Module: Faker::Char

Defined in:
lib/helpers/char.rb

Class Method Summary collapse

Class Method Details

.fix_umlauts(string) ⇒ Object



9
10
11
12
13
14
15
16
17
18
# File 'lib/helpers/char.rb', line 9

def self.fix_umlauts(string)
  string.gsub(/[äöüß]/i) do |match|
    case match.downcase
    when 'ä' then 'ae'
    when 'ö' then 'oe'
    when 'ü' then 'ue'
    when 'ß' then 'ss'
    end
  end
end

.prepare(string) ⇒ Object



3
4
5
6
7
# File 'lib/helpers/char.rb', line 3

def self.prepare(string)
  result = romanize_cyrillic string
  result = fix_umlauts result
  result.gsub(/\W/, '').downcase
end

.romanize_cyrillic(string) ⇒ Object



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
# File 'lib/helpers/char.rb', line 20

def self.romanize_cyrillic(string)
  if Faker::Config.locale == 'uk'
    # Based on conventions abopted by BGN/PCGN for Ukrainian
    uk_chars = {
      'а' => 'a',  'б' => 'b',  'в' => 'v',  'г' => 'h',  'ґ' => 'g',  'д' => 'd',
      'е' => 'e',  'є' => 'ye', 'ж' => 'zh', 'з' => 'z',  'и' => 'y',  'і' => 'i',
      'ї' => 'yi', 'й' => 'y',  'к' => 'k',  'л' => 'l',  'м' => 'm',  'н' => 'n',
      'о' => 'o',  'п' => 'p',  'р' => 'r',  'с' => 's',  'т' => 't',  'у' => 'u',
      'ф' => 'f',  'х' => 'kh', 'ц' => 'ts', 'ч' => 'ch', 'ш' => 'sh', 'щ' => 'shch',
      'ю' => 'yu', 'я' => 'ya',
      'А' => 'a',  'Б' => 'b',  'В' => 'v',  'Г' => 'h',  'Ґ' => 'g',  'Д' => 'd',
      'Е' => 'e',  'Є' => 'ye', 'Ж' => 'zh', 'З' => 'z',  'И' => 'y',  'І' => 'i',
      'Ї' => 'yi', 'Й' => 'y',  'К' => 'k',  'Л' => 'l',  'М' => 'm',  'Н' => 'n',
      'О' => 'o',  'П' => 'p',  'Р' => 'r',  'С' => 's',  'Т' => 't',  'У' => 'u',
      'Ф' => 'f',  'Х' => 'kh', 'Ц' => 'ts', 'Ч' => 'ch', 'Ш' => 'sh', 'Щ' => 'shch',
      'Ю' => 'yu', 'Я' => 'ya',
      'ь' => '' # Ignore symbol, because its standard presentation is not allowed in URLs
    }
    return string.gsub(/[а-яА-ЯіїєґІЇЄҐ]/, uk_chars)
  end

  if Faker::Config.locale == 'ru'
    # Based on conventions abopted by BGN/PCGN for Russian
    ru_chars = {
      'а' => 'a', 'б' => 'b', 'в' => 'v', 'г' => 'h', 'д' => 'd', 'е' => 'e',
      'ё' => 'ye', 'ж' => 'zh', 'з' => 'z',    'и' => 'i',  'й' => 'y',  'к' => 'k',
      'л' => 'l',  'м' => 'm',  'н' => 'n',    'о' => 'o',  'п' => 'p',  'р' => 'r',
      'с' => 's',  'т' => 't',  'у' => 'u',    'ф' => 'f',  'х' => 'kh', 'ц' => 'ts',
      'ч' => 'ch', 'ш' => 'sh', 'щ' => 'shch', 'ы' => 'у',  'э' => 'e',  'ю' => 'yu',
      'я' => 'ya',
      'А' => 'a',  'Б' => 'b',  'В' => 'v',    'Г' => 'h',  'Д' => 'd',  'Е' => 'e',
      'Ё' => 'ye', 'Ж' => 'zh', 'З' => 'z',    'И' => 'i',  'Й' => 'y',  'К' => 'k',
      'Л' => 'l',  'М' => 'm',  'Н' => 'n',    'О' => 'o',  'П' => 'p',  'Р' => 'r',
      'С' => 's',  'Т' => 't',  'У' => 'u',    'Ф' => 'f',  'Х' => 'kh', 'Ц' => 'ts',
      'Ч' => 'ch', 'Ш' => 'sh', 'Щ' => 'shch', 'Ы' => 'у',  'Э' => 'e',  'Ю' => 'yu',
      'Я' => 'ya',
      'ь' => '', 'ъ' => '' # Ignore symbols, because its standard presentation is not allowed in URLs
    }
    return string.gsub(/[а-яА-Я]/, ru_chars)
  end

  string
end