說明：數據清洗的過程往往只需要運行Mapper程序，不需要運行Reduce程序。
已采集到日志數據存入web.log文件中，其中一條日志格式如下：
101.206.68.147 - - [18/Sep/2018:20:05:16 +0000] "HEAD / HTTP/1.2" 200 20 "-" "DNSPod-Monitor/1.0"
清洗目標：清除日志中字段長度比11小的日志記錄。
具體代碼如下：
項目1數據清洗一
新建包com.scitc.clean
1.編寫LogMapper類：
package com.scitc.clean;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
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 獲取1行數據
String line = value.toString();
// 2 解析日志
boolean result = parseLog(line,context);
// 3 日志不合法退出
if (!result) {
return;
}
// 4 設置key
k.set(line);
// 5 寫出數據
context.write(k, NullWritable.get());
}
/**
* 功能：解析日志
* @param line 日志內容
* @param context 上下文對象
* @return
*/
private boolean parseLog(String line, Context context) {
// 1 截取
String[] fields = line.split(" ");
// 2 日志長度大於11的為合法
if (fields.length > 11) {
// 系統計數器
context.getCounter("map", "true").increment(1);
return true;
}else {
context.getCounter("map", "false").increment(1);
return false;
}
}
}
2.編寫LogDriver類
package com.scitc.clean;
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 {
//設置輸入輸出路徑設置
args = new String[] { "E:/hadoop開發文件/input", "E:/hadoop開發文件/output" };
//1 獲取job信息
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
//2 加載jar包
job.setJarByClass(LogDriver.class);
//3 關聯map
job.setMapperClass(LogMapper.class);
//4 設置最終輸出類型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(NullWritable.class);
//設置reducetask個數為0
job.setNumReduceTasks(0);
// 5 設置輸入和輸出路徑
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
//6 提交job
job.waitForCompletion(true);
} }
本地測試：
右鍵LogDriver類àrun asàjava application
即可在輸出目錄查看到清洗后的數據。
也可以打包、上傳、在集群上運行，但注意修改輸入、輸出路徑。
項目2數據清洗二
通過自定義的Bean對象封裝清洗后的日志數據。
1.編寫UpLogBean類
package com.scitc.clean;
public class UpLogBean {
private String remote_addr;// 記錄客戶端的ip地址
private String remote_user;// 記錄客戶端用戶名稱,忽略屬性"-"
private String time_local;// 記錄訪問時間與時區
private String request;// 記錄請求的url與http協議
private String status;// 記錄請求狀態；成功是200
private String body_bytes_sent;// 記錄發送給客戶端文件主體內容大小
private String http_referer;// 用來記錄從那個頁面鏈接訪問過來的
private String http_user_agent;// 記錄客戶瀏覽器的相關信息
private boolean valid = true;// 判斷數據是否合法
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();
} }
2.編寫UpLogMapper類
package com.scitc.clean;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class UpLogMapper extends Mapper<LongWritable, Text, Text, NullWritable> {
Text k = new Text();
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
// 1 獲取1行
String line = value.toString();
// 2 解析日志是否合法
UpLogBean bean = parseLog(line);
if (!bean.isValid()) {
return;
}
k.set(bean.toString());
// 3 輸出
context.write(k, NullWritable.get());
}
// 解析日志
private UpLogBean parseLog(String line) {
UpLogBean logBean = new UpLogBean();
// 1 截取
String[] fields = line.split(" ");
if (fields.length > 11) {
// 2封裝數據
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]);
}
//大於400，HTTP錯誤
if (Integer.parseInt(logBean.getStatus()) >= 400) {
logBean.setValid(false);
}
}else {
logBean.setValid(false);
}
return logBean;
} }
3.編寫UpLogDriver類
package com.scitc.clean;
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 UpLogDriver {
public static void main(String[] args) throws Exception {
args = new String[] { "E:/hadoop開發文件/input", "E:/hadoop開發文件/upoutput" };
// 1 獲取job信息
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
// 2 加載jar包
job.setJarByClass(UpLogDriver.class);
// 3 關聯map
job.setMapperClass(UpLogMapper.class);
// 4 設置最終輸出類型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(NullWritable.class);
// 5 設置輸入和輸出路徑
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
// 6 提交
job.waitForCompletion(true);
} }
本地測試：
右鍵UpLogDriver類àrun asàjava application
即可在輸出目錄查看到清洗后的數據。
也可以打包、上傳、在集群上運行，但注意修改輸入、輸出路徑。