that_language 0.1.0 → 0.1.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +185 -22
- data/bin/console +1 -1
- data/lib/that_language.rb +4 -0
- data/lib/that_language/configuration.rb +6 -4
- data/lib/that_language/result.rb +5 -1
- data/lib/that_language/version.rb +1 -1
- data/that_language.gemspec +3 -2
- metadata +17 -3
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 41ecd55149abde5d1b27e64be73afd2e63d0b821
|
4
|
+
data.tar.gz: 82764566978fa2fdee98eaf3f8d7f7b71bdb6742
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: f4c718d69f9f1f38da49d24f80d01507064aa32a6571bfbe31ac99f2ac5ce45fdbd2437c2a9599cb1be6d9f36ae4838ec1783491826e1bd4642b714f9c5e83f3
|
7
|
+
data.tar.gz: 8d1482da930ffe300f288476b11274f22b001df698f49d7901fdfbb6944b827b75f37a0f3650892ce3433932fb843dd918c5425a3b285cbd7c99a95229624233
|
data/README.md
CHANGED
@@ -1,15 +1,11 @@
|
|
1
|
-
#
|
2
|
-
|
3
|
-
Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/detect_language`. To experiment with that code, run `bin/console` for an interactive prompt.
|
4
|
-
|
5
|
-
TODO: Delete this and the text above, and describe your gem
|
1
|
+
# ThatLanguage
|
6
2
|
|
7
3
|
## Installation
|
8
4
|
|
9
5
|
Add this line to your application's Gemfile:
|
10
6
|
|
11
7
|
```ruby
|
12
|
-
gem '
|
8
|
+
gem 'that_language'
|
13
9
|
```
|
14
10
|
|
15
11
|
And then execute:
|
@@ -18,32 +14,199 @@ And then execute:
|
|
18
14
|
|
19
15
|
Or install it yourself as:
|
20
16
|
|
21
|
-
$ gem install
|
17
|
+
$ gem install that_language
|
18
|
+
|
19
|
+
## Examples
|
20
|
+
|
21
|
+
```ruby
|
22
|
+
text = "This is just a random english sentence."
|
23
|
+
|
24
|
+
## == Language
|
25
|
+
|
26
|
+
ThatLanguage.language(text)
|
27
|
+
# => :English
|
28
|
+
|
29
|
+
|
30
|
+
## == LanguageCode
|
31
|
+
|
32
|
+
ThatLanguage.language_code(text)
|
33
|
+
# => "en"
|
34
|
+
|
35
|
+
|
36
|
+
## == Detect
|
37
|
+
|
38
|
+
detect = ThatLanguage.detect(text)
|
39
|
+
# => #<ThatLanguage::Result:...
|
40
|
+
|
41
|
+
detect.language
|
42
|
+
# => :English
|
43
|
+
|
44
|
+
detect.language_code
|
45
|
+
# => "en"
|
46
|
+
|
47
|
+
detect.confidence
|
48
|
+
# => 0.5631093821386951
|
49
|
+
|
50
|
+
detect.to_h
|
51
|
+
# =>
|
52
|
+
# {
|
53
|
+
# language: :English,
|
54
|
+
# language_code: "en",
|
55
|
+
# confidence: 0.5631093821386951,
|
56
|
+
# value: 3.9417656749708656,
|
57
|
+
# hit_ratio: 0.8571428571428571,
|
58
|
+
# hit_count: 6,
|
59
|
+
# words_count: 7
|
60
|
+
# }
|
61
|
+
|
62
|
+
|
63
|
+
## == Details
|
64
|
+
|
65
|
+
details = ThatLanguage.details(text)
