2010-01-01 09:07:05 -04:00
|
|
|
|
# Copyright (C) 2001-2010 Python Software Foundation
|
2004-10-03 00:16:19 -03:00
|
|
|
|
# Contact: email-sig@python.org
|
2001-09-23 00:17:28 -03:00
|
|
|
|
|
2004-10-03 00:16:19 -03:00
|
|
|
|
"""Classes to generate plain text from a message object tree."""
|
2001-09-23 00:17:28 -03:00
|
|
|
|
|
2006-03-18 11:41:53 -04:00
|
|
|
|
__all__ = ['Generator', 'DecodedGenerator']
|
|
|
|
|
|
2001-09-23 00:17:28 -03:00
|
|
|
|
import re
|
2003-05-29 16:39:33 -03:00
|
|
|
|
import sys
|
2003-03-06 01:22:02 -04:00
|
|
|
|
import time
|
2001-09-23 00:17:28 -03:00
|
|
|
|
import random
|
2004-10-03 00:16:19 -03:00
|
|
|
|
import warnings
|
2001-09-23 00:17:28 -03:00
|
|
|
|
|
2006-03-18 11:41:53 -04:00
|
|
|
|
from cStringIO import StringIO
|
|
|
|
|
from email.header import Header
|
2002-09-10 13:13:45 -03:00
|
|
|
|
|
2001-09-23 00:17:28 -03:00
|
|
|
|
UNDERSCORE = '_'
|
|
|
|
|
NL = '\n'
|
|
|
|
|
|
|
|
|
|
fcre = re.compile(r'^From ', re.MULTILINE)
|
|
|
|
|
|
2002-10-14 12:09:30 -03:00
|
|
|
|
def _is8bitstring(s):
|
2004-05-09 00:35:17 -03:00
|
|
|
|
if isinstance(s, str):
|
2002-10-14 12:09:30 -03:00
|
|
|
|
try:
|
|
|
|
|
unicode(s, 'us-ascii')
|
|
|
|
|
except UnicodeError:
|
|
|
|
|
return True
|
|
|
|
|
return False
|
|
|
|
|
|
2001-09-23 00:17:28 -03:00
|
|
|
|
|
2001-10-04 14:05:11 -03:00
|
|
|
|
|
2001-09-23 00:17:28 -03:00
|
|
|
|
class Generator:
|
|
|
|
|
"""Generates output from a Message object tree.
|
|
|
|
|
|
|
|
|
|
This basic generator writes the message to the given file object as plain
|
|
|
|
|
text.
|
|
|
|
|
"""
|
|
|
|
|
#
|
|
|
|
|
# Public interface
|
|
|
|
|
#
|
|
|
|
|
|
2002-09-28 15:04:55 -03:00
|
|
|
|
def __init__(self, outfp, mangle_from_=True, maxheaderlen=78):
|
2001-09-23 00:17:28 -03:00
|
|
|
|
"""Create the generator for message flattening.
|
|
|
|
|
|
|
|
|
|
outfp is the output file-like object for writing the message to. It
|
|
|
|
|
must have a write() method.
|
|
|
|
|
|
2002-09-28 15:04:55 -03:00
|
|
|
|
Optional mangle_from_ is a flag that, when True (the default), escapes
|
|
|
|
|
From_ lines in the body of the message by putting a `>' in front of
|
|
|
|
|
them.
|
2001-09-23 00:17:28 -03:00
|
|
|
|
|
|
|
|
|
Optional maxheaderlen specifies the longest length for a non-continued
|
|
|
|
|
header. When a header line is longer (in characters, with tabs
|
2003-11-18 22:23:01 -04:00
|
|
|
|
expanded to 8 spaces) than maxheaderlen, the header will split as
|
|
|
|
|
defined in the Header class. Set maxheaderlen to zero to disable
|
|
|
|
|
header wrapping. The default is 78, as recommended (but not required)
|
|
|
|
|
by RFC 2822.
