nhkore 0.3.13 → 0.3.16
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +17 -1
- data/Gemfile.lock +41 -41
- data/README.md +4 -5
- data/Rakefile +5 -3
- data/lib/nhkore/app.rb +8 -19
- data/lib/nhkore/article.rb +5 -9
- data/lib/nhkore/article_scraper.rb +15 -14
- data/lib/nhkore/cleaner.rb +0 -12
- data/lib/nhkore/cli/fx_cmd.rb +0 -4
- data/lib/nhkore/cli/get_cmd.rb +0 -4
- data/lib/nhkore/cli/news_cmd.rb +29 -17
- data/lib/nhkore/cli/search_cmd.rb +45 -35
- data/lib/nhkore/cli/sift_cmd.rb +1 -5
- data/lib/nhkore/datetime_parser.rb +1 -5
- data/lib/nhkore/defn.rb +1 -5
- data/lib/nhkore/dict.rb +2 -5
- data/lib/nhkore/dict_scraper.rb +2 -6
- data/lib/nhkore/entry.rb +3 -9
- data/lib/nhkore/error.rb +1 -11
- data/lib/nhkore/fileable.rb +0 -4
- data/lib/nhkore/lib.rb +0 -3
- data/lib/nhkore/missingno.rb +2 -6
- data/lib/nhkore/news.rb +3 -15
- data/lib/nhkore/polisher.rb +0 -12
- data/lib/nhkore/scraper.rb +8 -5
- data/lib/nhkore/search_link.rb +9 -17
- data/lib/nhkore/search_scraper.rb +34 -24
- data/lib/nhkore/sifter.rb +7 -8
- data/lib/nhkore/splitter.rb +0 -18
- data/lib/nhkore/user_agents.rb +1 -4
- data/lib/nhkore/util.rb +0 -4
- data/lib/nhkore/variator.rb +0 -14
- data/lib/nhkore/version.rb +1 -1
- data/lib/nhkore/word.rb +0 -4
- data/lib/nhkore.rb +0 -5
- data/nhkore.gemspec +40 -37
- data/samples/looper.rb +0 -3
- metadata +24 -24
data/lib/nhkore/sifter.rb
CHANGED
@@ -15,10 +15,6 @@ require 'nhkore/util'
|
|
15
15
|
|
16
16
|
|
17
17
|
module NHKore
|
18
|
-
###
|
19
|
-
# @author Jonathan Bradley Whited
|
20
|
-
# @since 0.2.0
|
21
|
-
###
|
22
18
|
class Sifter
|
23
19
|
include Fileable
|
24
20
|
|
@@ -61,10 +57,8 @@ module NHKore
|
|
61
57
|
end
|
62
58
|
|
63
59
|
def build_rows(words)
|
64
|
-
rows =
|
65
|
-
|
66
|
-
words.each do |word|
|
67
|
-
rows << build_word_row(word)
|
60
|
+
rows = words.map do |word|
|
61
|
+
build_word_row(word)
|
68
62
|
end
|
69
63
|
|
70
64
|
return rows
|
@@ -336,6 +330,11 @@ module NHKore
|
|
336
330
|
next if filter?(article)
