Module: Taxamatch::Phonetizer

Defined in:
lib/taxamatch_rb/phonetizer.rb

Class Method Summary collapse

Class Method Details

.near_match(a_word, normalize_ending = false) ⇒ Object 



10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
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
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
 
# File 'lib/taxamatch_rb/phonetizer.rb', line 10

def self.near_match(a_word, normalize_ending = false)
  a_word = a_word.strip rescue ''
  return '' if a_word == ''
  a_word = Taxamatch::Normalizer.normalize a_word
  case a_word
    when /^AE/
      a_word = 'E' + a_word[2..-1]
    when /^CN/
      a_word = 'N' + a_word[2..-1]
    when /^CT/
      a_word = 'T' + a_word[2..-1]
    when /^CZ/
      a_word = 'C' + a_word[2..-1]
    when /^DJ/
      a_word = 'J' + a_word[2..-1]
    when /^EA/
      a_word = 'E' + a_word[2..-1]
    when /^EU/
      a_word = 'U' + a_word[2..-1]
    when /^GN/
      a_word = 'N' + a_word[2..-1]
    when /^KN/
      a_word = 'N' + a_word[2..-1]
    when /^MC/
      a_word = 'MAC' + a_word[2..-1]
    when /^MN/
      a_word = 'N' + a_word[2..-1]
    when /^OE/
      a_word = 'E' + a_word[2..-1]
    when /^QU/
      a_word = 'Q' + a_word[2..-1]
    when /^PS/
      a_word = 'S' + a_word[2..-1]
    when /^PT/
      a_word = 'T' + a_word[2..-1]
    when /^TS/
      a_word = 'S' + a_word[2..-1]
    when /^WR/
      a_word = 'R' + a_word[2..-1]
    when /^X/
      a_word = 'Z' + a_word[1..-1]
  end
  first_char = a_word.split('')[0]
  rest_chars = a_word.split('')[1..-1].join('')
  rest_chars.gsub!('AE', 'I')
  rest_chars.gsub!('IA', 'A')
  rest_chars.gsub!('OE', 'I')
  rest_chars.gsub!('OI', 'A')
  rest_chars.gsub!('SC', 'S')
  rest_chars.gsub!('H', '')
  rest_chars.tr!('EOUYKZ', 'IAIICS')
  a_word = (first_char + rest_chars).squeeze

  if normalize_ending && a_word.size > 4
    a_word = self.normalize_ending(a_word)
  end
  a_word
end

.normalize_ending(a_word) ⇒ Object 



69
70
71
72
73
74
75
76
 
# File 'lib/taxamatch_rb/phonetizer.rb', line 69

def self.normalize_ending(a_word)
    # -- deal with variant endings
    # -is (includes -us, -ys, -es), -im (was -um), -as (-os)
    # -- at the end of a string translate all to -a
    a_word.gsub!(/IS$/, 'A')
    a_word.gsub!(/IM$/, 'A')
    a_word.gsub(/AS$/, 'A')
end

.phonetize(a_word, normalize_ending = false) ⇒ Object 



6
7
8
 
# File 'lib/taxamatch_rb/phonetizer.rb', line 6

def self.phonetize(a_word, normalize_ending = false)
  self.near_match(a_word, normalize_ending)
end