use XML::TreeBuilder;


my $file= 'swbd_50k_42tags.xml';
my $tree = XML::TreeBuilder->new();

$tree->parse_file($file);




foreach my $dialogue ($tree->find_by_tag_name ('dialogue')){
		
        
        $dialogue_name = $dialogue->attr_get_i('name');
        
        
	foreach my $turn ($dialogue->find_by_tag_name('turn')){
		
		$turn_no = $turn->attr_get_i('no');
		$turn_speaker = $turn->attr_get_i('speaker');	
		@speaker = ( ++$turn_no, $turn_speaker );

	foreach my $utt ($dialogue->find_by_tag_name('utt')){
		
		$da = $utt->attr_get_i('da');
	#	$id = $utt->attr_get_i('id');




	@statement = ('sb','sb');		#array of classified DA
	@Question = ( 'qy', 'qw', 'qy\^d' );	#array of classified DA
	@Acknowledge = ( 'b', 'bh', 'bk');	#array of classified DA
	@Answer = ( 'nn', 'ny');			#array of classified DA
	@Agreement = ('aa');			#array of classified DA

	


	if ($da eq "$statement[0]" or $da eq "$statement[1]") { 	# checking for DA class of utterance
		$da = Astatement;

	}	   elsif ($da eq "$Question[0]" or $da eq "$Question[1]" or $da eq "$Question[2]")	{ # checking for DA class of utterance
		   $da = Question;

	}	   elsif ($da eq "$Acknowledge[0]" or $da eq "$Acknowledge[1]" or $da eq "$Acknowledge[2]") { # checking for DA class of utterance
		   $da = Acknowledgement;

	}	   elsif ($da eq "$Answer[0]" or $da eq "$Answer[1]") {   # checking for DA class of utterance
		   $da = Answer;

	}          elsif ($da eq "$Agreement[0]")   {			# checking for DA class of utterance
		
		   $da = Agreement;
 	} 
	
	
		$line = $utt->as_text;
		
		@line = split(/\s+ /, $line);
		
		$gram = substr($line, 0, 3);		#split utterance into n-grams of 1-4

	

	if ( $gram =~ /(I think|I believe|It seems|It\'s my opinion that|I mean|Suppose|Of course|we|they|they say)/gi {
		
		$gram = $myda;
		$myda = Dstatement;
		
		

	}	elsif ( $gram =~ /(Do you|Do you have|Do you know|Is that|Have you|what|who\'s your|Does he|Does she|Are they|did you|how about|what|isn\'t|wasn\'t it|hasn\'t it|how)/gi {

		$gram = $myda;
		$myda = DQuestion;

	}	elsif ( $gram =~ /(exactly|definitely|yes|that\'s a fact|that\'s true|true)/gi	{
		
		$gram = $myda;
	        $myda = DAgreement;

	}	elsif ( $gram =~ /(\{F oh \} really|Really|Is that right\?|\{F oh\} yeah|Is it|\{F oh\} do you|No \?|Did you|\{F oh} are you\?|was it|Have you\?|\{F oh} is it \?|\{F oh} do you|uh\-huh yeah right|oh yes|oh yeah|huh|sure|um|huh-huhokay|\{F oh} okay|oh|\{F oh}|i see|uh\-huh|all right|yeah|)/gi {
			
			
		
		$gram = $myda;
		$myda = DAcknowledgement;


	}	else ( $gram =~ /(yes|yeah|yep|uh\-huh|yes actually|i do|no|um no|nope|uh actually no|probably not|but uh no)/gi {

		$gram = $myda;
		$myda = DAnswer;

	}

		@u = ( ++$turn_no, \[$line\] );
		@da = (++$turn_no, '$da' ) ;
		@myda = (++$turn_no, $da, $myda) 
	
	
		print 'speaker (@speaker)\n'; # reqd format
		print 'u (@u)\n';	# reqd format
		print 'da (@da)\n';	#reqd format
		print 'da (@myda)\n';	#reqd format


		}

	}
}