gencode

#!/usr/bin/perl

=head1 NAME

gencode - encode your file as base pairs

=cut

my @bases = qw(A C G T);

sub ncode {
	my ($n, @chars) = @_;
	my $s = '';
	for (3,2,1,0) { 
		$s .= $chars [ int($n / @chars**$_) ];
		$n %= @chars**$_ if $_;
	}
	return $s;
}

sub dcode {
	my ($s, @chars) = @_;
	my %chars = map { $chars[$_] => $_ } (0 .. $#chars);

	die "invalid quad $s" if length $s > 4;
	my @digits = split //, $s;
	my $n = 0;
	for (0 .. 3) {
		$n += $chars{$digits[$_]} * (@chars ** (3-$_));
	}
	return $n;
}

sub ncode_file {
	my ($filename) = @_;

	open my $fh, "<", $filename
		or die "can't open input file: $!";
	
	my $string = join '',
	             map { ncode(ord($_), @bases) } 
	             map { split //, $_ } <$fh>;

	print "$_\n" for chunk_by_n(60, $string);
}

sub chunk_by_n {
	my ($n, $string) = @_;
	my @chunks;
	while ($string =~ /(.{$n})/og) { push @chunks, $1 }
	return @chunks;
}

sub dcode_file {
	my ($filename) = @_;

	open my $fh, "<", $filename
		or die "can't open input file: $!";
	
	for my $line (<$fh>) { 
		chomp $line;
		print chr dcode($_, @bases) for chunk_by_n(4, $line)
	}
}

my ($opt, $filename) = @_;

if ($opt eq '-e') { ncode_file($filename); exit; }
if ($opt eq '-d') { dcode_file($filename); exit; }
else { print "usage: gencode [ -e | -d ] filename\n"; exit; }