* lib/uri/common.rb (URI.decode_www_form): scrub string if decoded

  bytes are invalid for the encoding.

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@40820 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

3 files changed, 16 insertions, 13 deletions

diff --git a/ChangeLog b/ChangeLog
index d56bc85af7..dd50f1c296 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,8 @@
+Sun May 19 03:48:26 2013  NARUSE, Yui  <naruse@ruby-lang.org>
+
+	* lib/uri/common.rb (URI.decode_www_form): scrub string if decoded
+	  bytes are invalid for the encoding.
+
 Sun May 19 02:46:32 2013  Akinori MUSHA  <knu@iDaemons.org>
 
 	* lib/set.rb (Set#delete_if, Set#keep_if): Make Set#delete_if and
diff --git a/lib/uri/common.rb b/lib/uri/common.rb
index 5914868e94..1da9f47647 100644
--- a/lib/uri/common.rb
+++ b/lib/uri/common.rb
@@ -981,17 +981,9 @@ module URI
         isindex = false
       end
 
-      if use__charset_
-        if key == '_charset_'
-          if e = get_encoding(val)
-            enc = e
-            use__charset_ = false
-            ary.each do |k, v|
-              v.force_encoding(enc)
-              k.force_encoding(enc)
-            end
-          end
-        end
+      if use__charset_ and key == '_charset_' and e = get_encoding(val)
+        enc = e
+        use__charset_ = false
       end
 
       key.gsub!(/\+|%\h\h/, TBLDECWWWCOMP_)
@@ -1001,10 +993,14 @@ module URI
         val = ''
       end
 
-      val.force_encoding(enc)
-      key.force_encoding(enc)
       ary << [key, val]
     end
+    ary.each do |k, v|
+      k.force_encoding(enc)
+      k.scrub!
+      v.force_encoding(enc)
+      v.scrub!
+    end
     ary
   end
 
diff --git a/test/uri/test_common.rb b/test/uri/test_common.rb
index a72d7bf9be..65a92f3868 100644
--- a/test/uri/test_common.rb
+++ b/test/uri/test_common.rb
@@ -135,6 +135,8 @@ class TestCommon < Test::Unit::TestCase
     assert_raise(ArgumentError){URI.decode_www_form("\u3042")}
     assert_equal([%w[a 1], ["\u3042", "\u6F22"]],
                  URI.decode_www_form("a=1&%E3%81%82=%E6%BC%A2"))
+    assert_equal([%w[a 1], ["\uFFFD%8", "\uFFFD"]],
+                 URI.decode_www_form("a=1&%E3%81%8=%E6%BC"))
     assert_equal([%w[?a 1], %w[a 2]], URI.decode_www_form("?a=1&a=2"))
     assert_equal([], URI.decode_www_form(""))
     assert_equal([%w[% 1]], URI.decode_www_form("%=1"))