twitter_ebooks 2.0.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +1 -0
- data/Gemfile +4 -0
- data/Gemfile.lock +78 -0
- data/NOTES.md +4 -0
- data/README.md +20 -0
- data/bin/ebooks +83 -0
- data/data/adjectives.txt +1466 -0
- data/data/nouns.txt +2193 -0
- data/data/stopwords.txt +639 -0
- data/lib/twitter_ebooks/archiver.rb +86 -0
- data/lib/twitter_ebooks/bot.rb +145 -0
- data/lib/twitter_ebooks/markov.rb +89 -0
- data/lib/twitter_ebooks/model.rb +147 -0
- data/lib/twitter_ebooks/nlp.rb +142 -0
- data/lib/twitter_ebooks/version.rb +3 -0
- data/lib/twitter_ebooks.rb +20 -0
- data/skeleton/Procfile +1 -0
- data/skeleton/bots.rb +47 -0
- data/skeleton/corpus/README.md +1 -0
- data/skeleton/model/README.md +1 -0
- data/test/corpus/0xabad1dea.tweets +14696 -0
- data/test/tokenize.rb +18 -0
- data/twitter_ebooks.gemspec +30 -0
- metadata +247 -0
data/test/tokenize.rb
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
1
|
+
#!/usr/bin/env ruby
|
|
2
|
+
# encoding: utf-8
|
|
3
|
+
|
|
4
|
+
require 'twitter_ebooks'
|
|
5
|
+
require 'minitest/autorun'
|
|
6
|
+
|
|
7
|
+
module Ebooks
|
|
8
|
+
class TestTokenize < Minitest::Test
|
|
9
|
+
corpus = NLP.normalize(File.read(TEST_CORPUS_PATH))
|
|
10
|
+
sents = NLP.sentences(corpus).sample(10)
|
|
11
|
+
|
|
12
|
+
NLP.sentences(corpus).sample(10).each do |sent|
|
|
13
|
+
p sent
|
|
14
|
+
p NLP.tokenize(sent)
|
|
15
|
+
puts
|
|
16
|
+
end
|
|
17
|
+
end
|
|
18
|
+
end
|
|
@@ -0,0 +1,30 @@
|
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
|
2
|
+
require File.expand_path('../lib/twitter_ebooks/version', __FILE__)
|
|
3
|
+
|
|
4
|
+
Gem::Specification.new do |gem|
|
|
5
|
+
gem.authors = ["Jaiden Mispy"]
|
|
6
|
+
gem.email = ["^_^@mispy.me"]
|
|
7
|
+
gem.description = %q{Markov chains for all your friends~}
|
|
8
|
+
gem.summary = %q{Markov chains for all your friends~}
|
|
9
|
+
gem.homepage = ""
|
|
10
|
+
|
|
11
|
+
gem.files = `git ls-files`.split($\)
|
|
12
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
|
13
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
|
14
|
+
gem.name = "twitter_ebooks"
|
|
15
|
+
gem.require_paths = ["lib"]
|
|
16
|
+
gem.version = Ebooks::VERSION
|
|
17
|
+
|
|
18
|
+
gem.add_runtime_dependency 'minitest'
|
|
19
|
+
|
|
20
|
+
gem.add_runtime_dependency 'twitter'
|
|
21
|
+
gem.add_runtime_dependency 'tweetstream'
|
|
22
|
+
gem.add_runtime_dependency 'tactful_tokenizer'
|
|
23
|
+
gem.add_runtime_dependency 'tokenizer'
|
|
24
|
+
gem.add_runtime_dependency 'ruby-stemmer'
|
|
25
|
+
gem.add_runtime_dependency 'engtagger'
|
|
26
|
+
gem.add_runtime_dependency 'linguistics'
|
|
27
|
+
gem.add_runtime_dependency 'rufus-scheduler'
|
|
28
|
+
gem.add_runtime_dependency 'gingerice'
|
|
29
|
+
gem.add_runtime_dependency 'htmlentities'
|
|
30
|
+
end
|
metadata
ADDED
|
@@ -0,0 +1,247 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: twitter_ebooks
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 2.0.0
|
|
5
|
+
prerelease:
|
|
6
|
+
platform: ruby
|
|
7
|
+
authors:
|
|
8
|
+
- Jaiden Mispy
|
|
9
|
+
autorequire:
|
|
10
|
+
bindir: bin
|
|
11
|
+
cert_chain: []
|
|
12
|
+
date: 2013-11-05 00:00:00.000000000 Z
|
|
13
|
+
dependencies:
|
|
14
|
+
