#!/usr/bin/perl-w
use strict;
use warnings;
use open ':utf8';
use autodie;

open NONMATCHINPUT, "<OutputNonMatchedWords.txt";
open OIC, ">OutputIdenticalCognates.txt";
open ONIC, ">OutputNonIdenticalCognates.txt";
open ONC, ">OutputNonCognates.txt";

my %nonmatchhash;

while (my $line = <NONMATCHINPUT>)
{
	chomp $line;

	#split the line on tab
	my ($nonmatchhashkeys, $nonmatchhashvalues) = split /\t/, $line;
	$nonmatchhash{$nonmatchhashkeys} = $nonmatchhashvalues;

	#if the values of the hash are exactly the same as the keys of the hash
	if ($nonmatchhash{$nonmatchhashkeys} = $nonmatchhash{$nonmatchhashvalues})
	{
		#print both key and value to OutputIdenticalCognates.txt, separated by a tab
		print OIC "$nonmatchhashkeys\t$nonmatchhashvalues\n";
	}

	#assign each key in the hash to $AfrColumn1token
	foreach my $AfrColumn1token(keys %nonmatchhash)
	{
        
		#if the Afrikaans word ($AfrColumn1token) contains: anything, followed by 'agtig', followed by 'e' or 'er' or 'ste' (optional), at the end of the string
		if ($AfrColumn1token =~ /(.*)(agtig)(e|er|ste)?$/)
		{
			#then, by using a foreach, assign each value in the hash to $DutColumn2token
			foreach my $DutColumn2token (values %nonmatchhash)
			{
				#And then, if the Dutch word ($DutColumn2token) contains: anything, followed by 'achtig', followed by 'e' or 'er' or 'ste' (optional), at the end of the string
				if ($DutColumn2token =~ /(.*)(achtig)(e|er|ste)?$/)
				{
					#print it to OutputNonIdenticalCognates.txt
					print ONIC "$AfrColumn1token\t$DutColumn2token\n";
				}
			}
		}
		else
		{	
			#else, print it to OutputNonCognates.txt
			print ONC "$AfrColumn1token\t$DutColumn2token\n";
		}
	}
}