if not isinstance(s, str):
raise TypeError('the JSON object must be str, not {!r}'.format(
s.__class__.__name__))
+ if s.startswith(u'\ufeff'):
+ raise ValueError("Unexpected UTF-8 BOM (decode using utf-8-sig)")
if (cls is None and object_hook is None and
parse_int is None and parse_float is None and
parse_constant is None and object_pairs_hook is None and not kw):
with self.assertRaisesRegex(TypeError, msg):
self.json.load(BytesIO(b'[1,2,3]'))
+ def test_string_with_utf8_bom(self):
+ # see #18958
+ bom_json = "[1,2,3]".encode('utf-8-sig').decode('utf-8')
+ with self.assertRaises(ValueError) as cm:
+ self.loads(bom_json)
+ self.assertIn('BOM', str(cm.exception))
+ with self.assertRaises(ValueError) as cm:
+ self.json.load(StringIO(bom_json))
+ self.assertIn('BOM', str(cm.exception))
+ # make sure that the BOM is not detected in the middle of a string
+ bom_in_str = '"{}"'.format(''.encode('utf-8-sig').decode('utf-8'))
+ self.assertEqual(self.loads(bom_in_str), '\ufeff')
+ self.assertEqual(self.json.load(StringIO(bom_in_str)), '\ufeff')
+
class TestPyDecode(TestDecode, PyTest): pass
class TestCDecode(TestDecode, CTest): pass
Library
-------
+- Issue #18958: Improve error message for json.load(s) while passing a string
+ that starts with a UTF-8 BOM.
+
- Issue #19307: Improve error message for json.load(s) while passing objects
of the wrong type.