Python codecs.lookup_error() Examples
The following are 30
code examples of codecs.lookup_error().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
codecs
, or try the search function
.
.
Example #1
| Source File: test_codeccallbacks.py From Fluid-Designer with GNU General Public License v3.0 | 6 votes |
|
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")
)
self.assertEqual(
codecs.namereplace_errors,
codecs.lookup_error("namereplace")
)
Example #2
| Source File: _java.py From CTFCrackTools-V2 with GNU General Public License v3.0 | 6 votes |
|
def decode(self, input, errors='strict', final=True):
error_function = codecs.lookup_error(errors)
input_buffer = ByteBuffer.wrap(array('b', input))
decoder = Charset.forName(self.encoding).newDecoder()
output_buffer = CharBuffer.allocate(min(max(int(len(input) / 2), 256), 1024))
builder = StringBuilder(int(decoder.averageCharsPerByte() * len(input)))
while True:
result = decoder.decode(input_buffer, output_buffer, False)
pos = output_buffer.position()
output_buffer.rewind()
builder.append(output_buffer.subSequence(0, pos))
if result.isUnderflow():
if final:
_process_incomplete_decode(self.encoding, input, error_function, input_buffer, builder)
break
_process_decode_errors(self.encoding, input, result, error_function, input_buffer, builder)
return builder.toString(), input_buffer.position()
Example #3
| Source File: test_codecs.py From ironpython3 with Apache License 2.0 | 6 votes |
|
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)
Example #4
| Source File: test_codecs.py From Project-New-Reign---Nemesis-Main with GNU General Public License v3.0 | 6 votes |
|
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",
"namereplace_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)
Example #5
| Source File: test_codeccallbacks.py From ironpython2 with Apache License 2.0 | 6 votes |
|
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
Example #6
| Source File: _java.py From CTFCrackTools-V2 with GNU General Public License v3.0 | 6 votes |
|
def encode(self, input, errors='strict'):
error_function = codecs.lookup_error(errors)
# workaround non-BMP issues - need to get the exact count of chars, not codepoints
input_buffer = CharBuffer.allocate(StringBuilder(input).length())
input_buffer.put(input)
input_buffer.rewind()
encoder = Charset.forName(self.encoding).newEncoder()
output_buffer = ByteBuffer.allocate(min(max(len(input) * 2, 256), 1024))
builder = StringIO()
while True:
result = encoder.encode(input_buffer, output_buffer, True)
pos = output_buffer.position()
output_buffer.rewind()
builder.write(output_buffer.array()[0:pos].tostring())
if result.isUnderflow():
break
_process_encode_errors(self.encoding, input, result, error_function, input_buffer, builder)
return builder.getvalue(), len(input)
Example #7
| Source File: test_codeccallbacks.py From ironpython3 with Apache License 2.0 | 6 votes |
|
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
Example #8
| Source File: test_codeccallbacks.py From BinderFilter with MIT License | 6 votes |
|
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
Example #9
| Source File: test_codeccallbacks.py From medicare-demo with Apache License 2.0 | 6 votes |
|
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"):
for err in errors:
try:
uni.encode(enc, err)
except UnicodeError:
pass
Example #10
| Source File: test_codeccallbacks.py From oss-ftp with MIT License | 6 votes |
|
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
Example #11
| Source File: test_codeccallbacks.py From Project-New-Reign---Nemesis-Main with GNU General Public License v3.0 | 6 votes |
|
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")
)
self.assertEqual(
codecs.namereplace_errors,
codecs.lookup_error("namereplace")
)
Example #12
| Source File: _java.py From CTFCrackTools-V2 with GNU General Public License v3.0 | 6 votes |
|
def encode(self, input, final=False):
error_function = codecs.lookup_error(self.errors)
# workaround non-BMP issues - need to get the exact count of chars, not codepoints
input_buffer = CharBuffer.allocate(StringBuilder(input).length())
input_buffer.put(input)
input_buffer.rewind()
self.output_buffer.rewind()
builder = StringIO()
while True:
result = self.encoder.encode(input_buffer, self.output_buffer, final)
pos = self.output_buffer.position()
self.output_buffer.rewind()
builder.write(self.output_buffer.array()[0:pos].tostring())
if result.isUnderflow():
break
_process_encode_errors(self.encoding, input, result, error_function, input_buffer, builder)
return builder.getvalue()
Example #13
| Source File: test_codeccallbacks.py From gcblue with BSD 3-Clause "New" or "Revised" License | 6 votes |
|
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
Example #14
| Source File: test_codeccallbacks.py From Fluid-Designer with GNU General Public License v3.0 | 6 votes |
|
def test_longstrings(self):
# test long strings to check for memory overflow problems
errors = [ "strict", "ignore", "replace", "xmlcharrefreplace",
"backslashreplace", "namereplace"]
