From ef282220bd6e759c125c82351355d27627a0c08f Mon Sep 17 00:00:00 2001
From: Victor Stinner <vstinner@python.org>
Date: Thu, 15 Sep 2022 17:35:24 +0200
Subject: [PATCH] 00387: CVE-2020-10735: Prevent DoS by very large int()
gh-95778: CVE-2020-10735: Prevent DoS by very large int() (GH-96504)
Converting between `int` and `str` in bases other than 2
(binary), 4, 8 (octal), 16 (hexadecimal), or 32 such as base 10 (decimal) now
raises a `ValueError` if the number of digits in string form is above a
limit to avoid potential denial of service attacks due to the algorithmic
complexity. This is a mitigation for CVE-2020-10735
(https://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2020-10735).
This new limit can be configured or disabled by environment variable, command
line flag, or :mod:`sys` APIs. See the `Integer String Conversion Length
Limitation` documentation. The default limit is 4300
digits in string form.
Patch by Gregory P. Smith [Google] and Christian Heimes [Red Hat] with feedback
from Victor Stinner, Thomas Wouters, Steve Dower, Ned Deily, and Mark Dickinson.
Notes on the backport to Python 3.6 in RHEL:
* Use "Python 3.6.8-48" version in the documentation, whereas this
version will never be released
* Only add _Py_global_config_int_max_str_digits global variable:
Python 3.6 doesn't have PyConfig API (PEP 597) nor _PyRuntime.
* sys.flags.int_max_str_digits cannot be -1 on Python 3.6: it is
set to the default limit. Adapt test_int_max_str_digits() for that.
* Declare _PY_LONG_DEFAULT_MAX_STR_DIGITS and
_PY_LONG_MAX_STR_DIGITS_THRESHOLD macros in longobject.h but only
if the Py_BUILD_CORE macro is defined.
* Declare _Py_global_config_int_max_str_digits in pydebug.h.
(cherry picked from commit 511ca9452033ef95bc7d7fc404b8161068226002)
gh-95778: Mention sys.set_int_max_str_digits() in error message (#96874)
When ValueError is raised if an integer is larger than the limit,
mention sys.set_int_max_str_digits() in the error message.
(cherry picked from commit e841ffc915e82e5ea6e3b473205417d63494808d)
gh-96848: Fix -X int_max_str_digits option parsing (#96988)
Fix command line parsing: reject "-X int_max_str_digits" option with
no value (invalid) when the PYTHONINTMAXSTRDIGITS environment
variable is set to a valid limit.
(cherry picked from commit 41351662bcd21672d8ccfa62fe44d72027e6bcf8)
---
Doc/library/functions.rst | 8 ++
Doc/library/json.rst | 11 ++
Doc/library/stdtypes.rst | 159 ++++++++++++++++++++++++
Doc/library/sys.rst | 53 ++++++--
Doc/library/test.rst | 10 ++
Doc/using/cmdline.rst | 14 +++
Doc/whatsnew/3.6.rst | 15 +++
Include/longobject.h | 38 ++++++
Include/pydebug.h | 2 +
Lib/test/support/__init__.py | 10 ++
Lib/test/test_ast.py | 8 ++
Lib/test/test_cmd_line.py | 35 ++++++
Lib/test/test_compile.py | 13 ++
Lib/test/test_decimal.py | 18 +++
Lib/test/test_int.py | 196 ++++++++++++++++++++++++++++++
Lib/test/test_json/test_decode.py | 8 ++
Lib/test/test_sys.py | 11 +-
Lib/test/test_xmlrpc.py | 10 ++
Modules/main.c | 7 ++
Objects/longobject.c | 168 ++++++++++++++++++++++++-
Python/ast.c | 26 +++-
Python/pylifecycle.c | 2 +
Python/sysmodule.c | 46 ++++++-
23 files changed, 853 insertions(+), 15 deletions(-)
diff --git a/Doc/library/functions.rst b/Doc/library/functions.rst
index bc528dd..b0806b2 100644
--- a/Doc/library/functions.rst
+++ b/Doc/library/functions.rst
@@ -748,6 +748,14 @@ are always available. They are listed here in alphabetical order.
.. versionchanged:: 3.6
Grouping digits with underscores as in code literals is allowed.
+ .. versionchanged:: 3.6.8-48
+ :class:`int` string inputs and string representations can be limited to
+ help avoid denial of service attacks. A :exc:`ValueError` is raised when
+ the limit is exceeded while converting a string *x* to an :class:`int` or
+ when converting an :class:`int` into a string would exceed the limit.
+ See the :ref:`integer string conversion length limitation
+ <int_max_str_digits>` documentation.
+
.. function:: isinstance(object, classinfo)
diff --git a/Doc/library/json.rst b/Doc/library/json.rst
index 98ca86e..330e53f 100644
--- a/Doc/library/json.rst
+++ b/Doc/library/json.rst
@@ -18,6 +18,11 @@ is a lightweight data interchange format inspired by
`JavaScript <https://en.wikipedia.org/wiki/JavaScript>`_ object literal syntax
(although it is not a strict subset of JavaScript [#rfc-errata]_ ).
+.. warning::
+ Be cautious when parsing JSON data from untrusted sources. A malicious
+ JSON string may cause the decoder to consume considerable CPU and memory
+ resources. Limiting the size of data to be parsed is recommended.
+
:mod:`json` exposes an API familiar to users of the standard library
:mod:`marshal` and :mod:`pickle` modules.
@@ -245,6 +250,12 @@ Basic Usage
be used to use another datatype or parser for JSON integers
(e.g. :class:`float`).
+ .. versionchanged:: 3.6.8-48
+ The default *parse_int* of :func:`int` now limits the maximum length of
+ the integer string via the interpreter's :ref:`integer string
+ conversion length limitation <int_max_str_digits>` to help avoid denial
+ of service attacks.
+
*parse_constant*, if specified, will be called with one of the following
strings: ``'-Infinity'``, ``'Infinity'``, ``'NaN'``.
This can be used to raise an exception if invalid JSON numbers
diff --git a/Doc/library/stdtypes.rst b/Doc/library/stdtypes.rst
index 00e1f4c..1dc3253 100644
--- a/Doc/library/stdtypes.rst
+++ b/Doc/library/stdtypes.rst
@@ -4671,6 +4671,165 @@ types, where they are relevant. Some of these are not reported by the
[<class 'bool'>]
+.. _int_max_str_digits:
+
+Integer string conversion length limitation
+===========================================
+
+CPython has a global limit for converting between :class:`int` and :class:`str`
+to mitigate denial of service attacks. This limit *only* applies to decimal or
+other non-power-of-two number bases. Hexadecimal, octal, and binary conversions
+are unlimited. The limit can be configured.
+
+The :class:`int` type in CPython is an abitrary length number stored in binary
+form (commonly known as a "bignum"). There exists no algorithm that can convert
+a string to a binary integer or a binary integer to a string in linear time,
+*unless* the base is a power of 2. Even the best known algorithms for base 10
+have sub-quadratic complexity. Converting a large value such as ``int('1' *
+500_000)`` can take over a second on a fast CPU.
+
+Limiting conversion size offers a practical way to avoid `CVE-2020-10735
+<https://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2020-10735>`_.
+
+The limit is applied to the number of digit characters in the input or output
+string when a non-linear conversion algorithm would be involved. Underscores
+and the sign are not counted towards the limit.
