Module: Grc

Included in:
String
Defined in:
lib/grc.rb,
lib/grc/version.rb

Overview

Methods for working with ancient greek in ruby

Defined Under Namespace

Classes: Error

Constant Summary collapse

VERSION = 
'0.1.4'

Instance Method Summary collapse

Instance Method Details

#acute_to_grave ⇒ Object 



243
244
245
246
247
 
# File 'lib/grc.rb', line 243

def acute_to_grave
  return @std_error unless grc?

  to_grave
end

#grave_to_acute ⇒ Object 



237
238
239
240
241
 
# File 'lib/grc.rb', line 237

def grave_to_acute
  return @std_error unless grc?

  to_acute
end

#grc? ⇒ Boolean

grc? (str → bool) Returns true if the string contains greek characters.

Returns:

  • (Boolean) 


15
16
17
 
# File 'lib/grc.rb', line 15

def grc?
  !scan(/(\p{Greek})/).empty?
end

#grc_downcase ⇒ Object

grc_downcase (str → str) Returns the lowercase version of string for greek characters resolving confusable characters. See https://www.w3.org/TR/charmod-norm/#PreNormalization



89
90
91
 
# File 'lib/grc.rb', line 89

def grc_downcase
  nfd.downcase.nfc
end

#grc_upcase ⇒ Object

grc_upcase (str → str) Default upcase methods strips diacritical marks from greek characters. This method returns the corresponding uppercase version of string for greek characters preserving diacritical marks. See pages 1-7 of http://www.tlg.uci.edu/encoding/precomposed.pdf https://icu.unicode.org/design/case/greek-upper



98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
 
# File 'lib/grc.rb', line 98

def grc_upcase
  case_map = {
    ᾀ: 'ᾈ',
    ᾁ: 'ᾉ',
    ᾂ: 'ᾊ',
    ᾃ: 'ᾋ',
    ᾄ: 'ᾌ',
    ᾅ: 'ᾍ',
    ᾆ: 'ᾎ',
    ᾇ: 'ᾏ',
    ᾐ: 'ᾘ',
    ᾑ: 'ᾙ',
    ᾒ: 'ᾚ',
    ᾓ: 'ᾛ',
    ᾔ: 'ᾜ',
    ᾕ: 'ᾝ',
    ᾖ: 'ᾞ',
    ᾗ: 'ᾟ',
    ᾠ: 'ᾨ',
    ᾡ: 'ᾩ',
    ᾢ: 'ᾪ',
    ᾣ: 'ᾫ',
    ᾤ: 'ᾬ',
    ᾥ: 'ᾭ',
    ᾦ: 'ᾮ',
    ᾧ: 'ᾯ',
    ᾳ: 'ᾼ',
    ῃ: 'ῌ',
    ῳ: 'ῼ'
  }

  nfc.each_char.map do |char|
    if char.grc?
      case_map[:"#{char}"] || char.upcase
    else
      char
    end
  end.join
end

#hash_dump ⇒ Object

hash_dump: (str → hash) Returns a hash of the string's unicode points (Char: Unicode_points).



55
56
57
58
59
60
61
 
# File 'lib/grc.rb', line 55

def hash_dump
  hash = {}
  each_char do |character|
    hash[character] = character.dump
  end
  hash
end

#lower? ⇒ Boolean

Returns:

  • (Boolean) 


221
222
223
 
# File 'lib/grc.rb', line 221

def lower?
  !!match(/\p{Lower}/)
end

#nfc ⇒ Object

nfc (str → str) Returns a string with the canonical composition of the string.



80
81
82
 
# File 'lib/grc.rb', line 80

def nfc
  unicode_normalize(:nfc)
end

#nfd ⇒ Object

nfd (str → str) Returns a string with the canonical decomposition of the string.



74
75
76
 
# File 'lib/grc.rb', line 74

def nfd
  unicode_normalize(:nfd)
end

#no_diacritics ⇒ Object

no_diacritics (str → str) Returns a string with the diacritics removed.



170
171
172
173
174
 
# File 'lib/grc.rb', line 170

def no_diacritics
  return @std_error unless grc?

  no_downcase_diacritics.no_upcase_diacritics
end

#no_downcase_diacritics ⇒ Object

no_downcase_diacritics (str → str) Returns a string with the diacritics removed from lowercase characters.



142
143
144
145
146
147
148
149
150
151
152
 
# File 'lib/grc.rb', line 142

def no_downcase_diacritics
  return @std_error unless grc?

  each_char.map do |char| # Loop through each character
    if char.grc? && char.lower? # If character is greek and lowercase
      char.nfd.gsub(/\p{Mn}/, '').nfc # decompose, remove non-spacing markers (diacritics), recompose and return
    else # else
      char # return char
    end
  end.join # end char loop
end

#no_upcase_diacritics ⇒ Object

no_upcase_diacritics (str → str) Returns a string with the diacritics removed from uppercase characters.



