proiel 1.1.0 → 1.3.1

Sign up to get free protection for your applications and to get access to all the features.
Files changed (37) hide show
  1. checksums.yaml +5 -5
  2. data/LICENSE +1 -1
  3. data/README.md +2 -2
  4. data/lib/proiel.rb +16 -1
  5. data/lib/proiel/alignment.rb +3 -0
  6. data/lib/proiel/alignment/builder.rb +220 -0
  7. data/lib/proiel/annotation_schema.rb +11 -4
  8. data/lib/proiel/chronology.rb +80 -0
  9. data/lib/proiel/dictionary.rb +79 -0
  10. data/lib/proiel/dictionary/builder.rb +224 -0
  11. data/lib/proiel/div.rb +22 -3
  12. data/lib/proiel/language.rb +108 -0
  13. data/lib/proiel/lemma.rb +77 -0
  14. data/lib/proiel/proiel_xml/proiel-3.0/proiel-3.0.xsd +383 -0
  15. data/lib/proiel/proiel_xml/reader.rb +138 -2
  16. data/lib/proiel/proiel_xml/schema.rb +4 -2
  17. data/lib/proiel/proiel_xml/validator.rb +76 -9
  18. data/lib/proiel/sentence.rb +27 -4
  19. data/lib/proiel/source.rb +14 -4
  20. data/lib/proiel/statistics.rb +2 -2
  21. data/lib/proiel/token.rb +14 -6
  22. data/lib/proiel/tokenization.rb +5 -3
  23. data/lib/proiel/treebank.rb +23 -6
  24. data/lib/proiel/utils.rb +0 -1
  25. data/lib/proiel/valency.rb +5 -0
  26. data/lib/proiel/valency/arguments.rb +151 -0
  27. data/lib/proiel/valency/lexicon.rb +59 -0
  28. data/lib/proiel/valency/obliqueness.rb +31 -0
  29. data/lib/proiel/version.rb +2 -3
  30. data/lib/proiel/visualization.rb +1 -0
  31. data/lib/proiel/visualization/graphviz.rb +111 -0
  32. data/lib/proiel/visualization/graphviz/aligned-modern.dot.erb +83 -0
  33. data/lib/proiel/visualization/graphviz/classic.dot.erb +24 -0
  34. data/lib/proiel/visualization/graphviz/linearized.dot.erb +57 -0
  35. data/lib/proiel/visualization/graphviz/modern.dot.erb +39 -0
  36. data/lib/proiel/visualization/graphviz/packed.dot.erb +25 -0
  37. metadata +76 -31
@@ -0,0 +1,24 @@
1
+ digraph "<%= @title -%>" {
2
+ charset="UTF-8";
3
+ graph [truecolor=true,bgcolor=transparent];
4
+ root [label="",shape=circle];
5
+ rankdir="<%= @direction -%>";
6
+
7
+ <%- @graph.tokens.select { |t| t.empty_token_sort != 'P' }.each do |token| -%>
8
+ <%- if token.empty_token_sort == 'C' or token.part_of_speech == 'C-' -%>
9
+ <%= node token.id, token.form || token.empty_token_sort, shape: :diamond -%>
10
+ <%- elsif token.is_empty? -%>
11
+ <%= node token.id, token.empty_token_sort, shape: :circle -%>
12
+ <%- else -%>
13
+ <%= node token.id, token.form, shape: :box -%>
14
+ <%- end -%>
15
+
16
+ <%- if token.relation -%>
17
+ <%= edge (token.head ? token.head.id : :root), token.id, token.relation.to_s.upcase, weight: 1.0, color: :orange -%>
18
+ <%- end -%>
19
+
20
+ <%- token.slashes.each do |(relation, target)| -%>
21
+ <%= edge token.id, target, relation.to_s.upcase, weight: 0.0, color: :blue, style: :dashed %>
22
+ <%- end -%>
23
+ <%- end -%>
24
+ }
@@ -0,0 +1,57 @@
1
+ digraph "<%= @title -%>" {
2
+ charset="UTF-8";
3
+ ranksep=.0005;
4
+ nodesep=.05;
5
+ graph [truecolor=true,bgcolor=transparent];
6
+ rankdir="<%= @direction -%>";
7
+
8
+ node [shape=none]; {
9
+ depthR ->
10
+ <% (0..@sentence.max_depth).each do |depth| %>
11
+ depth<%= depth %> ->
12
+ <% end %>
13
+ WORDS [style=invis];
14
+ }
15
+
