def decode_payload(self, encoding, payload):
"""
Decode attachment payload data.
:param encoding:
The current encoding of the payload data.
:param payload:
the payload data
"""
cte = encoding.lower()
if cte == 'quoted-printable':
return utils._qdecode(payload)
elif cte == 'base64':
try:
return utils._bdecode(payload)
except binascii.Error:
# Incorrect padding
return payload
elif cte in ('x-uuencode', 'uuencode', 'uue', 'x-uue'):
sfp = StringIO()
try:
uu.decode(StringIO(payload + '\n'), sfp, quiet=True)
payload = sfp.getvalue()
except uu.Error:
# Some decoding problem
return payload
def get_payload(self, i=None, decode=False):
if i is None:
payload = self._payload
elif not isinstance(self._payload, list):
raise TypeError('Expected list, got %s' % type(self._payload))
else:
payload = self._payload[i]
if decode:
if self.is_multipart():
return
cte = self.get('content-transfer-encoding', '').lower()
if cte == 'quoted-printable':
return utils._qdecode(payload)
if cte == 'base64':
try:
return utils._bdecode(payload)
except binascii.Error:
return payload
elif cte in ('x-uuencode', 'uuencode', 'uue', 'x-uue'):
sfp = StringIO()
try:
uu.decode(StringIO(payload + '\n'), sfp, quiet=True)
payload = sfp.getvalue()
except uu.Error:
return payload
return payload
def get_payload(self, i = None, decode = False):
if i is None:
payload = self._payload
elif not isinstance(self._payload, list):
raise TypeError('Expected list, got %s' % type(self._payload))
else:
payload = self._payload[i]
if decode:
if self.is_multipart():
return
cte = self.get('content-transfer-encoding', '').lower()
if cte == 'quoted-printable':
return utils._qdecode(payload)
if cte == 'base64':
try:
return utils._bdecode(payload)
except binascii.Error:
return payload
elif cte in ('x-uuencode', 'uuencode', 'uue', 'x-uue'):
sfp = StringIO()
try:
uu.decode(StringIO(payload + '\n'), sfp, quiet=True)
payload = sfp.getvalue()
except uu.Error:
return payload
return payload
def get_payload(self, i=None, decode=False):
"""Return a reference to the payload.
The payload will either be a list object or a string. If you mutate
the list object, you modify the message's payload in place. Optional
i returns that index into the payload.
Optional decode is a flag indicating whether the payload should be
decoded or not, according to the Content-Transfer-Encoding header
(default is False).
When True and the message is not a multipart, the payload will be
decoded if this header's value is `quoted-printable' or `base64'. If
some other encoding is used, or the header is missing, or if the
payload has bogus data (i.e. bogus base64 or uuencoded data), the
payload is returned as-is.
If the message is a multipart and the decode flag is True, then None
is returned.
"""
if i is None:
payload = self._payload
elif not isinstance(self._payload, list):
raise TypeError('Expected list, got %s' % type(self._payload))
else:
payload = self._payload[i]
if not decode:
return payload
# Decoded payloads always return bytes. XXX split this part out into
# a new method called .get_decoded_payload().
if self.is_multipart():
return None
cte = self.get('content-transfer-encoding', '').lower()
if cte == 'quoted-printable':
return utils._qdecode(payload)
elif cte == 'base64':
try:
if isinstance(payload, str):
payload = payload.encode('raw-unicode-escape')
return base64.b64decode(payload)
#return utils._bdecode(payload)
except binascii.Error:
# Incorrect padding
pass
elif cte in ('x-uuencode', 'uuencode', 'uue', 'x-uue'):
in_file = BytesIO(payload.encode('raw-unicode-escape'))
out_file = BytesIO()
try:
uu.decode(in_file, out_file, quiet=True)
return out_file.getvalue()
except uu.Error:
# Some decoding problem
pass
# Is there a better way to do this? We can't use the bytes
# constructor.
if isinstance(payload, str):
return payload.encode('raw-unicode-escape')
return payload
def get_payload(self, i=None, decode=False):
"""Return a reference to the payload.
The payload will either be a list object or a string. If you mutate
the list object, you modify the message's payload in place. Optional
i returns that index into the payload.
