use strict;
use warnings;


my $wordData = bless {};
my $previousWord;

while (<DATA>) {
    chomp;
    my @parts = split;

    for my $part (@parts) {
        my ($word, $punct) = (lc $part) =~ /(\w+)(.*)/;

        $wordData->AddBigram ($word, $previousWord);
        if ($word) {
            $previousWord = $word;
        } elsif ($punct) {
            $previousWord = undef;
        }
    }
}

my $first  = 'the';
my $second = 'value';

if ($wordData->HaveBigram ($first, $second)) {
    print "Count for '$first' is ", $wordData->WordCount ($first), "\n";
}


sub AddBigram {
    my ($self, $word, $previousWord) = @_;

    if ($word) {
        $self->{$previousWord}{$word}++ if $previousWord;
        $self->{$word}{'!count'}++;
    }
}


sub HaveBigram {
    my ($self, $firstWord, $secondWord) = @_;

    return exists $self->{$firstWord} && exists $self->{$firstWord}{$secondWord};
}


sub WordCount {
    my ($self, $word) = @_;

    return 0 if ! exists $self->{$word};
    return $self->{$word}{'!count'};
}

__DATA__

##</code><code>##

Count for 'the' is 5