| #!/usr/bin/env perl |
| use strict; |
| use warnings; |
| use utf8; |
| use Test::More skip_all => 'Not yet implemented'; |
| use Scalar::Util qw/weaken/; |
| use Data::Dumper; |
| |
| use_ok('KorAP::Document'); |
| |
| use File::Basename 'dirname'; |
| use File::Spec::Functions 'catdir'; |
| |
| my $path = catdir(dirname(__FILE__), 'corpus', 'doc', 'text'); |
| |
| ok(my $doc = KorAP::Document->new( |
| path => $path . '/' |
| ), 'Load Korap::Document'); |
| |
| like($doc->path, qr!$path/$!, 'Path'); |
| ok($doc->parse, 'Parse document'); |
| |
| ok($doc->primary->data, 'Primary data in existence'); |
| is($doc->primary->data_length, 129, 'Data length'); |
| |
| use_ok('KorAP::Tokenizer'); |
| |
| ok(my $tokens = KorAP::Tokenizer->new( |
| path => $doc->path, |
| doc => $doc, |
| foundry => 'OpenNLP', |
| layer => 'Tokens', |
| name => 'tokens' |
| ), 'New Tokenizer'); |
| |
| ok($tokens->parse, 'Parse'); |
| |
| ok($tokens->add('Mate', 'Dependency'), 'Add Structure'); |
| |
| # my $data = $tokens->to_data->{data}; |
| |
| done_testing; |
| |
| __END__ |
| |