Re: analyzing data - if I understand the question

[Discipulus]

Hello matt00perl and welcome,

be sure next time to be precise as you can about what yoou have and what you expect, because, as chatted some hours ago, i think your expectection are mispelled.

In any case, if this can help you, for uniqueness i suggest to use hash.

#!perl
use strict;
use warnings;
use Data::Dumper;

my %occur;
my $data_pos = tell DATA; # save the position, for later use
while (<DATA>) {

    chomp;         #elimnates newline
    s/\s*<p>\s*//g;#remove tags and unecessary withespaces
    my ($time,$src_mac,$dest_mac,$src_ip,$src_port,$dest_ip,$dest_port
+) = split /\s\|\s/, $_;
    #check lesser time
    # be AWARE of the poor time comparison implementation: maybe bette
+r transform each time
    #in seconds from epoch, do the comparison numerically (ie: < or > 
+instead of lt gt), riconvert in what you want
    if (defined $occur{$dest_ip}{'mintime'}) {
        $occur{$dest_ip}{'mintime'} = $time if $time lt $occur{$dest_i
+p}{'mintime'};
    }
    else {$occur{$dest_ip}{'mintime'} = $time}
    #check greater time
    if (defined $occur{$dest_ip}{'maxtime'}) {
        $occur{$dest_ip}{'maxtime'} = $time if $time gt $occur{$dest_i
+p}{'maxtime'};
    }
    else {$occur{$dest_ip}{'maxtime'} = $time}
    #you can save in the hash entry other fields you may need..
    # $occur{$dest_ip}{'src_mac'} =  $src_mac; and so on..
}

print Dumper (\%occur);

#or to be precise we need unique connections i think
undef %occur;
seek DATA, $data_pos, 0; #rewind DATA
while (<DATA>){
    chomp;
    s/\s*<p>\s*//g;
    my ($time,$src_mac,$dest_mac,$src_ip,$src_port,$dest_ip,$dest_port
+) = split /\s\|\s/, $_;
    #change only the hash key creation
    my $connection = 'from_'.$src_ip.'_to_'.$dest_ip.'_port_'.$dest_po
+rt;
    #all the same now
    if (defined $occur{$connection}{'mintime'}) {
        $occur{$connection}{'mintime'} = $time if $time lt $occur{$con
+nection}{'mintime'};
    }
    else {$occur{$connection}{'mintime'} = $time}
    #check greater time
    if (defined $occur{$connection}{'maxtime'}) {
        $occur{$connection}{'maxtime'} = $time if $time gt $occur{$con
+nection}{'maxtime'};
    }
    else {$occur{$connection}{'maxtime'} = $time}
    
}
print Dumper (\%occur);
__DATA__
<p> 03-23 00:37:28.174515 | 8ca982044d00 | c04a00332142 | 192.168.1.10
+0 | 49671 | 180.149.153.11 | 80 <p>
<p> 03-23 00:37:28.174536 | 8ca982044d00 | c04a00332142 | 192.168.1.10
+0 | 49671 | 180.149.153.11 | 80 <p>
<p> 03-23 00:41:36.422588 | 8ca982044d00 | c04a00332142 | 192.168.1.10
+0 | 49672 | 180.149.153.11 | 80 <p>
<p> 03-23 00:44:18.584080 | 8ca982044d00 | c04a00332142 | 192.168.1.10
+0 | 49671 | 180.149.153.11 | 80 <p>
<p> 03-23 00:44:22.588592 | 8ca982044d00 | c04a00332142 | 192.168.1.10
+0 | 35660 | 180.149.134.61 | 80 <p>
<p> 03-23 00:45:12.636571 | 8ca982044d00 | c04a00332142 | 192.168.1.10
+0 | 35661 | 180.149.134.61 | 80 <p>

####OUTPUT
$VAR1 = {
          '180.149.153.11' => {
                                'maxtime' => '03-23 00:44:18.584080',
                                'mintime' => '03-23 00:37:28.174515'
                              },
          '180.149.134.61' => {
                                'maxtime' => '03-23 00:45:12.636571',
                                'mintime' => '03-23 00:44:22.588592'
                              }
        };
$VAR1 = {
          'from_192.168.1.100_to_180.149.153.11_port_80' => {
                                                              'maxtime
+' => '03-23 00:44:18.584080',
                                                              'mintime
+' => '03-23 00:37:28.174515'
                                                            },
          'from_192.168.1.100_to_180.149.134.61_port_80' => {
                                                              'maxtime
+' => '03-23 00:45:12.636571',
                                                              'mintime
+' => '03-23 00:44:22.588592'
                                                            }
        };

HtH
L*

[matt00perl]

thank you for the piece of code i appreciate your time.here is what is happening... i have foreach which index through my raw pcap data and decode it, after that i printed out the output above. Instead of printing out that out i want to extend the foreach to calculate the time based on destination ip add