nhkore 0.3.18 → 0.3.22
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.
- checksums.yaml +4 -4
- data/CHANGELOG.md +25 -9
- data/Gemfile +1 -0
- data/Gemfile.lock +2 -2
- data/README.md +1 -1
- data/bin/nhkore +1 -1
- data/lib/nhkore/app.rb +1 -4
- data/lib/nhkore/article.rb +1 -1
- data/lib/nhkore/article_scraper.rb +1 -1
- data/lib/nhkore/cleaner.rb +1 -1
- data/lib/nhkore/cli/fx_cmd.rb +1 -1
- data/lib/nhkore/cli/get_cmd.rb +6 -6
- data/lib/nhkore/cli/news_cmd.rb +2 -1
- data/lib/nhkore/cli/search_cmd.rb +3 -3
- data/lib/nhkore/cli/sift_cmd.rb +1 -1
- data/lib/nhkore/datetime_parser.rb +1 -1
- data/lib/nhkore/defn.rb +1 -1
- data/lib/nhkore/dict.rb +1 -1
- data/lib/nhkore/dict_scraper.rb +1 -1
- data/lib/nhkore/entry.rb +1 -1
- data/lib/nhkore/error.rb +1 -1
- data/lib/nhkore/fileable.rb +1 -1
- data/lib/nhkore/lib.rb +6 -10
- data/lib/nhkore/missingno.rb +1 -1
- data/lib/nhkore/news.rb +1 -1
- data/lib/nhkore/polisher.rb +1 -1
- data/lib/nhkore/scraper.rb +11 -3
- data/lib/nhkore/search_link.rb +1 -1
- data/lib/nhkore/search_scraper.rb +12 -5
- data/lib/nhkore/sifter.rb +4 -4
- data/lib/nhkore/splitter.rb +1 -1
- data/lib/nhkore/user_agents.rb +1 -1
- data/lib/nhkore/util.rb +1 -1
- data/lib/nhkore/variator.rb +1 -1
- data/lib/nhkore/version.rb +2 -2
- data/lib/nhkore/word.rb +1 -1
- data/lib/nhkore.rb +2 -8
- data/nhkore.gemspec +24 -22
- data/samples/looper.rb +1 -1
- data/test/nhkore/test_helper.rb +1 -1
- data/test/nhkore_test.rb +1 -1
- metadata +55 -55
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 6d6942febe79f05d1cbd53e40f9048671ee0462d16e22945a6b7bdb3bb5bb2ae
|
4
|
+
data.tar.gz: 226acf4e93e6b95b475a1d42bc7a0d2dff82d5647613164fc2feba882e24b6c7
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 40d4b5513b9a3d22e4969ef7d88c477d4c1dc118165660e751c8c9d742305d74470494597e5e12f61e15af9dc4c3f4e0bccdd82ac7e8488cb2a312a9749ada20
|
7
|
+
data.tar.gz: 00307ecff6363a7f0b80595fc7ec14a01f3e9e303d5d3023e084883a075bed12464a388ca16b6ff6ca143e993bdb5834493d361084452dd61846567173f0ef7f
|
data/CHANGELOG.md
CHANGED
@@ -1,26 +1,42 @@
|
|
1
1
|
# Changelog | NHKore
|
2
2
|
|
3
|
-
|
3
|
+
- [Keep a Changelog v1.0.0](https://keepachangelog.com/en/1.0.0)
|
4
|
+
- [Semantic Versioning v2.0.0](https://semver.org/spec/v2.0.0.html)
|
4
5
|
|
5
|
-
|
6
|
-
|
6
|
+
## [Unreleased]
|
7
|
+
- https://github.com/esotericpig/nhkore/compare/v0.3.22...v0.3
|
7
8
|
|
8
|
-
|
9
|
-
-
|
9
|
+
|
10
|
+
## [v0.3.22] - 2025-04-30
|
11
|
+
|
12
|
+
### Changed
|
13
|
+
- Put v0.3 in its own branch to prepare for v0.4, which will heavily change.
|
14
|
+
- Changed v0.3 links to use v0.3 branch.
|
15
|
+
- Reverted the removing of `UserAgents` for v0.3 only.
|
16
|
+
|
17
|
+
|
18
|
+
## [v0.3.19] - 2025-04-28
|
19
|
+
|
20
|
+
### Fixed
|
21
|
+
- Fixed to include `fileutils` for `news` cmd when directory doesn't exist.
|
22
|
+
|
23
|
+
### Changed
|
24
|
+
- Removed `UserAgents`. Replaced with Gem `ronin-web-user_agents`.
|
25
|
+
- Made some changes to `BingScraper`. Ultimately, it just doesn't work anymore, as Bing has become too strict. In the future, need to use a different search engine or a different way. Leaving for now as a zombie, and unnecessary for most NHKore functionality anyway.
|
10
26
|
|
11
27
|
|
12
28
|
## [v0.3.18] - 2025-04-24
|
13
29
|
|
30
|
+
### Fixed
|
31
|
+
- Bing no longer allows `count`, so removed it. No workaround/fix for now....
