MapReduce資料清洗
阿新 • • 發佈:2018-11-25
一、 簡單解析版
1.需求
去除日誌中欄位長度小於等於11的日誌。
2.輸入資料
3.實現程式碼
(1)編寫LogMapper
package com.bigdata.mapreduce.weblog; 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行資料 String line = value.toString(); // 2 解析日誌 boolean result = parseLog(line,context); // 3 日誌不合法退出 if (!result) { return; } // 4 設定key k.set(line); // 5 寫出資料 context.write(k, NullWritable.get()); } // 2 解析日誌 private boolean parseLog(String line, Context context) { // 1 擷取 String[] fields = line.split(" "); // 2 日誌長度大於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
package com.bigdata.mapreduce.weblog; 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 { args = new String[] { "e:/input/inputlog", "e:/output1" }; // 1 獲取job資訊 Configuration conf = new Configuration(); Job job = Job.getInstance(conf); // 2 載入jar包 job.setJarByClass(LogDriver.class); // 3 關聯map job.setMapperClass(LogMapper.class); // 4 設定最終輸出型別 job.setOutputKeyClass(Text.class); job.setOutputValueClass(NullWritable.class); // 設定reducetask個數為0 job.setNumReduceTasks(0); // 5 設定輸入和輸出路徑 FileInputFormat.setInputPaths(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); // 6 提交 job.waitForCompletion(true); } }
二、複雜解析版
1.需求
對web訪問日誌中的各欄位識別切分
去除日誌中不合法的記錄
根據統計需求,生成各類訪問請求過濾資料
2.輸入資料
3.實現程式碼
(1)定義一個bean,用來記錄日誌資料中的各資料欄位
package com.bigdata.mapreduce.log; @Data public class LogBean { private String remote_addr;// 記錄客戶端的ip地址 private String remote_user;// 記錄客戶端使用者名稱稱,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;// 記錄傳送給客戶端檔案主體內容大小 private String http_referer;// 用來記錄從那個頁面連結訪問過來的 private String http_user_agent;// 記錄客戶瀏覽器的相關資訊 private boolean valid = true;// 判斷資料是否合法 @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(); } }
(2)編寫LogMapper程式
package com.bigdata.mapreduce.log;
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
String line = value.toString();
// 2 解析日誌是否合法
LogBean bean = pressLog(line);
if (!bean.isValid()) {
return;
}
k.set(bean.toString());
// 3 輸出
context.write(k, NullWritable.get());
}
// 解析日誌
private LogBean pressLog(String line) {
LogBean logBean = new LogBean();
// 1 擷取
String[] fields = line.split(" ");
if (fields.length > 11) {
// 2封裝資料
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LogDriver程式
package com.bigdata.mapreduce.log;
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 {
// 1 獲取job資訊
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
// 2 載入jar包
job.setJarByClass(LogDriver.class);
// 3 關聯map
job.setMapperClass(LogMapper.class);
// 4 設定最終輸出型別
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(NullWritable.class);
// 5 設定輸入和輸出路徑
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
// 6 提交
job.waitForCompletion(true);
}
}