detect_language 1.0.0
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.
- data/.gitignore +18 -0
- data/.rspec +2 -0
- data/.travis.yml +10 -0
- data/Gemfile +10 -0
- data/LICENSE +22 -0
- data/README.md +51 -0
- data/Rakefile +7 -0
- data/detect_language.gemspec +17 -0
- data/lib/detect_language.rb +39 -0
- data/lib/detect_language/client.rb +67 -0
- data/lib/detect_language/configuration.rb +83 -0
- data/lib/detect_language/exception.rb +5 -0
- data/lib/detect_language/version.rb +3 -0
- data/spec/detect_language_spec.rb +55 -0
- data/spec/spec_helper.rb +7 -0
- metadata +63 -0
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2012 Laurynas Butkus
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,51 @@
|
|
1
|
+
Detect Language API Client [](http://travis-ci.org/detectlanguage/detect_language)
|
2
|
+
========
|
3
|
+
|
4
|
+
Detects language of given text. Returns detected language codes and scores.
|
5
|
+
|
6
|
+
Before using Detect Language API client you setup your personal API key.
|
7
|
+
You can get it by signing up at http://detectlanguage.com
|
8
|
+
|
9
|
+
## Installation
|
10
|
+
|
11
|
+
Add this line to your application's Gemfile:
|
12
|
+
|
13
|
+
gem 'detect_language'
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install detect_language
|
18
|
+
|
19
|
+
### Configuration
|
20
|
+
|
21
|
+
If you are using Rails, create initializer `config/initializers/detect_language.rb` and add following code there.
|
22
|
+
Otherwise just integrate following code into your apps configuration.
|
23
|
+
|
24
|
+
DetectLanguage.configure do |config|
|
25
|
+
config.api_key = "YOUR API KEY"
|
26
|
+
end
|
27
|
+
|
28
|
+
## Usage
|
29
|
+
|
30
|
+
### Language detection
|
31
|
+
|
32
|
+
DetectLanguage.detect("Buenos dias señor")
|
33
|
+
|
34
|
+
#### Result
|
35
|
+
|
36
|
+
[ {"language"=>"es", "isReliable"=>false, "confidence"=>0.3271028037383178},
|
37
|
+
{"language"=>"pt", "isReliable"=>false, "confidence"=>0.08356545961002786} ]
|
38
|
+
|
39
|
+
### Simple language detection
|
40
|
+
|
41
|
+
If you need just a language code you can use `simple_detect`. It returns just the language code.
|
42
|
+
|
43
|
+
DetectLanguage.simple_detect("Buenos dias señor")
|
44
|
+
|
45
|
+
#### Result
|
46
|
+
|
47
|
+
"es"
|
48
|
+
|
49
|
+
## License
|
50
|
+
|
51
|
+
Detect Language API Client is free software, and may be redistributed under the terms specified in the MIT-LICENSE file.
|
data/Rakefile
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
require File.expand_path('../lib/detect_language/version', __FILE__)
|
3
|
+
|
4
|
+
Gem::Specification.new do |gem|
|
5
|
+
gem.authors = ["Laurynas Butkus"]
|
6
|
+
gem.email = ["laurynas.butkus@gmail.com"]
|
7
|
+
gem.description = %q{Language Detection API Client}
|
8
|
+
gem.summary = %q{Detects language of given text. Returns detected language codes and scores.}
|
9
|
+
gem.homepage = "https://github.com/detectlanguage/detect_language"
|
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 = "detect_language"
|
15
|
+
gem.require_paths = ["lib"]
|
16
|
+
gem.version = DetectLanguage::VERSION
|
17
|
+
end
|
@@ -0,0 +1,39 @@
|
|
1
|
+
require "detect_language/version"
|
2
|
+
require "detect_language/exception"
|
3
|
+
require "detect_language/configuration"
|
4
|
+
require "detect_language/client"
|
5
|
+
|
6
|
+
module DetectLanguage
|
7
|
+
class << self
|
8
|
+
attr_writer :configuration
|
9
|
+
|
10
|
+
def configure
|
11
|
+
yield(configuration)