156
157
158
159
160
161
162
163
164
165
166
 
# File 'lib/grc.rb', line 156

def no_upcase_diacritics
  return @std_error unless grc?

  each_char.map do |char| # Loop through each character
    if char.grc? && char.upper? # If character is greek and uppercase
      char.nfd.gsub(/\p{Mn}/, '').nfc # Decompose, remove non-spacing markers (diacritics), recompose and return
    else # else
      char # Return char
    end
  end.join
end

#oxia_to_tonos ⇒ Object 



225
226
227
228
229
 
# File 'lib/grc.rb', line 225

def oxia_to_tonos
  return @std_error unless grc?

  to_tonos
end

#to_acute ⇒ Object

to_acute (str → str) Returns a string with the acute replacing the grave accent.



190
191
192
193
194
195
196
 
# File 'lib/grc.rb', line 190

def to_acute
  return @std_error unless grc?

  # Simple transform method with acute to grave mapping
  tr('ἂᾂἃᾃὰὰᾲἒἓὲὲἢᾒἣᾓὴὴῂἲἳὶὶῒὂὃὸὸὒὓὺὺῢῢὢᾢὣᾣὼῲ',
     'ἄᾄἅᾅάάᾴἔἕέέἤᾔἥᾕήήῄἴἵίίΐὄὅόόὔὕύύΰΰὤᾤὥᾥώῴ')
end

#to_grave ⇒ Object

to_grave (str → str) Returns a string with the grave replacing the acute accent.



180
181
182
183
184
185
186
 
# File 'lib/grc.rb', line 180

def to_grave
  return @std_error unless grc?

  # Simple transform method with grave to acute mapping
  tr('ἄᾄἅᾅάάᾴἔἕέέἤᾔἥᾕήήῄἴἵίίΐὄὅόόὔὕύύΰΰὤᾤὥᾥώῴ',
     'ἂᾂἃᾃὰὰᾲἒἓὲὲἢᾒἣᾓὴὴῂἲἳὶὶῒὂὃὸὸὒὓὺὺῢῢὢᾢὣᾣὼῲ')
end

#to_oxia ⇒ Object

to_oxia (str → str) Returns a string with the oxia replacing the tonos.



200
201
202
203
204
205
 
# File 'lib/grc.rb', line 200

def to_oxia
  return @std_error unless grc?

  tr('άΆέΈήΉίΊΐόΌύΎΰώΏ',
     'άΆέΈήΉίΊΐόΌύΎΰώΏ')
end

#to_tonos ⇒ Object

to_tonos (str → str) Returns a string with the tonos replacing the oxia. See page 9 of http://www.tlg.uci.edu/encoding/precomposed.pdf



210
211
212
213
214
215
 
# File 'lib/grc.rb', line 210

def to_tonos
  return @std_error unless grc?

  tr('άΆέΈήΉίΊΐόΌύΎΰώΏ',
     'άΆέΈήΉίΊΐόΌύΎΰώΏ')
end

#tokenize ⇒ Object

tokenize (str → array) Returns an array of tokens from the string.



21
22
23
 
# File 'lib/grc.rb', line 21

def tokenize
  gsub(/([[:punct:]]|·|·|‧|⸱|𐄁|\.|;|;)/, ' \1').split
end

#tonos_to_oxia ⇒ Object 



231
232
233
234
235
 
# File 'lib/grc.rb', line 231

def tonos_to_oxia
  return @std_error unless grc?

  to_oxia
end

#transliterate ⇒ Object

transliterate (str → str) Returns a string with greek characters replaced with their transliteration.



27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
 
# File 'lib/grc.rb', line 27

def transliterate
  return @std_error unless grc?

  result = []
  str = self
  str.tokenize do |token|
    result << if token.grc?
                the_word = token.gsub(/ῥ/, 'rh')
                the_word = the_word =~ /[ἁἅᾅἃᾃἇᾇᾁἑἕἓἡἥᾕἣᾓἧᾗᾑἱἵἳἷὁὅὃὑὕὓὗὡὥᾥὣᾣὧᾧᾡ]/ ? "h#{the_word.no_diacritics}" : the_word.no_diacritics
                hash.each { |k, v| the_word = the_word.gsub(/#{k}/, v) }
                the_word
              else
                word
              end
  end
  result.join(' ')
end

#unicode_name ⇒ Object

unicode_name (str → array) Returns an array of unicode names from the string.



65
66
67
68
 
# File 'lib/grc.rb', line 65

def unicode_name
  require 'unicode/name'
  each_char.map { |character| Unicode::Name.of character }
end

#unicode_points ⇒ Object

unicode_points (str → array) Returns an array of unicode points from the string.



49
50
51
 
# File 'lib/grc.rb', line 49

def unicode_points
  unpack('U*').map { |i| "\\u#{i.to_s(16).rjust(4, "0").upcase}" }
end

#upper? ⇒ Boolean

Returns:

  • (Boolean) 


217
218
219
 
# File 'lib/grc.rb', line 217

def upper?
  !!match(/\p{Upper}/)
end