cantonese 0.1.0

Sign up to get free protection for your applications and to get access to all the features.
@@ -0,0 +1,17 @@
1
+ require 'spec_helper'
2
+ require 'cantonese/scraper/classified_scraper'
3
+
4
+ describe Cantonese::Scraper::ClassifiedScraper do
5
+ context "#crawl", :vcr => {:record => :new_episodes} do
6
+ it "should fetch list of classified words" do
7
+ classified = subject.crawl
8
+ expect(classified).to be_a(Array)
9
+
10
+ classified.each do |word|
11
+ expect(word[:radical_id]).to_not be_nil
12
+ expect(word[:text]).to_not be_nil
13
+ expect(word[:type]).to_not be_nil
14
+ end
15
+ end
16
+ end
17
+ end
@@ -0,0 +1,16 @@
1
+ require 'spec_helper'
2
+ require 'cantonese/scraper/radical_scraper'
3
+
4
+ describe Cantonese::Scraper::RadicalScraper do
5
+ context "#crawl", :vcr => {:record => :new_episodes} do
6
+ it "should list of radicals" do
7
+ radicals = subject.crawl
8
+ expect(radicals).to be_a(Array)
9
+ radicals.each do |radical|
10
+ expect(radical[:name]).to_not be_nil
11
+ expect(radical[:stroke]).to_not be_nil
12
+ expect(radical[:id]).to_not be_nil
13
+ end
14
+ end
15
+ end
16
+ end
@@ -0,0 +1,62 @@
1
+ require 'spec_helper'
2
+ require 'cantonese/scraper/word_scraper'
3
+
4
+ describe Cantonese::Scraper::WordScraper do
5
+ context "#crawl", :vcr => {:record => :new_episodes} do
6
+ it "should return detail of a word" do
7
+ word = subject.crawl("一")
8
+ expect(word).to be_a(Hash)
9
+
10
+ expect(word[:text]).to eq("一")
11
+
12
+ expect(word[:stroke]).to eq(1)
13
+ expect(word[:radical_id]).to eq(1)
14
+ expect(word[:classified]).to be_include("單讀音字")
15
+
16
+ expect(word[:big5]).to eq("A440")
17
+ expect(word[:chanjie]).to eq("一")
18
+ expect(word[:frequency]).to eq("2 / 166396")
19
+ expect(word[:combination]).to be_a(Array)
20
+ expect(word[:combination]).to be_include("山")
21
+
22
+ expect(word[:syllable]).to be_a(Array)
23
+ expect(word[:syllable][0][:initial]).to eq("j")
24
+ expect(word[:syllable][0][:final]).to eq("at")
25
+ expect(word[:syllable][0][:tone]).to eq("1")
26
+
27
+ expect(word[:syllable][0][:examples]).to be_a(Array)
28
+ expect(word[:syllable][0][:examples]).to be_include("一視同仁")
29
+ end
30
+
31
+ it "should return detail of a word with multiple sounds" do
32
+ word = subject.crawl("可")
33
+ expect(word).to be_a(Hash)
34
+
35
+ expect(word[:text]).to eq("可")
36
+
37
+ expect(word[:stroke]).to eq(5)
38
+ expect(word[:radical_id]).to eq(30)
39
+ expect(word[:classified]).to eq("破音字")
40
+
41
+ expect(word[:big5]).to eq("A569")
42
+ expect(word[:chanjie]).to eq("一弓口")
43
+ expect(word[:frequency]).to eq("36 / 40754")
44
+ expect(word[:combination]).to be_a(Array)
45
+ expect(word[:combination]).to be_include("不")
46
+
47
+ expect(word[:syllable]).to be_a(Array)
48
+ expect(word[:syllable][0][:initial]).to eq("h")
49
+ expect(word[:syllable][0][:final]).to eq("ak")
50
+ expect(word[:syllable][0][:tone]).to eq("1")
51
+ expect(word[:syllable][0][:examples]).to be_a(Array)
52
+ expect(word[:syllable][0][:examples]).to be_include("可汗")
53
+
54
+ expect(word[:syllable][1][:initial]).to eq("h")
55
+ expect(word[:syllable][1][:final]).to eq("o")
56
+ expect(word[:syllable][1][:tone]).to eq("2")
57
+ expect(word[:syllable][1][:examples]).to be_a(Array)
58
+ expect(word[:syllable][1][:examples]).to be_include("可歌可泣")
59
+ end
60
+
61
+ end
62
+ end
@@ -0,0 +1,10 @@
1
+ $LOAD_PATH << "lib"
2
+
3
+ require 'vcr'
4
+ require 'pry'
5
+
6
+ VCR.configure do |c|
7
+ c.cassette_library_dir = 'spec/fixtures/cassettes'
8
+ c.hook_into :webmock
9
+ c.configure_rspec_metadata!