|
2001-09-23 00:17:28 -03:00
|
|
|
|
"""
|
|
|
|
|
self._fp = outfp
|
|
|
|
|
self._mangle_from_ = mangle_from_
|
2004-05-09 00:35:17 -03:00
|
|
|
|
self._maxheaderlen = maxheaderlen
|
2001-09-23 00:17:28 -03:00
|
|
|
|
|
|
|
|
|
def write(self, s):
|
|
|
|
|
# Just delegate to the file object
|
|
|
|
|
self._fp.write(s)
|
|
|
|
|
|
2002-09-28 15:04:55 -03:00
|
|
|
|
def flatten(self, msg, unixfrom=False):
|
2001-09-23 00:17:28 -03:00
|
|
|
|
"""Print the message object tree rooted at msg to the output file
|
|
|
|
|
specified when the Generator instance was created.
|
|
|
|
|
|
|
|
|
|
unixfrom is a flag that forces the printing of a Unix From_ delimiter
|
|
|
|
|
before the first object in the message tree. If the original message
|
|
|
|
|
has no From_ delimiter, a `standard' one is crafted. By default, this
|
2002-09-28 15:04:55 -03:00
|
|
|
|
is False to inhibit the printing of any From_ delimiter.
|
2001-09-23 00:17:28 -03:00
|
|
|
|
|
|
|
|
|
Note that for subobjects, no From_ line is printed.
|
|
|
|
|
"""
|
|
|
|
|
if unixfrom:
|
|
|
|
|
ufrom = msg.get_unixfrom()
|
|
|
|
|
if not ufrom:
|
|
|
|
|
ufrom = 'From nobody ' + time.ctime(time.time())
|
|
|
|
|
print >> self._fp, ufrom
|
|
|
|
|
self._write(msg)
|
|
|
|
|
|
2002-07-08 23:43:47 -03:00
|
|
|
|
def clone(self, fp):
|
|
|
|
|
"""Clone this generator with the exact same options."""
|
2004-05-09 00:35:17 -03:00
|
|
|
|
return self.__class__(fp, self._mangle_from_, self._maxheaderlen)
|
2002-07-08 23:43:47 -03:00
|
|
|
|
|
2001-09-23 00:17:28 -03:00
|
|
|
|
#
|
|
|
|
|
# Protected interface - undocumented ;/
|
|
|
|
|
#
|
|
|
|
|
|
|
|
|
|
def _write(self, msg):
|
|
|
|
|
# We can't write the headers yet because of the following scenario:
|
|
|
|
|
# say a multipart message includes the boundary string somewhere in
|
|
|
|
|
# its body. We'd have to calculate the new boundary /before/ we write
|
|
|
|
|
# the headers so that we can write the correct Content-Type:
|
|
|
|
|
# parameter.
|
|
|
|
|
#
|
|
|
|
|
# The way we do this, so as to make the _handle_*() methods simpler,
|
|
|
|
|
# is to cache any subpart writes into a StringIO. The we write the
|
|
|
|
|
# headers and the StringIO contents. That way, subpart handlers can
|
|
|
|
|
# Do The Right Thing, and can still modify the Content-Type: header if
|
|
|
|
|
# necessary.
|
|
|
|
|
oldfp = self._fp
|
|
|
|
|
try:
|
|
|
|
|
self._fp = sfp = StringIO()
|
|
|
|
|
self._dispatch(msg)
|
|
|
|
|
finally:
|
|
|
|
|
self._fp = oldfp
|
|
|
|
|
# Write the headers. First we see if the message object wants to
|
|
|
|
|
# handle that itself. If not, we'll do it generically.
|
|
|
|
|
meth = getattr(msg, '_write_headers', None)
|
|
|
|
|
if meth is None:
|
|
|
|
|
self._write_headers(msg)
|
|
|
|
|
else:
|
|
|
|
|
meth(self)
|
|
|
|
|
self._fp.write(sfp.getvalue())
|
|
|
|
|
|
|
|
|
|
def _dispatch(self, msg):
