123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384 |
- From 7bd6f0e5500f778e940374237b94651f60ae1990 Mon Sep 17 00:00:00 2001
- From: "Miss Islington (bot)"
- <31488909+miss-islington@users.noreply.github.com>
- Date: Fri, 6 Jul 2018 21:00:45 -0700
- Subject: [PATCH] closes bpo-34056: Always return bytes from
- _HackedGetData.get_data(). (GH-8130)
- * Always return bytes from _HackedGetData.get_data().
- Ensure the imp.load_source shim always returns bytes by reopening the file in
- binary mode if needed. Hash-based pycs have to receive the source code in bytes.
- It's tempting to change imp.get_suffixes() to always return 'rb' as a mode, but
- that breaks some stdlib tests and likely 3rdparty code, too.
- (cherry picked from commit b0274f2cddd36b49fe5080efbe160277ef546471)
- Co-authored-by: Benjamin Peterson <benjamin@python.org>
- ---
- Lib/imp.py | 13 ++++++-------
- Lib/test/test_imp.py | 15 +++++++++++++++
- 2 files changed, 21 insertions(+), 7 deletions(-)
- diff --git a/Lib/imp.py b/Lib/imp.py
- index 866464b245b2..31f8c766381a 100644
- --- a/Lib/imp.py
- +++ b/Lib/imp.py
- @@ -142,17 +142,16 @@ def __init__(self, fullname, path, file=None):
- def get_data(self, path):
- """Gross hack to contort loader to deal w/ load_*()'s bad API."""
- if self.file and path == self.path:
- + # The contract of get_data() requires us to return bytes. Reopen the
- + # file in binary mode if needed.
- if not self.file.closed:
- file = self.file
- - else:
- - self.file = file = open(self.path, 'r')
- + if 'b' not in file.mode:
- + file.close()
- + if self.file.closed:
- + self.file = file = open(self.path, 'rb')
-
- with file:
- - # Technically should be returning bytes, but
- - # SourceLoader.get_code() just passed what is returned to
- - # compile() which can handle str. And converting to bytes would
- - # require figuring out the encoding to decode to and
- - # tokenize.detect_encoding() only accepts bytes.
- return file.read()
- else:
- return super().get_data(path)
- diff --git a/Lib/test/test_imp.py b/Lib/test/test_imp.py
- index a115e60d4e4f..bb0144b12d41 100644
- --- a/Lib/test/test_imp.py
- +++ b/Lib/test/test_imp.py
- @@ -2,6 +2,7 @@
- import importlib.util
- import os
- import os.path
- +import py_compile
- import sys
- from test import support
- from test.support import script_helper
- @@ -350,6 +351,20 @@ def test_pyc_invalidation_mode_from_cmdline(self):
- res = script_helper.assert_python_ok(*args)
- self.assertEqual(res.out.strip().decode('utf-8'), expected)
-
- + def test_find_and_load_checked_pyc(self):
- + # issue 34056
- + with support.temp_cwd():
- + with open('mymod.py', 'wb') as fp:
- + fp.write(b'x = 42\n')
- + py_compile.compile(
- + 'mymod.py',
- + doraise=True,
- + invalidation_mode=py_compile.PycInvalidationMode.CHECKED_HASH,
- + )
- + file, path, description = imp.find_module('mymod', path=['.'])
- + mod = imp.load_module('mymod', file, path, description)
- + self.assertEqual(mod.x, 42)
- +
-
- class ReloadTests(unittest.TestCase):
-
|