langue-japanese 0.0.2
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +17 -0
- data/Gemfile +6 -0
- data/LICENSE +22 -0
- data/README.md +53 -0
- data/Rakefile +2 -0
- data/langue-japanese.gemspec +22 -0
- data/lib/langue/japanese/language.rb +36 -0
- data/lib/langue/japanese/logging.rb +21 -0
- data/lib/langue/japanese/parser.rb +77 -0
- data/lib/langue/japanese/shaper.rb +70 -0
- data/lib/langue/japanese/structurer.rb +74 -0
- data/lib/langue/japanese/version.rb +5 -0
- data/lib/langue/japanese/words/adjective.rb +67 -0
- data/lib/langue/japanese/words/adjective_noun.rb +76 -0
- data/lib/langue/japanese/words/attribute.rb +100 -0
- data/lib/langue/japanese/words/classifier.rb +107 -0
- data/lib/langue/japanese/words/morpheme_filter.rb +26 -0
- data/lib/langue/japanese/words/noun.rb +61 -0
- data/lib/langue/japanese/words/period.rb +55 -0
- data/lib/langue/japanese/words/prefix.rb +19 -0
- data/lib/langue/japanese/words/pronoun.rb +16 -0
- data/lib/langue/japanese/words/verb.rb +100 -0
- data/lib/langue/japanese.rb +2 -0
- data/lib/langue-japanese.rb +1 -0
- data/spec/langue/japanese/data.yaml +169 -0
- data/spec/langue/japanese/language_spec.rb +120 -0
- data/spec/langue/japanese/parser_spec.rb +147 -0
- data/spec/langue/japanese/shaper_spec.rb +34 -0
- data/spec/langue/japanese/structurer_spec.rb +116 -0
- data/spec/langue/japanese/words/adjective_noun_spec.rb +76 -0
- data/spec/langue/japanese/words/adjective_spec.rb +123 -0
- data/spec/langue/japanese/words/noun_spec.rb +79 -0
- data/spec/langue/japanese/words/period_spec.rb +69 -0
- data/spec/langue/japanese/words/pronoun_spec.rb +24 -0
- data/spec/langue/japanese/words/verb_spec.rb +242 -0
- data/spec/langue/japanese_spec.rb +7 -0
- data/spec/spec_helper.rb +75 -0
- metadata +131 -0
@@ -0,0 +1,242 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
require 'spec_helper'
|
3
|
+
require 'langue/japanese/words/verb'
|
4
|
+
|
5
|
+
describe Langue::Japanese::Verb, '.take' do
|
6
|
+
after do
|
7
|
+
@pairs.each do |text, size|
|
8
|
+
morphemes = parser.parse(text)
|
9
|
+
described_class.take(morphemes, 0).should == size
|
10
|
+
end
|
11
|
+
end
|
12
|
+
|
13
|
+
it 'takes a verb' do
|
14
|
+
@pairs = {
|
15
|
+
'話すこと' => 1,
|
16
|
+
'喋ること' => 1,
|
17
|
+
'会話だ' => 0,
|
18
|
+
'かわいいこと' => 0
|
19
|
+
}
|
20
|
+
end
|
21
|
+
|
22
|
+
it 'takes a verb with prefix' do
|
23
|
+
@pairs = {
|
24
|
+
'ぶっ話すこと' => 2,
|
25
|
+
'ぶっぶち話すこと' => 3,
|
26
|
+
'ぶっ会話だ' => 0,
|
27
|
+
'ぶっかわいいこと' => 0
|
28
|
+
}
|
29
|
+
end
|
30
|
+
|
31
|
+
it 'takes a noun conjunct to suru-verb as a verb' do
|
32
|
+
@pairs = {
|
33
|
+
'会話すること' => 2,
|
34
|
+
'連絡すること' => 2,
|
35
|
+
'会話だ' => 0,
|
36
|
+
'すること' => 0
|
37
|
+
}
|
38
|
+
end
|
39
|
+
|
40
|
+
it 'takes a noun conjunct to suru-verb with prefix as a verb' do
|
41
|
+
@pairs = {
|
42
|
+
'ご連絡すること' => 3,
|
43
|
+
'超反連絡すること' => 4,
|
44
|
+
'ご連絡だ' => 0,
|
45
|
+
'反超すること' => 0
|
46
|
+
}
|
47
|
+
end
|
48
|
+
|
49
|
+
it 'takes a verb with suffix' do