# 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
Example #15
| Source File: pyexiftool.py From elodie with Apache License 2.0 | 6 votes |
|
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
Example #16
| Source File: test_codecs.py From Fluid-Designer with GNU General Public License v3.0 | 6 votes |
|
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",
"namereplace_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)
Example #17
| Source File: exiftool.py From Fluid-Designer with GNU General Public License v3.0 | 6 votes |
|
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
Example #18
| Source File: shell.py From supersqlite with MIT License | 6 votes |
|
def set_encoding(self, enc):
"""Saves *enc* as the default encoding, after verifying that
it is valid. You can also include :error to specify error
handling - eg 'cp437:replace'
Raises an exception on invalid encoding or error
"""
enc=enc.split(":", 1)
if len(enc)>1:
enc, errors=enc
else:
enc=enc[0]
errors=None
try:
codecs.lookup(enc)
except LookupError:
raise self.Error("No known encoding '%s'" % (enc,))
try:
if errors is not None:
codecs.lookup_error(errors)
except LookupError:
raise self.Error("No known codec error handler '%s'" % (errors,))
self.encoding=enc, errors
Example #19
| Source File: test_codeccallbacks.py From Project-New-Reign---Nemesis-Main with GNU General Public License v3.0 | 6 votes |
|
def test_longstrings(self):
# test long strings to check for memory overflow problems
errors = [ "strict", "ignore", "replace", "xmlcharrefreplace",
"backslashreplace", "namereplace"]
# 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
Example #20
| Source File: shell.py From magnitude with MIT License | 6 votes |
|
def set_encoding(self, enc):
"""Saves *enc* as the default encoding, after verifying that
it is valid. You can also include :error to specify error
handling - eg 'cp437:replace'
Raises an exception on invalid encoding or error
"""
enc=enc.split(":", 1)
if len(enc)>1:
enc, errors=enc
else:
enc=enc[0]
errors=None
try:
codecs.lookup(enc)
except LookupError:
raise self.Error("No known encoding '%s'" % (enc,))
try:
if errors is not None:
codecs.lookup_error(errors)
except LookupError:
raise self.Error("No known codec error handler '%s'" % (errors,))
self.encoding=enc, errors
Example #21
| Source File: test_codecs.py From ironpython3 with Apache License 2.0 | 5 votes |
|
def test_surrogatepass_handler(self):
self.assertEqual("abc\ud800def".encode("cp65001", "surrogatepass"),
b"abc\xed\xa0\x80def")
self.assertEqual(b"abc\xed\xa0\x80def".decode("cp65001", "surrogatepass"),
"abc\ud800def")
self.assertEqual("\U00010fff\uD800".encode("cp65001", "surrogatepass"),
b"\xf0\x90\xbf\xbf\xed\xa0\x80")
self.assertEqual(b"\xf0\x90\xbf\xbf\xed\xa0\x80".decode("cp65001", "surrogatepass"),
"\U00010fff\uD800")
self.assertTrue(codecs.lookup_error("surrogatepass"))
Example #22
| Source File: surrogateescape.py From blackmamba with MIT License | 5 votes |
|
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)
Example #23
| Source File: frontend.py From blackmamba with MIT License | 5 votes |
|
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)
return value
Example #24
| Source File: frontend.py From AWS-Transit-Gateway-Demo-MultiAccount with MIT License | 5 votes |
|
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)
return value
Example #25
| Source File: frontend.py From AWS-Transit-Gateway-Demo-MultiAccount with MIT License | 5 votes |
|
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)
return value
Example #26
| Source File: frontend.py From cadquery-freecad-module with GNU Lesser General Public License v3.0 | 5 votes |
|
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
Example #27
| Source File: surrogateescape.py From addon with GNU General Public License v3.0 | 5 votes |
|
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)
Example #28
| Source File: surrogateescape.py From misp42splunk with GNU Lesser General Public License v3.0 | 5 votes |
|
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)
Example #29
| Source File: surrogateescape.py From cadquery-freecad-module with GNU Lesser General Public License v3.0 | 5 votes |
|
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)
Example #30
| Source File: test_codecs.py From ironpython3 with Apache License 2.0 | 5 votes |
|
def test_lookup_error(self):
#sanity
self.assertRaises(LookupError, codecs.lookup_error, "blah garbage xyz")
def garbage_error1(someError): pass
codecs.register_error("blah garbage xyz", garbage_error1)
self.assertEqual(codecs.lookup_error("blah garbage xyz"), garbage_error1)
def garbage_error2(someError): pass
codecs.register_error("some other", garbage_error2)
self.assertEqual(codecs.lookup_error("some other"), garbage_error2)
self.assertRaises(TypeError, codecs.lookup_error, None)
self.assertRaises(TypeError, codecs.register_error, None, garbage_error1)
self.assertRaises(TypeError, codecs.register_error, "blah none garbage", None)
#TODO: @skip("multiple_execute")
