This commit is contained in:
Stefan Krah 2012-11-06 23:51:42 +01:00
commit cd81709b9e
5 changed files with 64 additions and 19 deletions

View File

@ -603,6 +603,32 @@ else:
# module name. # module name.
TESTFN = "{}_{}_tmp".format(TESTFN, os.getpid()) TESTFN = "{}_{}_tmp".format(TESTFN, os.getpid())
# FS_NONASCII: non-ASCII character encodable by os.fsencode(),
# or None if there is no such character.
FS_NONASCII = None
for character in (
# U+00E6 (Latin small letter AE): Encodable to cp1252, cp1254, cp1257, iso-8859-1
'\u00E6',
# U+0141 (Latin capital letter L with stroke): Encodable to cp1250, cp1257
'\u0141',
# U+041A (Cyrillic capital letter KA): Encodable to cp932, cp950, cp1251
'\u041A',
# U+05D0 (Hebrew Letter Alef): Encodable to cp424, cp1255
'\u05D0',
# U+06A9 (Arabic letter KEHEH): Encodable to cp1256
'\u06A9',
# U+03A9 (Greek capital letter OMEGA): Encodable to cp932, cp950, cp1253
'\u03A9',
# U+0E01 (Thai character KO KAI): Encodable to cp874
'\u0E01',
):
try:
os.fsdecode(os.fsencode(character))
except UnicodeError:
pass
else:
FS_NONASCII = character
break
# TESTFN_UNICODE is a non-ascii filename # TESTFN_UNICODE is a non-ascii filename
TESTFN_UNICODE = TESTFN + "-\xe0\xf2\u0258\u0141\u011f" TESTFN_UNICODE = TESTFN + "-\xe0\xf2\u0258\u0141\u011f"
@ -651,13 +677,22 @@ elif sys.platform != 'darwin':
# decoded from the filesystem encoding (in strict mode). It can be None if we # decoded from the filesystem encoding (in strict mode). It can be None if we
# cannot generate such filename. # cannot generate such filename.
TESTFN_UNDECODABLE = None TESTFN_UNDECODABLE = None
for name in (b'abc\xff', b'\xe7w\xf0'): # b'\xff' is not decodable by os.fsdecode() with code page 932. Windows
# accepts it to create a file or a directory, or don't accept to enter to
# such directory (when the bytes name is used). So test b'\xe7' first: it is
# not decodable from cp932.
for name in (b'\xe7w\xf0', b'abc\xff'):
try: try:
os.fsdecode(name) os.fsdecode(name)
except UnicodeDecodeError: except UnicodeDecodeError:
TESTFN_UNDECODABLE = name TESTFN_UNDECODABLE = name
break break
if FS_NONASCII:
TESTFN_NONASCII = TESTFN + '- ' + FS_NONASCII
else:
TESTFN_NONASCII = None
# Save the initial cwd # Save the initial cwd
SAVEDCWD = os.getcwd() SAVEDCWD = os.getcwd()

View File

@ -93,15 +93,15 @@ class CmdLineTest(unittest.TestCase):
# All good if execution is successful # All good if execution is successful
assert_python_ok('-c', 'pass') assert_python_ok('-c', 'pass')
@unittest.skipIf(sys.getfilesystemencoding() == 'ascii', @unittest.skipUnless(test.support.FS_NONASCII, 'need support.FS_NONASCII')
'need a filesystem encoding different than ASCII')
def test_non_ascii(self): def test_non_ascii(self):
# Test handling of non-ascii data # Test handling of non-ascii data
if test.support.verbose: if test.support.verbose:
import locale import locale
print('locale encoding = %s, filesystem encoding = %s' print('locale encoding = %s, filesystem encoding = %s'
% (locale.getpreferredencoding(), sys.getfilesystemencoding())) % (locale.getpreferredencoding(), sys.getfilesystemencoding()))
command = "assert(ord('\xe9') == 0xe9)" command = ("assert(ord(%r) == %s)"
% (test.support.FS_NONASCII, ord(test.support.FS_NONASCII)))
assert_python_ok('-c', command) assert_python_ok('-c', command)
# On Windows, pass bytes to subprocess doesn't test how Python decodes the # On Windows, pass bytes to subprocess doesn't test how Python decodes the

