| Akron | 7d5e638 | 2019-08-08 16:36:27 +0200 | [diff] [blame^] | 1 | use strict; | 
|  | 2 | use warnings; | 
|  | 3 | use Test::More; | 
|  | 4 | use Data::Dumper; | 
|  | 5 | use JSON::XS; | 
|  | 6 |  | 
|  | 7 | use Benchmark qw/:hireswallclock/; | 
|  | 8 |  | 
|  | 9 | my $t = Benchmark->new; | 
|  | 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/WPF19/P00/0042242'); | 
|  | 20 |  | 
|  | 21 | ok(my $doc = KorAP::XML::Krill->new( path => $path . '/' ), 'Load Korap::Document'); | 
|  | 22 | ok($doc->parse, 'Parse document'); | 
|  | 23 |  | 
|  | 24 | is($doc->text_sigle, 'WPF19/P00/0042242', 'Correct text sigle'); | 
|  | 25 | is($doc->doc_sigle, 'WPF19/P00', 'Correct document sigle'); | 
|  | 26 | is($doc->corpus_sigle, 'WPF19', 'Correct corpus sigle'); | 
|  | 27 |  | 
|  | 28 | my $meta = $doc->meta; | 
|  | 29 |  | 
|  | 30 | is($meta->{T_title}, 'Psychanalyse', 'Title'); | 
|  | 31 | is($meta->{S_pub_place}, 'URL:http://fr.wikipedia.org', 'PubPlace'); | 
|  | 32 | is($meta->{D_pub_date}, '20190220', 'Creation Date'); | 
|  | 33 | is($meta->{S_text_type}, 'Enzyklopädie', 'Text type'); | 
|  | 34 | is($meta->{T_author}, 'Pierrette13, u.a.', 'Author'); | 
|  | 35 | is($meta->{S_language}, 'fr', 'Author'); | 
|  | 36 |  | 
|  | 37 | is($meta->{T_doc_title}, 'Wikipedia, Artikel mit Anfangsbuchstabe P, Teil 00', 'Correct Doc title'); | 
|  | 38 | ok(!$meta->{T_doc_sub_title}, 'Correct Doc Sub title'); | 
|  | 39 | ok(!$meta->{T_doc_author}, 'Correct Doc author'); | 
|  | 40 | ok(!$meta->{A_doc_editor}, 'Correct Doc editor'); | 
|  | 41 |  | 
|  | 42 | is($meta->{T_corpus_title}, 'Wikipedia', 'Correct Corpus title'); | 
|  | 43 | ok(!$meta->{T_corpus_sub_title}, 'Correct Corpus Sub title'); | 
|  | 44 |  | 
|  | 45 | # This link is broken, but that's due to the data | 
|  | 46 | is($meta->{A_externalLink}, 'data:application/x.korap-link;title=Wikipedia,http://fr.wikipedia.org/wiki/Psychanalyse', 'No link'); | 
|  | 47 |  | 
|  | 48 | # Tokenization | 
|  | 49 | use_ok('KorAP::XML::Tokenizer'); | 
|  | 50 |  | 
|  | 51 | my ($token_base_foundry, $token_base_layer) = (qw/Base Tokens/); | 
|  | 52 |  | 
|  | 53 | # Get tokenization | 
|  | 54 | my $tokens = KorAP::XML::Tokenizer->new( | 
|  | 55 | path => $doc->path, | 
|  | 56 | doc => $doc, | 
|  | 57 | foundry => $token_base_foundry, | 
|  | 58 | layer => $token_base_layer, | 
|  | 59 | name => 'tokens' | 
|  | 60 | ); | 
|  | 61 | ok($tokens, 'Token Object is fine'); | 
|  | 62 | ok($tokens->parse, 'Token parsing is fine'); | 
|  | 63 |  | 
|  | 64 | my $output = $tokens->to_data; | 
|  | 65 |  | 
|  | 66 | is(substr($output->{data}->{text}, 0, 100), 'Fichier:Sigmund Freud LIFE.jpg La psychanalyse est, selon la définition classique qu\'en a donnée Sig', 'Primary Data'); | 
|  | 67 | is($output->{data}->{name}, 'tokens', 'tokenName'); | 
|  | 68 | is($output->{data}->{tokenSource}, 'base#tokens', 'tokenSource'); | 
|  | 69 |  | 
|  | 70 | is($output->{version}, '0.03', 'version'); | 
|  | 71 | is($output->{data}->{foundries}, '', 'Foundries'); | 
|  | 72 | is($output->{data}->{layerInfos}, '', 'layerInfos'); | 
|  | 73 | is($output->{data}->{stream}->[0]->[4], 's:Fichier', 'data'); | 
