Skip to content

[SPARK-61253][PYTHON] Avoid parsing sys.version when detecting PyPy in cloudpickle #60244

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
LorenzoMartini wants to merge 1 commit into
base: master
Choose a base branch
from
Open

[SPARK-61253][PYTHON] Avoid parsing sys.version when detecting PyPy in cloudpickle #60244

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 1 addition & 2 deletions python/pyspark/cloudpickle/cloudpickle.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,7 +64,6 @@
import opcode
import pickle
from pickle import _getattribute as _pickle_getattribute
import platform
import struct
import sys
import threading
Expand Down Expand Up @@ -95,7 +94,7 @@
_DYNAMIC_CLASS_TRACKER_BY_ID = weakref.WeakValueDictionary()
_DYNAMIC_CLASS_TRACKER_LOCK = threading.Lock()

PYPY = platform.python_implementation() == "PyPy"
PYPY = sys.implementation.name == "pypy"

builtin_code_type = None
if PYPY:
Expand Down
17 changes: 17 additions & 0 deletions python/pyspark/tests/test_serializers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,9 @@
import collections
import math
import pickle
import subprocess
import sys
import textwrap
import unittest

from pyspark import serializers
Expand Down Expand Up @@ -45,6 +47,21 @@


class SerializationTestCase(unittest.TestCase):
def test_cloudpickle_with_packaged_python_version(self):
script = textwrap.dedent(
"""
import sys
sys.version = sys.version.replace(" ", " | packaged by example | ", 1)

from pyspark import cloudpickle

func = cloudpickle.loads(cloudpickle.dumps(lambda x: x + 1))
assert func(1) == 2
"""
)
result = subprocess.run([sys.executable, "-c", script], capture_output=True, text=True)
self.assertEqual(result.returncode, 0, result.stdout + result.stderr)

def test_namedtuple(self):
from collections import namedtuple

Expand Down