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
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
|
# Copyright (C) 2001,2002 Python Software Foundation
# Author: barry@zope.com (Barry Warsaw)
"""Basic message object for the email package object model.
"""
import re
import warnings
from cStringIO import StringIO
from types import ListType, StringType
# Intrapackage imports
import Errors
import Utils
import Charset
SEMISPACE = '; '
# Regular expression used to split header parameters. BAW: this may be too
# simple. It isn't strictly RFC 2045 (section 5.1) compliant, but it catches
# most headers found in the wild. We may eventually need a full fledged
# parser eventually.
paramre = re.compile(r'\s*;\s*')
# Regular expression that matches `special' characters in parameters, the
# existance of which force quoting of the parameter value.
tspecials = re.compile(r'[ \(\)<>@,;:\\"/\[\]\?=]')
# Helper function
def _formatparam(param, value=None, quote=1):
"""Convenience function to format and return a key=value pair.
Will quote the value if needed or if quote is true.
"""
if value is not None and len(value) > 0:
# BAW: Please check this. I think that if quote is set it should
# force quoting even if not necessary.
if quote or tspecials.search(value):
return '%s="%s"' % (param, Utils.quote(value))
else:
return '%s=%s' % (param, value)
else:
return param
class Message:
"""Basic message object for use inside the object tree.
A message object is defined as something that has a bunch of RFC 2822
headers and a payload. If the body of the message is a multipart, then
the payload is a list of Messages, otherwise it is a string.
These objects implement part of the `mapping' interface, which assumes
there is exactly one occurrance of the header per message. Some headers
do in fact appear multiple times (e.g. Received:) and for those headers,
you must use the explicit API to set or get all the headers. Not all of
the mapping methods are implemented.
"""
def __init__(self):
self._headers = []
self._unixfrom = None
self._payload = None
self._charset = None
# Defaults for multipart messages
self.preamble = self.epilogue = None
def __str__(self):
"""Return the entire formatted message as a string.
This includes the headers, body, and `unixfrom' line.
"""
return self.as_string(unixfrom=1)
def as_string(self, unixfrom=0):
"""Return the entire formatted message as a string.
Optional `unixfrom' when true, means include the Unix From_ envelope
header.
"""
from Generator import Generator
fp = StringIO()
g = Generator(fp)
g(self, unixfrom=unixfrom)
return fp.getvalue()
def is_multipart(self):
"""Return true if the message consists of multiple parts."""
if type(self._payload) is ListType:
return 1
return 0
#
# Unix From_ line
#
def set_unixfrom(self, unixfrom):
self._unixfrom = unixfrom
def get_unixfrom(self):
return self._unixfrom
#
# Payload manipulation.
#
def add_payload(self, payload):
"""Add the given payload to the current payload.
If the current payload is empty, then the current payload will be made
a scalar, set to the given value.
"""
warnings.warn('add_payload() is deprecated, use attach() instead.',
DeprecationWarning, 2)
if self._payload is None:
self._payload = payload
elif type(self._payload) is ListType:
self._payload.append(payload)
elif self.get_main_type() not in (None, 'multipart'):
raise Errors.MultipartConversionError(
'Message main Content-Type: must be "multipart" or missing')
else:
self._payload = [self._payload, payload]
def attach(self, payload):
"""Add the given payload to the current payload.
The current payload will always be a list of objects after this method
is called. If you want to set the payload to a scalar object
(e.g. because you're attaching a message/rfc822 subpart), use
set_payload() instead.
"""
if self._payload is None:
self._payload = [payload]
else:
self._payload.append(payload)
def get_payload(self, i=None, decode=0):
"""Return the current payload exactly as is.
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.
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, the payload is
returned as-is (undecoded). If the message is a multipart and the
decode flag is true, then None is returned.
"""
if i is None:
payload = self._payload
elif type(self._payload) is not ListType:
raise TypeError, i
else:
payload = self._payload[i]
if decode:
if self.is_multipart():
return None
cte = self.get('content-transfer-encoding', '')
if cte.lower() == 'quoted-printable':
return Utils._qdecode(payload)
elif cte.lower() == 'base64':
return Utils._bdecode(payload)
# Everything else, including encodings with 8bit or 7bit are returned
# unchanged.
return payload
def set_payload(self, payload, charset=None):
"""Set the payload to the given value.
