Contents

# encoding: utf-8
#
# THINK Does it also remove diaritics, like べ to へ?
#
module Picky

  module CharacterSubstituters

    # Substitutes Umlauts like
    # ä, ö, ü => ae, oe, ue.
    # (and more, see specs)
    #
    class WestEuropean

      def initialize # :nodoc:
        @chars = ActiveSupport::Multibyte.proxy_class
      end

      # Substitutes occurrences of certain characters
      # (like Umlauts) with ASCII representations of them.
      #
      # Examples:
      #   ä -> ae
      #   Ö -> Oe
      #   ß -> ss
      #   ç -> c
      #
      # (See the associated spec for all examples)
      #
      def substitute text
        trans = @chars.new(text).normalize(:kd)

        # Substitute special cases.
        #
        trans.gsub!('ß', 'ss')

        # Substitute umlauts (of A,O,U,a,o,u).
        #
        trans.gsub!(/([AOUaou])\314\210/u, '\1e')

        # Get rid of ecutes, graves etc.
        #
        trans.unpack('U*').select { |cp|
          cp < 0x0300 || cp > 0x035F
        }.pack('U*')
      end

      def to_s # :nodoc:
        self.class.name
      end

    end

  end

end

Version data entries

26 entries across 26 versions & 1 rubygems

Version	Path
picky-3.1.3	lib/picky/character_substituters/west_european.rb
picky-3.1.2	lib/picky/character_substituters/west_european.rb
picky-3.1.1	lib/picky/character_substituters/west_european.rb
picky-3.1.0	lib/picky/character_substituters/west_european.rb
picky-3.0.1	lib/picky/character_substituters/west_european.rb
picky-3.0.0	lib/picky/character_substituters/west_european.rb