Python codecs.xmlcharrefreplace_errors() Examples

The following are 30 code examples of codecs.xmlcharrefreplace_errors(). 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 ironpython3 with Apache License 2.0 6 votes vote down vote up 
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())
Example #2
Source File: test_codeccallbacks.py    From Project-New-Reign---Nemesis-Main with GNU General Public License v3.0 6 votes vote down vote up 
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 #3
Source File: test_codeccallbacks.py    From Project-New-Reign---Nemesis-Main with GNU General Public License v3.0 6 votes vote down vote up 
def test_fake_error_class(self):
        handlers = [
            codecs.strict_errors,
            codecs.ignore_errors,
            codecs.replace_errors,
            codecs.backslashreplace_errors,
            codecs.namereplace_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())
Example #4
Source File: test_codeccallbacks.py    From ironpython2 with Apache License 2.0 6 votes vote down vote up 
def test_fake_error_class(self):
        handlers = [
            codecs.strict_errors,
            codecs.ignore_errors,
            codecs.replace_errors,
            codecs.backslashreplace_errors,
            codecs.xmlcharrefreplace_errors,
        ]
        for cls in UnicodeEncodeError, UnicodeDecodeError, UnicodeTranslateError:
            class FakeUnicodeError(str):
                __class__ = cls
            for handler in handlers:
                self.assertRaises(TypeError, handler, FakeUnicodeError())
            class FakeUnicodeError(Exception):
                __class__ = cls
            for handler in handlers:
                with self.assertRaises((TypeError, FakeUnicodeError)):
                    handler(FakeUnicodeError())
Example #5
Source File: test_codeccallbacks.py    From Fluid-Designer with GNU General Public License v3.0 6 votes vote down vote up 
def test_fake_error_class(self):
        handlers = [
            codecs.strict_errors,
            codecs.ignore_errors,
            codecs.replace_errors,
            codecs.backslashreplace_errors,
            codecs.namereplace_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())
Example #6
Source File: test_codeccallbacks.py    From Fluid-Designer with GNU General Public License v3.0 6 votes vote down vote up 
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 #7
Source File: test_codeccallbacks.py    From gcblue with BSD 3-Clause "New" or "Revised" License 5 votes vote down vote up 
def test_badandgoodxmlcharrefreplaceexceptions(self):
        # "xmlcharrefreplace" complains about a non-exception passed in
        self.assertRaises(
           TypeError,
           codecs.xmlcharrefreplace_errors,
           42
        )
        # "xmlcharrefreplace" complains about the wrong exception types
        self.assertRaises(
           TypeError,
           codecs.xmlcharrefreplace_errors,
           UnicodeError("ouch")
        )
        # "xmlcharrefreplace" can only be used for encoding
        self.assertRaises(
            TypeError,
            codecs.xmlcharrefreplace_errors,
            UnicodeDecodeError("ascii", "\xff", 0, 1, "ouch")
        )
        self.assertRaises(
            TypeError,
            codecs.xmlcharrefreplace_errors,
            UnicodeTranslateError(u"\u3042", 0, 1, "ouch")
        )
        # Use the correct exception
        cs = (0, 1, 9, 10, 99, 100, 999, 1000, 9999, 10000, 0x3042)
        s = "".join(unichr(c) for c in cs)
        self.assertEqual(
            codecs.xmlcharrefreplace_errors(
                UnicodeEncodeError("ascii", s, 0, len(s), "ouch")
            ),
            (u"".join(u"&#%d;" % ord(c) for c in s), len(s))
        )
Example #8
Source File: htmlserializer.py    From ImageFusion with MIT License 5 votes vote down vote up 
def htmlentityreplace_errors(exc):
        if isinstance(exc, (UnicodeEncodeError, UnicodeTranslateError)):
            res = []
            codepoints = []
            skip = False
            for i, c in enumerate(exc.object[exc.start:exc.end]):
                if skip:
                    skip = False
                    continue
                index = i + exc.start
                if utils.isSurrogatePair(exc.object[index:min([exc.end, index + 2])]):
                    codepoint = utils.surrogatePairToCodepoint(exc.object[index:index + 2])
                    skip = True
                else:
                    codepoint = ord(c)
                codepoints.append(codepoint)
            for cp in codepoints:
                e = encode_entity_map.get(cp)
                if e:
                    res.append("&")
                    res.append(e)
                    if not e.endswith(";"):
                        res.append(";")
                else:
                    res.append("&#x%s;" % (hex(cp)[2:]))
            return ("".join(res), exc.end)
        else:
            return xmlcharrefreplace_errors(exc)
Example #9
Source File: test_codeccallbacks.py    From gcblue with BSD 3-Clause "New" or "Revised" License 5 votes vote down vote up 
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")
        )
Example #10
Source File: test_codeccallbacks.py    From gcblue with BSD 3-Clause "New" or "Revised" License 5 votes vote down vote up 
def test_xmlcharrefvalues(self):
        # enhance coverage of:
        # Python/codecs.c::PyCodec_XMLCharRefReplaceErrors()
        # and inline implementations
        v = (1, 5, 10, 50, 100, 500, 1000, 5000, 10000, 50000)
        if sys.maxunicode>=100000:
            v += (100000, 500000, 1000000)
        s = u"".join([unichr(x) for x in v])
        codecs.register_error("test.xmlcharrefreplace", codecs.xmlcharrefreplace_errors)
        for enc in ("ascii", "iso-8859-15"):
            for err in ("xmlcharrefreplace", "test.xmlcharrefreplace"):
                s.encode(enc, err)
Example #11
Source File: test_codeccallbacks.py    From CTFCrackTools-V2 with GNU General Public License v3.0 5 votes vote down vote up 
def test_xmlcharrefvalues(self):
        # enhance coverage of:
        # Python/codecs.c::PyCodec_XMLCharRefReplaceErrors()
        # and inline implementations
        v = (1, 5, 10, 50, 100, 500, 1000, 5000, 10000, 50000)
        if sys.maxunicode>=100000:
            v += (100000, 500000, 1000000)
        s = u"".join([unichr(x) for x in v])
        codecs.register_error("test.xmlcharrefreplace", codecs.xmlcharrefreplace_errors)
        for enc in ("ascii", "iso-8859-15"):
            for err in ("xmlcharrefreplace", "test.xmlcharrefreplace"):
                s.encode(enc, err)
Example #12
Source File: htmlserializer.py    From syntheticmass with Apache License 2.0 5 votes vote down vote up 
def htmlentityreplace_errors(exc):
        if isinstance(exc, (UnicodeEncodeError, UnicodeTranslateError)):
            res = []
            codepoints = []
            skip = False
            for i, c in enumerate(exc.object[exc.start:exc.end]):
                if skip:
                    skip = False
                    continue
                index = i + exc.start
                if utils.isSurrogatePair(exc.object[index:min([exc.end, index + 2])]):
                    codepoint = utils.surrogatePairToCodepoint(exc.object[index:index + 2])
                    skip = True
                else:
                    codepoint = ord(c)
                codepoints.append(codepoint)
            for cp in codepoints:
                e = encode_entity_map.get(cp)
                if e:
                    res.append("&")
                    res.append(e)
                    if not e.endswith(";"):
                        res.append(";")
                else:
                    res.append("&#x%s;" % (hex(cp)[2:]))
            return ("".join(res), exc.end)
        else:
            return xmlcharrefreplace_errors(exc)
Example #13
Source File: serializer.py    From CTFCrackTools-V2 with GNU General Public License v3.0 5 votes vote down vote up 
def htmlentityreplace_errors(exc):
    if isinstance(exc, (UnicodeEncodeError, UnicodeTranslateError)):
        res = []
        codepoints = []
        skip = False
        for i, c in enumerate(exc.object[exc.start:exc.end]):
            if skip:
                skip = False
                continue
            index = i + exc.start
            if _utils.isSurrogatePair(exc.object[index:min([exc.end, index + 2])]):
                codepoint = _utils.surrogatePairToCodepoint(exc.object[index:index + 2])
                skip = True
            else:
                codepoint = ord(c)
            codepoints.append(codepoint)
        for cp in codepoints:
            e = _encode_entity_map.get(cp)
            if e:
                res.append("&")
                res.append(e)
                if not e.endswith(";"):
                    res.append(";")
            else:
                res.append("&#x%s;" % (hex(cp)[2:]))
        return ("".join(res), exc.end)
    else:
        return xmlcharrefreplace_errors(exc)
Example #14
Source File: test_codeccallbacks.py    From CTFCrackTools-V2 with GNU General Public License v3.0 5 votes vote down vote up 
def test_badandgoodxmlcharrefreplaceexceptions(self):
        # "xmlcharrefreplace" complains about a non-exception passed in
        self.assertRaises(
           TypeError,
           codecs.xmlcharrefreplace_errors,
           42
        )
        # "xmlcharrefreplace" complains about the wrong exception types
        self.assertRaises(
           TypeError,
           codecs.xmlcharrefreplace_errors,
           UnicodeError("ouch")
        )
        # "xmlcharrefreplace" can only be used for encoding
        self.assertRaises(
            TypeError,
            codecs.xmlcharrefreplace_errors,
            UnicodeDecodeError("ascii", "\xff", 0, 1, "ouch")
        )
        self.assertRaises(
            TypeError,
            codecs.xmlcharrefreplace_errors,
            UnicodeTranslateError(u"\u3042", 0, 1, "ouch")
        )
        # Use the correct exception
        cs = (0, 1, 9, 10, 99, 100, 999, 1000, 9999, 10000, 0x3042)
        s = "".join(unichr(c) for c in cs)
        self.assertEqual(
            codecs.xmlcharrefreplace_errors(
                UnicodeEncodeError("ascii", s, 0, len(s), "ouch")
            ),
            (u"".join(u"&#%d;" % ord(c) for c in s), len(s))
        )
Example #15
Source File: test_codeccallbacks.py    From CTFCrackTools-V2 with GNU General Public License v3.0 5 votes vote down vote up 
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")
        )
Example #16
Source File: serializer.py    From bazarr with GNU General Public License v3.0 5 votes vote down vote up 
def htmlentityreplace_errors(exc):
    if isinstance(exc, (UnicodeEncodeError, UnicodeTranslateError)):
        res = []
        codepoints = []
        skip = False
        for i, c in enumerate(exc.object[exc.start:exc.end]):
            if skip:
                skip = False
                continue
            index = i + exc.start
            if _utils.isSurrogatePair(exc.object[index:min([exc.end, index + 2])]):
                codepoint = _utils.surrogatePairToCodepoint(exc.object[index:index + 2])
                skip = True
            else:
                codepoint = ord(c)
            codepoints.append(codepoint)
        for cp in codepoints:
            e = _encode_entity_map.get(cp)
            if e:
                res.append("&")
                res.append(e)
                if not e.endswith(";"):
                    res.append(";")
            else:
                res.append("&#x%s;" % (hex(cp)[2:]))
        return ("".join(res), exc.end)
    else:
        return xmlcharrefreplace_errors(exc)
Example #17
Source File: serializer.py    From CogAlg with MIT License 5 votes vote down vote up 
def htmlentityreplace_errors(exc):
    if isinstance(exc, (UnicodeEncodeError, UnicodeTranslateError)):
        res = []
        codepoints = []
        skip = False
        for i, c in enumerate(exc.object[exc.start:exc.end]):
            if skip:
                skip = False
                continue
            index = i + exc.start
            if _utils.isSurrogatePair(exc.object[index:min([exc.end, index + 2])]):
                codepoint = _utils.surrogatePairToCodepoint(exc.object[index:index + 2])
                skip = True
            else:
                codepoint = ord(c)
            codepoints.append(codepoint)
        for cp in codepoints:
            e = _encode_entity_map.get(cp)
            if e:
                res.append("&")
                res.append(e)
                if not e.endswith(";"):
                    res.append(";")
            else:
                res.append("&#x%s;" % (hex(cp)[2:]))
        return ("".join(res), exc.end)
    else:
        return xmlcharrefreplace_errors(exc)
Example #18
Source File: serializer.py    From coffeegrindsize with MIT License 5 votes vote down vote up 
def htmlentityreplace_errors(exc):
    if isinstance(exc, (UnicodeEncodeError, UnicodeTranslateError)):
        res = []
        codepoints = []
        skip = False
        for i, c in enumerate(exc.object[exc.start:exc.end]):
            if skip:
                skip = False
                continue
            index = i + exc.start
            if _utils.isSurrogatePair(exc.object[index:min([exc.end, index + 2])]):
                codepoint = _utils.surrogatePairToCodepoint(exc.object[index:index + 2])
                skip = True
            else:
                codepoint = ord(c)
            codepoints.append(codepoint)
        for cp in codepoints:
            e = _encode_entity_map.get(cp)
            if e:
                res.append("&")
                res.append(e)
                if not e.endswith(";"):
                    res.append(";")
            else:
                res.append("&#x%s;" % (hex(cp)[2:]))
        return ("".join(res), exc.end)
    else:
        return xmlcharrefreplace_errors(exc)
Example #19
Source File: serializer.py    From python2017 with MIT License 5 votes vote down vote up 
def htmlentityreplace_errors(exc):
    if isinstance(exc, (UnicodeEncodeError, UnicodeTranslateError)):
        res = []
        codepoints = []
        skip = False
        for i, c in enumerate(exc.object[exc.start:exc.end]):
            if skip:
                skip = False
                continue
            index = i + exc.start
            if _utils.isSurrogatePair(exc.object[index:min([exc.end, index + 2])]):
                codepoint = _utils.surrogatePairToCodepoint(exc.object[index:index + 2])
                skip = True
            else:
                codepoint = ord(c)
            codepoints.append(codepoint)
        for cp in codepoints:
            e = _encode_entity_map.get(cp)
            if e:
                res.append("&")
                res.append(e)
                if not e.endswith(";"):
                    res.append(";")
            else:
                res.append("&#x%s;" % (hex(cp)[2:]))
        return ("".join(res), exc.end)
    else:
        return xmlcharrefreplace_errors(exc)
Example #20
Source File: htmlserializer.py    From ImageFusion with MIT License 5 votes vote down vote up 
def htmlentityreplace_errors(exc):
        if isinstance(exc, (UnicodeEncodeError, UnicodeTranslateError)):
            res = []
            codepoints = []
            skip = False
            for i, c in enumerate(exc.object[exc.start:exc.end]):
                if skip:
                    skip = False
                    continue
                index = i + exc.start
                if utils.isSurrogatePair(exc.object[index:min([exc.end, index + 2])]):
                    codepoint = utils.surrogatePairToCodepoint(exc.object[index:index + 2])
                    skip = True
                else:
                    codepoint = ord(c)
                codepoints.append(codepoint)
            for cp in codepoints:
                e = encode_entity_map.get(cp)
                if e:
                    res.append("&")
                    res.append(e)
                    if not e.endswith(";"):
                        res.append(";")
                else:
                    res.append("&#x%s;" % (hex(cp)[2:]))
            return ("".join(res), exc.end)
        else:
            return xmlcharrefreplace_errors(exc)
Example #21
Source File: htmlserializer.py    From datafari with Apache License 2.0 5 votes vote down vote up 
def htmlentityreplace_errors(exc):
        if isinstance(exc, (UnicodeEncodeError, UnicodeTranslateError)):
            res = []
            codepoints = []
            skip = False
            for i, c in enumerate(exc.object[exc.start:exc.end]):
                if skip:
                    skip = False
                    continue
                index = i + exc.start
                if utils.isSurrogatePair(exc.object[index:min([exc.end, index + 2])]):
                    codepoint = utils.surrogatePairToCodepoint(exc.object[index:index + 2])
                    skip = True
                else:
                    codepoint = ord(c)
                codepoints.append(codepoint)
            for cp in codepoints:
                e = encode_entity_map.get(cp)
                if e:
                    res.append("&")
                    res.append(e)
                    if not e.endswith(";"):
                        res.append(";")
                else:
                    res.append("&#x%s;" % (hex(cp)[2:]))
            return ("".join(res), exc.end)
        else:
            return xmlcharrefreplace_errors(exc)
Example #22
Source File: serializer.py    From rules_pip with MIT License 5 votes vote down vote up 
def htmlentityreplace_errors(exc):
    if isinstance(exc, (UnicodeEncodeError, UnicodeTranslateError)):
        res = []
        codepoints = []
        skip = False
        for i, c in enumerate(exc.object[exc.start:exc.end]):
            if skip:
                skip = False
                continue
            index = i + exc.start
            if _utils.isSurrogatePair(exc.object[index:min([exc.end, index + 2])]):
                codepoint = _utils.surrogatePairToCodepoint(exc.object[index:index + 2])
                skip = True
            else:
                codepoint = ord(c)
            codepoints.append(codepoint)
        for cp in codepoints:
            e = _encode_entity_map.get(cp)
            if e:
                res.append("&")
                res.append(e)
                if not e.endswith(";"):
                    res.append(";")
            else:
                res.append("&#x%s;" % (hex(cp)[2:]))
        return ("".join(res), exc.end)
    else:
        return xmlcharrefreplace_errors(exc)
Example #23
Source File: htmlserializer.py    From MARA_Framework with GNU Lesser General Public License v3.0 5 votes vote down vote up 
def htmlentityreplace_errors(exc):
        if isinstance(exc, (UnicodeEncodeError, UnicodeTranslateError)):
            res = []
            codepoints = []
            skip = False
            for i, c in enumerate(exc.object[exc.start:exc.end]):
                if skip:
                    skip = False
                    continue
                index = i + exc.start
                if utils.isSurrogatePair(exc.object[index:min([exc.end, index + 2])]):
                    codepoint = utils.surrogatePairToCodepoint(exc.object[index:index + 2])
                    skip = True
                else:
                    codepoint = ord(c)
                codepoints.append(codepoint)
            for cp in codepoints:
                e = encode_entity_map.get(cp)
                if e:
                    res.append("&")
                    res.append(e)
                    if not e.endswith(";"):
                        res.append(";")
                else:
                    res.append("&#x%s;" % (hex(cp)[2:]))
            return ("".join(res), exc.end)
        else:
            return xmlcharrefreplace_errors(exc)
Example #24
Source File: serializer.py    From planespotter with MIT License 5 votes vote down vote up 
def htmlentityreplace_errors(exc):
    if isinstance(exc, (UnicodeEncodeError, UnicodeTranslateError)):
        res = []
        codepoints = []
        skip = False
        for i, c in enumerate(exc.object[exc.start:exc.end]):
            if skip:
                skip = False
                continue
            index = i + exc.start
            if _utils.isSurrogatePair(exc.object[index:min([exc.end, index + 2])]):
                codepoint = _utils.surrogatePairToCodepoint(exc.object[index:index + 2])
                skip = True
            else:
                codepoint = ord(c)
            codepoints.append(codepoint)
        for cp in codepoints:
            e = _encode_entity_map.get(cp)
            if e:
                res.append("&")
                res.append(e)
                if not e.endswith(";"):
                    res.append(";")
            else:
                res.append("&#x%s;" % (hex(cp)[2:]))
        return ("".join(res), exc.end)
    else:
        return xmlcharrefreplace_errors(exc)
Example #25
Source File: serializer.py    From Weapon-Detection-And-Classification with MIT License 5 votes vote down vote up 
def htmlentityreplace_errors(exc):
    if isinstance(exc, (UnicodeEncodeError, UnicodeTranslateError)):
        res = []
        codepoints = []
        skip = False
        for i, c in enumerate(exc.object[exc.start:exc.end]):
            if skip:
                skip = False
                continue
            index = i + exc.start
            if _utils.isSurrogatePair(exc.object[index:min([exc.end, index + 2])]):
                codepoint = _utils.surrogatePairToCodepoint(exc.object[index:index + 2])
                skip = True
            else:
                codepoint = ord(c)
            codepoints.append(codepoint)
        for cp in codepoints:
            e = _encode_entity_map.get(cp)
            if e:
                res.append("&")
                res.append(e)
                if not e.endswith(";"):
                    res.append(";")
            else:
                res.append("&#x%s;" % (hex(cp)[2:]))
        return ("".join(res), exc.end)
    else:
        return xmlcharrefreplace_errors(exc)
Example #26
Source File: htmlserializer.py    From Flask-P2P with MIT License 5 votes vote down vote up 
def htmlentityreplace_errors(exc):
        if isinstance(exc, (UnicodeEncodeError, UnicodeTranslateError)):
            res = []
            codepoints = []
            skip = False
            for i, c in enumerate(exc.object[exc.start:exc.end]):
                if skip:
                    skip = False
                    continue
                index = i + exc.start
                if utils.isSurrogatePair(exc.object[index:min([exc.end, index + 2])]):
                    codepoint = utils.surrogatePairToCodepoint(exc.object[index:index + 2])
                    skip = True
                else:
                    codepoint = ord(c)
                codepoints.append(codepoint)
            for cp in codepoints:
                e = encode_entity_map.get(cp)
                if e:
                    res.append("&")
                    res.append(e)
                    if not e.endswith(";"):
                        res.append(";")
                else:
                    res.append("&#x%s;" % (hex(cp)[2:]))
            return ("".join(res), exc.end)
        else:
            return xmlcharrefreplace_errors(exc)
Example #27
Source File: serializer.py    From python with Apache License 2.0 5 votes vote down vote up 
def htmlentityreplace_errors(exc):
    if isinstance(exc, (UnicodeEncodeError, UnicodeTranslateError)):
        res = []
        codepoints = []
        skip = False
        for i, c in enumerate(exc.object[exc.start:exc.end]):
            if skip:
                skip = False
                continue
            index = i + exc.start
            if _utils.isSurrogatePair(exc.object[index:min([exc.end, index + 2])]):
                codepoint = _utils.surrogatePairToCodepoint(exc.object[index:index + 2])
                skip = True
            else:
                codepoint = ord(c)
            codepoints.append(codepoint)
        for cp in codepoints:
            e = _encode_entity_map.get(cp)
            if e:
                res.append("&")
                res.append(e)
                if not e.endswith(";"):
                    res.append(";")
            else:
                res.append("&#x%s;" % (hex(cp)[2:]))
        return ("".join(res), exc.end)
    else:
        return xmlcharrefreplace_errors(exc)
Example #28
Source File: htmlserializer.py    From Financial-Portfolio-Flask with MIT License 5 votes vote down vote up 
def htmlentityreplace_errors(exc):
        if isinstance(exc, (UnicodeEncodeError, UnicodeTranslateError)):
            res = []
            codepoints = []
            skip = False
            for i, c in enumerate(exc.object[exc.start:exc.end]):
                if skip:
                    skip = False
                    continue
                index = i + exc.start
                if utils.isSurrogatePair(exc.object[index:min([exc.end, index + 2])]):
                    codepoint = utils.surrogatePairToCodepoint(exc.object[index:index + 2])
                    skip = True
                else:
                    codepoint = ord(c)
                codepoints.append(codepoint)
            for cp in codepoints:
                e = encode_entity_map.get(cp)
                if e:
                    res.append("&")
                    res.append(e)
                    if not e.endswith(";"):
                        res.append(";")
                else:
                    res.append("&#x%s;" % (hex(cp)[2:]))
            return ("".join(res), exc.end)
        else:
            return xmlcharrefreplace_errors(exc)
Example #29
Source File: serializer.py    From Hands-On-Application-Development-with-PyCharm with MIT License 5 votes vote down vote up 
def htmlentityreplace_errors(exc):
    if isinstance(exc, (UnicodeEncodeError, UnicodeTranslateError)):
        res = []
        codepoints = []
        skip = False
        for i, c in enumerate(exc.object[exc.start:exc.end]):
            if skip:
                skip = False
                continue
            index = i + exc.start
            if _utils.isSurrogatePair(exc.object[index:min([exc.end, index + 2])]):
                codepoint = _utils.surrogatePairToCodepoint(exc.object[index:index + 2])
                skip = True
            else:
                codepoint = ord(c)
            codepoints.append(codepoint)
        for cp in codepoints:
            e = _encode_entity_map.get(cp)
            if e:
                res.append("&")
                res.append(e)
                if not e.endswith(";"):
                    res.append(";")
            else:
                res.append("&#x%s;" % (hex(cp)[2:]))
        return ("".join(res), exc.end)
    else:
        return xmlcharrefreplace_errors(exc)
Example #30
Source File: test_codeccallbacks.py    From ironpython3 with Apache License 2.0 5 votes vote down vote up 
def test_xmlcharrefvalues(self):
        # enhance coverage of:
        # Python/codecs.c::PyCodec_XMLCharRefReplaceErrors()
        # and inline implementations
        v = (1, 5, 10, 50, 100, 500, 1000, 5000, 10000, 50000, 100000,
             500000, 1000000)
        s = "".join([chr(x) for x in v])
        codecs.register_error("test.xmlcharrefreplace", codecs.xmlcharrefreplace_errors)
        for enc in ("ascii", "iso-8859-15"):
            for err in ("xmlcharrefreplace", "test.xmlcharrefreplace"):
                s.encode(enc, err)