|
50
|
+
@pairs = {
|
51
|
+
'話されること' => 2,
|
52
|
+
'ぶっ放されること' => 3,
|
53
|
+
'会話されること' => 3,
|
54
|
+
'ご連絡されること' => 4
|
55
|
+
}
|
56
|
+
end
|
57
|
+
|
58
|
+
it 'takes a successive verb' do
|
59
|
+
@pairs = {
|
60
|
+
'話し続けること' => 2,
|
61
|
+
'ぶっ話し続けること' => 3,
|
62
|
+
'会話し続けること' => 3,
|
63
|
+
'ご連絡し続けること' => 4
|
64
|
+
}
|
65
|
+
end
|
66
|
+
|
67
|
+
it 'takes a progressive verb' do
|
68
|
+
@pairs = {
|
69
|
+
'話していること' => 3,
|
70
|
+
'話してること' => 2,
|
71
|
+
'ぶっ話していること' => 4,
|
72
|
+
'ぶっ話してること' => 3,
|
73
|
+
'会話していること' => 4,
|
74
|
+
'会話してること' => 3,
|
75
|
+
'ご連絡していること' => 5,
|
76
|
+
'ご連絡してること' => 4
|
77
|
+
}
|
78
|
+
end
|
79
|
+
|
80
|
+
it 'takes a negative verb' do
|
81
|
+
@pairs = {
|
82
|
+
'話さないこと' => 2,
|
83
|
+
'ぶっ話さないこと' => 3,
|
84
|
+
'会話しないこと' => 3,
|
85
|
+
'ご連絡しないこと' => 4
|
86
|
+
}
|
87
|
+
end
|
88
|
+
|
89
|
+
it 'takes an aggressive verb' do
|
90
|
+
@pairs = {
|
91
|
+
'話したいこと' => 2,
|
92
|
+
'ぶっ話したいこと' => 3,
|
93
|
+
'会話したいこと' => 3,
|
94
|
+
'ご連絡したいこと' => 4
|
95
|
+
}
|
96
|
+
end
|
97
|
+
|
98
|
+
it 'takes a perfective verb' do
|
99
|
+
@pairs = {
|
100
|
+
'話したこと' => 2,
|
101
|
+
'ぶっ話したこと' => 3,
|
102
|
+
'会話したこと' => 3,
|
103
|
+
'ご連絡したこと' => 4
|
104
|
+
}
|
105
|
+
end
|
106
|
+
|
107
|
+
it 'takes a complex verb' do
|
108
|
+
@pairs = {
|
109
|
+
'話し続けていたくなかったこと' => 7,
|
110
|
+
'ぶっ話し続けていたくなかったこと' => 8,
|
111
|
+
'会話し続けていたくなかったこと' => 8,
|
112
|
+
'ご連絡し続けていたくなかったこと' => 9
|
113
|
+
}
|
114
|
+
end
|
115
|
+
|
116
|
+
it 'takes a verb by other' do
|
117
|
+
@pairs = {
|
118
|
+
'話しましょう' => 3,
|
119
|
+
'話さぬこと' => 2
|
120
|
+
}
|
121
|
+
end
|
122
|
+
|
123
|
+
it 'does not take special verbs' do
|
124
|
+
@pairs = {
|
125
|
+
'しましょう' => 0,
|
126
|
+
'ぶっしましょう' => 0,
|
127
|
+
'なるでしょう' => 0,
|
128
|
+
'ぶちなること' => 0,
|
129
|
+
'思い続けていること' => 0,
|
130
|
+
'ぶっ思います' => 0,
|
131
|
+
'おもわれたいこと' => 0,
|
132
|
+
'ぶちおもわない' => 0
|
133
|
+
}
|
134
|
+
end
|
135
|
+
end
|
136
|
+
|
137
|
+
describe Langue::Japanese::Verb, '#key_morpheme' do
|
138
|
+
it 'returns the categorematic verb or the noncategorematic verb' do
|
139
|
+
{
|
140
|
+
'話す' => 0,
|
141
|
+
'話し続けている' => 1,
|
142
|
+
'話される' => 0,
|
143
|
+
'話してる' => 0,
|
144
|
+
'話している' => 0,
|
145
|
+
'話しとる' => 0,
|
146
|
+
'話しちゃう' => 0
|
147
|
+
}.each do |text, index|
|
148
|
+
word = verb(text)
|
149
|
+
word.key_morpheme.should == word[index]
|
150
|
+
end
|
151
|
+
end
|
152
|
+
|
153
|
+
context 'with an empty word' do
|
154
|
+
it 'returns nil' do
|
155
|
+
word = described_class.new
|
156
|
+
word.key_morpheme.should be_nil
|
157
|
+
end
|
158
|
+
end
|
159
|
+
end
|
160
|
+
|
161
|
+
describe Langue::Japanese::Verb, '#prefix' do
|
162
|
+
it 'returns the prefix' do
|
163
|
+
verb('ぶっぶち話さない').prefix.should == 'ぶっぶち'
|
164
|
+
verb('超ご連絡しない').prefix.should == '超ご'
|
165
|
+
end
|
166
|
+
end
|
167
|
+
|
168
|
+
describe Langue::Japanese::Verb, '#body' do
|
169
|
+
it 'returns the text without the prefix and the attribute' do
|
170
|
+