+
+When an operation would exceed the limit, a :exc:`ValueError` is raised:
+
+.. doctest::
+
+ >>> import sys
+ >>> sys.set_int_max_str_digits(4300) # Illustrative, this is the default.
+ >>> _ = int('2' * 5432)
+ Traceback (most recent call last):
+ ...
+ ValueError: Exceeds the limit (4300) for integer string conversion: value has 5432 digits; use sys.set_int_max_str_digits() to increase the limit.
+ >>> i = int('2' * 4300)
+ >>> len(str(i))
+ 4300
+ >>> i_squared = i*i
+ >>> len(str(i_squared))
+ Traceback (most recent call last):
+ ...
+ ValueError: Exceeds the limit (4300) for integer string conversion: value has 8599 digits; use sys.set_int_max_str_digits() to increase the limit.
+ >>> len(hex(i_squared))
+ 7144
+ >>> assert int(hex(i_squared), base=16) == i*i # Hexadecimal is unlimited.
+
+The default limit is 4300 digits as provided in
+:data:`sys.int_info.default_max_str_digits <sys.int_info>`.
+The lowest limit that can be configured is 640 digits as provided in
+:data:`sys.int_info.str_digits_check_threshold <sys.int_info>`.
+
+Verification:
+
+.. doctest::
+
+ >>> import sys
+ >>> assert sys.int_info.default_max_str_digits == 4300, sys.int_info
+ >>> assert sys.int_info.str_digits_check_threshold == 640, sys.int_info
+ >>> msg = int('578966293710682886880994035146873798396722250538762761564'
+ ... '9252925514383915483333812743580549779436104706260696366600'
+ ... '571186405732').to_bytes(53, 'big')
+ ...
+
+.. versionadded:: 3.6.8-48
+
+Affected APIs
+-------------
+
+The limitation only applies to potentially slow conversions between :class:`int`
+and :class:`str` or :class:`bytes`:
+
+* ``int(string)`` with default base 10.
+* ``int(string, base)`` for all bases that are not a power of 2.
+* ``str(integer)``.
+* ``repr(integer)``
+* any other string conversion to base 10, for example ``f"{integer}"``,
+ ``"{}".format(integer)``, or ``b"%d" % integer``.
+
+The limitations do not apply to functions with a linear algorithm:
+
+* ``int(string, base)`` with base 2, 4, 8, 16, or 32.
+* :func:`int.from_bytes` and :func:`int.to_bytes`.
+* :func:`hex`, :func:`oct`, :func:`bin`.
+* :ref:`formatspec` for hex, octal, and binary numbers.
+* :class:`str` to :class:`float`.
+* :class:`str` to :class:`decimal.Decimal`.
+
+Configuring the limit
+---------------------
+
+Before Python starts up you can use an environment variable or an interpreter
+command line flag to configure the limit:
+
+* :envvar:`PYTHONINTMAXSTRDIGITS`, e.g.
+ ``PYTHONINTMAXSTRDIGITS=640 python3`` to set the limit to 640 or
+ ``PYTHONINTMAXSTRDIGITS=0 python3`` to disable the limitation.
+* :option:`-X int_max_str_digits <-X>`, e.g.
+ ``python3 -X int_max_str_digits=640``
+* :data:`sys.flags.int_max_str_digits` contains the value of
+ :envvar:`PYTHONINTMAXSTRDIGITS` or :option:`-X int_max_str_digits <-X>`.
+ If both the env var and the ``-X`` option are set, the ``-X`` option takes
+ precedence. A value of *-1* indicates that both were unset, thus a value of
+ :data:`sys.int_info.default_max_str_digits` was used during initilization.
+
+From code, you can inspect the current limit and set a new one using these
+:mod:`sys` APIs:
+
+* :func:`sys.get_int_max_str_digits` and :func:`sys.set_int_max_str_digits` are
+ a getter and setter for the interpreter-wide limit. Subinterpreters have
+ their own limit.
+
+Information about the default and minimum can be found in :attr:`sys.int_info`:
+
+* :data:`sys.int_info.default_max_str_digits <sys.int_info>` is the compiled-in
+ default limit.
+* :data:`sys.int_info.str_digits_check_threshold <sys.int_info>` is the lowest
+ accepted value for the limit (other than 0 which disables it).
+
+.. versionadded:: 3.6.8-48
+
+.. caution::
+
+ Setting a low limit *can* lead to problems. While rare, code exists that
+ contains integer constants in decimal in their source that exceed the
+ minimum threshold. A consequence of setting the limit is that Python source
+ code containing decimal integer literals longer than the limit will
+ encounter an error during parsing, usually at startup time or import time or
+ even at installation time - anytime an up to date ``.pyc`` does not already
+ exist for the code. A workaround for source that contains such large
+ constants is to convert them to ``0x`` hexadecimal form as it has no limit.
+
+ Test your application thoroughly if you use a low limit. Ensure your tests
+ run with the limit set early via the environment or flag so that it applies
+ during startup and even during any installation step that may invoke Python
+ to precompile ``.py`` sources to ``.pyc`` files.
+
+Recommended configuration
+-------------------------
+
+The default :data:`sys.int_info.default_max_str_digits` is expected to be
+reasonable for most applications. If your application requires a different
+limit, set it from your main entry point using Python version agnostic code as
+these APIs were added in security patch releases in versions before 3.11.
+
+Example::
+
+ >>> import sys
+ >>> if hasattr(sys, "set_int_max_str_digits"):
+ ... upper_bound = 68000
+ ... lower_bound = 4004
+ ... current_limit = sys.get_int_max_str_digits()
+ ... if current_limit == 0 or current_limit > upper_bound:
+ ... sys.set_int_max_str_digits(upper_bound)
+ ... elif current_limit < lower_bound:
+ ... sys.set_int_max_str_digits(lower_bound)
+
+If you need to disable it entirely, set it to ``0``.
+
+
.. rubric:: Footnotes
.. [1] Additional information on these special methods may be found in the Python
diff --git a/Doc/library/sys.rst b/Doc/library/sys.rst
index 9198466..6144f8f 100644
--- a/Doc/library/sys.rst
+++ b/Doc/library/sys.rst
@@ -296,6 +296,7 @@ always available.
:const:`bytes_warning` :option:`-b`
:const:`quiet` :option:`-q`
:const:`hash_randomization` :option:`-R`
+ :const:`int_max_str_digits` :option:`-X int_max_str_digits <-X>` (:ref:`integer string conversion length limitation <int_max_str_digits>`)
============================= =============================
.. versionchanged:: 3.2
@@ -310,6 +311,9 @@ always available.
.. versionchanged:: 3.4
Added ``isolated`` attribute for :option:`-I` ``isolated`` flag.
+ .. versionchanged:: 3.6.8-48
+ Added the ``int_max_str_digits`` attribute.
+
.. data:: float_info
A :term:`struct sequence` holding information about the float type. It
@@ -468,6 +472,15 @@ always available.
.. versionadded:: 3.6
+
+.. function:: get_int_max_str_digits()
+
+ Returns the current value for the :ref:`integer string conversion length
+ limitation <int_max_str_digits>`. See also :func:`set_int_max_str_digits`.
+
+ .. versionadded:: 3.6.8-48
+
+
.. function:: getrefcount(object)
Return the reference count of the *object*. The count returned is generally one
@@ -730,19 +743,31 @@ always available.