Optionally set the charset, which must be a Charset instance."""
self._payload = payload
if charset is not None:
self.set_charset(charset)
def set_charset(self, charset):
"""Set the charset of the payload to a given character set.
charset can be a string or a Charset object. If it is a string, it
will be converted to a Charset object by calling Charset's
constructor. If charset is None, the charset parameter will be
removed from the Content-Type: field. Anything else will generate a
TypeError.
The message will be assumed to be a text message encoded with
charset.input_charset. It will be converted to charset.output_charset
and encoded properly, if needed, when generating the plain text
representation of the message. MIME headers (MIME-Version,
Content-Type, Content-Transfer-Encoding) will be added as needed.
"""
if charset is None:
self.del_param('charset')
self._charset = None
return
if isinstance(charset, StringType):
charset = Charset.Charset(charset)
if not isinstance(charset, Charset.Charset):
raise TypeError, charset
# BAW: should we accept strings that can serve as arguments to the
# Charset constructor?
self._charset = charset
if not self.has_key('MIME-Version'):
self.add_header('MIME-Version', '1.0')
if not self.has_key('Content-Type'):
self.add_header('Content-Type', 'text/plain',
charset=charset.get_output_charset())
else:
self.set_param('charset', charset.get_output_charset())
if not self.has_key('Content-Transfer-Encoding'):
cte = charset.get_body_encoding()
if callable(cte):
cte(self)
else:
self.add_header('Content-Transfer-Encoding', cte)
def get_charset(self):
"""Return the Charset object associated with the message's payload."""
return self._charset
#
# MAPPING INTERFACE (partial)
#
def __len__(self):
"""Return the total number of headers, including duplicates."""
return len(self._headers)
def __getitem__(self, name):
"""Get a header value.
Return None if the header is missing instead of raising an exception.
Note that if the header appeared multiple times, exactly which
occurrance gets returned is undefined. Use getall() to get all
the values matching a header field name.
"""
return self.get(name)
def __setitem__(self, name, val):
"""Set the value of a header.
Note: this does not overwrite an existing header with the same field
name. Use __delitem__() first to delete any existing headers.
"""
self._headers.append((name, val))
def __delitem__(self, name):
"""Delete all occurrences of a header, if present.
Does not raise an exception if the header is missing.
"""
name = name.lower()
newheaders = []
for k, v in self._headers:
if k.lower() <> name:
newheaders.append((k, v))
self._headers = newheaders
def __contains__(self, key):
return key.lower() in [k.lower() for k, v in self._headers]
def has_key(self, name):
"""Return true if the message contains the header."""
missing = []
return self.get(name, missing) is not missing
def keys(self):
"""Return a list of all the message's header field names.
These will be sorted in the order they appeared in the original
message, and may contain duplicates. Any fields deleted and
re-inserted are always appended to the header list.
"""
return [k for k, v in self._headers]
def values(self):
"""Return a list of all the message's header values.
These will be sorted in the order they appeared in the original
message, and may contain duplicates. Any fields deleted and
re-inserted are always appended to the header list.
"""
return [v for k, v in self._headers]
def items(self):
"""Get all the message's header fields and values.
These will be sorted in the order they appeared in the original
message, and may contain duplicates. Any fields deleted and
re-inserted are always appended to the header list.
"""
return self._headers[:]
def get(self, name, failobj=None):
"""Get a header value.
Like __getitem__() but return failobj instead of None when the field
is missing.
"""
name = name.lower()
for k, v in self._headers:
if k.lower() == name:
return v
return failobj
#
# Additional useful stuff
#
def get_all(self, name, failobj=None):
"""Return a list of all the values for the named field.
These will be sorted in the order they appeared in the original
message, and may contain duplicates. Any fields deleted and
re-inserted are always appended to the header list.
If no such fields exist, failobj is returned (defaults to None).
"""
values = []
name = name.lower()
for k, v in self._headers:
if k.lower() == name:
values.append(v)
if not values:
return failobj
return values
def add_header(self, _name, _value, **_params):
"""Extended header setting.
name is the header field to add. keyword arguments can be used to set
additional parameters for the header field, with underscores converted
to dashes. Normally the parameter will be added as key="value" unless
value is None, in which case only the key will be added.
