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
}

##</code><code>##

__DATA__
<strong>S1</strong>: Native-Speaker Status: Native speaker, American English; Academic Role: Senior Undergraduate; Gender: Male; Age: 17-23; Restriction: None<br>
<strong>S2</strong>: Native-Speaker Status: Native speaker, American English; Academic Role: Researcher; Gender: Male; Age: 31-50; Restriction: Cite<br>
<strong>S3</strong>: Native-Speaker Status: Native speaker, American English; Academic Role: Junior Undergraduate; Gender: Female; Age: 17-23; Restriction: None<br>
<strong>S4</strong>: Native-Speaker Status: Native speaker, American English; Academic Role: Senior Undergraduate; Gender: Female; Age: 17-23; Restriction: None<br>
<strong>S5</strong>: Native-Speaker Status: Native speaker, American English; Academic Role: Junior Undergraduate; Gender: Female; Age: 17-23; Restriction: None<br>
<strong>SS</strong>: Native-Speaker Status: Native speaker, American English; Academic Role: Unknown; Gender: Male; Age: Unknown; Restriction: None<br>

<p><b>S1: </b> it was presented to them by Chuck D and Public Enemy.  <font color="#ff6600"><b> [S2: </b> mhm  <b> ] </b></font> and the rest of th- Public Enemy and you know and and Chuck D's f- publicly gets up and says you know they were with us from the beginning and,  <font color="#ff6600"><b> [S2: </b> <font color="#3333ff"> mhm </font>  <b> ] </b></font> <font color="#3333ff"> all that </font> now wheth- whether or not you know that he was reading a TelePrompTer,  <font color="#ff6600"><b> [S2: </b> mhm  <b> ] </b></font> or or not i i think is uh </p>

 <p><b>S2: </b> or if he was trying to make nice because of the fact that Public Enemy hasn't sold records lately,  <font color="#ff6600"><b> [S1: </b> right  <b> ] </b></font> and he doesn't wanna look like some kinda old sourpuss </p>