.. tabularcolumns:: |l|L|
- +-------------------------+----------------------------------------------+
- | Attribute | Explanation |
- +=========================+==============================================+
- | :const:`bits_per_digit` | number of bits held in each digit. Python |
- | | integers are stored internally in base |
- | | ``2**int_info.bits_per_digit`` |
- +-------------------------+----------------------------------------------+
- | :const:`sizeof_digit` | size in bytes of the C type used to |
- | | represent a digit |
- +-------------------------+----------------------------------------------+
+ +----------------------------------------+-----------------------------------------------+
+ | Attribute | Explanation |
+ +========================================+===============================================+
+ | :const:`bits_per_digit` | number of bits held in each digit. Python |
+ | | integers are stored internally in base |
+ | | ``2**int_info.bits_per_digit`` |
+ +----------------------------------------+-----------------------------------------------+
+ | :const:`sizeof_digit` | size in bytes of the C type used to |
+ | | represent a digit |
+ +----------------------------------------+-----------------------------------------------+
+ | :const:`default_max_str_digits` | default value for |
+ | | :func:`sys.get_int_max_str_digits` when it |
+ | | is not otherwise explicitly configured. |
+ +----------------------------------------+-----------------------------------------------+
+ | :const:`str_digits_check_threshold` | minimum non-zero value for |
+ | | :func:`sys.set_int_max_str_digits`, |
+ | | :envvar:`PYTHONINTMAXSTRDIGITS`, or |
+ | | :option:`-X int_max_str_digits <-X>`. |
+ +----------------------------------------+-----------------------------------------------+
.. versionadded:: 3.1
+ .. versionchanged:: 3.6.8-48
+ Added ``default_max_str_digits`` and ``str_digits_check_threshold``.
+
.. data:: __interactivehook__
@@ -1001,6 +1026,14 @@ always available.
Availability: Unix.
+.. function:: set_int_max_str_digits(n)
+
+ Set the :ref:`integer string conversion length limitation
+ <int_max_str_digits>` used by this interpreter. See also
+ :func:`get_int_max_str_digits`.
+
+ .. versionadded:: 3.6.8-48
+
.. function:: setprofile(profilefunc)
.. index::
diff --git a/Doc/library/test.rst b/Doc/library/test.rst
index 04d6cd8..5153162 100644
--- a/Doc/library/test.rst
+++ b/Doc/library/test.rst
@@ -625,6 +625,16 @@ The :mod:`test.support` module defines the following functions:
.. versionadded:: 3.6
+.. function:: adjust_int_max_str_digits(max_digits)
+
+ This function returns a context manager that will change the global
+ :func:`sys.set_int_max_str_digits` setting for the duration of the
+ context to allow execution of test code that needs a different limit
+ on the number of digits when converting between an integer and string.
+
+ .. versionadded:: 3.6.8-48
+
+
The :mod:`test.support` module defines the following classes:
.. class:: TransientResource(exc, **kwargs)
diff --git a/Doc/using/cmdline.rst b/Doc/using/cmdline.rst
index 65aa3ad..f5f76c4 100644
--- a/Doc/using/cmdline.rst
+++ b/Doc/using/cmdline.rst
@@ -422,6 +422,9 @@ Miscellaneous options
* ``-X showalloccount`` to output the total count of allocated objects for
each type when the program finishes. This only works when Python was built with
``COUNT_ALLOCS`` defined.
+ * ``-X int_max_str_digits`` configures the :ref:`integer string conversion
+ length limitation <int_max_str_digits>`. See also
+ :envvar:`PYTHONINTMAXSTRDIGITS`.
It also allows passing arbitrary values and retrieving them through the
:data:`sys._xoptions` dictionary.
@@ -438,6 +441,9 @@ Miscellaneous options
.. versionadded:: 3.6
The ``-X showalloccount`` option.
+ .. versionadded:: 3.6.8-48
+ The ``-X int_max_str_digits`` option.
+
Options you shouldn't use
~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -571,6 +577,14 @@ conflict.
.. versionadded:: 3.2.3
+.. envvar:: PYTHONINTMAXSTRDIGITS
+
+ If this variable is set to an integer, it is used to configure the
+ interpreter's global :ref:`integer string conversion length limitation
+ <int_max_str_digits>`.
+
+ .. versionadded:: 3.6.8-48
+
.. envvar:: PYTHONIOENCODING
If this is set before running the interpreter, it overrides the encoding used
diff --git a/Doc/whatsnew/3.6.rst b/Doc/whatsnew/3.6.rst
index 0095844..d669c5c 100644
--- a/Doc/whatsnew/3.6.rst
+++ b/Doc/whatsnew/3.6.rst
@@ -2438,3 +2438,18 @@ In 3.6.7 the :mod:`tokenize` module now implicitly emits a ``NEWLINE`` token
when provided with input that does not have a trailing new line. This behavior
now matches what the C tokenizer does internally.
(Contributed by Ammar Askar in :issue:`33899`.)
+
+
+Notable security feature in 3.6.8-48
+=====================================
+
+Converting between :class:`int` and :class:`str` in bases other than 2
+(binary), 4, 8 (octal), 16 (hexadecimal), or 32 such as base 10 (decimal)
+now raises a :exc:`ValueError` if the number of digits in string form is
+above a limit to avoid potential denial of service attacks due to the
+algorithmic complexity. This is a mitigation for `CVE-2020-10735
+<https://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2020-10735>`_.
+This limit can be configured or disabled by environment variable, command
+line flag, or :mod:`sys` APIs. See the :ref:`integer string conversion
+length limitation <int_max_str_digits>` documentation. The default limit
+is 4300 digits in string form.
diff --git a/Include/longobject.h b/Include/longobject.h
index efd409c..d8a080a 100644
--- a/Include/longobject.h
+++ b/Include/longobject.h
@@ -209,6 +209,44 @@ PyAPI_FUNC(long) PyOS_strtol(const char *, char **, int);
PyAPI_FUNC(PyObject *) _PyLong_GCD(PyObject *, PyObject *);
#endif /* !Py_LIMITED_API */
+#ifdef Py_BUILD_CORE
+/*
+ * Default int base conversion size limitation: Denial of Service prevention.
+ *
+ * Chosen such that this isn't wildly slow on modern hardware and so that
+ * everyone's existing deployed numpy test suite passes before
+ * https://github.com/numpy/numpy/issues/22098 is widely available.
+ *
+ * $ python -m timeit -s 's = "1"*4300' 'int(s)'
+ * 2000 loops, best of 5: 125 usec per loop
+ * $ python -m timeit -s 's = "1"*4300; v = int(s)' 'str(v)'
+ * 1000 loops, best of 5: 311 usec per loop
+ * (zen2 cloud VM)
+ *
+ * 4300 decimal digits fits a ~14284 bit number.
+ */
+#define _PY_LONG_DEFAULT_MAX_STR_DIGITS 4300
+/*
+ * Threshold for max digits check. For performance reasons int() and
+ * int.__str__() don't checks values that are smaller than this
+ * threshold. Acts as a guaranteed minimum size limit for bignums that
+ * applications can expect from CPython.
+ *
+ * % python -m timeit -s 's = "1"*640; v = int(s)' 'str(int(s))'
+ * 20000 loops, best of 5: 12 usec per loop
+ *
+ * "640 digits should be enough for anyone." - gps
+ * fits a ~2126 bit decimal number.
