Class: TwitterKorean::Processor

Inherits:
Object
  • Object
show all
Defined in:
lib/twitter_korean/processor.rb

Overview

Ruby interface to Scala TwitterKoreanProcessor

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(*jvmargs) ⇒ Processor

Returns a new instance of Processor.



8
9
10
11
# File 'lib/twitter_korean/processor.rb', line 8

def initialize(*jvmargs)
  bridge = TwitterKorean::JvmBridge.new(jvmargs)
  @jvm_processor = bridge.scala_twitter_korean_processor
end

Instance Attribute Details

#java_convertorObject (readonly)

Returns the value of attribute java_convertor.



6
7
8
# File 'lib/twitter_korean/processor.rb', line 6

def java_convertor
  @java_convertor
end

#jvm_processorObject (readonly)

Returns the value of attribute jvm_processor.



6
7
8
# File 'lib/twitter_korean/processor.rb', line 6

def jvm_processor
  @jvm_processor
end

Instance Method Details

#extract_phrases(text, options = {}) ⇒ Object



32
33
34
35
36
37
38
39
# File 'lib/twitter_korean/processor.rb', line 32

def extract_phrases(text, options = {})
  return unless text
  filter_spam = options[:filter_spam] || false
  including_hashtags = options[:including_hashtags] || true      
  converto_to_korean_tokens do
    jvm_processor.extractPhrases(jvm_processor.tokenize(text), filter_spam, including_hashtags)
  end
end

#normalize(text) ⇒ Object



13
14
15
16
# File 'lib/twitter_korean/processor.rb', line 13

def normalize(text)
  return unless text
  jvm_processor.normalize(text).toString
end

#stem(text) ⇒ Object



25
26
27
28
29
30
# File 'lib/twitter_korean/processor.rb', line 25

def stem(text)
  return unless text
  converto_to_korean_tokens do
    jvm_processor.stem(jvm_processor.tokenize(text))
  end
end

#tokenize(text) ⇒ Object



18
19
20
21
22
23
# File 'lib/twitter_korean/processor.rb', line 18

def tokenize(text)
  return unless text
  converto_to_korean_tokens do
    jvm_processor.tokenize(text)
  end
end