Optional decode is a flag indicating whether the payload should be
decoded or not, according to the Content-Transfer-Encoding header
(default is False).
When True and the message is not a multipart, the payload will be
decoded if this header's value is `quoted-printable' or `base64'. If
some other encoding is used, or the header is missing, or if the
payload has bogus data (i.e. bogus base64 or uuencoded data), the
payload is returned as-is.
If the message is a multipart and the decode flag is True, then None
is returned.
"""
if i is None:
payload = self._payload
elif not isinstance(self._payload, list):
raise TypeError('Expected list, got %s' % type(self._payload))
else:
payload = self._payload[i]
if not decode:
return payload
# Decoded payloads always return bytes. XXX split this part out into
# a new method called .get_decoded_payload().
if self.is_multipart():
return None
cte = self.get('content-transfer-encoding', '').lower()
if cte == 'quoted-printable':
return utils._qdecode(payload)
elif cte == 'base64':
try:
if isinstance(payload, str):
payload = payload.encode('raw-unicode-escape')
return base64.b64decode(payload)
#return utils._bdecode(payload)
except binascii.Error:
# Incorrect padding
pass
elif cte in ('x-uuencode', 'uuencode', 'uue', 'x-uue'):
in_file = BytesIO(payload.encode('raw-unicode-escape'))
out_file = BytesIO()
try:
uu.decode(in_file, out_file, quiet=True)
return out_file.getvalue()
except uu.Error:
# Some decoding problem
pass
# Is there a better way to do this? We can't use the bytes
# constructor.
if isinstance(payload, str):
return payload.encode('raw-unicode-escape')
return payload
def get_payload(self, i=None, decode=False):
if self.is_multipart():
if decode:
return
if i is None:
return self._payload
return self._payload[i]
if i is not None and not isinstance(self._payload, list):
raise TypeError('Expected list, got %s' % type(self._payload))
payload = self._payload
cte = str(self.get('content-transfer-encoding', '')).lower()
if isinstance(payload, str):
if utils._has_surrogates(payload):
bpayload = payload.encode('ascii', 'surrogateescape')
if not decode:
try:
payload = bpayload.decode(
self.get_param('charset', 'ascii'), 'replace')
except LookupError:
payload = bpayload.decode('ascii', 'replace')
if decode:
try:
bpayload = payload.encode('ascii')
except UnicodeError:
bpayload = payload.encode('raw-unicode-escape')
elif decode:
try:
bpayload = payload.encode('ascii')
except UnicodeError:
bpayload = payload.encode('raw-unicode-escape')
if not decode:
return payload
if cte == 'quoted-printable':
return utils._qdecode(bpayload)
if cte == 'base64':
(value, defects) = decode_b(b''.join(bpayload.splitlines()))
for defect in defects:
self.policy.handle_defect(self, defect)
return value
if cte in ('x-uuencode', 'uuencode', 'uue', 'x-uue'):
in_file = BytesIO(bpayload)
out_file = BytesIO()
try:
uu.decode(in_file, out_file, quiet=True)
return out_file.getvalue()
except uu.Error:
return bpayload
if isinstance(payload, str):
return bpayload
return payload
def get_payload(self, i=None, decode=False):
"""Return a reference to the payload.
The payload will either be a list object or a string. If you mutate
the list object, you modify the message's payload in place. Optional
i returns that index into the payload.
Optional decode is a flag indicating whether the payload should be
decoded or not, according to the Content-Transfer-Encoding header
(default is False).
When True and the message is not a multipart, the payload will be
decoded if this header's value is `quoted-printable' or `base64'. If
some other encoding is used, or the header is missing, or if the
payload has bogus data (i.e. bogus base64 or uuencoded data), the
payload is returned as-is.
If the message is a multipart and the decode flag is True, then None
is returned.
"""
if i is None:
payload = self._payload
elif not isinstance(self._payload, list):
raise TypeError('Expected list, got %s' % type(self._payload))
else:
payload = self._payload[i]
if decode:
if self.is_multipart():
return None
cte = self.get('content-transfer-encoding', '').lower()
if cte == 'quoted-printable':
return utils._qdecode(payload)
elif cte == 'base64':
try:
return utils._bdecode(payload)
except binascii.Error:
# Incorrect padding
return payload
elif cte in ('x-uuencode', 'uuencode', 'uue', 'x-uue'):
sfp = StringIO()
try:
uu.decode(StringIO(payload+'\n'), sfp, quiet=True)
payload = sfp.getvalue()
except uu.Error:
# Some decoding problem
return payload
# Everything else, including encodings with 8bit or 7bit are returned
# unchanged.
return payload
def get_payload(self, i=None, decode=False):
"""Return a reference to the payload.