verb('ぶっぶち話さない').body.should == '話す'
|
171
|
+
verb('超ご連絡しない').body.should == '連絡する'
|
172
|
+
end
|
173
|
+
end
|
174
|
+
|
175
|
+
describe Langue::Japanese::Verb, '#progressive?' do
|
176
|
+
it 'returns true if it is progressive' do
|
177
|
+
verb('話している').should be_progressive
|
178
|
+
verb('話してる').should be_progressive
|
179
|
+
verb('話しとる').should be_progressive
|
180
|
+
verb('富んでいる').should be_progressive
|
181
|
+
verb('富んでる').should be_progressive
|
182
|
+
verb('富んどる').should be_progressive
|
183
|
+
end
|
184
|
+
|
185
|
+
it 'returns false if it is not progressive' do
|
186
|
+
verb('話されたくなかった').should_not be_progressive
|
187
|
+
end
|
188
|
+
end
|
189
|
+
|
190
|
+
describe Langue::Japanese::Verb, '#passive?' do
|
191
|
+
it 'returns true if it is passive' do
|
192
|
+
verb('話される').should be_passive
|
193
|
+
verb('富んでられる').should be_passive
|
194
|
+
end
|
195
|
+
|
196
|
+
it 'returns false if it is not passive' do
|
197
|
+
verb('話していたくなかった').should_not be_passive
|
198
|
+
end
|
199
|
+
end
|
200
|
+
|
201
|
+
describe Langue::Japanese::Verb, '#aggressive?' do
|
202
|
+
it 'returns true if it is aggressive' do
|
203
|
+
verb('話したい').should be_aggressive
|
204
|
+
end
|
205
|
+
|
206
|
+
it 'returns false if it is not aggressive' do
|
207
|
+
verb('話されていなかった').should_not be_aggressive
|
208
|
+
end
|
209
|
+
end
|
210
|
+
|
211
|
+
describe Langue::Japanese::Verb, '#negative?' do
|
212
|
+
it 'returns true if it is negative' do
|
213
|
+
verb('話さない').should be_negative
|
214
|
+
verb('話さぬ').should be_negative
|
215
|
+
end
|
216
|
+
|
217
|
+
it 'returns false if it is not negative' do
|
218
|
+
verb('話されていたかった').should_not be_negative
|
219
|
+
end
|
220
|
+
end
|
221
|
+
|
222
|
+
describe Langue::Japanese::Verb, '#perfective?' do
|
223
|
+
it 'returns true if it is perfective' do
|
224
|
+
verb('話した').should be_perfective
|
225
|
+
verb('去りぬ').should be_perfective
|
226
|
+
end
|
227
|
+
|
228
|
+
it 'returns false if it is not perfective' do
|
229
|
+
verb('話されていたくない').should_not be_perfective
|
230
|
+
end
|
231
|
+
end
|
232
|
+
|
233
|
+
describe Langue::Japanese::Verb, '#imperative?' do
|
234
|
+
it 'returns true if it is imperative' do
|
235
|
+
verb('話せ').should be_imperative
|
236
|
+
verb('話してください').should be_imperative
|
237
|
+
end
|
238
|
+
|
239
|
+
it 'returns false if it is not imperative' do
|
240
|
+
verb('話されていたくなかった').should_not be_imperative
|
241
|
+
end
|
242
|
+
end
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,75 @@
|
|
1
|
+
def operator_stub(file_name, class_name)
|
2
|
+
stub.tap do |s|
|
3
|
+
require "langue/japanese/#{file_name}" unless Langue::Japanese.const_defined?(class_name)
|
4
|
+
Langue::Japanese.const_get(class_name).stub!(:new).and_return(s)
|
5
|
+
yield s
|
6
|
+
end
|
7
|
+
end
|
8
|
+
|
9
|
+
def parser_stub
|
10
|
+
operator_stub('parser', :Parser) do |s|
|
11
|
+
s.stub!(:parse).and_return('value returning from parse method')
|
12
|
+
yield s if block_given?