|
|
|
|
|
# Get the Content-Type: for the message, then try to dispatch to
|
2002-07-11 15:48:40 -03:00
|
|
|
|
# self._handle_<maintype>_<subtype>(). If there's no handler for the
|
|
|
|
|
# full MIME type, then dispatch to self._handle_<maintype>(). If
|
|
|
|
|
# that's missing too, then dispatch to self._writeBody().
|
2002-08-20 11:47:30 -03:00
|
|
|
|
main = msg.get_content_maintype()
|
|
|
|
|
sub = msg.get_content_subtype()
|
2002-07-08 23:43:47 -03:00
|
|
|
|
specific = UNDERSCORE.join((main, sub)).replace('-', '_')
|
|
|
|
|
meth = getattr(self, '_handle_' + specific, None)
|
|
|
|
|
if meth is None:
|
|
|
|
|
generic = main.replace('-', '_')
|
|
|
|
|
meth = getattr(self, '_handle_' + generic, None)
|
2001-09-23 00:17:28 -03:00
|
|
|
|
if meth is None:
|
2002-07-08 23:43:47 -03:00
|
|
|
|
meth = self._writeBody
|
|
|
|
|
meth(msg)
|
2001-09-23 00:17:28 -03:00
|
|
|
|
|
|
|
|
|
#
|
|
|
|
|
# Default handlers
|
|
|
|
|
#
|
|
|
|
|
|
|
|
|
|
def _write_headers(self, msg):
|
|
|
|
|
for h, v in msg.items():
|
2003-03-07 11:43:17 -04:00
|
|
|
|
print >> self._fp, '%s:' % h,
|
2004-05-09 00:35:17 -03:00
|
|
|
|
if self._maxheaderlen == 0:
|
2003-03-07 11:43:17 -04:00
|
|
|
|
# Explicit no-wrapping
|
|
|
|
|
print >> self._fp, v
|
|
|
|
|
elif isinstance(v, Header):
|
|
|
|
|
# Header instances know what to do
|
|
|
|
|
print >> self._fp, v.encode()
|
|
|
|
|
elif _is8bitstring(v):
|
|
|
|
|
# If we have raw 8bit data in a byte string, we have no idea
|
|
|
|
|
# what the encoding is. There is no safe way to split this
|
|
|
|
|
# string. If it's ascii-subset, then we could do a normal
|
|
|
|
|
# ascii split, but if it's multibyte then we could break the
|
|
|
|
|
# string. There's no way to know so the least harm seems to
|
|
|
|
|
# be to not split the string and risk it being too long.
|
|
|
|
|
print >> self._fp, v
|
|
|
|
|
else:
|
2009-03-30 19:42:17 -03:00
|
|
|
|
# Header's got lots of smarts, so use it. Note that this is
|
|
|
|
|
# fundamentally broken though because we lose idempotency when
|
|
|
|
|
# the header string is continued with tabs. It will now be
|
|
|
|
|
# continued with spaces. This was reversedly broken before we
|
|
|
|
|
# fixed bug 1974. Either way, we lose.
|
2003-03-07 11:43:17 -04:00
|
|
|
|
print >> self._fp, Header(
|
2009-03-30 19:42:17 -03:00
|
|
|
|
v, maxlinelen=self._maxheaderlen, header_name=h).encode()
|
2001-09-23 00:17:28 -03:00
|
|
|
|
# A blank line always separates headers from body
|
|
|
|
|
print >> self._fp
|
|
|
|
|
|
|
|
|
|
#
|
|
|
|
|
# Handlers for writing types and subtypes
|
|
|
|
|
#
|
|
|
|
|
|
|
|
|
|
def _handle_text(self, msg):
|
|
|
|
|
payload = msg.get_payload()
|
2001-09-26 02:32:41 -03:00
|
|
|
|
if payload is None:
|
|
|
|
|
return
|
2004-05-09 00:35:17 -03:00
|
|
|
|
if not isinstance(payload, basestring):
|
2004-10-03 00:16:19 -03:00
|
|
|
|
raise TypeError('string payload expected: %s' % type(payload))
|
2001-09-23 00:17:28 -03:00
|
|
|
|
if self._mangle_from_:
|
|
|
|
|
payload = fcre.sub('>From ', payload)
|
|
|
|
|
self._fp.write(payload)
|
|
|
|
|
|
|
|
|
|
# Default body handler
|
|
|
|
|
_writeBody = _handle_text
|
|
|
|
|
|
2002-07-08 23:43:47 -03:00
|
|
|
|
def _handle_multipart(self, msg):
