Remove unicode character encoding from ActiveSupport::JSON.encode

The encoding scheme (e.g. ☠ -> "\u2620") was broken for characters
not in the Basic Multilingual Plane.  It is possible to escape them
for json using the weird encoding scheme of a twelve-character
sequence representing the UTF-16 surrogate pair (e.g. '𠜎' ->
"\u270e\u263a") but this wasn't properly handled in the escaping code.
Since raw UTF-8 is allowed in json, it was decided to simply pass
through the raw bytes rather than attempt to escape them.

Backport of https://github.com/zbskii/rails/commit/9ace3a8820a5270f9b3f37b593f8bbea3e940f73

Conflicts:

	activesupport/CHANGELOG.md
	activesupport/lib/active_support/json/encoding.rb
	activesupport/test/json/encoding_test.rb

3 files changed, 24 insertions, 10 deletions

diff --git a/activesupport/CHANGELOG.md b/activesupport/CHANGELOG.md
index a3e1854ada..88707d7edb 100644
--- a/activesupport/CHANGELOG.md
+++ b/activesupport/CHANGELOG.md
@@ -1,5 +1,12 @@
 ## Rails 3.2.10 (unreleased)
 
+*   Remove surrogate unicode character encoding from ActiveSupport::JSON.encode
+    The encoding scheme was broken for unicode characters outside the basic
+    multilingual plane; since json is assumed to be UTF-8, and we already force the
+    encoding to UTF-8 simply pass through the un-encoded characters.
+
+    *Brett Carter*
+
 *   Fix mocha v0.13.0 compatibility. *James Mead*
 
 *   `#as_json` isolates options when encoding a hash. [Backport #8185]
diff --git a/activesupport/lib/active_support/json/encoding.rb b/activesupport/lib/active_support/json/encoding.rb
index bd2f909ca9..a50e6524c6 100644
--- a/activesupport/lib/active_support/json/encoding.rb
+++ b/activesupport/lib/active_support/json/encoding.rb
@@ -122,13 +122,7 @@ module ActiveSupport
           if string.respond_to?(:force_encoding)
             string = string.encode(::Encoding::UTF_8, :undef => :replace).force_encoding(::Encoding::BINARY)
           end
-          json = string.
-            gsub(escape_regex) { |s| ESCAPED_CHARS[s] }.
-            gsub(/([\xC0-\xDF][\x80-\xBF]|
-                   [\xE0-\xEF][\x80-\xBF]{2}|
-                   [\xF0-\xF7][\x80-\xBF]{3})+/nx) { |s|
-            s.unpack("U*").pack("n*").unpack("H*")[0].gsub(/.{4}/n, '\\\\u\&')
-          }
+          json = string.gsub(escape_regex) { |s| ESCAPED_CHARS[s] }
           json = %("#{json}")
           json.force_encoding(::Encoding::UTF_8) if json.respond_to?(:force_encoding)
           json
diff --git a/activesupport/test/json/encoding_test.rb b/activesupport/test/json/encoding_test.rb
index 19881287b5..b734729988 100644
--- a/activesupport/test/json/encoding_test.rb
+++ b/activesupport/test/json/encoding_test.rb
@@ -100,11 +100,11 @@ class TestJSONEncoding < Test::Unit::TestCase
   def test_utf8_string_encoded_properly_when_kcode_is_utf8
     with_kcode 'UTF8' do
       result = ActiveSupport::JSON.encode('€2.99')
-      assert_equal '"\\u20ac2.99"', result
+      assert_equal '"€2.99"', result
       assert_equal(Encoding::UTF_8, result.encoding) if result.respond_to?(:encoding)
 
       result = ActiveSupport::JSON.encode('✎☺')
-      assert_equal '"\\u270e\\u263a"', result
+      assert_equal '"✎☺"', result
       assert_equal(Encoding::UTF_8, result.encoding) if result.respond_to?(:encoding)
     end
   end
@@ -113,11 +113,24 @@ class TestJSONEncoding < Test::Unit::TestCase
     def test_non_utf8_string_transcodes
       s = '二'.encode('Shift_JIS')
       result = ActiveSupport::JSON.encode(s)
-      assert_equal '"\\u4e8c"', result
+      assert_equal '"二"', result
       assert_equal Encoding::UTF_8, result.encoding
     end
   end
 
+  def test_wide_utf8_chars
+    w = '𠜎'
+    result = ActiveSupport::JSON.encode(w)
+    assert_equal '"𠜎"', result
+  end
+
+  def test_wide_utf8_roundtrip
+    hash = { string: "𐒑" }
+    json = ActiveSupport::JSON.encode(hash)
+    decoded_hash = ActiveSupport::JSON.decode(json)
+    assert_equal "𐒑", decoded_hash['string']
+  end
+
   def test_exception_raised_when_encoding_circular_reference_in_array
     a = [1]
     a << a