Example:
msg.add_header('content-disposition', 'attachment', filename='bud.gif')
"""
parts = []
for k, v in _params.items():
if v is None:
parts.append(k.replace('_', '-'))
else:
parts.append(_formatparam(k.replace('_', '-'), v))
if _value is not None:
parts.insert(0, _value)
self._headers.append((_name, SEMISPACE.join(parts)))
def get_type(self, failobj=None):
"""Returns the message's content type.
The returned string is coerced to lowercase and returned as a single
string of the form `maintype/subtype'. If there was no Content-Type:
header in the message, failobj is returned (defaults to None).
"""
missing = []
value = self.get('content-type', missing)
if value is missing:
return failobj
return paramre.split(value)[0].lower()
def get_main_type(self, failobj=None):
"""Return the message's main content type if present."""
missing = []
ctype = self.get_type(missing)
if ctype is missing:
return failobj
parts = ctype.split('/')
if len(parts) > 0:
return ctype.split('/')[0]
return failobj
def get_subtype(self, failobj=None):
"""Return the message's content subtype if present."""
missing = []
ctype = self.get_type(missing)
if ctype is missing:
return failobj
parts = ctype.split('/')
if len(parts) > 1:
return ctype.split('/')[1]
return failobj
def _get_params_preserve(self, failobj, header):
# Like get_params() but preserves the quoting of values. BAW:
# should this be part of the public interface?
missing = []
value = self.get(header, missing)
if value is missing:
return failobj
params = []
for p in paramre.split(value):
try:
name, val = p.split('=', 1)
name = name.rstrip()
val = val.lstrip()
except ValueError:
# Must have been a bare attribute
name = p
val = ''
params.append((name, val))
return params
def get_params(self, failobj=None, header='content-type', unquote=1):
"""Return the message's Content-Type: parameters, as a list.
The elements of the returned list are 2-tuples of key/value pairs, as
split on the `=' sign. The left hand side of the `=' is the key,
while the right hand side is the value. If there is no `=' sign in
the parameter the value is the empty string. The value is always
unquoted, unless unquote is set to a false value.
Optional failobj is the object to return if there is no Content-Type:
header. Optional header is the header to search instead of
Content-Type:.
"""
missing = []
params = self._get_params_preserve(missing, header)
if params is missing:
return failobj
if unquote:
return [(k, Utils.unquote(v)) for k, v in params]
else:
return params
def get_param(self, param, failobj=None, header='content-type', unquote=1):
"""Return the parameter value if found in the Content-Type: header.
Optional failobj is the object to return if there is no Content-Type:
header. Optional header is the header to search instead of
Content-Type:
Parameter keys are always compared case insensitively. Values are
always unquoted, unless unquote is set to a false value.
"""
if not self.has_key(header):
return failobj
for k, v in self._get_params_preserve(failobj, header):
if k.lower() == param.lower():
if unquote:
return Utils.unquote(v)
else:
return v
return failobj
def set_param(self, param, value, header='Content-Type', requote=1):
"""Set a parameter in the Content-Type: header.
If the parameter already exists in the header, its value will be
replaced with the new value.
If header is Content-Type: and has not yet been defined in this
message, it will be set to "text/plain" and the new parameter and
value will be appended, as per RFC 2045.
An alternate header can specified in the header argument, and
all parameters will be quoted as appropriate unless requote is
set to a false value.
"""
if not self.has_key(header) and header.lower() == 'content-type':
ctype = 'text/plain'
else:
ctype = self.get(header)
if not self.get_param(param, header=header):
if not ctype:
ctype = _formatparam(param, value, requote)
else:
ctype = SEMISPACE.join(
[ctype, _formatparam(param, value, requote)])
else:
ctype = ''
for old_param, old_value in self.get_params(header=header,
unquote=requote):
append_param = ''
if old_param.lower() == param.lower():
append_param = _formatparam(param, value, requote)
else:
append_param = _formatparam(old_param, old_value, requote)
if not ctype:
ctype = append_param
else:
ctype = SEMISPACE.join([ctype, append_param])
if ctype <> self.get(header):
del self[header]
self[header] = ctype
def del_param(self, param, header='content-type', requote=1):
"""Remove the given parameter completely from the Content-Type header.
