Class: String

Inherits:
Object
  • Object
show all
Defined in:
lib/simple_geolocation/utils/remove_accents.rb

Constant Summary collapse

ACCENTS_MAPPING =

The extended characters map used by removeaccents. The accented characters are coded here using their numerical equivalent to sidestep encoding issues. These correspond to ISO-8859-1 encoding.

{
  'E' => [200,201,202,203],
  'e' => [232,233,234,235],
  'A' => [192,193,194,195,196,197],
  'a' => [224,225,226,227,228,229,230],
  'C' => [199],
  'c' => [231],
  'O' => [210,211,212,213,214,216],
  'o' => [242,243,244,245,246,248],
  'I' => [204,205,206,207],
  'i' => [236,237,238,239],
  'U' => [217,218,219,220],
  'u' => [249,250,251,252],
  'N' => [209],
  'n' => [241],
  'Y' => [221],
  'y' => [253,255],
  'AE' => [306],
  'ae' => [346],
  'OE' => [188],
  'oe' => [189]
}

Instance Method Summary collapse

Instance Method Details

#removeaccents ⇒ Object

Remove the accents from the string. Uses String::ACCENTS_MAPPING as the source map.



30
31
32
33
34
35
36
37
38
39
 
# File 'lib/simple_geolocation/utils/remove_accents.rb', line 30

def removeaccents
  str = String.new(self)
  String::ACCENTS_MAPPING.each {|letter,accents|
    packed = accents.pack('U*')
    rxp = Regexp.new("[#{packed}]", nil)
    str.gsub!(rxp, letter)
  }

  str
end

#urlize(options = {}) ⇒ Object

Convert a string to a format suitable for a URL without ever using escaped characters. It calls strip, removeaccents, downcase (optional) then removes the spaces (optional) and finally removes any characters matching the default regexp (/[^-_A-Za-z0-9]/).

Options

  • :downcase => call downcase on the string (defaults to true)

  • :convert_spaces => Convert space to underscore (defaults to false)

  • :regexp => The regexp matching characters that will be converting to an empty string (defaults to /[^-_A-Za-z0-9]/)



51
52
53
54
55
56
57
58
59
60
 
# File 'lib/simple_geolocation/utils/remove_accents.rb', line 51

def urlize(options = {})
  options[:downcase] ||= true
  options[:convert_spaces] ||= false
  options[:regexp] ||= /[^-_A-Za-z0-9]/

    str = self.strip.removeaccents
  str.downcase! if options[:downcase]
  str.gsub!(/\ /,'_') if options[:convert_spaces]
  str.gsub(options[:regexp], '')
end