Python errors.HeaderParseError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 HeaderParseError [as 别名]
def parse_docstring(docstring):
    """
    Parse out the parts of a docstring.  Return (title, body, metadata).
    """
    docstring = trim_docstring(docstring)
    parts = re.split(r'\n{2,}', docstring)
    title = parts[0]
    if len(parts) == 1:
        body = ''
        metadata = {}
    else:
        parser = HeaderParser()
        try:
            metadata = parser.parsestr(parts[-1])
        except HeaderParseError:
            metadata = {}
            body = "\n\n".join(parts[1:])
        else:
            metadata = dict(metadata.items())
            if metadata:
                body = "\n\n".join(parts[1:-1])
            else:
                body = "\n\n".join(parts[1:])
    return title, body, metadata 

# 需要导入模块: from email import errors [as 别名]
# 或者: from email.errors import HeaderParseError [as 别名]
def test_set_boundary(self):
        eq = self.assertEqual
        # This one has no existing boundary parameter, but the Content-Type:
        # header appears fifth.
        msg = self._msgobj('msg_01.txt')
        msg.set_boundary('BOUNDARY')
        header, value = msg.items()[4]
        eq(header.lower(), 'content-type')
        eq(value, 'text/plain; charset="us-ascii"; boundary="BOUNDARY"')
        # This one has a Content-Type: header, with a boundary, stuck in the
        # middle of its headers.  Make sure the order is preserved; it should
        # be fifth.
        msg = self._msgobj('msg_04.txt')
        msg.set_boundary('BOUNDARY')
        header, value = msg.items()[4]
        eq(header.lower(), 'content-type')
        eq(value, 'multipart/mixed; boundary="BOUNDARY"')
        # And this one has no Content-Type: header at all.
        msg = self._msgobj('msg_03.txt')
        self.assertRaises(errors.HeaderParseError,
                          msg.set_boundary, 'BOUNDARY') 

# 需要导入模块: from email import errors [as 别名]
# 或者: from email.errors import HeaderParseError [as 别名]
def get_dot_atom_text(value):
    """ dot-text = 1*atext *("." 1*atext)

    """
    dot_atom_text = DotAtomText()
    if not value or value[0] in ATOM_ENDS:
        raise errors.HeaderParseError("expected atom at a start of "
            "dot-atom-text but found '{}'".format(value))
    while value and value[0] not in ATOM_ENDS:
        token, value = get_atext(value)
        dot_atom_text.append(token)
        if value and value[0] == '.':
            dot_atom_text.append(DOT)
            value = value[1:]
    if dot_atom_text[-1] is DOT:
        raise errors.HeaderParseError("expected atom at end of dot-atom-text "
            "but found '{}'".format('.'+value))
    return dot_atom_text, value 

# 需要导入模块: from email import errors [as 别名]
# 或者: from email.errors import HeaderParseError [as 别名]
def get_dot_atom(value):
    """ dot-atom = [CFWS] dot-atom-text [CFWS]

    Any place we can have a dot atom, we could instead have an rfc2047 encoded
    word.
    """
    dot_atom = DotAtom()
    if value[0] in CFWS_LEADER:
        token, value = get_cfws(value)
        dot_atom.append(token)
    if value.startswith('=?'):
        try:
            token, value = get_encoded_word(value)
        except errors.HeaderParseError:
            # XXX: need to figure out how to register defects when
            # appropriate here.
            token, value = get_dot_atom_text(value)
    else:
        token, value = get_dot_atom_text(value)
    dot_atom.append(token)
    if value and value[0] in CFWS_LEADER:
        token, value = get_cfws(value)
        dot_atom.append(token)
    return dot_atom, value 

# 需要导入模块: from email import errors [as 别名]
# 或者: from email.errors import HeaderParseError [as 别名]
def get_mailbox(value):
    """ mailbox = name-addr / addr-spec

    """
    # The only way to figure out if we are dealing with a name-addr or an
    # addr-spec is to try parsing each one.
    mailbox = Mailbox()
    try:
        token, value = get_name_addr(value)
    except errors.HeaderParseError:
        try:
            token, value = get_addr_spec(value)
        except errors.HeaderParseError:
            raise errors.HeaderParseError(
                "expected mailbox but found '{}'".format(value))
    if any(isinstance(x, errors.InvalidHeaderDefect)
                       for x in token.all_defects):
        mailbox.token_type = 'invalid-mailbox'
    mailbox.append(token)
    return mailbox, value 

# 需要导入模块: from email import errors [as 别名]
# 或者: from email.errors import HeaderParseError [as 别名]
def get_token(value):
    """token = [CFWS] 1*ttext [CFWS]

    The RFC equivalent of ttext is any US-ASCII chars except space, ctls, or
    tspecials.  We also exclude tabs even though the RFC doesn't.