+ */
+#define _PY_LONG_MAX_STR_DIGITS_THRESHOLD 640
+
+#if ((_PY_LONG_DEFAULT_MAX_STR_DIGITS != 0) && \
+ (_PY_LONG_DEFAULT_MAX_STR_DIGITS < _PY_LONG_MAX_STR_DIGITS_THRESHOLD))
+# error "_PY_LONG_DEFAULT_MAX_STR_DIGITS smaller than threshold."
+#endif
+
+#endif /* Py_BUILD_CORE */
+
#ifdef __cplusplus
}
#endif
diff --git a/Include/pydebug.h b/Include/pydebug.h
index 6e23a89..657c552 100644
--- a/Include/pydebug.h
+++ b/Include/pydebug.h
@@ -28,6 +28,8 @@ PyAPI_DATA(int) Py_IsolatedFlag;
PyAPI_DATA(int) Py_LegacyWindowsStdioFlag;
#endif
+PyAPI_DATA(int) _Py_global_config_int_max_str_digits;
+
/* this is a wrapper around getenv() that pays attention to
Py_IgnoreEnvironmentFlag. It should be used for getting variables like
PYTHONPATH and PYTHONHOME from the environment */
diff --git a/Lib/test/support/__init__.py b/Lib/test/support/__init__.py
index e33096e..99920ac 100644
--- a/Lib/test/support/__init__.py
+++ b/Lib/test/support/__init__.py
@@ -2912,3 +2912,13 @@ class FakePath:
raise self.path
else:
return self.path
+
+@contextlib.contextmanager
+def adjust_int_max_str_digits(max_digits):
+ """Temporarily change the integer string conversion length limit."""
+ current = sys.get_int_max_str_digits()
+ try:
+ sys.set_int_max_str_digits(max_digits)
+ yield
+ finally:
+ sys.set_int_max_str_digits(current)
diff --git a/Lib/test/test_ast.py b/Lib/test/test_ast.py
index e68d0de..7f2d793 100644
--- a/Lib/test/test_ast.py
+++ b/Lib/test/test_ast.py
@@ -571,6 +571,14 @@ class ASTHelpers_Test(unittest.TestCase):
exec(code, ns)
self.assertIn('sleep', ns)
+ def test_literal_eval_str_int_limit(self):
+ with support.adjust_int_max_str_digits(4000):
+ ast.literal_eval('3'*4000) # no error
+ with self.assertRaises(SyntaxError) as err_ctx:
+ ast.literal_eval('3'*4001)
+ self.assertIn('Exceeds the limit ', str(err_ctx.exception))
+ self.assertIn(' Consider hexadecimal ', str(err_ctx.exception))
+
class ASTValidatorTests(unittest.TestCase):
diff --git a/Lib/test/test_cmd_line.py b/Lib/test/test_cmd_line.py
index 5922ed9..fe456ee 100644
--- a/Lib/test/test_cmd_line.py
+++ b/Lib/test/test_cmd_line.py
@@ -502,6 +502,41 @@ class CmdLineTest(unittest.TestCase):
self.assertEqual(proc.returncode, 0, proc)
self.assertEqual(proc.stdout.strip(), b'0')
+ def test_int_max_str_digits(self):
+ code = "import sys; print(sys.flags.int_max_str_digits, sys.get_int_max_str_digits())"
+
+ assert_python_failure('-X', 'int_max_str_digits', '-c', code)
+ assert_python_failure('-X', 'int_max_str_digits=foo', '-c', code)
+ assert_python_failure('-X', 'int_max_str_digits=100', '-c', code)
+ assert_python_failure('-X', 'int_max_str_digits', '-c', code,
+ PYTHONINTMAXSTRDIGITS='4000')
+
+ assert_python_failure('-c', code, PYTHONINTMAXSTRDIGITS='foo')
+ assert_python_failure('-c', code, PYTHONINTMAXSTRDIGITS='100')
+
+ def res2int(res):
+ out = res.out.strip().decode("utf-8")
+ return tuple(int(i) for i in out.split())
+
+ res = assert_python_ok('-c', code)
+ self.assertEqual(res2int(res), (sys.get_int_max_str_digits(), sys.get_int_max_str_digits()))
+ res = assert_python_ok('-X', 'int_max_str_digits=0', '-c', code)
+ self.assertEqual(res2int(res), (0, 0))
+ res = assert_python_ok('-X', 'int_max_str_digits=4000', '-c', code)
+ self.assertEqual(res2int(res), (4000, 4000))
+ res = assert_python_ok('-X', 'int_max_str_digits=100000', '-c', code)
+ self.assertEqual(res2int(res), (100000, 100000))
+
+ res = assert_python_ok('-c', code, PYTHONINTMAXSTRDIGITS='0')
+ self.assertEqual(res2int(res), (0, 0))
+ res = assert_python_ok('-c', code, PYTHONINTMAXSTRDIGITS='4000')
+ self.assertEqual(res2int(res), (4000, 4000))
+ res = assert_python_ok(
+ '-X', 'int_max_str_digits=6000', '-c', code,
+ PYTHONINTMAXSTRDIGITS='4000'
+ )
+ self.assertEqual(res2int(res), (6000, 6000))
+
def test_main():
test.support.run_unittest(CmdLineTest)
diff --git a/Lib/test/test_compile.py b/Lib/test/test_compile.py
index 13cc882..00e6468 100644
--- a/Lib/test/test_compile.py
+++ b/Lib/test/test_compile.py
@@ -189,6 +189,19 @@ if 1:
self.assertEqual(eval("0o777"), 511)
self.assertEqual(eval("-0o0000010"), -8)
+ def test_int_literals_too_long(self):
+ n = 3000
+ source = f"a = 1\nb = 2\nc = {'3'*n}\nd = 4"
+ with support.adjust_int_max_str_digits(n):
+ compile(source, "<long_int_pass>", "exec") # no errors.
+ with support.adjust_int_max_str_digits(n-1):
+ with self.assertRaises(SyntaxError) as err_ctx:
+ compile(source, "<long_int_fail>", "exec")
+ exc = err_ctx.exception
+ self.assertEqual(exc.lineno, 3)
+ self.assertIn('Exceeds the limit ', str(exc))
+ self.assertIn(' Consider hexadecimal ', str(exc))
+
def test_unary_minus(self):
# Verify treatment of unary minus on negative numbers SF bug #660455
if sys.maxsize == 2147483647:
diff --git a/Lib/test/test_decimal.py b/Lib/test/test_decimal.py
index 8808a67..4459b82 100644
--- a/Lib/test/test_decimal.py
+++ b/Lib/test/test_decimal.py
@@ -2442,6 +2442,15 @@ class CUsabilityTest(UsabilityTest):
class PyUsabilityTest(UsabilityTest):
decimal = P
+ def setUp(self):
+ super().setUp()
+ self._previous_int_limit = sys.get_int_max_str_digits()
+ sys.set_int_max_str_digits(7000)
+
+ def tearDown(self):
+ sys.set_int_max_str_digits(self._previous_int_limit)
+ super().tearDown()
+
class PythonAPItests(unittest.TestCase):
def test_abc(self):
@@ -4499,6 +4508,15 @@ class CCoverage(Coverage):
class PyCoverage(Coverage):
decimal = P
+ def setUp(self):
+ super().setUp()
+ self._previous_int_limit = sys.get_int_max_str_digits()
+ sys.set_int_max_str_digits(7000)
+
+ def tearDown(self):
+ sys.set_int_max_str_digits(self._previous_int_limit)
+ super().tearDown()
+
class PyFunctionality(unittest.TestCase):
"""Extra functionality in decimal.py"""
diff --git a/Lib/test/test_int.py b/Lib/test/test_int.py
index a36076e..6cd9a5e 100644
--- a/Lib/test/test_int.py
+++ b/Lib/test/test_int.py
@@ -1,4 +1,5 @@
import sys
+import time
import unittest
from test import support
@@ -514,5 +515,200 @@ class IntTestCases(unittest.TestCase):
self.assertEqual(int('1_2_3_4_5_6_7', 32), 1144132807)
+class IntStrDigitLimitsTests(unittest.TestCase):
+
+ int_class = int # Override this in subclasses to reuse the suite.
