MapReduce高级案例②

kamisamak 发布于 2020-06-15 1809 次阅读

日志清洗案例

数据 展开 / 收起

[infobox title="简单解析版"]
去除日志中字段长度小于等于11的日志。
[successbox title="ruaMap01"]

package com.kami.demo02;

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;

/**
 * @version v 1.0
 * @Author kamisamak
 * @Date 2020/6/15
 */
public class ruaMap01 extends Mapper<LongWritable, Text, Text, NullWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString();
        String[] sps = line.split(" ");
        if (sps.length > 11) {
            context.getCounter("map", "true").increment(1);
            context.write(new Text(line),NullWritable.get());
        }else {
            context.getCounter("map","false").increment(1);
        }
    }
}

[/successbox]
[successbox title="ruaDriver01"]

package com.kami.demo02;

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;

/**
 * @version v 1.0
 * @Author kamisamak
 * @Date 2020/6/15
 */
public class ruaDriver01 {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        job.setJarByClass(ruaDriver01.class);

        FileInputFormat.setInputPaths(job,new Path("data\\d02\\rua01.txt"));
        FileOutputFormat.setOutputPath(job,new Path("output\\d05"));

        job.setMapperClass(ruaMap01.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);

        job.waitForCompletion(true);
    }
}

[/successbox]
[/infobox]

[infobox title="复杂解析版"]
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
[successbox title="定义的一个日志类，用来记录日志数据中的各数据字段"]


package com.kami.demo02;

/**
 * @version v 1.0
 * @Author kamisamak
 * @Date 2020/6/15
 */
public class ruaLogBean02 {
    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();
    }

    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;
    }

    public ruaLogBean02() {
    }

    public ruaLogBean02(String remote_addr, String remote_user, String time_local, String request, String status, String body_bytes_sent, String http_referer, String http_user_agent, boolean valid) {
        this.remote_addr = remote_addr;
        this.remote_user = remote_user;
        this.time_local = time_local;
        this.request = request;
        this.status = status;
        this.body_bytes_sent = body_bytes_sent;
        this.http_referer = http_referer;
        this.http_user_agent = http_user_agent;
        this.valid = valid;
    }
}

[/successbox]
[successbox title="ruaDriver02"]

package com.kami.demo02;

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;

/**
 * @version v 1.0
 * @Author kamisamak
 * @Date 2020/6/15
 */
public class ruaDriver02 {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        job.setJarByClass(ruaDriver02.class);

        FileInputFormat.setInputPaths(job,new Path("data\\d02\\rua01.txt"));
        FileOutputFormat.setOutputPath(job,new Path("output\\d06"));

        job.setMapperClass(ruaMapper02.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);

        job.waitForCompletion(true);
    }
}

[/successbox]
[successbox title="ruaMapper02"]

package com.kami.demo02;

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;

/**
 * @version v 1.0
 * @Author kamisamak
 * @Date 2020/6/15
 */
public class ruaMapper02 extends Mapper {
    Text k = new Text();
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString();
        String[] sps = line.split(" ");
        ruaLogBean02 ruaLogBean = new ruaLogBean02();
        if (sps.length > 11) {
            context.getCounter("map", "true").increment(1);
            ruaLogBean.setRemote_addr(sps[0]);
            ruaLogBean.setRemote_user(sps[1]);
            ruaLogBean.setTime_local(sps[3].substring(1));
            ruaLogBean.setRequest(sps[6]);
            ruaLogBean.setStatus(sps[8]);
            ruaLogBean.setBody_bytes_sent(sps[9]);
            ruaLogBean.setHttp_referer(sps[10]);

            if (sps.length > 12) {
                ruaLogBean.setHttp_user_agent(sps[11] + " "+ sps[12]);
            }else {
                ruaLogBean.setHttp_user_agent(sps[11]);
            }
            if (Integer.parseInt(ruaLogBean.getStatus()) >= 400) {
                ruaLogBean.setValid(false);
            }
        }else {
            ruaLogBean.setValid(false);
            context.getCounter("map","false").increment(1);
        }
        k.set(ruaLogBean.toString());
        context.write(k,NullWritable.get());
    }
}

[/successbox]
[/infobox]
题目来源:https://www.cnblogs.com/frankdeng/p/9255766.html