#!/usr/bin/perl -w

use strict;

my(%scraped,%inboth);

for (<cmpages/*/*.html>) {
	next if /tmp/;
	my $mod = -M;
	s/cmpages\/(.*?)\..*/$1/;
	$scraped{$_} = $mod;
}

my (%xmlolder, %xmlonly, %htmlonly);

for (<scrapedxml/*/*.xml>) {
	next if /divisionsonly/;
	my $mod = -M;
	s/scrapedxml\/(.*?)\/([a-z]+)(.*?)\..*/$1\/$2$3/;
	my $cat = $1; my $date = $3;
	if ($scraped{$_}) {
		if ($mod>$scraped{$_}) {
			push @{$xmlolder{$cat}}, $date;
		}
		$inboth{$_} = 1;
	} else {
		push @{$xmlonly{$cat}}, $date;
	}
}

foreach (sort keys %scraped) {
	/^(.*?)\/([a-z]+)(.*)$/;
	my $cat = $1; my $date = $3;
	if (!$inboth{$_}) {
		push @{$htmlonly{$cat}}, $date;
	}
}

display('XML older than HTML', %xmlolder) if (%xmlolder);
display('Only in XML', %xmlonly) if (%xmlonly);
display('Only in HTML', %htmlonly) if (%htmlonly);

sub display {
	my($title,%hash) = @_;
	print "$title\n" . '~' x length($title) . "\n";
	foreach (keys %hash) {
		print "$_ : " . join(', ', @{$hash{$_}}) . "\n";
	}
	print "\n";
}