def _fscodec():
encoding = sys.getfilesystemencoding()
errors = "strict"
if encoding != "mbcs":
try:
codecs.lookup_error("surrogateescape")
except LookupError:
pass
else:
errors = "surrogateescape"
def fsencode(filename):
"""
Encode filename to the filesystem encoding with 'surrogateescape' error
handler, return bytes unchanged. On Windows, use 'strict' error handler
if the file system encoding is 'mbcs' (which is the default encoding).
"""
if isinstance(filename, bytes):
return filename
else:
return filename.encode(encoding, errors)
return fsencode
python类lookup_error()的实例源码
def test_longstrings(self):
# test long strings to check for memory overflow problems
errors = [ "strict", "ignore", "replace", "xmlcharrefreplace",
"backslashreplace"]
# register the handlers under different names,
# to prevent the codec from recognizing the name
for err in errors:
codecs.register_error("test." + err, codecs.lookup_error(err))
l = 1000
errors += [ "test." + err for err in errors ]
for uni in [ s*l for s in ("x", "\u3042", "a\xe4") ]:
for enc in ("ascii", "latin-1", "iso-8859-1", "iso-8859-15",
"utf-8", "utf-7", "utf-16", "utf-32"):
for err in errors:
try:
uni.encode(enc, err)
except UnicodeError:
pass
def test_longstrings(self):
# test long strings to check for memory overflow problems
errors = [ "strict", "ignore", "replace", "xmlcharrefreplace",
"backslashreplace"]
# register the handlers under different names,
# to prevent the codec from recognizing the name
for err in errors:
codecs.register_error("test." + err, codecs.lookup_error(err))
l = 1000
errors += [ "test." + err for err in errors ]
for uni in [ s*l for s in (u"x", u"\u3042", u"a\xe4") ]:
for enc in ("ascii", "latin-1", "iso-8859-1", "iso-8859-15",
"utf-8", "utf-7", "utf-16", "utf-32"):
for err in errors:
try:
uni.encode(enc, err)
except UnicodeError:
pass
def test_longstrings(self):
# test long strings to check for memory overflow problems
errors = [ "strict", "ignore", "replace", "xmlcharrefreplace",
"backslashreplace"]
# register the handlers under different names,
# to prevent the codec from recognizing the name
for err in errors:
codecs.register_error("test." + err, codecs.lookup_error(err))
l = 1000
errors += [ "test." + err for err in errors ]
for uni in [ s*l for s in (u"x", u"\u3042", u"a\xe4") ]:
for enc in ("ascii", "latin-1", "iso-8859-1", "iso-8859-15",
"utf-8", "utf-7", "utf-16", "utf-32"):
for err in errors:
try:
uni.encode(enc, err)
except UnicodeError:
pass
def test_longstrings(self):
# test long strings to check for memory overflow problems
errors = [ "strict", "ignore", "replace", "xmlcharrefreplace",
"backslashreplace"]
# register the handlers under different names,
# to prevent the codec from recognizing the name
for err in errors:
codecs.register_error("test." + err, codecs.lookup_error(err))
l = 1000
errors += [ "test." + err for err in errors ]
for uni in [ s*l for s in ("x", "\u3042", "a\xe4") ]:
for enc in ("ascii", "latin-1", "iso-8859-1", "iso-8859-15",
"utf-8", "utf-7", "utf-16", "utf-32"):
for err in errors:
try:
uni.encode(enc, err)
except UnicodeError:
pass
def test_longstrings(self):
# test long strings to check for memory overflow problems
errors = [ "strict", "ignore", "replace", "xmlcharrefreplace",
"backslashreplace"]
# register the handlers under different names,
# to prevent the codec from recognizing the name
for err in errors:
codecs.register_error("test." + err, codecs.lookup_error(err))
l = 1000
errors += [ "test." + err for err in errors ]
for uni in [ s*l for s in (u"x", u"\u3042", u"a\xe4") ]:
for enc in ("ascii", "latin-1", "iso-8859-1", "iso-8859-15",
"utf-8", "utf-7", "utf-16", "utf-32"):
for err in errors:
try:
uni.encode(enc, err)
except UnicodeError:
pass
def test_all(self):
api = (
"encode", "decode",
"register", "CodecInfo", "Codec", "IncrementalEncoder",
"IncrementalDecoder", "StreamReader", "StreamWriter", "lookup",
"getencoder", "getdecoder", "getincrementalencoder",
"getincrementaldecoder", "getreader", "getwriter",
"register_error", "lookup_error",
"strict_errors", "replace_errors", "ignore_errors",
