treat 0.2.5 → 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- data/LICENSE +3 -3
- data/README.md +33 -0
- data/files/INFO +1 -0
- data/lib/treat.rb +40 -105
- data/lib/treat/ai.rb +12 -0
- data/lib/treat/ai/classifiers/id3.rb +27 -0
- data/lib/treat/categories.rb +82 -35
- data/lib/treat/categorizable.rb +44 -0
- data/lib/treat/classification.rb +61 -0
- data/lib/treat/configurable.rb +115 -0
- data/lib/treat/data_set.rb +42 -0
- data/lib/treat/dependencies.rb +24 -0
- data/lib/treat/downloader.rb +87 -0
- data/lib/treat/entities.rb +68 -66
- data/lib/treat/entities/abilities.rb +10 -0
- data/lib/treat/entities/abilities/buildable.rb +327 -0
- data/lib/treat/entities/abilities/checkable.rb +31 -0
- data/lib/treat/entities/abilities/copyable.rb +45 -0
- data/lib/treat/entities/abilities/countable.rb +51 -0
- data/lib/treat/entities/abilities/debuggable.rb +83 -0
- data/lib/treat/entities/abilities/delegatable.rb +123 -0
- data/lib/treat/entities/abilities/doable.rb +62 -0
- data/lib/treat/entities/abilities/exportable.rb +11 -0
- data/lib/treat/entities/abilities/iterable.rb +115 -0
- data/lib/treat/entities/abilities/magical.rb +83 -0
- data/lib/treat/entities/abilities/registrable.rb +74 -0
- data/lib/treat/entities/abilities/stringable.rb +91 -0
- data/lib/treat/entities/entities.rb +104 -0
- data/lib/treat/entities/entity.rb +122 -245
- data/lib/treat/exception.rb +4 -4
- data/lib/treat/extractors.rb +77 -80
- data/lib/treat/extractors/keywords/tf_idf.rb +56 -22
- data/lib/treat/extractors/language/what_language.rb +50 -45
- data/lib/treat/extractors/name_tag/stanford.rb +55 -0
- data/lib/treat/extractors/tf_idf/native.rb +87 -0
- data/lib/treat/extractors/time/chronic.rb +55 -0
- data/lib/treat/extractors/time/nickel.rb +86 -62
- data/lib/treat/extractors/time/ruby.rb +53 -0
- data/lib/treat/extractors/topic_words/lda.rb +67 -58
- data/lib/treat/extractors/topics/reuters.rb +100 -87
- data/lib/treat/formatters.rb +39 -35
- data/lib/treat/formatters/readers/abw.rb +49 -29
- data/lib/treat/formatters/readers/autoselect.rb +37 -33
- data/lib/treat/formatters/readers/doc.rb +19 -13
- data/lib/treat/formatters/readers/html.rb +52 -30
- data/lib/treat/formatters/readers/image.rb +41 -40
- data/lib/treat/formatters/readers/odt.rb +59 -45
- data/lib/treat/formatters/readers/pdf.rb +28 -25
- data/lib/treat/formatters/readers/txt.rb +12 -15
- data/lib/treat/formatters/readers/xml.rb +73 -36
- data/lib/treat/formatters/serializers/xml.rb +80 -79
- data/lib/treat/formatters/serializers/yaml.rb +19 -18
- data/lib/treat/formatters/unserializers/autoselect.rb +12 -22
- data/lib/treat/formatters/unserializers/xml.rb +94 -99
- data/lib/treat/formatters/unserializers/yaml.rb +20 -19
- data/lib/treat/formatters/visualizers/dot.rb +132 -132
- data/lib/treat/formatters/visualizers/standoff.rb +52 -44
- data/lib/treat/formatters/visualizers/tree.rb +26 -29
- data/lib/treat/groupable.rb +153 -0
- data/lib/treat/helpers/decimal_point_escaper.rb +22 -0
- data/lib/treat/inflectors.rb +50 -45
- data/lib/treat/inflectors/cardinalizers/linguistics.rb +40 -0
- data/lib/treat/inflectors/conjugators/linguistics.rb +55 -0
- data/lib/treat/inflectors/declensors/active_support.rb +31 -0
- data/lib/treat/inflectors/declensors/english.rb +38 -0
- data/lib/treat/inflectors/declensors/english/inflect.rb +288 -0
- data/lib/treat/inflectors/declensors/linguistics.rb +49 -0
- data/lib/treat/inflectors/ordinalizers/linguistics.rb +17 -0
- data/lib/treat/inflectors/stemmers/porter.rb +160 -0
- data/lib/treat/inflectors/stemmers/porter_c.rb +24 -0
- data/lib/treat/inflectors/stemmers/uea.rb +28 -0
