/usr/lib/python3/dist-packages/future/backports/email/message.py is in python3-future 0.15.2-4.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 | # -*- coding: utf-8 -*-
# Copyright (C) 2001-2007 Python Software Foundation
# Author: Barry Warsaw
# Contact: email-sig@python.org
"""Basic message object for the email package object model."""
from __future__ import absolute_import, division, unicode_literals
from future.builtins import list, range, str, zip
__all__ = ['Message']
import re
import uu
import base64
import binascii
from io import BytesIO, StringIO
# Intrapackage imports
from future.utils import as_native_str
from future.backports.email import utils
from future.backports.email import errors
from future.backports.email._policybase import compat32
from future.backports.email import charset as _charset
from future.backports.email._encoded_words import decode_b
Charset = _charset.Charset
SEMISPACE = '; '
# Regular expression that matches `special' characters in parameters, the
# existence of which force quoting of the parameter value.
tspecials = re.compile(r'[ \(\)<>@,;:\\"/\[\]\?=]')
def _splitparam(param):
# 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.
# RDM: we might have a Header here; for now just stringify it.
a, sep, b = str(param).partition(';')
if not sep:
return a.strip(), None
return a.strip(), b.strip()
def _formatparam(param, value=None, quote=True):
"""Convenience function to format and return a key=value pair.
This will quote the value if needed or if quote is true. If value is a
three tuple (charset, language, value), it will be encoded according
to RFC2231 rules. If it contains non-ascii characters it will likewise
be encoded according to RFC2231 rules, using the utf-8 charset and
a null language.
"""
if value is not None and len(value) > 0:
# A tuple is used for RFC 2231 encoded parameter values where items
# are (charset, language, value). charset is a string, not a Charset
# instance. RFC 2231 encoded values are never quoted, per RFC.
if isinstance(value, tuple):
# Encode as per RFC 2231
param += '*'
value = utils.encode_rfc2231(value[2], value[0], value[1])
return '%s=%s' % (param, value)
else:
try:
value.encode('ascii')
except UnicodeEncodeError:
param += '*'
value = utils.encode_rfc2231(value, 'utf-8', '')
return '%s=%s' % (param, value)
# 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
def _parseparam(s):
# RDM This might be a Header, so for now stringify it.
s = ';' + str(s)
plist = []
while s[:1] == ';':
s = s[1:]
end = s.find(';')
while end > 0 and (s.count('"', 0, end) - s.count('\\"', 0, end)) % 2:
end = s.find(';', end + 1)
if end < 0:
end = len(s)
f = s[:end]
if '=' in f:
i = f.index('=')
f = f[:i].strip().lower() + '=' + f[i+1:].strip()
plist.append(f.strip())
s = s[end:]
return plist
def _unquotevalue(value):
# This is different than utils.collapse_rfc2231_value() because it doesn't
# try to convert the value to a unicode. Message.get_param() and
# Message.get_params() are both currently defined to return the tuple in
# the face of RFC 2231 parameters.
if isinstance(value, tuple):
return value[0], value[1], utils.unquote(value[2])
else:
return utils.unquote(value)
class Message(object):
"""Basic message object.
A message object is defined as something that has a bunch of RFC 2822
headers and a payload. It may optionally have an envelope header
(a.k.a. Unix-From or From_ header). If the message is a container (i.e. a
multipart or a message/rfc822), then the payload is a list of Message
objects, otherwise it is a string.
Message objects implement part of the `mapping' interface, which assumes
there is exactly one occurrence 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, policy=compat32):
self.policy = policy
self._headers = list()
self._unixfrom = None
self._payload = None
self._charset = None
# Defaults for multipart messages
self.preamble = self.epilogue = None
self.defects = []
# Default content type
self._default_type = 'text/plain'
@as_native_str(encoding='utf-8')
def __str__(self):
"""Return the entire formatted message as a string.
This includes the headers, body, and envelope header.
"""
return self.as_string()
def as_string(self, unixfrom=False, maxheaderlen=0):
"""Return the entire formatted message as a (unicode) string.
Optional `unixfrom' when True, means include the Unix From_ envelope
header.
This is a convenience method and may not generate the message exactly
as you intend. For more flexibility, use the flatten() method of a
Generator instance.
"""
from future.backports.email.generator import Generator
fp = StringIO()
g = Generator(fp, mangle_from_=False, maxheaderlen=maxheaderlen)
g.flatten(self, unixfrom=unixfrom)
return fp.getvalue()
def is_multipart(self):
"""Return True if the message consists of multiple parts."""
return isinstance(self._payload, list)
#
# Unix From_ line
#
def set_unixfrom(self, unixfrom):
self._unixfrom = unixfrom
def get_unixfrom(self):
return self._unixfrom
#
# Payload manipulation.
#
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, use
set_payload() instead.
"""
if self._payload is None:
self._payload = [payload]
else:
self._payload.append(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):
payload = str(payload) # for Python-Future, so surrogateescape works
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 set_payload(self, payload, charset=None):
"""Set the payload to the given value.
Optional charset sets the message's default character set. See
set_charset() for details.
"""
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 Charset instance, a string naming a character set, or
None. If it is a string it will be converted to a Charset instance.
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 of type text/* 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 not isinstance(charset, Charset):
charset = Charset(charset)
self._charset = charset
if 'MIME-Version' not in self:
self.add_header('MIME-Version', '1.0')
if 'Content-Type' not in self:
self.add_header('Content-Type', 'text/plain',
charset=charset.get_output_charset())
else:
self.set_param('charset', charset.get_output_charset())
if charset != charset.get_output_charset():
self._payload = charset.body_encode(self._payload)
if 'Content-Transfer-Encoding' not in self:
cte = charset.get_body_encoding()
try:
cte(self)
except TypeError:
self._payload = charset.body_encode(self._payload)
self.add_header('Content-Transfer-Encoding', cte)
def get_charset(self):
"""Return the Charset instance 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
occurrence gets returned is undefined. Use get_all() 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.
"""
max_count = self.policy.header_max_count(name)
if max_count:
lname = name.lower()
found = 0
for k, v in self._headers:
if k.lower() == lname:
found += 1
if found >= max_count:
raise ValueError("There may be at most {} {} headers "
"in a message".format(max_count, name))
self._headers.append(self.policy.header_store_parse(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 = list()
for k, v in self._headers:
if k.lower() != name:
newheaders.append((k, v))
self._headers = newheaders
def __contains__(self, name):
return name.lower() in [k.lower() for k, v in self._headers]
def __iter__(self):
for field, value in self._headers:
yield field
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, or were added to the 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, or were added to the message, and may contain duplicates.
Any fields deleted and re-inserted are always appended to the header
list.
"""
return [self.policy.header_fetch_parse(k, 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, or were added to the message, and may contain duplicates.
Any fields deleted and re-inserted are always appended to the header
list.
"""
return [(k, self.policy.header_fetch_parse(k, v))
for k, v in 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 self.policy.header_fetch_parse(k, v)
return failobj
#
# "Internal" methods (public API, but only intended for use by a parser
# or generator, not normal application code.
#
def set_raw(self, name, value):
"""Store name and value in the model without modification.
This is an "internal" API, intended only for use by a parser.
"""
self._headers.append((name, value))
def raw_items(self):
"""Return the (name, value) header pairs without modification.
This is an "internal" API, intended only for use by a generator.
"""
return iter(self._headers.copy())
#
# 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(self.policy.header_fetch_parse(k, 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. If a
parameter value contains non-ASCII characters it can be specified as a
three-tuple of (charset, language, value), in which case it will be
encoded according to RFC2231 rules. Otherwise it will be encoded using
the utf-8 charset and a language of ''.
Examples:
msg.add_header('content-disposition', 'attachment', filename='bud.gif')
msg.add_header('content-disposition', 'attachment',
filename=('utf-8', '', 'Fußballer.ppt'))
msg.add_header('content-disposition', 'attachment',
filename='Fußballer.ppt'))
"""
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[_name] = SEMISPACE.join(parts)
def replace_header(self, _name, _value):
"""Replace a header.
Replace the first matching header found in the message, retaining
header order and case. If no matching header was found, a KeyError is
raised.
"""
_name = _name.lower()
for i, (k, v) in zip(range(len(self._headers)), self._headers):
if k.lower() == _name:
self._headers[i] = self.policy.header_store_parse(k, _value)
break
else:
raise KeyError(_name)
#
# Use these three methods instead of the three above.
#
def get_content_type(self):
"""Return the message's content type.
The returned string is coerced to lower case of the form
`maintype/subtype'. If there was no Content-Type header in the
message, the default type as given by get_default_type() will be
returned. Since according to RFC 2045, messages always have a default
type this will always return a value.
RFC 2045 defines a message's default type to be text/plain unless it
appears inside a multipart/digest container, in which case it would be
message/rfc822.
"""
missing = object()
value = self.get('content-type', missing)
if value is missing:
# This should have no parameters
return self.get_default_type()
ctype = _splitparam(value)[0].lower()
# RFC 2045, section 5.2 says if its invalid, use text/plain
if ctype.count('/') != 1:
return 'text/plain'
return ctype
def get_content_maintype(self):
"""Return the message's main content type.
This is the `maintype' part of the string returned by
get_content_type().
"""
ctype = self.get_content_type()
return ctype.split('/')[0]
def get_content_subtype(self):
"""Returns the message's sub-content type.
This is the `subtype' part of the string returned by
get_content_type().
"""
ctype = self.get_content_type()
return ctype.split('/')[1]
def get_default_type(self):
"""Return the `default' content type.
Most messages have a default content type of text/plain, except for
messages that are subparts of multipart/digest containers. Such
subparts have a default content type of message/rfc822.
"""
return self._default_type
def set_default_type(self, ctype):
"""Set the `default' content type.
ctype should be either "text/plain" or "message/rfc822", although this
is not enforced. The default content type is not stored in the
Content-Type header.
"""
self._default_type = ctype
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 = object()
value = self.get(header, missing)
if value is missing:
return failobj
params = []
for p in _parseparam(value):
try:
name, val = p.split('=', 1)
name = name.strip()
val = val.strip()
except ValueError:
# Must have been a bare attribute
name = p.strip()
val = ''
params.append((name, val))
params = utils.decode_params(params)
return params
def get_params(self, failobj=None, header='content-type', unquote=True):
"""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 as
described in the get_param() method.
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. If unquote is True, the value is unquoted.
"""
missing = object()
params = self._get_params_preserve(missing, header)
if params is missing:
return failobj
if unquote:
return [(k, _unquotevalue(v)) for k, v in params]
else:
return params
def get_param(self, param, failobj=None, header='content-type',
unquote=True):
"""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, or the Content-Type header has no such parameter. Optional
header is the header to search instead of Content-Type.
Parameter keys are always compared case insensitively. The return
value can either be a string, or a 3-tuple if the parameter was RFC
2231 encoded. When it's a 3-tuple, the elements of the value are of
the form (CHARSET, LANGUAGE, VALUE). Note that both CHARSET and
LANGUAGE can be None, in which case you should consider VALUE to be
encoded in the us-ascii charset. You can usually ignore LANGUAGE.
The parameter value (either the returned string, or the VALUE item in
the 3-tuple) is always unquoted, unless unquote is set to False.
If your application doesn't care whether the parameter was RFC 2231
encoded, it can turn the return value into a string as follows:
param = msg.get_param('foo')
param = email.utils.collapse_rfc2231_value(rawparam)
"""
if header not in self:
return failobj
for k, v in self._get_params_preserve(failobj, header):
if k.lower() == param.lower():
if unquote:
return _unquotevalue(v)
else:
return v
return failobj
def set_param(self, param, value, header='Content-Type', requote=True,
charset=None, language=''):
"""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 for 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 necessary unless requote is False.
If charset is specified, the parameter will be encoded according to RFC
2231. Optional language specifies the RFC 2231 language, defaulting
to the empty string. Both charset and language should be strings.
"""
if not isinstance(value, tuple) and charset:
value = (charset, language, value)
if header not in self 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=True):
"""Remove the given parameter completely from the Content-Type header.
The header will be re-written in place without the parameter or its
value. All values will be quoted as necessary unless requote is
False. Optional header specifies an alternative to the Content-Type
header.
"""
if header not in self:
return
new_ctype = ''
for p, v in self.get_params(header=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=True):
"""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 alternative 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 header not in self:
self[header] = type
return
params = self.get_params(header=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. If that header is missing
the `filename' parameter, this method falls back to looking for the
`name' parameter.
"""
missing = object()
filename = self.get_param('filename', missing, 'content-disposition')
if filename is missing:
filename = self.get_param('name', missing, 'content-type')
if filename is missing:
return failobj
return utils.collapse_rfc2231_value(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 = object()
boundary = self.get_param('boundary', missing)
if boundary is missing:
return failobj
# RFC 2046 says that boundaries may begin but not end in w/s
return utils.collapse_rfc2231_value(boundary).rstrip()
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 = object()
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 = False
for pk, pv in params:
if pk.lower() == 'boundary':
newparams.append(('boundary', '"%s"' % boundary))
foundp = True
else:
newparams.append((pk, pv))
if not foundp:
# The original Content-Type header had no boundary attribute.
# Tack one on 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))
val = SEMISPACE.join(parts)
newheaders.append(self.policy.header_store_parse(h, val))
else:
newheaders.append((h, v))
self._headers = newheaders
def get_content_charset(self, failobj=None):
"""Return the charset parameter of the Content-Type header.
The returned string is always coerced to lower case. If there is no
Content-Type header, or if that header has no charset parameter,
failobj is returned.
"""
missing = object()
charset = self.get_param('charset', missing)
if charset is missing:
return failobj
if isinstance(charset, tuple):
# RFC 2231 encoded, so decode it, and it better end up as ascii.
pcharset = charset[0] or 'us-ascii'
try:
# LookupError will be raised if the charset isn't known to
# Python. UnicodeError will be raised if the encoded text
# contains a character not in the charset.
as_bytes = charset[2].encode('raw-unicode-escape')
charset = str(as_bytes, pcharset)
except (LookupError, UnicodeError):
charset = charset[2]
# charset characters must be in us-ascii range
try:
charset.encode('us-ascii')
except UnicodeError:
return failobj
# RFC 2046, $4.1.2 says charsets are not case sensitive
return charset.lower()
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_content_charset(failobj) for part in self.walk()]
# I.e. def walk(self): ...
from future.backports.email.iterators import walk
|