SJ-PT-23-03: Backport integer string length limitation to limit quadratic parsing

5 files changed, 40 insertions, 3 deletions

diff --git a/CHANGES.txt b/CHANGES.txt
index ddb2bd8..b70200f 100644
--- a/CHANGES.txt
+++ b/CHANGES.txt
@@ -4,6 +4,8 @@ Version 3.19.0 released 2023-04-XX
   implementation of the decoder (SJ-PT-23-01)
 * Fix missing reference count decrease if PyOS_string_to_double raises
   an exception in Python 2.x; was probably unreachable (SJ-PT-23-02)
+* Backport the integer string length limitation from Python 3.11 to
+  limit quadratic number parsing (SJ-PT-23-03)
 
 Version 3.18.4 released 2023-03-14
 
diff --git a/index.rst b/index.rst
index fbb52b5..a10ccb7 100644
--- a/index.rst
+++ b/index.rst
@@ -412,6 +412,13 @@ Basic Usage
     be used to use another datatype or parser for JSON integers
     (e.g. :class:`float`).
 
+    .. versionchanged:: 3.19.0
+        The integer to string conversion length limitation introduced in
+        Python 3.11 has been backported. An attempt to parse an integer
+        with more than 4300 digits will result in an exception unless a
+        suitable alternative parser is specified
+        (e.g. :class:`decimal.Decimal`)
+
     *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 are encountered.
@@ -502,6 +509,13 @@ Encoders and decoders
    be used to use another datatype or parser for JSON integers
    (e.g. :class:`float`).
 
+    .. versionchanged:: 3.19.0
+        The integer to string conversion length limitation introduced in
+        Python 3.11 has been backported. An attempt to parse an integer
+        with more than 4300 digits will result in an exception unless a
+        suitable alternative parser is specified
+        (e.g. :class:`decimal.Decimal`)
+
    *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 are encountered.
diff --git a/simplejson/__init__.py b/simplejson/__init__.py
index 2f0bebf..92b6009 100644
--- a/simplejson/__init__.py
+++ b/simplejson/__init__.py
@@ -442,12 +442,12 @@ def load(fp, encoding=None, cls=None, object_hook=None, parse_float=None,
     takes priority.
 
     *parse_float*, if specified, will be called with the string of every
-    JSON float to be decoded.  By default, this is equivalent to
+    JSON float to be decoded. By default, this is equivalent to
     ``float(num_str)``. This can be used to use another datatype or parser
     for JSON floats (e.g. :class:`decimal.Decimal`).
 
     *parse_int*, if specified, will be called with the string of every
-    JSON int to be decoded.  By default, this is equivalent to
+    JSON int to be decoded. By default, this is equivalent to
     ``int(num_str)``.  This can be used to use another datatype or parser
     for JSON integers (e.g. :class:`float`).
 
diff --git a/simplejson/decoder.py b/simplejson/decoder.py
index e1f10ae..c28e445 100644
--- a/simplejson/decoder.py
+++ b/simplejson/decoder.py
@@ -46,6 +46,19 @@ BACKSLASH = {
 
 DEFAULT_ENCODING = "utf-8"
 
+if hasattr(sys, 'get_int_max_str_digits'):
+    bounded_int = int
+else:
+    def bounded_int(s, INT_MAX_STR_DIGITS=4300):
+        """Backport of the integer string length conversion limitation
+
+        https://docs.python.org/3/library/stdtypes.html#int-max-str-digits
+        """
+        if len(s) > INT_MAX_STR_DIGITS:
+            raise ValueError("Exceeds the limit (%s) for integer string conversion: value has %s digits" % (INT_MAX_STR_DIGITS, len(s)))
+        return int(s)
+
+
 def scan_four_digit_hex(s, end, _m=re.compile(r'^[0-9a-fA-F]{4}$').match):
     """Scan a four digit hex number from s[end:end + 4]
     """
@@ -349,7 +362,7 @@ class JSONDecoder(object):
         self.object_hook = object_hook
         self.object_pairs_hook = object_pairs_hook
         self.parse_float = parse_float or float
-        self.parse_int = parse_int or int
+        self.parse_int = parse_int or bounded_int
         self.parse_constant = parse_constant or _CONSTANTS.__getitem__
         self.strict = strict
         self.parse_object = JSONObject
diff --git a/simplejson/tests/test_decode.py b/simplejson/tests/test_decode.py
index 6960ee5..317b4f9 100644
--- a/simplejson/tests/test_decode.py
+++ b/simplejson/tests/test_decode.py
@@ -2,6 +2,7 @@ from __future__ import absolute_import
 import decimal
 from unittest import TestCase
 
+import sys
 import simplejson as json
 from simplejson.compat import StringIO, b, binary_type
 from simplejson import OrderedDict
@@ -117,3 +118,10 @@ class TestDecode(TestCase):
         diff = id(x) - id(y)
         self.assertRaises(ValueError, j.scan_once, y, diff)
         self.assertRaises(ValueError, j.raw_decode, y, i)
+
+    def test_bounded_int(self):
+        # SJ-PT-23-03, limit quadratic number parsing per Python 3.11
+        max_str_digits = getattr(sys, 'get_int_max_str_digits', lambda: 4300)()
+        s = '1' + '0' * (max_str_digits - 1)
+        self.assertEqual(json.loads(s), int(s))
+        self.assertRaises(ValueError, json.loads, s + '0')