|
13
|
+
end
|
14
|
+
end
|
15
|
+
|
16
|
+
def shaper_stub
|
17
|
+
operator_stub('shaper', :Shaper) do |s|
|
18
|
+
s.stub!(:shape_person_name).and_return('value returning from shape_person_name method')
|
19
|
+
yield s if block_given?
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
def structurer_stub
|
24
|
+
operator_stub('structurer', :Structurer) do |s|
|
25
|
+
s.stub!(:structure).and_return('value returning from structure method')
|
26
|
+
yield s if block_given?
|
27
|
+
end
|
28
|
+
end
|
29
|
+
|
30
|
+
def tagger_stub(nodes = nil)
|
31
|
+
stub.tap do |s|
|
32
|
+
MeCab::Tagger.stub!(:new).and_return(s)
|
33
|
+
|
34
|
+
if nodes
|
35
|
+
node = make_node('')
|
36
|
+
nodes.times { |i| node = make_node(nodes - i, node) }
|
37
|
+
s.stub!(:parseToNode).and_return(make_node('', node))
|
38
|
+
end
|
39
|
+
|
40
|
+
yield s if block_given?
|
41
|
+
end
|
42
|
+
end
|
43
|
+
|
44
|
+
def make_node(surface, next_node = nil)
|
45
|
+
stub.tap do |s|
|
46
|
+
s.stub!(:surface).and_return(surface.to_s)
|
47
|
+
s.stub!(:feature).and_return('part_of_speech,category1,*,*,*,*,*,*')
|
48
|
+
s.stub!(:next).and_return(next_node)
|
49
|
+
end
|
50
|
+
end
|
51
|
+
|
52
|
+
def parser
|
53
|
+
require 'langue/japanese/parser' unless defined? Langue::Japanese::Parser
|
54
|
+
Langue::Japanese::Parser.new
|
55
|
+
end
|
56
|
+
|
57
|
+
def adjective(text)
|
58
|
+
morphemes = parser.parse(text)
|
59
|
+
Langue::Japanese::Adjective.new(morphemes)
|
60
|
+
end
|
61
|
+
|
62
|
+
def adjective_noun(text)
|
63
|
+
morphemes = parser.parse(text)
|
64
|
+
Langue::Japanese::AdjectiveNoun.new(morphemes)
|
65
|
+
end
|
66
|
+
|
67
|
+
def verb(text)
|
68
|
+
morphemes = parser.parse(text)
|
69
|
+
Langue::Japanese::Verb.new(morphemes)
|
70
|
+
end
|
71
|
+
|
72
|
+
def period(text)
|
73
|
+
morphemes = parser.parse(text)
|
74
|
+
Langue::Japanese::Period.new(morphemes)
|
75
|
+
end
|
metadata
ADDED
@@ -0,0 +1,131 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: langue-japanese
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.2
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Takahiro Kondo
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2012-04-13 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: langue
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '0'
|
22
|
+
type: :runtime
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ! '>='
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '0'
|
30
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: activesupport
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
33
|
+
none: false
|
34
|
+
requirements:
|
35
|
+
- - ! '>='
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: '0'
|
38
|
+
type: :runtime
|
39
|
+
prerelease: false
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ! '>='
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: '0'
|
46
|
+
- !ruby/object:Gem::Dependency
|
47
|
+
name: rspec
|
48
|
+
requirement: !ruby/object:Gem::Requirement
|
49
|
+
none: false
|
50
|
+
requirements:
|
51
|
+
- - ! '>='
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: '0'
|
54
|
+
type: :development
|
55
|
+
prerelease: false
|
56
|
+
version_requirements: !ruby/object:Gem::Requirement
|
57
|
+
none: false
|
58
|
+
requirements:
|
59
|
+
- - ! '>='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
description: It provides the operations to Japanese.
