use strict;
use warnings;
my %mycorpus = (
    a => "date:#20180101# comment:#d1 d2 d3 d4 d5 d6#",
    b => "date:#20180101# comment:#b1 b2 b3 b4 b5 b6 b7# comment:#c1 c2 c3 c4 c5 c6#",
    c => "date:#20180101# comment:#d1 d2 d3 d4 d5 d6#",
);

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

    while ( $mycorpus{$filename} =~ /date:#(\d+)#/g ) {
        $date = $1;
    }

    while ( $mycorpus{$filename} =~ /comment:#(.*?)#/g ) {
        $dataset .= "$1    ";

    }
	
    while ( $dataset =~ m/(\w+) \s (?= (\w+) \s (\w+) \s (\w+) \s (\w+) )/gx ) {
        $word = "$1 $2 $3 $4 $5";

        $counts{$date}{$word}++;
    }
}

use Data::Dumper;
print Dumper \%counts;

##</code><code>##

$VAR1 = {
          '20180101' => {
                          'c1 c2 c3 c4 c5' => 1,
                          'b1 b2 b3 b4 b5' => 1,
                          'b3 b4 b5 b6 b7' => 1,
                          'b2 b3 b4 b5 b6' => 1,
                          'd2 d3 d4 d5 d6' => 2,
                          'd1 d2 d3 d4 d5' => 2,
                          'c2 c3 c4 c5 c6' => 1
                        }
        };