- data/lib/treat/installer.rb +308 -0
- data/lib/treat/kernel.rb +105 -27
- data/lib/treat/languages.rb +122 -88
- data/lib/treat/languages/arabic.rb +15 -15
- data/lib/treat/languages/chinese.rb +15 -15
- data/lib/treat/languages/dutch.rb +15 -15
- data/lib/treat/languages/english.rb +61 -62
- data/lib/treat/languages/french.rb +19 -19
- data/lib/treat/languages/german.rb +20 -20
- data/lib/treat/languages/greek.rb +15 -15
- data/lib/treat/languages/italian.rb +16 -16
- data/lib/treat/languages/polish.rb +15 -15
- data/lib/treat/languages/portuguese.rb +15 -15
- data/lib/treat/languages/russian.rb +15 -15
- data/lib/treat/languages/spanish.rb +16 -16
- data/lib/treat/languages/swedish.rb +16 -16
- data/lib/treat/lexicalizers.rb +34 -55
- data/lib/treat/lexicalizers/categorizers/from_tag.rb +54 -0
- data/lib/treat/lexicalizers/sensers/wordnet.rb +57 -0
- data/lib/treat/lexicalizers/sensers/wordnet/synset.rb +71 -0
- data/lib/treat/lexicalizers/taggers/brill.rb +70 -0
- data/lib/treat/lexicalizers/taggers/brill/patch.rb +61 -0
- data/lib/treat/lexicalizers/taggers/lingua.rb +90 -0
- data/lib/treat/lexicalizers/taggers/stanford.rb +97 -0
- data/lib/treat/linguistics.rb +9 -0
- data/lib/treat/linguistics/categories.rb +11 -0
- data/lib/treat/linguistics/tags.rb +422 -0
- data/lib/treat/loaders/linguistics.rb +30 -0
- data/lib/treat/loaders/stanford.rb +27 -0
- data/lib/treat/object.rb +1 -0
- data/lib/treat/processors.rb +37 -44
- data/lib/treat/processors/chunkers/autoselect.rb +16 -0
- data/lib/treat/processors/chunkers/html.rb +71 -0
- data/lib/treat/processors/chunkers/txt.rb +18 -24
- data/lib/treat/processors/parsers/enju.rb +253 -208
- data/lib/treat/processors/parsers/stanford.rb +130 -131
- data/lib/treat/processors/segmenters/punkt.rb +79 -45
- data/lib/treat/processors/segmenters/stanford.rb +46 -48
- data/lib/treat/processors/segmenters/tactful.rb +43 -36
- data/lib/treat/processors/tokenizers/perl.rb +124 -92
- data/lib/treat/processors/tokenizers/ptb.rb +81 -0
- data/lib/treat/processors/tokenizers/punkt.rb +48 -42
- data/lib/treat/processors/tokenizers/stanford.rb +39 -38
- data/lib/treat/processors/tokenizers/tactful.rb +64 -55
- data/lib/treat/proxies.rb +52 -35
- data/lib/treat/retrievers.rb +26 -16
- data/lib/treat/retrievers/indexers/ferret.rb +47 -26
- data/lib/treat/retrievers/searchers/ferret.rb +69 -50
- data/lib/treat/tree.rb +241 -183
- data/spec/collection.rb +123 -0
- data/spec/document.rb +93 -0
- data/spec/entity.rb +408 -0
- data/spec/languages.rb +25 -0
- data/spec/phrase.rb +146 -0
- data/spec/samples/mathematicians/archimedes.abw +34 -0
- data/spec/samples/mathematicians/euler.html +21 -0
- data/spec/samples/mathematicians/gauss.pdf +0 -0
- data/spec/samples/mathematicians/leibniz.txt +13 -0
- data/spec/samples/mathematicians/newton.doc +0 -0
- data/spec/sandbox.rb +5 -0
- data/spec/token.rb +109 -0
- data/spec/treat.rb +52 -0
- data/spec/tree.rb +117 -0
- data/spec/word.rb +110 -0
- data/spec/zone.rb +66 -0
- data/tmp/INFO +1 -1
- metadata +100 -201
- data/INSTALL +0 -1
- data/README +0 -3
- data/TODO +0 -28
- data/lib/economist/half_cocked_basel.txt +0 -16
- data/lib/economist/hungarys_troubles.txt +0 -46
- data/lib/economist/indias_slowdown.txt +0 -15
- data/lib/economist/merkozy_rides_again.txt +0 -24
- data/lib/economist/prada_is_not_walmart.txt +0 -9
- data/lib/economist/to_infinity_and_beyond.txt +0 -15
- data/lib/ferret/_11.cfs +0 -0
- data/lib/ferret/_14.cfs +0 -0
- data/lib/ferret/_p.cfs +0 -0
- data/lib/ferret/_s.cfs +0 -0
- data/lib/ferret/_v.cfs +0 -0
- data/lib/ferret/_y.cfs +0 -0
- data/lib/ferret/segments +0 -0
- data/lib/ferret/segments_15 +0 -0