10
+ end
metadata ADDED
@@ -0,0 +1,169 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: cantonese
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.1.0
5
+ platform: ruby
6
+ authors:
7
+ - Francis Chong
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2014-03-31 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ name: nokogiri
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: bundler
29
+ requirement: !ruby/object:Gem::Requirement
30
+ requirements:
31
+ - - "~>"
32
+ - !ruby/object:Gem::Version
33
+ version: '1.5'
34
+ type: :development
35
+ prerelease: false
36
+ version_requirements: !ruby/object:Gem::Requirement
37
+ requirements:
38
+ - - "~>"
39
+ - !ruby/object:Gem::Version
40
+ version: '1.5'
41
+ - !ruby/object:Gem::Dependency
42
+ name: rake
43
+ requirement: !ruby/object:Gem::Requirement
44
+ requirements:
45
+ - - ">="
46
+ - !ruby/object:Gem::Version
47
+ version: '0'
48
+ type: :development
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: webmock
57
+ requirement: !ruby/object:Gem::Requirement
58
+ requirements:
59
+ - - ">="
60
+ - !ruby/object:Gem::Version
61
+ version: '0'
62
+ type: :development
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: vcr
71
+ requirement: !ruby/object:Gem::Requirement
72
+ requirements:
73
+ - - ">="
74
+ - !ruby/object:Gem::Version
75
+ version: '0'
76
+ type: :development
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: rspec
85
+ requirement: !ruby/object:Gem::Requirement
86
+ requirements:
87
+ - - ">="
88
+ - !ruby/object:Gem::Version
89
+ version: '0'
90
+ type: :development
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: pry
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
+ description:
112
+ email:
113
+ - francis@ignition.hk
114
+ executables: []
115
+ extensions: []
116
+ extra_rdoc_files: []
117
+ files:
118
+ - ".gitignore"
119
+ - Gemfile
120
+ - LICENSE.txt
121
+ - README.md
122
+ - Rakefile
123
+ - cantonese.gemspec
124
+ - lib/cantonese.rb
125
+ - lib/cantonese/scraper/classified_scraper.rb
126
+ - lib/cantonese/scraper/radical_scraper.rb
127
+ - lib/cantonese/scraper/word_scraper.rb
128
+ - lib/cantonese/version.rb
129
+ - spec/fixtures/cassettes/Cantonese_Scraper_ClassifiedScraper/_crawl/should_fetch_list_of_classified_words.yml
130
+ - spec/fixtures/cassettes/Cantonese_Scraper_RadicalScraper/_crawl/should_list_of_radicals.yml
131
+ - spec/fixtures/cassettes/Cantonese_Scraper_WordScraper/_crawl/should_return_detail_of_a_word.yml
132
+ - spec/fixtures/cassettes/Cantonese_Scraper_WordScraper/_crawl/should_return_detail_of_a_word_with_multiple_sounds.yml
133
+ - spec/scraper/classified_scraper_spec.rb
134
+ - spec/scraper/radical_scraper_spec.rb
135
+ - spec/scraper/word_scraper_spec.rb
136
+ - spec/spec_helper.rb
137
+ homepage: https://github.com/siuying/cantonese
138
+ licenses:
139
+ - MIT
140
+ metadata: {}
141
+ post_install_message:
142
+ rdoc_options: []
143
+ require_paths:
144
+ - lib
145
+ required_ruby_version: !ruby/object:Gem::Requirement
146
+ requirements:
147
+ - - ">="
148
+ - !ruby/object:Gem::Version
149
+ version: '0'
150
+ required_rubygems_version: !ruby/object:Gem::Requirement
151
+ requirements:
152
+ - - ">="
153
+ - !ruby/object:Gem::Version
154
+ version: '0'
155
+ requirements: []
156
+ rubyforge_project:
157
+ rubygems_version: 2.2.0
158
+ signing_key:
159
+ specification_version: 4
160
+ summary: Set of scraper and processor to fetch Cantonese data.
161
+ test_files:
162
+ - spec/fixtures/cassettes/Cantonese_Scraper_ClassifiedScraper/_crawl/should_fetch_list_of_classified_words.yml
163
+ - spec/fixtures/cassettes/Cantonese_Scraper_RadicalScraper/_crawl/should_list_of_radicals.yml
164
+ - spec/fixtures/cassettes/Cantonese_Scraper_WordScraper/_crawl/should_return_detail_of_a_word.yml
165
+ - spec/fixtures/cassettes/Cantonese_Scraper_WordScraper/_crawl/should_return_detail_of_a_word_with_multiple_sounds.yml
166
+ - spec/scraper/classified_scraper_spec.rb
167
+ - spec/scraper/radical_scraper_spec.rb
168
+ - spec/scraper/word_scraper_spec.rb
169
+ - spec/spec_helper.rb