16
+ node [shape=point]; {
17
+ rank = same;
18
+ depthR [label=""];
19
+ root;
20
+ }
21
+
22
+ <% @graph.tokens.select { |t| t.empty_token_sort != 'P' }.inject({}) { |k, e| (k[e.depth] ||= []) << e; k }.sort.each do |depth, tokens| %>
23
+ node [shape=point]; {
24
+ rank = same;
25
+ <%= node "depth#{depth}" %>
26
+ <% tokens.each do |t| %>
27
+ <%= node t.id %>
28
+ <% end %>
29
+ }
30
+ <% end %>
31
+
32
+ node [shape=none]; {
33
+ rank = same;
34
+ WORDS [label=""];
35
+ <% @graph.tokens.select { |t| t.empty_token_sort != 'P' }.reject { |t| t.is_empty? }.sort_by { |t| t.token_number }.each do |t| %>
36
+ <%= node "f#{t.id}", t.form %>
37
+ <% end %>
38
+ }
39
+
40
+ <% @graph.tokens.select { |t| t.empty_token_sort != 'P' }.each do |t| %>
41
+ <% if t.relation %>
42
+ <%= edge (t.head ? t.head.id : :root), t.id, t.relation.to_s.upcase, fontcolor: :black, fontsize: 10 %>
43
+ <% end %>
44
+
45
+ <% unless t.is_empty? %>
46
+ <%= edge "f#{t.id}", t.id, '', arrowhead: :none, color: :lightgrey %>
47
+ <% end %>
48
+
49
+ <% t.slashes.each do |(relation, target)| %>
50
+ <%= edge t.id, target, relation.to_s.upcase, color: :blue, weight: 0.0, style: :dotted, fontsize: 10 %>
51
+ <% end %>
52
+ <% end %>
53
+
54
+ <% @graph.tokens.select { |t| t.empty_token_sort.blank? }.sort_by(&:token_number).each_cons(2) do |n1, n2| %>
55
+ <%= edge "f#{n1.id}", "f#{n2.id}", '', weight: 10.0, style: :invis %>
56
+ <% end %>
57
+ }
@@ -0,0 +1,39 @@
1
+ digraph "<%= @title -%>" {
2
+ charset="UTF-8";
3
+ graph [truecolor=true,bgcolor=transparent];
4
+ rankdir="<%= @direction -%>";
5
+ nodesep=0.1;
6
+ ranksep=0.25;
7
+
8
+ root [label="",shape=point];
9
+
10
+ <%- @graph.tokens.select { |t| t.empty_token_sort != 'P' }.each do |token| -%>
11
+ <%- if token.empty_token_sort -%>
12
+ <%= node token.id, token.relation.to_s.upcase, shape: :none, fontcolor: :gray -%>
13
+ <%- else -%>
14
+ <%= node token.id, token.relation.to_s.upcase, shape: :none -%>
15
+ <%- end -%>
16
+
17
+ <%- if token.relation -%>
18
+ <%= edge (token.head ? token.head.id : :root), token.id, '', weight: 1.0, color: :orange, arrowhead: :none -%>
19
+ <%- end -%>
20
+
21
+ <%- token.slashes.each do |(relation, target)| -%>
22
+ <%= edge token.id, target, relation.to_s.upcase, weight: 0.0, fontcolor: :blue,color: :blue, style: :dashed %>
23
+ <%- end -%>
24
+ <%- end -%>
25
+
26
+ <%- @graph.tokens.reject(&:empty_token_sort).each do |token| -%>
27
+ <%= edge token.id, "T#{token.id}", nil, weight: 10, arrowhead: :none -%>
28
+ <%- end -%>
29
+
30
+ {
31
+ rank="same";
32
+
33
+ <%- @graph.tokens.reject(&:empty_token_sort).each do |token| -%>
34
+ <%= node "T#{token.id}", token.form, shape: :none, fontcolor: :blue, tooltip: [token.lemma, token.part_of_speech, token.morphology].join("\n") -%>
35
+ <%- end -%>
36
+
37
+ <%= @graph.tokens.reject(&:empty_token_sort).map { |token| "T#{token.id}" }.join('->') -%> [style="invis"];
38
+ }
39
+ }
@@ -0,0 +1,25 @@
1
+ digraph "<%= @title -%>" {
2
+ charset="UTF-8";
3
+ graph [truecolor=true,bgcolor=transparent];
4
+ rankdir="<%= @direction -%>";
5
+
6
+ root [label="",shape=none];
7
+
8
+ <% @graph.tokens.each do |token| %>
9
+ <% if token.conjunction? %>
10
