in reply to Building "islands" of related data
use strict; use warnings; my (%domains, @domains, @sets, $i, $j); %domains = ( 'domain1.com' => ['company1', 'contact1', 'address1', 'phone1', 'fax1', 'email1 +'], 'domain2.com' => ['company2', 'contact2', 'address2', 'phone1', 'fax2', 'email1 +'], 'domain3.com' => ['company3', 'contact3', 'address3', 'phone3', 'fax3', 'email3 +'], 'domain4.com' => ['company3', 'contact4', 'address4', 'phone3', 'fax1', 'email1 +'], 'domain5.com' => ['company5', 'contact5', 'address5', 'phone5', 'fax5', 'email5 +'], 'domain6.com' => ['company5', 'contact6', 'address6', 'phone6', 'fax6', 'email5 +']); @domains = keys %domains; while ($#domains > -1) { my @newset = shift @domains; for ($i = 0; $i <= $#newset; $i++) { for ($j = 0; $j <= $#domains; $j++) { push @newset, splice(@domains, $j--, 1) if compare($newset[$i], $domains[$j]); } } push @sets, \@newset; } for (@sets) { print join ' ', sort @$_; print "\n"; } sub compare { my $d1 = $domains{$_[0]}; my $d2 = $domains{$_[1]}; my $c = 0; for (0..$#$d1) { return 1 if $d1->[$_] && $d1->[$_] eq $d2->[$_] && ++$c == 2; } }
|
---|