- data/lib/treat/buildable.rb +0 -157
- data/lib/treat/category.rb +0 -33
- data/lib/treat/delegatable.rb +0 -116
- data/lib/treat/doable.rb +0 -45
- data/lib/treat/entities/collection.rb +0 -14
- data/lib/treat/entities/document.rb +0 -12
- data/lib/treat/entities/phrases.rb +0 -17
- data/lib/treat/entities/tokens.rb +0 -61
- data/lib/treat/entities/zones.rb +0 -41
- data/lib/treat/extractors/coreferences/stanford.rb +0 -69
- data/lib/treat/extractors/date/chronic.rb +0 -32
- data/lib/treat/extractors/date/ruby.rb +0 -25
- data/lib/treat/extractors/keywords/topics_tf_idf.rb +0 -48
- data/lib/treat/extractors/language/language_extractor.rb +0 -27
- data/lib/treat/extractors/named_entity_tag/stanford.rb +0 -53
- data/lib/treat/extractors/roles/naive.rb +0 -73
- data/lib/treat/extractors/statistics/frequency_in.rb +0 -16
- data/lib/treat/extractors/statistics/position_in.rb +0 -14
- data/lib/treat/extractors/statistics/tf_idf.rb +0 -104
- data/lib/treat/extractors/statistics/transition_matrix.rb +0 -105
- data/lib/treat/extractors/statistics/transition_probability.rb +0 -57
- data/lib/treat/extractors/topic_words/lda/data.dat +0 -46
- data/lib/treat/extractors/topic_words/lda/wiki.yml +0 -121
- data/lib/treat/extractors/topics/reuters/industry.xml +0 -2717
- data/lib/treat/extractors/topics/reuters/region.xml +0 -13586
- data/lib/treat/extractors/topics/reuters/topics.xml +0 -17977
- data/lib/treat/feature.rb +0 -58
- data/lib/treat/features.rb +0 -7
- data/lib/treat/formatters/visualizers/short_value.rb +0 -29
- data/lib/treat/formatters/visualizers/txt.rb +0 -45
- data/lib/treat/group.rb +0 -106
- data/lib/treat/helpers/linguistics_loader.rb +0 -18
- data/lib/treat/inflectors/cardinal_words/linguistics.rb +0 -42
- data/lib/treat/inflectors/conjugations/linguistics.rb +0 -36
- data/lib/treat/inflectors/declensions/english.rb +0 -319
- data/lib/treat/inflectors/declensions/linguistics.rb +0 -42
- data/lib/treat/inflectors/ordinal_words/linguistics.rb +0 -20
- data/lib/treat/inflectors/stem/porter.rb +0 -162
- data/lib/treat/inflectors/stem/porter_c.rb +0 -26
- data/lib/treat/inflectors/stem/uea.rb +0 -30
- data/lib/treat/install.rb +0 -59
- data/lib/treat/languages/tags.rb +0 -377
- data/lib/treat/lexicalizers/category/from_tag.rb +0 -49
- data/lib/treat/lexicalizers/linkages/naive.rb +0 -63
- data/lib/treat/lexicalizers/synsets/wordnet.rb +0 -76
- data/lib/treat/lexicalizers/tag/brill.rb +0 -91
- data/lib/treat/lexicalizers/tag/lingua.rb +0 -123
- data/lib/treat/lexicalizers/tag/stanford.rb +0 -70
- data/lib/treat/processors/segmenters/punkt/dutch.yaml +0 -9716
- data/lib/treat/processors/segmenters/punkt/english.yaml +0 -10340
- data/lib/treat/processors/segmenters/punkt/french.yaml +0 -43159
- data/lib/treat/processors/segmenters/punkt/german.yaml +0 -9572
- data/lib/treat/processors/segmenters/punkt/greek.yaml +0 -6050
- data/lib/treat/processors/segmenters/punkt/italian.yaml +0 -14748
- data/lib/treat/processors/segmenters/punkt/polish.yaml +0 -9751
- data/lib/treat/processors/segmenters/punkt/portuguese.yaml +0 -13662
- data/lib/treat/processors/segmenters/punkt/russian.yaml +0 -4237
- data/lib/treat/processors/segmenters/punkt/spanish.yaml +0 -24034
- data/lib/treat/processors/segmenters/punkt/swedish.yaml +0 -10001
- data/lib/treat/processors/tokenizers/macintyre.rb +0 -77
- data/lib/treat/processors/tokenizers/multilingual.rb +0 -30
- data/lib/treat/registrable.rb +0 -28
- data/lib/treat/sugar.rb +0 -50
- data/lib/treat/viewable.rb +0 -29
- data/lib/treat/visitable.rb +0 -28
- data/test/profile.rb +0 -2
- data/test/tc_entity.rb +0 -117
- data/test/tc_extractors.rb +0 -73