|
32
|
+
- New NHK Easy pages no longer have a dictionary, so changed it to only warn instead of an exception.
|
33
|
+
|
14
34
|
### Changed
|
15
35
|
- Changed Nokogiri gem version to `~> 1`, instead of `~> 1.xx`, as I got tired of the security alerts. Now, it will always be up-to-date and secure.
|
16
36
|
- Updated gems.
|
17
37
|
- Removed `yard_ghurt` gem.
|
18
38
|
- Applied new RuboCop suggestions.
|
19
39
|
|
20
|
-
### Fixed
|
21
|
-
- Bing no longer allows `count`, so removed it. No workaround/fix for now....
|
22
|
-
- New NHK Easy pages no longer have a dictionary, so changed it to only warn instead of an exception.
|
23
|
-
|
24
40
|
|
25
41
|
## [v0.3.17] - 2024-09-03
|
26
42
|
|
data/Gemfile
CHANGED
@@ -9,6 +9,7 @@ group :development,:test do
|
|
9
9
|
gem 'bundler' ,'~> 2.6'
|
10
10
|
gem 'rake' ,'~> 13.2'
|
11
11
|
gem 'raketeer' ,'~> 0.2' # Extra Rake tasks.
|
12
|
+
# Doc.
|
12
13
|
gem 'rdoc' ,'~> 6.13' # YARDoc RDoc (*.rb).
|
13
14
|
gem 'redcarpet','~> 3.6' # YARDoc Markdown (*.md).
|
14
15
|
gem 'yard' ,'~> 0.9' # YARDoc doc.
|
data/Gemfile.lock
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
PATH
|
2
2
|
remote: .
|
3
3
|
specs:
|
4
|
-
nhkore (0.3.
|
4
|
+
nhkore (0.3.22)
|
5
5
|
attr_bool (~> 0.2)
|
6
6
|
bimyou_segmenter (~> 1.2)
|
7
7
|
cri (~> 2.15)
|
@@ -49,7 +49,7 @@ GEM
|
|
49
49
|
stringio
|
50
50
|
psychgus (1.3.5)
|
51
51
|
psych (>= 3.0)
|
52
|
-
public_suffix (6.0.
|
52
|
+
public_suffix (6.0.2)
|
53
53
|
racc (1.8.1)
|
54
54
|
rainbow (3.1.1)
|
55
55
|
rake (13.2.1)
|
data/README.md
CHANGED
@@ -884,7 +884,7 @@ Releasing new HTML file for website:
|
|
884
884
|
[GNU LGPL v3+](LICENSE.txt)
|
885
885
|
|
886
886
|
> NHKore (<https://github.com/esotericpig/nhkore>)
|
887
|
-
> Copyright (c) 2020-
|
887
|
+
> Copyright (c) 2020-2025 Bradley Whited
|
888
888
|
>
|
889
889
|
> NHKore is free software: you can redistribute it and/or modify
|
890
890
|
> it under the terms of the GNU Lesser General Public License as published by
|
data/bin/nhkore
CHANGED
data/lib/nhkore/app.rb
CHANGED
@@ -3,7 +3,7 @@
|
|
3
3
|
|
4
4
|
#--
|
5
5
|
# This file is part of NHKore.
|
6
|
-
# Copyright (c) 2020
|
6
|
+
# Copyright (c) 2020 Bradley Whited
|
7
7
|
#
|
8
8
|
# SPDX-License-Identifier: LGPL-3.0-or-later
|
9
9
|
#++
|
@@ -25,9 +25,6 @@ require 'nhkore/cli/search_cmd'
|
|
25
25
|
require 'nhkore/cli/sift_cmd'
|
26
26
|
|
27
27
|
module NHKore
|
28
|
-
module CLI
|
29
|
-
end
|
30
|
-
|
31
28
|
###
|
32
29
|
# For disabling/enabling color output.
|
33
30
|
###
|
data/lib/nhkore/article.rb
CHANGED
data/lib/nhkore/cleaner.rb
CHANGED
data/lib/nhkore/cli/fx_cmd.rb
CHANGED
data/lib/nhkore/cli/get_cmd.rb
CHANGED
@@ -3,12 +3,13 @@
|
|
3
3
|
|
4
4
|
#--
|
5
5
|
# This file is part of NHKore.
|
6
|
-
# Copyright (c) 2020
|
6
|
+
# Copyright (c) 2020 Bradley Whited
|
7
7
|
#
|
8
8
|
# SPDX-License-Identifier: LGPL-3.0-or-later
|
9
9
|
#++
|
10
10
|
|
11
11
|
require 'nhkore/util'
|
12
|
+
require 'nhkore/version'
|
12
13
|
|
13
14
|
module NHKore
|
14
15
|
module CLI
|
@@ -16,7 +17,8 @@ module CLI
|
|
16
17
|
DEFAULT_GET_CHUNK_SIZE = 4 * 1024
|
17
18
|
DEFAULT_GET_URL_LENGTH = 11_000_000 # Just a generous estimation used as a fallback; may be outdated.
