RustPython · youknowone · Jul 20, 2025 · Jul 20, 2025 · Jul 20, 2025 · Jul 20, 2025
diff --git a/Lib/json/__init__.py b/Lib/json/__init__.py
@@ -1,4 +1,4 @@
-r"""JSON (JavaScript Object Notation) <http://json.org> is a subset of
+r"""JSON (JavaScript Object Notation) <https://json.org> is a subset of
 JavaScript syntax (ECMA-262 3rd edition) used as a lightweight data
 interchange format.
 

diff --git a/Lib/json/decoder.py b/Lib/json/decoder.py
@@ -41,7 +41,6 @@ def _from_serde(cls, msg, doc, line, col):
         pos += col
         return cls(msg, doc, pos)
 
-
     # Note that this exception is used from _json
     def __init__(self, msg, doc, pos):
         lineno = doc.count('\n', 0, pos) + 1
@@ -65,17 +64,18 @@ def __reduce__(self):
 }
 
 
+HEXDIGITS = re.compile(r'[0-9A-Fa-f]{4}', FLAGS)
 STRINGCHUNK = re.compile(r'(.*?)(["\\\x00-\x1f])', FLAGS)
 BACKSLASH = {
     '"': '"', '\\': '\\', '/': '/',
     'b': '\b', 'f': '\f', 'n': '\n', 'r': '\r', 't': '\t',
 }
 
-def _decode_uXXXX(s, pos):
-    esc = s[pos + 1:pos + 5]
-    if len(esc) == 4 and esc[1] not in 'xX':
+def _decode_uXXXX(s, pos, _m=HEXDIGITS.match):
+    esc = _m(s, pos + 1)
+    if esc is not None:
         try:
-            return int(esc, 16)
+            return int(esc.group(), 16)
         except ValueError:
             pass
     msg = "Invalid \\uXXXX escape"
@@ -215,10 +215,13 @@ def JSONObject(s_and_end, strict, scan_once, object_hook, object_pairs_hook,
             break
         elif nextchar != ',':
             raise JSONDecodeError("Expecting ',' delimiter", s, end - 1)
+        comma_idx = end - 1
         end = _w(s, end).end()
         nextchar = s[end:end + 1]
         end += 1
         if nextchar != '"':
+            if nextchar == '}':
+                raise JSONDecodeError("Illegal trailing comma before end of object", s, comma_idx)
             raise JSONDecodeError(
                 "Expecting property name enclosed in double quotes", s, end - 1)
     if object_pairs_hook is not None:
@@ -255,19 +258,23 @@ def JSONArray(s_and_end, scan_once, _w=WHITESPACE.match, _ws=WHITESPACE_STR):
             break
         elif nextchar != ',':
             raise JSONDecodeError("Expecting ',' delimiter", s, end - 1)
+        comma_idx = end - 1
         try:
             if s[end] in _ws:
                 end += 1
                 if s[end] in _ws:
                     end = _w(s, end + 1).end()
+            nextchar = s[end:end + 1]
         except IndexError:
             pass
+        if nextchar == ']':
+            raise JSONDecodeError("Illegal trailing comma before end of array", s, comma_idx)
 
     return values, end
 
 
 class JSONDecoder(object):
-    """Simple JSON <http://json.org> decoder
+    """Simple JSON <https://json.org> decoder
 
     Performs the following translations in decoding by default:
 

diff --git a/Lib/json/encoder.py b/Lib/json/encoder.py
@@ -30,6 +30,7 @@
 for i in range(0x20):
     ESCAPE_DCT.setdefault(chr(i), '\\u{0:04x}'.format(i))
     #ESCAPE_DCT.setdefault(chr(i), '\\u%04x' % (i,))
+del i
 
 INFINITY = float('inf')
 
@@ -71,7 +72,7 @@ def replace(match):
     c_encode_basestring_ascii or py_encode_basestring_ascii)
 
 class JSONEncoder(object):
-    """Extensible JSON <http://json.org> encoder for Python data structures.
+    """Extensible JSON <https://json.org> encoder for Python data structures.
 
