in reply to Re^3: Installing Lingua BrillTagger
in thread Installing Lingua BrillTagger

Thanks. So using Lingua::EN::Tagger code below I can get the output of a file all tagged. But I still can't work out how just to display the tags.

Looking at the .pm file I cannot see an obvious way for it to output, say, <NN> : 2, <CC> : 5 and so on. I can only see subs to add_tag to text, not just to display them.

#!/usr/bin/env perl
use Lingua::EN::Tagger 
qw(add_tags);
my $postagger = new Lingua::EN::Tagger;

my $file = "test.txt";
my $text = do {
    local $/ = undef;
    open my $fh, "<", $file
        or die "could not open $file: $!";
    <$fh>;
};    


    my $tagged = $postagger->add_tags($text);

    print $tagged, "\n";

[download]

Replies are listed 'Best First'.
Re^5: Installing Lingua BrillTagger ( sub Lingua::EN::Tagger::get_tag_counts )
by Anonymous Monk on Jan 21, 2014 at 02:37 UTC

    Here you go 

    #!/usr/bin/perl --
## perltidy -olq  -csc -csci=10 -cscl="sub : BEGIN END if " -otr -opr 
+-ce -nibc -i=4 -pt=0   "-nsak=*"
use strict; use warnings; use Data::Dump qw/ dd /;
use Lingua::EN::Tagger ;

Main( @ARGV );
exit( 0 );

sub Main {
    my $text = q{
If that is a question, can you show small code sample,
complete with small input
and word description of what counts you expect?
Now <brackets> here :/
};

    my $postagger = Lingua::EN::Tagger->new;
    my $tagged    = $postagger->add_tags($text);
#~     dd( $postagger, $tagged );
#~     dd ( map { [ $_, $postagger->$_( $text ) ] } qw{ get_words get_
+readable get_sentences } );
#~     dd ( map { [ $_, $postagger->$_( $tagged ) ] } qw{ get_proper_n
+ouns get_nouns get_max_noun_phrases get_noun_phrases  } );
    
    dd( scalar $postagger->get_tag_counts( $tagged ) );
} ## end sub Main


sub Lingua::EN::Tagger::get_tag_counts {
#~     my( $self, $tagged ) = @_;
    my %counts;
    $counts{$1}++ while $_[1] =~ m{<([^>/]+)>}g;
    return wantarray ? %counts : \%counts;
}
__END__
{
  cc  => 1,
  det => 2,
  in  => 3,
  jj  => 3,
  md  => 1,
  nn  => 6,
  pp  => 1,
  ppc => 2,
  prp => 2,
  rb  => 2,
  sym => 1,
  vbp => 2,
  vbz => 2,
  wp  => 1,
}

    [download]
[reply]
[d/l]
      Thank you!
[reply]

In Section Seekers of Perl Wisdom