use 5.12.0;
use File::Slurp;
use File::Find ; 
use Cwd ; 

my %location;

open LOG, ">log/log.log" or die;

open(IN, "/Users/Henry/Documents/WACS/Tips_and_Hacks/MAST_tW_PDF_Updater/FilesForUpdates/Temp/ULB_text.txt") or die "$!";

say "Reading ULB";

while (<IN>) {
	#print LOG "$_";
	chomp;
	while (s/^([^\n\t]*)\t([^\n]*?)([A-Z][a-z]+(-[A-Z][a-z]+)?)/$1\t$2/) {
	#	say LOG $3;
		unless (exists $location{$3}) {$location{$3} = $1}
	}
	
}

close IN;

say "Outputting hash";

open(OUT, ">out/results.txt") or die "$!";

foreach my $word (sort keys %location) {
	say OUT "$word, $location{$word}";
}

close OUT;

say "Deleting common words";

my $fileText = read_file("/Users/Henry/Documents/WACS/Tips_and_Hacks/MAST_tW_PDF_Updater/FilesForUpdates/Temp/ULB_text.txt", binmode => 'utf8');

foreach my $word (sort keys %location) {
	my $temp = lc $word;
	#say LOG $word . "\t" . $temp;
	if ($fileText =~ /\b$temp\b/) {
		delete $location{$word}
	}
}

say "Outputting final product";

open(OUT, ">out/results.txt") or die "$!";

foreach my $word (sort keys %location) {
	say OUT "$word, $location{$word}";
}

close OUT;


close LOG;