    The RFC implies the CFWS but is not explicit about it in the BNF.

    """
    mtoken = Token()
    if value and value[0] in CFWS_LEADER:
        token, value = get_cfws(value)
        mtoken.append(token)
    if value and value[0] in TOKEN_ENDS:
        raise errors.HeaderParseError(
            "expected token but found '{}'".format(value))
    token, value = get_ttext(value)
    mtoken.append(token)
    if value and value[0] in CFWS_LEADER:
        token, value = get_cfws(value)
        mtoken.append(token)
    return mtoken, value 

# 需要导入模块: from email import errors [as 别名]
# 或者: from email.errors import HeaderParseError [as 别名]
def get_attrtext(value):
    """attrtext = 1*(any non-ATTRIBUTE_ENDS character)

    We allow any non-ATTRIBUTE_ENDS in attrtext, but add defects to the
    token's defects list if we find non-attrtext characters.  We also register
    defects for *any* non-printables even though the RFC doesn't exclude all of
    them, because we follow the spirit of RFC 5322.

    """
    m = _non_attribute_end_matcher(value)
    if not m:
        raise errors.HeaderParseError(
            "expected attrtext but found {!r}".format(value))
    attrtext = m.group()
    value = value[len(attrtext):]
    attrtext = ValueTerminal(attrtext, 'attrtext')
    _validate_xtext(attrtext)
    return attrtext, value 

# 需要导入模块: from email import errors [as 别名]
# 或者: from email.errors import HeaderParseError [as 别名]
def get_attribute(value):
    """ [CFWS] 1*attrtext [CFWS]

    This version of the BNF makes the CFWS explicit, and as usual we use a
    value terminal for the actual run of characters.  The RFC equivalent of
    attrtext is the token characters, with the subtraction of '*', "'", and '%'.
    We include tab in the excluded set just as we do for token.

    """
    attribute = Attribute()
    if value and value[0] in CFWS_LEADER:
        token, value = get_cfws(value)
        attribute.append(token)
    if value and value[0] in ATTRIBUTE_ENDS:
        raise errors.HeaderParseError(
            "expected token but found '{}'".format(value))
    token, value = get_attrtext(value)
    attribute.append(token)
    if value and value[0] in CFWS_LEADER:
        token, value = get_cfws(value)
        attribute.append(token)
    return attribute, value 

# 需要导入模块: from email import errors [as 别名]
# 或者: from email.errors import HeaderParseError [as 别名]
def get_extended_attrtext(value):
    """attrtext = 1*(any non-ATTRIBUTE_ENDS character plus '%')

    This is a special parsing routine so that we get a value that
    includes % escapes as a single string (which we decode as a single
    string later).

    """
    m = _non_extended_attribute_end_matcher(value)
    if not m:
        raise errors.HeaderParseError(
            "expected extended attrtext but found {!r}".format(value))
    attrtext = m.group()
    value = value[len(attrtext):]
    attrtext = ValueTerminal(attrtext, 'extended-attrtext')
    _validate_xtext(attrtext)
    return attrtext, value 

# 需要导入模块: from email import errors [as 别名]
# 或者: from email.errors import HeaderParseError [as 别名]
def get_extended_attribute(value):
    """ [CFWS] 1*extended_attrtext [CFWS]

    This is like the non-extended version except we allow % characters, so that
    we can pick up an encoded value as a single string.

    """
    # XXX: should we have an ExtendedAttribute TokenList?
    attribute = Attribute()
    if value and value[0] in CFWS_LEADER:
        token, value = get_cfws(value)
        attribute.append(token)
    if value and value[0] in EXTENDED_ATTRIBUTE_ENDS:
        raise errors.HeaderParseError(
            "expected token but found '{}'".format(value))
    token, value = get_extended_attrtext(value)
    attribute.append(token)
    if value and value[0] in CFWS_LEADER:
        token, value = get_cfws(value)
        attribute.append(token)
    return attribute, value 

# 需要导入模块: from email import errors [as 别名]
# 或者: from email.errors import HeaderParseError [as 别名]
def get_value(value):
    """ quoted-string / attribute

    """
    v = Value()
    if not value:
        raise errors.HeaderParseError("Expected value but found end of string")
    leader = None
    if value[0] in CFWS_LEADER:
        leader, value = get_cfws(value)
    if not value:
        raise errors.HeaderParseError("Expected value but found "
                                      "only {}".format(leader))
    if value[0] == '"':
        token, value = get_quoted_string(value)
    else:
        token, value = get_extended_attribute(value)
    if leader is not None:
        token[:0] = [leader]
    v.append(token)
    return v, value 

# 需要导入模块: from email import errors [as 别名]
# 或者: from email.errors import HeaderParseError [as 别名]
def encode(self, splitchars=';, '):
        """Encode a message header into an RFC-compliant format.

