use strict;
use warnings;
use HTML::TreeBuilder;

my @goodWordsList = (
    "mhm", "right", "well", "yeah", "sure", "good", "ah", "okay", "yep", "hm",
    "definitely", "alright", "'m'm", "oh", "my", "god", "wow", "uhuh", "exactly",
    "yup", "mkay", "i see", "ooh", "cool", "uh", "fine", "true", "hm'm", "hmm",
    "yes", "absolutely", "great", "um", "so", "mm", "weird", "ye-", "i mean",
    "i know", "i think so", "huh", "yay", "maybe", "eh", "obviously", "correct",
    "awesome", "really", "interesting",
);
my %goodwords;

@goodwords{@goodWordsList} = (1) x @goodWordsList;

my $root = HTML::TreeBuilder->new ();

$root->parse_file (*DATA);

my %speakers;

# Parse out speaker attributes
for ($root->look_down ('_tag', 'strong')) {
    my $info = $_->right ();
    my $name = $_->as_text ();
    
    $speakers{$name}{info} = $info;
    for my $param (split /\s*(?:;\s*|$)/, $info) {
        my ($key, $value) =  $param =~ /^:?\s*([^:]*):\s*(.*)/;
        
        $speakers{$name}{$key} = $value;
    }
}

my %stats;

# Do the analysis
for ($root->look_down ('_tag', 'p')) {
    my $line = $_->as_text ();;
    my ($name) = $line =~ /(\w+):/;
    
    # Preform analysis on paragraph here
}