summaryrefslogtreecommitdiffstats
path: root/Lib/email/generator.py
blob: 04c021018308d4f8ef4172b9abb083a36a3bff77 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
# Copyright (C) 2001-2010 Python Software Foundation
# Author: Barry Warsaw
# Contact: email-sig@python.org

"""Classes to generate plain text from a message object tree."""

__all__ = ['Generator', 'DecodedGenerator', 'BytesGenerator']

import re
import sys
import time
import random
import warnings

from io import StringIO, BytesIO
from email.header import Header
from email.message import _has_surrogates

UNDERSCORE = '_'
NL = '\n'  # XXX: no longer used by the code below.

fcre = re.compile(r'^From ', re.MULTILINE)



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
    #

    def __init__(self, outfp, mangle_from_=True, maxheaderlen=78):
        """Create the generator for message flattening.

        outfp is the output file-like object for writing the message to.  It
        must have a write() method.

        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.

        Optional maxheaderlen specifies the longest length for a non-continued
        header.  When a header line is longer (in characters, with tabs
        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.
        """
        self._fp = outfp
        self._mangle_from_ = mangle_from_
        self._maxheaderlen = maxheaderlen

    def write(self, s):
        # Just delegate to the file object
        self._fp.write(s)

    def flatten(self, msg, unixfrom=False, linesep='\n'):
        r"""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
        is False to inhibit the printing of any From_ delimiter.

        Note that for subobjects, no From_ line is printed.

        linesep specifies the characters used to indicate a new line in
        the output.  The default value is the most useful for typical
        Python applications, but it can be set to \r\n to produce RFC-compliant
        line separators when needed.

        """
        # We use the _XXX constants for operating on data that comes directly
        # from the msg, and _encoded_XXX constants for operating on data that
        # has already been converted (to bytes in the BytesGenerator) and
        # inserted into a temporary buffer.
        self._NL = linesep
        self._encoded_NL = self._encode(linesep)
        self._EMPTY = ''
        self._encoded_EMTPY = self._encode('')
        if unixfrom:
            ufrom = msg.get_unixfrom()
            if not ufrom:
                ufrom = 'From nobody ' + time.ctime(time.time())
            self.write(ufrom + self._NL)
        self._write(msg)

    def clone(self, fp):
        """Clone this generator with the exact same options."""
        return self.__class__(fp, self._mangle_from_, self._maxheaderlen)

    #
    # Protected interface - undocumented ;/
    #

    # Note that we use 'self.write' when what we are writing is coming from
    # the source, and self._fp.write when what we are writing is coming from a
    # buffer (because the Bytes subclass has already had a chance to transform
    # the data in its write method in that case).  This is an entirely
    # pragmatic split determined by experiment; we could be more general by
    # always using write and having the Bytes subclass write method detect when
    # it has already transformed the input; but, since this whole thing is a
    # hack anyway this seems good enough.

    # Similarly, we have _XXX and _encoded_XXX attributes that are used on
    # source and buffer data, respectively.
    _encoded_EMPTY = ''

    def _new_buffer(self):
        # BytesGenerator overrides this to return BytesIO.
        return StringIO()

    def _encode(self, s):
        # BytesGenerator overrides this to encode strings to bytes.
        return s

    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 buffer.  The we write the
        # headers and the buffer 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 = self._new_buffer()
            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
        # 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().
        main = msg.get_content_maintype()
        sub = msg.get_content_subtype()
        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)
            if meth is None:
                meth = self._writeBody
        meth(msg)

    #
    # Default handlers
    #

    def _write_headers(self, msg):
        for h, v in msg.items():
            self.write('%s: ' % h)
            if isinstance(v, Header):
                self.write(v.encode(
                    maxlinelen=self._maxheaderlen, linesep=self._NL)+self._NL)
            else:
                # Header's got lots of smarts, so use it.
                header = Header(v, maxlinelen=self._maxheaderlen,
                                header_name=h)
                self.write(header.encode(linesep=self._NL)+self._NL)
        # A blank line always separates headers from body
        self.write(self._NL)

    #
    # Handlers for writing types and subtypes
    #

    def _handle_text(self, msg):
        payload = msg.get_payload()
        if payload is None:
            return
        if not isinstance(payload, str):
            raise TypeError('string payload expected: %s' % type(payload))
        if _has_surrogates(msg._payload):
            charset = msg.get_param('charset')
            if charset is not None:
                del msg['content-transfer-encoding']
                msg.set_payload(payload, charset)
                payload = msg.get_payload()
        if self._mangle_from_:
            payload = fcre.sub('>From ', payload)
        self.write(payload)

