Shell Programming and Scripting

foreach $item (@a1, @a2) { $count{$item}++;}

foreach $item (keys %count) {
    if ($count{$item} == 2) {
        next;
    } else {
        push @diff, $item;
    }
}

my @sorted =sort @diff;
#print "\nIntersect Array = @isect\n";
foreach my $el(@sorted){
print "$el\n";
}

open( my $lfh, '<', 'file' ) 
or die "Unable to open file - 'file' <$!>\n";

my %uniqHash;
while ( my $data = <$lfh> ) {
    chomp($data);
    $uniqHash{$data}++;
}

close($lfh);

$
$ cat data.txt
KB0005 1019 T IFVATVPVI 0.691 PKC YES
KB0005 1036 T YFLQTSQQL 0.785 PKC YES
KB0005 1037 S FLQTSQQLK 0.585 DNAPK YES
KB0005 1045 S KQLESEGRS 0.669 PKC YES
KB0005 1045 S KQLESEGRS 0.880 unsp YES
KB204320 1019 T IFVATVPVI 0.699 PKC YES
KB204320 1036 T YFLQTSQQL 0.789 PKC YES
KB204320 1037 S FLQTSQQLK 0.589 DNAPK YES
KB204320 1045 S KQLESEGRS 0.880 unsp YES
$
$ cat testscr.pl
#!/usr/bin/perl -w
$prevname = "";
open (F,"data.txt") or die "Can't open data.txt: $!";
while (<F>) {
  chomp;
  ($name = $_) =~ s/(\w+) .*/$1/;
  ($elem = $_) =~ s/\w+ (.*)/$1/;
  if ($prevname eq "") {
    $arrnum = 1;
  } elsif ($name ne $prevname) {
    $arrnum = 2;
  }
  # assuming there are only 2 distinct names, hence 2 arrays
  if ($arrnum == 1) {
    push @a1, "$name:$elem";
  } elsif ($arrnum == 2) {
    push @a2, "$name:$elem";
  }
  $prevname = $name;
}
close (F) or die "Can't close data.txt: $!";
# the value is a tilde-delimited string of names for which the
# line occurs
foreach $item (@a1, @a2) {
  ($key = $item) =~ s/\w+:(.*)/$1/;
  ($val = $item) =~ s/(\w+):.*/$1/;
  $count{$key} .= "~".$val
}
foreach $item (keys %count) {
  ($x = $count{$item}) =~ s/[^~]//g;
  if ( $x eq "~~") {  # line occurred for both names
    next;
  } else {            # array element has the line followed by "~name"
    push @diff, "$item$count{$item}";
  }
}
@sorted = sort @diff;
foreach $el (@sorted) {
  ($name = $el) =~ s/.*~(\w+)/$1/;
  ($elem = $el) =~ s/(.*)~\w+/$1/;
  printf("%-10s => %s\n",$name,$elem);
}
$
$ perl testscr.pl
KB0005     => 1019 T IFVATVPVI 0.691 PKC YES
KB204320   => 1019 T IFVATVPVI 0.699 PKC YES
KB0005     => 1036 T YFLQTSQQL 0.785 PKC YES
KB204320   => 1036 T YFLQTSQQL 0.789 PKC YES
KB0005     => 1037 S FLQTSQQLK 0.585 DNAPK YES
KB204320   => 1037 S FLQTSQQLK 0.589 DNAPK YES
KB0005     => 1045 S KQLESEGRS 0.669 PKC YES
$
$