|
18
19
|
GET_URL_FILENAME = 'nhkore-core.zip'
|
19
|
-
GET_URL = "https://github.com/esotericpig/nhkore/releases/
|
20
|
+
GET_URL = "https://github.com/esotericpig/nhkore/releases/download/v#{NHKore::VERSION}" \
|
21
|
+
"/#{GET_URL_FILENAME}".freeze
|
20
22
|
|
21
23
|
def build_get_cmd
|
22
24
|
app = self
|
@@ -36,9 +38,7 @@ module CLI
|
|
36
38
|
DESC
|
37
39
|
|
38
40
|
option :o,:out,'directory to save downloaded files to',argument: :required,default: Util::CORE_DIR,
|
39
|
-
|
40
|
-
app.check_empty_opt(:out,value)
|
41
|
-
}
|
41
|
+
transform: ->(value) { app.check_empty_opt(:out,value) }
|
42
42
|
flag nil,:'show-url','show download URL and exit (for downloading manually)' do |_value,_cmd|
|
43
43
|
puts GET_URL
|
44
44
|
exit
|
@@ -69,7 +69,7 @@ module CLI
|
|
69
69
|
out_dir = @cmd_opts[:out]
|
70
70
|
|
71
71
|
begin
|
72
|
-
start_spin(
|
72
|
+
start_spin("Opening URL: #{GET_URL} ")
|
73
73
|
|
74
74
|
begin
|
75
75
|
down = Down::NetHttp.open(GET_URL,rewindable: false,**@scraper_kargs)
|
data/lib/nhkore/cli/news_cmd.rb
CHANGED
@@ -3,11 +3,12 @@
|
|
3
3
|
|
4
4
|
#--
|
5
5
|
# This file is part of NHKore.
|
6
|
-
# Copyright (c) 2020
|
6
|
+
# Copyright (c) 2020 Bradley Whited
|
7
7
|
#
|
8
8
|
# SPDX-License-Identifier: LGPL-3.0-or-later
|
9
9
|
#++
|
10
10
|
|
11
|
+
require 'fileutils'
|
11
12
|
require 'time'
|
12
13
|
|
13
14
|
require 'nhkore/datetime_parser'
|
@@ -3,7 +3,7 @@
|
|
3
3
|
|
4
4
|
#--
|
5
5
|
# This file is part of NHKore.
|
6
|
-
# Copyright (c) 2020
|
6
|
+
# Copyright (c) 2020 Bradley Whited
|
7
7
|
#
|
8
8
|
# SPDX-License-Identifier: LGPL-3.0-or-later
|
9
9
|
#++
|
@@ -27,7 +27,7 @@ module CLI
|
|
27
27
|
|
28
28
|
description <<-DESC
|
29
29
|
Search for links (using a Search Engine, etc.) to NHK News Web (Easy) &
|
30
|
-
save to folder: #{SearchLinks::DEFAULT_DIR}
|
30
|
+
save to folder: '#{SearchLinks::DEFAULT_DIR}'
|
31
31
|
DESC
|
32
32
|
|
33
33
|
option :i,:in,<<-DESC,argument: :required,transform: lambda { |value|
|
@@ -38,7 +38,7 @@ module CLI
|
|
38
38
|
}
|
39
39
|
option :l,:loop,'number of times to repeat the search to ensure results',argument: :required,
|
40
40
|
transform: lambda { |value|
|
41
|
-
value = value.to_i
|
41
|
+
value = value.to_s.strip.to_i
|
42
42
|
value = 1 if value < 1
|
43
43
|
value
|
44
44
|
}
|
data/lib/nhkore/cli/sift_cmd.rb
CHANGED
data/lib/nhkore/defn.rb
CHANGED
data/lib/nhkore/dict.rb
CHANGED
data/lib/nhkore/dict_scraper.rb
CHANGED
data/lib/nhkore/entry.rb
CHANGED
data/lib/nhkore/error.rb
CHANGED
data/lib/nhkore/fileable.rb
CHANGED
data/lib/nhkore/lib.rb
CHANGED
@@ -3,11 +3,16 @@
|
|
3
3
|
|
4
4
|
#--
|
5
5
|
# This file is part of NHKore.
|
6
|
-
# Copyright (c) 2020
|
6
|
+
# Copyright (c) 2020 Bradley Whited
|
7
7
|
#
|
8
8
|
# SPDX-License-Identifier: LGPL-3.0-or-later
|
9
9
|
#++
|
10
10
|
|
11
|
+
###
|
12
|
+
# Include this file to only require the files needed to use this
|
13
|
+
# Gem as a library (i.e., don't include CLI-related files).
|
14
|
+
###
|
15
|
+
|
11
16
|
require 'nhkore/article'
|
12
17
|
require 'nhkore/article_scraper'
|
13
18
|
require 'nhkore/cleaner'
|
@@ -31,12 +36,3 @@ require 'nhkore/util'
|
|
31
36
|
require 'nhkore/variator'
|
32
37
|
require 'nhkore/version'
|
33
38
|
require 'nhkore/word'