     Supports the following objects and types by default:
 
@@ -107,8 +108,8 @@ def __init__(self, *, skipkeys=False, ensure_ascii=True,
         """Constructor for JSONEncoder, with sensible defaults.
 
         If skipkeys is false, then it is a TypeError to attempt
-        encoding of keys that are not str, int, float or None.  If
-        skipkeys is True, such items are simply skipped.
+        encoding of keys that are not str, int, float, bool or None.
+        If skipkeys is True, such items are simply skipped.
 
         If ensure_ascii is true, the output is guaranteed to be str
         objects with all incoming non-ASCII characters escaped.  If
@@ -173,7 +174,7 @@ def default(self, o):
                 else:
                     return list(iterable)
                 # Let the base class default method raise the TypeError
-                return JSONEncoder.default(self, o)
+                return super().default(o)
 
         """
         raise TypeError(f'Object of type {o.__class__.__name__} '
@@ -243,15 +244,18 @@ def floatstr(o, allow_nan=self.allow_nan,
             return text
 
 
-        if (_one_shot and c_make_encoder is not None
-                and self.indent is None):
+        if self.indent is None or isinstance(self.indent, str):
+            indent = self.indent
+        else:
+            indent = ' ' * self.indent
+        if _one_shot and c_make_encoder is not None:
             _iterencode = c_make_encoder(
-                markers, self.default, _encoder, self.indent,
+                markers, self.default, _encoder, indent,
                 self.key_separator, self.item_separator, self.sort_keys,
                 self.skipkeys, self.allow_nan)
         else:
             _iterencode = _make_iterencode(
-                markers, self.default, _encoder, self.indent, floatstr,
+                markers, self.default, _encoder, indent, floatstr,
                 self.key_separator, self.item_separator, self.sort_keys,
                 self.skipkeys, _one_shot)
         return _iterencode(o, 0)
@@ -271,9 +275,6 @@ def _make_iterencode(markers, _default, _encoder, _indent, _floatstr,
         _intstr=int.__repr__,
     ):
 
-    if _indent is not None and not isinstance(_indent, str):
-        _indent = ' ' * _indent
-
     def _iterencode_list(lst, _current_indent_level):
         if not lst:
             yield '[]'
@@ -344,7 +345,6 @@ def _iterencode_dict(dct, _current_indent_level):
             _current_indent_level += 1
             newline_indent = '\n' + _indent * _current_indent_level
             item_separator = _item_separator + newline_indent
-            yield newline_indent
         else:
             newline_indent = None
             item_separator = _item_separator
@@ -377,6 +377,8 @@ def _iterencode_dict(dct, _current_indent_level):
                                 f'not {key.__class__.__name__}')
             if first:
                 first = False
+                if newline_indent is not None:
+                    yield newline_indent
             else:
                 yield item_separator
             yield _encoder(key)
@@ -403,7 +405,7 @@ def _iterencode_dict(dct, _current_indent_level):
                 else:
                     chunks = _iterencode(value, _current_indent_level)
                 yield from chunks
-        if newline_indent is not None:
+        if not first and newline_indent is not None:
             _current_indent_level -= 1
             yield '\n' + _indent * _current_indent_level
         yield '}'

diff --git a/Lib/json/scanner.py b/Lib/json/scanner.py
@@ -9,7 +9,7 @@
 __all__ = ['make_scanner']
 
