Class: RMMSeg::ComplexAlgorithm

Inherits:
Object
  • Object
show all
Includes:
Algorithm
Defined in:
lib/rmmseg/complex_algorithm.rb

Instance Method Summary collapse

Methods included from Algorithm

#basic_latin?, #find_match_words, #get_basic_latin_word, #get_cjk_word, #next_token, #nonword_char?, #segment

Constructor Details

#initialize(text) ⇒ ComplexAlgorithm

Create a new ComplexAlgorithm . Rules used by this algorithm includes MMRule , LAWLRule , SVWLRule and LSDMFOCWRule .



13
14
15
16
17
18
19
20
21
 
# File 'lib/rmmseg/complex_algorithm.rb', line 13

def initialize(text)
  super
  @rules = [
            MMRule.new,
            LAWLRule.new,
            SVWLRule.new,
            LSDMFOCWRule.new
           ]
end

Instance Method Details

#create_chunks ⇒ Object

Create all possible three-word (or less) chunks starting from @index .



25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
 
# File 'lib/rmmseg/complex_algorithm.rb', line 25

def create_chunks
  chunks = Array.new
  find_match_words(@chars, @index).each { |w0|
    index0 = @index + w0.length
    if index0 < @chars.length
      find_match_words(@chars, index0).each { |w1|
        index1 = index0 + w1.length
        if index1 < @chars.length
          find_match_words(@chars, index1).each { |w2|
            if w2.type == Word::TYPES[:unrecognized]
              chunks << Chunk.new([w0, w1])
            else
              chunks << Chunk.new([w0, w1, w2])
            end
          }
        elsif index1 == @chars.length
          chunks << Chunk.new([w0, w1])
        end
      }
    elsif index0 == @chars.length
      chunks << Chunk.new([w0])
    end
  }

  chunks
end