"xmlcharrefreplace_errors", "backslashreplace_errors",
"open", "EncodedFile",
"iterencode", "iterdecode",
"BOM", "BOM_BE", "BOM_LE",
"BOM_UTF8", "BOM_UTF16", "BOM_UTF16_BE", "BOM_UTF16_LE",
"BOM_UTF32", "BOM_UTF32_BE", "BOM_UTF32_LE",
"BOM32_BE", "BOM32_LE", "BOM64_BE", "BOM64_LE", # Undocumented
"StreamReaderWriter", "StreamRecoder",
)
self.assertCountEqual(api, codecs.__all__)
for api in codecs.__all__:
getattr(codecs, api)
def test_longstrings(self):
# test long strings to check for memory overflow problems
errors = [ "strict", "ignore", "replace", "xmlcharrefreplace",
"backslashreplace"]
# register the handlers under different names,
# to prevent the codec from recognizing the name
for err in errors:
codecs.register_error("test." + err, codecs.lookup_error(err))
l = 1000
errors += [ "test." + err for err in errors ]
for uni in [ s*l for s in ("x", "\u3042", "a\xe4") ]:
for enc in ("ascii", "latin-1", "iso-8859-1", "iso-8859-15",
"utf-8", "utf-7", "utf-16", "utf-32"):
for err in errors:
try:
uni.encode(enc, err)
except UnicodeError:
pass
def test_fake_error_class(self):
handlers = [
codecs.strict_errors,
codecs.ignore_errors,
codecs.replace_errors,
codecs.backslashreplace_errors,
codecs.xmlcharrefreplace_errors,
codecs.lookup_error('surrogateescape'),
codecs.lookup_error('surrogatepass'),
]
for cls in UnicodeEncodeError, UnicodeDecodeError, UnicodeTranslateError:
class FakeUnicodeError(str):
__class__ = cls
for handler in handlers:
with self.subTest(handler=handler, error_class=cls):
self.assertRaises(TypeError, handler, FakeUnicodeError())
class FakeUnicodeError(Exception):
__class__ = cls
for handler in handlers:
with self.subTest(handler=handler, error_class=cls):
with self.assertRaises((TypeError, FakeUnicodeError)):
handler(FakeUnicodeError())
def test_longstrings(self):
# test long strings to check for memory overflow problems
errors = [ "strict", "ignore", "replace", "xmlcharrefreplace",
"backslashreplace"]
# register the handlers under different names,
# to prevent the codec from recognizing the name
for err in errors:
codecs.register_error("test." + err, codecs.lookup_error(err))
l = 1000
errors += [ "test." + err for err in errors ]
for uni in [ s*l for s in (u"x", u"\u3042", u"a\xe4") ]:
for enc in ("ascii", "latin-1", "iso-8859-1", "iso-8859-15",
"utf-8", "utf-7", "utf-16", "utf-32"):
for err in errors:
try:
uni.encode(enc, err)
except UnicodeError:
pass
def test_longstrings(self):
# test long strings to check for memory overflow problems
errors = [ "strict", "ignore", "replace", "xmlcharrefreplace",
"backslashreplace"]
# register the handlers under different names,
# to prevent the codec from recognizing the name
for err in errors:
codecs.register_error("test." + err, codecs.lookup_error(err))
l = 1000
errors += [ "test." + err for err in errors ]
for uni in [ s*l for s in ("x", "\u3042", "a\xe4") ]:
for enc in ("ascii", "latin-1", "iso-8859-1", "iso-8859-15",
"utf-8", "utf-7", "utf-16", "utf-32"):
for err in errors:
try:
uni.encode(enc, err)
except UnicodeError:
pass
def _fscodec():
encoding = sys.getfilesystemencoding()
errors = "strict"
if encoding != "mbcs":
try:
codecs.lookup_error("surrogateescape")
except LookupError:
pass
else:
errors = "surrogateescape"
def fsencode(filename):
"""
Encode filename to the filesystem encoding with 'surrogateescape' error
handler, return bytes unchanged. On Windows, use 'strict' error handler if
the file system encoding is 'mbcs' (which is the default encoding).
"""
if isinstance(filename, bytes):
return filename
else:
return filename.encode(encoding, errors)
return fsencode
def _fscodec():
encoding = sys.getfilesystemencoding()
errors = "strict"
if encoding != "mbcs":
try:
codecs.lookup_error("surrogateescape")
except LookupError:
pass
else:
errors = "surrogateescape"
def fsencode(filename):
"""
Encode filename to the filesystem encoding with 'surrogateescape' error
handler, return bytes unchanged. On Windows, use 'strict' error handler if
the file system encoding is 'mbcs' (which is the default encoding).
