#!/usr/bin/perl
use strict;
use warnings;
use Data::Dumper qw(Dumper);
use re::engine::RE2;
use List::MoreUtils qw(uniq);
use Sort::Naturally;


#This program reads abstract sentence file and produces output with the following format:
#

if ($#ARGV != 1) {
	print "usage: program arguments\n";
}

my $inputfile1=$ARGV[0];
my $outputfile = $ARGV[1];
my %hashunique=();

open(RF, "$inputfile1") or die "Can't open < $inputfile1: $!";
open(WF, ">$outputfile"); #open for output

$/ = ''; #this sets the delimiter for an empty line
while (<RF>) {
	my @one = split /\n/ , $_;

	my ( $indexofdashinarray ) = grep { $one[$_] =~ /\-\-/ } 0..$#one;

	for (my $i=0;$i<=$#one;$i++) {
		next if $i==0;
		next if $one[$i] =~ /^\-\-$/;
		
		while ($one[$i] =~ m/(\b)D\*(.*?)\*(.*?)\*D(\b)/g) {
			unless ($hashunique{"D$2"}) {
				$hashunique{"D$2"}="$3";
			}
			else {
				$hashunique{"D$2"}=$hashunique{"D$2"}.'|'."$3";
			}
		} 
	}
}

foreach my $i (nsort keys %hashunique) {
	$hashunique{$i} = join ( "\|", uniq split /\|/ , $hashunique{$i});
	print WF "$i=>$hashunique{$i}\n";
}
close (RF);
close (WF);