Python codecs 模块，lookup_error() 实例源码

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 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)

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.assertEqual("\U00010fff\uD800".encode("utf-8", "surrogatepass"),
                         b"\xf0\x90\xbf\xbf\xed\xa0\x80")
        self.assertEqual(b"\xf0\x90\xbf\xbf\xed\xa0\x80".decode("utf-8", "surrogatepass"),
                         "\U00010fff\uD800")
        self.assertTrue(codecs.lookup_error("surrogatepass"))
        with self.assertRaises(UnicodeDecodeError):
            b"abc\xed\xa0".decode("utf-8", "surrogatepass")
        with self.assertRaises(UnicodeDecodeError):
            b"abc\xed\xa0z".decode("utf-8", "surrogatepass")

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"))

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 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 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 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_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_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.assertEqual("\U00010fff\uD800".encode("utf-8", "surrogatepass"),
                         b"\xf0\x90\xbf\xbf\xed\xa0\x80")
        self.assertEqual(b"\xf0\x90\xbf\xbf\xed\xa0\x80".decode("utf-8", "surrogatepass"),
                         "\U00010fff\uD800")
        self.assertTrue(codecs.lookup_error("surrogatepass"))
        with self.assertRaises(UnicodeDecodeError):
            b"abc\xed\xa0".decode("utf-8", "surrogatepass")
        with self.assertRaises(UnicodeDecodeError):
            b"abc\xed\xa0z".decode("utf-8", "surrogatepass")

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"))

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 upgrade_backslashreplace():
    if codecs.lookup_error('backslashreplace') is not codecs.backslashreplace_errors:
        return  # don't upgrade if someone else already has
    codecs.register_error('old-backslashreplace', codecs.backslashreplace_errors)
    codecs.register_error('backslashreplace', backslashreplace_errors)

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)
    return value