大数据MapReduce-数据清洗ETL案例实践

数据清洗ETL

代码实现

package com.it.lkw.etl;

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,默认是合法的

    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;
    }

    @Override
    public String toString() {
        StringBuilder sb = new StringBuilder();
        sb.append(this.valid);// 是否合法
        sb.append("\t").append(this.remote_addr); // 客户端的ip地址
        sb.append("\t").append(this.remote_user);//户端用户名称
        sb.append("\t").append(this.time_local);//问时间与时区
        sb.append("\t").append(this.request);//请求的url与http协议
        sb.append("\t").append(this.status);//请求状态;成功是200
        sb.append("\t").append(this.body_bytes_sent);//发送给客户端文件主体内容大小
        sb.append("\t").append(this.http_referer);//从那个页面链接访问过来的
        sb.append("\t").append(this.http_user_agent);//客户浏览器的相关信息
        return sb.toString();
    }
}

package com.it.lkw.etl;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

/**
 * web.log 数据的清洗案例分析
 */
public class LogDemo {

    /**
     * Mapper阶段
     */
    public static class LogMapper extends Mapper<LongWritable, Text, Text, NullWritable> {
        private Text k = new Text();

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            // 获取一行数据
            String line = value.toString();

            // 解析日志是否合法
            LogBean bean = parseLog(line);
            if (!bean.isValid()) {
                return;
            }

            k.set(bean.toString());

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

        // 解析日志
        private LogBean parseLog(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]);

                // 判断是否有记录客户浏览器的相关信息
                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;
        }
    }

    /**
     * Drive 阶段
     * @param args
     */
    public static void main(String[] args) throws Exception {
        // args = new String[]{"e:/input/ETL/web.log", "e:/output"};

        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        job.setJarByClass(LogDemo.class);
        job.setMapperClass(LogMapper.class);

        // job.setMapOutputKeyClass(Text.class);
        // job.setMapOutputValueClass(NullWritable.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);

        Path output = new Path(args[1]);
        if (FileSystem.get(conf).exists(output)) {
            FileSystem.get(conf).delete(output, true);
        }

        FileInputFormat.setInputPaths(job, args[0]);
        FileOutputFormat.setOutputPath(job, output);

        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : -1);
    }
}

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值