|
337
331
|
|
338
332
|
article.words.each_value do |word|
|
333
|
+
# TODO: Try to remove garbage data better.
|
334
|
+
next if word.word.length < 2
|
335
|
+
next if word.freq <= 1
|
336
|
+
next if word.word =~ /\p{Latin}|[[:digit:]]/
|
337
|
+
|
339
338
|
master_article.add_word(word,use_freq: true)
|
340
339
|
end
|
341
340
|
end
|
data/lib/nhkore/splitter.rb
CHANGED
@@ -13,10 +13,6 @@ require 'nhkore/util'
|
|
13
13
|
|
14
14
|
|
15
15
|
module NHKore
|
16
|
-
###
|
17
|
-
# @author Jonathan Bradley Whited
|
18
|
-
# @since 0.2.0
|
19
|
-
###
|
20
16
|
class Splitter
|
21
17
|
def begin_split(str)
|
22
18
|
return str
|
@@ -30,19 +26,12 @@ module NHKore
|
|
30
26
|
end
|
31
27
|
end
|
32
28
|
|
33
|
-
###
|
34
|
-
# @author Jonathan Bradley Whited
|
35
|
-
# @since 0.2.0
|
36
|
-
###
|
37
29
|
class BasicSplitter < Splitter
|
38
30
|
def end_split(str)
|
39
31
|
return str.split(Util::NORMALIZE_STR_REGEX)
|
40
32
|
end
|
41
33
|
end
|
42
34
|
|
43
|
-
###
|
44
|
-
# @since 0.2.0
|
45
|
-
###
|
46
35
|
class BimyouSplitter < Splitter
|
47
36
|
def initialize(*)
|
48
37
|
require 'bimyou_segmenter'
|
@@ -55,9 +44,6 @@ module NHKore
|
|
55
44
|
end
|
56
45
|
end
|
57
46
|
|
58
|
-
###
|
59
|
-
# @since 0.2.0
|
60
|
-
###
|
61
47
|
class TinySplitter < Splitter
|
62
48
|
attr_accessor :tiny
|
63
49
|
|
@@ -74,10 +60,6 @@ module NHKore
|
|
74
60
|
end
|
75
61
|
end
|
76
62
|
|
77
|
-
###
|
78
|
-
# @author Jonathan Bradley Whited
|
79
|
-
# @since 0.2.0
|
80
|
-
###
|
81
63
|
class BestSplitter < BimyouSplitter
|
82
64
|
end
|
83
65
|
end
|
data/lib/nhkore/user_agents.rb
CHANGED
@@ -38,9 +38,6 @@ module NHKore
|
|
38
38
|
#
|
39
39
|
# The gem is really old and had a lot of warnings, so decided to make this class.
|
40
40
|
# Maybe I'll fork the gem and maintain a new version in the future...
|
41
|
-
#
|
42
|
-
# @author Jonathan Bradley Whited
|
43
|
-
# @since 0.2.1
|
44
41
|
###
|
45
42
|
class UserAgents
|
46
43
|
attr_accessor :data
|
@@ -53,7 +50,7 @@ module NHKore
|
|
53
50
|
# because we don't need all of the data in memory after getting just 1
|
54
51
|
# sample, even though it's slower.
|
55
52
|
def initialize
|
56
|
-
super
|
53
|
+
super
|
57
54
|
|
58
55
|
# rubocop:disable all
|
59
56
|
@data = [
|
data/lib/nhkore/util.rb
CHANGED
data/lib/nhkore/variator.rb
CHANGED
@@ -10,10 +10,6 @@
|
|
10
10
|
|
11
11
|
|
12
12
|
module NHKore
|
13
|
-
###
|
14
|
-
# @author Jonathan Bradley Whited
|
15
|
-
# @since 0.2.0
|
16
|
-
###
|
17
13
|
class Variator
|
18
14
|
def begin_variate(str)
|
19
15
|
return str
|
@@ -27,10 +23,6 @@ module NHKore
|
|
27
23
|
end
|
28
24
|
end
|
29
25
|
|
30
|
-
###
|
31
|
-
# @author Jonathan Bradley Whited
|
32
|
-
# @since 0.2.0
|
33
|
-
###
|
34
26
|
class BasicVariator < Variator
|
35
27
|
def end_variate(str)