|
2001-09-23 00:17:28 -03:00
|
|
|
|
# The trick here is to write out each part separately, merge them all
|
|
|
|
|
# together, and then make sure that the boundary we've chosen isn't
|
|
|
|
|
# present in the payload.
|
|
|
|
|
msgtexts = []
|
2002-04-10 18:01:31 -03:00
|
|
|
|
subparts = msg.get_payload()
|
|
|
|
|
if subparts is None:
|
2004-05-09 00:35:17 -03:00
|
|
|
|
subparts = []
|
|
|
|
|
elif isinstance(subparts, basestring):
|
2002-09-10 13:13:45 -03:00
|
|
|
|
# e.g. a non-strict parse of a message with no starting boundary.
|
|
|
|
|
self._fp.write(subparts)
|
|
|
|
|
return
|
2004-05-09 00:35:17 -03:00
|
|
|
|
elif not isinstance(subparts, list):
|
2002-04-10 18:01:31 -03:00
|
|
|
|
# Scalar payload
|
|
|
|
|
subparts = [subparts]
|
|
|
|
|
for part in subparts:
|
2001-09-23 00:17:28 -03:00
|
|
|
|
s = StringIO()
|
2002-07-08 23:43:47 -03:00
|
|
|
|
g = self.clone(s)
|
2002-09-28 15:04:55 -03:00
|
|
|
|
g.flatten(part, unixfrom=False)
|
2001-09-23 00:17:28 -03:00
|
|
|
|
msgtexts.append(s.getvalue())
|
|
|
|
|
# BAW: What about boundaries that are wrapped in double-quotes?
|
2010-12-12 16:32:19 -04:00
|
|
|
|
boundary = msg.get_boundary()
|
|
|
|
|
if not boundary:
|
|
|
|
|
# Create a boundary that doesn't appear in any of the
|
|
|
|
|
# message texts.
|
|
|
|
|
alltext = NL.join(msgtexts)
|
2010-12-21 14:12:50 -04:00
|
|
|
|
boundary = _make_boundary(alltext)
|
|
|
|
|
msg.set_boundary(boundary)
|
2004-05-09 00:35:17 -03:00
|
|
|
|
# If there's a preamble, write it out, with a trailing CRLF
|
2001-09-23 00:17:28 -03:00
|
|
|
|
if msg.preamble is not None:
|
2004-05-09 00:35:17 -03:00
|
|
|
|
print >> self._fp, msg.preamble
|
|
|
|
|
# dash-boundary transport-padding CRLF
|
2001-09-23 00:17:28 -03:00
|
|
|
|
print >> self._fp, '--' + boundary
|
2004-05-09 00:35:17 -03:00
|
|
|
|
# body-part
|
|
|
|
|
if msgtexts:
|
|
|
|
|
self._fp.write(msgtexts.pop(0))
|
|
|
|
|
# *encapsulation
|
|
|
|
|
# --> delimiter transport-padding
|
|
|
|
|
# --> CRLF body-part
|
|
|
|
|
for body_part in msgtexts:
|
|
|
|
|
# delimiter transport-padding CRLF
|
|
|
|
|
print >> self._fp, '\n--' + boundary
|
|
|
|
|
# body-part
|
|
|
|
|
self._fp.write(body_part)
|
|
|
|
|
# close-delimiter transport-padding
|
|
|
|
|
self._fp.write('\n--' + boundary + '--')
|
2001-09-23 00:17:28 -03:00
|
|
|
|
if msg.epilogue is not None:
|
2004-05-09 00:35:17 -03:00
|
|
|
|
print >> self._fp
|
2001-09-23 00:17:28 -03:00
|
|
|
|
self._fp.write(msg.epilogue)
|
|
|
|
|
|
2010-01-16 01:15:17 -04:00
|
|
|
|
def _handle_multipart_signed(self, msg):