|
34
|
-
|
35
|
-
module NHKore
|
36
|
-
###
|
37
|
-
# Include this file to only require the files needed to use this
|
38
|
-
# Gem as a library (i.e., don't include CLI-related files).
|
39
|
-
###
|
40
|
-
module Lib
|
41
|
-
end
|
42
|
-
end
|
data/lib/nhkore/missingno.rb
CHANGED
data/lib/nhkore/news.rb
CHANGED
data/lib/nhkore/polisher.rb
CHANGED
data/lib/nhkore/scraper.rb
CHANGED
@@ -3,7 +3,7 @@
|
|
3
3
|
|
4
4
|
#--
|
5
5
|
# This file is part of NHKore.
|
6
|
-
# Copyright (c) 2020
|
6
|
+
# Copyright (c) 2020 Bradley Whited
|
7
7
|
#
|
8
8
|
# SPDX-License-Identifier: LGPL-3.0-or-later
|
9
9
|
#++
|
@@ -21,10 +21,18 @@ module NHKore
|
|
21
21
|
extend AttrBool::Ext
|
22
22
|
|
23
23
|
DEFAULT_HEADER = {
|
24
|
+
# See for better ones:
|
25
|
+
# - https://www.useragentstring.com/pages/Chrome/
|
24
26
|
'user-agent' => UserAgents.sample,
|
25
|
-
|
26
|
-
|
27
|
+
|
28
|
+
'accept' => 'text/html,application/xhtml+xml,application/xml,application/rss+xml,text/xml;' \
|
29
|
+
'q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
|
30
|
+
'accept-language' => 'en;q=0.9,ja-JP;q=0.8,ja',
|
31
|
+
'cache-control' => 'max-age=0',
|
27
32
|
'dnt' => '1',
|
33
|
+
'ect' => '4g',
|
34
|
+
'priority' => 'u=0, i',
|
35
|
+
'upgrade-insecure-requests' => '1',
|
28
36
|
}.freeze
|
29
37
|
|
30
38
|
attr_accessor? :eat_cookie
|
data/lib/nhkore/search_link.rb
CHANGED
@@ -3,7 +3,7 @@
|
|
3
3
|
|
4
4
|
#--
|
5
5
|
# This file is part of NHKore.
|
6
|
-
# Copyright (c) 2020
|
6
|
+
# Copyright (c) 2020 Bradley Whited
|
7
7
|
#
|
8
8
|
# SPDX-License-Identifier: LGPL-3.0-or-later
|
9
9
|
#++
|
@@ -111,19 +111,26 @@ module NHKore
|
|
111
111
|
super(url,**kargs)
|
112
112
|
end
|
113
113
|
|
114
|
-
# rubocop:disable Lint/UnusedMethodArgument
|
115
114
|
def self.build_url(site,count: DEFAULT_RESULT_COUNT,**_kargs)
|
116
115
|
url = ''.dup
|
117
116
|
|
118
117
|
url << 'https://www.bing.com/search?'
|
119
118
|
url << URI.encode_www_form(
|
120
119
|
q: "site:#{site}",
|
121
|
-
|
120
|
+
count: count,
|
121
|
+
|
122
|
+
qs: 'n',
|
123
|
+
sp: '-1',
|
124
|
+
lq: '0',
|
125
|
+
pq: "site:#{site}",
|
126
|
+
sc: '1-25',
|
127
|
+
sk: '',
|
128
|
+
first: '1',
|
129
|
+
FORM: 'PERE',
|
122
130
|
)
|
123
131
|
|
124
132
|
return url
|
125
133
|
end
|
126
|
-
# rubocop:enable Lint/UnusedMethodArgument
|
127
134
|
|
128
135
|
def scrape(slinks,page = NextPage.new())
|
129
136
|
next_page,link_count = scrape_html(slinks,page)
|
@@ -147,7 +154,7 @@ module NHKore
|
|
147
154
|
|
148
155
|
next if ignore_link?(href)
|
149
156
|
|
150
|
-
if (md = href.match(/first=(\d+)/))
|
157
|
+
if (md = href.match(/first=(\d+)/i)) && href =~ /FORM=PERE/i
|
151
158
|
count = md[1].to_i
|
152
159
|
|
153
160
|
if count > page.count && (next_page.count < 0 || count < next_page.count)
|
data/lib/nhkore/sifter.rb
CHANGED
@@ -3,7 +3,7 @@
|
|
3
3
|
|
4
4
|
#--
|
5
5
|
# This file is part of NHKore.
|
6
|
-
# Copyright (c) 2020
|
6
|
+
# Copyright (c) 2020 Bradley Whited
|
7
7
|
#
|
8
8
|
# SPDX-License-Identifier: LGPL-3.0-or-later
|
9
9
|
#++
|
@@ -322,7 +322,7 @@ module NHKore
|
|
322
322
|
end
|
323
323
|
|
324
324
|
def sift
|
325
|
-
|
325
|
+
result = Article.new
|
326
326
|
|
327
327
|
@articles.each do |article|
|
328
328
|
next if filter?(article)
|
@@ -333,11 +333,11 @@ module NHKore
|
|
333
333
|
next if word.freq <= 1
|
334
334
|
next if word.word =~ /\p{Latin}|[[:digit:]]/
|
335
335
|
|
336
|
-
|
336
|
+
result.add_word(word,use_freq: true)
