Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.8/email/generator.py: 21%
235 statements
« prev ^ index » next coverage.py v7.0.5, created at 2023-01-17 06:13 +0000
1# Copyright (C) 2001-2010 Python Software Foundation
2# Author: Barry Warsaw
3# Contact: email-sig@python.org
5"""Classes to generate plain text from a message object tree."""
7__all__ = ['Generator', 'DecodedGenerator', 'BytesGenerator']
9import re
10import sys
11import time
12import random
14from copy import deepcopy
15from io import StringIO, BytesIO
16from email.utils import _has_surrogates
18UNDERSCORE = '_'
19NL = '\n' # XXX: no longer used by the code below.
21NLCRE = re.compile(r'\r\n|\r|\n')
22fcre = re.compile(r'^From ', re.MULTILINE)
26class Generator:
27 """Generates output from a Message object tree.
29 This basic generator writes the message to the given file object as plain
30 text.
31 """
32 #
33 # Public interface
34 #
36 def __init__(self, outfp, mangle_from_=None, maxheaderlen=None, *,
37 policy=None):
38 """Create the generator for message flattening.
40 outfp is the output file-like object for writing the message to. It
41 must have a write() method.
43 Optional mangle_from_ is a flag that, when True (the default if policy
44 is not set), escapes From_ lines in the body of the message by putting
45 a `>' in front of them.
47 Optional maxheaderlen specifies the longest length for a non-continued
48 header. When a header line is longer (in characters, with tabs
49 expanded to 8 spaces) than maxheaderlen, the header will split as
50 defined in the Header class. Set maxheaderlen to zero to disable
51 header wrapping. The default is 78, as recommended (but not required)
52 by RFC 2822.
54 The policy keyword specifies a policy object that controls a number of
55 aspects of the generator's operation. If no policy is specified,
56 the policy associated with the Message object passed to the
57 flatten method is used.
59 """
61 if mangle_from_ is None:
62 mangle_from_ = True if policy is None else policy.mangle_from_
63 self._fp = outfp
64 self._mangle_from_ = mangle_from_
65 self.maxheaderlen = maxheaderlen
66 self.policy = policy
68 def write(self, s):
69 # Just delegate to the file object
70 self._fp.write(s)
72 def flatten(self, msg, unixfrom=False, linesep=None):
73 r"""Print the message object tree rooted at msg to the output file
74 specified when the Generator instance was created.
76 unixfrom is a flag that forces the printing of a Unix From_ delimiter
77 before the first object in the message tree. If the original message
78 has no From_ delimiter, a `standard' one is crafted. By default, this
79 is False to inhibit the printing of any From_ delimiter.
81 Note that for subobjects, no From_ line is printed.
83 linesep specifies the characters used to indicate a new line in
84 the output. The default value is determined by the policy specified
85 when the Generator instance was created or, if none was specified,
86 from the policy associated with the msg.
88 """
89 # We use the _XXX constants for operating on data that comes directly
90 # from the msg, and _encoded_XXX constants for operating on data that
91 # has already been converted (to bytes in the BytesGenerator) and
92 # inserted into a temporary buffer.
93 policy = msg.policy if self.policy is None else self.policy
94 if linesep is not None:
95 policy = policy.clone(linesep=linesep)
96 if self.maxheaderlen is not None:
97 policy = policy.clone(max_line_length=self.maxheaderlen)
98 self._NL = policy.linesep
99 self._encoded_NL = self._encode(self._NL)
100 self._EMPTY = ''
101 self._encoded_EMPTY = self._encode(self._EMPTY)
102 # Because we use clone (below) when we recursively process message
103 # subparts, and because clone uses the computed policy (not None),
104 # submessages will automatically get set to the computed policy when
105 # they are processed by this code.
106 old_gen_policy = self.policy
107 old_msg_policy = msg.policy
108 try:
109 self.policy = policy
110 msg.policy = policy
111 if unixfrom:
112 ufrom = msg.get_unixfrom()
113 if not ufrom:
114 ufrom = 'From nobody ' + time.ctime(time.time())
115 self.write(ufrom + self._NL)
116 self._write(msg)
117 finally:
118 self.policy = old_gen_policy
119 msg.policy = old_msg_policy
121 def clone(self, fp):
122 """Clone this generator with the exact same options."""