The payload will either be a list object or a string. If you mutate
the list object, you modify the message's payload in place. Optional
i returns that index into the payload.
Optional decode is a flag indicating whether the payload should be
decoded or not, according to the Content-Transfer-Encoding header
(default is False).
When True and the message is not a multipart, the payload will be
decoded if this header's value is `quoted-printable' or `base64'. If
some other encoding is used, or the header is missing, or if the
payload has bogus data (i.e. bogus base64 or uuencoded data), the
payload is returned as-is.
If the message is a multipart and the decode flag is True, then None
is returned.
"""
if i is None:
payload = self._payload
elif not isinstance(self._payload, list):
raise TypeError("Expected list, got %s" % type(self._payload))
else:
payload = self._payload[i]
if decode:
if self.is_multipart():
return None
cte = self.get("content-transfer-encoding", "").lower()
if cte == "quoted-printable":
return utils._qdecode(payload)
elif cte == "base64":
try:
return utils._bdecode(payload)
except binascii.Error:
# Incorrect padding
return payload
elif cte in ("x-uuencode", "uuencode", "uue", "x-uue"):
sfp = StringIO()
try:
uu.decode(StringIO(payload + "\n"), sfp, quiet=True)
payload = sfp.getvalue()
except uu.Error:
# Some decoding problem
return payload
# Everything else, including encodings with 8bit or 7bit are returned
# unchanged.
return payload
def get_payload(self, i=None, decode=False):
if self.is_multipart():
if decode:
return
if i is None:
return self._payload
return self._payload[i]
if i is not None and not isinstance(self._payload, list):
raise TypeError('Expected list, got %s' % type(self._payload))
payload = self._payload
cte = str(self.get('content-transfer-encoding', '')).lower()
if isinstance(payload, str):
if utils._has_surrogates(payload):
bpayload = payload.encode('ascii', 'surrogateescape')
if not decode:
try:
payload = bpayload.decode(self.get_param('charset', 'ascii'), 'replace')
except LookupError:
payload = bpayload.decode('ascii', 'replace')
if decode:
try:
bpayload = payload.encode('ascii')
except UnicodeError:
bpayload = payload.encode('raw-unicode-escape')
elif decode:
try:
bpayload = payload.encode('ascii')
except UnicodeError:
bpayload = payload.encode('raw-unicode-escape')
if not decode:
return payload
if cte == 'quoted-printable':
return utils._qdecode(bpayload)
if cte == 'base64':
(value, defects) = decode_b(b''.join(bpayload.splitlines()))
for defect in defects:
self.policy.handle_defect(self, defect)
return value
if cte in ('x-uuencode', 'uuencode', 'uue', 'x-uue'):
in_file = BytesIO(bpayload)
out_file = BytesIO()
try:
uu.decode(in_file, out_file, quiet=True)
return out_file.getvalue()
except uu.Error:
return bpayload
if isinstance(payload, str):
return bpayload
return payload
def get_payload(self, i = None, decode = False):
"""Return a reference to the payload.
The payload will either be a list object or a string. If you mutate
the list object, you modify the message's payload in place. Optional
i returns that index into the payload.
Optional decode is a flag indicating whether the payload should be
decoded or not, according to the Content-Transfer-Encoding header
(default is False).
When True and the message is not a multipart, the payload will be
decoded if this header's value is `quoted-printable' or `base64'. If
some other encoding is used, or the header is missing, or if the
payload has bogus data (i.e. bogus base64 or uuencoded data), the
payload is returned as-is.
If the message is a multipart and the decode flag is True, then None
is returned.
