search_query_logic.rb

# encoding: utf-8
require 'whittle'

# Re-opening Whittle.
#
# Riddle: What's the difference between reopened initializate method
#         and original library?
#
# Answer: There's none
#
# Reason: Regexp are encoded as source file, so Regexps defined in this file
#         are UTF-8. Regexps defined in original Whittle are US-ASCII,
#         which doesn't work with UTF-8 queries. That's why redefining
#         initialization method here, where Regexps can happily parse Unicodes.
module Whittle
  class Terminal
    def initialize(name, *components)
      raise ArgumentError, \
        "Rule #{name.inspect} is terminal and can only have one rule component" \
        unless components.length == 1

      super

      pattern = components.first

      @pattern = if pattern.kind_of?(Regexp)
        Regexp.new("\\G#{pattern}")
      else
        Regexp.new("\\G#{Regexp.escape(pattern)}")
      end
    end
  end
end