#!/usr/bin/perl

# turn on perl safety features
        use strict;
        use warnings;

#initialize modules
	use XML::Twig;
	use DirHandle;
	
	my ($dir, $filepath, @filename, @filepath_list, %company_hist, @company_list, %reference_hist, @reference_list);
		
$dir = $ARGV[0] or die "Must specify directory";
         
@filepath_list = get_file_list($dir);

foreach $filepath (@filepath_list) 
{
	my $twig = XML::Twig -> new(
		twig_roots => { 'article/reference' => \&get_ref,
				company => \&get_code 
		});

$company_hist{$_}++ for @company_list;			#sort results from
my @unique_comp = keys %company_hist;			#"get_code" sub then
@company_list = ( sort { $company_hist{$b} <=>		#return 3 most freq
	$company_hist{$a} } @unique_comp )[0..2];	#codes.
          	
#my $ref_length = scalar( @reference_list );		#take ref list and
$reference_hist{$_}++ for @reference_list;		#eliminate duplicates
my @unique_ref = keys %reference_hist;			#return a tally
my $uni_count = scalar ( @unique_ref );
my @by_date_tally = get_date(\@unique_ref);
my $dup_count = (scalar( @reference_list ) - $uni_count);
#my($k, $v);
#while ( ($k,$v) = each %reference_hist ) {
#print "$k => $v\n";
#}


#print "File name: ", print_file_name($filepath), "\n";		
#print "Total Dupicate Articles: $dup_count\n";	
#print "Total Articles Found: $uni_count\n";
		
		
 		
#print "@company_list\n";
undef %company_hist;					#reinitialize global
undef @company_list;					#vars.
undef %reference_hist;					#
undef @reference_list;					#

$twig->parsefile($filepath);				# purge to save mem.
$twig->purge;                  
} 							#end of foreach loop
 

exit(0);

sub get_file_list
{
        $dir = shift;
        print $dir, "\n";
        my $dh = DirHandle->new($dir) or die "can't open directory";
        return sort                      # sort pathnames
                grep {    -f     }       # choose only files
                map  { "$dir/$_" }       # create full paths
                grep {  !/^\./   }       # filter out dot files
                $dh->read();             # read all filenames
}

sub print_file_name
{
	my($path, $position, $path_strip);		#take filepath and
		$path = $_[0];				#return filename.
		$position = rindex($path,"/") + 1;	#
		$path_strip = substr($path, $position);
		#print "For file: $path_strip\n";
	
		return $path_strip;
}


sub get_code
{

	my $company;					#get company code
	my( $twig, $elt)= @_;				#attribute and
        $company = $elt->{'att'}->{'code'};		#put into array
	push @company_list, $company;  
	#return @company_list;

}


sub get_ref
{

	my( $twig, $elt)= @_;				#take reference elt
	my $ref = $elt;					#and return just the
	my $position = rindex($ref->text(), "/") + 1;	#reference ID string
	my $ref_strip = substr($ref->text(), $position);	
	push @reference_list, $ref_strip;
}

sub get_date
{
	my $ref;
	#my @refs = @_;
	foreach $ref (@_) {
	print @$ref, "\t";
	}
	print "\n\n";
	
	
}


##</code><code>##

<article>
          <accessionno>MTPW000020090731e57v004mr</accessionno>
          <reference>distdoc:archive/ArchiveDoc::Article/MTPW000020090731e57v004mr</reference>
          <baselanguage>EN</baselanguage>
          <copyright>(c) 2009 M2 Communications, Ltd. All Rights Reserved.   </copyright>
          <headline>
            <paragraph display="Proportional" truncation="None" lang="EN">Anadys Pharmaceuticals, Inc (NASDAQ:ANDS) is the Highest Percentage Gainers Among NASDAQ Stocks During Morning Trading Hours; Microsoft Corporation (NASDAQ:<hlt>MSFT</hlt>) And Orthofix International NV (NASDAQ:OFIX) Round Out Top Three Percentage Gainers During Morning Trading Hours</paragraph>
          </headline>
          <publicationdate>
            <date>2009-07-31</date>
          </publicationdate>
          <sourcename>M2 Presswire</sourcename>
          <company code="oficks">
            <name>Orthofix International N.V.</name>
            <newsmentions>0</newsmentions>
            <newshits>0</newshits>
          </company>
          <company code="scrptg">
            <name>Anadys Pharmaceuticals Inc</name>
            <newsmentions>0</newsmentions>
            <newshits>0</newshits>
          </company>
          <company code="mcrost">
            <name>Microsoft Corporation</name>
            <newsmentions>0</newsmentions>
            <newshits>0</newshits>
          </company>
          <industry code="i3302">
            <name>Computers/Electronics</name>
          </industry>
          <industry code="i3302021">
            <name>Applications Software</name>
          </industry>
          <industry code="i257">
            <name>Pharmaceuticals</name>
          </industry>
          <industry code="i330202">
            <name>Software</name>
          </industry>
          <industry code="icomp">
            <name>Computing</name>
          </industry>
          <industry code="i3302020">
            <name>Systems Software</name>
          </industry>
          <industry code="i372">
            <name>Medical Equipment/Supplies</name>
          </industry>
          <industry code="i951">
            <name>Health Care</name>
          </industry>
          <industry code="iphmed">
            <name>Medical/Surgical Instruments/Apparatus/Devices</name>
          </industry>
          <region code="usa">
            <name>United States</name>
          </region>
          <region code="namz">
            <name>North American Countries/Regions</name>
          </region>
          <newssubject code="c42" position="0">
            <name>Labor/Personnel Issues</name>
          </newssubject>
          <newssubject code="ghepat" position="0">
            <name>Hepatitis</name>
          </newssubject>
          <newssubject code="mstock" position="0">
            <name>Stock Exchanges</name>
          </newssubject>
          <newssubject code="npress" position="0">
            <name>Press Release</name>
          </newssubject>
          <newssubject code="ccat" position="0">
            <name>Corporate/Industrial News</name>
          </newssubject>
          <newssubject code="gcat" position="0">
            <name>Political/General News</name>
          </newssubject>
          <newssubject code="ghea" position="0">
            <name>Health</name>
          </newssubject>
          <newssubject code="gmed" position="0">
            <name>Medical Conditions</name>
          </newssubject>
          <newssubject code="m11" position="0">
            <name>Equity Markets</name>
          </newssubject>
          <newssubject code="mcat" position="0">
            <name>Commodity/Financial Market News</name>
          </newssubject>
          <newssubject code="ncat" position="0">
            <name>Content Types</name>
          </newssubject>
          <newssubject code="nfact" position="0">
            <name>Factiva Filters</name>
          </newssubject>
          <newssubject code="nfce" position="0">
            <name>FC&amp;E Exclusion Filter</name>
          </newssubject>
          <newssubject code="nfcpin" position="0">
            <name>FC&amp;E Industry News Filter</name>
          </newssubject>
          <sourcecode>MTPW</sourcecode>
          <tailparagraphs>
            
          </tailparagraphs>
          <contact>Liquid Tycoon
 | e-mail: info@LiquidTycoon.com
 | Tel: +1 214 556 6798   </contact>
          <logo source="http://logos.factiva.com.ezproxy.insead.edu" image="mtpwLogo.gif"></logo>
          <wordcount>679</wordcount>
        </article>