twitter-korean-text-ruby 0.9.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +12 -0
- data/.travis.yml +11 -0
- data/Gemfile +4 -0
- data/README.md +68 -0
- data/Rakefile +10 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/lib/twitter-korean-text-ruby.rb +7 -0
- data/lib/twitter_korean/jars/korean-text-4.4.jar +0 -0
- data/lib/twitter_korean/jars/scala-library-2.11.7.jar +0 -0
- data/lib/twitter_korean/jars/twitter-text-1.13.3.jar +0 -0
- data/lib/twitter_korean/jvm_bridge.rb +15 -0
- data/lib/twitter_korean/korean_token.rb +53 -0
- data/lib/twitter_korean/processor.rb +55 -0
- data/lib/twitter_korean/version.rb +3 -0
- data/twitter-korean-text-ruby.gemspec +26 -0
- metadata +146 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 66a39cfe7f6759aa6bc9412a49e069817201d08b
|
4
|
+
data.tar.gz: d2d0ffd199077dd5f7d0463764e2d1b2c6bb1f27
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 5522edf916fb34042b99333b141146d450634e7d3503e0716204e4dcf2a74a2361fd3ad77dce961142b077f998e6dff627a0fb0603ad7e446b7c0fce1c64ac8e
|
7
|
+
data.tar.gz: d812c9d805a0957631a7845cde29ec9bbead25a610ef42d19834cd518e9b12648a210d5a071f837fd5669b93dcbb2aff284b200148dd1b425f04514397df8946
|
data/.gitignore
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/README.md
ADDED
@@ -0,0 +1,68 @@
|
|
1
|
+
## twitter-korean-text-ruby
|
2
|
+
[![Build Status](https://travis-ci.org/keepcosmos/twitter-korean-text-ruby.svg?branch=master)](https://travis-ci.org/keepcosmos/twitter-korean-text-ruby)
|
3
|
+
[![Code Climate](https://codeclimate.com/repos/56d562f8e4ecf4707f00309b/badges/7673319c6a92ab7ace9f/gpa.svg)](https://codeclimate.com/repos/56d562f8e4ecf4707f00309b/feed)
|
4
|
+
|
5
|
+
Ruby interface to [twitter-korean-text](https://github.com/twitter/twitter-korean-text) by Twitter
|
6
|
+
|
7
|
+
트위터에서 제공하는 한글 형태소 분석기인 [twitter-korean-text](https://github.com/twitter/twitter-korean-text)(Scala)를 Ruby에서 사용가능하도록 Wrapping 하였습니다.
|
8
|
+
|
9
|
+
### install
|
10
|
+
```{ruby}
|
11
|
+
$ gem install twitter-korean-text-ruby
|
12
|
+
```
|
13
|
+
Gemfile을 사용할 경우
|
14
|
+
```{ruby}
|
15
|
+
# Gemfile
|
16
|
+
gem 'twitter-korean-text-ruby'
|
17
|
+
```
|
18
|
+
|
19
|
+
### Useage
|
20
|
+
```ruby
|
21
|
+
require 'twitter-korean-text-ruby'
|
22
|
+
|
23
|
+
processor = TwitterKorean::Processor.new
|
24
|
+
# OR with JVM arguments
|
25
|
+
processor = TwitterKorean::Processor.new('-Xms126M', '-Xms512M', ...)