|
|
|
|
|
# The contents of signed parts has to stay unmodified in order to keep
|
|
|
|
|
# the signature intact per RFC1847 2.1, so we disable header wrapping.
|
|
|
|
|
# RDM: This isn't enough to completely preserve the part, but it helps.
|
|
|
|
|
old_maxheaderlen = self._maxheaderlen
|
|
|
|
|
try:
|
|
|
|
|
self._maxheaderlen = 0
|
|
|
|
|
self._handle_multipart(msg)
|
|
|
|
|
finally:
|
|
|
|
|
self._maxheaderlen = old_maxheaderlen
|
|
|
|
|
|
2001-09-26 02:32:41 -03:00
|
|
|
|
def _handle_message_delivery_status(self, msg):
|
|
|
|
|
# We can't just write the headers directly to self's file object
|
|
|
|
|
# because this will leave an extra newline between the last header
|
|
|
|
|
# block and the boundary. Sigh.
|
|
|
|
|
blocks = []
|
|
|
|
|
for part in msg.get_payload():
|
|
|
|
|
s = StringIO()
|
2002-07-08 23:43:47 -03:00
|
|
|
|
g = self.clone(s)
|
2002-09-28 15:04:55 -03:00
|
|
|
|
g.flatten(part, unixfrom=False)
|
2001-09-26 02:32:41 -03:00
|
|
|
|
text = s.getvalue()
|
|
|
|
|
lines = text.split('\n')
|
|
|
|
|
# Strip off the unnecessary trailing empty line
|
|
|
|
|
if lines and lines[-1] == '':
|
|
|
|
|
blocks.append(NL.join(lines[:-1]))
|
|
|
|
|
else:
|
|
|
|
|
blocks.append(text)
|
|
|
|
|
# Now join all the blocks with an empty line. This has the lovely
|
|
|
|
|
# effect of separating each block with an empty line, but not adding
|
|
|
|
|
# an extra one after the last one.
|
|
|
|
|
self._fp.write(NL.join(blocks))
|
|
|
|
|
|
|
|
|
|
def _handle_message(self, msg):
|
2001-09-23 00:17:28 -03:00
|
|
|
|
s = StringIO()
|
2002-07-08 23:43:47 -03:00
|
|
|
|
g = self.clone(s)
|
2002-06-02 16:02:37 -03:00
|
|
|
|
# The payload of a message/rfc822 part should be a multipart sequence
|
|
|
|
|
# of length 1. The zeroth element of the list should be the Message
|
2002-07-08 23:43:47 -03:00
|
|
|
|
# object for the subpart. Extract that object, stringify it, and
|
|
|
|
|
# write it out.
|
2010-02-21 00:23:00 -04:00
|
|
|
|
# Except, it turns out, when it's a string instead, which happens when
|
|
|
|
|
# and only when HeaderParser is used on a message of mime type
|
|
|
|
|
# message/rfc822. Such messages are generated by, for example,
|
|
|
|
|
# Groupwise when forwarding unadorned messages. (Issue 7970.) So
|
|
|
|
|
# in that case we just emit the string body.
|
|
|
|
|
payload = msg.get_payload()
|
|
|
|
|
if isinstance(payload, list):
|
|
|
|
|
g.flatten(msg.get_payload(0), unixfrom=False)
|
|
|
|
|
payload = s.getvalue()
|
|
|
|
|
self._fp.write(payload)
|
2001-09-23 00:17:28 -03:00
|
|
|
|
|
|
|
|
|
|
2001-10-04 14:05:11 -03:00
|
|
|
|
|
2004-10-03 00:16:19 -03:00
|
|
|
|
_FMT = '[Non-text (%(type)s) part of message omitted, filename %(filename)s]'
|
|
|
|
|
|
2001-09-23 00:17:28 -03:00
|
|
|
|
class DecodedGenerator(Generator):
|
2010-12-06 14:48:31 -04:00
|
|
|
|
"""Generates a text representation of a message.
|
2001-09-23 00:17:28 -03:00
|
|
|
|
|
|
|
|
|
Like the Generator base class, except that non-text parts are substituted
|
|
|
|
|
with a format string representing the part.
|
|
|
|
|
"""
|
2002-09-28 15:04:55 -03:00
|
|
|
|
def __init__(self, outfp, mangle_from_=True, maxheaderlen=78, fmt=None):
|
2001-09-23 00:17:28 -03:00
|
|
|
|
"""Like Generator.__init__() except that an additional optional
|
|
|
|
|
argument is allowed.
|
|
|
|
|
|
|
|
|
|
Walks through all subparts of a message. If the subpart is of main
|
|
|
|
|
type `text', then it prints the decoded payload of the subpart.
