# BilingualWorldList.txt (Les't call it FileA)

vriendelik	aardig
irriterend	vervelend
losieshuis	pension
eksamen	examen
goed	braaf
damwal	dam
water	water
rekenaar	computer
outoritêr	outoritaire
wêreld	wereld
alle	alle
word	worden
angesien	overwegende
erkenning	erkenning
afrigter	trainer

FalseFriendsList.txt (Let's call it FileB)

vriendelik	aardig
goed	braaf
damwal	dam
bruinmens	kleurling
kamera	fototoestel
jammer	sneu//spijten
japon	ochtendjas
losieshuis	pension
buffer	bumper
bruinmens	kleurling
brulpadda	brulkikker
jammerlik	zielig
buffer	bumper
irriterend	irritant//vervelend
kameelperd	giraf//giraffe

##</code><code>##

#FileA
irriterend	vervelend
#FileB
irriterend	irritant//vervelend
##</code><code>##

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

#open files
open (FALSEF, "<FalseFriendsList.txt");
open (BILWL, "<BilingualWordList.txt");

#declare hashes
my %falsef;
my %existingfalsefriend;

#while the FF input exists
while (<FALSEF>)
{
	#assign each line to $line
	my $line = $_;
	#chomp off the new line
	chomp $line;
	#increment $line
	$falsef{$line}++;
}

#declare variables
my $token;
my %hash;

#open output files
open (OUTPUT1, ">OutputFalseFriends.txt");
open (OUTPUT2, ">OutputUnsortedWordList.txt");

#while input is received
while (<BILWL>)
{
	#assign each line to $line
	my $line = $_;
	#chomp off the new line
	chomp $line;
	
	#assign $line to the array
	my @wordlist = split/\t/,$line;
	
	#a for-loop to 'clean up' the words, to get rid of all the commas, full stops, etc, except the apstrophes and hyphens
	for (my $x = 0; $x <= $#wordlist; $x++)
	{
		my $token = $wordlist[$x];
		
		if ($token =~ /(['\-\w]+)/)
		{
			#$word is now clean
			my $searchword = $1;
			
			#checks to see whether the word exists in the false friends list
			if (exists $hash{$searchword} || exists $falsef{$searchword})
			{
				$existingfalsefriend{$searchword}++;
				
			}	
			else
			{	
				#print to unsorted.txt
				print OUTPUT2 "$searchword\n";
			}
		}
	}
}

my $searchword;

foreach my $searchword(sort keys %existingfalsefriend)
{
	#sorts the matched words alphabetically
	my $value = $existingfalsefriend{$searchword};
	print OUTPUT1 "$searchword\t $value\n";
}

##</code><code>##

#OutputFalseFriends.txt
vriendelik	aardig
losieshuis	pension
goed	braaf
damwal	dam
irriterend	irritant//vervelend

#OutputUnsortedWorldList.txt
eksamen	examen
water	water
rekenaar	computer
outoritêr	outoritaire
wêreld	wereld
alle	alle
word	worden
angesien	overwegende
erkenning	erkenning
afrigter	trainer

##</code><code>##

goed
braaf
naak
bloot
damwal
dam
kombers
deken
homoseksueel
flikker
bronstig
geil
munisipaliteit
gemeente

##</code><code>##

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

#open FILE B
open (FALSEFRIENDINPUT, "<SNonCognatesAndFF.txt");

#declare hash
my %fileb;

#get a line from   #FILEB
while (my $line = <FALSEFRIENDINPUT>)
{
	#chomp off the new line
	chomp $line;
	
	# split the line on tab
	my ($filebkeys, $filebvalues) = split /\t/, $line;
	$fileb{$filebkeys} = $filebvalues;
	
		#open output files
		open (OUTPUT1, ">OutputMatchedFalseFriends.txt");
		open (OUTPUT2, ">OutputNonMatchedWords.txt");

		#open FILE A
		open (BILINGUALWL, "<BilingualWordList.1.0.0.IW.2012-06-20.txt");

		my %filea;	

		#get a line from   #FILEA
		while (my $line = <BILINGUALWL> )
		{
			chomp $line;
			#split the line on tab
			my ($fileakeys, $fileavalues) = split /\t/, $line;   
		
			#do first columns match?
			if ($fileb{$fileakeys})                         
			{
				#does the second column value contain the other as a substring?
				if ($fileb{$fileakeys} =~ /$fileavalues/ or $fileavalues =~ /$fileb{$fileakeys}/)
				{	
					#if yes, print it to OutputMatchedFalseFriends.txt
					print OUTPUT1 "$line\n";
					#loop to the next line
					next;                                 
				}
			}
			else
			{
				#if not, print it to OutputNonMatchedWords.txt
				print OUTPUT2 "$line\n";
			}
		}
}

##</code><code>##

#OutputMatchedFalseFriends.txt

damwal	dam
bitsig	vinnig
bot	been
dikwels	vaak
aantreklik	knap
bees	rund
baas	chef
bestuur	directie
alles	alles
afrigter	trainer

#OutputNonMatchedWords.txt (only a sample of a 73 line output)

vriendelik	aardig
polisieman	agent
net-net	amper
gedierte	beest
goed	braaf
naak	bloot
kombers	deken
homoseksueel	flikker
bronstig	geil
munisipaliteit	gemeente
menskop	hoofd
toedraai	inpakken
kiestand	kies
dierekop	kop

##</code><code>##

Can't open '>MatchedFalseFriends.txt' for writing: 'Invalid argument' at Script.ExtractionofCognates.1.0.5.2012.06.28.pl  line 25

#and
Can't open '>OutputNonMatchedWords.txt' for writing: 'Invalid argument' at Script.ExtractionofCognates.1.0.5.2012.06.28.pl  line 25