+
+ def setUp(self):
+ super().setUp()
+ self._previous_limit = sys.get_int_max_str_digits()
+ sys.set_int_max_str_digits(2048)
+
+ def tearDown(self):
+ sys.set_int_max_str_digits(self._previous_limit)
+ super().tearDown()
+
+ def test_disabled_limit(self):
+ self.assertGreater(sys.get_int_max_str_digits(), 0)
+ self.assertLess(sys.get_int_max_str_digits(), 20_000)
+ with support.adjust_int_max_str_digits(0):
+ self.assertEqual(sys.get_int_max_str_digits(), 0)
+ i = self.int_class('1' * 20_000)
+ str(i)
+ self.assertGreater(sys.get_int_max_str_digits(), 0)
+
+ def test_max_str_digits_edge_cases(self):
+ """Ignore the +/- sign and space padding."""
+ int_class = self.int_class
+ maxdigits = sys.get_int_max_str_digits()
+
+ int_class('1' * maxdigits)
+ int_class(' ' + '1' * maxdigits)
+ int_class('1' * maxdigits + ' ')
+ int_class('+' + '1' * maxdigits)
+ int_class('-' + '1' * maxdigits)
+ self.assertEqual(len(str(10 ** (maxdigits - 1))), maxdigits)
+
+ def check(self, i, base=None):
+ with self.assertRaises(ValueError):
+ if base is None:
+ self.int_class(i)
+ else:
+ self.int_class(i, base)
+
+ def test_max_str_digits(self):
+ maxdigits = sys.get_int_max_str_digits()
+
+ self.check('1' * (maxdigits + 1))
+ self.check(' ' + '1' * (maxdigits + 1))
+ self.check('1' * (maxdigits + 1) + ' ')
+ self.check('+' + '1' * (maxdigits + 1))
+ self.check('-' + '1' * (maxdigits + 1))
+ self.check('1' * (maxdigits + 1))
+
+ i = 10 ** maxdigits
+ with self.assertRaises(ValueError):
+ str(i)
+
+ def test_denial_of_service_prevented_int_to_str(self):
+ """Regression test: ensure we fail before performing O(N**2) work."""
+ maxdigits = sys.get_int_max_str_digits()
+ assert maxdigits < 50_000, maxdigits # A test prerequisite.
+ get_time = time.process_time
+ if get_time() <= 0: # some platforms like WASM lack process_time()
+ get_time = time.monotonic
+
+ huge_int = int(f'0x{"c"*65_000}', base=16) # 78268 decimal digits.
+ digits = 78_268
+ with support.adjust_int_max_str_digits(digits):
+ start = get_time()
+ huge_decimal = str(huge_int)
+ seconds_to_convert = get_time() - start
+ self.assertEqual(len(huge_decimal), digits)
+ # Ensuring that we chose a slow enough conversion to measure.
+ # It takes 0.1 seconds on a Zen based cloud VM in an opt build.
+ if seconds_to_convert < 0.005:
+ raise unittest.SkipTest('"slow" conversion took only '
+ f'{seconds_to_convert} seconds.')
+
+ # We test with the limit almost at the size needed to check performance.
+ # The performant limit check is slightly fuzzy, give it a some room.
+ with support.adjust_int_max_str_digits(int(.995 * digits)):
+ with self.assertRaises(ValueError) as err:
+ start = get_time()
+ str(huge_int)
+ seconds_to_fail_huge = get_time() - start
+ self.assertIn('conversion', str(err.exception))
+ self.assertLess(seconds_to_fail_huge, seconds_to_convert/8)
+
+ # Now we test that a conversion that would take 30x as long also fails
+ # in a similarly fast fashion.
+ extra_huge_int = int(f'0x{"c"*500_000}', base=16) # 602060 digits.
+ with self.assertRaises(ValueError) as err:
+ start = get_time()
+ # If not limited, 8 seconds said Zen based cloud VM.
+ str(extra_huge_int)
+ seconds_to_fail_extra_huge = get_time() - start
+ self.assertIn('conversion', str(err.exception))
+ self.assertLess(seconds_to_fail_extra_huge, seconds_to_convert/8)
+
+ def test_denial_of_service_prevented_str_to_int(self):
+ """Regression test: ensure we fail before performing O(N**2) work."""
+ maxdigits = sys.get_int_max_str_digits()
+ assert maxdigits < 100_000, maxdigits # A test prerequisite.
+ get_time = time.process_time
+ if get_time() <= 0: # some platforms like WASM lack process_time()
+ get_time = time.monotonic
+
+ digits = 133700
+ huge = '8'*digits
+ with support.adjust_int_max_str_digits(digits):
+ start = get_time()
+ int(huge)
+ seconds_to_convert = get_time() - start
+ # Ensuring that we chose a slow enough conversion to measure.
+ # It takes 0.1 seconds on a Zen based cloud VM in an opt build.
+ if seconds_to_convert < 0.005:
+ raise unittest.SkipTest('"slow" conversion took only '
+ f'{seconds_to_convert} seconds.')
+
+ with support.adjust_int_max_str_digits(digits - 1):
+ with self.assertRaises(ValueError) as err:
+ start = get_time()
+ int(huge)
+ seconds_to_fail_huge = get_time() - start
+ self.assertIn('conversion', str(err.exception))
+ self.assertLess(seconds_to_fail_huge, seconds_to_convert/8)
+
+ # Now we test that a conversion that would take 30x as long also fails
+ # in a similarly fast fashion.
+ extra_huge = '7'*1_200_000
+ with self.assertRaises(ValueError) as err:
+ start = get_time()
+ # If not limited, 8 seconds in the Zen based cloud VM.
+ int(extra_huge)
+ seconds_to_fail_extra_huge = get_time() - start
+ self.assertIn('conversion', str(err.exception))
+ self.assertLess(seconds_to_fail_extra_huge, seconds_to_convert/8)
+
+ def test_power_of_two_bases_unlimited(self):
+ """The limit does not apply to power of 2 bases."""