123 return self.__class__(fp,
124 self._mangle_from_,
125 None, # Use policy setting, which we've adjusted
126 policy=self.policy)
128 #
129 # Protected interface - undocumented ;/
130 #
132 # Note that we use 'self.write' when what we are writing is coming from
133 # the source, and self._fp.write when what we are writing is coming from a
134 # buffer (because the Bytes subclass has already had a chance to transform
135 # the data in its write method in that case). This is an entirely
136 # pragmatic split determined by experiment; we could be more general by
137 # always using write and having the Bytes subclass write method detect when
138 # it has already transformed the input; but, since this whole thing is a
139 # hack anyway this seems good enough.
141 def _new_buffer(self):
142 # BytesGenerator overrides this to return BytesIO.
143 return StringIO()
145 def _encode(self, s):
146 # BytesGenerator overrides this to encode strings to bytes.
147 return s
149 def _write_lines(self, lines):
150 # We have to transform the line endings.
151 if not lines:
152 return
153 lines = NLCRE.split(lines)
154 for line in lines[:-1]:
155 self.write(line)
156 self.write(self._NL)
157 if lines[-1]:
158 self.write(lines[-1])
159 # XXX logic tells me this else should be needed, but the tests fail
160 # with it and pass without it. (NLCRE.split ends with a blank element
161 # if and only if there was a trailing newline.)
162 #else:
163 # self.write(self._NL)
165 def _write(self, msg):
166 # We can't write the headers yet because of the following scenario:
167 # say a multipart message includes the boundary string somewhere in
168 # its body. We'd have to calculate the new boundary /before/ we write
169 # the headers so that we can write the correct Content-Type:
170 # parameter.
171 #
172 # The way we do this, so as to make the _handle_*() methods simpler,
173 # is to cache any subpart writes into a buffer. The we write the
174 # headers and the buffer contents. That way, subpart handlers can
175 # Do The Right Thing, and can still modify the Content-Type: header if
176 # necessary.
177 oldfp = self._fp
178 try:
179 self._munge_cte = None
180 self._fp = sfp = self._new_buffer()
181 self._dispatch(msg)
182 finally:
183 self._fp = oldfp
184 munge_cte = self._munge_cte
185 del self._munge_cte
186 # If we munged the cte, copy the message again and re-fix the CTE.
187 if munge_cte:
188 msg = deepcopy(msg)
189 msg.replace_header('content-transfer-encoding', munge_cte[0])
190 msg.replace_header('content-type', munge_cte[1])
191 # Write the headers. First we see if the message object wants to
192 # handle that itself. If not, we'll do it generically.
193 meth = getattr(msg, '_write_headers', None)
194 if meth is None:
195 self._write_headers(msg)
196 else:
197 meth(self)
198 self._fp.write(sfp.getvalue())
200 def _dispatch(self, msg):
201 # Get the Content-Type: for the message, then try to dispatch to
202 # self._handle_<maintype>_<subtype>(). If there's no handler for the
203 # full MIME type, then dispatch to self._handle_<maintype>(). If
204 # that's missing too, then dispatch to self._writeBody().
205 main = msg.get_content_maintype()
206 sub = msg.get_content_subtype()
207 specific = UNDERSCORE.join((main, sub)).replace('-', '_')
208 meth = getattr(self, '_handle_' + specific, None)
209 if meth is None:
210 generic = main.replace('-', '_')
211 meth = getattr(self, '_handle_' + generic, None)
212 if meth is None:
213 meth = self._writeBody
214 meth(msg)
216 #
217 # Default handlers
218 #
220 def _write_headers(self, msg):
221 for h, v in msg.raw_items():
222 self.write(self.policy.fold(h, v))
223 # A blank line always separates headers from body
224 self.write(self._NL)
226 #
227 # Handlers for writing types and subtypes
228 #
230 def _handle_text(self, msg):
231 payload = msg.get_payload()
232 if payload is None:
233 return
234 if not isinstance(payload, str):
235 raise TypeError('string payload expected: %s' % type(payload))
236 if _has_surrogates(msg._payload):
237 charset = msg.get_param('charset')
238 if charset is not None:
239 # XXX: This copy stuff is an ugly hack to avoid modifying the
240 # existing message.
241 msg = deepcopy(msg)
242 del msg['content-transfer-encoding']
243 msg.set_payload(payload, charset)
244 payload = msg.get_payload()
245 self._munge_cte = (msg['content-transfer-encoding'],
246 msg['content-type'])
247 if self._mangle_from_:
248 payload = fcre.sub('>From ', payload)
249 self._write_lines(payload)
251 # Default body handler
252 _writeBody = _handle_text
254 def _handle_multipart(self, msg):
255 # The trick here is to write out each part separately, merge them all
256 # together, and then make sure that the boundary we've chosen isn't
257 # present in the payload.
