gh-59598: Ignore leading whitespace in JSONDecoder.raw_decode

crazymerlyn · crazymerlyn · commit ed178b9d16c8 · 2024-04-22T03:47:29.000+01:00
Whitespace is allowed before JSON objects according to RFC 4627.
diff --git a/Lib/json/decoder.py b/Lib/json/decoder.py
@@ -341,23 +341,27 @@ def decode(self, s, _w=WHITESPACE.match):
         containing a JSON document).
 
         """
-        obj, end = self.raw_decode(s, idx=_w(s, 0).end())
+        obj, end = self.raw_decode(s)
         end = _w(s, end).end()
         if end != len(s):
             raise JSONDecodeError("Extra data", s, end)
         return obj
 
-    def raw_decode(self, s, idx=0):
+    def raw_decode(self, s, idx=0, _w=WHITESPACE.match):
         """Decode a JSON document from ``s`` (a ``str`` beginning with
         a JSON document) and return a 2-tuple of the Python
         representation and the index in ``s`` where the document ended.
+        Whitespace at the beginning of the document will be ignored.
+
+        Optionally, ``idx`` can be used to specify an offset in ``s``
+        where the document begins.
 
         This can be used to decode a JSON document from a string that may
         have extraneous data at the end.
 
         """
         try:
-            obj, end = self.scan_once(s, idx)
+            obj, end = self.scan_once(s, idx=_w(s, idx).end())
         except StopIteration as err:
             raise JSONDecodeError("Expecting value", s, err.value) from None
         return obj, end
diff --git a/Lib/test/test_json/test_decode.py b/Lib/test/test_json/test_decode.py
@@ -103,6 +103,20 @@ def test_limit_int(self):
             with self.assertRaises(ValueError):
                 self.loads('1' * (maxdigits + 1))
 
+class TestRawDecode:
+    def test_whitespace(self):
+        decoder = self.json.JSONDecoder()
+        self.assertEqual(decoder.raw_decode(' {}'), ({}, 3))
+        self.assertEqual(decoder.raw_decode('  []'), ([], 4))
+        self.assertEqual(decoder.raw_decode('   ""'), ('', 5))
+        s = '  {   "key"    :    "value"    ,  "k":"v"    } \n' \
+            ' { "key": "value",  "k" :"v"} '
+        val1, n1 = decoder.raw_decode(s)
+        val2, n2 = decoder.raw_decode(s[n1:])
+        self.assertEqual(val1, {"key":"value", "k":"v"})
+        self.assertEqual(val2, {"key":"value", "k":"v"})
 
 class TestPyDecode(TestDecode, PyTest): pass
 class TestCDecode(TestDecode, CTest): pass
+class TestPyRawDecode(TestRawDecode, PyTest): pass
+class TestCRawDecode(TestRawDecode, CTest): pass
