mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-04 17:08:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 13

bpo-41069: Make TESTFN and the CWD for tests containing non-ascii characters. (GH-21035)

Browse source
This commit is contained in:
Serhiy Storchaka 2020-06-25 17:56:31 +03:00 • committed by GitHub
parent 8ea6353f60
commit 700cfa8c90
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
24 changed files with 110 additions and 77 deletions
Download patch file Download diff file Expand all files Collapse all files

2
Lib/test/support/__init__.py
View file

@ -20,7 +20,7 @@ from .import_helper import (
forget, import_fresh_module, import_module, make_legacy_pyc,
modules_cleanup, modules_setup, unload)
from .os_helper import (
FS_NONASCII, SAVEDCWD, TESTFN, TESTFN_NONASCII,
FS_NONASCII, SAVEDCWD, TESTFN, TESTFN_ASCII, TESTFN_NONASCII,
TESTFN_UNENCODABLE, TESTFN_UNDECODABLE,
TESTFN_UNICODE, can_symlink, can_xattr,
change_cwd, create_empty_file, fd_count,

21
Lib/test/support/os_helper.py
View file

@ -13,16 +13,16 @@ import warnings
# Filename used for testing
if os.name == 'java':
# Jython disallows @ in module names
TESTFN = '$test'
TESTFN_ASCII = '$test'
else:
TESTFN = '@test'
TESTFN_ASCII = '@test'
# Disambiguate TESTFN for parallel testing, while letting it remain a valid
# module name.
TESTFN = "{}_{}_tmp".format(TESTFN, os.getpid())
TESTFN_ASCII = "{}_{}_tmp".format(TESTFN_ASCII, os.getpid())
# TESTFN_UNICODE is a non-ascii filename
TESTFN_UNICODE = TESTFN + "-\xe0\xf2\u0258\u0141\u011f"
TESTFN_UNICODE = TESTFN_ASCII + "-\xe0\xf2\u0258\u0141\u011f"
if sys.platform == 'darwin':
# In Mac OS X's VFS API file names are, by definition, canonically
# decomposed Unicode, encoded using UTF-8. See QA1173:
@ -39,7 +39,7 @@ if os.name == 'nt':
if sys.getwindowsversion().platform >= 2:
# Different kinds of characters from various languages to minimize the
# probability that the whole name is encodable to MBCS (issue #9819)
TESTFN_UNENCODABLE = TESTFN + "-\u5171\u0141\u2661\u0363\uDC80"
TESTFN_UNENCODABLE = TESTFN_ASCII + "-\u5171\u0141\u2661\u0363\uDC80"
try:
TESTFN_UNENCODABLE.encode(sys.getfilesystemencoding())
except UnicodeEncodeError:
@ -56,7 +56,7 @@ elif sys.platform != 'darwin':
b'\xff'.decode(sys.getfilesystemencoding())
except UnicodeDecodeError:
# 0xff will be encoded using the surrogate character u+DCFF
TESTFN_UNENCODABLE = TESTFN \
TESTFN_UNENCODABLE = TESTFN_ASCII \
+ b'-\xff'.decode(sys.getfilesystemencoding(), 'surrogateescape')
else:
# File system encoding (eg. ISO-8859-* encodings) can encode
@ -64,8 +64,8 @@ elif sys.platform != 'darwin':
pass
# FS_NONASCII: non-ASCII character encodable by os.fsencode(),
# or None if there is no such character.
FS_NONASCII = None
# or an empty string if there is no such character.
FS_NONASCII = ''
for character in (
# First try printable and common characters to have a readable filename.
# For each character, the encoding list are just example of encodings able
@ -141,13 +141,14 @@ for name in (
try:
name.decode(sys.getfilesystemencoding())
except UnicodeDecodeError:
TESTFN_UNDECODABLE = os.fsencode(TESTFN) + name
TESTFN_UNDECODABLE = os.fsencode(TESTFN_ASCII) + name
break
if FS_NONASCII:
TESTFN_NONASCII = TESTFN + '-' + FS_NONASCII
TESTFN_NONASCII = TESTFN_ASCII + FS_NONASCII
else:
TESTFN_NONASCII = None
TESTFN = TESTFN_NONASCII or TESTFN_ASCII
def make_bad_fd():