view release on metacpan or  search on metacpan

lib/AI/Categorizer/Document.pm  view on Meta::CPAN

			 default => "stem",
			},
  );

__PACKAGE__->contained_objects
  (
   features => { delayed => 1,
		 class => 'AI::Categorizer::FeatureVector' },
  );

### Constructors

my $NAME = 'a';

sub new {
  my $pkg = shift;
  my $self = $pkg->SUPER::new(name => $NAME++,  # Use a default name
			      @_);

  # Get efficient internal data structures
  $self->{categories} = new AI::Categorizer::ObjectSet( @{$self->{categories}} );

  $self->_fix_stopwords;
  
  # A few different ways for the caller to initialize the content
  if (exists $self->{parse}) {
    $self->parse(content => delete $self->{parse});
    
  } elsif (exists $self->{parse_handle}) {
    $self->parse_handle(handle => delete $self->{parse_handle});
    
  } elsif (defined $self->{content}) {
    # Allow a simple string as the content
    $self->{content} = { body => $self->{content} } unless ref $self->{content};
  }
  
  $self->finish if $self->{content};
  return $self;
}

sub _fix_stopwords {
  my $self = shift;
  
  # Convert to hash
  $self->{stopwords} = { map {($_ => 1)} @{ $self->{stopwords} } }
    if UNIVERSAL::isa($self->{stopwords}, 'ARRAY');
  
  my $s = $self->{stopwords};

  # May need to perform stemming on the stopwords
  return unless keys %$s; # No point in doing anything if there are no stopwords
  return unless $self->{stopword_behavior} eq 'stem';
  return if !defined($self->{stemming}) or $self->{stemming} eq 'none';
  return if $s->{___stemmed};
  
  my @keys = keys %$s;
  %$s = ();
  $self->stem_words(\@keys);
  $s->{$_} = 1 foreach @keys;
  
  # This flag is attached to the stopword structure itself so that
  # other documents will notice it.
  $s->{___stemmed} = 1;
}

sub finish {
  my $self = shift;
  $self->create_feature_vector;
  
  # Now we're done with all the content stuff
  delete @{$self}{'content', 'content_weights', 'stopwords', 'use_features'};
}


# Parse a document format - a virtual method
sub parse;

sub parse_handle {
  my ($self, %args) = @_;
  my $fh = $args{handle} or die "No 'handle' argument given to parse_handle()";
  return $self->parse( content => join '', <$fh> );
}

### Accessors

sub name { $_[0]->{name} }
sub stopword_behavior { $_[0]->{stopword_behavior} }

sub features {
  my $self = shift;
  if (@_) {
    $self->{features} = shift;
  }
  return $self->{features};
}

sub categories {
  my $c = $_[0]->{categories};
  return wantarray ? $c->members : $c->size;
}


### Workers

sub create_feature_vector {
  my $self = shift;
  my $content = $self->{content};
  my $weights = $self->{content_weights};

  die "'stopword_behavior' must be one of 'stem', 'no_stem', or 'pre_stemmed'"
    unless $self->{stopword_behavior} =~ /^stem|no_stem|pre_stemmed$/;

  $self->{features} = $self->create_delayed_object('features');
  while (my ($name, $data) = each %$content) {
    my $t = $self->tokenize($data);
    $t = $self->_filter_tokens($t) if $self->{stopword_behavior} eq 'no_stem';
    $self->stem_words($t);
    $t = $self->_filter_tokens($t) if $self->{stopword_behavior} =~ /^stem|pre_stemmed$/;
    my $h = $self->vectorize(tokens => $t, weight => exists($weights->{$name}) ? $weights->{$name} : 1 );
    $self->{features}->add($h);
  }