|
26
|
+
|
27
|
+
# Normalize
|
28
|
+
processor.normalize("형태소 분석을 합니닼ㅋㅋㅋㅋㅋㅋ")
|
29
|
+
# => "형태소 분석을 합니다ㅋㅋㅋㅋㅋㅋ"
|
30
|
+
|
31
|
+
# Tokenize
|
32
|
+
tokens = proccessor.tokenize("한국어를 처리하는 예시입니다 ㅋㅋ")
|
33
|
+
puts tokens
|
34
|
+
# => ["한국어", "를", " ", "처리", "하는", " ", "예시", "입니", "다", " ", "ㅋㅋ"]
|
35
|
+
|
36
|
+
# metadata of token, 토큰에 대한 정보
|
37
|
+
metadata = tokens.first.metadata
|
38
|
+
matadata #=> "noun, 0, 3"
|
39
|
+
metadata.pos #=> :noun
|
40
|
+
metadata.offset #=> 0
|
41
|
+
metadata.length #=> 3
|
42
|
+
|
43
|
+
# Stemming
|
44
|
+
tokens = proccessor.stem("한국어를 처리하는 예시입니다 ㅋㅋ")
|
45
|
+
puts tokens
|
46
|
+
# => ["한국어", "를", " ", "처리", "하다", " ", "예시", "이다", " ", "ㅋㅋ"]
|
47
|
+
|
48
|
+
# extract phrases
|
49
|
+
tokens = proccessor.stem("한국어를 처리하는 예시입니다 ㅋㅋ")
|
50
|
+
puts tokens
|
51
|
+
# => ["한국어", "처리", "처리하는 예시", "예시"]
|
52
|
+
|
53
|
+
```
|
54
|
+
|
55
|
+
### Test
|
56
|
+
```{ruby}
|
57
|
+
rake test
|
58
|
+
```
|
59
|
+
|
60
|
+
### Issue
|
61
|
+
JAVA Path를 찾지 못했을 경우,
|
62
|
+
```{bash}
|
63
|
+
export JAVA_HOME=$(java_home_path)
|
64
|
+
|
65
|
+
### Contribute
|
66
|
+
이 프로젝트는 [twitter-korean-text](https://github.com/twitter/twitter-korean-text) 프로젝트의 Scala 코드를 Ruby로 Wrapping하는 프로젝트입니다.
|
67
|
+
관련된 범주에 대한 Issue와 Pull Request(테스트 코드가 포함된)는 언제나 환영입니다.
|
68
|
+
```
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "twitter/korean/text/ruby"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start
|
data/bin/setup
ADDED
Binary file
|
Binary file
|
Binary file
|
@@ -0,0 +1,15 @@
|
|
1
|
+
require 'rjb'
|
2
|
+
|
3
|
+
module TwitterKorean
|
4
|
+
class JvmBridge
|
5
|
+
CLASS_PATH = Dir.glob(File.dirname(__FILE__) + '/jars/*.jar').join(File::PATH_SEPARATOR).freeze
|
6
|
+
|
7
|
+
def initialize(jvmargs = [])
|
8
|
+
Rjb.load CLASS_PATH, jvmargs
|
9
|
+
end
|
10
|
+
|
11
|
+
def scala_twitter_korean_processor
|
12
|
+
Rjb.import('com.twitter.penguin.korean.TwitterKoreanProcessor')
|
13
|
+
end
|
14
|
+
end
|
15
|
+
end
|
@@ -0,0 +1,53 @@
|
|
1
|
+
module TwitterKorean
|
2
|
+
class KoreanToken < String
|
3
|
+
attr_accessor :metadata
|
4
|
+
|
5
|
+
class << self
|
6
|
+
# by form like `한국어(Noun: 0, 3)`
|
7
|
+
def build_by_formed_str(str)
|
8
|
+
token = new(str[0...str.rindex('(')])
|
9
|
+
|
10
|
+
infos = str[(str.rindex('(') + 1)...str.rindex(')')]
|
11
|
+
attrs = {
|
12
|
+
pos: infos.match(/\w+/).to_s,
|
13
|
+
offset: infos.match(/\d+/).to_s.to_i,
|
14
|
+
length: infos.match(/\d+$/).to_s.to_i
|
15
|
+
}
|
16
|
+
|
17
|
+
token.metadata = TwitterKorean::KoreanToken::Metadata.new(attrs)
|
18
|
+
token
|
19
|
+
end
|
20
|
+
end
|
21
|
+
|
22
|
+
class Metadata
|
23
|
+
attr_accessor :pos, :offset, :length, :unkown
|
24
|
+
|
25
|
+
def initialize(attrs = {})
|
26
|
+
attrs.each { |k, v| send("#{k}=", v) if respond_to?("#{k}=") }
|
27
|
+
symbolize_pos!