"""
if i is None:
payload = self._payload
elif not isinstance(self._payload, list):
raise TypeError('Expected list, got %s' % type(self._payload))
else:
payload = self._payload[i]
if decode:
if self.is_multipart():
return
cte = self.get('content-transfer-encoding', '').lower()
if cte == 'quoted-printable':
return utils._qdecode(payload)
if cte == 'base64':
try:
return utils._bdecode(payload)
except binascii.Error:
return payload
elif cte in ('x-uuencode', 'uuencode', 'uue', 'x-uue'):
sfp = StringIO()
try:
uu.decode(StringIO(payload + '\n'), sfp, quiet=True)
payload = sfp.getvalue()
except uu.Error:
return payload
return payload
def get_payload(self, i=None, decode=False):
"""Return a reference to the payload.
The payload will either be a list object or a string. If you mutate
the list object, you modify the message's payload in place. Optional
i returns that index into the payload.
Optional decode is a flag indicating whether the payload should be
decoded or not, according to the Content-Transfer-Encoding header
(default is False).
When True and the message is not a multipart, the payload will be
decoded if this header's value is `quoted-printable' or `base64'. If
some other encoding is used, or the header is missing, or if the
payload has bogus data (i.e. bogus base64 or uuencoded data), the
payload is returned as-is.
If the message is a multipart and the decode flag is True, then None
is returned.
"""
# Here is the logic table for this code, based on the email5.0.0 code:
# i decode is_multipart result
# ------ ------ ------------ ------------------------------
# None True True None
# i True True None
# None False True _payload (a list)
# i False True _payload element i (a Message)
# i False False error (not a list)
# i True False error (not a list)
# None False False _payload
# None True False _payload decoded (bytes)
# Note that Barry planned to factor out the 'decode' case, but that
# isn't so easy now that we handle the 8 bit data, which needs to be
# converted in both the decode and non-decode path.
if self.is_multipart():
if decode:
return None
if i is None:
return self._payload
else:
return self._payload[i]
# For backward compatibility, Use isinstance and this error message
# instead of the more logical is_multipart test.
if i is not None and not isinstance(self._payload, list):
raise TypeError('Expected list, got %s' % type(self._payload))
payload = self._payload
# cte might be a Header, so for now stringify it.
cte = str(self.get('content-transfer-encoding', '')).lower()
# payload may be bytes here.
if isinstance(payload, str):
if utils._has_surrogates(payload):
bpayload = payload.encode('ascii', 'surrogateescape')
if not decode:
try:
payload = bpayload.decode(
self.get_param('charset', 'ascii'), 'replace')
except LookupError:
payload = bpayload.decode('ascii', 'replace')
elif decode:
try:
bpayload = payload.encode('ascii')
except UnicodeError:
# This won't happen for RFC compliant messages (messages
# containing only ASCII codepoints in the unicode input).
# If it does happen, turn the string into bytes in a way
# guaranteed not to fail.
bpayload = payload.encode('raw-unicode-escape')
if not decode:
return payload
if cte == 'quoted-printable':
return utils._qdecode(bpayload)
elif cte == 'base64':
# XXX: this is a bit of a hack; decode_b should probably be factored
# out somewhere, but I haven't figured out where yet.
value, defects = decode_b(b''.join(bpayload.splitlines()))
for defect in defects:
self.policy.handle_defect(self, defect)
return value
elif cte in ('x-uuencode', 'uuencode', 'uue', 'x-uue'):
in_file = BytesIO(bpayload)
out_file = BytesIO()
try:
uu.decode(in_file, out_file, quiet=True)
return out_file.getvalue()
except uu.Error:
# Some decoding problem
return bpayload
if isinstance(payload, str):
return bpayload
return payload
def get_payload(self, i=None, decode=False):
"""Return a reference to the payload.
The payload will either be a list object or a string. If you mutate
the list object, you modify the message's payload in place. Optional
i returns that index into the payload.
Optional decode is a flag indicating whether the payload should be
decoded or not, according to the Content-Transfer-Encoding header
(default is False).
When True and the message is not a multipart, the payload will be
decoded if this header's value is `quoted-printable' or `base64'. If
some other encoding is used, or the header is missing, or if the
payload has bogus data (i.e. bogus base64 or uuencoded data), the
payload is returned as-is.
If the message is a multipart and the decode flag is True, then None
is returned.
