infoboxer 0.1.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (61) hide show
  1. checksums.yaml +7 -0
  2. data/.dokaz +1 -0
  3. data/.yardopts +1 -0
  4. data/LICENSE.txt +22 -0
  5. data/Parsing.md +33 -0
  6. data/README.md +115 -0
  7. data/examples/output/.gitkeep +0 -0
  8. data/examples/pages/argentina.wiki +808 -0
  9. data/examples/to_text.rb +8 -0
  10. data/examples/tree.rb +8 -0
  11. data/infoboxer.gemspec +43 -0
  12. data/lib/infoboxer.rb +196 -0
  13. data/lib/infoboxer/core_ext.rb +10 -0
  14. data/lib/infoboxer/definitions/en.wikipedia.org.rb +355 -0
  15. data/lib/infoboxer/media_wiki.rb +162 -0
  16. data/lib/infoboxer/media_wiki/page.rb +38 -0
  17. data/lib/infoboxer/media_wiki/traits.rb +60 -0
  18. data/lib/infoboxer/navigation.rb +84 -0
  19. data/lib/infoboxer/navigation/lookup.rb +216 -0
  20. data/lib/infoboxer/navigation/sections.rb +179 -0
  21. data/lib/infoboxer/navigation/selector.rb +59 -0
  22. data/lib/infoboxer/navigation/shortcuts.rb +165 -0
  23. data/lib/infoboxer/parser.rb +71 -0
  24. data/lib/infoboxer/parser/context.rb +165 -0
  25. data/lib/infoboxer/parser/html.rb +58 -0
  26. data/lib/infoboxer/parser/image.rb +59 -0
  27. data/lib/infoboxer/parser/inline.rb +142 -0
  28. data/lib/infoboxer/parser/paragraphs.rb +66 -0
  29. data/lib/infoboxer/parser/table.rb +132 -0
  30. data/lib/infoboxer/parser/template.rb +47 -0
  31. data/lib/infoboxer/parser/util.rb +73 -0
  32. data/lib/infoboxer/templates.rb +10 -0
  33. data/lib/infoboxer/templates/base.rb +82 -0
  34. data/lib/infoboxer/templates/set.rb +72 -0
  35. data/lib/infoboxer/tree.rb +70 -0
  36. data/lib/infoboxer/tree/compound.rb +81 -0
  37. data/lib/infoboxer/tree/document.rb +11 -0
  38. data/lib/infoboxer/tree/html.rb +76 -0
  39. data/lib/infoboxer/tree/image.rb +53 -0
  40. data/lib/infoboxer/tree/inline.rb +39 -0
  41. data/lib/infoboxer/tree/list.rb +160 -0
  42. data/lib/infoboxer/tree/node.rb +181 -0
  43. data/lib/infoboxer/tree/nodes.rb +185 -0
  44. data/lib/infoboxer/tree/paragraphs.rb +122 -0
  45. data/lib/infoboxer/tree/ref.rb +34 -0
  46. data/lib/infoboxer/tree/table.rb +89 -0
  47. data/lib/infoboxer/tree/template.rb +82 -0
  48. data/lib/infoboxer/tree/text.rb +60 -0
  49. data/lib/infoboxer/tree/wikilink.rb +83 -0
  50. data/lib/infoboxer/version.rb +4 -0
  51. data/profile/out/.gitkeep +0 -0
  52. data/profile/pages/argentina.txt +808 -0
  53. data/profile/pages/canada.wiki +544 -0
  54. data/profile/pages/ukraine.wiki +1006 -0
  55. data/profile/pages/usa.wiki +843 -0
  56. data/regression/pages/canada.wiki +544 -0
  57. data/regression/pages/chiang_mai.wiki +2615 -0
  58. data/regression/pages/south_america.wiki +640 -0
  59. data/regression/pages/ukraine.wiki +1006 -0
  60. data/regression/pages/usa.wiki +843 -0
  61. metadata +272 -0
metadata ADDED
@@ -0,0 +1,272 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: infoboxer
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.1.0
5
+ platform: ruby
6
+ authors:
7
+ - Victor Shepelev
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2015-08-07 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ name: htmlentities
15
+ requirement: !ruby/object:Gem::Requirement
16
+ requirements:
17
+ - - ">="
18
+ - !ruby/object:Gem::Version
19
+ version: '0'
20
+ type: :runtime
21
+ prerelease: false
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - ">="
25
+ - !ruby/object:Gem::Version
26
+ version: '0'
27
+ - !ruby/object:Gem::Dependency
28
+ name: procme
29
+ requirement: !ruby/object:Gem::Requirement
30
+ requirements:
31
+ - - ">="
32
+ - !ruby/object:Gem::Version
33
+ version: '0'
34
+ type: :runtime
35
+ prerelease: false
36
+ version_requirements: !ruby/object:Gem::Requirement
37
+ requirements:
38
+ - - ">="
39
+ - !ruby/object:Gem::Version
40
+ version: '0'
41
+ - !ruby/object:Gem::Dependency
42
+ name: rest-client
43
