Class: Tokenizer::Tokenizer

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

Constant Summary collapse

FS = 
Regexp.new('[[:blank:]]+')
SIMPLE_PRE =

spanish marks

[]
PAIR_PRE = 
['(', '{', '[', '<']
SIMPLE_POST = 
['!', '?', ',', ':', ';', '.']
PAIR_POST = 
[')', '}', ']', '>']
PRE_N_POST = 
['"', "'"]
PRE = 
SIMPLE_PRE + PAIR_PRE
POST = 
SIMPLE_POST + PAIR_POST

Instance Method Summary collapse

Constructor Details

#initialize(lang = :de, options = {}) ⇒ Tokenizer

Returns a new instance of Tokenizer.



20
21
22
23
24
25
26
27
 
# File 'lib/tokenizer/tokenizer.rb', line 20

def initialize(lang = :de, options = {})
  @lang = lang
  @options = {
    pre: SIMPLE_PRE + PAIR_PRE,
    post: SIMPLE_POST + PAIR_POST,
    pre_n_post: PRE_N_POST
  }.merge(options)
end

Instance Method Details

#tokenize(str) ⇒ Object 



29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
 
# File 'lib/tokenizer/tokenizer.rb', line 29

def tokenize(str)
  output = ''

  fields = str.chomp.split(FS)

  return [''] if fields.empty?

  fields.each do |field|
    field.each_char.with_index do |ch, idx|
      case
      when @options[:pre].include?(ch)
        output << "#{ch}\n"
      when @options[:post].include?(ch)
        output << "\n#{ch}"
        if ['?', '!', '.'].include?(ch)
          output << "\n"
        end
      when @options[:pre_n_post].include?(ch)
        if idx == 0
          output << "#{ch}\n"
        elsif idx != 0
          output << "\n#{ch}"
        end
      else
        output << ch
      end
    end

    output << "\n"
  end

  # @TODO: Rework the format of the string!
  output.chomp('').split("\n", -1)
end