I have the following code that reads information from a MySQL database, determines log file format, then calls other programs as necessary to convert from IIS to NCSA format, and finally generate pretty pictures for customers. I am a big fan of efficiency, so is there a better way to do what I have here? Bear in mind that there are other programs that, for space reasons, I have not posted. 
#!/usr/bin/perl
# -*- perl -*- @(#) $Id: webalize,v 1.3 2000/06/26 20:04:11 root Exp $
#
# $Revision: 1.3 $
# $Date: 2000/06/26 20:04:11 $
# $Author: root $
# $Locker:  $
# $RCSfile: webalize,v $
# $State: Exp $
# $Source: /opt/webalizer/bin/RCS/webalize,v $

require 5.005;
use strict;
use DBI;

umask 002;

my @dom_list = '';
my $dom_restrict_query = '';
if ( scalar(@ARGV) > 0 )
{
    @dom_list = @ARGV;
    $dom_restrict_query = " and domain in ('"
    . join("','", @dom_list)
        . "') ";
}

my $prog_name = $0;
# my $log_basedir = '/webstat-filer/NT/';
my $log_basedir = '/webstat/NT/';
my $log_dir = '';

my $syscmd_webalizer_wrapper = '/opt/webalizer/bin/webalizer-wrapper';

# The parse2ncsa command takes a directory name as a parameter,
# and parses all of the logs in that directory in chronological
# order, converting to NCSA format wherever necessary.  It sends
# the NCSA common/combined log format to STDOUT.
my $syscmd_parse2ncsa = '/opt/webalizer/bin/parse2ncsa';

chdir $log_dir or die "Could not change to $log_dir";

my $domain;
my $webserver;
my $w3svc;
my $ip_addr;

my $line;

my $driver = 'mysql';
my $database = 'webstat';
my $table = 'sites';
my $user = 'statadmin';
my $password = 'statsrus';
my $dbh;
my $dsn = "DBI:$driver:$database";
my $dbh = DBI->connect($dsn, $user, $password, {RaiseError => 1, AutoC
+ommit => 1});
my $query = "select domain, server_type, server_name, log_code, log_lo
+cation from sites "
        . " where active = 1 "
    . $dom_restrict_query  # gets domains from command line
       . " order by priority ";

my $sth = $dbh->prepare($query);
$sth->execute();

my $res_hashref;

while (defined ( $res_hashref = $sth->fetchrow_hashref ))
{
    # variables are
    # $$res_hashref{'domain'}       # domain name for stats
    # $$res_hashref{'server_name'}  # server such as "ntpub1"
    # $$res_hashref{'log_code'}     # W3SVC number

    # change ARGV[0] so that current info will appear in a "ps" listin
+g
    $0 = sprintf ("%s - processing %s from %s/%s",
          $prog_name,
          $$res_hashref{'domain'},
          $$res_hashref{'server_name'},
          $$res_hashref{'log_code'});

    if ( $$res_hashref{'server_type'} eq 'iis4.0' or $$res_hashref{'se
+rver_type'} eq 'iis5.0' )
    {
    #next unless $$res_hashref{'log_code'};
    my $log_dir = join('/',
               $log_basedir,
               $$res_hashref{'server_name'},
               $$res_hashref{'log_code'});
    
    open(NCSA_STREAM,"$syscmd_parse2ncsa $log_dir $$res_hashref{'domai
+n'} |") or next;
    }
    elsif ( $$res_hashref{'server_type'} eq 'apache' )
    {
    my $log_file = $$res_hashref{'log_location'};
    open(NCSA_STREAM,"<$log_file");
    }
    else  # not iis4.0/iis5.0 nor apache
    {
    next;
    }

    open(WEBALIZER, "|$syscmd_webalizer_wrapper $$res_hashref{'domain'
+}") or next;
    while (defined ($line = <NCSA_STREAM>))
    {
    $line =~ tr/\000//d;  # remove ASCII nulls that NT IIS puts in log
+ files
    print WEBALIZER $line while defined ($line = <NCSA_STREAM>);
    }
    close(NCSA_STREAM);
    close(WEBALIZER);

}

$dbh->disconnect;

[download]

In reply to Efficiency 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.