Merge issue #26355 fix from Python 3.5

4 files changed, 27 insertions, 8 deletions

diff --git a/Lib/test/test_json/__init__.py b/Lib/test/test_json/__init__.py
index 0807e6fb4f..bac370dadf 100644
--- a/Lib/test/test_json/__init__.py
+++ b/Lib/test/test_json/__init__.py
@@ -1,5 +1,4 @@
 import os
-import sys
 import json
 import doctest
 import unittest
diff --git a/Lib/test/test_json/test_decode.py b/Lib/test/test_json/test_decode.py
index fdafeb6d8f..7e568be409 100644
--- a/Lib/test/test_json/test_decode.py
+++ b/Lib/test/test_json/test_decode.py
@@ -72,10 +72,8 @@ class TestDecode:
 
     def test_invalid_input_type(self):
         msg = 'the JSON object must be str'
-        for value in [1, 3.14, b'bytes', b'\xff\x00', [], {}, None]:
+        for value in [1, 3.14, [], {}, None]:
             self.assertRaisesRegex(TypeError, msg, self.loads, value)
-        with self.assertRaisesRegex(TypeError, msg):
-            self.json.load(BytesIO(b'[1,2,3]'))
 
     def test_string_with_utf8_bom(self):
         # see #18958
diff --git a/Lib/test/test_json/test_fail.py b/Lib/test/test_json/test_fail.py
index 95ff5b8d1e..7910521021 100644
--- a/Lib/test/test_json/test_fail.py
+++ b/Lib/test/test_json/test_fail.py
@@ -1,5 +1,4 @@
 from test.test_json import PyTest, CTest
-import re
 
 # 2007-10-05
 JSONDOCS = [
diff --git a/Lib/test/test_json/test_unicode.py b/Lib/test/test_json/test_unicode.py
index c7cc8a7e92..2e8bba2775 100644
--- a/Lib/test/test_json/test_unicode.py
+++ b/Lib/test/test_json/test_unicode.py
@@ -1,3 +1,4 @@
+import codecs
 from collections import OrderedDict
 from test.test_json import PyTest, CTest
 
@@ -52,9 +53,31 @@ class TestUnicode:
         self.assertRaises(TypeError, self.dumps, [b"hi"])
 
     def test_bytes_decode(self):
-        self.assertRaises(TypeError, self.loads, b'"hi"')
-        self.assertRaises(TypeError, self.loads, b'["hi"]')
-
+        for encoding, bom in [
+                ('utf-8', codecs.BOM_UTF8),
+                ('utf-16be', codecs.BOM_UTF16_BE),
+                ('utf-16le', codecs.BOM_UTF16_LE),
+                ('utf-32be', codecs.BOM_UTF32_BE),
+                ('utf-32le', codecs.BOM_UTF32_LE),
+            ]:
+            data = ["a\xb5\u20ac\U0001d120"]
+            encoded = self.dumps(data).encode(encoding)
+            self.assertEqual(self.loads(bom + encoded), data)
+            self.assertEqual(self.loads(encoded), data)
+        self.assertRaises(UnicodeDecodeError, self.loads, b'["\x80"]')
+        # RFC-7159 and ECMA-404 extend JSON to allow documents that
+        # consist of only a string, which can present a special case
+        # not covered by the encoding detection patterns specified in
+        # RFC-4627 for utf-16-le (XX 00 XX 00).
+        self.assertEqual(self.loads('"\u2600"'.encode('utf-16-le')),
+                         '\u2600')
+        # Encoding detection for small (<4) bytes objects
+        # is implemented as a special case. RFC-7159 and ECMA-404
+        # allow single codepoint JSON documents which are only two
+        # bytes in utf-16 encodings w/o BOM.
+        self.assertEqual(self.loads(b'5\x00'), 5)
+        self.assertEqual(self.loads(b'\x007'), 7)
+        self.assertEqual(self.loads(b'57'), 57)
 
     def test_object_pairs_hook_with_unicode(self):
         s = '{"xkd":1, "kcw":2, "art":3, "hxm":4, "qrt":5, "pad":6, "hoy":7}'