sorah	2013-07-31 18:00:18 +0900 (Wed, 31 Jul 2013)

  New Revision: 42271

  http://svn.ruby-lang.org/cgi-bin/viewvc.cgi?view=rev&revision=42271

  Log:
    * lib/uri/common.rb (URI.decode_www_form_component):
      Don't raise error when str includes multibyte characters.

  Modified files:
    trunk/ChangeLog
    trunk/lib/uri/common.rb
    trunk/test/uri/test_common.rb

Index: ChangeLog
===================================================================
--- ChangeLog	(revision 42270)
+++ ChangeLog	(revision 42271)
@@ -1,3 +1,8 @@ https://github.com/ruby/ruby/blob/trunk/ChangeLog#L1
+Wed Jul 31 17:55:55 2013  Shota Fukumori  <her@s...>
+
+	* lib/uri/common.rb (URI.decode_www_form_component):
+	  Don't raise error when str includes multibyte characters.
+
 Wed Jul 31 17:45:39 2013  Masaki Matsushita  <glass.saga@g...>
 
 	* string.c (rb_str_rindex): performance improvement by using
Index: lib/uri/common.rb
===================================================================
--- lib/uri/common.rb	(revision 42270)
+++ lib/uri/common.rb	(revision 42271)
@@ -899,7 +899,9 @@ module URI https://github.com/ruby/ruby/blob/trunk/lib/uri/common.rb#L899
   # See URI.encode_www_form_component, URI.decode_www_form
   def self.decode_www_form_component(str, enc=Encoding::UTF_8)
     raise ArgumentError, "invalid %-encoding (#{str})" unless /\A[^%]*(?:%\h\h[^%]*)*\z/ =~ str
-    str.gsub(/\+|%\h\h/, TBLDECWWWCOMP_).force_encoding(enc)
+    str.dup.force_encoding("ASCII-8BIT") \
+       .gsub(/\+|%\h\h/, TBLDECWWWCOMP_) \
+       .force_encoding(enc)
   end
 
   # Generate URL-encoded form data from given +enum+.
Index: test/uri/test_common.rb
===================================================================
--- test/uri/test_common.rb	(revision 42270)
+++ test/uri/test_common.rb	(revision 42271)
@@ -91,6 +91,9 @@ class TestCommon < Test::Unit::TestCase https://github.com/ruby/ruby/blob/trunk/test/uri/test_common.rb#L91
                    "AZ%5B%5C%5D%5E_%60az%7B%7C%7D%7E"))
     assert_equal("\xA1\xA2".force_encoding(Encoding::EUC_JP),
                  URI.decode_www_form_component("%A1%A2", "EUC-JP"))
+    assert_equal("\xE3\x81\x82\xE3\x81\x82".force_encoding("UTF-8"),
+                 URI.decode_www_form_component("\xE3\x81\x82%E3%81%82".force_encoding("UTF-8")))
+
     assert_raise(ArgumentError){URI.decode_www_form_component("%")}
   end
 

--
ML: ruby-changes@q...
Info: http://www.atdot.net/~ko1/quickml/