|
66
|
+
# => #<ThatLanguage::ResultSet:...
|
67
|
+
|
68
|
+
winner = details.winner
|
69
|
+
# => #<ThatLanguage::Result:...
|
70
|
+
|
71
|
+
results = details.results
|
72
|
+
# => [#<ThatLanguage::Result, #<ThatLanguage::Result, ...]
|
73
|
+
|
74
|
+
details.to_h
|
75
|
+
# =>
|
76
|
+
# {
|
77
|
+
# "results" => [
|
78
|
+
# {
|
79
|
+
# language: :English,
|
80
|
+
# language_code: "en",
|
81
|
+
# confidence: 0.5631093821386951,
|
82
|
+
# value: 3.9417656749708656,
|
83
|
+
# hit_ratio: 0.8571428571428571,
|
84
|
+
# hit_count: 6,
|
85
|
+
# words_count: 7
|
86
|
+
# },
|
87
|
+
# {
|
88
|
+
# language: :Hungarian,
|
89
|
+
# language_code: "hu",
|
90
|
+
# confidence: 0.21380816083786156,
|
91
|
+
# value: 1.496657125865031,
|
92
|
+
# hit_ratio: 0.42857142857142855,
|
93
|
+
# hit_count: 3,
|
94
|
+
# words_count: 7
|
95
|
+
# },
|
96
|
+
# # ...
|
97
|
+
# ]
|
98
|
+
# }
|
99
|
+
```
|
22
100
|
|
23
101
|
## Supported locales
|
24
102
|
|
25
|
-
|
26
|
-
|
27
|
-
|
28
|
-
|
29
|
-
|
30
|
-
|
31
|
-
|
32
|
-
|
33
|
-
|
34
|
-
|
35
|
-
|
36
|
-
|
103
|
+
```ruby
|
104
|
+
require 'pp'
|
105
|
+
|
106
|
+
pp ThatLanguage.available
|
107
|
+
|
108
|
+
{
|
109
|
+
ak: :Akan,
|
110
|
+
am: :Amharic,
|
111
|
+
ar: :Arabic,
|
112
|
+
as: :Assamese,
|
113
|
+
az: :Azerbaijani,
|
114
|
+
be: :Belarusian,
|
115
|
+
bn: :Bengali,
|
116
|
+
cs: :Czech,
|
117
|
+
da: :Danish,
|
118
|
+
de: :German,
|
119
|
+
el: :Greek,
|
120
|
+
en: :English,
|
121
|
+
es: :Spanish,
|
122
|
+
fa: :Persian,
|
123
|
+
ff: :Fula,
|
124
|
+
fi: :Finnish,
|
125
|
+
fr: :French,
|
126
|
+
gu: :Gujarati,
|
127
|
+
ha: :Hausa,
|
128
|
+
he: :Hebrew,
|
129
|
+
hi: :Hindi,
|
130
|
+
ht: :Haitian,
|
131
|
+
hu: :Hungarian,
|
132
|
+
it: :Italian,
|
133
|
+
ja: :Japanese,
|
134
|
+
jv: :Javanese,
|
135
|
+
kk: :Kazakh,
|
136
|
+
km: :Khmer,
|
137
|
+
kn: :Kannada,
|
138
|
+
ko: :Korean,
|
139
|
+
ku: :Kurdish,
|
140
|
+
mg: :Malagasy,
|
141
|
+
mr: :Marathi,
|
142
|
+
ms: :Malay,
|
143
|
+
my: :Burmese,
|
144
|
+
ne: :Nepali,
|
145
|
+
nl: :Dutch,
|
146
|
+
nn: :"Norwegian Nynorsk",
|
147
|
+
no: :Norwegian,
|
148
|
+
ny: :Chichewa,
|
149
|
+
om: :Oromo,
|
150
|
+
or: :Oriya,
|
151
|
+
pa: :Panjabi,
|
152
|
+
pl: :Polish,
|
153
|
+
ps: :Pashto,
|
154
|
+
pt: :Portuguese,
|
155
|
+
qu: :Quechua,
|
156
|
+
rn: :Kirundi,
|
157
|
+
ro: :Romanian,
|
158
|
+
ru: :Russian,
|
159
|
+
rw: :Kinyarwanda,
|
160
|
+
sd: :Sindhi,
|
161
|
+
si: :Sinhala,
|
162
|
+
sn: :Shona,
|
163
|
+
so: :Somali,
|
164
|
+
su: :Sundanese,
|
165
|
+
sv: :Swedish,
|
166
|
+
ta: :Tamil,
|
167
|
+
te: :Telugu,
|
168
|
+
th: :Thai,
|
169
|
+
tk: :Turkmen,
|
170
|
+
tl: :Tagalog,
|
171
|
+
tr: :Turkish,
|
172
|
+
ug: :Uyghur,
|
173
|
+
uk: :Ukrainian,
|
174
|
+
ur: :Urdu,
|
175
|
+
uz: :Uzbek,
|
176
|
+
vi: :Vietnamese,
|
177
|
+
xh: :Xhosa,
|
178
|
+
yo: :Yoruba,
|
179
|
+
zh: :Chinese,
|
180
|
+
zu: :Zulu
|
181
|
+
}
|
182
|
+
|
183
|
+
```
|
184
|
+
|
185
|
+
## Configure
|
186
|
+
|
187
|
+
To use a custom directory that contains all the wordlists:
|
188
|
+
|
189
|
+
```ruby
|
190
|
+
ThatLanguage.configure do |config|
|
191
|
+
config.wordlist_path = File.join("wordlists", "100k")
|
192
|
+
end
|
193
|
+
```
|
37
194
|
|
38
195
|
## Development
|
39
196
|
|
40
|
-
After checking out the repo, run `bin/setup` to install dependencies.