+ maxdigits = sys.get_int_max_str_digits()
+
+ for base in (2, 4, 8, 16, 32):
+ with self.subTest(base=base):
+ self.int_class('1' * (maxdigits + 1), base)
+ assert maxdigits < 100_000
+ self.int_class('1' * 100_000, base)
+
+ def test_underscores_ignored(self):
+ maxdigits = sys.get_int_max_str_digits()
+
+ triples = maxdigits // 3
+ s = '111' * triples
+ s_ = '1_11' * triples
+ self.int_class(s) # succeeds
+ self.int_class(s_) # succeeds
+ self.check(f'{s}111')
+ self.check(f'{s_}_111')
+
+ def test_sign_not_counted(self):
+ int_class = self.int_class
+ max_digits = sys.get_int_max_str_digits()
+ s = '5' * max_digits
+ i = int_class(s)
+ pos_i = int_class(f'+{s}')
+ assert i == pos_i
+ neg_i = int_class(f'-{s}')
+ assert -pos_i == neg_i
+ str(pos_i)
+ str(neg_i)
+
+ def _other_base_helper(self, base):
+ int_class = self.int_class
+ max_digits = sys.get_int_max_str_digits()
+ s = '2' * max_digits
+ i = int_class(s, base)
+ if base > 10:
+ with self.assertRaises(ValueError):
+ str(i)
+ elif base < 10:
+ str(i)
+ with self.assertRaises(ValueError) as err:
+ int_class(f'{s}1', base)
+
+ def test_int_from_other_bases(self):
+ base = 3
+ with self.subTest(base=base):
+ self._other_base_helper(base)
+ base = 36
+ with self.subTest(base=base):
+ self._other_base_helper(base)
+
+
+class IntSubclassStrDigitLimitsTests(IntStrDigitLimitsTests):
+ int_class = IntSubclass
+
+
if __name__ == "__main__":
unittest.main()
diff --git a/Lib/test/test_json/test_decode.py b/Lib/test/test_json/test_decode.py
index 738f109..b5fd4f2 100644
--- a/Lib/test/test_json/test_decode.py
+++ b/Lib/test/test_json/test_decode.py
@@ -2,6 +2,7 @@ import decimal
from io import StringIO, BytesIO
from collections import OrderedDict
from test.test_json import PyTest, CTest
+from test import support
class TestDecode:
@@ -95,5 +96,12 @@ class TestDecode:
d = self.json.JSONDecoder()
self.assertRaises(ValueError, d.raw_decode, 'a'*42, -50000)
+ 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
class TestCDecode(TestDecode, CTest): pass
diff --git a/Lib/test/test_sys.py b/Lib/test/test_sys.py
index b41239a..f2b9e08 100644
--- a/Lib/test/test_sys.py
+++ b/Lib/test/test_sys.py
@@ -444,11 +444,17 @@ class SysModuleTest(unittest.TestCase):
self.assertIsInstance(sys.executable, str)
self.assertEqual(len(sys.float_info), 11)
self.assertEqual(sys.float_info.radix, 2)
- self.assertEqual(len(sys.int_info), 2)
+ self.assertEqual(len(sys.int_info), 4)
self.assertTrue(sys.int_info.bits_per_digit % 5 == 0)
self.assertTrue(sys.int_info.sizeof_digit >= 1)
+ self.assertGreaterEqual(sys.int_info.default_max_str_digits, 500)
+ self.assertGreaterEqual(sys.int_info.str_digits_check_threshold, 100)
+ self.assertGreater(sys.int_info.default_max_str_digits,
+ sys.int_info.str_digits_check_threshold)
self.assertEqual(type(sys.int_info.bits_per_digit), int)
self.assertEqual(type(sys.int_info.sizeof_digit), int)
+ self.assertIsInstance(sys.int_info.default_max_str_digits, int)
+ self.assertIsInstance(sys.int_info.str_digits_check_threshold, int)
self.assertIsInstance(sys.hexversion, int)
self.assertEqual(len(sys.hash_info), 9)
@@ -552,7 +558,8 @@ class SysModuleTest(unittest.TestCase):
attrs = ("debug",
"inspect", "interactive", "optimize", "dont_write_bytecode",
"no_user_site", "no_site", "ignore_environment", "verbose",
- "bytes_warning", "quiet", "hash_randomization", "isolated")
+ "bytes_warning", "quiet", "hash_randomization", "isolated",
+ "int_max_str_digits")
for attr in attrs:
self.assertTrue(hasattr(sys.flags, attr), attr)
self.assertEqual(type(getattr(sys.flags, attr)), int, attr)
diff --git a/Lib/test/test_xmlrpc.py b/Lib/test/test_xmlrpc.py
index fc601d4..58553dd 100644
--- a/Lib/test/test_xmlrpc.py
+++ b/Lib/test/test_xmlrpc.py
@@ -286,6 +286,16 @@ class XMLRPCTestCase(unittest.TestCase):
check('<bigdecimal>9876543210.0123456789</bigdecimal>',
decimal.Decimal('9876543210.0123456789'))
+ def test_limit_int(self):
+ check = self.check_loads
+ maxdigits = 5000
+ with support.adjust_int_max_str_digits(maxdigits):
+ s = '1' * (maxdigits + 1)
+ with self.assertRaises(ValueError):
+ check(f'<int>{s}</int>', None)
+ with self.assertRaises(ValueError):
+ check(f'<biginteger>{s}</biginteger>', None)
+
def test_get_host_info(self):
# see bug #3613, this raised a TypeError
transp = xmlrpc.client.Transport()
diff --git a/Modules/main.c b/Modules/main.c
index 96d8be4..405e883 100644
--- a/Modules/main.c
+++ b/Modules/main.c
@@ -84,6 +84,9 @@ static const char usage_3[] = "\
also PYTHONWARNINGS=arg\n\
-x : skip first line of source, allowing use of non-Unix forms of #!cmd\n\
-X opt : set implementation-specific option\n\
+-X int_max_str_digits=number: limit the size of int<->str conversions.\n\
+ This helps avoid denial of service attacks when parsing untrusted data.\n\
+ The default is sys.int_info.default_max_str_digits. 0 disables.\n\
";
static const char usage_4[] = "\
file : program read from script file\n\
@@ -105,6 +108,10 @@ static const char usage_6[] =
" to seed the hashes of str, bytes and datetime objects. It can also be\n"
" set to an integer in the range [0,4294967295] to get hash values with a\n"
" predictable seed.\n"
+"PYTHONINTMAXSTRDIGITS: limits the maximum digit characters in an int value\n"
+" when converting from a string and when converting an int back to a str.\n"
+" A value of 0 disables the limit. Conversions to or from bases 2, 4, 8,\n"
+" 16, and 32 are never limited.\n"
"PYTHONMALLOC: set the Python memory allocators and/or install debug hooks\n"
" on Python memory allocators. Use PYTHONMALLOC=debug to install debug\n"
" hooks.\n"
diff --git a/Objects/longobject.c b/Objects/longobject.c
index 3864cec..ea01169 100644
--- a/Objects/longobject.c
+++ b/Objects/longobject.c
@@ -33,6 +33,9 @@ static PyLongObject small_ints[NSMALLNEGINTS + NSMALLPOSINTS];
Py_ssize_t quick_int_allocs, quick_neg_int_allocs;
#endif
+#define _MAX_STR_DIGITS_ERROR_FMT_TO_INT "Exceeds the limit (%d) for integer string conversion: value has %zd digits; use sys.set_int_max_str_digits() to increase the limit"
+#define _MAX_STR_DIGITS_ERROR_FMT_TO_STR "Exceeds the limit (%d) for integer string conversion; use sys.set_int_max_str_digits() to increase the limit"
+
static PyObject *
get_small_int(sdigit ival)
{
@@ -1593,6 +1596,22 @@ long_to_decimal_string_internal(PyObject *aa,
size_a = Py_ABS(Py_SIZE(a));
negative = Py_SIZE(a) < 0;
+ /* quick and dirty pre-check for overflowing the decimal digit limit,
+ based on the inequality 10/3 >= log2(10)
+
+ explanation in https://github.com/python/cpython/pull/96537
+ */
