"));
        //输出数据路径
        FileOutputFormat.setOutputPath(job,new Path("D:\\BigdataTest\\LogCleaning\\result2"));
        //提交任务
        job.waitForCompletion(true);

    }
}

输出结果

清洗之前：大小2970kb

清洗之后：大小1602kb