Files
RustPython/Lib/test/test_json/test_scanstring.py
T
Jeong, YunWonandJames David Clarke 1dcdec4dd5 Port the remaining runtime fixes from #7993 (#8995)
* Take re pos/endpos as signed integers

Negative values clamp to 0, and values beyond Py_ssize_t raise
OverflowError.

Assisted-by: Claude Code:claude-opus-5-5

* Port the remaining runtime fixes from #7993

- bytearray: keep the buffer exported while converting the needle of
  find/count/index/rfind/rindex/__contains__/split/rsplit and the hex
  separator, so resizing from there raises BufferError
- str(): report non-str encoding/errors as "str() argument 'X' must be
  str, not T", and check argument counts and name/position duplicates
  for keyword calls
- _json.scanstring: take end as a signed integer and raise ValueError
  when it is out of bounds
- lzma: reject filter specs with keys the filter does not take
- mmap: raise ValueError when growing a shared anonymous mapping on
  Linux/NetBSD
- _sqlite3: check that the backup progress argument is callable
- Remove the expectedFailure markers of the tests these fix

Assisted-by: Claude Code:claude-opus-5-5

* Reject arguments given by name and position in FuncArgs::bind_for

bind_for reports a keyword that fills a parameter already given by
position before other binding errors, using the parameter list of the
FromArgs type. getargs shares the message, str() drops its own check,
and blake2b/blake2s name themselves in binding errors.

Assisted-by: Claude Code:claude-opus-5-5

---------

Co-authored-by: James David Clarke <james@jamesdavidclarke.com>
2026-10-08 08:11:26 +09:00

154 lines
4.9 KiB
Python
Vendored

import sys
from test.test_json import PyTest, CTest
import unittest # XXX: RUSTPYTHON; importing to be able to skip tests
class TestScanstring:
def test_scanstring(self):
scanstring = self.json.decoder.scanstring
self.assertEqual(
scanstring('"z\U0001d120x"', 1, True),
('z\U0001d120x', 5))
self.assertEqual(
scanstring('"\\u007b"', 1, True),
('{', 8))
self.assertEqual(
scanstring('"A JSON payload should be an object or array, not a string."', 1, True),
('A JSON payload should be an object or array, not a string.', 60))
self.assertEqual(
scanstring('["Unclosed array"', 2, True),
('Unclosed array', 17))
self.assertEqual(
scanstring('["extra comma",]', 2, True),
('extra comma', 14))
self.assertEqual(
scanstring('["double extra comma",,]', 2, True),
('double extra comma', 21))
self.assertEqual(
scanstring('["Comma after the close"],', 2, True),
('Comma after the close', 24))
self.assertEqual(
scanstring('["Extra close"]]', 2, True),
('Extra close', 14))
self.assertEqual(
scanstring('{"Extra comma": true,}', 2, True),
('Extra comma', 14))
self.assertEqual(
scanstring('{"Extra value after close": true} "misplaced quoted value"', 2, True),
('Extra value after close', 26))
self.assertEqual(
scanstring('{"Illegal expression": 1 + 2}', 2, True),
('Illegal expression', 21))
self.assertEqual(
scanstring('{"Illegal invocation": alert()}', 2, True),
('Illegal invocation', 21))
self.assertEqual(
scanstring('{"Numbers cannot have leading zeroes": 013}', 2, True),
('Numbers cannot have leading zeroes', 37))
self.assertEqual(
scanstring('{"Numbers cannot be hex": 0x14}', 2, True),
('Numbers cannot be hex', 24))
self.assertEqual(
scanstring('[[[[[[[[[[[[[[[[[[[["Too deep"]]]]]]]]]]]]]]]]]]]]', 21, True),
('Too deep', 30))
self.assertEqual(
scanstring('{"Missing colon" null}', 2, True),
('Missing colon', 16))
self.assertEqual(
scanstring('{"Double colon":: null}', 2, True),
('Double colon', 15))
self.assertEqual(
scanstring('{"Comma instead of colon", null}', 2, True),
('Comma instead of colon', 25))
self.assertEqual(
scanstring('["Colon instead of comma": false]', 2, True),
('Colon instead of comma', 25))
self.assertEqual(
scanstring('["Bad value", truth]', 2, True),
('Bad value', 12))
def test_surrogates(self):
scanstring = self.json.decoder.scanstring
def assertScan(given, expect):
self.assertEqual(scanstring(given, 1, True),
(expect, len(given)))
assertScan('"z\\ud834\\u0079x"', 'z\ud834yx')
assertScan('"z\\ud834\\udd20x"', 'z\U0001d120x')
assertScan('"z\\ud834\\ud834\\udd20x"', 'z\ud834\U0001d120x')
assertScan('"z\\ud834x"', 'z\ud834x')
assertScan('"z\\ud834\udd20x12345"', 'z\ud834\udd20x12345')
assertScan('"z\\udd20x"', 'z\udd20x')
assertScan('"z\ud834\udd20x"', 'z\ud834\udd20x')
assertScan('"z\ud834\\udd20x"', 'z\ud834\udd20x')
assertScan('"z\ud834x"', 'z\ud834x')
def test_bad_escapes(self):
scanstring = self.json.decoder.scanstring
bad_escapes = [
'"\\"',
'"\\x"',
'"\\u"',
'"\\u0"',
'"\\u01"',
'"\\u012"',
'"\\uz012"',
'"\\u0z12"',
'"\\u01z2"',
'"\\u012z"',
'"\\u0x12"',
'"\\u0X12"',
'"\\u{0}"'.format("\uff10" * 4),
'"\\u 123"',
'"\\u-123"',
'"\\u+123"',
'"\\u1_23"',
'"\\ud834\\"',
'"\\ud834\\u"',
'"\\ud834\\ud"',
'"\\ud834\\udd"',
'"\\ud834\\udd2"',
'"\\ud834\\uzdd2"',
'"\\ud834\\udzd2"',
'"\\ud834\\uddz2"',
'"\\ud834\\udd2z"',
'"\\ud834\\u0x20"',
'"\\ud834\\u0X20"',
'"\\ud834\\u{0}"'.format("\uff10" * 4),
'"\\ud834\\u 123"',
'"\\ud834\\u-123"',
'"\\ud834\\u+123"',
'"\\ud834\\u1_23"',
]
for s in bad_escapes:
with self.assertRaises(self.JSONDecodeError, msg=s):
scanstring(s, 1, True)
def test_overflow(self):
with self.assertRaises(OverflowError):
self.json.decoder.scanstring("xxx", sys.maxsize+1)
class TestPyScanstring(TestScanstring, PyTest): pass
class TestCScanstring(TestScanstring, CTest): pass