This program reads IIS logs and parses them into NCSA format in order to be processed by a statistics program. Again, I would like this done in the most efficient manner possible, so any suggestions to improve efficieny are more than welcome. 
#!/usr/bin/perl

# Microsoft IIS Log Format
#   fields are separated by commas
#   a hyphen '-' serves as placeholder if no valid data present
#
my $user_ip_addr;
my $username;             # username of user   RFC931 ?
my $date;                 # MM/DD/YY
my $time;                 # H:MM:SS
my $ms_service;           # such as W3SVC1
my $server_hostname;      # such as NTPUB1
my $server_ip_addr; 
my $time_elapsed;         # in seconds
my $bytes_received; 
my $bytes_sent; 
my $service_status_code;  # HTTP code
my $mswin_status_code;    # MS Windows NT status code
my $op_name;              # such as GET, POST, HEAD, PUT
my $op_target;            # such as index.html
my $junk;

my $date_year;
my $date_mon;
my $date_dd;

my @months = qw( NUL Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec )
+;
my $line;

my $utc_offset = '-0500';
my $century = '20';

while (defined ($line = <STDIN>))
{
    chomp $line;
    $line =~ tr/\000//d;
    $line =~ s# "HTTP/1\.# HTTP/1.#;

    next if $line eq '';

    (
    $user_ip_addr,
    $username,
    $date,
    $time,
    $ms_service,
    $server_hostname,
    $server_ip_addr,
    $time_elapsed,
    $bytes_received,
    $bytes_sent,
    $service_status_code,
    $mswin_status_code,
    $op_name,
    $op_target,
    $junk
    ) = split(/, /, $line, 15);

    next if $op_target eq '' or ! defined $op_target;

    ($date_mon, $date_dd, $date_year) = split(m#/#, $date, 3);
    $century = ( $date_year < 90 ) ? '20' : '19';
    $date_mon = sprintf("%02s",$date_mon);
    $date_dd = sprintf("%02s",$date_dd);
    $date_mon = $months[$date_mon];
    # $time =~ s/([0-9]:[0-9][0-9]:[0-9][0-9])/0$1/;
    $time = sprintf "%08s", $time;
    
    #NCSA combined log format:
    #$remote_host $remote_logname $remote_user $time_commonlog "$reque
+st" $status $bytes_sent "$http_referer" "$http_user_agent"

    print "$user_ip_addr $username - [$date_dd/$date_mon/$century$date
+_year:$time $utc_offset] \"$op_name $op_target\" $service_status_code
+ $bytes_sent \"-\" \"-\"\n";

#    print join(' ',
#        $user_ip_addr,
#        $username,
#        '-',
#        join('', '[', $date_dd, '/', $date_mon, '/', $century,
#            $date_year, ':', $time, ' ', $utc_offset, ']'),
#        join('', '"', $op_name, ' ', $op_target, '"'),
#        $service_status_code,
#        $bytes_sent,
#        '"-"',  # HTTP_REFERER
#        '"-"'   # HTTP_USER_AGENT
#        );
#    print "\n";

}

[download]

In reply to Efficiency revisited by tekniko

Title:
Use:  <p> text here (a paragraph) </p>
and:  <code> code here </code>
to format your post, it's "PerlMonks-approved HTML":


  • Posts are HTML formatted. Put <p> </p> tags around your paragraphs. Put <code> </code> tags around your code and data!
  • Titles consisting of a single word are discouraged, and in most cases are disallowed outright.
  • Read Where should I post X? if you're not absolutely sure you're posting in the right place.
  • Please read these before you post! —
  • Posts may use any of the Perl Monks Approved HTML tags:
    a, abbr, b, big, blockquote, br, caption, center, col, colgroup, dd, del, details, div, dl, dt, em, font, h1, h2, h3, h4, h5, h6, hr, i, ins, li, ol, p, pre, readmore, small, span, spoiler, strike, strong, sub, summary, sup, table, tbody, td, tfoot, th, thead, tr, tt, u, ul, wbr
  • You may need to use entities for some characters, as follows. (Exception: Within code tags, you can put the characters literally.)
            For:     Use:
    & &amp;
    < &lt;
    > &gt;
    [ &#91;
    ] &#93;
  • Link using PerlMonks shortcuts! What shortcuts can I use for linking?
  • See Writeup Formatting Tips and other pages linked from there for more info.