#! /usr/bin/perl
#
# This script converts a MS-IIS4 logfile to the CLF logfile format
# which is used by Apache among others.
# 
# Author: Philipp Tobler, mailto:Philipp.Tobler@eurecom.fr
#
# Description of an IIS logfile, long format:
# Software: Microsoft Internet Information Server 4.0
# Version: 1.0
# Fields: date time c-ip cs-username s-sitename s-computername s-ip cs-method
# cs-uri-stem cs-uri-query sc-status sc-win32-status sc-bytes cs-bytes
# time-taken s-port cs-version cs(User-Agent) cs(Cookie) cs(Referer)
#
# Description of an IIS logfile, short format:
# Software: Microsoft Internet Information Server 4.0
# Version: 1.0
# Fields: date time c-ip cs-username cs-method cs-uri-stem sc-status
# sc-bytes cs(User-Agent) cs(Cookie) cs(Referer)


# IIS seems to store the time in the current timezone of the server,
# but in CLF, the time is stored in UTC +-timezone shift
$timezone = "+0200";

unless ($#ARGV == 1) {
die("Too few or too many input arguments.\nUsage: $0 <inputfile> <outputfile>");
}

$inputfilename=$ARGV[0];
$outputfilename=$ARGV[1];
@months=("Jan", "Feb", "Mar", "Apr", "May", "Jun", 
	 "Jul", "Aug", "Sep", "Oct", "Nov", "Dec");

open(INFILE, "$inputfilename") || die("$inputfilename not found.");
open(OUTFILE, ">$outputfilename") || die("$outputfilename not found.");

while (<INFILE>) {
  unless (/^\#/) {    # skip comments
    chomp;

# uncomment these lines if your server produces the logfiles in the "long" format
    ($date, $time, $c_ip, $cs_username, $s_sitename, 
     $s_computername, $s_ip, $cs_method, $cs_uri_stem, $cs_uri_query, 
     $sc_status, $sc_win32_status, $sc_bytes, $cs_bytes, $time_taken, 
     $s_port, $cs_version, $cs_User_Agent, $cs_Cookie, $cs_Referer) = split;

# uncomment these lines if your server produces the logfiles in the "short" format
#    ($date, $time, $c_ip, $cs_username, $cs_method, 
#     $cs_uri_stem, $sc_status, $sc_bytes, $cs_User_Agent, $cs_Cookie, 
#     $cs_Referer) = split;

    @date_clf = split /-/, $date;
    $date_clf[1] = $months[$date_clf[1]-1];
    $cs_User_Agent =~ s/\+/ /g;
    
    print OUTFILE "$c_ip - - [$date_clf[2]/$date_clf[1]/$date_clf[0]:$time ";
    print OUTFILE "$timezone] \"$cs_method $cs_uri_stem $cs_version\" ";
    print OUTFILE "$sc_status $sc_bytes \"$cs_Referer\" \"$cs_User_Agent\"\n";
  }
}
close (INFILE);
close (OUTFILE);