|  | 74 |  | 
|  | 75 | $tokens->add('Malt', 'Dependency'); | 
|  | 76 |  | 
|  | 77 | my $stream = $tokens->to_data->{data}->{stream}; | 
|  | 78 |  | 
|  | 79 | # This is not a goot relation example | 
|  | 80 | is($stream->[77]->[0], | 
|  | 81 | '>:malt/d:nsubj$<b>32<i>78', | 
|  | 82 | 'element to term'); | 
|  | 83 | is($stream->[78]->[0], '>:malt/d:null$<b>32<i>76', 'term to element'); | 
|  | 84 |  | 
|  | 85 | # Add structure | 
|  | 86 | $tokens->add('DeReKo', 'Structure'); | 
|  | 87 |  | 
|  | 88 | $stream = $tokens->to_data->{data}->{stream}; | 
|  | 89 |  | 
|  | 90 | is($stream->[71]->[1], '<>:dereko/s:s$<b>64<i>530<i>856<i>124<b>4', 'Text starts with sentence'); | 
|  | 91 |  | 
|  | 92 | # Add Talismane Dependency | 
|  | 93 | $tokens->add('Talismane', 'Dependency'); | 
|  | 94 |  | 
|  | 95 | $stream = $tokens->to_data->{data}->{stream}; | 
|  | 96 | is($stream->[1]->[0], '>:talismane/d:mod$<b>32<i>0', 'Talismane dependency annotation'); | 
|  | 97 | is($stream->[300]->[0], '>:talismane/d:det$<b>32<i>301', 'Talismane dep annotation'); | 
|  | 98 |  | 
|  | 99 |  | 
|  | 100 | # Add Talismane Morpho | 
|  | 101 | $tokens->add('Talismane', 'Morpho'); | 
|  | 102 |  | 
|  | 103 | $stream = $tokens->to_data->{data}->{stream}; | 
|  | 104 | is($stream->[1]->[10], 'talismane/l:Sigmund', 'Talismane morpho annotation'); | 
|  | 105 | is($stream->[1]->[11], 'talismane/m:g:m', 'Talismane morpho annotation'); | 
|  | 106 | is($stream->[1]->[12], 'talismane/m:n:s', 'Talismane morpho annotation'); | 
|  | 107 | is($stream->[1]->[13], 'talismane/p:NPP', 'Talismane morpho annotation'); | 
|  | 108 |  | 
|  | 109 | is($stream->[300]->[5], 'talismane/l:son', 'Talismane lemma annotation'); | 
|  | 110 | is($stream->[300]->[6], 'talismane/m:g:m', 'Talismane morph annotation'); | 
|  | 111 | is($stream->[300]->[7], 'talismane/m:n:s', 'Talismane morph annotation'); | 
|  | 112 | is($stream->[300]->[8], 'talismane/m:p:3', 'Talismane morph annotation'); | 
|  | 113 | is($stream->[300]->[9], 'talismane/m:poss:s', 'Talismane morph annotation'); | 
|  | 114 | is($stream->[300]->[10], 'talismane/p:DET', 'Talismane pos annotation'); | 
|  | 115 |  | 
|  | 116 | # Add Malt dependency | 
|  | 117 | $tokens->add('Malt', 'Dependency'); | 
|  | 118 | $stream = $tokens->to_data->{data}->{stream}; | 
|  | 119 | is($stream->[1]->[1], '>:malt/d:dep$<b>33<i>7<i>8<i>0<i>1', 'Malt dep annotation'); | 
|  | 120 | is($stream->[1]->[2], '<:malt/d:dep$<b>32<i>2', 'Malt dep annotation'); | 
|  | 121 | is($stream->[300]->[1], '>:malt/d:punct$<b>32<i>302', 'Malt dep annotation'); | 
|  | 122 |  | 
|  | 123 |  | 
|  | 124 | # Add TreeTagger morpho | 
|  | 125 | $tokens->add('TreeTagger', 'Morpho'); | 
|  | 126 | $stream = $tokens->to_data->{data}->{stream}; | 
|  | 127 | is($stream->[1]->[14], 'tt/p:ADJ$<b>129<b>26', 'TreeTagger morph annotation'); | 
|  | 128 | is($stream->[1]->[15], 'tt/p:NAM$<b>129<b>200', 'TreeTagger morph annotation'); | 
|  | 129 | is($stream->[1]->[16], 'tt/p:NOM$<b>129<b>27', 'TreeTagger morph annotation'); | 
|  | 130 |  | 
|  | 131 |  | 
|  | 132 | done_testing; | 
|  | 133 | __END__ | 
|  | 134 |  | 
|  | 135 |  | 
|  | 136 |  | 
|  | 137 |  |