Skip to content

gh-154582: Fix test_invalid_utf8_arg in non-UTF-8 multibyte locales #154584

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
serhiy-storchaka wants to merge 1 commit into
base: main
Choose a base branch
from
+22 −3
Open

gh-154582: Fix test_invalid_utf8_arg in non-UTF-8 multibyte locales #154584

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
25 changes: 22 additions & 3 deletions Lib/test/test_cmd_line.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@
# Most tests are executed with environment variables ignored
# See test_cmd_line_script.py for testing of script execution

import locale
import os
import re
import subprocess
Expand Down Expand Up @@ -369,9 +370,27 @@ def run_no_utf8_mode(arg):
)
test_args = [valid_utf8, invalid_utf8]

for run_cmd in (run_default, run_c_locale, run_utf8_mode,
run_no_utf8_mode):
with self.subTest(run_cmd=run_cmd):
for run_cmd, encoding in (
(run_default, sys.getfilesystemencoding()),
(run_c_locale, None),
(run_utf8_mode, None),
(run_no_utf8_mode, locale.getencoding())
):
with self.subTest(run_cmd=run_cmd.__name__):
# Arbitrary bytes round-trip through surrogateescape only in
# UTF-8 and single-byte encodings, not in a multibyte encoding
# such as EUC-JP.
if encoding is not None:
try:
lossless = len(bytes(range(256)).decode(
encoding, 'surrogateescape')) == 256
except UnicodeError:
lossless = False
else:
lossless = True
if not lossless:
self.skipTest(f'{encoding} cannot losslessly '
f'round-trip arbitrary bytes')
for arg in test_args:
proc = run_cmd(arg)
self.assertEqual(proc.stdout.rstrip(), ascii(arg))
Expand Down
Loading