258 msgtexts = []
259 subparts = msg.get_payload()
260 if subparts is None:
261 subparts = []
262 elif isinstance(subparts, str):
263 # e.g. a non-strict parse of a message with no starting boundary.
264 self.write(subparts)
265 return
266 elif not isinstance(subparts, list):
267 # Scalar payload
268 subparts = [subparts]
269 for part in subparts:
270 s = self._new_buffer()
271 g = self.clone(s)
272 g.flatten(part, unixfrom=False, linesep=self._NL)
273 msgtexts.append(s.getvalue())
274 # BAW: What about boundaries that are wrapped in double-quotes?
275 boundary = msg.get_boundary()
276 if not boundary:
277 # Create a boundary that doesn't appear in any of the
278 # message texts.
279 alltext = self._encoded_NL.join(msgtexts)
280 boundary = self._make_boundary(alltext)
281 msg.set_boundary(boundary)
282 # If there's a preamble, write it out, with a trailing CRLF
283 if msg.preamble is not None:
284 if self._mangle_from_:
285 preamble = fcre.sub('>From ', msg.preamble)
286 else:
287 preamble = msg.preamble
288 self._write_lines(preamble)
289 self.write(self._NL)
290 # dash-boundary transport-padding CRLF
291 self.write('--' + boundary + self._NL)
292 # body-part
293 if msgtexts:
294 self._fp.write(msgtexts.pop(0))
295 # *encapsulation
296 # --> delimiter transport-padding
297 # --> CRLF body-part
298 for body_part in msgtexts:
299 # delimiter transport-padding CRLF
300 self.write(self._NL + '--' + boundary + self._NL)
301 # body-part
302 self._fp.write(body_part)
303 # close-delimiter transport-padding
304 self.write(self._NL + '--' + boundary + '--' + self._NL)
305 if msg.epilogue is not None:
306 if self._mangle_from_:
307 epilogue = fcre.sub('>From ', msg.epilogue)
308 else:
309 epilogue = msg.epilogue
310 self._write_lines(epilogue)
312 def _handle_multipart_signed(self, msg):
313 # The contents of signed parts has to stay unmodified in order to keep
314 # the signature intact per RFC1847 2.1, so we disable header wrapping.
315 # RDM: This isn't enough to completely preserve the part, but it helps.
316 p = self.policy
317 self.policy = p.clone(max_line_length=0)
318 try:
319 self._handle_multipart(msg)
320 finally:
321 self.policy = p
323 def _handle_message_delivery_status(self, msg):
324 # We can't just write the headers directly to self's file object
325 # because this will leave an extra newline between the last header
326 # block and the boundary. Sigh.
327 blocks = []
328 for part in msg.get_payload():
329 s = self._new_buffer()
330 g = self.clone(s)
331 g.flatten(part, unixfrom=False, linesep=self._NL)
332 text = s.getvalue()
333 lines = text.split(self._encoded_NL)
334 # Strip off the unnecessary trailing empty line
335 if lines and lines[-1] == self._encoded_EMPTY:
336 blocks.append(self._encoded_NL.join(lines[:-1]))
337 else:
338 blocks.append(text)
339 # Now join all the blocks with an empty line. This has the lovely
340 # effect of separating each block with an empty line, but not adding
341 # an extra one after the last one.
342 self._fp.write(self._encoded_NL.join(blocks))
344 def _handle_message(self, msg):
345 s = self._new_buffer()
346 g = self.clone(s)
347 # The payload of a message/rfc822 part should be a multipart sequence
348 # of length 1. The zeroth element of the list should be the Message
349 # object for the subpart. Extract that object, stringify it, and
350 # write it out.
351 # Except, it turns out, when it's a string instead, which happens when
352 # and only when HeaderParser is used on a message of mime type
353 # message/rfc822. Such messages are generated by, for example,
354 # Groupwise when forwarding unadorned messages. (Issue 7970.) So
355 # in that case we just emit the string body.
356 payload = msg._payload
357 if isinstance(payload, list):
358 g.flatten(msg.get_payload(0), unixfrom=False, linesep=self._NL)
359 payload = s.getvalue()
360 else:
361 payload = self._encode(payload)
362 self._fp.write(payload)
364 # This used to be a module level function; we use a classmethod for this
365 # and _compile_re so we can continue to provide the module level function
366 # for backward compatibility by doing
367 # _make_boundary = Generator._make_boundary
368 # at the end of the module. It *is* internal, so we could drop that...