- data/test/tc_formatters.rb +0 -41
- data/test/tc_inflectors.rb +0 -34
- data/test/tc_lexicalizers.rb +0 -32
- data/test/tc_processors.rb +0 -50
- data/test/tc_resources.rb +0 -22
- data/test/tc_treat.rb +0 -60
- data/test/tc_tree.rb +0 -60
- data/test/tests.rb +0 -20
- data/test/texts.rb +0 -19
- data/test/texts/english/half_cocked_basel.txt +0 -16
- data/test/texts/english/hose_and_dry.doc +0 -0
- data/test/texts/english/hungarys_troubles.abw +0 -70
- data/test/texts/english/long.html +0 -24
- data/test/texts/english/long.txt +0 -22
- data/test/texts/english/medium.txt +0 -5
- data/test/texts/english/republican_nomination.pdf +0 -0
- data/test/texts/english/saving_the_euro.odt +0 -0
- data/test/texts/english/short.txt +0 -3
- data/test/texts/english/zero_sum.html +0 -111
data/spec/document.rb
ADDED
@@ -0,0 +1,93 @@
|
|
1
|
+
require_relative '../lib/treat'
|
2
|
+
|
3
|
+
describe Treat::Entities::Document do
|
4
|
+
|
5
|
+
describe "Extractable" do
|
6
|
+
|
7
|
+
describe "#topics" do
|
8
|
+
|
9
|
+
it "returns a list of general topics the document belongs to" do
|
10
|
+
#doc = Treat::Entities::Document.new(
|
11
|
+
#Treat.spec + 'samples/mathematicians/archimedes.abw').read(:abw)
|
12
|
+
#doc.do(:chunk, :segment, :tokenize)
|
13
|
+
#puts doc.topics.inspect
|
14
|
+
end
|
15
|
+
|
16
|
+
end
|
17
|
+
|
18
|
+
end
|
19
|
+
|
20
|
+
describe "Buildable" do
|
21
|
+
|
22
|
+
describe "#build" do
|
23
|
+
|
24
|
+
context "when supplied with a readable file name" do
|
25
|
+
it "opens the file and reads its " +
|
26
|
+
"content into a document" do
|
27
|
+
f = Treat.spec + 'samples/mathematicians/leibniz.txt'
|
28
|
+
d = Treat::Entities::Document.build(f)
|
29
|
+
d.should be_an_instance_of Treat::Entities::Document
|
30
|
+
d.to_s.index('Gottfried Leibniz').should_not eql nil
|
31
|
+
end
|
32
|
+
end
|
33
|
+
|
34
|
+
context "when supplied with a url" do
|
35
|
+
it "downloads the file the URL points to and opens " +
|
36
|
+
"a document with the contents of the file" do
|
37
|
+
url = 'http://www.rubyinside.com/nethttp-cheat-sheet-2940.html'
|
38
|
+
d = Treat::Entities::Document.build(url)
|
39
|
+
d.should be_an_instance_of Treat::Entities::Document
|
40
|
+
d.to_s.index('Rubyist').should_not eql nil
|
41
|
+
end
|
42
|
+
end
|
43
|
+
|
44
|
+
context "when called with anything else than a " +
|
45
|
+
"readable file name or url" do
|
46
|
+
|
47
|
+
it "raises an exception" do
|
48
|
+
lambda do
|
49
|
+
Treat::Entities::Document.build('nonexistent')
|
50
|
+
end.should raise_error
|
51
|
+
end
|
52
|
+
|
53
|
+
end
|
54
|
+
|
55
|
+
end
|
56
|
+
|
57
|
+
end
|
58
|
+
|
59
|
+
describe "Processable" do
|
60
|
+
|
61
|
+
describe "#chunk" do
|
62
|
+
|
63
|
+
context "when called on an HTML document" do
|
64
|
+
doc = Treat::Entities::Document.new(
|
65
|
+
Treat.spec + 'samples/mathematicians/euler.html').read(:html)
|
66
|
+
it "splits the HTML document into sections, " +
|
67
|
+
"titles, paragraphs and lists" do
|
68
|
+
doc.chunk
|
69
|
+
doc.title_count.should eql 1
|
70
|
+
doc.title.to_s.should eql "Leonhard Euler (1707-1783)"
|
71
|
+
doc.paragraph_count.should eql 5
|
72
|
+
end
|
73
|
+
|
74
|
+
end
|
75
|
+
|
76
|
+
context "when called on a text document" do
|
77
|
+
|
78
|
+
doc = Treat::Entities::Document.new(Treat.spec +
|
79
|
+
'samples/mathematicians/leibniz.txt').read(:txt)
|
80
|
+
it "splits the document into titles and paragraphs" do
|
81
|
+
doc.chunk
|
82
|
+
doc.title_count.should eql 1
|
83
|
+
doc.title.to_s.should eql "Gottfried Leibniz (1646-1716)"
|
84
|
+
doc.paragraph_count.should eql 6
|
85
|
+
end
|
86
|
+
|
87
|
+