- !ruby/object:Gem::Dependency
|
|
15
|
+
name: minitest
|
|
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: twitter
|
|
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: tweetstream
|
|
48
|
+
requirement: !ruby/object:Gem::Requirement
|
|
49
|
+
none: false
|
|
50
|
+
requirements:
|
|
51
|
+
- - ! '>='
|
|
52
|
+
- !ruby/object:Gem::Version
|
|
53
|
+
version: '0'
|
|
54
|
+
type: :runtime
|
|
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
|
+
- !ruby/object:Gem::Dependency
|
|
63
|
+
name: tactful_tokenizer
|
|
64
|
+
requirement: !ruby/object:Gem::Requirement
|
|
65
|
+
none: false
|
|
66
|
+
requirements:
|
|
67
|
+
- - ! '>='
|
|
68
|
+
- !ruby/object:Gem::Version
|
|
69
|
+
version: '0'
|
|
70
|
+
type: :runtime
|
|
71
|
+
prerelease: false
|
|
72
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
73
|
+
none: false
|
|
74
|
+
requirements:
|
|
75
|
+
- - ! '>='
|
|
76
|
+
- !ruby/object:Gem::Version
|
|
77
|
+
version: '0'
|
|
78
|
+
- !ruby/object:Gem::Dependency
|
|
79
|
+
name: tokenizer
|
|
80
|
+
requirement: !ruby/object:Gem::Requirement
|
|
81
|
+
none: false
|
|
82
|
+
requirements:
|
|
83
|
+
- - ! '>='
|
|
84
|
+
- !ruby/object:Gem::Version
|
|
85
|
+
version: '0'
|
|
86
|
+
type: :runtime
|
|
87
|
+
prerelease: false
|
|
88
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
89
|
+
none: false
|
|
90
|
+
requirements:
|
|
91
|
+
- - ! '>='
|
|
92
|
+
- !ruby/object:Gem::Version
|
|
93
|
+
version: '0'
|
|
94
|
+
- !ruby/object:Gem::Dependency
|
|
95
|
+
name: ruby-stemmer
|
|
96
|
+
requirement: !ruby/object:Gem::Requirement
|
|
97
|
+
none: false
|
|
98
|
+
requirements:
|
|
99
|
+
- - ! '>='
|
|
100
|
+
- !ruby/object:Gem::Version
|
|
101
|
+
version: '0'
|
|
102
|
+
type: :runtime
|
|
103
|
+
prerelease: false
|
|
104
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
105
|
+
none: false
|
|
106
|
+
requirements:
|
|
107
|
+
- - ! '>='
|
|
108
|
+
- !ruby/object:Gem::Version
|
|
109
|
+
version: '0'
|
|
110
|
+
- !ruby/object:Gem::Dependency
|
|
111
|
+
name: engtagger
|
|
112
|
+
requirement: !ruby/object:Gem::Requirement
|
|
113
|
+
none: false
|
|
114
|
+
requirements:
|
|
115
|
+
- - ! '>='
|
|
116
|
+
- !ruby/object:Gem::Version
|
|
117
|
+
version: '0'
|
|
118
|
+
type: :runtime
|
|
119
|
+
prerelease: false
|
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
121
|
+
none: false
|
|
122
|
+
requirements:
|
|
123
|
+
- - ! '>='
|
|
124
|
+
- !ruby/object:Gem::Version
|
|
125
|
+
version: '0'
|
|
126
|
+
- !ruby/object:Gem::Dependency
|
|
127
|
+
name: linguistics
|
|
128
|
+
requirement: !ruby/object:Gem::Requirement
|
|
129
|
+
none: false
|
|
130
|
+
requirements:
|
|
131
|
+
- - ! '>='
|
|
132
|
+
- !ruby/object:Gem::Version
|
|
133
|
+
version: '0'
|
|
134
|
+
type: :runtime
|
|
135
|
+
prerelease: false
|
|
136
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
137
|
+
none: false
|
|
138
|
+
requirements:
|
|
139
|
+
- - ! '>='
|
|
140
|
+
- !ruby/object:Gem::Version
|
|
141
|
+
version: '0'
|
|
142
|
+
- !ruby/object:Gem::Dependency
|
|
143
|
+
name: rufus-scheduler
|
|
144
|
+
requirement: !ruby/object:Gem::Requirement
|
|
145
|
+
none: false
|
|
146
|
+
requirements:
|
|
147
|
+
- - ! '>='
|
|
148
|
+