|
|
|
|
|
|
|
|
|
|
Otherwise, fmt is a format string that is used instead of the message
|
|
|
|
|
payload. fmt is expanded with the following keywords (in
|
|
|
|
|
%(keyword)s format):
|
|
|
|
|
|
|
|
|
|
type : Full MIME type of the non-text part
|
|
|
|
|
maintype : Main MIME type of the non-text part
|
|
|
|
|
subtype : Sub-MIME type of the non-text part
|
|
|
|
|
filename : Filename of the non-text part
|
|
|
|
|
description: Description associated with the non-text part
|
|
|
|
|
encoding : Content transfer encoding of the non-text part
|
|
|
|
|
|
|
|
|
|
The default value for fmt is None, meaning
|
|
|
|
|
|
|
|
|
|
[Non-text (%(type)s) part of message omitted, filename %(filename)s]
|
|
|
|
|
"""
|
|
|
|
|
Generator.__init__(self, outfp, mangle_from_, maxheaderlen)
|
|
|
|
|
if fmt is None:
|
2004-10-03 00:16:19 -03:00
|
|
|
|
self._fmt = _FMT
|
|
|
|
|
else:
|
|
|
|
|
self._fmt = fmt
|
2001-09-23 00:17:28 -03:00
|
|
|
|
|
|
|
|
|
def _dispatch(self, msg):
|
|
|
|
|
for part in msg.walk():
|
2004-10-03 00:16:19 -03:00
|
|
|
|
maintype = part.get_content_maintype()
|
2001-09-26 02:32:41 -03:00
|
|
|
|
if maintype == 'text':
|
2002-09-28 15:04:55 -03:00
|
|
|
|
print >> self, part.get_payload(decode=True)
|
2001-09-26 02:32:41 -03:00
|
|
|
|
elif maintype == 'multipart':
|
|
|
|
|
# Just skip this
|
|
|
|
|
pass
|
2001-09-23 00:17:28 -03:00
|
|
|
|
else:
|
|
|
|
|
print >> self, self._fmt % {
|
2004-10-03 00:16:19 -03:00
|
|
|
|
'type' : part.get_content_type(),
|
|
|
|
|
'maintype' : part.get_content_maintype(),
|
|
|
|
|
'subtype' : part.get_content_subtype(),
|
2001-09-23 00:17:28 -03:00
|
|
|
|
'filename' : part.get_filename('[no filename]'),
|
|
|
|
|
'description': part.get('Content-Description',
|
|
|
|
|
'[no description]'),
|
|
|
|
|
'encoding' : part.get('Content-Transfer-Encoding',
|
|
|
|
|
'[no encoding]'),
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
2001-10-04 14:05:11 -03:00
|
|
|
|
|
2001-09-23 00:17:28 -03:00
|
|
|
|
# Helper
|
2003-05-29 16:39:33 -03:00
|
|
|
|
_width = len(repr(sys.maxint-1))
|
|
|
|
|
_fmt = '%%0%dd' % _width
|
|
|
|
|
|
2002-04-10 18:01:31 -03:00
|
|
|
|
def _make_boundary(text=None):
|
2001-09-23 00:17:28 -03:00
|
|
|
|
# Craft a random boundary. If text is given, ensure that the chosen
|
|
|
|
|
# boundary doesn't appear in the text.
|
2003-06-24 17:19:34 -03:00
|
|
|
|
token = random.randrange(sys.maxint)
|
2003-05-29 16:39:33 -03:00
|
|
|
|
boundary = ('=' * 15) + (_fmt % token) + '=='
|
2001-09-23 00:17:28 -03:00
|
|
|
|
if text is None:
|
|
|
|
|
return boundary
|
|
|
|
|
b = boundary
|
|
|
|
|
counter = 0
|
2002-09-28 15:04:55 -03:00
|
|
|
|
while True:
|
2001-09-23 00:17:28 -03:00
|
|
|
|
cre = re.compile('^--' + re.escape(b) + '(--)?$', re.MULTILINE)
|
|
|
|
|
if not cre.search(text):
|
|
|
|
|
break
|
|
|
|
|
b = boundary + '.' + str(counter)
|
|
|
|
|
counter += 1
|
|
|
|
|
return b
|