end
|
88
|
+
|
89
|
+
end
|
90
|
+
|
91
|
+
end
|
92
|
+
|
93
|
+
end
|
data/spec/entity.rb
ADDED
@@ -0,0 +1,408 @@
|
|
1
|
+
require_relative '../lib/treat'
|
2
|
+
|
3
|
+
describe Treat::Entities::Entity do
|
4
|
+
|
5
|
+
before do
|
6
|
+
|
7
|
+
@paragraph = Treat::Entities::Paragraph.new
|
8
|
+
@sentence = Treat::Entities::Sentence.new
|
9
|
+
@noun_phrase = Treat::Entities::Phrase.new
|
10
|
+
@noun_phrase.set :tag, 'NP'
|
11
|
+
@verb_phrase = Treat::Entities::Phrase.new
|
12
|
+
@verb_phrase.set :tag, 'VP'
|
13
|
+
@adj_phrase = Treat::Entities::Phrase.new
|
14
|
+
@adj_phrase.set :tag, 'ADJP'
|
15
|
+
@det = Treat::Entities::Word.new('The')
|
16
|
+
@det.set :category, :determiner
|
17
|
+
@det.set :tag, 'DT'
|
18
|
+
@adj = Treat::Entities::Word.new('lazy')
|
19
|
+
@adj.set :category, :adjective
|
20
|
+
@adj.set :tag, 'JJ'
|
21
|
+
@noun = Treat::Entities::Word.new('fox')
|
22
|
+
@noun.set :category, :noun
|
23
|
+
@noun.set :tag, 'NN'
|
24
|
+
@aux = Treat::Entities::Word.new('is')
|
25
|
+
@aux.set :category, :verb
|
26
|
+
@aux.set :tag, 'VBZ'
|
27
|
+
@verb = Treat::Entities::Word.new('running')
|
28
|
+
@verb.set :category, :verb
|
29
|
+
@verb.set :tag, 'VBG'
|
30
|
+
@dot = Treat::Entities::Punctuation.new('.')
|
31
|
+
@dot.set :tag, '.'
|
32
|
+
@paragraph << @sentence << [@noun_phrase, @verb_phrase, @dot]
|
33
|
+
@noun_phrase << [@det, @adj_phrase, @noun]
|
34
|
+
@adj_phrase << @adj
|
35
|
+
@verb_phrase << [@aux, @verb]
|
36
|
+
|
37
|
+
end
|
38
|
+
|
39
|
+
|
40
|
+
describe "Checkable" do
|
41
|
+
|
42
|
+
describe "#check_has(feature, do_it = true) " do
|
43
|
+
|
44
|
+
it "checks if an entity has the feature; if not, " +
|
45
|
+
"calls the default worker to get the feature if do_it " +
|
46
|
+
"is set to true; if the entity doesn't have the feature " +
|
47
|
+
" and do_it is set to false, it raises an exception." do
|
48
|
+
|
49
|
+
# NOT PASSING! Dependence on caller method.
|
50
|
+
|
51
|
+
# lambda { '$'.to_entity.check_has(:tag, false) }.should raise_error Treat::Exception
|
52
|
+
|
53
|
+
end
|
54
|
+
|
55
|
+
end
|
56
|
+
|
57
|
+
end
|
58
|
+
|
59
|
+
describe "Countable" do
|
60
|
+
|
61
|
+
describe "#position" do
|
62
|
+
|
63
|
+
it "returns the position of the entity in its parent, sarting at 1" do
|
64
|
+
@noun_phrase.position.should eql 1
|
65
|
+
@det.position.should eql 1
|
66
|
+
end
|
67
|
+
|
68
|
+
end
|
69
|
+
|
70
|
+
=begin
|
71
|
+
|
72
|
+
describe "#frequency" do
|
73
|
+
|
74
|
+
it "returns the frequency of the entity's value in the root" do
|
75
|
+
@det.frequency.should eql 1
|
76
|
+
end
|
77
|
+
|
78
|
+
end
|
79
|
+
|
80
|
+
|
81
|
+
describe "#frequency_in(parent_type = nil)" do
|
82
|
+
|
83
|
+
it "returns the position of the entity's value "+
|
84
|
+
"in the supplied parent type, or root if nil" do
|
85
|
+
@noun_phrase.frequency_in(:sentence).should eql 1
|
86
|
+
|
87
|
+
end
|
88
|
+
|
89
|
+
end
|
90
|
+
|
91
|
+
=end
|
92
|
+
|
93
|
+
end
|
94
|
+
|
95
|
+
describe "Delegatable" do
|
96
|
+
|
97
|
+
describe "#self.call_worker" do
|
98
|
+
|
99
|
+
it "finds the worker class to " +
|
100
|
+
"perform a task and delegates the task to it " do
|
101
|
+
|
102
|
+
Treat::Entities::Entity.call_worker(
|
103
|
+
'$'.to_entity, :tag, :lingua,
|
104
|
+
Treat::Lexicalizers::Taggers, {}).should
|
105
|
+
eql @sentence.tag(:lingua)
|
106
|
+
|
107
|
+
end
|
108
|
+
|
109
|
+
end
|
110
|
+
|
111
|
+
end
|
112
|
+
|
113
|
+
describe "Exportable" do
|
114
|
+
|
115
|
+
context "when supplied with a classification to export" do
|
116
|
+
classification = Treat::Classification.new(:word, :tag, :is_keyword?)
