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.

Author: Brett Carter

activesupport/CHANGELOG.md

@@ -1,4 +1,10 @@
 ## Rails 4.0.0 (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*
 
 *   Deprecate `Time.time_with_date_fallback`, `Time.utc_time` and `Time.local_time`.
     These methods were added to handle the limited range of Ruby's native Time

activesupport/lib/active_support/json/encoding.rb

@@ -129,13 +129,7 @@ def escape_html_entities_in_json=(value)
 
         def escape(string)
           string = string.encode(::Encoding::UTF_8, :undef => :replace).force_encoding(::Encoding::BINARY)
-          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)
           json

activesupport/test/json/encoding_test.rb

@@ -112,21 +112,34 @@ def test_hash_encoding
 
   def test_utf8_string_encoded_properly
     result = ActiveSupport::JSON.encode('€2.99')
-    assert_equal '"\\u20ac2.99"', result
+    assert_equal '"€2.99"', result
     assert_equal(Encoding::UTF_8, result.encoding)
 
     result = ActiveSupport::JSON.encode('✎☺')
-    assert_equal '"\\u270e\\u263a"', result
+    assert_equal '"✎☺"', result
     assert_equal(Encoding::UTF_8, result.encoding)
   end
 
   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
 
+  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