+ requirement: !ruby/object:Gem::Requirement
44
+ requirements:
45
+ - - ">="
46
+ - !ruby/object:Gem::Version
47
+ version: '0'
48
+ type: :runtime
49
+ prerelease: false
50
+ version_requirements: !ruby/object:Gem::Requirement
51
+ requirements:
52
+ - - ">="
53
+ - !ruby/object:Gem::Version
54
+ version: '0'
55
+ - !ruby/object:Gem::Dependency
56
+ name: addressable
57
+ requirement: !ruby/object:Gem::Requirement
58
+ requirements:
59
+ - - ">="
60
+ - !ruby/object:Gem::Version
61
+ version: '0'
62
+ type: :runtime
63
+ prerelease: false
64
+ version_requirements: !ruby/object:Gem::Requirement
65
+ requirements:
66
+ - - ">="
67
+ - !ruby/object:Gem::Version
68
+ version: '0'
69
+ - !ruby/object:Gem::Dependency
70
+ name: terminal-table
71
+ requirement: !ruby/object:Gem::Requirement
72
+ requirements:
73
+ - - ">="
74
+ - !ruby/object:Gem::Version
75
+ version: '0'
76
+ type: :runtime
77
+ prerelease: false
78
+ version_requirements: !ruby/object:Gem::Requirement
79
+ requirements:
80
+ - - ">="
81
+ - !ruby/object:Gem::Version
82
+ version: '0'
83
+ - !ruby/object:Gem::Dependency
84
+ name: backports
85
+ requirement: !ruby/object:Gem::Requirement
86
+ requirements:
87
+ - - ">="
88
+ - !ruby/object:Gem::Version
89
+ version: '0'
90
+ type: :runtime
91
+ prerelease: false
92
+ version_requirements: !ruby/object:Gem::Requirement
93
+ requirements:
94
+ - - ">="
95
+ - !ruby/object:Gem::Version
96
+ version: '0'
97
+ - !ruby/object:Gem::Dependency
98
+ name: rake
99
+ requirement: !ruby/object:Gem::Requirement
100
+ requirements:
101
+ - - ">="
102
+ - !ruby/object:Gem::Version
103
+ version: '0'
104
+ type: :development
105
+ prerelease: false
106
+ version_requirements: !ruby/object:Gem::Requirement
107
+ requirements:
108
+ - - ">="
109
+ - !ruby/object:Gem::Version
110
+ version: '0'
111
+ - !ruby/object:Gem::Dependency
112
+ name: rspec
113
+ requirement: !ruby/object:Gem::Requirement
114
+ requirements:
115
+ - - "~>"
116
+ - !ruby/object:Gem::Version
117
+ version: '3'
118
+ type: :development
119
+ prerelease: false
120
+ version_requirements: !ruby/object:Gem::Requirement
121
+ requirements:
122
+ - - "~>"
123
+ - !ruby/object:Gem::Version
124
+ version: '3'
125
+ - !ruby/object:Gem::Dependency
126
+ name: rspec-its
127
+ requirement: !ruby/object:Gem::Requirement
128
+ requirements:
129
+ - - "~>"
130
+ - !ruby/object:Gem::Version
131
+ version: '1'
132
+ type: :development
133
+ prerelease: false
134
+ version_requirements: !ruby/object:Gem::Requirement
135
+ requirements:
136
+ - - "~>"
137
+ - !ruby/object:Gem::Version
138
+ version: '1'
139
+ - !ruby/object:Gem::Dependency
140
+ name: ruby-prof
141
+ requirement: !ruby/object:Gem::Requirement
142
+ requirements:
143
+ - - ">="
144
+ - !ruby/object:Gem::Version
145
+ version: '0'
146
+ type: :development
147
+ prerelease: false
148
+ version_requirements: !ruby/object:Gem::Requirement
149
+ requirements:
150
+ - - ">="
151
+ - !ruby/object:Gem::Version
152
+ version: '0'
153
+ - !ruby/object:Gem::Dependency
154
+ name: vcr
155
+ requirement: !ruby/object:Gem::Requirement
156
+ requirements:
157
+ - - ">="
158
+ - !ruby/object:Gem::Version
159
+ version: '0'
160
+ type: :development
161
+ prerelease: false
162
+ version_requirements: !ruby/object:Gem::Requirement
163
+ requirements:
164
+ - - ">="
165
+ - !ruby/object:Gem::Version
166
+ version: '0'
167
+ - !ruby/object:Gem::Dependency
168
+ name: webmock
169
+ requirement: !ruby/object:Gem::Requirement
170
+ requirements:
171
+ - - ">="
172
+ - !ruby/object:Gem::Version
173
+ version: '0'
174
+ type: :development
175
+ prerelease: false
176
+ version_requirements: !ruby/object:Gem::Requirement
177
+ requirements:
178
+ - - ">="
179
+ - !ruby/object:Gem::Version
180
+ version: '0'
181
+ description: |2
182
+ Infoboxer is library targeting use of Wikipedia (or any other
183
+ MediaWiki-based wiki) as a rich powerful data source.