|
12
|
+
end
|
13
|
+
|
14
|
+
# The configuration object.
|
15
|
+
# @see DetectLanguage.configure
|
16
|
+
def configuration
|
17
|
+
@configuration ||= Configuration.new
|
18
|
+
end
|
19
|
+
|
20
|
+
def client
|
21
|
+
@client ||= Client.new(configuration)
|
22
|
+
end
|
23
|
+
|
24
|
+
def detect(text)
|
25
|
+
result = client.execute(:detect, :q => text)
|
26
|
+
result['data']['detections']
|
27
|
+
end
|
28
|
+
|
29
|
+
def simple_detect(text)
|
30
|
+
detections = detect(text)
|
31
|
+
|
32
|
+
if detections.empty?
|
33
|
+
nil
|
34
|
+
else
|
35
|
+
detections[0]['language']
|
36
|
+
end
|
37
|
+
end
|
38
|
+
end
|
39
|
+
end
|
@@ -0,0 +1,67 @@
|
|
1
|
+
require 'net/http'
|
2
|
+
require 'net/https'
|
3
|
+
require 'json'
|
4
|
+
|
5
|
+
module DetectLanguage
|
6
|
+
class Client
|
7
|
+
attr_reader :configuration
|
8
|
+
|
9
|
+
def initialize(configuration)
|
10
|
+
@configuration = configuration
|
11
|
+
end
|
12
|
+
|
13
|
+
def execute(method, params)
|
14
|
+
http = setup_http_connection
|
15
|
+
|
16
|
+
request_params = params.merge(:key => configuration.api_key)
|
17
|
+
|
18
|
+
request = Net::HTTP::Post.new(request_uri(method))
|
19
|
+
request.set_form_data(request_params)
|
20
|
+
request.add_field('User-Agent', configuration.user_agent)
|
21
|
+
|
22
|
+
response = http.request(request)
|
23
|
+
|
24
|
+
case response
|
25
|
+
when Net::HTTPSuccess then
|
26
|
+
parse_response(response.body)
|
27
|
+
else
|
28
|
+
raise "Failure: #{response.class}"
|
29
|
+
end
|
30
|
+
end
|
31
|
+
|
32
|
+
private
|
33
|
+
|
34
|
+
def parse_response(response_body)
|
35
|
+
response = JSON.parse(response_body)
|
36
|
+
|
37
|
+
if response["error"].nil?
|
38
|
+
response
|
39
|
+
else
|
40
|
+
raise Exception.new(response["error"]["message"])
|
41
|
+
end
|
42
|
+
end
|
43
|
+
|
44
|
+
def request_uri(method)
|
45
|
+
"/#{configuration.api_version}/#{method}"
|
46
|
+
end
|
47
|
+
|
48
|
+
def setup_http_connection
|
49
|
+
http =
|
50
|
+
Net::HTTP::Proxy(configuration.proxy_host, configuration.proxy_port, configuration.proxy_user,
|
51
|
+
configuration.proxy_pass).
|
52
|
+
new(configuration.host, configuration.port)
|
53
|
+
|
54
|
+
http.read_timeout = configuration.http_read_timeout
|
55
|
+
http.open_timeout = configuration.http_open_timeout
|
56
|
+
|
57
|
+
if configuration.secure?