+ if (size_a >= 10 * _PY_LONG_MAX_STR_DIGITS_THRESHOLD
+ / (3 * PyLong_SHIFT) + 2) {
+ int max_str_digits = _Py_global_config_int_max_str_digits ;
+ if ((max_str_digits > 0) &&
+ (max_str_digits / (3 * PyLong_SHIFT) <= (size_a - 11) / 10)) {
+ PyErr_Format(PyExc_ValueError, _MAX_STR_DIGITS_ERROR_FMT_TO_STR,
+ max_str_digits);
+ return -1;
+ }
+ }
+
/* quick and dirty upper bound for the number of digits
required to express a in base _PyLong_DECIMAL_BASE:
@@ -1652,6 +1671,16 @@ long_to_decimal_string_internal(PyObject *aa,
tenpow *= 10;
strlen++;
}
+ if (strlen > _PY_LONG_MAX_STR_DIGITS_THRESHOLD) {
+ int max_str_digits = _Py_global_config_int_max_str_digits ;
+ Py_ssize_t strlen_nosign = strlen - negative;
+ if ((max_str_digits > 0) && (strlen_nosign > max_str_digits)) {
+ Py_DECREF(scratch);
+ PyErr_Format(PyExc_ValueError, _MAX_STR_DIGITS_ERROR_FMT_TO_STR,
+ max_str_digits);
+ return -1;
+ }
+ }
if (writer) {
if (_PyUnicodeWriter_Prepare(writer, strlen, '9') == -1) {
Py_DECREF(scratch);
@@ -2166,6 +2195,7 @@ PyLong_FromString(const char *str, char **pend, int base)
start = str;
if ((base & (base - 1)) == 0) {
+ /* binary bases are not limited by int_max_str_digits */
int res = long_from_binary_base(&str, base, &z);
if (res < 0) {
/* Syntax error. */
@@ -2318,6 +2348,16 @@ digit beyond the first.
goto onError;
}
+ /* Limit the size to avoid excessive computation attacks. */
+ if (digits > _PY_LONG_MAX_STR_DIGITS_THRESHOLD) {
+ int max_str_digits = _Py_global_config_int_max_str_digits ;
+ if ((max_str_digits > 0) && (digits > max_str_digits)) {
+ PyErr_Format(PyExc_ValueError, _MAX_STR_DIGITS_ERROR_FMT_TO_INT,
+ max_str_digits, digits);
+ return NULL;
+ }
+ }
+
/* Create an int object that can contain the largest possible
* integer with this base and length. Note that there's no
* need to initialize z->ob_digit -- no slot is read up before
@@ -4820,6 +4860,7 @@ long_new(PyTypeObject *type, PyObject *args, PyObject *kwds)
}
return PyLong_FromLong(0L);
}
+ /* default base and limit, forward to standard implementation */
if (obase == NULL)
return PyNumber_Long(x);
@@ -5482,6 +5523,8 @@ internal representation of integers. The attributes are read only.");
static PyStructSequence_Field int_info_fields[] = {
{"bits_per_digit", "size of a digit in bits"},
{"sizeof_digit", "size in bytes of the C type used to represent a digit"},
+ {"default_max_str_digits", "maximum string conversion digits limitation"},
+ {"str_digits_check_threshold", "minimum positive value for int_max_str_digits"},
{NULL, NULL}
};
@@ -5489,7 +5532,7 @@ static PyStructSequence_Desc int_info_desc = {
"sys.int_info", /* name */
int_info__doc__, /* doc */
int_info_fields, /* fields */
- 2 /* number of fields */
+ 4 /* number of fields */
};
PyObject *
@@ -5504,6 +5547,17 @@ PyLong_GetInfo(void)
PyLong_FromLong(PyLong_SHIFT));
PyStructSequence_SET_ITEM(int_info, field++,
PyLong_FromLong(sizeof(digit)));
+ /*
+ * The following two fields were added after investigating uses of
+ * sys.int_info in the wild: Exceedingly rarely used. The ONLY use found was
+ * numba using sys.int_info.bits_per_digit as attribute access rather than
+ * sequence unpacking. Cython and sympy also refer to sys.int_info but only
+ * as info for debugging. No concern about adding these in a backport.
+ */
+ PyStructSequence_SET_ITEM(int_info, field++,
+ PyLong_FromLong(_PY_LONG_DEFAULT_MAX_STR_DIGITS));
+ PyStructSequence_SET_ITEM(int_info, field++,
+ PyLong_FromLong(_PY_LONG_MAX_STR_DIGITS_THRESHOLD));
if (PyErr_Occurred()) {
Py_CLEAR(int_info);
return NULL;
@@ -5511,6 +5565,116 @@ PyLong_GetInfo(void)
return int_info;
}
+
+static int
+pymain_str_to_int(const char *str, int *result)
+{
+ errno = 0;
+ const char *endptr = str;
+ long value = strtol(str, (char **)&endptr, 10);
+ if (*endptr != '\0' || errno == ERANGE) {
+ return -1;
+ }
+ if (value < INT_MIN || value > INT_MAX) {
+ return -1;
+ }
+
+ *result = (int)value;
+ return 0;
+}
+
+
+static int
+long_get_max_str_digits_xoption(int *pmaxdigits)
+{
+ PyObject *xoptions = PySys_GetXOptions();
+ if (xoptions == NULL) {
+ return -1;
+ }
+
+ PyObject *key = PyUnicode_FromString("int_max_str_digits");
+ if (key == NULL) {
+ return -1;
+ }
+
+ PyObject *value = PyDict_GetItemWithError(xoptions, key); /* borrowed */
+ Py_DECREF(key);
+ if (value == NULL) {
+ if (PyErr_Occurred()) {
+ return -1;
+ }
+ return 0;
+ }
+
+ if (!PyUnicode_Check(value)) {
+ return -1;
+ }
+
+ PyObject *valuelong = PyLong_FromUnicodeObject(value, 10);
+ if (valuelong == NULL) {
+ return -1;
+ }
+
+ int maxdigits = _PyLong_AsInt(valuelong);
+ Py_DECREF(valuelong);
+ if (maxdigits == -1 && PyErr_Occurred()) {
+ return -1;
+ }
+
+ *pmaxdigits = maxdigits;
+ return 1;
+}
+
+
+static void
+long_init_max_str_digits(void)
+{
+ // PYTHONINTMAXSTRDIGITS env var
+ char *opt = Py_GETENV("PYTHONINTMAXSTRDIGITS");
+ int maxdigits;
+ if (opt) {
+ int valid = 0;
+ if (!pymain_str_to_int(opt, &maxdigits)) {
+ valid = ((maxdigits == 0) || (maxdigits >= _PY_LONG_MAX_STR_DIGITS_THRESHOLD));
+ }
+ if (!valid) {
+#define STRINGIFY(VAL) _STRINGIFY(VAL)
+#define _STRINGIFY(VAL) #VAL
+ fprintf(stderr, "Error in PYTHONINTMAXSTRDIGITS: "
+ "invalid limit; must be >= "
+ STRINGIFY(_PY_LONG_MAX_STR_DIGITS_THRESHOLD)
+ " or 0 for unlimited.\n");
+ exit(1);
+ }
+ _Py_global_config_int_max_str_digits = maxdigits;
+ }
+
+ // -X int_max_str_digits command line option
+ int res = long_get_max_str_digits_xoption(&maxdigits);
+ if (res == 1) {
+ int valid = ((maxdigits == 0) || (maxdigits >= _PY_LONG_MAX_STR_DIGITS_THRESHOLD));
+ if (!valid) {
+ res = -1;
+ }
+ }
+ if (res < 0) {
+ fprintf(stderr, "Error in -X int_max_str_digits: "
+ "invalid limit; must be >= "
+ STRINGIFY(_PY_LONG_MAX_STR_DIGITS_THRESHOLD)
+ " or 0 for unlimited.\n");
+ exit(1);
+ }
+ if (res == 1) {
+ _Py_global_config_int_max_str_digits = maxdigits;
+ }
+
+ // Default value
+ if (_Py_global_config_int_max_str_digits == -1) {
+ _Py_global_config_int_max_str_digits = _PY_LONG_DEFAULT_MAX_STR_DIGITS;
+ }
+}
+
+
int
_PyLong_Init(void)
{
@@ -5549,6 +5713,8 @@ _PyLong_Init(void)
return 0;
}
+ long_init_max_str_digits();
+
return 1;
}
diff --git a/Python/ast.c b/Python/ast.c
index 675063e..4b69d86 100644
--- a/Python/ast.c
+++ b/Python/ast.c
@@ -2149,8 +2149,32 @@ ast_for_atom(struct compiling *c, const node *n)
}
case NUMBER: {
PyObject *pynum = parsenumber(c, STR(ch));
- if (!pynum)
+ if (!pynum) {
+ PyThreadState *tstate = PyThreadState_GET();
+ // The only way a ValueError should happen in _this_ code is via
+ // PyLong_FromString hitting a length limit.