"""
# Here is the logic table for this code, based on the email5.0.0 code:
# i decode is_multipart result
# ------ ------ ------------ ------------------------------
# None True True None
# i True True None
# None False True _payload (a list)
# i False True _payload element i (a Message)
# i False False error (not a list)
# i True False error (not a list)
# None False False _payload
# None True False _payload decoded (bytes)
# Note that Barry planned to factor out the 'decode' case, but that
# isn't so easy now that we handle the 8 bit data, which needs to be
# converted in both the decode and non-decode path.
if self.is_multipart():
if decode:
return None
if i is None:
return self._payload
else:
return self._payload[i]
# For backward compatibility, Use isinstance and this error message
# instead of the more logical is_multipart test.
if i is not None and not isinstance(self._payload, list):
raise TypeError('Expected list, got %s' % type(self._payload))
payload = self._payload
# cte might be a Header, so for now stringify it.
cte = str(self.get('content-transfer-encoding', '')).lower()
# payload may be bytes here.
if isinstance(payload, str):
if utils._has_surrogates(payload):
bpayload = payload.encode('ascii', 'surrogateescape')
if not decode:
try:
payload = bpayload.decode(self.get_param('charset', 'ascii'), 'replace')
except LookupError:
payload = bpayload.decode('ascii', 'replace')
elif decode:
try:
bpayload = payload.encode('ascii')
except UnicodeError:
# This won't happen for RFC compliant messages (messages
# containing only ASCII codepoints in the unicode input).
# If it does happen, turn the string into bytes in a way
# guaranteed not to fail.
bpayload = payload.encode('raw-unicode-escape')
if not decode:
return payload
if cte == 'quoted-printable':
return utils._qdecode(bpayload)
elif cte == 'base64':
# XXX: this is a bit of a hack; decode_b should probably be factored
# out somewhere, but I haven't figured out where yet.
value, defects = decode_b(b''.join(bpayload.splitlines()))
for defect in defects:
self.policy.handle_defect(self, defect)
return value
elif cte in ('x-uuencode', 'uuencode', 'uue', 'x-uue'):
in_file = BytesIO(bpayload)
out_file = BytesIO()
try:
uu.decode(in_file, out_file, quiet=True)
return out_file.getvalue()
except uu.Error:
# Some decoding problem
return bpayload
if isinstance(payload, str):
return bpayload
return payload
def rewrite(part):
need_rewrite = False
for hdr in part.values():
if max([len(i) for i in hdr.split('\n')]) > MAX_LINE_LENGTH:
need_rewrite = True # Force MIME rewrite if we have long headers
sys.stderr.write("FIXUP NEXT: Rewrite forced by long header line\n")
for hdr, max_lines, max_items, max_bytes in NUKE_HDRS:
(hdr, val) = (hdr.lower(), msg.get(hdr))
if (val and ((max_lines >= 0 and len(val.split('\n')) > max_lines) or
(max_items >= 0 and len(val.split()) > max_items) or
(max_bytes >= 0 and len(val) > max_bytes))):
del msg[hdr]
sys.stderr.write("FIXUP NEXT: Removed long header line: "+hdr+"\n")
need_rewrite = True
if part.is_multipart():
for subpart in part.get_payload():
if rewrite(subpart):
need_rewrite = True
return need_rewrite
payload = part.get_payload()
max_line_length = max([ len(i) for i in payload.split('\n') ])
cte = part.get('content-transfer-encoding', '').lower().strip()
if cte in ['8bit', '7bit', 'binary', '']:
# Encode unencoded forms which contain 8bit characters or long lines
update_cte = part.replace_header if (cte != '') else part.add_header
nonascii_count = [(ord(c) >= 128) for c in payload].count(True)
if ((NUKE_8BIT and nonascii_count > 0) or
max_line_length > MAX_LINE_LENGTH):
if nonascii_count < 100:
part.set_payload(qp_encode(payload))
update_cte('Content-Transfer-Encoding', "quoted-printable")
else:
part.set_payload(utils._bencode(payload))
update_cte('Content-Transfer-Encoding', "base64")
need_rewrite = True
elif cte in ['quoted-printable', 'base64']:
