Class: Babosa::Transliterator::Base

Inherits:
Object
  • Object
show all
Includes:
Singleton
Defined in:
lib/babosa/transliterator/base.rb

Direct Known Subclasses

Cyrillic, Greek, Hindi, Latin

Constant Summary collapse

APPROXIMATIONS = 
{
  "×" => "x",
  "÷" => "/",
  "‐" => "-",
  "‑" => "-",
  "‒" => "-",
  "–" => "-",
  "—" => "-",
  "―" => "-",
  "‘" => "'",
  "‛" => "'",
  "“" => '"',
  "”" => '"',
  "„" => '"',
  "‟" => '"',
  "’" => "'",
  "，" => ",",
  "。" => ".",
  "！" => "!",
  "？" => "?",
  "、" => ",",
  "（" => "(",
  "）" => ")",
  "【" => "[",
  "】" => "]",
  "；" => ";",
  "：" => ":",
  "《" => "<",
  "》" => ">"
}.merge(
  {
    # various kinds of space characters
    "\xc2\xa0"     => " ",
    "\xe2\x80\x80" => " ",
    "\xe2\x80\x81" => " ",
    "\xe2\x80\x82" => " ",
    "\xe2\x80\x83" => " ",
    "\xe2\x80\x84" => " ",
    "\xe2\x80\x85" => " ",
    "\xe2\x80\x86" => " ",
    "\xe2\x80\x87" => " ",
    "\xe2\x80\x88" => " ",
    "\xe2\x80\x89" => " ",
    "\xe2\x80\x8a" => " ",
    "\xe2\x81\x9f" => " ",
    "\xe3\x80\x80" => " "
  }
).freeze

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize ⇒ Base

Returns a new instance of Base.



66
67
68
69
70
71
72
73
74
75
76
77
78
79
 
# File 'lib/babosa/transliterator/base.rb', line 66

def initialize
  if self.class < Base
    @approximations = self.class.superclass.instance.approximations.dup
  else
    @approximations = {}
  end
  self.class.const_get(:APPROXIMATIONS).inject(@approximations) do |memo, object|
    index       = object[0].codepoints.shift
    value       = object[1].codepoints
    memo[index] = value.length == 1 ? value[0] : value
    memo
  end
  @approximations.freeze
end

Instance Attribute Details

#approximations ⇒ Object (readonly)

Returns the value of attribute approximations.



64
65
66
 
# File 'lib/babosa/transliterator/base.rb', line 64

def approximations
  @approximations
end

Instance Method Details

#[](codepoint) ⇒ Object

Accepts a single UTF-8 codepoint and returns the ASCII character code used as the transliteration value.



83
84
85
 
# File 'lib/babosa/transliterator/base.rb', line 83

def [](codepoint)
  @approximations[codepoint]
end

#transliterate(string) ⇒ Object

Transliterates a string.



88
89
90
 
# File 'lib/babosa/transliterator/base.rb', line 88

def transliterate(string)
  string.codepoints.map { |char| self[char] || char }.flatten.pack("U*")
end