cld3 3.1.0

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 (72) hide show
  1. checksums.yaml +7 -0
  2. data/Gemfile +18 -0
  3. data/LICENSE +204 -0
  4. data/LICENSE_CLD3 +203 -0
  5. data/README.md +22 -0
  6. data/cld3.gemspec +35 -0
  7. data/ext/cld3/base.cc +36 -0
  8. data/ext/cld3/base.h +106 -0
  9. data/ext/cld3/casts.h +98 -0
  10. data/ext/cld3/embedding_feature_extractor.cc +51 -0
  11. data/ext/cld3/embedding_feature_extractor.h +182 -0
  12. data/ext/cld3/embedding_network.cc +196 -0
  13. data/ext/cld3/embedding_network.h +186 -0
  14. data/ext/cld3/embedding_network_params.h +285 -0
  15. data/ext/cld3/extconf.rb +49 -0
  16. data/ext/cld3/feature_extractor.cc +137 -0
  17. data/ext/cld3/feature_extractor.h +633 -0
  18. data/ext/cld3/feature_extractor.proto +50 -0
  19. data/ext/cld3/feature_types.cc +72 -0
  20. data/ext/cld3/feature_types.h +158 -0
  21. data/ext/cld3/fixunicodevalue.cc +55 -0
  22. data/ext/cld3/fixunicodevalue.h +69 -0
  23. data/ext/cld3/float16.h +58 -0
  24. data/ext/cld3/fml_parser.cc +308 -0
  25. data/ext/cld3/fml_parser.h +123 -0
  26. data/ext/cld3/generated_entities.cc +296 -0
  27. data/ext/cld3/generated_ulscript.cc +678 -0
  28. data/ext/cld3/generated_ulscript.h +142 -0
  29. data/ext/cld3/getonescriptspan.cc +1109 -0
  30. data/ext/cld3/getonescriptspan.h +124 -0
  31. data/ext/cld3/integral_types.h +37 -0
  32. data/ext/cld3/lang_id_nn_params.cc +57449 -0
  33. data/ext/cld3/lang_id_nn_params.h +178 -0
  34. data/ext/cld3/language_identifier_features.cc +165 -0
  35. data/ext/cld3/language_identifier_features.h +116 -0
  36. data/ext/cld3/nnet_language_identifier.cc +380 -0
  37. data/ext/cld3/nnet_language_identifier.h +175 -0
  38. data/ext/cld3/nnet_language_identifier_c.cc +72 -0
  39. data/ext/cld3/offsetmap.cc +478 -0
  40. data/ext/cld3/offsetmap.h +168 -0
  41. data/ext/cld3/port.h +143 -0
  42. data/ext/cld3/registry.cc +28 -0
  43. data/ext/cld3/registry.h +242 -0
  44. data/ext/cld3/relevant_script_feature.cc +89 -0
  45. data/ext/cld3/relevant_script_feature.h +49 -0
  46. data/ext/cld3/script_detector.h +156 -0
  47. data/ext/cld3/sentence.proto +77 -0
  48. data/ext/cld3/sentence_features.cc +29 -0
  49. data/ext/cld3/sentence_features.h +35 -0
  50. data/ext/cld3/simple_adder.h +72 -0
  51. data/ext/cld3/stringpiece.h +81 -0
  52. data/ext/cld3/task_context.cc +161 -0
  53. data/ext/cld3/task_context.h +81 -0
  54. data/ext/cld3/task_context_params.cc +74 -0
  55. data/ext/cld3/task_context_params.h +54 -0
  56. data/ext/cld3/task_spec.proto +98 -0
  57. data/ext/cld3/text_processing.cc +245 -0
  58. data/ext/cld3/text_processing.h +30 -0
  59. data/ext/cld3/unicodetext.cc +96 -0
  60. data/ext/cld3/unicodetext.h +144 -0
  61. data/ext/cld3/utf8acceptinterchange.h +486 -0
  62. data/ext/cld3/utf8prop_lettermarkscriptnum.h +1631 -0
  63. data/ext/cld3/utf8repl_lettermarklower.h +758 -0
  64. data/ext/cld3/utf8scannot_lettermarkspecial.h +1455 -0
  65. data/ext/cld3/utf8statetable.cc +1344 -0
  66. data/ext/cld3/utf8statetable.h +285 -0
  67. data/ext/cld3/utils.cc +241 -0
  68. data/ext/cld3/utils.h +144 -0
  69. data/ext/cld3/workspace.cc +64 -0
  70. data/ext/cld3/workspace.h +177 -0
  71. data/lib/cld3.rb +99 -0
  72. metadata +158 -0
metadata ADDED
@@ -0,0 +1,158 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: cld3
3
+ version: !ruby/object:Gem::Version
4
+ version: 3.1.0
5
+ platform: ruby
6
+ authors:
7
+ - Akihiko Odaki
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2017-05-06 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ name: ffi
15
+ requirement: !ruby/object:Gem::Requirement
16
+ requirements:
17
+ - - ">="
18
+ - !ruby/object:Gem::Version
19
+ version: 1.1.0
20
+ - - "<"
21
+ - !ruby/object:Gem::Version
22
+ version: 1.10.0
23
+ type: :runtime
24
+ prerelease: false
25
+ version_requirements: !ruby/object:Gem::Requirement
26
+ requirements:
27
+ - - ">="
28
+ - !ruby/object:Gem::Version
29
+ version: 1.1.0
30
+ - - "<"
31
+ - !ruby/object:Gem::Version
32
+ version: 1.10.0
33
+ - !ruby/object:Gem::Dependency
34
+ name: rspec
35
+ requirement: !ruby/object:Gem::Requirement
36
+ requirements:
37
+ - - ">="
38
+ - !ruby/object:Gem::Version
39
+ version: 2.11.0
40
+ - - "<"
41
+ - !ruby/object:Gem::Version
42
+ version: 3.7.0
43
+ type: :development
44
+ prerelease: false
45
+ version_requirements: !ruby/object:Gem::Requirement
46
+ requirements:
47
+ - - ">="
48
+ - !ruby/object:Gem::Version
49
+ version: 2.11.0
50
+ - - "<"
51
+ - !ruby/object:Gem::Version
52
+ version: 3.7.0
53
+ description: Compact Language Detector v3 (CLD3) is a neural network model for language
54
+ identification.