|
117
|
+
it "returns a data set with the exported features" do
|
118
|
+
ds = @sentence.export(classification)
|
119
|
+
ds.classification.should eql classification
|
120
|
+
ds.labels.should eql [:tag]
|
121
|
+
ds.ids.should eql @sentence.words.map { |w| w.id }
|
122
|
+
ds.items.should eql [
|
123
|
+
["DT", false], ["JJ", false],
|
124
|
+
["NN", false], ["VBZ", false],
|
125
|
+
["VBG", false]
|
126
|
+
]
|
127
|
+
end
|
128
|
+
end
|
129
|
+
|
130
|
+
end
|
131
|
+
|
132
|
+
describe "Iterable" do
|
133
|
+
|
134
|
+
describe "#each { |child| ... }" do
|
135
|
+
it "yields each direct child of a node" do
|
136
|
+
a = []
|
137
|
+
@sentence.each do |child|
|
138
|
+
a << child
|
139
|
+
end
|
140
|
+
a.should eql [@noun_phrase, @verb_phrase, @dot]
|
141
|
+
end
|
142
|
+
end
|
143
|
+
|
144
|
+
describe "#each_entity(*entity_types) { |entity| ... }" do
|
145
|
+
|
146
|
+
context "when called with no arguments" do
|
147
|
+
it "recursively yields each element in " +
|
148
|
+
"the tree, including itself, top-down " +
|
149
|
+
"first then left to right" do
|
150
|
+
|
151
|
+
a = []
|
152
|
+
@sentence.each_entity do |e|
|
153
|
+
a << e
|
154
|
+
end
|
155
|
+
|
156
|
+
a.should eql [@sentence, @noun_phrase, @det,
|
157
|
+
@adj_phrase, @adj, @noun,
|
158
|
+
@verb_phrase, @aux, @verb, @dot]
|
159
|
+
|
160
|
+
end
|
161
|
+
end
|
162
|
+
|
163
|
+
context "when called with one or more entity " +
|
164
|
+
"types supplied as lowercase symbols" do
|
165
|
+
it "recursively yields all elements with the given type(s), "+
|
166
|
+
"including the receiver if it matches on of the types" do
|
167
|
+
a = []
|
168
|
+
@sentence.each_entity(:phrase, :punctuation) do |e|
|
169
|
+
a << e
|
170
|
+
end
|
171
|
+
a.should eql [@sentence, @noun_phrase,
|
172
|
+
@adj_phrase, @verb_phrase, @dot]
|
173
|
+
end
|
174
|
+
end
|
175
|
+
|
176
|
+
end
|
177
|
+
end
|
178
|
+
|
179
|
+
describe "Magical" do
|
180
|
+
|
181
|
+
describe "#<entity or word type> - e.g. " +
|
182
|
+
"#title, #paragraph, etc. and #adjective, #noun, etc." do
|
183
|
+
|
184
|
+
it "return the first entity with the corresponding " +
|
185
|
+
"type inside another entity, but raises an exception "+
|
186
|
+
"the type occurs more than once in the entity" do
|
187
|
+
@paragraph.sentence.should eql @sentence
|
188
|
+
end
|
189
|
+
|
190
|
+
end
|
191
|
+
|
192
|
+
|
193
|
+
describe "#<entity or word type>s - e.g. " +
|
194
|
+
"#sections, #words, etc. and #nouns, #adverbs, etc." do
|
195
|
+
|
196
|
+
it "return an array of the entities with the " +
|
197
|
+
"corresponding type in the subtree of an entity" do
|
198
|
+
@paragraph.phrases.should eql [@sentence,
|
199
|
+
@noun_phrase, @adj_phrase, @verb_phrase]
|
200
|
+
end
|
201
|
+
|
202
|
+
end
|
203
|
+
|
204
|
+
describe "#each_<entity type> - e.g. " +
|
205
|
+
"#each_sentence, #each_word, etc." do
|
206
|
+
|
207
|
+
it "yields each of the entities with the " +
|
208
|
+
"corresponding type in the subtree of an entity" do
|
209
|
+
a = []
|
210
|
+
|
211
|