    # Default body handler
    _writeBody = _handle_text

    def _handle_multipart(self, msg):
        # 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 = []
        subparts = msg.get_payload()
        if subparts is None:
            subparts = []
        elif isinstance(subparts, str):
            # e.g. a non-strict parse of a message with no starting boundary.
            self.write(subparts)
            return
        elif not isinstance(subparts, list):
            # Scalar payload
            subparts = [subparts]
        for part in subparts:
            s = self._new_buffer()
            g = self.clone(s)
            g.flatten(part, unixfrom=False, linesep=self._NL)
            msgtexts.append(s.getvalue())
        # BAW: What about boundaries that are wrapped in double-quotes?
        boundary = msg.get_boundary()
        if not boundary:
            # Create a boundary that doesn't appear in any of the
            # message texts.
            alltext = self._encoded_NL.join(msgtexts)
            boundary = self._make_boundary(alltext)
            msg.set_boundary(boundary)
        # If there's a preamble, write it out, with a trailing CRLF
        if msg.preamble is not None:
            self.write(msg.preamble + self._NL)
        # dash-boundary transport-padding CRLF
        self.write('--' + boundary + self._NL)
        # 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
            self.write(self._NL + '--' + boundary + self._NL)
            # body-part
            self._fp.write(body_part)
        # close-delimiter transport-padding
        self.write(self._NL + '--' + boundary + '--')
        if msg.epilogue is not None:
            self.write(self._NL)
            self.write(msg.epilogue)

    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

    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 = self._new_buffer()
            g = self.clone(s)
            g.flatten(part, unixfrom=False, linesep=self._NL)
            text = s.getvalue()
            lines = text.split(self._encoded_NL)
            # Strip off the unnecessary trailing empty line
            if lines and lines[-1] == self._encoded_EMPTY:
                blocks.append(self._encoded_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(self._encoded_NL.join(blocks))

    def _handle_message(self, msg):
        s = self._new_buffer()
        g = self.clone(s)
        # 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
        # object for the subpart.  Extract that object, stringify it, and
        # write it out.
        # 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, linesep=self._NL)
            payload = s.getvalue()
        self._fp.write(payload)

    # This used to be a module level function; we use a classmethod for this
    # and _compile_re so we can continue to provide the module level function
    # for backward compatibility by doing
    #   _make_boudary = Generator._make_boundary
    # at the end of the module.  It *is* internal, so we could drop that...
    @classmethod
    def _make_boundary(cls, text=None):
        # Craft a random boundary.  If text is given, ensure that the chosen
        # boundary doesn't appear in the text.
        token = random.randrange(sys.maxsize)
        boundary = ('=' * 15) + (_fmt % token) + '=='
        if text is None:
            return boundary
        b = boundary
        counter = 0
        while True:
            cre = cls._compile_re('^--' + re.escape(b) + '(--)?$', re.MULTILINE)
            if not cre.search(text):
                break
            b = boundary + '.' + str(counter)
            counter += 1
        return b

    @classmethod
    def _compile_re(cls, s, flags):
        return re.compile(s, flags)


class BytesGenerator(Generator):
    """Generates a bytes version of a Message object tree.

    Functionally identical to the base Generator except that the output is
    bytes and not string.  When surrogates were used in the input to encode
    bytes, these are decoded back to bytes for output.

    The outfp object must accept bytes in its write method.
    """

    # Bytes versions of this constant for use in manipulating data from
    # the BytesIO buffer.
    _encoded_EMPTY = b''

    def write(self, s):
        self._fp.write(s.encode('ascii', 'surrogateescape'))

    def _new_buffer(self):
        return BytesIO()

    def _encode(self, s):
        return s.encode('ascii')

    def _write_headers(self, msg):
        # This is almost the same as the string version, except for handling
        # strings with 8bit bytes.
        for h, v in msg._headers:
            self.write('%s: ' % h)
            if isinstance(v, Header):
                self.write(v.encode(maxlinelen=self._maxheaderlen)+self._NL)
            elif _has_surrogates(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.
                self.write(v+NL)
            else:
                # Header's got lots of smarts and this string is safe...
                header = Header(v, maxlinelen=self._maxheaderlen,
                                header_name=h)
                self.write(header.encode(linesep=self._NL)+self._NL)
        # A blank line always separates headers from body
        self.write(self._NL)

    def _handle_text(self, msg):
        # If the string has surrogates the original source was bytes, so
        # just write it back out.
        if msg._payload is None:
            return
        if _has_surrogates(msg._payload):
            self.write(msg._payload)
        else:
            super(BytesGenerator,self)._handle_text(msg)

    @classmethod
    def _compile_re(cls, s, flags):
        return re.compile(s.encode('ascii'), flags)



_FMT = '[Non-text (%(type)s) part of message omitted, filename %(filename)s]'

class DecodedGenerator(Generator):
    """Generates a text representation of a message.

    Like the Generator base class, except that non-text parts are substituted
    with a format string representing the part.
    """
    def __init__(self, outfp, mangle_from_=True, maxheaderlen=78, fmt=None):
        """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:
            self._fmt = _FMT
        else:
            self._fmt = fmt

    def _dispatch(self, msg):
        for part in msg.walk():
            maintype = part.get_content_maintype()
            if maintype == 'text':
                print(part.get_payload(decode=False), file=self)
            elif maintype == 'multipart':
                # Just skip this
                pass
            else:
                print(self._fmt % {
                    'type'       : part.get_content_type(),
                    'maintype'   : part.get_content_maintype(),
                    'subtype'    : part.get_content_subtype(),
                    'filename'   : part.get_filename('[no filename]'),
                    'description': part.get('Content-Description',
                                            '[no description]'),
                    'encoding'   : part.get('Content-Transfer-Encoding',
                                            '[no encoding]'),
                    }, file=self)



# Helper used by Generator._make_boundary
_width = len(repr(sys.maxsize-1))
_fmt = '%%0%dd' % _width

# Backward compatibility
_make_boundary = Generator._make_boundary