+ if (tstate->curexc_type == PyExc_ValueError &&
+ tstate->curexc_value != NULL) {
+ PyObject *type, *value, *tb;
+ // This acts as PyErr_Clear() as we're replacing curexc.
+ PyErr_Fetch(&type, &value, &tb);
+ Py_XDECREF(tb);
+ Py_DECREF(type);
+ PyObject *helpful_msg = PyUnicode_FromFormat(
+ "%S - Consider hexadecimal for huge integer literals "
+ "to avoid decimal conversion limits.",
+ value);
+ if (helpful_msg) {
+ const char* error_msg = PyUnicode_AsUTF8(helpful_msg);
+ if (error_msg) {
+ ast_error(c, ch, error_msg);
+ }
+ Py_DECREF(helpful_msg);
+ }
+ Py_DECREF(value);
+ }
return NULL;
+ }
if (PyArena_AddPyObject(c->c_arena, pynum) < 0) {
Py_DECREF(pynum);
diff --git a/Python/pylifecycle.c b/Python/pylifecycle.c
index 0b985bf..095d1ef 100644
--- a/Python/pylifecycle.c
+++ b/Python/pylifecycle.c
@@ -97,6 +97,8 @@ int Py_IsolatedFlag = 0; /* for -I, isolate from user's env */
int Py_LegacyWindowsFSEncodingFlag = 0; /* Uses mbcs instead of utf-8 */
int Py_LegacyWindowsStdioFlag = 0; /* Uses FileIO instead of WindowsConsoleIO */
#endif
+/* Unusual name compared to the above for backporting from 3.12 reasons. */
+int _Py_global_config_int_max_str_digits = -1; /* -X int_max_str_digits or PYTHONINTMAXSTRDIGITS */
PyThreadState *_Py_Finalizing = NULL;
diff --git a/Python/sysmodule.c b/Python/sysmodule.c
index 7d1493c..ecdb62c 100644
--- a/Python/sysmodule.c
+++ b/Python/sysmodule.c
@@ -1079,6 +1079,46 @@ sys_mdebug(PyObject *self, PyObject *args)
}
#endif /* USE_MALLOPT */
+static PyObject *
+sys_get_int_max_str_digits(PyObject *module, PyObject *Py_UNUSED(ignored))
+{
+ return PyLong_FromSsize_t(_Py_global_config_int_max_str_digits);
+}
+
+PyDoc_STRVAR(sys_get_int_max_str_digits__doc__,
+"get_int_max_str_digits($module, /)\n"
+"--\n"
+"\n"
+"Set the maximum string digits limit for non-binary int<->str conversions.");
+
+static PyObject *
+sys_set_int_max_str_digits(PyObject *module, PyObject *args, PyObject *kwds)
+{
+ static char *kwlist[] = {"maxdigits", NULL};
+ int maxdigits;
+
+ if (!PyArg_ParseTupleAndKeywords(args, kwds, "i:set_int_max_str_digits",
+ kwlist, &maxdigits))
+ return NULL;
+
+ if ((!maxdigits) || (maxdigits >= _PY_LONG_MAX_STR_DIGITS_THRESHOLD)) {
+ _Py_global_config_int_max_str_digits = maxdigits;
+ Py_RETURN_NONE;
+ } else {
+ PyErr_Format(
+ PyExc_ValueError, "maxdigits must be 0 or larger than %d",
+ _PY_LONG_MAX_STR_DIGITS_THRESHOLD);
+ return NULL;
+ }
+}
+
+PyDoc_STRVAR(sys_set_int_max_str_digits__doc__,
+"set_int_max_str_digits($module, /, maxdigits)\n"
+"--\n"
+"\n"
+"Set the maximum string digits limit for non-binary int<->str conversions.");
+
+
size_t
_PySys_GetSizeOf(PyObject *o)
{
@@ -1434,6 +1474,8 @@ static PyMethodDef sys_methods[] = {
METH_VARARGS | METH_KEYWORDS, set_asyncgen_hooks_doc},
{"get_asyncgen_hooks", sys_get_asyncgen_hooks, METH_NOARGS,
get_asyncgen_hooks_doc},
+ {"get_int_max_str_digits", sys_get_int_max_str_digits, METH_NOARGS, sys_get_int_max_str_digits__doc__},
+ {"set_int_max_str_digits", (PyCFunction)sys_set_int_max_str_digits, METH_VARARGS|METH_KEYWORDS, sys_set_int_max_str_digits__doc__},
{NULL, NULL} /* sentinel */
};
@@ -1681,6 +1723,7 @@ static PyStructSequence_Field flags_fields[] = {
{"quiet", "-q"},
{"hash_randomization", "-R"},
{"isolated", "-I"},
+ {"int_max_str_digits", "-X int_max_str_digits"},
{0}
};
@@ -1688,7 +1731,7 @@ static PyStructSequence_Desc flags_desc = {
"sys.flags", /* name */
flags__doc__, /* doc */
flags_fields, /* fields */
- 13
+ 14
};
static PyObject*
@@ -1719,6 +1762,7 @@ make_flags(void)
SetFlag(Py_QuietFlag);
SetFlag(Py_HashRandomizationFlag);
SetFlag(Py_IsolatedFlag);
+ SetFlag(_Py_global_config_int_max_str_digits);
#undef SetFlag
if (PyErr_Occurred()) {
--
2.37.3