Sha256: 1edd4d271234cf50b299f0fa0fa9358fb9c11f496bfc5b4876a644ec82f6de65
Contents?: true
Size: 685 Bytes
Versions: 52
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
52 entries across 50 versions & 8 rubygems