File Coverage

blib/lib/HTML/WordTagRatio/Ratio.pm

Criterion	Covered	Total	%
statement	12	31	38.7
branch	0	2	0.0
condition	0	3	0.0
subroutine	4	6	66.6
pod	2	2	100.0
total	18	44	40.9

=head1 NAME

HTML::WordTagRatio::Ratio - Default module for determining the ratio of words to tags in a range of tokens in an HTML document.

=head1 SYNOPSIS

  use HTML::WordTagRatio::Ratio;
  use HTML::Content::HTMLTokenizer;
  use HTML::Content::ContentExtractor;

  my $tokenizer = new HTML::Content::HTMLTokenizer('TAG','WORD');

  open(HTML,"index.html");
  my $doc = join("",);
  close(HTML);

  my ($word_count_arr_ref,$tag_count_arr_ref,$token_type_arr_ref,$token_hash_ref) = $tokenizer->Tokenize($doc);

  my $ratio = new HTML::WordTagRatio::Ratio();

  my $value = $ratio->RangeValue(0, @$word_count_arr_ref,
  				$word_count_arr_ref, $tag_count_arr_ref);

=head1 DESCRIPTION

HTML::WordTagRatio::Ratio and derived classes compute a ratio of Words to Tags for a given range.  Ratio is the base class and merely returns the number of word tokens in the range.

=head2 Methods

=over 4

=item * my $ratio = new HTML::WordTagRatio::Ratio()

Initializes HTML::WordTagRatio::Ratio

=item * my $value = $ratio->RangeValue($start, $end, \@WordCount, \@TagCount)

Returns the number of word tokens in ($start,$end].  $WordCount[$i] is the number of word tokens before or at the ith token in the input HTML document. $TagCount[$i] is the number of tag tokens before or at the ith token in the input HTML document.

=back

=head1 AUTHOR

Jean Tavernier ([e-mail])

=head1 COPYRIGHT

Copyright 2005 Jean Tavernier.  All rights reserved.

This library is free software; you can redistribute it and/or
modify it under the same terms as Perl itself.

=head1 SEE ALSO

ContentExtractorDriver.pl (1), HTML::Content::ContentExtractor (3), HTML::Content::HTMLTokenizer (3), HTML::WordTagRatio::WeightedRatio (3), HTML::WordTagRatio::SmoothedRatio (3), HTML::WordTagRatio::RelativeRatio (3), HTML::WordTagRatio::ExponentialRatio (3), HTML::WordTagRatio::NormalizedRatio (3).

=cut
package HTML::WordTagRatio::Ratio;
use strict;
use warnings;
use Carp;

use fields qw(Exists);

# new - constructs Ratio object
# - preconditions: 	none
# - postconditions: 	Ratio is constructed
sub new
{
	my $invocant = shift;
    	my $class   = ref($invocant) || $invocant;

    	my $self = fields::new($invocant);
    	$self->{Exists} = 1;
    	return bless($self, $class);
}
# RangeValue - returns value of a range of tokens
# - preconditions: 	1st arg is an integer >= 0 and < length of @{3rd argument}
#			2nd arg is an integer > 1st arg and < length of @{3rd argument}
#			3rd arg is an array ref which points to an array of monotonically
#				increasing integers, indicating the number of words found
#				in the HTML document before or at the i_th token (i being an
#				index into the array)
#			4th arg is an array ref which points to an array of monotonically
#				increasing integers, indicating the number of tags found
#				in the HTML document before or at the i_th token (i being an
#				index into the array)
# - postconditions: 	floating point value returned indicating the value of the range
sub RangeValue
{
	my $self = shift;
	my $i = shift;
	my $j = shift;
	my $tN = shift;
	my $tT = shift;
	my @N = @{$tN};
	my @T = @{$tT};

	if ($j <= $i)
	{
		return -1;
	}
	my $NinRange = $N[$j] - $N[$i];
	my $TinRange = $T[$j] - $T[$i];
	return $NinRange;
}
1;