View File

@ -363,19 +363,12 @@ class CmdLineTest(unittest.TestCase):
self.assertTrue(text[1].startswith(' File ')) self.assertTrue(text[1].startswith(' File '))
self.assertTrue(text[3].startswith('NameError')) self.assertTrue(text[3].startswith('NameError'))
@unittest.skipUnless(support.TESTFN_NONASCII, 'need support.TESTFN_NONASCII')
def test_non_ascii(self): def test_non_ascii(self):
# Issue #16218 # Issue #16218
# non-ascii filename encodable to cp1252, cp932, latin1 and utf8 # non-ascii filename encodable to cp1252, cp932, latin1 and utf8
filename = support.TESTFN + '\xa3'
try:
os.fsencode(filename)
except UnicodeEncodeError:
self.skipTest(
"Filesystem encoding %r cannot encode "
"the filename: %a"
% (sys.getfilesystemencoding(), filename))
source = 'print(ascii(__file__))\n' source = 'print(ascii(__file__))\n'
script_name = _make_test_script(os.curdir, filename, source) script_name = _make_test_script(os.curdir, support.TESTFN_NONASCII, source)
self.addCleanup(support.unlink, script_name) self.addCleanup(support.unlink, script_name)
rc, stdout, stderr = assert_python_ok(script_name) rc, stdout, stderr = assert_python_ok(script_name)
self.assertEqual( self.assertEqual(

View File

@ -308,15 +308,28 @@ class CommonTest(GenericTest):
for path in ('', 'fuu', 'f\xf9\xf9', '/fuu', 'U:\\'): for path in ('', 'fuu', 'f\xf9\xf9', '/fuu', 'U:\\'):
self.assertIsInstance(abspath(path), str) self.assertIsInstance(abspath(path), str)
@unittest.skipIf(sys.platform == 'darwin',
"Mac OS X denies the creation of a directory with an invalid utf8 name")
def test_nonascii_abspath(self): def test_nonascii_abspath(self):
# Test non-ASCII in the path
if sys.platform in ('win32', 'darwin'):
if support.TESTFN_NONASCII:
name = support.TESTFN_NONASCII
else:
# Mac OS X denies the creation of a directory with an invalid
# UTF-8 name. Windows allows to create a directory with an
# arbitrary bytes name, but fails to enter this directory
# (when the bytes name is used).
self.skipTest("need support.TESTFN_NONASCII")
else:
if support.TESTFN_UNDECODABLE: if support.TESTFN_UNDECODABLE:
name = support.TESTFN_UNDECODABLE name = support.TESTFN_UNDECODABLE
elif support.TESTFN_NONASCII:
name = support.TESTFN_NONASCII
else: else:
# On UNIX, the surrogateescape error handler is used to
# decode paths, so any byte is allowed, it does not depend
# on the locale
name = b'a\xffb\xe7w\xf0' name = b'a\xffb\xe7w\xf0'
# Test non-ASCII, non-UTF8 bytes in the path.
with warnings.catch_warnings(): with warnings.catch_warnings():
warnings.simplefilter("ignore", DeprecationWarning) warnings.simplefilter("ignore", DeprecationWarning)
with support.temp_cwd(name): with support.temp_cwd(name):

View File

@ -1243,6 +1243,8 @@ if sys.platform != 'win32':
def setUp(self): def setUp(self):
if support.TESTFN_UNENCODABLE: if support.TESTFN_UNENCODABLE:
self.dir = support.TESTFN_UNENCODABLE self.dir = support.TESTFN_UNENCODABLE
elif support.TESTFN_NONASCII:
self.dir = support.TESTFN_NONASCII
else: else:
self.dir = support.TESTFN self.dir = support.TESTFN
self.bdir = os.fsencode(self.dir) self.bdir = os.fsencode(self.dir)
@ -1257,6 +1259,8 @@ if sys.platform != 'win32':
add_filename(support.TESTFN_UNICODE) add_filename(support.TESTFN_UNICODE)
if support.TESTFN_UNENCODABLE: if support.TESTFN_UNENCODABLE:
add_filename(support.TESTFN_UNENCODABLE) add_filename(support.TESTFN_UNENCODABLE)
if support.TESTFN_NONASCII:
add_filename(support.TESTFN_NONASCII)
if not bytesfn: if not bytesfn:
self.skipTest("couldn't create any non-ascii filename") self.skipTest("couldn't create any non-ascii filename")