The header will be re-written in place without param or its value.
All values will be quoted as appropriate unless requote is set to a
false value.
"""
if not self.has_key(header):
return
new_ctype = ''
for p, v in self.get_params(header, unquote=requote):
if p.lower() <> param.lower():
if not new_ctype:
new_ctype = _formatparam(p, v, requote)
else:
new_ctype = SEMISPACE.join([new_ctype,
_formatparam(p, v, requote)])
if new_ctype <> self.get(header):
del self[header]
self[header] = new_ctype
def set_type(self, type, header='Content-Type', requote=1):
"""Set the main type and subtype for the Content-Type: header.
type must be a string in the form "maintype/subtype", otherwise a
ValueError is raised.
This method replaces the Content-Type: header, keeping all the
parameters in place. If requote is false, this leaves the existing
header's quoting as is. Otherwise, the parameters will be quoted (the
default).
An alternate header can be specified in the header argument. When the
Content-Type: header is set, we'll always also add a MIME-Version:
header.
"""
# BAW: should we be strict?
if not type.count('/') == 1:
raise ValueError
# Set the Content-Type: you get a MIME-Version:
if header.lower() == 'content-type':
del self['mime-version']
self['MIME-Version'] = '1.0'
if not self.has_key(header):
self[header] = type
return
params = self.get_params(header, unquote=requote)
del self[header]
self[header] = type
# Skip the first param; it's the old type.
for p, v in params[1:]:
self.set_param(p, v, header, requote)
def get_filename(self, failobj=None):
"""Return the filename associated with the payload if present.
The filename is extracted from the Content-Disposition: header's
`filename' parameter, and it is unquoted.
"""
missing = []
filename = self.get_param('filename', missing, 'content-disposition')
if filename is missing:
return failobj
return Utils.unquote(filename.strip())
def get_boundary(self, failobj=None):
"""Return the boundary associated with the payload if present.
The boundary is extracted from the Content-Type: header's `boundary'
parameter, and it is unquoted.
"""
missing = []
boundary = self.get_param('boundary', missing)
if boundary is missing:
return failobj
return Utils.unquote(boundary.strip())
def set_boundary(self, boundary):
"""Set the boundary parameter in Content-Type: to 'boundary'.
This is subtly different than deleting the Content-Type: header and
adding a new one with a new boundary parameter via add_header(). The
main difference is that using the set_boundary() method preserves the
order of the Content-Type: header in the original message.
HeaderParseError is raised if the message has no Content-Type: header.
"""
missing = []
params = self._get_params_preserve(missing, 'content-type')
if params is missing:
# There was no Content-Type: header, and we don't know what type
# to set it to, so raise an exception.
raise Errors.HeaderParseError, 'No Content-Type: header found'
newparams = []
foundp = 0
for pk, pv in params:
if pk.lower() == 'boundary':
newparams.append(('boundary', '"%s"' % boundary))
foundp = 1
else:
newparams.append((pk, pv))
if not foundp:
# The original Content-Type: header had no boundary attribute.
# Tack one one the end. BAW: should we raise an exception
# instead???
newparams.append(('boundary', '"%s"' % boundary))
# Replace the existing Content-Type: header with the new value
newheaders = []
for h, v in self._headers:
if h.lower() == 'content-type':
parts = []
for k, v in newparams:
if v == '':
parts.append(k)
else:
parts.append('%s=%s' % (k, v))
newheaders.append((h, SEMISPACE.join(parts)))
else:
newheaders.append((h, v))
self._headers = newheaders
try:
from email._compat22 import walk
except SyntaxError:
# Must be using Python 2.1
from email._compat21 import walk
def get_charsets(self, failobj=None):
"""Return a list containing the charset(s) used in this message.
The returned list of items describes the Content-Type: headers'
charset parameter for this message and all the subparts in its
payload.
Each item will either be a string (the value of the charset parameter
in the Content-Type: header of that part) or the value of the
'failobj' parameter (defaults to None), if the part does not have a
main MIME type of "text", or the charset is not defined.
The list will contain one string for each part of the message, plus
one for the container message (i.e. self), so that a non-multipart
message will still return a list of length 1.
"""
return [part.get_param('charset', failobj) for part in self.walk()]
|