Akron | 88d063a | 2022-03-21 15:10:01 +0100 | [diff] [blame^] | 1 | use strict; |
| 2 | use warnings; |
| 3 | use Test::More; |
| 4 | use Data::Dumper; |
| 5 | use JSON::XS; |
| 6 | |
| 7 | if ($ENV{SKIP_REAL}) { |
| 8 | plan skip_all => 'Skip real tests'; |
| 9 | }; |
| 10 | |
| 11 | use utf8; |
| 12 | use lib 'lib', '../lib'; |
| 13 | |
| 14 | use File::Basename 'dirname'; |
| 15 | use File::Spec::Functions 'catdir'; |
| 16 | |
| 17 | use_ok('KorAP::XML::Krill'); |
| 18 | |
| 19 | my $path = catdir(dirname(__FILE__), 'corpus','NKJP','NKJP','KOT'); |
| 20 | |
| 21 | ok(my $doc = KorAP::XML::Krill->new( path => $path . '/' ), 'Load Korap::Document'); |
| 22 | ok($doc->parse, 'Parse document'); |
| 23 | |
| 24 | is($doc->text_sigle, 'NKJP/NKJP/KOT', 'Correct text sigle'); |
| 25 | is($doc->doc_sigle, 'NKJP/NKJP', 'Correct document sigle'); |
| 26 | is($doc->corpus_sigle, 'NKJP', 'Correct corpus sigle'); |
| 27 | |
| 28 | my $meta = $doc->meta; |
| 29 | |
| 30 | is($meta->{T_title}, 'TEI P5 encoded version of sample(s) of "Kot"', 'Title'); |
| 31 | ok(!$meta->{T_sub_title}, 'SubTitle'); |
| 32 | ok(!$meta->{T_author}, 'Author'); |
| 33 | ok(!$meta->{A_editor}, 'Editor'); |
| 34 | ok(!$meta->{S_pub_place}, 'PubPlace'); |
| 35 | ok(!$meta->{A_publisher}, 'Publisher'); |
| 36 | |
| 37 | ok(!$meta->{S_text_type}, 'No Text Type'); |
| 38 | ok(!$meta->{S_text_type_art}, 'No Text Type Art'); |
| 39 | ok(!$meta->{S_text_type_ref}, 'No Text Type Ref'); |
| 40 | ok(!$meta->{S_text_domain}, 'No Text Domain'); |
| 41 | ok(!$meta->{S_text_column}, 'No Text Column'); |
| 42 | |
| 43 | |
| 44 | # Tokenization |
| 45 | use_ok('KorAP::XML::Tokenizer'); |
| 46 | |
| 47 | my ($token_base_foundry, $token_base_layer) = (qw/nkjp Morpho/); |
| 48 | |
| 49 | # Get tokenization |
| 50 | my $tokens = KorAP::XML::Tokenizer->new( |
| 51 | path => $doc->path, |
| 52 | doc => $doc, |
| 53 | foundry => $token_base_foundry, |
| 54 | layer => $token_base_layer, |
| 55 | name => 'tokens' |
| 56 | ); |
| 57 | ok($tokens, 'Token Object is fine'); |
| 58 | ok($tokens->parse, 'Token parsing is fine'); |
| 59 | |
| 60 | my $output = decode_json( $tokens->to_json ); |
| 61 | |
| 62 | is($output->{data}->{stream}->[0]->[0], '-:tokens$<i>43', 't'); |
| 63 | is($output->{data}->{stream}->[0]->[3], 'i:nie', 't'); |
| 64 | is($output->{data}->{stream}->[1]->[2], 's:zdążyła', 't'); |
| 65 | |
| 66 | ## Base |
| 67 | ok($tokens->add('DeReKo', 'Structure', 'base_sentences_paragraphs')); |
| 68 | ok($tokens->add('NKJP', 'Morpho'), 'Add Gingko'); |
| 69 | |
| 70 | $output = $tokens->to_data; |
| 71 | |
| 72 | is($output->{data}->{foundries}, 'dereko dereko/structure dereko/structure/base_sentences_paragraphs nkjp nkjp/morpho', 'Foundries'); |
| 73 | |
| 74 | is($output->{data}->{layerInfos}, 'dereko/s=spans nkjp/l=tokens nkjp/m=tokens nkjp/p=tokens', 'layerInfos'); |
| 75 | |
| 76 | my $token = join('||', @{$output->{data}->{stream}->[7]}); |
| 77 | |
| 78 | like($token, qr!<>:dereko\/s:seg\$<b>64!); |
| 79 | like($token, qr!<>:dereko\/s:seg\$<b>64!); |
| 80 | like($token, qr!i:ładu!); |
| 81 | like($token, qr!nkjp\/l:ład!); |
| 82 | like($token, qr!nkjp\/m:sg:gen:m3!); |
| 83 | like($token, qr!nkjp\/p:subst!); |
| 84 | like($token, qr!s:ładu!); |
| 85 | |
| 86 | done_testing; |
| 87 | __END__ |
| 88 | |