use strict;
use warnings;
use Test::More tests => 2;

my %mycorpus = (
          a => "<p><time datetime=2017-09-04T05:23:39Z>04/09/17 06:23:39</time>
		  			Irrelevant text that may feature the word soft, softest, or softly.
ar##*whispers softly* don\'t##
##very soft##
##the softest even##
 — 164 notes",
		
			b => "p><time datetime=2017-09-30T18:20:56Z>30/09/17 19:20:56</time>
			Irrelevant text that may feature the word soft, softest, or softly.
4r##skam##
rr##isak valtersen##
rr##even bech næsheim##
dr##god##
r##they're so soft##
sr##my heart is bursting##
##This is the softest##
 — 379 notes
 			Irrelevant text that may feature the word soft, softest, or softly.",
			
			c => "<p><time datetime=2017-09-04T05:27:03Z>04/09/17 06:27:03</time>
##SKSNSKXBXKXND##
r##I LOVE THESE##
##such soft boyfriend™##
##you're my sunshine##
 — 180 notes
 Irrelevant text that may feature the word soft, softest, or softly."
);

my %counts;
foreach my $filename (sort keys %mycorpus) {
        my $date;
        my $hashtags = '';

        if ($mycorpus{$filename} =~ /(?<==)(\d{4}-\d{2}-\d{2})(?=T)/g){
            $date = $1;
        }

        if ($mycorpus{$filename} =~ /[#][#](.*)[#][#]/g){
            $hashtags = $1;
        }

         if (my $matches =()= $hashtags =~ /\bsoft/gi){
             $counts{$date} += $matches;
         }
}


is ($counts{'2017-09-04'}, 4, "2017-09-04 tally correct");
is ($counts{'2017-09-30'}, 2, "2017-09-30 tally correct");