|
28
|
+
end
|
29
|
+
|
30
|
+
def inspect
|
31
|
+
"#{pos}, #{offset}, #{length}"
|
32
|
+
end
|
33
|
+
|
34
|
+
def ==(other)
|
35
|
+
[:pos, :offset, :length, :unkown].inject(true) { |res, attr| res && (send(attr) == other.send(attr)) }
|
36
|
+
end
|
37
|
+
|
38
|
+
private
|
39
|
+
|
40
|
+
def symbolize_pos!
|
41
|
+
return if pos.nil?
|
42
|
+
@pos = to_underscore(pos).to_sym
|
43
|
+
end
|
44
|
+
|
45
|
+
def to_underscore(txt)
|
46
|
+
txt.gsub(/([A-Z]+)([A-Z][a-z])/,'\1_\2').
|
47
|
+
gsub(/([a-z\d])([A-Z])/,'\1_\2').
|
48
|
+
tr("-", "_").
|
49
|
+
downcase
|
50
|
+
end
|
51
|
+
end
|
52
|
+
end
|
53
|
+
end
|
@@ -0,0 +1,55 @@
|
|
1
|
+
require 'rjb'
|
2
|
+
|
3
|
+
module TwitterKorean
|
4
|
+
# Ruby interface to Scala TwitterKoreanProcessor
|
5
|
+
class Processor
|
6
|
+
attr_reader :jvm_processor, :java_convertor
|
7
|
+
|
8
|
+
def initialize(*jvmargs)
|
9
|
+
bridge = TwitterKorean::JvmBridge.new(jvmargs)
|
10
|
+
@jvm_processor = bridge.scala_twitter_korean_processor
|
11
|
+
end
|
12
|
+
|
13
|
+
def normalize(text)
|
14
|
+
return unless text
|
15
|
+
jvm_processor.normalize(text).toString
|
16
|
+
end
|
17
|
+
|
18
|
+
def tokenize(text)
|
19
|
+
return unless text
|
20
|
+
converto_to_korean_tokens do
|
21
|
+
jvm_processor.tokenize(text)
|
22
|
+
end
|
23
|
+
end
|
24
|
+
|
25
|
+
def stem(text)
|
26
|
+
return unless text
|
27
|
+
converto_to_korean_tokens do
|
28
|
+
jvm_processor.stem(jvm_processor.tokenize(text))
|
29
|
+
end
|
30
|
+
end
|
31
|
+
|
32
|
+
def extract_phrases(text, options = {})
|
33
|
+
return unless text
|
34
|
+
filter_spam = options[:filter_spam] || false
|
35
|
+
including_hashtags = options[:including_hashtags] || true
|
36
|
+
converto_to_korean_tokens do
|
37
|
+
jvm_processor.extractPhrases(jvm_processor.tokenize(text), filter_spam, including_hashtags)
|
38
|
+
end
|
39
|
+
end
|
40
|
+
|
41
|
+
private
|
42
|
+
|
43
|
+
def converto_to_korean_tokens &block
|
44
|
+
scala_list = block.call.toString
|
45
|
+
token_strs = scala_list_to_array(scala_list)
|
46
|
+
token_strs.map do |formed_token_str|
|
47
|
+
TwitterKorean::KoreanToken.build_by_formed_str(formed_token_str.first)
|
48
|
+
end
|
49
|
+
end
|
50
|
+
|
51
|
+
def scala_list_to_array(result)
|
52
|
+
result.scan(/(?<=List\(|\,\s)(.*?\([a-zA-Z]+\:\s[0-9]+,\s[0-9]\))/).to_a
|
53
|
+
end
|
54
|
+
end
|
55
|
+
end
|
@@ -0,0 +1,26 @@
|
|
1
|
+
lib = File.expand_path('../lib', __FILE__)
|
2
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
3
|
+
require 'twitter_korean/version'
|
4
|
+
|
5
|
+
Gem::Specification.new do |spec|
|
6
|
+
spec.name = "twitter-korean-text-ruby"
|
7
|
+
spec.version = TwitterKorean::VERSION
|
8
|
+
spec.authors = ["Jaehyun Shin"]
|
9
|
+
spec.email = ["keepcosmos@gmail.com"]
|
10
|
+
|
11
|
+
spec.summary = "Ruby interface to Twitter Korean Text(written in Scala)"
|
12
|
+
spec.description = "Ruby interface to Twitter Korean Text written in Scala(https://github.com/twitter/twitter-korean-text) "
|
13
|
+
spec.homepage = 'https://github.com/keepcosmos/twitter-korean-text-ruby'
|
14
|
+
spec.license = "Apache License 2.0"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
17
|
+
spec.require_paths = ["lib"]
|
18
|
+
|
19
|
+
spec.add_dependency "rjb", "~> 1.5"
|
20
|
+
|
21
|
+
spec.add_development_dependency "bundler", "~> 1.11"
|
22
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
23
|
+