|
58
|
+
http.use_ssl = true
|
59
|
+
http.verify_mode = OpenSSL::SSL::VERIFY_PEER
|
60
|
+
else
|
61
|
+
http.use_ssl = false
|
62
|
+
end
|
63
|
+
|
64
|
+
http
|
65
|
+
end
|
66
|
+
end
|
67
|
+
end
|
@@ -0,0 +1,83 @@
|
|
1
|
+
module DetectLanguage
|
2
|
+
class Configuration
|
3
|
+
# The API key for your project, found on your homepage after you login into detectlanguage.com website
|
4
|
+
# Defaults to 'demo', which has a limited number of requests.
|
5
|
+
attr_accessor :api_key
|
6
|
+
|
7
|
+
# The API version you are using (defaults to 0.2).
|
8
|
+
attr_accessor :api_version
|
9
|
+
|
10
|
+
# HTTP request user agent (defaults to 'Detect Language API ruby gem').
|
11
|
+
attr_accessor :user_agent
|
12
|
+
|
13
|
+
# The host to connect to (defaults to ws.detectlanguage.com).
|
14
|
+
attr_accessor :host
|
15
|
+
|
16
|
+
# The port on which your DetectLanguage server runs (defaults to 443 for secure
|
17
|
+
# connections, 80 for insecure connections).
|
18
|
+
attr_accessor :port
|
19
|
+
|
20
|
+
# +true+ for https connections, +false+ for http connections.
|
21
|
+
attr_accessor :secure
|
22
|
+
|
23
|
+
# The HTTP open timeout in seconds.
|
24
|
+
attr_accessor :http_open_timeout
|
25
|
+
|
26
|
+
# The HTTP read timeout in seconds.
|
27
|
+
attr_accessor :http_read_timeout
|
28
|
+
|
29
|
+
# The hostname of your proxy server (if using a proxy).
|
30
|
+
attr_accessor :proxy_host
|
31
|
+
|
32
|
+
# The port of your proxy server (if using a proxy).
|
33
|
+
attr_accessor :proxy_port
|
34
|
+
|
35
|
+
# The username to use when logging into your proxy server (if using a proxy).
|
36
|
+
attr_accessor :proxy_user
|
37
|
+
|
38
|
+
# The password to use when logging into your proxy server (if using a proxy).
|
39
|
+
attr_accessor :proxy_pass
|
40
|
+
|
41
|
+
alias_method :secure?, :secure
|
42
|
+
|
43
|
+
def initialize
|
44
|
+
@api_key = "demo"
|
45
|
+
@api_version = "0.2"
|
46
|
+
@host = "ws.detectlanguage.com"
|
47
|
+
@user_agent = "Detect Language API ruby gem"
|
48
|
+
end
|
49
|
+
|
50
|
+
def protocol
|
51
|
+
if secure?
|
52
|
+
'https'
|
53
|
+
else
|
54
|
+
'http'
|
55
|
+
end
|
56
|
+
end
|
57
|
+
|
58
|
+
def port
|
59
|
+
@port || default_port
|
60
|
+
end
|
61
|
+
|
62
|
+
# Allows config options to be read like a hash
|
63
|
+
#
|
64
|
+
# @param [Symbol] option Key for a given attribute
|
65
|
+
def [](option)
|
66
|
+
send(option)
|
67
|
+
end
|
68
|
+
|
69
|
+
private
|
70
|
+
|
71
|
+
# Determines what port should we use for sending requests.
|
72
|
+
# @return [Fixnum] Returns 443 if you've set secure to true in your
|
73
|
+
# configuration, and 80 otherwise.
|
74
|
+
def default_port
|
75
|
+
if secure?