+
@paragraph.each_phrase { |p| a << p }
|
212
|
+
a.should eql [@sentence, @noun_phrase,
|
213
|
+
@adj_phrase, @verb_phrase]
|
214
|
+
|
215
|
+
end
|
216
|
+
|
217
|
+
end
|
218
|
+
|
219
|
+
describe "#<entity or word type>_count - e.g. " +
|
220
|
+
"#sentence_count, #paragraph_count, etc. and " +
|
221
|
+
"#noun_count, #verb_count, etc." do
|
222
|
+
|
223
|
+
it "return the number of entities with the " +
|
224
|
+
"corresponding type inside another entity" do
|
225
|
+
@paragraph.sentence_count.should eql 1
|
226
|
+
@paragraph.phrase_count.should eql 4
|
227
|
+
end
|
228
|
+
|
229
|
+
end
|
230
|
+
|
231
|
+
describe "#<entity or word type>_with_<feature>(value) - " +
|
232
|
+
"e.g. #word_with_id(x) or #adverb_with_value('seemingly')" do
|
233
|
+
|
234
|
+
it "return the entity with the corresponding type " +
|
235
|
+
"that have [feature] set to the supplied value; raise" +
|
236
|
+
"a warning if there are many entities of that type" do
|
237
|
+
@paragraph.word_with_value('The').should eql @det
|
238
|
+
@paragraph.token_with_tag('.').should eql @dot
|
239
|
+
@sentence.phrase_with_tag('NP').should eql @noun_phrase
|
240
|
+
end
|
241
|
+
|
242
|
+
end
|
243
|
+
|
244
|
+
describe "#<entity or word type>s_with_<feature>(value) - " +
|
245
|
+
"e.g. #phrases_with_tag('NP'), #nouns_with_value('foo')" do
|
246
|
+
|
247
|
+
it "return an array of the entities with the " +
|
248
|
+
"corresponding type that have [feature] set to "+
|
249
|
+
"the supplied value" do
|
250
|
+
@paragraph.words_with_value('The').should eql [@det]
|
251
|
+
@paragraph.tokens_with_tag('.').should eql [@dot]
|
252
|
+
@sentence.phrases_with_tag('NP').should eql [@noun_phrase]
|
253
|
+
end
|
254
|
+
|
255
|
+
end
|
256
|
+
|
257
|
+
describe "#parent_<entity type> - e.g. " +
|
258
|
+
"#parent_document, #parent_collection, etc." do
|
259
|
+
|
260
|
+
it "return the first ancestor of the entity " +
|
261
|
+
"that has the supplied type, or nil if none" do
|
262
|
+
@sentence.parent_paragraph.should eql @paragraph
|
263
|
+
@adj.parent_sentence.should eql @sentence
|
264
|
+
end
|
265
|
+
|
266
|
+
end
|
267
|
+
|
268
|
+
describe "#frequency_in_<entity type> - e.g. " +
|
269
|
+
"#frequency_in_collection, #frequency_in_document, etc." do
|
270
|
+
|
271
|
+
it "return the frequency of this entity's value " +
|
272
|
+
"in the parent entity with the corresponding type" do
|
273
|
+
@adj.frequency_in_sentence.should eql 1
|
274
|
+
end
|
275
|
+
|
276
|
+
end
|
277
|
+
|
278
|
+
end
|
279
|
+
|
280
|
+
describe "Stringable" do
|
281
|
+
|
282
|
+
describe "#to_string" do
|
283
|
+
it "returns the true text value of the entity " +
|
284
|
+
"or an empty string if it has none" do
|
285
|
+
@paragraph.to_string.should eql ''
|
286
|
+
@noun.to_string.should eql 'fox'
|
287
|
+
end
|
288
|
+
end
|
289
|
+
|
290
|
+
describe "#to_s" do
|
291
|
+
it "returns the string value of the " +
|
292
|
+
"entity or its full subtree" do
|
293
|
+
@paragraph.to_s.should
|
294
|
+
eql 'The lazy fox is running.'