# Recode quoted-printable or base64 with long lines
if max_line_length > MAX_LINE_LENGTH:
if cte == 'quoted-printable':
raw=utils._qdecode(payload)
part.set_payload(qp_encode(raw))
need_rewrite = True
elif cte == 'base64':
try:
raw=utils._bdecode(payload)
part.set_payload(utils._bencode(raw))
need_rewrite = True
except binascii.Error:
pass
newcte = part.get('content-transfer-encoding', '').lower().strip()
if (newcte != cte):
part.add_header('X-Mime-Autoconverted',
"from " + (cte or "none") + " to " + newcte)
sys.stderr.write("FIXUP NEXT: Attachment converted " +
"from " + (cte or "none") + " to " + newcte + "\n")
return need_rewrite
def rewrite(part):
need_rewrite = False
for hdr in part.values():
if max([len(i) for i in hdr.split('\n')]) > MAX_LINE_LENGTH:
need_rewrite = True # Force MIME rewrite if we have long headers
sys.stderr.write(
"FIXUP NEXT: Rewrite forced by long header line\n")
for hdr, max_lines, max_items, max_bytes in NUKE_HDRS:
(hdr, val) = (hdr.lower(), msg.get(hdr))
if (val and ((max_lines >= 0 and len(val.split('\n')) > max_lines) or
(max_items >= 0 and len(val.split()) > max_items) or
(max_bytes >= 0 and len(val) > max_bytes))):
del msg[hdr]
sys.stderr.write("FIXUP NEXT: Removed long header line: " + hdr +
"\n")
need_rewrite = True
if part.is_multipart():
for subpart in part.get_payload():
if rewrite(subpart):
need_rewrite = True
return need_rewrite
payload = part.get_payload()
max_line_length = max([len(i) for i in payload.split('\n')])
cte = part.get('content-transfer-encoding', '').lower().strip()
if cte in ['8bit', '7bit', 'binary', '']:
# Encode unencoded forms which contain 8bit characters or long lines
update_cte = part.replace_header if (cte != '') else part.add_header
nonascii_count = [(ord(c) >= 128) for c in payload].count(True)
if ((NUKE_8BIT and nonascii_count > 0)
or max_line_length > MAX_LINE_LENGTH):
if nonascii_count < 100:
part.set_payload(qp_encode(payload))
update_cte('Content-Transfer-Encoding', "quoted-printable")
else:
part.set_payload(utils._bencode(payload))
update_cte('Content-Transfer-Encoding', "base64")
need_rewrite = True
elif cte in ['quoted-printable', 'base64']:
# Recode quoted-printable or base64 with long lines
if max_line_length > MAX_LINE_LENGTH:
if cte == 'quoted-printable':
raw = utils._qdecode(payload)
part.set_payload(qp_encode(raw))
need_rewrite = True
elif cte == 'base64':
try:
raw = utils._bdecode(payload)
part.set_payload(utils._bencode(raw))
need_rewrite = True
except binascii.Error:
pass
newcte = part.get('content-transfer-encoding', '').lower().strip()
if (newcte != cte):
part.add_header('X-Mime-Autoconverted',
"from " + (cte or "none") + " to " + newcte)
sys.stderr.write("FIXUP NEXT: Attachment converted " + "from " +
(cte or "none") + " to " + newcte + "\n")
return need_rewrite
def rewrite(part, drop_all_multipart_err):
need_rewrite = False
if (part.preamble and max_line_len(part.preamble) > MAX_LINE_LENGTH):
part.preamble = "\n"
sys.stderr.write("FIXUP NEXT: Removed over-long MIME preamble\n")
need_rewrite = True
if (part.epilogue and max_line_len(part.epilogue) > MAX_LINE_LENGTH):
part.epilogue = "\n"
sys.stderr.write("FIXUP NEXT: Removed over-long MIME epilogue\n")
need_rewrite = True
for hdr in part.values():
if max_line_len(hdr) > MAX_LINE_LENGTH:
need_rewrite = True # Force MIME rewrite if we have long headers
sys.stderr.write("FIXUP NEXT: Rewrite forced by long header line\n")
for hdr, max_lines, max_items, max_bytes in NUKE_HDRS:
(hdr, val) = (hdr.lower(), part.get(hdr))
if (val and ((max_lines >= 0 and len(val.split('\n')) > max_lines) or
(max_items >= 0 and len(val.split()) > max_items) or
(max_bytes >= 0 and len(val) > max_bytes))):
del part[hdr]
sys.stderr.write("FIXUP NEXT: Removed long header line: "+hdr+"\n")
need_rewrite = True
# Exchange Online can't cope with very long component in address list
for hdr in ['To', 'Cc', 'Bcc']:
val = part.get(hdr, "")
for addr in val.split(','): # Need better parsing here!
