use strict;

my %goodwords = ("mhm" => 1,		"right" => 1,		"well" => 1,
		"yeah" => 1,		"sure" => 1,		"good" => 1,
		"ah" => 1,		"okay" => 1,		"yep" => 1,
		"hm" => 1,		"definitely" => 1,		"alright" => 1,
		"'m'm" => 1,		"oh" => 1,		"my" => 1,
		"god" => 1,		"wow" => 1,		"uhuh" => 1,
		"exactly" => 1,		"yup" => 1,		"mkay" => 1,
		"i see" => 1,		"ooh" => 1,		"cool" => 1,
		"uh" => 1,		"fine" => 1,		"true" => 1,
		"hm'm" => 1,		"hmm" => 1,		"yes" => 1,
		"absolutely" => 1,		"great" => 1,		"um" => 1,
		"so" => 1,		"mm" => 1,		"weird" => 1,
		"ye-" => 1,		"i mean" => 1,		"i know" => 1,
		"i think so" => 1,		"huh" => 1,		"yay" => 1,
		"maybe" => 1,		"eh" => 1,		"obviously" => 1,
		"correct" => 1,		"awesome" => 1,		"really" => 1,
		"interesting" => 1,);


my(%speaker_record); # store the info in this hash in an array ref
my $gender = 0; # array number for gender
my $matched_words = 1; # array number for matched words count
my $unmatched_words = 2; # array number for unmatched words count
while(<DATA>){
  if(/<strong>(S[\w\-]+)<\/strong>:.*Gender:\s+(Male|Female)/i){
		$speaker_record{$1}->[$gender]=$2;
    $speaker_record{$1}->[$matched_words]=0;
    $speaker_record{$1}->[$unmatched_words]=0;
  }
  else{
    # hopefully, a chunk contains just the stuff attributed to one speaker (split on <b>)
    my @chunks = split /<b>/, $_;
    foreach my $chunk(@chunks){
      if($chunk =~ /(\w+?):/){ # who is the speaker of this chunk?
        my $speaker = $1;
        # get rid of stuff we don't want to count
        $chunk =~ s/<.*?>//g; # html tags and content
        $chunk =~ s/\[|\]//g; # '[' and ']'
        $chunk =~ s/(\w+?)://g; # the speaker
        my @words = split /\s+/, $chunk; # break the chunk up into words
        foreach my $word(@words){
          #non-blank 'word' and valid speaker
          if($word !~ /^\s*$/ and exists $speaker_record{$speaker}){
            # a matched goodword
            if(exists $goodwords{$word}){
              $speaker_record{$speaker}->[$matched_words] ++;
            }
            # an unmatched word
            else{
              $speaker_record{$speaker}->[$unmatched_words] ++;
            }
          }
        }
      }
    }
  }
}
foreach(keys %speaker_record){
  print "Speaker: $_, Gender: $speaker_record{$_}->[$gender], ";
  print "Matched words: $speaker_record{$_}->[$matched_words], ";
  print "Unmatched words: $speaker_record{$_}->[$unmatched_words]\n";
}

__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>