|
295
|
+
@noun.to_s.should eql 'fox'
|
296
|
+
end
|
297
|
+
end
|
298
|
+
|
299
|
+
describe "#inspect" do
|
300
|
+
it "returns an informative string " +
|
301
|
+
"concerning the entity" do
|
302
|
+
@paragraph.inspect.should
|
303
|
+
be_an_instance_of String
|
304
|
+
end
|
305
|
+
end
|
306
|
+
|
307
|
+
describe "#short_value" do
|
308
|
+
it "returns a shortened version of the " +
|
309
|
+
"entity's string value" do
|
310
|
+
@paragraph.short_value.should
|
311
|
+
eql 'The lazy fox is running.'
|
312
|
+
end
|
313
|
+
end
|
314
|
+
|
315
|
+
end
|
316
|
+
|
317
|
+
describe "Formatters" do
|
318
|
+
|
319
|
+
describe "#serialize" do
|
320
|
+
|
321
|
+
before :all do
|
322
|
+
@serializers = [:xml, :yaml] # Treat::Languages::All::Serializers
|
323
|
+
@txt = "The story of the fox. The quick brown fox jumped over the lazy dog."
|
324
|
+
end
|
325
|
+
|
326
|
+
context "when called with a file to save to" do
|
327
|
+
|
328
|
+
it "serializes a document to the supplied format" do
|
329
|
+
|
330
|
+
@serializers.each do |ser|
|
331
|
+
f = Treat.spec + 'test.' + ser.to_s
|
332
|
+
s = Treat::Entities::Paragraph.new(@txt)
|
333
|
+
s.do(:segment, :tokenize)
|
334
|
+
s.serialize(ser, :file => f)
|
335
|
+
d = Treat::Entities::Document.build(f)
|
336
|
+
d.to_s.should eql @txt
|
337
|
+
d.size.should eql s.size
|
338
|
+
d.token_count.should eql s.token_count
|
339
|
+
d.tokens[0].id.should eql s.tokens[0].id
|
340
|
+
File.delete(f)
|
341
|
+
end
|
342
|
+
|
343
|
+
end
|
344
|
+
|
345
|
+
end
|
346
|
+
|
347
|
+
end
|
348
|
+
|
349
|
+
describe "#unserialize" do
|
350
|
+
|
351
|
+
end
|
352
|
+
|
353
|
+
end
|
354
|
+
|
355
|
+
describe "Extractors" do
|
356
|
+
|
357
|
+
describe "#language" do
|
358
|
+
context "when language detection is disabled " +
|
359
|
+
"(Treat.detect_language is set to false)" do
|
360
|
+
it "returns the default language (Treat.default_language)" do
|
361
|
+
Treat.detect_language = false
|
362
|
+
Treat.default_language = :test
|
363
|
+
s = 'Les grands hommes ne sont pas toujours grands, dit un jour Napoleon.'
|
364
|
+
s.language.should eql :test
|
365
|
+
Treat.default_language = :eng
|
366
|
+
end
|
367
|
+
end
|
368
|
+
|
369
|
+
context "when language detection is enabled " +
|
370
|
+
"(Treat.detect_language is set to true)" do
|
371
|
+
|
372
|
+
it "guesses the language of the entity" do
|
373
|
+
|
374
|
+
Treat.detect_language = true
|
375
|
+
a = 'I want to know God\'s thoughts; the rest are details. - Albert Einstein'
|
376
|
+
b = 'El mundo de hoy no tiene sentido, asi que por que deberia pintar cuadros que lo tuvieran? - Pablo Picasso'
|
377
|
+
c = 'Un bon Allemand ne peut souffrir les Francais, mais il boit volontiers les vins de France. - Goethe'
|
378
|
+
d = 'Wir haben die Kunst, damit wir nicht an der Wahrheit zugrunde gehen. - Friedrich Nietzsche'
|
379
|
+
a.language.should eql :eng
|
380
|
+
b.language.should eql :spa
|
381
|
+
c.language.should eql :fre
|
382
|
+
d.language.should eql :ger
|
383
|
+
|
384
|
+
# Reset default
|
385
|
+
Treat.detect_language = false
|
386
|
+
end
|
387
|
+
|
388
|
+
end
|
389
|
+
|
390
|
+
end
|
391
|
+
|
392
|
+
end
|
393
|
+
|
394
|
+
end
|
395
|
+
|
396
|
+
|
397
|
+
=begin
|
398
|
+
|
399
|
+
|
400
|
+
def test_visualizers
|
401
|
+
assert_nothing_raised { @doc.visualize(:tree) }
|
402
|
+
# assert_nothing_raised { @doc.visualize(:html) }
|
403
|
+
assert_nothing_raised { @doc.visualize(:dot) }
|
404
|
+
assert_nothing_raised { @doc.visualize(:short_value) }
|
405
|
+
assert_nothing_raised { @sentence.visualize(:standoff) }
|
406
|
+
end
|
407
|
+
|
408
|
+
=end
|