source: sample/hadoop-0.16/tw/org/nchc/code/LogParser.java @ 30

package tw.org.nchc.code;

import java.text.ParseException;
import java.text.SimpleDateFormat;
import java.util.Locale;
import java.util.StringTokenizer;
import java.util.regex.Matcher;
import java.util.regex.Pattern;



public class AccessLogParser {
  private String ip;
  private String protocol;
  private String method;
  private String url;
  private String code;
  private String byteSize;
  private String referrer;
  private String agent;
  private long timestamp;

  private static Pattern p = Pattern
  .compile("([^ ]*) ([^ ]*) ([^ ]*) \\[([^]]*)\\] \"([^\"]*)\"" +
                  " ([^ ]*) ([^ ]*) \"([^\"]*)\" \"([^\"]*)\".*");
  
  
  
  public AccessLogParser(String line) throws ParseException, Exception{
   
   Matcher matcher = p.matcher(line);
   if(matcher.matches()){
     this.ip = matcher.group(1);
     // IP address of the client requesting the web page.
     if(isIpAddress(ip)){
       SimpleDateFormat sdf = new SimpleDateFormat("dd/MMM/yyyy:HH:mm:ss Z",Locale.US);
       this.timestamp = sdf.parse(matcher.group(4)).getTime();
       String[] http = matcher.group(5).split(" ");
       this.method = http[0];
       this.url = http[1];
       this.protocol = http[2];
       this.code = matcher.group(6);
       this.byteSize = matcher.group(7);
       this.referrer = matcher.group(8);
       this.agent = matcher.group(9);
     }
   }


  }

  public static boolean isIpAddress(String inputString) {
    StringTokenizer tokenizer = new StringTokenizer(inputString, ".");
    if (tokenizer.countTokens() != 4) {
      return false;
    }
    try {
      for (int i = 0; i < 4; i++) {
        String t = tokenizer.nextToken();
        int chunk = Integer.parseInt(t);
        if ((chunk & 255) != chunk) {
          return false;
        }
      }
    } catch (NumberFormatException e) {
      return false;
    }
    if (inputString.indexOf("..") >= 0) {
      return false;
    }
    return true;
  }

  public String getIp() {
    return ip;
  }

  public String getProtocol() {
    return protocol;
  }

  public String getMethod() {
    return method;
  }

  public String getUrl() {
    return url;
  }

  public String getCode() {
    return code;
  }

  public String getByteSize() {
    return byteSize;
  }

  public String getReferrer() {
    return referrer;
  }

  public String getAgent() {
    return agent;
  }

  public long getTimestamp() {
    return timestamp;
  }
  
}