Sha256: 4bb75d9be24e52fa92aeb767aaa226a186cdff3f01c9c5a6c8cf79e956346d51
Contents?: true
Size: 685 Bytes
Versions: 23
Compression:
Stored size: 685 Bytes
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
23 entries across 23 versions & 3 rubygems