184
+ email: zverok.offline@gmail.com
185
+ executables: []
186
+ extensions: []
187
+ extra_rdoc_files: []
188
+ files:
189
+ - ".dokaz"
190
+ - ".yardopts"
191
+ - LICENSE.txt
192
+ - Parsing.md
193
+ - README.md
194
+ - examples/output/.gitkeep
195
+ - examples/pages/argentina.wiki
196
+ - examples/to_text.rb
197
+ - examples/tree.rb
198
+ - infoboxer.gemspec
199
+ - lib/infoboxer.rb
200
+ - lib/infoboxer/core_ext.rb
201
+ - lib/infoboxer/definitions/en.wikipedia.org.rb
202
+ - lib/infoboxer/media_wiki.rb
203
+ - lib/infoboxer/media_wiki/page.rb
204
+ - lib/infoboxer/media_wiki/traits.rb
205
+ - lib/infoboxer/navigation.rb
206
+ - lib/infoboxer/navigation/lookup.rb
207
+ - lib/infoboxer/navigation/sections.rb
208
+ - lib/infoboxer/navigation/selector.rb
209
+ - lib/infoboxer/navigation/shortcuts.rb
210
+ - lib/infoboxer/parser.rb
211
+ - lib/infoboxer/parser/context.rb
212
+ - lib/infoboxer/parser/html.rb
213
+ - lib/infoboxer/parser/image.rb
214
+ - lib/infoboxer/parser/inline.rb
215
+ - lib/infoboxer/parser/paragraphs.rb
216
+ - lib/infoboxer/parser/table.rb
217
+ - lib/infoboxer/parser/template.rb
218
+ - lib/infoboxer/parser/util.rb
219
+ - lib/infoboxer/templates.rb
220
+ - lib/infoboxer/templates/base.rb
221
+ - lib/infoboxer/templates/set.rb
222
+ - lib/infoboxer/tree.rb
223
+ - lib/infoboxer/tree/compound.rb
224
+ - lib/infoboxer/tree/document.rb
225
+ - lib/infoboxer/tree/html.rb
226
+ - lib/infoboxer/tree/image.rb
227
+ - lib/infoboxer/tree/inline.rb
228
+ - lib/infoboxer/tree/list.rb
229
+ - lib/infoboxer/tree/node.rb
230
+ - lib/infoboxer/tree/nodes.rb
231
+ - lib/infoboxer/tree/paragraphs.rb
232
+ - lib/infoboxer/tree/ref.rb
233
+ - lib/infoboxer/tree/table.rb
234
+ - lib/infoboxer/tree/template.rb
235
+ - lib/infoboxer/tree/text.rb
236
+ - lib/infoboxer/tree/wikilink.rb
237
+ - lib/infoboxer/version.rb
238
+ - profile/out/.gitkeep
239
+ - profile/pages/argentina.txt
240
+ - profile/pages/canada.wiki
241
+ - profile/pages/ukraine.wiki
242
+ - profile/pages/usa.wiki
243
+ - regression/pages/canada.wiki
244
+ - regression/pages/chiang_mai.wiki
245
+ - regression/pages/south_america.wiki
246
+ - regression/pages/ukraine.wiki
247
+ - regression/pages/usa.wiki
248
+ homepage: https://github.com/zverok/infoboxer
249
+ licenses:
250
+ - MIT
251
+ metadata: {}
252
+ post_install_message:
253
+ rdoc_options: []
254
+ require_paths:
255
+ - lib
256
+ required_ruby_version: !ruby/object:Gem::Requirement
257
+ requirements:
258
+ - - ">="
259
+ - !ruby/object:Gem::Version
260
+ version: '0'
261
+ required_rubygems_version: !ruby/object:Gem::Requirement
262
+ requirements:
263
+ - - ">="
264
+ - !ruby/object:Gem::Version
265
+ version: '0'
266
+ requirements: []
267
+ rubyforge_project:
268
+ rubygems_version: 2.4.6
269
+ signing_key:
270
+ specification_version: 4
271
+ summary: MediaWiki client and parser, targeting information extraction.
272
+ test_files: []