369 @classmethod
370 def _make_boundary(cls, text=None):
371 # Craft a random boundary. If text is given, ensure that the chosen
372 # boundary doesn't appear in the text.
373 token = random.randrange(sys.maxsize)
374 boundary = ('=' * 15) + (_fmt % token) + '=='
375 if text is None:
376 return boundary
377 b = boundary
378 counter = 0
379 while True:
380 cre = cls._compile_re('^--' + re.escape(b) + '(--)?$', re.MULTILINE)
381 if not cre.search(text):
382 break
383 b = boundary + '.' + str(counter)
384 counter += 1
385 return b
387 @classmethod
388 def _compile_re(cls, s, flags):
389 return re.compile(s, flags)
392class BytesGenerator(Generator):
393 """Generates a bytes version of a Message object tree.
395 Functionally identical to the base Generator except that the output is
396 bytes and not string. When surrogates were used in the input to encode
397 bytes, these are decoded back to bytes for output. If the policy has
398 cte_type set to 7bit, then the message is transformed such that the
399 non-ASCII bytes are properly content transfer encoded, using the charset
400 unknown-8bit.
402 The outfp object must accept bytes in its write method.
403 """
405 def write(self, s):
406 self._fp.write(s.encode('ascii', 'surrogateescape'))
408 def _new_buffer(self):
409 return BytesIO()
411 def _encode(self, s):
412 return s.encode('ascii')
414 def _write_headers(self, msg):
415 # This is almost the same as the string version, except for handling
416 # strings with 8bit bytes.
417 for h, v in msg.raw_items():
418 self._fp.write(self.policy.fold_binary(h, v))
419 # A blank line always separates headers from body
420 self.write(self._NL)
422 def _handle_text(self, msg):
423 # If the string has surrogates the original source was bytes, so
424 # just write it back out.
425 if msg._payload is None:
426 return
427 if _has_surrogates(msg._payload) and not self.policy.cte_type=='7bit':
428 if self._mangle_from_:
429 msg._payload = fcre.sub(">From ", msg._payload)
430 self._write_lines(msg._payload)
431 else:
432 super(BytesGenerator,self)._handle_text(msg)
434 # Default body handler
435 _writeBody = _handle_text
437 @classmethod
438 def _compile_re(cls, s, flags):
439 return re.compile(s.encode('ascii'), flags)
443_FMT = '[Non-text (%(type)s) part of message omitted, filename %(filename)s]'
445class DecodedGenerator(Generator):
446 """Generates a text representation of a message.
448 Like the Generator base class, except that non-text parts are substituted
449 with a format string representing the part.
450 """
451 def __init__(self, outfp, mangle_from_=None, maxheaderlen=None, fmt=None, *,
452 policy=None):
453 """Like Generator.__init__() except that an additional optional
454 argument is allowed.
456 Walks through all subparts of a message. If the subpart is of main
457 type `text', then it prints the decoded payload of the subpart.
459 Otherwise, fmt is a format string that is used instead of the message
460 payload. fmt is expanded with the following keywords (in
461 %(keyword)s format):
463 type : Full MIME type of the non-text part
464 maintype : Main MIME type of the non-text part
465 subtype : Sub-MIME type of the non-text part
466 filename : Filename of the non-text part
467 description: Description associated with the non-text part
468 encoding : Content transfer encoding of the non-text part
470 The default value for fmt is None, meaning
472 [Non-text (%(type)s) part of message omitted, filename %(filename)s]
473 """
474 Generator.__init__(self, outfp, mangle_from_, maxheaderlen,
475 policy=policy)
476 if fmt is None:
477 self._fmt = _FMT
478 else:
479 self._fmt = fmt
481 def _dispatch(self, msg):
482 for part in msg.walk():
483 maintype = part.get_content_maintype()
484 if maintype == 'text':
485 print(part.get_payload(decode=False), file=self)
486 elif maintype == 'multipart':
487 # Just skip this
488 pass
489 else:
490 print(self._fmt % {
491 'type' : part.get_content_type(),
492 'maintype' : part.get_content_maintype(),
493 'subtype' : part.get_content_subtype(),
494 'filename' : part.get_filename('[no filename]'),
495 'description': part.get('Content-Description',
496 '[no description]'),
497 'encoding' : part.get('Content-Transfer-Encoding',
498 '[no encoding]'),
499 }, file=self)
503# Helper used by Generator._make_boundary
504_width = len(repr(sys.maxsize-1))
505_fmt = '%%0%dd' % _width
507# Backward compatibility
508_make_boundary = Generator._make_boundary