Commit a94fd4ee authored by Christoph Haas's avatar Christoph Haas

logfileparser v1.0

parent fb680c86
package at.sprinternet.apache;
/**
* @author Christoph Haas <christoph.h@sprinternet.at>
*
* Parse an Apache log file with Regular Expressions
*
* output is configurable
*
* @version 1.0
*/
import java.io.BufferedReader;
import java.io.DataInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.regex.*;
/**
* Parse an Apache log file with Regular Expressions
*/
public class LogFileParser{
private static final int NUM_FIELDS = 9;
private static final String FIELD_SPACE = "# #";
private static final int[] DEFAULT_FIELDS = new int[] {1,3,4,5,6,7,8,9};
private static final String logEntryPattern = "^([\\d.]+) (\\S+) (\\S+) \\[([\\w:/]+\\s[+\\-]\\d{4})\\] \"(.+?)\" (\\d{3}) (\\d+) \"([^\"]+)\" \"([^\"]+)\"";
private static boolean showDebugOutput = false;
private static String logFilePath = "";
private static String parsedFilePath = "";
private static String filter = "";
private static int[] filterFields = DEFAULT_FIELDS;
private static File logFile;
private static Pattern pattern = Pattern.compile(logEntryPattern);
private static String[] parseLine(String line) {
String[] returnString = new String[filterFields.length];
Matcher matcher = pattern.matcher(line);
if (!matcher.matches() || NUM_FIELDS != matcher.groupCount()) {
System.err.println("Bad log entry (or problem with RE?):");
System.err.println(line);
} else {
for(int i = 0; i < filterFields.length; i++) {
returnString[i] = matcher.group(filterFields[i]);
}
if(showDebugOutput) {
System.out.println("IP Address: " + matcher.group(1));
System.out.println("User: " + matcher.group(3));
System.out.println("Date&Time: " + matcher.group(4));
System.out.println("Request: " + matcher.group(5));
System.out.println("Response: " + matcher.group(6));
System.out.println("Bytes Sent: " + matcher.group(7));
if (!matcher.group(8).equals("-"))
System.out.println("Referer: " + matcher.group(8));
System.out.println("Browser: " + matcher.group(9));
}
}
return returnString;
}
private static void parseFilter() {
if(filter != null && filter != "" && filter != " ") {
String[] split = filter.split(" ");
filterFields = new int[split.length];
for(int i = 0; i < split.length; i++) {
int id = 2; // default id... should alwasy be -
if(split[i].equals("ip"))
id = 1;
else if(split[i].equals("user"))
id = 3;
else if(split[i].equals("datetime"))
id = 4;
else if(split[i].equals("request"))
id = 5;
else if(split[i].equals("response"))
id = 6;
else if(split[i].equals("size"))
id = 7;
else if(split[i].equals("referer"))
id = 8;
else if(split[i].equals("browser"))
id = 9;
filterFields[i] = id;
}
}
}
public static void main(String argv[]) throws IOException {
if(argv.length < 1) {
System.err.println("Invalid argument count!");
System.err.println("Usage: ");
System.err.println("java LogFileParser <pathtologfile> [options]");
System.err.println("Options: ");
System.err.println("-o <parsedoutputfile>");
System.err.println("-f <filter>");
System.err.println("Filter: (seperated by space)");
System.err.println("ip, user, request, response, datetime, size, referer, browser");
System.exit(1);
} else {
logFilePath = argv[0];
logFile = new File(logFilePath);
if(logFile.canRead()) {
if(showDebugOutput) {
System.out.println("Using Logfile: " + logFilePath);
}
} else {
System.err.println("Cannot read logfile: " + logFilePath);
System.exit(1);
}
// we have options =)
if(argv.length > 1) {
int options = argv.length -1;
String option = "";
boolean isOption = false;
for(int i=1; i <= options; i++) {
// we have a optionstartpoint...
if(argv[i].contains("-") && !isOption) {
isOption = true;
option = argv[i].substring(1);
} else if(isOption) {
if(option.equals("o")) {
if(argv[i].startsWith("-")) {
System.err.println("Option -o needs more arguments!");
System.exit(1);
} else {
parsedFilePath = argv[i];
isOption = false;
}
} else if(option.equals("f")) {
if(argv[i].startsWith("-")) {
isOption = false;
i--; // reuse this option!
} else {
filter = filter + argv[i] + " ";
}
} else {
System.err.println("Incorrect option " + option);
System.exit(1);
}
}
parseFilter();
}
}
}
// Read the logfile line by line
FileInputStream fileStream = new FileInputStream(logFile);
DataInputStream in = new DataInputStream(fileStream);
BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(in));
String line;
if(parsedFilePath != null && parsedFilePath != "") {
String parsedLine = "";
File parsedFile = new File(parsedFilePath);
if(!parsedFile.canWrite() && !parsedFile.createNewFile()) {
System.err.println("Cannot write output file: " + parsedFilePath + "!!!");
System.exit(1);
}
FileOutputStream fileOut = new FileOutputStream(parsedFile);
while((line = bufferedReader.readLine()) != null){
String[] pLine = parseLine(line);
for(int i = 0; i < filterFields.length; i++) {
if(i != 0) {
parsedLine += FIELD_SPACE;
}
parsedLine += pLine[i];
}
parsedLine += "\n";
fileOut.write(parsedLine.getBytes());
parsedLine = "";
}
System.out.println("Output written to file: " + parsedFilePath);
} else {
String parsedLine = "";
while((line = bufferedReader.readLine()) != null){
String[] pLine = parseLine(line);
for(int i = 0; i < filterFields.length; i++) {
if(i != 0) {
parsedLine += FIELD_SPACE;
}
parsedLine += pLine[i];
}
System.out.println(parsedLine);
parsedLine = "";
}
}
}
}
\ No newline at end of file
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment