/usr/lib/python3/dist-packages/future/backports/email/header.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 | # Copyright (C) 2002-2007 Python Software Foundation
# Author: Ben Gertzfield, Barry Warsaw
# Contact: email-sig@python.org
"""Header encoding and decoding functionality."""
from __future__ import unicode_literals
from __future__ import division
from __future__ import absolute_import
from future.builtins import bytes, range, str, super, zip
__all__ = [
'Header',
'decode_header',
'make_header',
]
import re
import binascii
from future.backports import email
from future.backports.email import base64mime
from future.backports.email.errors import HeaderParseError
import future.backports.email.charset as _charset
# Helpers
from future.backports.email.quoprimime import _max_append, header_decode
Charset = _charset.Charset
NL = '\n'
SPACE = ' '
BSPACE = b' '
SPACE8 = ' ' * 8
EMPTYSTRING = ''
MAXLINELEN = 78
FWS = ' \t'
USASCII = Charset('us-ascii')
UTF8 = Charset('utf-8')
# Match encoded-word strings in the form =?charset?q?Hello_World?=
ecre = re.compile(r'''
=\? # literal =?
(?P<charset>[^?]*?) # non-greedy up to the next ? is the charset
\? # literal ?
(?P<encoding>[qb]) # either a "q" or a "b", case insensitive
\? # literal ?
(?P<encoded>.*?) # non-greedy up to the next ?= is the encoded string
\?= # literal ?=
''', re.VERBOSE | re.IGNORECASE | re.MULTILINE)
# Field name regexp, including trailing colon, but not separating whitespace,
# according to RFC 2822. Character range is from tilde to exclamation mark.
# For use with .match()
fcre = re.compile(r'[\041-\176]+:$')
# Find a header embedded in a putative header value. Used to check for
# header injection attack.
_embeded_header = re.compile(r'\n[^ \t]+:')
def decode_header(header):
"""Decode a message header value without converting charset.
Returns a list of (string, charset) pairs containing each of the decoded
parts of the header. Charset is None for non-encoded parts of the header,
otherwise a lower-case string containing the name of the character set
specified in the encoded string.
header may be a string that may or may not contain RFC2047 encoded words,
or it may be a Header object.
An email.errors.HeaderParseError may be raised when certain decoding error
occurs (e.g. a base64 decoding exception).
"""
# If it is a Header object, we can just return the encoded chunks.
if hasattr(header, '_chunks'):
return [(_charset._encode(string, str(charset)), str(charset))
for string, charset in header._chunks]
# If no encoding, just return the header with no charset.
if not ecre.search(header):
return [(header, None)]
# First step is to parse all the encoded parts into triplets of the form
# (encoded_string, encoding, charset). For unencoded strings, the last
# two parts will be None.
words = []
for line in header.splitlines():
parts = ecre.split(line)
first = True
while parts:
unencoded = parts.pop(0)
if first:
unencoded = unencoded.lstrip()
first = False
if unencoded:
words.append((unencoded, None, None))
if parts:
charset = parts.pop(0).lower()
encoding = parts.pop(0).lower()
encoded = parts.pop(0)
words.append((encoded, encoding, charset))
# Now loop over words and remove words that consist of whitespace
# between two encoded strings.
import sys
droplist = []
for n, w in enumerate(words):
if n>1 and w[1] and words[n-2][1] and words[n-1][0].isspace():
droplist.append(n-1)
for d in reversed(droplist):
del words[d]
# The next step is to decode each encoded word by applying the reverse
# base64 or quopri transformation. decoded_words is now a list of the
# form (decoded_word, charset).
decoded_words = []
for encoded_string, encoding, charset in words:
if encoding is None:
# This is an unencoded word.
decoded_words.append((encoded_string, charset))
elif encoding == 'q':
word = header_decode(encoded_string)
decoded_words.append((word, charset))
elif encoding == 'b':
paderr = len(encoded_string) % 4 # Postel's law: add missing padding
if paderr:
encoded_string += '==='[:4 - paderr]
try:
word = base64mime.decode(encoded_string)
except binascii.Error:
raise HeaderParseError('Base64 decoding error')
else:
decoded_words.append((word, charset))
else:
raise AssertionError('Unexpected encoding: ' + encoding)
# Now convert all words to bytes and collapse consecutive runs of
# similarly encoded words.
collapsed = []
last_word = last_charset = None
for word, charset in decoded_words:
if isinstance(word, str):
word = bytes(word, 'raw-unicode-escape')
if last_word is None:
last_word = word
last_charset = charset
elif charset != last_charset:
collapsed.append((last_word, last_charset))
last_word = word
last_charset = charset
elif last_charset is None:
last_word += BSPACE + word
else:
last_word += word
collapsed.append((last_word, last_charset))
return collapsed
def make_header(decoded_seq, maxlinelen=None, header_name=None,
continuation_ws=' '):
"""Create a Header from a sequence of pairs as returned by decode_header()
decode_header() takes a header value string and returns a sequence of
pairs of the format (decoded_string, charset) where charset is the string
name of the character set.
This function takes one of those sequence of pairs and returns a Header
instance. Optional maxlinelen, header_name, and continuation_ws are as in
the Header constructor.
"""
h = Header(maxlinelen=maxlinelen, header_name=header_name,
continuation_ws=continuation_ws)
for s, charset in decoded_seq:
# None means us-ascii but we can simply pass it on to h.append()
if charset is not None and not isinstance(charset, Charset):
charset = Charset(charset)
h.append(s, charset)
return h
class Header(object):
def __init__(self, s=None, charset=None,
maxlinelen=None, header_name=None,
continuation_ws=' ', errors='strict'):
"""Create a MIME-compliant header that can contain many character sets.
Optional s is the initial header value. If None, the initial header
value is not set. You can later append to the header with .append()
method calls. s may be a byte string or a Unicode string, but see the
.append() documentation for semantics.
Optional charset serves two purposes: it has the same meaning as the
charset argument to the .append() method. It also sets the default
character set for all subsequent .append() calls that omit the charset
argument. If charset is not provided in the constructor, the us-ascii
charset is used both as s's initial charset and as the default for
subsequent .append() calls.
The maximum line length can be specified explicitly via maxlinelen. For
splitting the first line to a shorter value (to account for the field
header which isn't included in s, e.g. `Subject') pass in the name of
the field in header_name. The default maxlinelen is 78 as recommended
by RFC 2822.
continuation_ws must be RFC 2822 compliant folding whitespace (usually
either a space or a hard tab) which will be prepended to continuation
lines.
errors is passed through to the .append() call.
"""
if charset is None:
charset = USASCII
elif not isinstance(charset, Charset):
charset = Charset(charset)
self._charset = charset
self._continuation_ws = continuation_ws
self._chunks = []
if s is not None:
self.append(s, charset, errors)
if maxlinelen is None:
maxlinelen = MAXLINELEN
self._maxlinelen = maxlinelen
if header_name is None:
self._headerlen = 0
else:
# Take the separating colon and space into account.
self._headerlen = len(header_name) + 2
def __str__(self):
"""Return the string value of the header."""
self._normalize()
uchunks = []
lastcs = None
lastspace = None
for string, charset in self._chunks:
# We must preserve spaces between encoded and non-encoded word
# boundaries, which means for us we need to add a space when we go
# from a charset to None/us-ascii, or from None/us-ascii to a
# charset. Only do this for the second and subsequent chunks.
# Don't add a space if the None/us-ascii string already has
# a space (trailing or leading depending on transition)
nextcs = charset
if nextcs == _charset.UNKNOWN8BIT:
original_bytes = string.encode('ascii', 'surrogateescape')
string = original_bytes.decode('ascii', 'replace')
if uchunks:
hasspace = string and self._nonctext(string[0])
if lastcs not in (None, 'us-ascii'):
if nextcs in (None, 'us-ascii') and not hasspace:
uchunks.append(SPACE)
nextcs = None
elif nextcs not in (None, 'us-ascii') and not lastspace:
uchunks.append(SPACE)
lastspace = string and self._nonctext(string[-1])
lastcs = nextcs
uchunks.append(string)
return EMPTYSTRING.join(uchunks)
# Rich comparison operators for equality only. BAW: does it make sense to
# have or explicitly disable <, <=, >, >= operators?
def __eq__(self, other):
# other may be a Header or a string. Both are fine so coerce
# ourselves to a unicode (of the unencoded header value), swap the
# args and do another comparison.
return other == str(self)
def __ne__(self, other):
return not self == other
def append(self, s, charset=None, errors='strict'):
"""Append a string to the MIME header.
Optional charset, if given, should be a Charset instance or the name
of a character set (which will be converted to a Charset instance). A
value of None (the default) means that the charset given in the
constructor is used.
s may be a byte string or a Unicode string. If it is a byte string
(i.e. isinstance(s, str) is false), then charset is the encoding of
that byte string, and a UnicodeError will be raised if the string
cannot be decoded with that charset. If s is a Unicode string, then
charset is a hint specifying the character set of the characters in
the string. In either case, when producing an RFC 2822 compliant
header using RFC 2047 rules, the string will be encoded using the
output codec of the charset. If the string cannot be encoded to the
output codec, a UnicodeError will be raised.
Optional `errors' is passed as the errors argument to the decode
call if s is a byte string.
"""
if charset is None:
charset = self._charset
elif not isinstance(charset, Charset):
charset = Charset(charset)
if not isinstance(s, str):
input_charset = charset.input_codec or 'us-ascii'
if input_charset == _charset.UNKNOWN8BIT:
s = s.decode('us-ascii', 'surrogateescape')
else:
s = s.decode(input_charset, errors)
# Ensure that the bytes we're storing can be decoded to the output
# character set, otherwise an early error is raised.
output_charset = charset.output_codec or 'us-ascii'
if output_charset != _charset.UNKNOWN8BIT:
try:
s.encode(output_charset, errors)
except UnicodeEncodeError:
if output_charset!='us-ascii':
raise
charset = UTF8
self._chunks.append((s, charset))
def _nonctext(self, s):
"""True if string s is not a ctext character of RFC822.
"""
return s.isspace() or s in ('(', ')', '\\')
def encode(self, splitchars=';, \t', maxlinelen=None, linesep='\n'):
r"""Encode a message header into an RFC-compliant format.
There are many issues involved in converting a given string for use in
an email header. Only certain character sets are readable in most
email clients, and as header strings can only contain a subset of
7-bit ASCII, care must be taken to properly convert and encode (with
Base64 or quoted-printable) header strings. In addition, there is a
75-character length limit on any given encoded header field, so
line-wrapping must be performed, even with double-byte character sets.
Optional maxlinelen specifies the maximum length of each generated
line, exclusive of the linesep string. Individual lines may be longer
than maxlinelen if a folding point cannot be found. The first line
will be shorter by the length of the header name plus ": " if a header
name was specified at Header construction time. The default value for
maxlinelen is determined at header construction time.
Optional splitchars is a string containing characters which should be
given extra weight by the splitting algorithm during normal header
wrapping. This is in very rough support of RFC 2822's `higher level
syntactic breaks': split points preceded by a splitchar are preferred
during line splitting, with the characters preferred in the order in
which they appear in the string. Space and tab may be included in the
string to indicate whether preference should be given to one over the
other as a split point when other split chars do not appear in the line
being split. Splitchars does not affect RFC 2047 encoded lines.
Optional linesep is a string to be used to separate the lines of
the value. 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.
"""
self._normalize()
if maxlinelen is None:
maxlinelen = self._maxlinelen
# A maxlinelen of 0 means don't wrap. For all practical purposes,
# choosing a huge number here accomplishes that and makes the
# _ValueFormatter algorithm much simpler.
if maxlinelen == 0:
maxlinelen = 1000000
formatter = _ValueFormatter(self._headerlen, maxlinelen,
self._continuation_ws, splitchars)
lastcs = None
hasspace = lastspace = None
for string, charset in self._chunks:
if hasspace is not None:
hasspace = string and self._nonctext(string[0])
import sys
if lastcs not in (None, 'us-ascii'):
if not hasspace or charset not in (None, 'us-ascii'):
formatter.add_transition()
elif charset not in (None, 'us-ascii') and not lastspace:
formatter.add_transition()
lastspace = string and self._nonctext(string[-1])
lastcs = charset
hasspace = False
lines = string.splitlines()
if lines:
formatter.feed('', lines[0], charset)
else:
formatter.feed('', '', charset)
for line in lines[1:]:
formatter.newline()
if charset.header_encoding is not None:
formatter.feed(self._continuation_ws, ' ' + line.lstrip(),
charset)
else:
sline = line.lstrip()
fws = line[:len(line)-len(sline)]
formatter.feed(fws, sline, charset)
if len(lines) > 1:
formatter.newline()
if self._chunks:
formatter.add_transition()
value = formatter._str(linesep)
if _embeded_header.search(value):
raise HeaderParseError("header value appears to contain "
"an embedded header: {!r}".format(value))
return value
def _normalize(self):
# Step 1: Normalize the chunks so that all runs of identical charsets
# get collapsed into a single unicode string.
chunks = []
last_charset = None
last_chunk = []
for string, charset in self._chunks:
if charset == last_charset:
last_chunk.append(string)
else:
if last_charset is not None:
chunks.append((SPACE.join(last_chunk), last_charset))
last_chunk = [string]
last_charset = charset
if last_chunk:
chunks.append((SPACE.join(last_chunk), last_charset))
self._chunks = chunks
class _ValueFormatter(object):
def __init__(self, headerlen, maxlen, continuation_ws, splitchars):
self._maxlen = maxlen
self._continuation_ws = continuation_ws
self._continuation_ws_len = len(continuation_ws)
self._splitchars = splitchars
self._lines = []
self._current_line = _Accumulator(headerlen)
def _str(self, linesep):
self.newline()
return linesep.join(self._lines)
def __str__(self):
return self._str(NL)
def newline(self):
end_of_line = self._current_line.pop()
if end_of_line != (' ', ''):
self._current_line.push(*end_of_line)
if len(self._current_line) > 0:
if self._current_line.is_onlyws():
self._lines[-1] += str(self._current_line)
else:
self._lines.append(str(self._current_line))
self._current_line.reset()
def add_transition(self):
self._current_line.push(' ', '')
def feed(self, fws, string, charset):
# If the charset has no header encoding (i.e. it is an ASCII encoding)
# then we must split the header at the "highest level syntactic break"
# possible. Note that we don't have a lot of smarts about field
# syntax; we just try to break on semi-colons, then commas, then
# whitespace. Eventually, this should be pluggable.
if charset.header_encoding is None:
self._ascii_split(fws, string, self._splitchars)
return
# Otherwise, we're doing either a Base64 or a quoted-printable
# encoding which means we don't need to split the line on syntactic
# breaks. We can basically just find enough characters to fit on the
# current line, minus the RFC 2047 chrome. What makes this trickier
# though is that we have to split at octet boundaries, not character
# boundaries but it's only safe to split at character boundaries so at
# best we can only get close.
encoded_lines = charset.header_encode_lines(string, self._maxlengths())
# The first element extends the current line, but if it's None then
# nothing more fit on the current line so start a new line.
try:
first_line = encoded_lines.pop(0)
except IndexError:
# There are no encoded lines, so we're done.
return
if first_line is not None:
self._append_chunk(fws, first_line)
try:
last_line = encoded_lines.pop()
except IndexError:
# There was only one line.
return
self.newline()
self._current_line.push(self._continuation_ws, last_line)
# Everything else are full lines in themselves.
for line in encoded_lines:
self._lines.append(self._continuation_ws + line)
def _maxlengths(self):
# The first line's length.
yield self._maxlen - len(self._current_line)
while True:
yield self._maxlen - self._continuation_ws_len
def _ascii_split(self, fws, string, splitchars):
# The RFC 2822 header folding algorithm is simple in principle but
# complex in practice. Lines may be folded any place where "folding
# white space" appears by inserting a linesep character in front of the
# FWS. The complication is that not all spaces or tabs qualify as FWS,
# and we are also supposed to prefer to break at "higher level
# syntactic breaks". We can't do either of these without intimate
# knowledge of the structure of structured headers, which we don't have
# here. So the best we can do here is prefer to break at the specified
# splitchars, and hope that we don't choose any spaces or tabs that
# aren't legal FWS. (This is at least better than the old algorithm,
# where we would sometimes *introduce* FWS after a splitchar, or the
# algorithm before that, where we would turn all white space runs into
# single spaces or tabs.)
parts = re.split("(["+FWS+"]+)", fws+string)
if parts[0]:
parts[:0] = ['']
else:
parts.pop(0)
for fws, part in zip(*[iter(parts)]*2):
self._append_chunk(fws, part)
def _append_chunk(self, fws, string):
self._current_line.push(fws, string)
if len(self._current_line) > self._maxlen:
# Find the best split point, working backward from the end.
# There might be none, on a long first line.
for ch in self._splitchars:
for i in range(self._current_line.part_count()-1, 0, -1):
if ch.isspace():
fws = self._current_line[i][0]
if fws and fws[0]==ch:
break
prevpart = self._current_line[i-1][1]
if prevpart and prevpart[-1]==ch:
break
else:
continue
break
else:
fws, part = self._current_line.pop()
if self._current_line._initial_size > 0:
# There will be a header, so leave it on a line by itself.
self.newline()
if not fws:
# We don't use continuation_ws here because the whitespace
# after a header should always be a space.
fws = ' '
self._current_line.push(fws, part)
return
remainder = self._current_line.pop_from(i)
self._lines.append(str(self._current_line))
self._current_line.reset(remainder)
class _Accumulator(list):
def __init__(self, initial_size=0):
self._initial_size = initial_size
super().__init__()
def push(self, fws, string):
self.append((fws, string))
def pop_from(self, i=0):
popped = self[i:]
self[i:] = []
return popped
def pop(self):
if self.part_count()==0:
return ('', '')
return super().pop()
def __len__(self):
return sum((len(fws)+len(part) for fws, part in self),
self._initial_size)
def __str__(self):
return EMPTYSTRING.join((EMPTYSTRING.join((fws, part))
for fws, part in self))
def reset(self, startval=None):
if startval is None:
startval = []
self[:] = startval
self._initial_size = 0
def is_onlyws(self):
return self._initial_size==0 and (not self or str(self).isspace())
def part_count(self):
return super().__len__()
|