+ <%= node token.id, token.form || token.empty_token_sort, shape: :none %>
11
+ <% elsif token.is_empty? %>
12
+ <%= node token.id, token.empty_token_sort, shape: :none %>
13
+ <% else %>
14
+ <%= node token.id, token.form, shape: :none %>
15
+ <% end %>
16
+
17
+ <% if token.relation %>
18
+ <%= edge (token.head ? token.head.id : :root), token.id, token.relation.to_s.upcase, weight: 0.0, color: :purple %>
19
+ <% end %>
20
+
21
+ <% token.slashes.each do |(relation, target)| %>
22
+ <%= edge token.id, target, relation.to_s.upcase, weight: 0.0, color: :purple, style: :dashed %>
23
+ <% end %>
24
+ <% end %>
25
+ }
metadata CHANGED
@@ -1,43 +1,71 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: proiel
3
3
  version: !ruby/object:Gem::Version
4
- version: 1.1.0
4
+ version: 1.3.1
5
5
  platform: ruby
6
6
  authors:
7
7
  - Marius L. Jøhndal
8
- autorequire:
8
+ autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2016-06-04 00:00:00.000000000 Z
11
+ date: 2020-07-05 00:00:00.000000000 Z
12
12
  dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ name: builder
15
+ requirement: !ruby/object:Gem::Requirement
16
+ requirements:
17
+ - - "~>"
18
+ - !ruby/object:Gem::Version
19
+ version: 3.2.4
20
+ type: :runtime
21
+ prerelease: false
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - "~>"
25
+ - !ruby/object:Gem::Version
26
+ version: 3.2.4
13
27
  - !ruby/object:Gem::Dependency
14
28
  name: json
15
29
  requirement: !ruby/object:Gem::Requirement
16
30
  requirements:
17
31
  - - "~>"
18
32
  - !ruby/object:Gem::Version
19
- version: '1.8'
33
+ version: 2.3.0
34
+ type: :runtime
35
+ prerelease: false
36
+ version_requirements: !ruby/object:Gem::Requirement
37
+ requirements:
38
+ - - "~>"
39
+ - !ruby/object:Gem::Version
40
+ version: 2.3.0
41
+ - !ruby/object:Gem::Dependency
42
+ name: memoist
43
+ requirement: !ruby/object:Gem::Requirement
44
+ requirements:
45
+ - - "~>"
46
+ - !ruby/object:Gem::Version
47
+ version: 0.16.2
20
48
  type: :runtime
21
49
  prerelease: false
22
50
  version_requirements: !ruby/object:Gem::Requirement
23
51
  requirements:
24
52
  - - "~>"
25
53
  - !ruby/object:Gem::Version
26
- version: '1.8'
54
+ version: 0.16.2
27
55
  - !ruby/object:Gem::Dependency
28
56
  name: nokogiri
29
57
  requirement: !ruby/object:Gem::Requirement
30
58
  requirements:
31
59
  - - "~>"
32
60
  - !ruby/object:Gem::Version
33
- version: 1.6.6
61
+ version: 1.10.9
34
62
  type: :runtime
35
63
  prerelease: false
36
64
  version_requirements: !ruby/object:Gem::Requirement
37
65
  requirements:
38
66
  - - "~>"
39
67
  - !ruby/object:Gem::Version
40
- version: 1.6.6
68
+ version: 1.10.9
41
69
  - !ruby/object:Gem::Dependency
42
70
  name: sax-machine
43
71
  requirement: !ruby/object:Gem::Requirement
@@ -53,103 +81,103 @@ dependencies:
53
81
  - !ruby/object:Gem::Version
54
82
  version: 1.3.2
55
83
  - !ruby/object:Gem::Dependency
56
- name: memoist
84
+ name: bundler
57
85
  requirement: !ruby/object:Gem::Requirement
58
86
  requirements:
59
87
  - - "~>"
60
88
  - !ruby/object:Gem::Version
61
- version: '0.12'
62
- type: :runtime
89
+ version: 2.1.4
90
+ type: :development
63
91
  prerelease: false
64
92
  version_requirements: !ruby/object:Gem::Requirement
65
93
  requirements:
66
94
  - - "~>"
67
95
  - !ruby/object:Gem::Version
68
- version: '0.12'
96
+ version: 2.1.4
69
97
  - !ruby/object:Gem::Dependency
70
- name: bundler
98
+ name: pry
71
99
  requirement: !ruby/object:Gem::Requirement
72
100
  requirements:
73
101
  - - "~>"
74
102
  - !ruby/object:Gem::Version
75
- version: '1.10'
103
+ version: 0.13.1
76
104
  type: :development
77
105
  prerelease: false
78
106
  version_requirements: !ruby/object:Gem::Requirement
79
107
  requirements:
80
108
  - - "~>"
81
109
  - !ruby/object:Gem::Version
82
- version: '1.10'
110
+ version: 0.13.1
83
111
  - !ruby/object:Gem::Dependency
84
112
  name: rake
85
113
  requirement: !ruby/object:Gem::Requirement
86
114
  requirements:
87
115
  - - "~>"
88
116
  - !ruby/object:Gem::Version
89
- version: '10.0'
117
+ version: 13.0.1
90
118
  type: :development
91
119
  prerelease: false
92
120
  version_requirements: !ruby/object:Gem::Requirement
93
121
  requirements:
94
122
  - - "~>"
95
123
  - !ruby/object:Gem::Version
96
- version: '10.0'
124
+ version: 13.0.1
97
125
  - !ruby/object:Gem::Dependency
98
126
  name: rspec
99
127
  requirement: !ruby/object:Gem::Requirement
100
128
  requirements:
101
129
  - - "~>"
102
130
  - !ruby/object:Gem::Version
103
- version: '3.2'
131
+ version: 3.9.0
104
132
  type: :development
105
133
  prerelease: false
106
134
  version_requirements: !ruby/object:Gem::Requirement
107
135
  requirements:
108
136
  - - "~>"
109
137
  - !ruby/object:Gem::Version
110
- version: '3.2'
138
+ version: 3.9.0
111
139
  - !ruby/object:Gem::Dependency
112
- name: pry
140
+ name: rubocop
113
141
  requirement: !ruby/object:Gem::Requirement
114
142
  requirements:
115
143
  - - "~>"
116
144
  - !ruby/object:Gem::Version
117
- version: '0.10'
145
+ version: 0.86.0
118
146
  type: :development
119
147
  prerelease: false
120
148
  version_requirements: !ruby/object:Gem::Requirement
121
149
  requirements:
122
150
  - - "~>"
123
151
  - !ruby/object:Gem::Version
124
- version: '0.10'
152
+ version: 0.86.0
125
153
  - !ruby/object:Gem::Dependency
126
154
  name: simplecov
127
155
  requirement: !ruby/object:Gem::Requirement
128
156
  requirements:
129
157
  - - "~>"
130
158
  - !ruby/object:Gem::Version
131
- version: '0.10'
159
+ version: 0.18.5
132
160
  type: :development
133
161
  prerelease: false
134
162
  version_requirements: !ruby/object:Gem::Requirement
135
163
  requirements:
136
164
  - - "~>"
137
165
  - !ruby/object:Gem::Version
138
- version: '0.10'
166
+ version: 0.18.5
139
167
  - !ruby/object:Gem::Dependency
140
168
  name: yard
141
169
  requirement: !ruby/object:Gem::Requirement
142
170
  requirements:
143
171
  - - "~>"
144
172
  - !ruby/object:Gem::Version
145
- version: 0.8.7
173
+ version: 0.9.25
146
174
  type: :development
147
175
  prerelease: false
148
176
  version_requirements: !ruby/object:Gem::Requirement
149
177
  requirements:
150
178
  - - "~>"
151
179
  - !ruby/object:Gem::Version
152
- version: 0.8.7
180
+ version: 0.9.25
153
181
  description: This provides a library of functions for reading and manipulating treebanks
154
182
  using the PROIEL dependency format.
