#!/usr/bin/perl
use strict;
use utf8;
use warnings;
use Data::Dumper;

open ENGLISH, "corpus.e" or die $!;
open FOREIGN, "corpus.f" or die $!;
my @sents_en; my @sents_f;
while (<ENGLISH>){
 chomp;
 push @sents_en, $_;
}
while (<FOREIGN>){
 chomp;
 push @sents_f, $_;
}

my %uniform;
my $k;#index of english/foreign sentence
for ($k = 0; $k <= $#sents_en; $k++){
   my @words_en; my @words_f;
   @words_en = map { split / / } $sents_en[$k];
   @words_f = map { split / / } $sents_f[$k];
   my $j;
   for ($j = 0; $j <= $#words_en; $j++ ){
    my $i;
    my %seen;
       for ($i = 0; $i <= $#words_f; $i++){
                #$seen{$words_f[$i]}++; #TRY TO COUNT UNIQUE WORDS
                if ( defined( $uniform{ $words_en[$j] } ) ) { # and !$seen{$words_f[$i]}) ) {

                    $uniform{ $words_en[$j] } ++;
                }
                else {
                    $uniform{ $words_en[$j]} = 1;
                }

       }
    }
}  
print Dumper \%uniform;