|
36
28
|
return [] # No variations; don't return nil
|
@@ -41,8 +33,6 @@ module NHKore
|
|
41
33
|
# Guesses a word's dictionary/plain form (辞書形).
|
42
34
|
#
|
43
35
|
# It doesn't work very well,but better than nothing...
|
44
|
-
#
|
45
|
-
# @since 0.2.0
|
46
36
|
###
|
47
37
|
class DictFormVariator < Variator
|
48
38
|
attr_accessor :deinflector
|
@@ -66,10 +56,6 @@ module NHKore
|
|
66
56
|
end
|
67
57
|
end
|
68
58
|
|
69
|
-
###
|
70
|
-
# @author Jonathan Bradley Whited
|
71
|
-
# @since 0.2.0
|
72
|
-
###
|
73
59
|
class BestVariator < DictFormVariator
|
74
60
|
end
|
75
61
|
end
|
data/lib/nhkore/version.rb
CHANGED
data/lib/nhkore/word.rb
CHANGED
data/lib/nhkore.rb
CHANGED
data/nhkore.gemspec
CHANGED
@@ -26,48 +26,57 @@ Gem::Specification.new do |spec|
|
|
26
26
|
#'mailing_list_uri' => '',
|
27
27
|
}
|
28
28
|
|
29
|
+
spec.required_ruby_version = '>= 2.5'
|
29
30
|
spec.requirements = [
|
30
31
|
'Nokogiri: https://www.nokogiri.org/tutorials/installing_nokogiri.html',
|
31
32
|
]
|
32
33
|
|
33
|
-
spec.
|
34
|
-
spec.
|
35
|
-
spec.
|
36
|
-
|
34
|
+
spec.require_paths = ['lib']
|
35
|
+
spec.bindir = 'bin'
|
36
|
+
spec.executables = [spec.name]
|
37
|
+
|
38
|
+
spec.extra_rdoc_files = %w[ CHANGELOG.md LICENSE.txt README.md ]
|
39
|
+
spec.rdoc_options = [
|
40
|
+
'--hyperlink-all','--show-hash',
|
41
|
+
'--title',"NHKore v#{NHKore::VERSION} Doc",
|
42
|
+
'--main','README.md',
|
43
|
+
]
|
37
44
|
|
38
45
|
spec.files = [
|
39
46
|
Dir.glob(File.join("{#{spec.require_paths.join(',')}}",'**','*.{erb,rb}')),
|
40
47
|
Dir.glob(File.join(spec.bindir,'*')),
|
41
48
|
Dir.glob(File.join('{samples,test,yard}','**','*.{erb,rb}')),
|
42
49
|
%W[ Gemfile Gemfile.lock #{spec.name}.gemspec Rakefile .yardopts ],
|
43
|
-
|
50
|
+
spec.extra_rdoc_files,
|
44
51
|
].flatten
|
45
52
|
|
46
|
-
spec.add_runtime_dependency
|
47
|
-
|
48
|
-
|
49
|
-
|
50
|
-
|
51
|
-
|
52
|
-
|
53
|
-
|
54
|
-
|
55
|
-
|
56
|
-
|
57
|
-
|
58
|
-
|
59
|
-
|
60
|
-
|
61
|
-
|
53
|
+
run_dep = spec.method(:add_runtime_dependency)
|
54
|
+
run_dep[ 'attr_bool' ,'~> 0.2' ] # attr_accessor?/attr_reader?.
|
55
|
+
run_dep[ 'bimyou_segmenter' ,'~> 1.2' ] # Splitting Japanese sentences into words.
|
56
|
+
run_dep[ 'cri' ,'~> 2.15' ] # CLI commands/options.
|
57
|
+
run_dep[ 'down' ,'~> 5.4' ] # Downloading files (GetCmd).
|
58
|
+
run_dep[ 'highline' ,'~> 3.1' ] # CLI input/output.
|
59
|
+
run_dep[ 'http-cookie' ,'~> 1.0' ] # Parsing/Setting cookies [(Bing)Scraper].
|
60
|
+
run_dep[ 'japanese_deinflector','~> 0.0' ] # Unconjugating Japanese words (dictionary form).
|
61
|
+
run_dep[ 'nokogiri' ,'~> 1.16' ] # Scraping/Hacking.