        There are many issues involved in converting a given string for use in
        an email header.  Only certain character sets are readable in most
        email clients, and as header strings can only contain a subset of
        7-bit ASCII, care must be taken to properly convert and encode (with
        Base64 or quoted-printable) header strings.  In addition, there is a
        75-character length limit on any given encoded header field, so
        line-wrapping must be performed, even with double-byte character sets.

        This method will do its best to convert the string to the correct
        character set used in email, and encode and line wrap it safely with
        the appropriate scheme for that character set.

        If the given charset is not known or an error occurs during
        conversion, this function will return the header untouched.

        Optional splitchars is a string containing characters to split long
        ASCII lines on, in rough support of RFC 2822's `highest level
        syntactic breaks'.  This doesn't affect RFC 2047 encoded lines.
        """
        newchunks = []
        maxlinelen = self._firstlinelen
        lastlen = 0
        for s, charset in self._chunks:
            # The first bit of the next chunk should be just long enough to
            # fill the next line.  Don't forget the space separating the
            # encoded words.
            targetlen = maxlinelen - lastlen - 1
            if targetlen < charset.encoded_header_len(''):
                # Stick it on the next line
                targetlen = maxlinelen
            newchunks += self._split(s, charset, targetlen, splitchars)
            lastchunk, lastcharset = newchunks[-1]
            lastlen = lastcharset.encoded_header_len(lastchunk)
        value = self._encode_chunks(newchunks, maxlinelen)
        if _embeded_header.search(value):
            raise HeaderParseError("header value appears to contain "
                "an embedded header: {!r}".format(value))
        return value 

# 需要导入模块: from email import errors [as 别名]
# 或者: from email.errors import HeaderParseError [as 别名]
def test_broken_base64_header(self):
        raises = self.assertRaises
        s = 'Subject: =?EUC-KR?B?CSixpLDtKSC/7Liuvsax4iC6uLmwMcijIKHaILzSwd/H0SC8+LCjwLsgv7W/+Mj3I ?='
        raises(errors.HeaderParseError, decode_header, s)



# Test RFC 2231 header parameters (en/de)coding 

# 需要导入模块: from email import errors [as 别名]
# 或者: from email.errors import HeaderParseError [as 别名]
def get_encoded_word(value):
    """ encoded-word = "=?" charset "?" encoding "?" encoded-text "?="

    """
    ew = EncodedWord()
    if not value.startswith('=?'):
        raise errors.HeaderParseError(
            "expected encoded word but found {}".format(value))
    tok, *remainder = value[2:].split('?=', 1)
    if tok == value[2:]:
        raise errors.HeaderParseError(
            "expected encoded word but found {}".format(value))
    remstr = ''.join(remainder)
    if len(remstr) > 1 and remstr[0] in hexdigits and remstr[1] in hexdigits:
        # The ? after the CTE was followed by an encoded word escape (=XX).
        rest, *remainder = remstr.split('?=', 1)
        tok = tok + '?=' + rest
    if len(tok.split()) > 1:
        ew.defects.append(errors.InvalidHeaderDefect(
            "whitespace inside encoded word"))
    ew.cte = value
    value = ''.join(remainder)
    try:
        text, charset, lang, defects = _ew.decode('=?' + tok + '?=')
    except ValueError:
        raise errors.HeaderParseError(
            "encoded word format invalid: '{}'".format(ew.cte))
    ew.charset = charset
    ew.lang = lang
    ew.defects.extend(defects)
    while text:
        if text[0] in WSP:
            token, text = get_fws(text)
            ew.append(token)
            continue
        chars, *remainder = _wsp_splitter(text, 1)
        vtext = ValueTerminal(chars, 'vtext')
        _validate_xtext(vtext)
        ew.append(vtext)
        text = ''.join(remainder)
    return ew, value 

# 需要导入模块: from email import errors [as 别名]
# 或者: from email.errors import HeaderParseError [as 别名]
def get_atext(value):
    """atext = <matches _atext_matcher>

    We allow any non-ATOM_ENDS in atext, but add an InvalidATextDefect to
    the token's defects list if we find non-atext characters.
    """
    m = _non_atom_end_matcher(value)
    if not m:
        raise errors.HeaderParseError(
            "expected atext but found '{}'".format(value))
    atext = m.group()
    value = value[len(atext):]
    atext = ValueTerminal(atext, 'atext')
    _validate_xtext(atext)
    return atext, value