 NUMBER_RE = re.compile(
-    r'(-?(?:0|[1-9]\d*))(\.\d+)?([eE][-+]?\d+)?',
+    r'(-?(?:0|[1-9][0-9]*))(\.[0-9]+)?([eE][-+]?[0-9]+)?',
     (re.VERBOSE | re.MULTILINE | re.DOTALL))
 
 def py_make_scanner(context):

diff --git a/Lib/json/tool.py b/Lib/json/tool.py
@@ -13,7 +13,6 @@
 import argparse
 import json
 import sys
-from pathlib import Path
 
 
 def main():
@@ -22,11 +21,9 @@ def main():
                    'to validate and pretty-print JSON objects.')
     parser = argparse.ArgumentParser(prog=prog, description=description)
     parser.add_argument('infile', nargs='?',
-                        type=argparse.FileType(encoding="utf-8"),
                         help='a JSON file to be validated or pretty-printed',
-                        default=sys.stdin)
+                        default='-')
     parser.add_argument('outfile', nargs='?',
-                        type=Path,
                         help='write the output of infile to outfile',
                         default=None)
     parser.add_argument('--sort-keys', action='store_true', default=False,
@@ -59,23 +56,30 @@ def main():
         dump_args['indent'] = None
         dump_args['separators'] = ',', ':'
 
-    with options.infile as infile:
+    try:
+        if options.infile == '-':
+            infile = sys.stdin
+        else:
+            infile = open(options.infile, encoding='utf-8')
         try:
             if options.json_lines:
                 objs = (json.loads(line) for line in infile)
             else:
                 objs = (json.load(infile),)
+        finally:
+            if infile is not sys.stdin:
+                infile.close()
 
-            if options.outfile is None:
-                out = sys.stdout
-            else:
-                out = options.outfile.open('w', encoding='utf-8')
-            with out as outfile:
-                for obj in objs:
-                    json.dump(obj, outfile, **dump_args)
-                    outfile.write('\n')
-        except ValueError as e:
-            raise SystemExit(e)
+        if options.outfile is None:
+            outfile = sys.stdout
+        else:
+            outfile = open(options.outfile, 'w', encoding='utf-8')
+        with outfile:
+            for obj in objs:
+                json.dump(obj, outfile, **dump_args)
+                outfile.write('\n')
+    except ValueError as e:
+        raise SystemExit(e)
 
 
 if __name__ == '__main__':

diff --git a/Lib/test/test_json/test_decode.py b/Lib/test/test_json/test_decode.py
@@ -2,21 +2,50 @@
 from io import StringIO
 from collections import OrderedDict
 from test.test_json import PyTest, CTest
+from test import support
 
-import unittest
+import unittest # XXX: RUSTPYTHON; importing to be able to skip tests
 
 
 class TestDecode:
     def test_decimal(self):
         rval = self.loads('1.1', parse_float=decimal.Decimal)
-        self.assertTrue(isinstance(rval, decimal.Decimal))
+        self.assertIsInstance(rval, decimal.Decimal)
         self.assertEqual(rval, decimal.Decimal('1.1'))
 
     def test_float(self):
         rval = self.loads('1', parse_int=float)
-        self.assertTrue(isinstance(rval, float))
+        self.assertIsInstance(rval, float)
         self.assertEqual(rval, 1.0)
 
+    # TODO: RUSTPYTHON
+    @unittest.skip("TODO: RUSTPYTHON; called `Result::unwrap()` on an `Err` value: ParseFloatError { kind: Invalid }")
+    def test_nonascii_digits_rejected(self):
+        # JSON specifies only ascii digits, see gh-125687
+        for num in ["1\uff10", "0.\uff10", "0e\uff10"]:
+            with self.assertRaises(self.JSONDecodeError):
+                self.loads(num)
+
+    def test_bytes(self):
+        self.assertEqual(self.loads(b"1"), 1)
+
+    def test_parse_constant(self):
+        for constant, expected in [
+            ("Infinity", "INFINITY"),
+            ("-Infinity", "-INFINITY"),
+            ("NaN", "NAN"),
+        ]:
+            self.assertEqual(
+                self.loads(constant, parse_constant=str.upper), expected
+            )
+
+    def test_constant_invalid_case(self):
+        for constant in [
+            "nan", "NAN", "naN", "infinity", "INFINITY", "inFiniTy"
+        ]:
+            with self.assertRaises(self.JSONDecodeError):
+                self.loads(constant)
+
     def test_empty_objects(self):
         self.assertEqual(self.loads('{}'), {})
         self.assertEqual(self.loads('[]'), [])
@@ -89,17 +118,28 @@ def test_string_with_utf8_bom(self):
             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'))
+        bom = ''.encode('utf-8-sig').decode('utf-8')
+        bom_in_str = f'"{bom}"'
         self.assertEqual(self.loads(bom_in_str), '\ufeff')
         self.assertEqual(self.json.load(StringIO(bom_in_str)), '\ufeff')
 
