Hadoop(21)-数据清洗(ELT)简单版

有一个诸如这样的log日志

去除长度不合法,并且状态码不正确的记录

LogBean

package com.nty.elt;

/**
 * author nty
 * date time 2018-12-14 15:27
 */
public class Log {

    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 Log setRemote_addr(String remote_addr) {
        this.remote_addr = remote_addr;
        return this;
    }

    public String getRemote_user() {
        return remote_user;
    }

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

    public String getTime_local() {
        return time_local;
    }

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

    public String getRequest() {
        return request;
    }

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

    public String getStatus() {
        return status;
    }

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

    public String getBody_bytes_sent() {
        return body_bytes_sent;
    }

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

    public String getHttp_referer() {
        return http_referer;
    }

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

    public String getHttp_user_agent() {
        return http_user_agent;
    }

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

    public boolean isValid() {
        return valid;
    }

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

    @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();
    }

}

Mapper类

package com.nty.elt;

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;

/**
 * author nty
 * date time 2018-12-14 15:28
 */
public class LogMapper extends Mapper<LongWritable, Text, Text, NullWritable> {

    private Text logKey = new Text();

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //分割一行数据
        String[] fields = value.toString().split(" ");

        Log result = parseLog(fields);

        if (!result.isValid()) {
            return;
        }

        logKey.set(result.toString());

        // 3 输出
        context.write(logKey, NullWritable.get());
    }

    private Log parseLog(String[] fields) {

        Log log = new Log();

        if (fields.length > 11) {
            log.setRemote_addr(fields[0])
               .setRemote_user(fields[1])
               .setTime_local(fields[3].substring(1))
               .setRequest(fields[6])
               .setStatus(fields[8])
               .setBody_bytes_sent(fields[9])
               .setHttp_referer(fields[10]);
            if (fields.length > 12) {
                log.setHttp_user_agent(fields[11] + " " + fields[12]);
            } else {
                log.setHttp_user_agent(fields[11]);
            }
            // 大于400，HTTP错误
            if (Integer.parseInt(log.getStatus()) >= 400) {
                log.setValid(false);
            }
        } else {
            log.setValid(false);
        }

        return log;
    }

}

Driver

package com.nty.elt;

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;

/**
 * author nty
 * date time 2018-12-14 15:40
 */
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("d:\\Hadoop_test"));
        FileOutputFormat.setOutputPath(job, new Path("d:\\Hadoop_test_out"));

        // 6 提交
        job.waitForCompletion(true);

    }
}

结果