|
76
|
+
443
|
77
|
+
else
|
78
|
+
80
|
79
|
+
end
|
80
|
+
end
|
81
|
+
|
82
|
+
end
|
83
|
+
end
|
@@ -0,0 +1,55 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
|
3
|
+
require 'spec_helper'
|
4
|
+
|
5
|
+
describe DetectLanguage do
|
6
|
+
|
7
|
+
context "configuration" do
|
8
|
+
it "should have default configuration values" do
|
9
|
+
subject.configuration.api_key.should == 'demo'
|
10
|
+
subject.configuration.api_version.should == '0.2'
|
11
|
+
subject.configuration.host.should == 'ws.detectlanguage.com'
|
12
|
+
subject.configuration.user_agent.should == 'Detect Language API ruby gem'
|
13
|
+
end
|
14
|
+
|
15
|
+
it "should allow configuring" do
|
16
|
+
subject.configure do |config|
|
17
|
+
config.user_agent = "Detect Language testing"
|
18
|
+
end
|
19
|
+
|
20
|
+
subject.configuration.user_agent.should == "Detect Language testing"
|
21
|
+
end
|
22
|
+
end
|
23
|
+
|
24
|
+
context "detection" do
|
25
|
+
before do
|
26
|
+
# testing key
|
27
|
+
subject.configuration.api_key = "24c3185fef623b537a4df60df0a8d4d9"
|
28
|
+
end
|
29
|
+
|
30
|
+
it "should detect languages" do
|
31
|
+
result = subject.detect("Hello world")
|
32
|
+
result[0]['language'].should == "en"
|
33
|
+
|
34
|
+
result = subject.detect("Jau saulelė vėl atkopdama budino svietą")
|
35
|
+
result[0]['language'].should == "lt"
|
36
|
+
end
|
37
|
+
|
38
|
+
it "should have simple way to detect a language" do
|
39
|
+
subject.simple_detect("Hello world").should == "en"
|
40
|
+
end
|
41
|
+
end
|
42
|
+
|
43
|
+
it "should raise exception for invalid key" do
|
44
|
+
old_api_key = subject.configuration.api_key
|
45
|
+
|
46
|
+
subject.configuration.api_key = "invalid"
|
47
|
+
|
48
|
+
lambda {
|
49
|
+
subject.detect("Hello world")
|
50
|
+
}.should raise_error(::DetectLanguage::Exception)
|
51
|
+
|
52
|
+
subject.configuration.api_key = old_api_key
|
53
|
+
end
|
54
|
+
|
55
|
+
end
|
data/spec/spec_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,63 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: detect_language
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 1.0.0
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Laurynas Butkus
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2012-08-11 00:00:00.000000000 Z
|
13
|
+
dependencies: []
|
14
|
+
description: Language Detection API Client
|
15
|
+
email:
|
16
|
+
- laurynas.butkus@gmail.com
|
17
|
+
executables: []
|
18
|
+
extensions: []
|
19
|
+
extra_rdoc_files: []
|
20
|
+
files:
|
21
|
+
- .gitignore
|
22
|
+
- .rspec
|
23
|
+
- .travis.yml
|
24
|
+
- Gemfile
|
25
|
+
- LICENSE
|
26
|
+
- README.md
|
27
|
+
- Rakefile
|
28
|
+
- detect_language.gemspec
|
29
|
+
- lib/detect_language.rb
|
30
|
+
- lib/detect_language/client.rb
|
31
|
+
- lib/detect_language/configuration.rb
|
32
|
+
- lib/detect_language/exception.rb
|
33
|
+
- lib/detect_language/version.rb
|
34
|
+
- spec/detect_language_spec.rb
|
35
|
+
- spec/spec_helper.rb
|
36
|
+
homepage: https://github.com/detectlanguage/detect_language
|
37
|
+
licenses: []
|
38
|
+
post_install_message:
|
39
|
+
rdoc_options: []
|
40
|
+
require_paths:
|
41
|
+
- lib
|
42
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
43
|
+
none: false
|
44
|
+
requirements:
|
45
|
+
- - ! '>='
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
49
|
+
none: false
|
50
|
+
requirements:
|
51
|
+
- - ! '>='
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: '0'
|
54
|
+
requirements: []
|
55
|
+
rubyforge_project:
|
56
|
+
rubygems_version: 1.8.24
|
57
|
+
signing_key:
|
58
|
+
specification_version: 3
|
59
|
+
summary: Detects language of given text. Returns detected language codes and scores.
|
60
|
+
test_files:
|
61
|
+
- spec/detect_language_spec.rb
|
62
|
+
- spec/spec_helper.rb
|
63
|
+
has_rdoc:
|