#!/usr/bin/perl

use Getopt::Long;

$w=200000;		# window size
$x=10;			# segment count
GetOptions("only"=>\$only, "window=i"=>\$w, "segs=i"=>\$x);

die usage() unless @ARGV;
die usage() if $only && @ARGV > 1;

$x-=1;
for $f (@ARGV) {
	my $s = -s $f;
	open (IN, $f) || die "$f: $!\n";	
	my $rc = 0;
	my $nl = 0;
	if ($s > ($w*2)) {
		for ($i=0;$i<$x;++$i) {
			seek(IN, $i*($s-$w)/$x, 0) if $i > 0;
			read(IN, $d, $w/$x);
			#whole lines only, prevents overcounting
			if ($i > 0) {
				$d=substr($d, index($d, "\n")+1);
			}
			$d=substr($d, 0, rindex($d, "\n"));
			$rc += length($d);
    			$nl += xlc($d);
		}
		seek(IN, -$w/3, 2);
		read(IN, $d, $w/3);
		#whole lines only
		$d=substr($d, index($d, "\n")+1);
		$rc += length($d);
    		$nl += xlc($d);
	} else {
		$rc += read(IN, $d, $w);
    		$nl += xlc($d);
	}

	$nl = int($rc > 0 ? $nl * $s / $rc : 0);
	$tl += $nl;
	print "$nl\n" if $only;
	$nl{$f} = $nl if !$only;
}

if (!$only) {
	$m=length($tl)+1;
	for $f (@ARGV) {
		printf "%*d %s\n", $m, $nl{$f}, $f;
	}
	printf "%*d %s\n", $m, $tl, "total" if @ARGV > 1;
}

sub xlc {
	my $d = $_[0];
	my $p=0;
	my $c=0;
	my $i=0;
	while (($i=index($d, "\n", $p))>=0) {
		++$c;
		$p=$i+1;
	}
	return $p<length($d) ? $c+1 : $c;		# correct count
}

sub usage {<<EOF
Usage: alc [-o] <file1> [<file2>] ...

Approximate line counts for each file.  Attempts to be 
somewhat compatible with "wc -l" by default.

-o|--only            Output line count only for a single file.
-w|--window <int>    Read <int> bytes from head, mid, and tail.
-s|--segs <int>      Divide file & window into <int> segments.
EOF
};

__END__

=head1 NAME

alc - Approximate line count

=head1 DESCRIPTION

Approximate line counts for each file.  Attempts to be
somewhat compatible with "wc -l" by default.

=head1 AUTHOR

Erik Aronesty C<earonesty@cpan.org>

=head1 LICENSE

This program is free software; you can redistribute it and/or
modify it under the same terms as Perl itself.

See L<http://www.perl.com/perl/misc/Artistic.html>.

=cut