Hadoop(21)-資料清洗(ELT)簡單版
阿新 • • 發佈:2018-12-14
有一個諸如這樣的log日誌
去除長度不合法,並且狀態碼不正確的記錄
LogBean
package com.nty.elt; /** * author nty * date time 2018-12-14 15:27 */ public class Log { 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 public String getRemote_addr() { returnremote_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類
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 { //分割一行資料 String[] fields = value.toString().split(" "); Log result = parseLog(fields); if (!result.isValid()) { return; } logKey.set(result.toString()); // 3 輸出 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]); } // 大於400,HTTP錯誤 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 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("d:\\Hadoop_test")); FileOutputFormat.setOutputPath(job, new Path("d:\\Hadoop_test_out")); // 6 提交 job.waitForCompletion(true); } }
結果