|
62
|
+
run_dep[ 'psychgus' ,'~> 1.3' ] # Styling Psych YAML.
|
63
|
+
run_dep[ 'public_suffix' ,'~> 6.0' ] # Parsing URL domain names.
|
64
|
+
run_dep[ 'rainbow' ,'~> 3.1' ] # CLI color output.
|
65
|
+
run_dep[ 'rss' ,'~> 0.3' ] # Scraping [(Bing)Scraper].
|
66
|
+
run_dep[ 'rubyzip' ,'~> 2.3' ] # Extracting Zip files (GetCmd).
|
67
|
+
run_dep[ 'tiny_segmenter' ,'~> 0.0' ] # Splitting Japanese sentences into words.
|
68
|
+
run_dep[ 'tty-progressbar' ,'~> 0.18' ] # CLI progress bars.
|
69
|
+
run_dep[ 'tty-spinner' ,'~> 0.9' ] # CLI spinning progress.
|
62
70
|
|
63
|
-
spec.add_development_dependency
|
64
|
-
|
65
|
-
|
66
|
-
|
67
|
-
|
68
|
-
|
69
|
-
|
70
|
-
|
71
|
+
dev_dep = spec.method(:add_development_dependency)
|
72
|
+
dev_dep[ 'bundler' ,'~> 2.5' ]
|
73
|
+
dev_dep[ 'minitest' ,'~> 5.25' ]
|
74
|
+
dev_dep[ 'rake' ,'~> 13.2' ]
|
75
|
+
dev_dep[ 'raketeer' ,'~> 0.2' ] # Extra Rake tasks.
|
76
|
+
dev_dep[ 'rdoc' ,'~> 6.7' ] # YARDoc RDoc (*.rb).
|
77
|
+
dev_dep[ 'redcarpet' ,'~> 3.6' ] # YARDoc Markdown (*.md).
|
78
|
+
dev_dep[ 'yard' ,'~> 0.9' ] # Doc.
|
79
|
+
dev_dep[ 'yard_ghurt','~> 1.2' ] # Extra YARDoc Rake tasks.
|
71
80
|
|
72
81
|
spec.post_install_message = <<~MSG
|
73
82
|
+=============================================================================+
|
@@ -81,13 +90,7 @@ Gem::Specification.new do |spec|
|
|
81
90
|
| Changelog: #{spec.metadata['changelog_uri']}
|
82
91
|
+=============================================================================+
|
83
92
|
MSG
|
84
|
-
#puts spec.post_install_message.split("\n").map(&:length).max
|
85
|
-
|
86
|
-
spec.extra_rdoc_files = %w[ CHANGELOG.md LICENSE.txt README.md ]
|
87
93
|
|
88
|
-
|
89
|
-
|
90
|
-
'--title',"NHKore v#{NHKore::VERSION} Doc",
|
91
|
-
'--main','README.md',
|
92
|
-
]
|
94
|
+
# Uncomment to see max line length:
|
95
|
+
#puts spec.post_install_message.split("\n").map(&:length).max
|
93
96
|
end
|
data/samples/looper.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: nhkore
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.3.
|
4
|
+
version: 0.3.16
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Jonathan Bradley Whited
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2024-08-14 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: attr_bool
|
@@ -58,28 +58,28 @@ dependencies:
|
|
58
58
|
requirements:
|
59
59
|
- - "~>"
|
60
60
|
- !ruby/object:Gem::Version
|
61
|
-
version: '5.
|
61
|
+
version: '5.4'
|
62
62
|
type: :runtime
|
63
63
|
prerelease: false
|
64
64
|
version_requirements: !ruby/object:Gem::Requirement
|
65
65
|
requirements:
|
66
66
|
- - "~>"
|
67
67
|
- !ruby/object:Gem::Version
|
68
|
-
version: '5.
