check tags/data length

check_each_line.pl

#!/usr/bin/env perl

use 5.14.0;

my $odata = '============================================================================================================================================================================================================================================================================================================';
my $data_length = length($odata);

my $seq = {first => [], second => [], third => [], forth => []};
my $lines = 0;
my $bytes = 0;
my $broken = 0;

while(my $line = <STDIN>){
    $lines += 1;
    $bytes += length($line);
    chomp $line;
    my ($tag, $data) = split(/\t/, $line, 2);
    unless ($tag and $tag =~ /^(first|second|third|forth)(\d{8})$/ and $data and length($data) == $data_length) {
        $broken += 1;
        next;
    }
    my $tagname = $1;
    my $num = $2;
    my $pair = $seq->{$tagname}->[-1] || [-2, -2];
    if ($pair->[1] == $num - 1) {
        $pair->[1] = $num;
    }
    else {
        push $seq->{$tagname}, [$num, $num];
    }
}

foreach my $tagname (keys %$seq) {
    foreach my $pair (@{$seq->{$tagname}}) {
        print $tagname, "\t", $pair->[0], "\t", $pair->[1], "\n";
    }
}
print "lines\t", $lines, "\n";
print "bytes\t", $bytes, "\n";
print "broken\t", $broken, "\n";