|
337
337
|
end
|
338
338
|
end
|
339
339
|
|
340
|
-
words =
|
340
|
+
words = result.words.values
|
341
341
|
|
342
342
|
words.sort! do |word1,word2|
|
343
343
|
# Order by freq DESC (most frequent words to top).
|
data/lib/nhkore/splitter.rb
CHANGED
data/lib/nhkore/user_agents.rb
CHANGED
data/lib/nhkore/util.rb
CHANGED
data/lib/nhkore/variator.rb
CHANGED
data/lib/nhkore/version.rb
CHANGED
@@ -3,11 +3,11 @@
|
|
3
3
|
|
4
4
|
#--
|
5
5
|
# This file is part of NHKore.
|
6
|
-
# Copyright (c) 2020
|
6
|
+
# Copyright (c) 2020 Bradley Whited
|
7
7
|
#
|
8
8
|
# SPDX-License-Identifier: LGPL-3.0-or-later
|
9
9
|
#++
|
10
10
|
|
11
11
|
module NHKore
|
12
|
-
VERSION = '0.3.
|
12
|
+
VERSION = '0.3.22'
|
13
13
|
end
|
data/lib/nhkore/word.rb
CHANGED
data/lib/nhkore.rb
CHANGED
@@ -3,7 +3,7 @@
|
|
3
3
|
|
4
4
|
#--
|
5
5
|
# This file is part of NHKore.
|
6
|
-
# Copyright (c) 2020
|
6
|
+
# Copyright (c) 2020 Bradley Whited
|
7
7
|
#
|
8
8
|
# SPDX-License-Identifier: LGPL-3.0-or-later
|
9
9
|
#++
|
@@ -15,14 +15,8 @@ if TESTING
|
|
15
15
|
require 'bundler/setup'
|
16
16
|
end
|
17
17
|
|
18
|
-
require 'nhkore/app'
|
19
18
|
require 'nhkore/lib'
|
20
|
-
|
21
|
-
require 'nhkore/cli/fx_cmd'
|
22
|
-
require 'nhkore/cli/get_cmd'
|
23
|
-
require 'nhkore/cli/news_cmd'
|
24
|
-
require 'nhkore/cli/search_cmd'
|
25
|
-
require 'nhkore/cli/sift_cmd'
|
19
|
+
require 'nhkore/app'
|
26
20
|
|
27
21
|
module NHKore
|
28
22
|
def self.run(args = ARGV)
|
data/nhkore.gemspec
CHANGED
@@ -6,7 +6,7 @@ require_relative 'lib/nhkore/version'
|
|
6
6
|
Gem::Specification.new do |spec|
|
7
7
|
spec.name = 'nhkore'
|
8
8
|
spec.version = NHKore::VERSION
|
9
|
-
spec.authors = ['
|
9
|
+
spec.authors = ['Bradley Whited']
|
10
10
|
spec.email = ['code@esotericpig.com']
|
11
11
|
spec.licenses = ['LGPL-3.0-or-later']
|
12
12
|
spec.homepage = 'https://github.com/esotericpig/nhkore'
|
@@ -21,7 +21,7 @@ Gem::Specification.new do |spec|
|
|
21
21
|
'homepage_uri' => 'https://github.com/esotericpig/nhkore',
|
22
22
|
'source_code_uri' => 'https://github.com/esotericpig/nhkore',
|
23
23
|
'bug_tracker_uri' => 'https://github.com/esotericpig/nhkore/issues',
|
24
|
-
'changelog_uri' => 'https://github.com/esotericpig/nhkore/blob/
|
24
|
+
'changelog_uri' => 'https://github.com/esotericpig/nhkore/blob/v0.3/CHANGELOG.md',
|
25
25
|
# 'documentation_uri' => '',
|
26
26
|
# 'wiki_uri' => '',
|
27
27
|
# 'mailing_list_uri' => '',
|
@@ -51,23 +51,28 @@ Gem::Specification.new do |spec|
|
|
51
51
|
spec.extra_rdoc_files,
|
52
52
|
].flatten
|
53
53
|
|
54
|
-
|
55
|
-
spec.add_dependency 'bimyou_segmenter'
|
56
|
-
spec.add_dependency '
|
57
|
-
spec.add_dependency '
|
58
|
-
|
59
|
-
spec.add_dependency '
|
60
|
-
spec.add_dependency 'http-cookie'
|
61
|
-
spec.add_dependency '
|
62
|
-
spec.add_dependency '
|
63
|
-
spec.add_dependency '
|
64
|
-
|
65
|
-
spec.add_dependency '
|
66
|
-
spec.add_dependency '
|
67
|
-
spec.add_dependency 'rubyzip'
|
68
|
-
|
69
|
-
spec.add_dependency '
|
70
|
-
spec.add_dependency '
|
54
|
+
# Japanese.
|
55
|
+
spec.add_dependency 'bimyou_segmenter' ,'~> 1.2' # Splits Japanese sentences into words.