|
68
|
+
version: '5.4'
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
70
|
name: highline
|
71
71
|
requirement: !ruby/object:Gem::Requirement
|
72
72
|
requirements:
|
73
73
|
- - "~>"
|
74
74
|
- !ruby/object:Gem::Version
|
75
|
-
version: '
|
75
|
+
version: '3.1'
|
76
76
|
type: :runtime
|
77
77
|
prerelease: false
|
78
78
|
version_requirements: !ruby/object:Gem::Requirement
|
79
79
|
requirements:
|
80
80
|
- - "~>"
|
81
81
|
- !ruby/object:Gem::Version
|
82
|
-
version: '
|
82
|
+
version: '3.1'
|
83
83
|
- !ruby/object:Gem::Dependency
|
84
84
|
name: http-cookie
|
85
85
|
requirement: !ruby/object:Gem::Requirement
|
@@ -114,14 +114,14 @@ dependencies:
|
|
114
114
|
requirements:
|
115
115
|
- - "~>"
|
116
116
|
- !ruby/object:Gem::Version
|
117
|
-
version: '1.
|
117
|
+
version: '1.16'
|
118
118
|
type: :runtime
|
119
119
|
prerelease: false
|
120
120
|
version_requirements: !ruby/object:Gem::Requirement
|
121
121
|
requirements:
|
122
122
|
- - "~>"
|
123
123
|
- !ruby/object:Gem::Version
|
124
|
-
version: '1.
|
124
|
+
version: '1.16'
|
125
125
|
- !ruby/object:Gem::Dependency
|
126
126
|
name: psychgus
|
127
127
|
requirement: !ruby/object:Gem::Requirement
|
@@ -142,14 +142,14 @@ dependencies:
|
|
142
142
|
requirements:
|
143
143
|
- - "~>"
|
144
144
|
- !ruby/object:Gem::Version
|
145
|
-
version: '
|
145
|
+
version: '6.0'
|
146
146
|
type: :runtime
|
147
147
|
prerelease: false
|
148
148
|
version_requirements: !ruby/object:Gem::Requirement
|
149
149
|
requirements:
|
150
150
|
- - "~>"
|
151
151
|
- !ruby/object:Gem::Version
|
152
|
-
version: '
|
152
|
+
version: '6.0'
|
153
153
|
- !ruby/object:Gem::Dependency
|
154
154
|
name: rainbow
|
155
155
|
requirement: !ruby/object:Gem::Requirement
|
@@ -170,14 +170,14 @@ dependencies:
|
|
170
170
|
requirements:
|
171
171
|
- - "~>"
|
172
172
|
- !ruby/object:Gem::Version
|
173
|
-
version: '0.
|
173
|
+
version: '0.3'
|
174
174
|
type: :runtime
|
175
175
|
prerelease: false
|
176
176
|
version_requirements: !ruby/object:Gem::Requirement
|
177
177
|
requirements:
|
178
178
|
- - "~>"
|
179
179
|
- !ruby/object:Gem::Version
|
180
|
-
version: '0.
|
180
|
+
version: '0.3'
|
181
181
|
- !ruby/object:Gem::Dependency
|
182
182
|
name: rubyzip
|
183
183
|
requirement: !ruby/object:Gem::Requirement
|
@@ -240,42 +240,42 @@ dependencies:
|
|
240
240
|
requirements:
|
241
241
|
- - "~>"
|
242
242
|
- !ruby/object:Gem::Version
|
243
|
-
version: '2.
|
243
|
+
version: '2.5'
|
244
244
|
type: :development
|
245
245
|
prerelease: false
|
246
246
|
version_requirements: !ruby/object:Gem::Requirement
|
247
247
|
requirements:
|
248
248
|
- - "~>"
|
249
249
|
- !ruby/object:Gem::Version
|
250
|
-
version: '2.
