#! perl -w
use strict;
my ($file, $col, $file2, $col2) = @ARGV;
my (%unique, %unique2);
my @column;
my ($x, $header);

my @fields;
# I put something like this in all my scripts so I don't need to remember argument order
if ($file eq "?"){
	die "usage:  compcolumns.pl file1 column1 file2 column2\n";
	}
	

## whenever you open a file, do yourself a favor and tell yourself if it doesn't open
open FIL, $file or die "Could not open $file: $!\n";
$x = 0;
%unique=();
while (<FIL>){
	chomp;
        ##The split here, a regular expression, is what you would change (at least if your data is based on space delimiting instead of tab-delimiting).
	@fields = split /\t/;
	
	if (defined ($fields[$col]) ){
		$header = $fields[$col] if $x == 0;
		$unique{$fields[$col]}++;
			}
	else{
		$unique{"BLANK"}++;
		$header = "BLANK";
		}
	$x++;	
	}
	
open FIL, $file2 or die "Could not open $file2: $!\n";
$x=0;
while (<FIL>){
	chomp;
	@fields = split /\t/;
	if (defined ($fields[$col2]) ){
			$header = $fields[$col2] if $x == 0;
			$unique2{$fields[$col2]}++;
				}
		else{
			$unique2{"BLANK"}++;
			$header = "BLANK";
			}
	$x++;
	}
## The output routine.  Note that if something's in both files, it will be printed twice.  	
foreach (sort keys %unique) {
	if (!exists $unique2{$_}){
		print "$_ in $file but not $file2\n";
		}
	else {
		print "$_ in both files\n";
		}
	}

foreach (sort keys %unique2) {
	if (!exists $unique{$_}){
		print "$_ in $file2 but not $file\n";
		}
	else {
		print "$_ in both files\n";
		}
	}