|
56
|
+
spec.add_dependency 'japanese_deinflector' ,'~> 0.0' # Un-conjugates Japanese words (dictionary form).
|
57
|
+
spec.add_dependency 'tiny_segmenter' ,'~> 0.0' # Splits Japanese sentences into words.
|
58
|
+
# Network/Scraping.
|
59
|
+
spec.add_dependency 'down' ,'~> 5.4' # Downloads files (GetCmd).
|
60
|
+
spec.add_dependency 'http-cookie' ,'~> 1.0' # Parses/Sets cookies [(Bing)Scraper].
|
61
|
+
spec.add_dependency 'nokogiri' ,'~> 1' # Parses HTML.
|
62
|
+
spec.add_dependency 'public_suffix' ,'~> 6.0' # Parses URL domain names.
|
63
|
+
spec.add_dependency 'rss' ,'~> 0.3' # Parses RSS feeds [(Bing)Scraper].
|
64
|
+
# Data/Files.
|
65
|
+
spec.add_dependency 'csv' ,'~> 3.3' # Outputs CSV.
|
66
|
+
spec.add_dependency 'psychgus' ,'~> 1.3' # Styles Psych YAML.
|
67
|
+
spec.add_dependency 'rubyzip' ,'~> 2.4' # Extracts Zip files (GetCmd).
|
68
|
+
# CLI.
|
69
|
+
spec.add_dependency 'cri' ,'~> 2.15' # CLI commands/options.
|
70
|
+
spec.add_dependency 'highline' ,'~> 3.1' # CLI IO.
|
71
|
+
spec.add_dependency 'rainbow' ,'~> 3.1' # CLI color output.
|
72
|
+
spec.add_dependency 'tty-progressbar' ,'~> 0.18' # CLI progress bars.
|
73
|
+
spec.add_dependency 'tty-spinner' ,'~> 0.9' # CLI spinning progress.
|
74
|
+
# Utils.
|
75
|
+
spec.add_dependency 'attr_bool' ,'~> 0.2' # attr_accessor?/attr_reader?.
|
71
76
|
|
72
77
|
spec.post_install_message = <<~MSG
|
73
78
|
+=============================================================================+
|
@@ -81,7 +86,4 @@ Gem::Specification.new do |spec|
|
|
81
86
|
| Changelog: #{spec.metadata['changelog_uri']}
|
82
87
|
+=============================================================================+
|
83
88
|
MSG
|
84
|
-
|
85
|
-
# Uncomment to see max line length:
|
86
|
-
# puts spec.post_install_message.split("\n").map(&:length).max
|
87
89
|
end
|
data/samples/looper.rb
CHANGED
data/test/nhkore/test_helper.rb
CHANGED
data/test/nhkore_test.rb
CHANGED
metadata
CHANGED
@@ -1,141 +1,141 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: nhkore
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.3.
|
4
|
+
version: 0.3.22
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
|
-
-
|
7
|
+
- Bradley Whited
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2025-
|
11
|
+
date: 2025-05-01 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
|
-
name:
|
14
|
+
name: bimyou_segmenter
|
15
15
|
requirement: !ruby/object:Gem::Requirement
|
16
16
|
requirements:
|
17
17
|
- - "~>"
|
18
18
|
- !ruby/object:Gem::Version
|
19
|
-
version: '
|
19
|
+
version: '1.2'
|
20
20
|
type: :runtime
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
24
|
- - "~>"
|
25
25
|
- !ruby/object:Gem::Version
|
26
|
-
version: '
|
26
|
+
version: '1.2'
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
|
-
name:
|
28
|
+
name: japanese_deinflector
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
30
30
|
requirements:
|
31
31
|
- - "~>"
|
32
32
|
- !ruby/object:Gem::Version
|
33
|
-
version: '
|
33
|
+
version: '0.0'
|
34
34
|
type: :runtime
|
35
35
|
prerelease: false
|
36
36
|
version_requirements: !ruby/object:Gem::Requirement
|
37
37
|
requirements:
|
38
38
|
- - "~>"
|
39
39
|
- !ruby/object:Gem::Version
|
40
|
-
version: '
|
40
|
+
version: '0.0'
|
41
41
|
- !ruby/object:Gem::Dependency
|
42
|
-
name:
|
42
|
+
name: tiny_segmenter
|
43
43
|
requirement: !ruby/object:Gem::Requirement
|
44
44
|
requirements:
|
45
45
|
- - "~>"
|
46
46
|
- !ruby/object:Gem::Version
|
47
|
-
version: '
|
47
|
+
version: '0.0'
|
48
48
|
type: :runtime
|
49
49
|
prerelease: false
|
50
50
|
version_requirements: !ruby/object:Gem::Requirement
|
51
51
|
requirements:
|
52
52
|
- - "~>"
|
53
53
|
- !ruby/object:Gem::Version
|
54
|
-
version: '
|
54
|
+
version: '0.0'
|
55
55
|
- !ruby/object:Gem::Dependency
|
56
|
-
name:
|
56
|
+
name: down
|
57
57
|
requirement: !ruby/object:Gem::Requirement
|
58
58
|
requirements:
|
59
59
|
- - "~>"
|
60
60
|
- !ruby/object:Gem::Version
|
61
|
-
version: '
|
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: '
|
68
|
+
version: '5.4'
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
|
-
name:
|
70
|
+
name: http-cookie
|
71
71
|
requirement: !ruby/object:Gem::Requirement
|
72
72
|
requirements:
|
73
73
|
- - "~>"
|
74
74
|
- !ruby/object:Gem::Version
|
75
|
-
version: '
|
75
|
+
version: '1.0'
|
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: '1.0'
|
83
83
|
- !ruby/object:Gem::Dependency
|
84
|
-
name:
|
84
|
+
name: nokogiri
|
85
85
|
requirement: !ruby/object:Gem::Requirement
|
86
86
|
requirements:
|
87
87
|
- - "~>"
|
88
88
|
- !ruby/object:Gem::Version
|
89
|
-
version: '
|
89
|
+
version: '1'
|
90
90
|
type: :runtime
|
91
91
|
prerelease: false
|
92
92
|
version_requirements: !ruby/object:Gem::Requirement
|
93
93
|
requirements:
|
94
94
|
- - "~>"
|
95
95
|
- !ruby/object:Gem::Version
|
96
|
-
version: '
|
96
|
+
version: '1'
|
97
97
|
- !ruby/object:Gem::Dependency
|
98
|
-
name:
|
98
|
+
name: public_suffix
|
99
99
|
requirement: !ruby/object:Gem::Requirement
|
100
100
|
requirements:
|
101
101
|
- - "~>"
|
102
102
|
- !ruby/object:Gem::Version
|
103
|
-
version: '
|
103
|
+
version: '6.0'
|
104
104
|
type: :runtime
|
105
105
|
prerelease: false
|
106
106
|
version_requirements: !ruby/object:Gem::Requirement
|
107
107
|
requirements:
|
108
108
|
- - "~>"
|
109
109
|
- !ruby/object:Gem::Version
|
110
|
-
version: '
|
110
|
+
version: '6.0'
|
111
111
|
- !ruby/object:Gem::Dependency
|
112
|
-
name:
|
112
|
+
name: rss
|
113
113
|
requirement: !ruby/object:Gem::Requirement
|
114
114
|
requirements:
|
115
115
|
- - "~>"
|
116
116
|
- !ruby/object:Gem::Version
|
117
|
-
version: '0.
|
117
|
+
version: '0.3'
|
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: '0.
|
124
|
+
version: '0.3'
|
125
125
|
- !ruby/object:Gem::Dependency
|
126
|
-
name:
|
126
|
+
name: csv
|
127
127
|
requirement: !ruby/object:Gem::Requirement
|
128
128
|
requirements:
|
129
129
|
- - "~>"
|
130
130
|
- !ruby/object:Gem::Version
|
131
|
-
version: '
|
131
|
+
version: '3.3'
|
132
132
|
type: :runtime
|
133
133
|
prerelease: false
|
134
134
|
version_requirements: !ruby/object:Gem::Requirement
|
135
135
|
requirements:
|
136
136
|
- - "~>"
|
137
137
|
- !ruby/object:Gem::Version
|
138
|
-
version: '
|
138
|
+
version: '3.3'
|
139
139
|
- !ruby/object:Gem::Dependency
|
140
140
|
name: psychgus
|
141
141
|
requirement: !ruby/object:Gem::Requirement
|
@@ -151,103 +151,103 @@ dependencies:
|
|
151
151
|
- !ruby/object:Gem::Version
|
152
152
|
version: '1.3'
|
153
153
|
- !ruby/object:Gem::Dependency
|
154
|
-
name:
|
154
|
+
name: rubyzip
|
155
155
|
requirement: !ruby/object:Gem::Requirement
|
156
156
|
requirements:
|
157
157
|
- - "~>"
|
158
158
|
- !ruby/object:Gem::Version
|
159
|
-
version: '
|
159
|
+
version: '2.4'
|
160
160
|
type: :runtime
|
161
161
|
prerelease: false
|
162
162
|
version_requirements: !ruby/object:Gem::Requirement
|
163
163
|
requirements:
|
164
164
|
- - "~>"
|
165
165
|
- !ruby/object:Gem::Version
|
166
|
-
version: '
|
166
|
+
version: '2.4'
|
167
167
|
- !ruby/object:Gem::Dependency
|
168
|
-
name:
|
168
|
+
name: cri
|
169
169
|
requirement: !ruby/object:Gem::Requirement
|
170
170
|
requirements:
|
171
171
|
- - "~>"
|
172
172
|
- !ruby/object:Gem::Version
|
173
|
-
version: '
|
173
|
+
version: '2.15'
|
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: '
|
180
|
+
version: '2.15'
|
181
181
|
- !ruby/object:Gem::Dependency
|
182
|
-
name:
|
182
|
+
name: highline
|
183
183
|
requirement: !ruby/object:Gem::Requirement
|
184
184
|
requirements:
|
185
185
|
- - "~>"
|
186
186
|
- !ruby/object:Gem::Version