|
250
|
+
version: '2.5'
|
251
251
|
- !ruby/object:Gem::Dependency
|
252
252
|
name: minitest
|
253
253
|
requirement: !ruby/object:Gem::Requirement
|
254
254
|
requirements:
|
255
255
|
- - "~>"
|
256
256
|
- !ruby/object:Gem::Version
|
257
|
-
version: '5.
|
257
|
+
version: '5.25'
|
258
258
|
type: :development
|
259
259
|
prerelease: false
|
260
260
|
version_requirements: !ruby/object:Gem::Requirement
|
261
261
|
requirements:
|
262
262
|
- - "~>"
|
263
263
|
- !ruby/object:Gem::Version
|
264
|
-
version: '5.
|
264
|
+
version: '5.25'
|
265
265
|
- !ruby/object:Gem::Dependency
|
266
266
|
name: rake
|
267
267
|
requirement: !ruby/object:Gem::Requirement
|
268
268
|
requirements:
|
269
269
|
- - "~>"
|
270
270
|
- !ruby/object:Gem::Version
|
271
|
-
version: '13.
|
271
|
+
version: '13.2'
|
272
272
|
type: :development
|
273
273
|
prerelease: false
|
274
274
|
version_requirements: !ruby/object:Gem::Requirement
|
275
275
|
requirements:
|
276
276
|
- - "~>"
|
277
277
|
- !ruby/object:Gem::Version
|
278
|
-
version: '13.
|
278
|
+
version: '13.2'
|
279
279
|
- !ruby/object:Gem::Dependency
|
280
280
|
name: raketeer
|
281
281
|
requirement: !ruby/object:Gem::Requirement
|
@@ -296,28 +296,28 @@ dependencies:
|
|
296
296
|
requirements:
|
297
297
|
- - "~>"
|
298
298
|
- !ruby/object:Gem::Version
|
299
|
-
version: '6.
|
299
|
+
version: '6.7'
|
300
300
|
type: :development
|
301
301
|
prerelease: false
|
302
302
|
version_requirements: !ruby/object:Gem::Requirement
|
303
303
|
requirements:
|
304
304
|
- - "~>"
|
305
305
|
- !ruby/object:Gem::Version
|
306
|
-
version: '6.
|
306
|
+
version: '6.7'
|
307
307
|
- !ruby/object:Gem::Dependency
|
308
308
|
name: redcarpet
|
309
309
|
requirement: !ruby/object:Gem::Requirement
|
310
310
|
requirements:
|
311
311
|
- - "~>"
|
312
312
|
- !ruby/object:Gem::Version
|
313
|
-
version: '3.
|
313
|
+
version: '3.6'
|
314
314
|
type: :development
|
315
315
|
prerelease: false
|
316
316
|
version_requirements: !ruby/object:Gem::Requirement
|
317
317
|
requirements:
|
318
318
|
- - "~>"
|
319
319
|
- !ruby/object:Gem::Version
|
320
|
-
version: '3.
|
320
|
+
version: '3.6'
|
321
321
|
- !ruby/object:Gem::Dependency
|
322
322
|
name: yard
|
323
323
|
requirement: !ruby/object:Gem::Requirement
|
@@ -412,7 +412,7 @@ metadata:
|
|
412
412
|
changelog_uri: https://github.com/esotericpig/nhkore/blob/master/CHANGELOG.md
|
413
413
|
post_install_message: |
|
414
414
|
+=============================================================================+
|
415
|
-
| NHKore v0.3.
|
415
|
+
| NHKore v0.3.16
|
416
416
|
|
|
417
417
|
| You can now use [nhkore] on the command line.
|
418
418
|
|
|
@@ -425,7 +425,7 @@ rdoc_options:
|
|
425
425
|
- "--hyperlink-all"
|
426
426
|
- "--show-hash"
|
427
427
|
- "--title"
|
428
|
-
- NHKore v0.3.
|
428
|
+
- NHKore v0.3.16 Doc
|
429
429
|
- "--main"
|
430
430
|
- README.md
|
431
431
|
require_paths:
|