"""
if isinstance(filename, bytes):
return filename
else:
return filename.encode(encoding, errors)
return fsencode
def validate_encoding_error_handler(setting, value, option_parser,
config_parser=None, config_section=None):
try:
codecs.lookup_error(value)
except LookupError:
raise (LookupError(
'unknown encoding error handler: "%s" (choices: '
'"strict", "ignore", "replace", "backslashreplace", '
'"xmlcharrefreplace", and possibly others; see documentation for '
'the Python ``codecs`` module)' % value),
None, sys.exc_info()[2])
return value
def register_surrogateescape():
"""
Registers the surrogateescape error handler on Python 2 (only)
"""
if PY3:
return
try:
codecs.lookup_error(FS_ERRORS)
except LookupError:
codecs.register_error(FS_ERRORS, surrogateescape_handler)
def validate_encoding_error_handler(setting, value, option_parser,
config_parser=None, config_section=None):
try:
codecs.lookup_error(value)
except LookupError:
raise (LookupError(
'unknown encoding error handler: "%s" (choices: '
'"strict", "ignore", "replace", "backslashreplace", '
'"xmlcharrefreplace", and possibly others; see documentation for '
'the Python ``codecs`` module)' % value),
None, sys.exc_info()[2])
return value
def register_surrogateescape():
"""
Registers the surrogateescape error handler on Python 2 (only)
"""
if utils.PY3:
return
try:
codecs.lookup_error(FS_ERRORS)
except LookupError:
codecs.register_error(FS_ERRORS, surrogateescape_handler)
def test_surrogatepass_handler(self):
self.assertEqual("abc\ud800def".encode("utf-8", "surrogatepass"),
b"abc\xed\xa0\x80def")
self.assertEqual(b"abc\xed\xa0\x80def".decode("utf-8", "surrogatepass"),
"abc\ud800def")
self.assertTrue(codecs.lookup_error("surrogatepass"))
def test_lookup(self):
self.assertEqual(codecs.strict_errors, codecs.lookup_error("strict"))
self.assertEqual(codecs.ignore_errors, codecs.lookup_error("ignore"))
self.assertEqual(codecs.strict_errors, codecs.lookup_error("strict"))
self.assertEqual(
codecs.xmlcharrefreplace_errors,
codecs.lookup_error("xmlcharrefreplace")
)
self.assertEqual(
codecs.backslashreplace_errors,
codecs.lookup_error("backslashreplace")
)
def test_badlookupcall(self):
# enhance coverage of:
# Modules/_codecsmodule.c::lookup_error()
self.assertRaises(TypeError, codecs.lookup_error)
def test_unknownhandler(self):
# enhance coverage of:
# Modules/_codecsmodule.c::lookup_error()
self.assertRaises(LookupError, codecs.lookup_error, "test.unknown")
def test_lookup(self):
self.assertEqual(codecs.strict_errors, codecs.lookup_error("strict"))
self.assertEqual(codecs.ignore_errors, codecs.lookup_error("ignore"))
self.assertEqual(codecs.strict_errors, codecs.lookup_error("strict"))
self.assertEqual(
codecs.xmlcharrefreplace_errors,
codecs.lookup_error("xmlcharrefreplace")
)
self.assertEqual(
codecs.backslashreplace_errors,
codecs.lookup_error("backslashreplace")
)
def test_badlookupcall(self):
# enhance coverage of:
# Modules/_codecsmodule.c::lookup_error()
self.assertRaises(TypeError, codecs.lookup_error)
def test_unknownhandler(self):
# enhance coverage of:
# Modules/_codecsmodule.c::lookup_error()
self.assertRaises(LookupError, codecs.lookup_error, "test.unknown")
def test_lookup(self):
self.assertEqual(codecs.strict_errors, codecs.lookup_error("strict"))
self.assertEqual(codecs.ignore_errors, codecs.lookup_error("ignore"))
self.assertEqual(codecs.strict_errors, codecs.lookup_error("strict"))
self.assertEqual(
codecs.xmlcharrefreplace_errors,
codecs.lookup_error("xmlcharrefreplace")
)
self.assertEqual(
codecs.backslashreplace_errors,
codecs.lookup_error("backslashreplace")
)
def test_badlookupcall(self):
# enhance coverage of:
# Modules/_codecsmodule.c::lookup_error()
self.assertRaises(TypeError, codecs.lookup_error)
def test_unknownhandler(self):
# enhance coverage of:
# Modules/_codecsmodule.c::lookup_error()
self.assertRaises(LookupError, codecs.lookup_error, "test.unknown")
def register_surrogateescape():
"""
Registers the surrogateescape error handler on Python 2 (only)
"""
if utils.PY3:
return
try:
codecs.lookup_error(FS_ERRORS)
except LookupError:
codecs.register_error(FS_ERRORS, surrogateescape_handler)
def validate_encoding_error_handler(setting, value, option_parser,
config_parser=None, config_section=None):
try:
codecs.lookup_error(value)
except LookupError:
raise (LookupError(
'unknown encoding error handler: "%s" (choices: '
'"strict", "ignore", "replace", "backslashreplace", '
'"xmlcharrefreplace", and possibly others; see documentation for '
'the Python ``codecs`` module)' % value),
None, sys.exc_info()[2])
return value
def register_surrogateescape():
"""
Registers the surrogateescape error handler on Python 2 (only)
"""
if utils.PY3:
return
try:
codecs.lookup_error(FS_ERRORS)
except LookupError:
codecs.register_error(FS_ERRORS, surrogateescape_handler)