|
187
|
-
version: '
|
187
|
+
version: '3.1'
|
188
188
|
type: :runtime
|
189
189
|
prerelease: false
|
190
190
|
version_requirements: !ruby/object:Gem::Requirement
|
191
191
|
requirements:
|
192
192
|
- - "~>"
|
193
193
|
- !ruby/object:Gem::Version
|
194
|
-
version: '
|
194
|
+
version: '3.1'
|
195
195
|
- !ruby/object:Gem::Dependency
|
196
|
-
name:
|
196
|
+
name: rainbow
|
197
197
|
requirement: !ruby/object:Gem::Requirement
|
198
198
|
requirements:
|
199
199
|
- - "~>"
|
200
200
|
- !ruby/object:Gem::Version
|
201
|
-
version: '
|
201
|
+
version: '3.1'
|
202
202
|
type: :runtime
|
203
203
|
prerelease: false
|
204
204
|
version_requirements: !ruby/object:Gem::Requirement
|
205
205
|
requirements:
|
206
206
|
- - "~>"
|
207
207
|
- !ruby/object:Gem::Version
|
208
|
-
version: '
|
208
|
+
version: '3.1'
|
209
209
|
- !ruby/object:Gem::Dependency
|
210
|
-
name:
|
210
|
+
name: tty-progressbar
|
211
211
|
requirement: !ruby/object:Gem::Requirement
|
212
212
|
requirements:
|
213
213
|
- - "~>"
|
214
214
|
- !ruby/object:Gem::Version
|
215
|
-
version: '0.
|
215
|
+
version: '0.18'
|
216
216
|
type: :runtime
|
217
217
|
prerelease: false
|
218
218
|
version_requirements: !ruby/object:Gem::Requirement
|
219
219
|
requirements:
|
220
220
|
- - "~>"
|
221
221
|
- !ruby/object:Gem::Version
|
222
|
-
version: '0.
|
222
|
+
version: '0.18'
|
223
223
|
- !ruby/object:Gem::Dependency
|
224
|
-
name: tty-
|
224
|
+
name: tty-spinner
|
225
225
|
requirement: !ruby/object:Gem::Requirement
|
226
226
|
requirements:
|
227
227
|
- - "~>"
|
228
228
|
- !ruby/object:Gem::Version
|
229
|
-
version: '0.
|
229
|
+
version: '0.9'
|
230
230
|
type: :runtime
|
231
231
|
prerelease: false
|
232
232
|
version_requirements: !ruby/object:Gem::Requirement
|
233
233
|
requirements:
|
234
234
|
- - "~>"
|
235
235
|
- !ruby/object:Gem::Version
|
236
|
-
version: '0.
|
236
|
+
version: '0.9'
|
237
237
|
- !ruby/object:Gem::Dependency
|
238
|
-
name:
|
238
|
+
name: attr_bool
|
239
239
|
requirement: !ruby/object:Gem::Requirement
|
240
240
|
requirements:
|
241
241
|
- - "~>"
|
242
242
|
- !ruby/object:Gem::Version
|
243
|
-
version: '0.
|
243
|
+
version: '0.2'
|
244
244
|
type: :runtime
|
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: '0.
|
250
|
+
version: '0.2'
|
251
251
|
description: |
|
252
252
|
Scrapes NHK News Web (Easy) for the word frequency (core list) for Japanese language learners.
|
253
253
|
Includes a CLI app and a scraper library.
|
@@ -312,23 +312,23 @@ metadata:
|
|
312
312
|
homepage_uri: https://github.com/esotericpig/nhkore
|
313
313
|
source_code_uri: https://github.com/esotericpig/nhkore
|
314
314
|
bug_tracker_uri: https://github.com/esotericpig/nhkore/issues
|
315
|
-
changelog_uri: https://github.com/esotericpig/nhkore/blob/
|
315
|
+
changelog_uri: https://github.com/esotericpig/nhkore/blob/v0.3/CHANGELOG.md
|
316
316
|
post_install_message: |
|
317
317
|
+=============================================================================+
|
318
|
-
| NHKore v0.3.
|
318
|
+
| NHKore v0.3.22
|
319
319
|
|
|
320
320
|
| You can now use [nhkore] on the command line.
|
321
321
|
|
|
322
322
|
| Homepage: https://github.com/esotericpig/nhkore
|
323
323
|
| Code: https://github.com/esotericpig/nhkore
|
324
324
|
| Bugs: https://github.com/esotericpig/nhkore/issues
|
325
|
-
| Changelog: https://github.com/esotericpig/nhkore/blob/
|
325
|
+
| Changelog: https://github.com/esotericpig/nhkore/blob/v0.3/CHANGELOG.md
|
326
326
|
+=============================================================================+
|
327
327
|
rdoc_options:
|
328
328
|
- "--hyperlink-all"
|
329
329
|
- "--show-hash"
|
330
330
|
- "--title"
|
331
|
-
- NHKore v0.3.
|
331
|
+
- NHKore v0.3.22 Doc
|
332
332
|
- "--main"
|
333
333
|
- README.md
|
334
334
|
require_paths:
|