- !ruby/object:Gem::Version
|
|
149
|
+
version: '0'
|
|
150
|
+
type: :runtime
|
|
151
|
+
prerelease: false
|
|
152
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
153
|
+
none: false
|
|
154
|
+
requirements:
|
|
155
|
+
- - ! '>='
|
|
156
|
+
- !ruby/object:Gem::Version
|
|
157
|
+
version: '0'
|
|
158
|
+
- !ruby/object:Gem::Dependency
|
|
159
|
+
name: gingerice
|
|
160
|
+
requirement: !ruby/object:Gem::Requirement
|
|
161
|
+
none: false
|
|
162
|
+
requirements:
|
|
163
|
+
- - ! '>='
|
|
164
|
+
- !ruby/object:Gem::Version
|
|
165
|
+
version: '0'
|
|
166
|
+
type: :runtime
|
|
167
|
+
prerelease: false
|
|
168
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
169
|
+
none: false
|
|
170
|
+
requirements:
|
|
171
|
+
- - ! '>='
|
|
172
|
+
- !ruby/object:Gem::Version
|
|
173
|
+
version: '0'
|
|
174
|
+
- !ruby/object:Gem::Dependency
|
|
175
|
+
name: htmlentities
|
|
176
|
+
requirement: !ruby/object:Gem::Requirement
|
|
177
|
+
none: false
|
|
178
|
+
requirements:
|
|
179
|
+
- - ! '>='
|
|
180
|
+
- !ruby/object:Gem::Version
|
|
181
|
+
version: '0'
|
|
182
|
+
type: :runtime
|
|
183
|
+
prerelease: false
|
|
184
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
185
|
+
none: false
|
|
186
|
+
requirements:
|
|
187
|
+
- - ! '>='
|
|
188
|
+
- !ruby/object:Gem::Version
|
|
189
|
+
version: '0'
|
|
190
|
+
description: Markov chains for all your friends~
|
|
191
|
+
email:
|
|
192
|
+
- ^_^@mispy.me
|
|
193
|
+
executables:
|
|
194
|
+
- ebooks
|
|
195
|
+
extensions: []
|
|
196
|
+
extra_rdoc_files: []
|
|
197
|
+
files:
|
|
198
|
+
- .gitignore
|
|
199
|
+
- Gemfile
|
|
200
|
+
- Gemfile.lock
|
|
201
|
+
- NOTES.md
|
|
202
|
+
- README.md
|
|
203
|
+
- bin/ebooks
|
|
204
|
+
- data/adjectives.txt
|
|
205
|
+
- data/nouns.txt
|
|
206
|
+
- data/stopwords.txt
|
|
207
|
+
- lib/twitter_ebooks.rb
|
|
208
|
+
- lib/twitter_ebooks/archiver.rb
|
|
209
|
+
- lib/twitter_ebooks/bot.rb
|
|
210
|
+
- lib/twitter_ebooks/markov.rb
|
|
211
|
+
- lib/twitter_ebooks/model.rb
|
|
212
|
+
- lib/twitter_ebooks/nlp.rb
|
|
213
|
+
- lib/twitter_ebooks/version.rb
|
|
214
|
+
- skeleton/Procfile
|
|
215
|
+
- skeleton/bots.rb
|
|
216
|
+
- skeleton/corpus/README.md
|
|
217
|
+
- skeleton/model/README.md
|
|
218
|
+
- test/corpus/0xabad1dea.tweets
|
|
219
|
+
- test/tokenize.rb
|
|
220
|
+
- twitter_ebooks.gemspec
|
|
221
|
+
homepage: ''
|
|
222
|
+
licenses: []
|
|
223
|
+
post_install_message:
|
|
224
|
+
rdoc_options: []
|
|
225
|
+
require_paths:
|
|
226
|
+
- lib
|
|
227
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
228
|
+
none: false
|
|
229
|
+
requirements:
|
|
230
|
+
- - ! '>='
|
|
231
|
+
- !ruby/object:Gem::Version
|
|
232
|
+
version: '0'
|
|
233
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
234
|
+
none: false
|
|
235
|
+
requirements:
|
|
236
|
+
- - ! '>='
|
|
237
|
+
- !ruby/object:Gem::Version
|
|
238
|
+
version: '0'
|
|
239
|
+
requirements: []
|
|
240
|
+
rubyforge_project:
|
|
241
|
+
rubygems_version: 1.8.25
|
|
242
|
+
signing_key:
|
|
243
|
+
specification_version: 3
|
|
244
|
+
summary: Markov chains for all your friends~
|
|
245
|
+
test_files:
|
|
246
|
+
- test/corpus/0xabad1dea.tweets
|
|
247
|
+
- test/tokenize.rb
|