hadoop数据处理流程 hadoop数据清洗的方法

数据清洗（ETL）：提取-转换-装载（Extract-Transform-Load）

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。

一、数据清洗案例实操——简单案例

0. 需求
   去除网站日志中字段长度小于等于11的日志信息。
1. 输入数据

58.177.135.108 - - [19/Sep/2013:06:19:56 +0000] "GET /data-scientist-problems/?cf_action=sync_comments&post_id=59 HTTP/1.1" 200 48 "http://blog.fens.me/data-scientist-problems/" "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/29.0.1547.65 Safari/537.36"
111.192.165.229 - - [19/Sep/2013:06:20:16 +0000] "POST /wp-admin/admin-ajax.php HTTP/1.1" 200 95 "http://blog.fens.me/wp-admin/post.php?post=2445&action=edit&message=10" "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.95 Safari/537.36"
58.177.135.108 - - [19/Sep/2013:06:20:33 +0000] "GET /favicon.ico HTTP/1.1" 200 0 "-" "Mozilla/5.0 (iPhone; CPU iPhone OS 7_0 like Mac OS X) AppleWebKit/537.51.1 (KHTML, like Gecko) CriOS/30.0.1599.12 Mobile/11A465 Safari/8536.25"
58.177.135.108 - - [19/Sep/2013:06:20:33 +0000] "GET /wp-content/uploads/2013/05/favicon.ico HTTP/1.1" 304 0 "-" "Mozilla/5.0 (iPhone; CPU iPhone OS 7_0 like Mac OS X) AppleWebKit/537.51.1 (KHTML, like Gecko) CriOS/30.0.1599.12 Mobile/11A465 Safari/8536.25"
58.177.135.108 - - [19/Sep/2013:06:20:52 +0000] "-" 400 0 "-" "-"
163.177.71.12 - - [19/Sep/2013:06:21:14 +0000] "HEAD / HTTP/1.1" 200 20 "-" "DNSPod-Monitor/1.0"
......

0. 期望输出数据
   每行字段长度都大于11.
1. 创建包名：com.easysir.etl
2. 创建LogMapper类：

package com.easysir.etl;

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

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

        // 1 获取一行
        String line = value.toString();

        // 2 解析数据
        boolean result = parseLog(line, context);

        // 3 解析未通过
        if (!result){
            return;
        }

        // 3 解析通过
        context.write(value, NullWritable.get());
    }

    private boolean parseLog(String line, Context context){

        String[] fields = line.split(" ");

        if (fields.length > 11){
            // 实现计数器功能
            context.getCounter("map", "true").increment(1);
            return true;
        }else {
            // 实现计数器功能
            context.getCounter("map", "false").increment(1);
            return false;
        }
    }
}

0. 创建LogDriver类：

package com.easysir.etl;

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 {

        // 输入输出路径需要根据自己电脑上实际的输入输出路径设置
        args = new String[] { "E:\\idea-workspace\\mrWordCount\\input\\web.log", "E:\\idea-workspace\\mrWordCount\\output" };

        // 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);
    }
}

1. 运行结果（计数器）：

二、数据清洗案例实操——复杂案例

0. 需求
   对web访问日志中的各个字段识别切分，去除日志中不合法的记录，根据清洗规则，输出过滤后的数据.
1. 输入数据

58.177.135.108 - - [19/Sep/2013:06:19:56 +0000] "GET /data-scientist-problems/?cf_action=sync_comments&post_id=59 HTTP/1.1" 200 48 "http://blog.fens.me/data-scientist-problems/" "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/29.0.1547.65 Safari/537.36"
111.192.165.229 - - [19/Sep/2013:06:20:16 +0000] "POST /wp-admin/admin-ajax.php HTTP/1.1" 200 95 "http://blog.fens.me/wp-admin/post.php?post=2445&action=edit&message=10" "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.95 Safari/537.36"
58.177.135.108 - - [19/Sep/2013:06:20:33 +0000] "GET /favicon.ico HTTP/1.1" 200 0 "-" "Mozilla/5.0 (iPhone; CPU iPhone OS 7_0 like Mac OS X) AppleWebKit/537.51.1 (KHTML, like Gecko) CriOS/30.0.1599.12 Mobile/11A465 Safari/8536.25"
58.177.135.108 - - [19/Sep/2013:06:20:33 +0000] "GET /wp-content/uploads/2013/05/favicon.ico HTTP/1.1" 304 0 "-" "Mozilla/5.0 (iPhone; CPU iPhone OS 7_0 like Mac OS X) AppleWebKit/537.51.1 (KHTML, like Gecko) CriOS/30.0.1599.12 Mobile/11A465 Safari/8536.25"
58.177.135.108 - - [19/Sep/2013:06:20:52 +0000] "-" 400 0 "-" "-"
163.177.71.12 - - [19/Sep/2013:06:21:14 +0000] "HEAD / HTTP/1.1" 200 20 "-" "DNSPod-Monitor/1.0"
......

0. 期望输出
   均为合法数据。
1. 创建包名：com.easysir.etl2
2. 创建LogBean类，用来记录日志数据中各数据字段：

package com.easysir.etl2;

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;
    }

    @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();
    }
}

0. 创建LogMapper类：

package com.easysir.etl2;

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 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 = 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]);

            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;
    }
}

0. 创建LogDriver类：

package com.easysir.etl2;

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 {

        // 输入输出路径需要根据自己电脑上实际的输入输出路径设置
        args = new String[] { "E:\\idea-workspace\\mrWordCount\\input\\web.log", "E:\\idea-workspace\\mrWordCount\\output" };

        // 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);
    }
}