55
+ email: akihiko.odaki.4i@stu.hosei.ac.jp
56
+ executables: []
57
+ extensions:
58
+ - ext/cld3/extconf.rb
59
+ extra_rdoc_files: []
60
+ files:
61
+ - Gemfile
62
+ - LICENSE
63
+ - LICENSE_CLD3
64
+ - README.md
65
+ - cld3.gemspec
66
+ - ext/cld3/base.cc
67
+ - ext/cld3/base.h
68
+ - ext/cld3/casts.h
69
+ - ext/cld3/embedding_feature_extractor.cc
70
+ - ext/cld3/embedding_feature_extractor.h
71
+ - ext/cld3/embedding_network.cc
72
+ - ext/cld3/embedding_network.h
73
+ - ext/cld3/embedding_network_params.h
74
+ - ext/cld3/extconf.rb
75
+ - ext/cld3/feature_extractor.cc
76
+ - ext/cld3/feature_extractor.h
77
+ - ext/cld3/feature_extractor.proto
78
+ - ext/cld3/feature_types.cc
79
+ - ext/cld3/feature_types.h
80
+ - ext/cld3/fixunicodevalue.cc
81
+ - ext/cld3/fixunicodevalue.h
82
+ - ext/cld3/float16.h
83
+ - ext/cld3/fml_parser.cc
84
+ - ext/cld3/fml_parser.h
85
+ - ext/cld3/generated_entities.cc
86
+ - ext/cld3/generated_ulscript.cc
87
+ - ext/cld3/generated_ulscript.h
88
+ - ext/cld3/getonescriptspan.cc
89
+ - ext/cld3/getonescriptspan.h
90
+ - ext/cld3/integral_types.h
91
+ - ext/cld3/lang_id_nn_params.cc
92
+ - ext/cld3/lang_id_nn_params.h
93
+ - ext/cld3/language_identifier_features.cc
94
+ - ext/cld3/language_identifier_features.h
95
+ - ext/cld3/nnet_language_identifier.cc
96
+ - ext/cld3/nnet_language_identifier.h
97
+ - ext/cld3/nnet_language_identifier_c.cc
98
+ - ext/cld3/offsetmap.cc
99
+ - ext/cld3/offsetmap.h
100
+ - ext/cld3/port.h
101
+ - ext/cld3/registry.cc
102
+ - ext/cld3/registry.h
103
+ - ext/cld3/relevant_script_feature.cc
104
+ - ext/cld3/relevant_script_feature.h
105
+ - ext/cld3/script_detector.h
106
+ - ext/cld3/sentence.proto
107
+ - ext/cld3/sentence_features.cc
108
+ - ext/cld3/sentence_features.h
109
+ - ext/cld3/simple_adder.h
110
+ - ext/cld3/stringpiece.h
111
+ - ext/cld3/task_context.cc
112
+ - ext/cld3/task_context.h
113
+ - ext/cld3/task_context_params.cc
114
+ - ext/cld3/task_context_params.h
115
+ - ext/cld3/task_spec.proto
116
+ - ext/cld3/text_processing.cc
117
+ - ext/cld3/text_processing.h
118
+ - ext/cld3/unicodetext.cc
119
+ - ext/cld3/unicodetext.h
120
+ - ext/cld3/utf8acceptinterchange.h
121
+ - ext/cld3/utf8prop_lettermarkscriptnum.h
122
+ - ext/cld3/utf8repl_lettermarklower.h
123
+ - ext/cld3/utf8scannot_lettermarkspecial.h
124
+ - ext/cld3/utf8statetable.cc
125
+ - ext/cld3/utf8statetable.h
126
+ - ext/cld3/utils.cc
127
+ - ext/cld3/utils.h
128
+ - ext/cld3/workspace.cc
129
+ - ext/cld3/workspace.h
130
+ - lib/cld3.rb
131
+ homepage: https://github.com/akihikodaki/cld3-ruby
132
+ licenses:
133
+ - Apache-2.0
134
+ metadata: {}
135
+ post_install_message:
136
+ rdoc_options: []
137
+ require_paths:
138
+ - lib
139
+ required_ruby_version: !ruby/object:Gem::Requirement
140
+ requirements:
141
+ - - ">="
142
+ - !ruby/object:Gem::Version
143
+ version: 2.3.0
144
+ - - "<"
145
+ - !ruby/object:Gem::Version
146
+ version: 2.5.0
147
+ required_rubygems_version: !ruby/object:Gem::Requirement
148
+ requirements:
149
+ - - ">="
150
+ - !ruby/object:Gem::Version
151
+ version: '0'
152
+ requirements: []
153
+ rubyforge_project:
154
+ rubygems_version: 2.6.11
155
+ signing_key:
156
+ specification_version: 4
157
+ summary: Compact Language Detector v3 (CLD3)
158
+ test_files: []