From 518389d1ef41f8c4116bc844bad44356c7aa4f9d Mon Sep 17 00:00:00 2001 From: Jeremy Kemper Date: Fri, 20 Feb 2009 18:38:18 -0800 Subject: [PATCH] Broaden URI.unescape fix to all affected 1.9.x by checking for broken behavior instead of specific patchlevel --- .../lib/active_support/core_ext/uri.rb | 18 ++++++++++++------ activesupport/test/core_ext/uri_ext_test.rb | 11 ++++++----- 2 files changed, 18 insertions(+), 11 deletions(-) diff --git a/activesupport/lib/active_support/core_ext/uri.rb b/activesupport/lib/active_support/core_ext/uri.rb index 4c8ebbee5805e..9a1c61d99b59a 100644 --- a/activesupport/lib/active_support/core_ext/uri.rb +++ b/activesupport/lib/active_support/core_ext/uri.rb @@ -1,10 +1,16 @@ -if RUBY_VERSION == "1.9.1" && defined?(RUBY_PATCHLEVEL) && RUBY_PATCHLEVEL == 0 +if RUBY_VERSION >= '1.9' require 'uri' - URI::Parser.class_eval do - remove_method :unescape - def unescape(str, escaped = @regexp[:ESCAPED]) - enc = (str.encoding == Encoding::US_ASCII) ? Encoding::UTF_8 : str.encoding - str.gsub(escaped) { [$&[1, 2].hex].pack('C') }.force_encoding(enc) + + str = "\xE6\x97\xA5\xE6\x9C\xAC\xE8\xAA\x9E" # Ni-ho-nn-go in UTF-8, means Japanese. + str.force_encoding(Encoding::UTF_8) if str.respond_to?(:force_encoding) + + unless str == URI.unescape(URI.escape(str)) + URI::Parser.class_eval do + remove_method :unescape + def unescape(str, escaped = @regexp[:ESCAPED]) + enc = (str.encoding == Encoding::US_ASCII) ? Encoding::UTF_8 : str.encoding + str.gsub(escaped) { [$&[1, 2].hex].pack('C') }.force_encoding(enc) + end end end end diff --git a/activesupport/test/core_ext/uri_ext_test.rb b/activesupport/test/core_ext/uri_ext_test.rb index f25bc97aa5dfb..0837d3cb2daa9 100644 --- a/activesupport/test/core_ext/uri_ext_test.rb +++ b/activesupport/test/core_ext/uri_ext_test.rb @@ -1,11 +1,12 @@ require 'abstract_unit' +require 'uri' -class URITest < Test::Unit::TestCase +class URIExtTest < Test::Unit::TestCase def test_uri_decode_handle_multibyte - str = "\xE6\x97\xA5\xE6\x9C\xAC\xE8\xAA\x9E" # Ni-ho-nn-go in UTF-8, means Japanese. - str.force_encoding(Encoding::UTF_8) if(defined? Encoding::UTF_8) + str = "\xE6\x97\xA5\xE6\x9C\xAC\xE8\xAA\x9E" # Ni-ho-nn-go in UTF-8, means Japanese. + str.force_encoding(Encoding::UTF_8) if str.respond_to?(:force_encoding) - assert_equal str, ::URI.unescape( ::URI.escape(str) ) - assert_equal str, ::URI.decode( ::URI.escape(str) ) + assert_equal str, URI.unescape(URI.escape(str)) + assert_equal str, URI.decode(URI.escape(str)) end end