spec.add_development_dependency "byebug", "~> 8.0"
|
24
|
+
spec.add_development_dependency "minitest", "~> 5.0"
|
25
|
+
spec.add_development_dependency "simplecov", "~> 0.11.0"
|
26
|
+
end
|
metadata
ADDED
@@ -0,0 +1,146 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: twitter-korean-text-ruby
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.9.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Jaehyun Shin
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-03-01 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: rjb
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.5'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.5'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: bundler
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '1.11'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '1.11'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rake
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '10.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '10.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: byebug
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '8.0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '8.0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: minitest
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '5.0'
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '5.0'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: simplecov
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - "~>"
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: 0.11.0
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - "~>"
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: 0.11.0
|
97
|
+
description: 'Ruby interface to Twitter Korean Text written in Scala(https://github.com/twitter/twitter-korean-text) '
|
98
|
+
email:
|
99
|
+
- keepcosmos@gmail.com
|
100
|
+
executables: []
|
101
|
+
extensions: []
|
102
|
+
extra_rdoc_files: []
|
103
|
+
files:
|
104
|
+
- ".byebug_history"
|
105
|
+
- ".gitignore"
|
106
|
+
- ".travis.yml"
|
107
|
+
- Gemfile
|
108
|
+
- README.md
|
109
|
+
- Rakefile
|
110
|
+
- bin/console
|
111
|
+
- bin/setup
|
112
|
+
- lib/twitter-korean-text-ruby.rb
|
113
|
+
- lib/twitter_korean/jars/korean-text-4.4.jar
|
114
|
+
- lib/twitter_korean/jars/scala-library-2.11.7.jar
|
115
|
+
- lib/twitter_korean/jars/twitter-text-1.13.3.jar
|
116
|
+
- lib/twitter_korean/jvm_bridge.rb
|
117
|
+
- lib/twitter_korean/korean_token.rb
|
118
|
+
- lib/twitter_korean/processor.rb
|
119
|
+
- lib/twitter_korean/version.rb
|
120
|
+
- twitter-korean-text-ruby.gemspec
|
121
|
+
homepage: https://github.com/keepcosmos/twitter-korean-text-ruby
|
122
|
+
licenses:
|
123
|
+
- Apache License 2.0
|
124
|
+
metadata: {}
|
125
|
+
post_install_message:
|
126
|
+
rdoc_options: []
|
127
|
+
require_paths:
|
128
|
+
- lib
|
129
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
130
|
+
requirements:
|
131
|
+
- - ">="
|
132
|
+
- !ruby/object:Gem::Version
|
133
|
+
version: '0'
|
134
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
135
|
+
requirements:
|
136
|
+
- - ">="
|
137
|
+
- !ruby/object:Gem::Version
|
138
|
+
version: '0'
|
139
|
+
requirements: []
|
140
|
+
rubyforge_project:
|
141
|
+
rubygems_version: 2.5.1
|
142
|
+
signing_key:
|
143
|
+
specification_version: 4
|
144
|
+
summary: Ruby interface to Twitter Korean Text(written in Scala)
|
145
|
+
test_files: []
|
146
|
+
has_rdoc:
|