155
183
  email:
@@ -163,15 +191,23 @@ files:
163
191
  - bin/console
164
192
  - bin/setup
165
193
  - lib/proiel.rb
194
+ - lib/proiel/alignment.rb
195
+ - lib/proiel/alignment/builder.rb
166
196
  - lib/proiel/annotation_schema.rb
197
+ - lib/proiel/chronology.rb
167
198
  - lib/proiel/citations.rb
199
+ - lib/proiel/dictionary.rb
200
+ - lib/proiel/dictionary/builder.rb
168
201
  - lib/proiel/div.rb
202
+ - lib/proiel/language.rb
203
+ - lib/proiel/lemma.rb
169
204
  - lib/proiel/positional_tag.rb
170
205
  - lib/proiel/proiel_xml/proiel-1.0/proiel-1.0.xsd
171
206
  - lib/proiel/proiel_xml/proiel-1.0/teilite.xsd
172
207
  - lib/proiel/proiel_xml/proiel-1.0/xml.xsd
173
208
  - lib/proiel/proiel_xml/proiel-2.0/proiel-2.0.xsd
174
209
  - lib/proiel/proiel_xml/proiel-2.1/proiel-2.1.xsd
210
+ - lib/proiel/proiel_xml/proiel-3.0/proiel-3.0.xsd
175
211
  - lib/proiel/proiel_xml/reader.rb
176
212
  - lib/proiel/proiel_xml/schema.rb
177
213
  - lib/proiel/proiel_xml/validator.rb
@@ -183,12 +219,23 @@ files:
183
219
  - lib/proiel/treebank.rb
184
220
  - lib/proiel/treebank_object.rb
185
221
  - lib/proiel/utils.rb
222
+ - lib/proiel/valency.rb
223
+ - lib/proiel/valency/arguments.rb
224
+ - lib/proiel/valency/lexicon.rb
225
+ - lib/proiel/valency/obliqueness.rb
186
226
  - lib/proiel/version.rb
227
+ - lib/proiel/visualization.rb
228
+ - lib/proiel/visualization/graphviz.rb
229
+ - lib/proiel/visualization/graphviz/aligned-modern.dot.erb
230
+ - lib/proiel/visualization/graphviz/classic.dot.erb
231
+ - lib/proiel/visualization/graphviz/linearized.dot.erb
232
+ - lib/proiel/visualization/graphviz/modern.dot.erb
233
+ - lib/proiel/visualization/graphviz/packed.dot.erb
187
234
  homepage: http://proiel.github.com
188
235
  licenses:
189
236
  - MIT
190
237
  metadata: {}
191
- post_install_message:
238
+ post_install_message:
192
239
  rdoc_options: []
193
240
  require_paths:
194
241
  - lib
@@ -196,17 +243,15 @@ required_ruby_version: !ruby/object:Gem::Requirement
196
243
  requirements:
197
244
  - - ">="
198
245
  - !ruby/object:Gem::Version
199
- version: '2.1'
246
+ version: '2.4'
200
247
  required_rubygems_version: !ruby/object:Gem::Requirement
201
248
  requirements:
202
249
  - - ">="
203
250
  - !ruby/object:Gem::Version
204
251
  version: '0'
205
252
  requirements: []
206
- rubyforge_project:
207
- rubygems_version: 2.5.1
208
- signing_key:
253
+ rubygems_version: 3.1.2
254
+ signing_key:
209
255
  specification_version: 4
210
256
  summary: A library for working with treebanks using the PROIEL dependency format
211
257
  test_files: []
212
- has_rdoc: