Python errors.UndecodableBytesDefect方法代码示例

# 需要导入模块: from email import errors [as 别名]
# 或者: from email.errors import UndecodableBytesDefect [as 别名]
def decode(ew):
    """Decode encoded word and return (string, charset, lang, defects) tuple.

    An RFC 2047/2243 encoded word has the form:

        =?charset*lang?cte?encoded_string?=

    where '*lang' may be omitted but the other parts may not be.

    This function expects exactly such a string (that is, it does not check the
    syntax and may raise errors if the string is not well formed), and returns
    the encoded_string decoded first from its Content Transfer Encoding and
    then from the resulting bytes into unicode using the specified charset.  If
    the cte-decoded string does not successfully decode using the specified
    character set, a defect is added to the defects list and the unknown octets
    are replaced by the unicode 'unknown' character \\uFDFF.

    The specified charset and language are returned.  The default for language,
    which is rarely if ever encountered, is the empty string.

    """
    _, charset, cte, cte_string, _ = ew.split('?')
    charset, _, lang = charset.partition('*')
    cte = cte.lower()
    # Recover the original bytes and do CTE decoding.
    bstring = cte_string.encode('ascii', 'surrogateescape')
    bstring, defects = _cte_decoders[cte](bstring)
    # Turn the CTE decoded bytes into unicode.
    try:
        string = bstring.decode(charset)
    except UnicodeError:
        defects.append(errors.UndecodableBytesDefect("Encoded word "
            "contains bytes not decodable using {} charset".format(charset)))
        string = bstring.decode(charset, 'surrogateescape')
    except LookupError:
        string = bstring.decode('ascii', 'surrogateescape')
        if charset.lower() != 'unknown-8bit':
            defects.append(errors.CharsetError("Unknown charset {} "
                "in encoded word; decoded as unknown bytes".format(charset)))
    return string, charset, lang, defects 

# 需要导入模块: from email import errors [as 别名]
# 或者: from email.errors import UndecodableBytesDefect [as 别名]
def _fold(self, folded):
        encoding = 'utf-8' if folded.policy.utf8 else 'ascii'
        for part in self.parts:
            tstr = str(part)
            tlen = len(tstr)
            try:
                str(part).encode(encoding)
            except UnicodeEncodeError:
                if any(isinstance(x, errors.UndecodableBytesDefect)
                        for x in part.all_defects):
                    charset = 'unknown-8bit'
                else:
                    # XXX: this should be a policy setting when utf8 is False.
                    charset = 'utf-8'
                tstr = part.cte_encode(charset, folded.policy)
                tlen = len(tstr)
            if folded.append_if_fits(part, tstr):
                continue
            # Peel off the leading whitespace if any and make it sticky, to
            # avoid infinite recursion.
            ws = part.pop_leading_fws()
            if ws is not None:
                # Peel off the leading whitespace and make it sticky, to
                # avoid infinite recursion.
                folded.stickyspace = str(part.pop(0))
                if folded.append_if_fits(part):
                    continue
            if part.has_fws:
                part._fold(folded)
                continue
            # There are no fold points in this one; it is too long for a single
            # line and can't be split...we just have to put it on its own line.
            folded.append(tstr)
            folded.newline() 

# 需要导入模块: from email import errors [as 别名]
# 或者: from email.errors import UndecodableBytesDefect [as 别名]
def _validate_xtext(xtext):
    """If input token contains ASCII non-printables, register a defect."""

    non_printables = _non_printable_finder(xtext)
    if non_printables:
        xtext.defects.append(errors.NonPrintableDefect(non_printables))
    if utils._has_surrogates(xtext):
        xtext.defects.append(errors.UndecodableBytesDefect(
            "Non-ASCII characters found in header token")) 

# 需要导入模块: from email import errors [as 别名]
# 或者: from email.errors import UndecodableBytesDefect [as 别名]
def test_q_escaped_bytes_preserved(self):
        self._test(b'=?us-ascii?q?=20\xACfoo?='.decode('us-ascii',
                                                       'surrogateescape'),
                   ' \uDCACfoo',
                   defects = [errors.UndecodableBytesDefect]) 

# 需要导入模块: from email import errors [as 别名]
# 或者: from email.errors import UndecodableBytesDefect [as 别名]
def test_get_unstructured_undecodable_bytes(self):
        self._test_get_x(self._get_unst,
            b'test \xACfoo  val'.decode('ascii', 'surrogateescape'),
            'test \uDCACfoo  val',
            'test \uDCACfoo val',
            [errors.UndecodableBytesDefect],
            '') 

# 需要导入模块: from email import errors [as 别名]
# 或者: from email.errors import UndecodableBytesDefect [as 别名]
def test_get_unstructured_undecodable_bytes_in_EW(self):
        self._test_get_x(self._get_unst,
            (b'=?us-ascii?q?=20test?=   =?us-ascii?q?=20\xACfoo?='
                b'  val').decode('ascii', 'surrogateescape'),
            ' test \uDCACfoo  val',
            ' test \uDCACfoo val',
            [errors.UndecodableBytesDefect]*2,
            '') 

# 需要导入模块: from email import errors [as 别名]
# 或者: from email.errors import UndecodableBytesDefect [as 别名]
def _fold(self, folded):
        for part in self.parts:
            tstr = str(part)
            tlen = len(tstr)
            try:
                str(part).encode('us-ascii')
            except UnicodeEncodeError:
                if any(isinstance(x, errors.UndecodableBytesDefect)
                        for x in part.all_defects):
                    charset = 'unknown-8bit'
                else:
                    # XXX: this should be a policy setting
                    charset = 'utf-8'
                tstr = part.cte_encode(charset, folded.policy)
                tlen = len(tstr)
            if folded.append_if_fits(part, tstr):
                continue
            # Peel off the leading whitespace if any and make it sticky, to
            # avoid infinite recursion.
            ws = part.pop_leading_fws()
            if ws is not None:
                # Peel off the leading whitespace and make it sticky, to
                # avoid infinite recursion.
                folded.stickyspace = str(part.pop(0))
                if folded.append_if_fits(part):
                    continue
            if part.has_fws:
                part._fold(folded)
                continue
            # There are no fold points in this one; it is too long for a single
            # line and can't be split...we just have to put it on its own line.
            folded.append(tstr)
            folded.newline() 

# 需要导入模块: from email import errors [as 别名]
# 或者: from email.errors import UndecodableBytesDefect [as 别名]
def test_undecodable_bytes_error_preserved(self):
        badstr = b"le pouf c\xaflebre".decode('ascii', 'surrogateescape')
        unst = parser.get_unstructured(badstr)
        self.assertDefectsEqual(unst.all_defects, [errors.UndecodableBytesDefect])
        parts = list(unst.parts)
        self.assertDefectsEqual(parts[0].all_defects, [])
        self.assertDefectsEqual(parts[1].all_defects, [])
        self.assertDefectsEqual(parts[2].all_defects, [errors.UndecodableBytesDefect]) 

# 需要导入模块: from email import errors [as 别名]
# 或者: from email.errors import UndecodableBytesDefect [as 别名]
def _fold(self, folded):
        encoding = 'utf-8' if folded.policy.utf8 else 'ascii'
        for part in self.parts:
            tstr = str(part)
            tlen = len(tstr)
            try:
                str(part).encode(encoding)
            except UnicodeEncodeError:
                if any(isinstance(x, errors.UndecodableBytesDefect)
                        for x in part.all_defects):
                    charset = 'unknown-8bit'
                else:
                    # XXX: this should be a policy setting when utf8 is False.
                    charset = 'utf-8'
                tstr = part.cte_encode(charset, folded.policy)
                tlen = len(tstr)
            if folded.append_if_fits(part, tstr):
                continue
            # Peel off the leading whitespace if any and make it sticky, to
            # avoid infinite recursion.
            ws = part.pop_leading_fws()
            if ws is not None:
                folded.stickyspace = str(ws)
                if folded.append_if_fits(part):
                    continue
            if part.has_fws:
                part._fold(folded)
                continue
            # There are no fold points in this one; it is too long for a single
            # line and can't be split...we just have to put it on its own line.
            folded.append(tstr)
            folded.newline()