     def test_negative_index(self):
         d = self.json.JSONDecoder()
         self.assertRaises(ValueError, d.raw_decode, 'a'*42, -50000)
 
+    # TODO: RUSTPYTHON
+    @unittest.expectedFailure
+    def test_limit_int(self):
+        maxdigits = 5000
+        with support.adjust_int_max_str_digits(maxdigits):
+            self.loads('1' * maxdigits)
+            with self.assertRaises(ValueError):
+                self.loads('1' * (maxdigits + 1))
+
+
 class TestPyDecode(TestDecode, PyTest): pass
-# TODO: RUSTPYTHON
-class TestCDecode(TestDecode, CTest): # pass
+
+class TestCDecode(TestDecode, CTest):
     # TODO: RUSTPYTHON
     @unittest.expectedFailure
     def test_keys_reuse(self):

diff --git a/Lib/test/test_json/test_default.py b/Lib/test/test_json/test_default.py
@@ -1,3 +1,4 @@
+import collections
 from test.test_json import PyTest, CTest
 
 
@@ -7,6 +8,16 @@ def test_default(self):
             self.dumps(type, default=repr),
             self.dumps(repr(type)))
 
+    def test_ordereddict(self):
+        od = collections.OrderedDict(a=1, b=2, c=3, d=4)
+        od.move_to_end('b')
+        self.assertEqual(
+            self.dumps(od),
+            '{"a": 1, "c": 3, "d": 4, "b": 2}')
+        self.assertEqual(
+            self.dumps(od, sort_keys=True),
+            '{"a": 1, "b": 2, "c": 3, "d": 4}')
+
 
 class TestPyDefault(TestDefault, PyTest): pass
 class TestCDefault(TestDefault, CTest): pass
diff --git a/Lib/test/test_json/test_dump.py b/Lib/test/test_json/test_dump.py
@@ -22,6 +22,14 @@ def test_dump_skipkeys(self):
         self.assertIn('valid_key', o)
         self.assertNotIn(b'invalid_key', o)
 
+    def test_dump_skipkeys_indent_empty(self):
+        v = {b'invalid_key': False}
+        self.assertEqual(self.json.dumps(v, skipkeys=True, indent=4), '{}')
+
+    def test_skipkeys_indent(self):
+        v = {b'invalid_key': False, 'valid_key': True}
+        self.assertEqual(self.json.dumps(v, skipkeys=True, indent=4), '{\n    "valid_key": true\n}')
+
     def test_encode_truefalse(self):
         self.assertEqual(self.dumps(
                  {True: False, False: True}, sort_keys=True),

diff --git a/Lib/test/test_json/test_encode_basestring_ascii.py b/Lib/test/test_json/test_encode_basestring_ascii.py
@@ -23,8 +23,7 @@ def test_encode_basestring_ascii(self):
         for input_string, expect in CASES:
             result = self.json.encoder.encode_basestring_ascii(input_string)
             self.assertEqual(result, expect,
-                '{0!r} != {1!r} for {2}({3!r})'.format(
-                    result, expect, fname, input_string))
+                f'{result!r} != {expect!r} for {fname}({input_string!r})')
 
     def test_ordered_dict(self):
         # See issue 6105