Contents

require 'uri'

str = "\xE6\x97\xA5\xE6\x9C\xAC\xE8\xAA\x9E" # Ni-ho-nn-go in UTF-8, means Japanese.
parser = URI::Parser.new

unless str == parser.unescape(parser.escape(str))
  URI::Parser.class_eval do
    remove_method :unescape
    def unescape(str, escaped = /%[a-fA-F\d]{2}/)
      # TODO: Are we actually sure that ASCII == UTF-8?
      # YK: My initial experiments say yes, but let's be sure please
      enc = str.encoding
      enc = Encoding::UTF_8 if enc == Encoding::US_ASCII
      str.gsub(escaped) { |match| [match[1, 2].hex].pack('C') }.force_encoding(enc)
    end
  end
end

module URI
  class << self
    def parser
      @parser ||= URI::Parser.new
    end
  end
end

Version data entries

6 entries across 6 versions & 1 rubygems

Version	Path
core_ext-0.0.6	lib/core_ext/uri.rb
core_ext-0.0.5	lib/core_ext/uri.rb
core_ext-0.0.4	lib/core_ext/uri.rb
core_ext-0.0.3	lib/core_ext/uri.rb
core_ext-0.0.2	lib/core_ext/uri.rb
core_ext-0.0.1	lib/core_ext/uri.rb