|
197
|
+
After checking out the repo, run `bin/setup` to install dependencies.
|
198
|
+
Then, run `rake rspec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
41
199
|
|
42
|
-
To install this gem onto your local machine, run `bundle exec rake install`.
|
200
|
+
To install this gem onto your local machine, run `bundle exec rake install`.
|
201
|
+
To release a new version, update the version number in `version.rb`,
|
202
|
+
and then run `bundle exec rake release`, which will create a git tag for the version,
|
203
|
+
push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
|
43
204
|
|
44
205
|
## Contributing
|
45
206
|
|
46
|
-
Bug reports and pull requests are welcome on GitHub at https://github.com/
|
207
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/Deradon/that_language.
|
208
|
+
This project is intended to be a safe, welcoming space for collaboration,
|
209
|
+
and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
|
47
210
|
|
48
211
|
|
49
212
|
## License
|
data/bin/console
CHANGED
data/lib/that_language.rb
CHANGED
@@ -1,11 +1,13 @@
|
|
1
1
|
module ThatLanguage
|
2
2
|
class Configuration
|
3
|
-
|
4
|
-
|
5
|
-
def initialize
|
6
|
-
@wordlist_path = File.absolute_path(
|
3
|
+
def wordlist_path
|
4
|
+
@wordlist_path ||= File.absolute_path(
|
7
5
|
File.join(File.dirname(__FILE__), '../../wordlists/10k/')
|
8
6
|
)
|
9
7
|
end
|
8
|
+
|
9
|
+
def wordlist_path=(path)
|
10
|
+
@wordlist_path = path
|
11
|
+
end
|
10
12
|
end
|
11
13
|
end
|
data/lib/that_language/result.rb
CHANGED
@@ -43,9 +43,13 @@ module ThatLanguage
|
|
43
43
|
value > other.value
|
44
44
|
end
|
45
45
|
|
46
|
+
def language
|
47
|
+
Iso639[language_code]
|
48
|
+
end
|
49
|
+
|
46
50
|
def to_h
|
47
51
|
{
|
48
|
-
language:
|
52
|
+
language: language,
|
49
53
|
language_code: language_code,
|
50
54
|
confidence: confidence,
|
51
55
|
value: value,
|
data/that_language.gemspec
CHANGED
@@ -10,8 +10,8 @@ Gem::Specification.new do |spec|
|
|
10
10
|
spec.email = ["me@patrick-helm.de"]
|
11
11
|
|
12
12
|
spec.summary = %q{Detect language of given text}
|
13
|
-
spec.description = %q{Detect language of given text}
|
14
|
-
spec.homepage = "
|
13
|
+
# spec.description = %q{Detect language of given text}
|
14
|
+
spec.homepage = "https://github.com/Deradon/that_language"
|
15
15
|
spec.license = "MIT"
|
16
16
|
|
17
17
|
# Prevent pushing this gem to RubyGems.org by setting 'allowed_push_host', or
|
@@ -28,6 +28,7 @@ Gem::Specification.new do |spec|
|
|
28
28
|
spec.require_paths = ["lib"]
|
29
29
|
|
30
30
|
spec.add_development_dependency "bundler", "~> 1.10"
|
31
|
+
spec.add_development_dependency "pry"
|
31
32
|
spec.add_development_dependency "rake", "~> 10.0"
|
32
33
|
spec.add_development_dependency "rspec"
|
33
34
|
spec.add_development_dependency "rspec-its"
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: that_language
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Patrick Helm
|
@@ -24,6 +24,20 @@ dependencies:
|
|
24
24
|
- - "~>"
|
25
25
|
- !ruby/object:Gem::Version
|
26
26
|
version: '1.10'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: pry
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
27
41
|
- !ruby/object:Gem::Dependency
|
28
42
|
name: rake
|
29
43
|
requirement: !ruby/object:Gem::Requirement
|
@@ -66,7 +80,7 @@ dependencies:
|
|
66
80
|
- - ">="
|
67
81
|
- !ruby/object:Gem::Version
|
68
82
|
version: '0'
|
69
|
-
description:
|
83
|
+
description:
|
70
84
|
email:
|
71
85
|
- me@patrick-helm.de
|
72
86
|
executables: []
|
@@ -166,7 +180,7 @@ files:
|
|
166
180
|
- wordlists/10k/10000-yo.pstore
|
167
181
|
- wordlists/10k/10000-zh.pstore
|
168
182
|
- wordlists/10k/10000-zu.pstore
|
169
|
-
homepage:
|
183
|
+
homepage: https://github.com/Deradon/that_language
|
170
184
|
licenses:
|
171
185
|
- MIT
|
172
186
|
metadata: {}
|