if len(addr) > 1950:
part['X-Broken-' + hdr] = val
del part[hdr]
sys.stderr.write("FIXUP NEXT: Renamed broken " + hdr +
" to X-Broken-" + hdr + "\n")
need_rewrite = True
ct = part.get_content_type()
max_name_len = 0
params = part.get_params()
if params:
for (key,value) in part.get_params():
if key in ['name', 'filename']:
if len(value) > max_name_len:
max_name_len = len(value)
if max_name_len > MAX_FILENAME:
need_rewrite = True
part_count=len(part.get_payload())
part_str = ('Removed ' + ct +
' with long filename (' + str(max_name_len) +
' characters) which chokes Exchange Online')
nuke_part(part, 1, part_str)
return need_rewrite
if part.is_multipart():
if (drop_all_multipart_err):
need_rewrite = True
part_count=len(part.get_payload())
part_str = drop_all_multipart_err
nuke_part(part, 0, part_str)
elif (len(part.get_payload()) > MAX_SUBPARTS):
need_rewrite = True
part_count=len(part.get_payload())
part_str = ('Removed ' + ct +
' with ' + str(part_count) +
' subparts/attachments which chokes Exchange Online')
nuke_part(part, 1, part_str)
elif ct in ['multipart/appledouble']:
need_rewrite = True
part_str = ('Removed ' + ct +
' which chokes Exchange Online')
nuke_part(part, 1, part_str)
else:
for subpart in part.get_payload():
if rewrite(subpart, drop_all_multipart_err):
need_rewrite = True
return need_rewrite
payload = part.get_payload()
max_line_length = max_line_len(payload)
cte = part.get('content-transfer-encoding', '').lower().strip()
if cte in ['8bit', '7bit', 'binary', '']:
# Encode unencoded forms which contain 8bit characters or long lines
update_cte = part.replace_header if (cte != '') else part.add_header
nonascii_count = [(ord(c) >= 128) for c in payload].count(True)
if ((NUKE_8BIT and nonascii_count > 0) or
max_line_length > MAX_LINE_LENGTH):
if nonascii_count < 100:
part.set_payload(qp_encode(payload))
update_cte('Content-Transfer-Encoding', "quoted-printable")
else:
part.set_payload(utils._bencode(payload))
update_cte('Content-Transfer-Encoding', "base64")
need_rewrite = True
elif (cte in ['quoted-printable', 'base64']):
decode_error = False
try:
if cte == 'quoted-printable':
raw=utils._qdecode(payload)
else:
raw=utils._bdecode(payload)
if (len(payload) > 100) and (len(raw) < len(payload)/10):
raise binascii.Error
except binascii.Error:
decode_error = True
if decode_error:
# Discard broken attachment which would no decode
need_rewrite = True
part_str = ('Removed ' + ct +
' with broken attachment which failed to decode')
nuke_part(part, 1, part_str)
elif max_line_length > MAX_LINE_LENGTH:
sys.stderr.write("FIXUP NEXT: Recoded " +
(cte or "none") + " attachment [Long lines]\n")
# Recode quoted-printable or base64 with long lines
need_rewrite = True
if cte == 'quoted-printable':
part.set_payload(qp_encode(raw))
else:
part.set_payload(utils._bencode(raw))
newcte = part.get('content-transfer-encoding', '').lower().strip()
if (newcte and (newcte != cte)):
part.add_header('X-Mime-Autoconverted',
"from " + (cte or "none") + " to " + newcte)
if max_line_length > MAX_LINE_LENGTH:
sys.stderr.write("FIXUP NEXT: Attachment converted " +
"from " + (cte or "none") + " to " + newcte +
" [Long lines]\n")
else:
sys.stderr.write("FIXUP NEXT: Attachment converted " +
"from " + (cte or "none") + " to " + newcte +
" [Raw Binary data]\n")
return need_rewrite
