Class: Japanese

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

Constant Summary collapse

JAPANESE_PONCTUATION = 
{
    '　' => ' ',
    '、' => ',',
    '。' => '.',
    '：' => ':',
    '！' => '!',
    '？' => '?',
    '〜' => '~',
    '…' => '...',
    '‥' => '..',
    '「 ' => ' \'',
    '」' => '\'',
    '『 ' => ' "',
    '』' => '"',
    '〝 ' => ' "',
    '〟' => '"',
    '（ ' => ' (',
    '）' => ')',
    '【 ' => ' [',
    '】' => ']',
    '｛ ' => ' {',
    '｝' => '}',
}.freeze

Class Method Summary collapse

Class Method Details

.parse(text) ⇒ Object 



41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
 
# File 'lib/lib/japanese.rb', line 41

def self.parse(text)
  mecab_parsed = MecabStandalone.parse(text)
    .split("\n")
    .map{|k| k.split("\t")}.tap(&:pop)
    .map{|k| [k[0]].concat(k[1].split(','))}
    .map{|k| [k[0], k[1], k[-2]]}
  tokenized_kana = []
  mecab_parsed.each do |token|
    if token[1] == "助動詞"
      tokenized_kana[-1][0] +=  token[0]
      tokenized_kana[-1][-1] += token[-1]
    elsif token[-1] == '*'
      tokenized_kana << [token[0], token[1], token[0]]
    else
      tokenized_kana << token
    end
  end
  tokenized_kana
end

.t(text) ⇒ Object 



29
30
31
32
33
34
35
36
37
38
39
 
# File 'lib/lib/japanese.rb', line 29

def self.t(text)
  latin = text.dup
  parsed = parse(text)
  parsed.each do |token|
    if token[-1]=~ /\p{Katakana}/
      latin.sub!(token[0], ' ' + Romaji.kana2romaji(token[-1]) )
    end
  end
  JAPANESE_PONCTUATION.each { |k,v| latin.gsub!(k, v)}
  latin
end