|
63
|
+
email:
|
64
|
+
- kondo@atedesign.net
|
65
|
+
executables: []
|
66
|
+
extensions: []
|
67
|
+
extra_rdoc_files: []
|
68
|
+
files:
|
69
|
+
- .gitignore
|
70
|
+
- Gemfile
|
71
|
+
- LICENSE
|
72
|
+
- README.md
|
73
|
+
- Rakefile
|
74
|
+
- langue-japanese.gemspec
|
75
|
+
- lib/langue-japanese.rb
|
76
|
+
- lib/langue/japanese.rb
|
77
|
+
- lib/langue/japanese/language.rb
|
78
|
+
- lib/langue/japanese/logging.rb
|
79
|
+
- lib/langue/japanese/parser.rb
|
80
|
+
- lib/langue/japanese/shaper.rb
|
81
|
+
- lib/langue/japanese/structurer.rb
|
82
|
+
- lib/langue/japanese/version.rb
|
83
|
+
- lib/langue/japanese/words/adjective.rb
|
84
|
+
- lib/langue/japanese/words/adjective_noun.rb
|
85
|
+
- lib/langue/japanese/words/attribute.rb
|
86
|
+
- lib/langue/japanese/words/classifier.rb
|
87
|
+
- lib/langue/japanese/words/morpheme_filter.rb
|
88
|
+
- lib/langue/japanese/words/noun.rb
|
89
|
+
- lib/langue/japanese/words/period.rb
|
90
|
+
- lib/langue/japanese/words/prefix.rb
|
91
|
+
- lib/langue/japanese/words/pronoun.rb
|
92
|
+
- lib/langue/japanese/words/verb.rb
|
93
|
+
- spec/langue/japanese/data.yaml
|
94
|
+
- spec/langue/japanese/language_spec.rb
|
95
|
+
- spec/langue/japanese/parser_spec.rb
|
96
|
+
- spec/langue/japanese/shaper_spec.rb
|
97
|
+
- spec/langue/japanese/structurer_spec.rb
|
98
|
+
- spec/langue/japanese/words/adjective_noun_spec.rb
|
99
|
+
- spec/langue/japanese/words/adjective_spec.rb
|
100
|
+
- spec/langue/japanese/words/noun_spec.rb
|
101
|
+
- spec/langue/japanese/words/period_spec.rb
|
102
|
+
- spec/langue/japanese/words/pronoun_spec.rb
|
103
|
+
- spec/langue/japanese/words/verb_spec.rb
|
104
|
+
- spec/langue/japanese_spec.rb
|
105
|
+
- spec/spec_helper.rb
|
106
|
+
homepage: ''
|
107
|
+
licenses: []
|
108
|
+
post_install_message:
|
109
|
+
rdoc_options: []
|
110
|
+
require_paths:
|
111
|
+
- lib
|
112
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
113
|
+
none: false
|
114
|
+
requirements:
|
115
|
+
- - ! '>='
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: '0'
|
118
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
119
|
+
none: false
|
120
|
+
requirements:
|
121
|
+
- - ! '>='
|
122
|
+
- !ruby/object:Gem::Version
|
123
|
+
version: '0'
|
124
|
+
requirements: []
|
125
|
+
rubyforge_project:
|
126
|
+
rubygems_version: 1.8.21
|
127
|
+
signing_key:
|
128
|
+
specification_version: 3
|
129
|
+
summary: The foundation for Japanese
|
130
|
+
test_files: []
|
131
|
+
has_rdoc:
|